From 5550201c0fe26a76c53983bd36a58d4c4395ec22 Mon Sep 17 00:00:00 2001 From: Chris Lew Date: Fri, 7 Jul 2023 03:11:38 +0530 Subject: rpmsg: char: Add RPMSG GET/SET FLOWCONTROL IOCTL support Add RPMSG_GET_OUTGOING_FLOWCONTROL and RPMSG_SET_INCOMING_FLOWCONTROL IOCTL support for rpmsg char device nodes to get/set the low level transport signals. Signed-off-by: Chris Lew Signed-off-by: Deepak Kumar Singh Signed-off-by: Sarannya S Acked-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/1688679698-31274-4-git-send-email-quic_sarannya@quicinc.com Signed-off-by: Bjorn Andersson --- include/uapi/linux/rpmsg.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rpmsg.h b/include/uapi/linux/rpmsg.h index 1637e68177d9..f0c8da2b185b 100644 --- a/include/uapi/linux/rpmsg.h +++ b/include/uapi/linux/rpmsg.h @@ -43,4 +43,14 @@ struct rpmsg_endpoint_info { */ #define RPMSG_RELEASE_DEV_IOCTL _IOW(0xb5, 0x4, struct rpmsg_endpoint_info) +/** + * Get the flow control state of the remote rpmsg char device. + */ +#define RPMSG_GET_OUTGOING_FLOWCONTROL _IOR(0xb5, 0x5, int) + +/** + * Set the flow control state of the local rpmsg char device. + */ +#define RPMSG_SET_INCOMING_FLOWCONTROL _IOR(0xb5, 0x6, int) + #endif -- cgit From e78662e818f9478e70912cc2970ca632ec9f3635 Mon Sep 17 00:00:00 2001 From: Hao Xu Date: Tue, 1 Aug 2023 16:06:46 +0800 Subject: fuse: add a new fuse init flag to relax restrictions in no cache mode FOPEN_DIRECT_IO is usually set by fuse daemon to indicate need of strong coherency, e.g. network filesystems. Thus shared mmap is disabled since it leverages page cache and may write to it, which may cause inconsistence. But FOPEN_DIRECT_IO can be used not for coherency but to reduce memory footprint as well, e.g. reduce guest memory usage with virtiofs. Therefore, add a new fuse init flag FUSE_DIRECT_IO_RELAX to relax restrictions in that mode, currently, it allows shared mmap. One thing to note is to make sure it doesn't break coherency in your use case. Signed-off-by: Hao Xu Signed-off-by: Miklos Szeredi --- fs/fuse/file.c | 7 +++++-- fs/fuse/fuse_i.h | 3 +++ fs/fuse/inode.c | 4 +++- include/uapi/linux/fuse.h | 8 +++++++- 4 files changed, 18 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 1aa7dde665aa..e6034ce698e9 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2451,14 +2451,17 @@ static const struct vm_operations_struct fuse_file_vm_ops = { static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) { struct fuse_file *ff = file->private_data; + struct fuse_conn *fc = ff->fm->fc; /* DAX mmap is superior to direct_io mmap */ if (FUSE_IS_DAX(file_inode(file))) return fuse_dax_mmap(file, vma); if (ff->open_flags & FOPEN_DIRECT_IO) { - /* Can't provide the coherency needed for MAP_SHARED */ - if (vma->vm_flags & VM_MAYSHARE) + /* Can't provide the coherency needed for MAP_SHARED + * if FUSE_DIRECT_IO_RELAX isn't set. + */ + if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_relax) return -ENODEV; invalidate_inode_pages2(file->f_mapping); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 9b7fc7d3c7f1..d830c2360aef 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -792,6 +792,9 @@ struct fuse_conn { /* Is tmpfile not implemented by fs? */ unsigned int no_tmpfile:1; + /* relax restrictions in FOPEN_DIRECT_IO mode */ + unsigned int direct_io_relax:1; + /** The number of requests waiting for completion */ atomic_t num_waiting; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index f19d748890f0..4a16185eacae 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1212,6 +1212,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, fc->init_security = 1; if (flags & FUSE_CREATE_SUPP_GROUP) fc->create_supp_group = 1; + if (flags & FUSE_DIRECT_IO_RELAX) + fc->direct_io_relax = 1; } else { ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; @@ -1258,7 +1260,7 @@ void fuse_send_init(struct fuse_mount *fm) FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA | FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT | FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP | - FUSE_HAS_EXPIRE_ONLY; + FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_RELAX; #ifdef CONFIG_FUSE_DAX if (fm->fc->dax) flags |= FUSE_MAP_ALIGNMENT; diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index b3fcab13fcd3..c2da9503b04e 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -207,6 +207,9 @@ * - add FUSE_EXT_GROUPS * - add FUSE_CREATE_SUPP_GROUP * - add FUSE_HAS_EXPIRE_ONLY + * + * 7.39 + * - add FUSE_DIRECT_IO_RELAX */ #ifndef _LINUX_FUSE_H @@ -242,7 +245,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 38 +#define FUSE_KERNEL_MINOR_VERSION 39 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -371,6 +374,8 @@ struct fuse_file_lock { * FUSE_CREATE_SUPP_GROUP: add supplementary group info to create, mkdir, * symlink and mknod (single group that matches parent) * FUSE_HAS_EXPIRE_ONLY: kernel supports expiry-only entry invalidation + * FUSE_DIRECT_IO_RELAX: relax restrictions in FOPEN_DIRECT_IO mode, for now + * allow shared mmap */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -409,6 +414,7 @@ struct fuse_file_lock { #define FUSE_HAS_INODE_DAX (1ULL << 33) #define FUSE_CREATE_SUPP_GROUP (1ULL << 34) #define FUSE_HAS_EXPIRE_ONLY (1ULL << 35) +#define FUSE_DIRECT_IO_RELAX (1ULL << 36) /** * CUSE INIT request/reply flags -- cgit From ba58a37c2847f21494a04240fb48955cbd5d1aca Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 10 Aug 2023 12:45:05 +0200 Subject: fuse: add STATX request Use the same structure as statx. Signed-off-by: Miklos Szeredi --- include/uapi/linux/fuse.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index c2da9503b04e..db92a7202b34 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -210,6 +210,7 @@ * * 7.39 * - add FUSE_DIRECT_IO_RELAX + * - add FUSE_STATX and related structures */ #ifndef _LINUX_FUSE_H @@ -272,6 +273,40 @@ struct fuse_attr { uint32_t flags; }; +/* + * The following structures are bit-for-bit compatible with the statx(2) ABI in + * Linux. + */ +struct fuse_sx_time { + int64_t tv_sec; + uint32_t tv_nsec; + int32_t __reserved; +}; + +struct fuse_statx { + uint32_t mask; + uint32_t blksize; + uint64_t attributes; + uint32_t nlink; + uint32_t uid; + uint32_t gid; + uint16_t mode; + uint16_t __spare0[1]; + uint64_t ino; + uint64_t size; + uint64_t blocks; + uint64_t attributes_mask; + struct fuse_sx_time atime; + struct fuse_sx_time btime; + struct fuse_sx_time ctime; + struct fuse_sx_time mtime; + uint32_t rdev_major; + uint32_t rdev_minor; + uint32_t dev_major; + uint32_t dev_minor; + uint64_t __spare2[14]; +}; + struct fuse_kstatfs { uint64_t blocks; uint64_t bfree; @@ -581,6 +616,7 @@ enum fuse_opcode { FUSE_REMOVEMAPPING = 49, FUSE_SYNCFS = 50, FUSE_TMPFILE = 51, + FUSE_STATX = 52, /* CUSE specific operations */ CUSE_INIT = 4096, @@ -645,6 +681,22 @@ struct fuse_attr_out { struct fuse_attr attr; }; +struct fuse_statx_in { + uint32_t getattr_flags; + uint32_t reserved; + uint64_t fh; + uint32_t sx_flags; + uint32_t sx_mask; +}; + +struct fuse_statx_out { + uint64_t attr_valid; /* Cache timeout for the attributes */ + uint32_t attr_valid_nsec; + uint32_t flags; + uint64_t spare[2]; + struct fuse_statx stat; +}; + #define FUSE_COMPAT_MKNOD_IN_SIZE 8 struct fuse_mknod_in { -- cgit From 9300f00439743c4a34d735e1a27118eb68a1504e Mon Sep 17 00:00:00 2001 From: Andy Chiu Date: Fri, 25 Aug 2023 05:02:46 +0000 Subject: RISC-V: Add ptrace support for vectors This patch add back the ptrace support with the following fix: - Define NT_RISCV_CSR and re-number NT_RISCV_VECTOR to prevent conflicting with gdb's NT_RISCV_CSR. - Use struct __riscv_v_regset_state to handle ptrace requests Since gdb does not directly include the note description header in Linux and has already defined NT_RISCV_CSR as 0x900, we decide to sync with gdb and renumber NT_RISCV_VECTOR to solve and prevent future conflicts. Fixes: 0c59922c769a ("riscv: Add ptrace vector support") Signed-off-by: Andy Chiu Link: https://lore.kernel.org/r/20230825050248.32681-1-andy.chiu@sifive.com [Palmer: Drop the unused "size" variable in riscv_vr_set().] Signed-off-by: Palmer Dabbelt --- arch/riscv/include/uapi/asm/ptrace.h | 13 ++++-- arch/riscv/kernel/ptrace.c | 79 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/elf.h | 2 + 3 files changed, 90 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h index 283800130614..575e95bb1bc3 100644 --- a/arch/riscv/include/uapi/asm/ptrace.h +++ b/arch/riscv/include/uapi/asm/ptrace.h @@ -103,13 +103,18 @@ struct __riscv_v_ext_state { * In signal handler, datap will be set a correct user stack offset * and vector registers will be copied to the address of datap * pointer. - * - * In ptrace syscall, datap will be set to zero and the vector - * registers will be copied to the address right after this - * structure. */ }; +struct __riscv_v_regset_state { + unsigned long vstart; + unsigned long vl; + unsigned long vtype; + unsigned long vcsr; + unsigned long vlenb; + char vreg[]; +}; + /* * According to spec: The number of bits in a single vector register, * VLEN >= ELEN, which must be a power of 2, and must be no greater than diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 487303e3ef22..2afe460de16a 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -25,6 +25,9 @@ enum riscv_regset { #ifdef CONFIG_FPU REGSET_F, #endif +#ifdef CONFIG_RISCV_ISA_V + REGSET_V, +#endif }; static int riscv_gpr_get(struct task_struct *target, @@ -81,6 +84,71 @@ static int riscv_fpr_set(struct task_struct *target, } #endif +#ifdef CONFIG_RISCV_ISA_V +static int riscv_vr_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct __riscv_v_ext_state *vstate = &target->thread.vstate; + struct __riscv_v_regset_state ptrace_vstate; + + if (!riscv_v_vstate_query(task_pt_regs(target))) + return -EINVAL; + + /* + * Ensure the vector registers have been saved to the memory before + * copying them to membuf. + */ + if (target == current) + riscv_v_vstate_save(current, task_pt_regs(current)); + + ptrace_vstate.vstart = vstate->vstart; + ptrace_vstate.vl = vstate->vl; + ptrace_vstate.vtype = vstate->vtype; + ptrace_vstate.vcsr = vstate->vcsr; + ptrace_vstate.vlenb = vstate->vlenb; + + /* Copy vector header from vstate. */ + membuf_write(&to, &ptrace_vstate, sizeof(struct __riscv_v_regset_state)); + + /* Copy all the vector registers from vstate. */ + return membuf_write(&to, vstate->datap, riscv_v_vsize); +} + +static int riscv_vr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + struct __riscv_v_ext_state *vstate = &target->thread.vstate; + struct __riscv_v_regset_state ptrace_vstate; + + if (!riscv_v_vstate_query(task_pt_regs(target))) + return -EINVAL; + + /* Copy rest of the vstate except datap */ + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ptrace_vstate, 0, + sizeof(struct __riscv_v_regset_state)); + if (unlikely(ret)) + return ret; + + if (vstate->vlenb != ptrace_vstate.vlenb) + return -EINVAL; + + vstate->vstart = ptrace_vstate.vstart; + vstate->vl = ptrace_vstate.vl; + vstate->vtype = ptrace_vstate.vtype; + vstate->vcsr = ptrace_vstate.vcsr; + + /* Copy all the vector registers. */ + pos = 0; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vstate->datap, + 0, riscv_v_vsize); + return ret; +} +#endif + static const struct user_regset riscv_user_regset[] = { [REGSET_X] = { .core_note_type = NT_PRSTATUS, @@ -100,6 +168,17 @@ static const struct user_regset riscv_user_regset[] = { .set = riscv_fpr_set, }, #endif +#ifdef CONFIG_RISCV_ISA_V + [REGSET_V] = { + .core_note_type = NT_RISCV_VECTOR, + .align = 16, + .n = ((32 * RISCV_MAX_VLENB) + + sizeof(struct __riscv_v_regset_state)) / sizeof(__u32), + .size = sizeof(__u32), + .regset_get = riscv_vr_get, + .set = riscv_vr_set, + }, +#endif }; static const struct user_regset_view riscv_user_native_view = { diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index e0e159138331..20e285fdbc46 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -443,6 +443,8 @@ typedef struct elf64_shdr { #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ #define NT_MIPS_FP_MODE 0x801 /* MIPS floating-point mode */ #define NT_MIPS_MSA 0x802 /* MIPS SIMD registers */ +#define NT_RISCV_CSR 0x900 /* RISC-V Control and Status Registers */ +#define NT_RISCV_VECTOR 0x901 /* RISC-V vector registers */ #define NT_LOONGARCH_CPUCFG 0xa00 /* LoongArch CPU config registers */ #define NT_LOONGARCH_CSR 0xa01 /* LoongArch control and status registers */ #define NT_LOONGARCH_LSX 0xa02 /* LoongArch Loongson SIMD Extension registers */ -- cgit From fdc04cc2d5fd0bb9c17f36d0a895cf3e151109e6 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Fri, 1 Sep 2023 14:15:16 +0200 Subject: netfilter: nf_tables: uapi: Describe NFTA_RULE_CHAIN_ID Add a brief description to the enum's comment. Fixes: 837830a4b439 ("netfilter: nf_tables: add NFTA_RULE_CHAIN_ID attribute") Signed-off-by: Phil Sutter Signed-off-by: Florian Westphal --- include/uapi/linux/netfilter/nf_tables.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 8466c2a9938f..ca30232b7bc8 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -263,6 +263,7 @@ enum nft_chain_attributes { * @NFTA_RULE_USERDATA: user data (NLA_BINARY, NFT_USERDATA_MAXLEN) * @NFTA_RULE_ID: uniquely identifies a rule in a transaction (NLA_U32) * @NFTA_RULE_POSITION_ID: transaction unique identifier of the previous rule (NLA_U32) + * @NFTA_RULE_CHAIN_ID: add the rule to chain by ID, alternative to @NFTA_RULE_CHAIN (NLA_U32) */ enum nft_rule_attributes { NFTA_RULE_UNSPEC, -- cgit From 9bc95a95abbe91e9315c1fe27dc124019bd2592c Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sun, 27 Aug 2023 08:28:37 -0700 Subject: bpf: Mark BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE deprecated Now 'BPF_MAP_TYPE_CGRP_STORAGE + local percpu ptr' can cover all BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE functionality and more. So mark BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE deprecated. Also make changes in selftests/bpf/test_bpftool_synctypes.py and selftest libbpf_str to fix otherwise test errors. Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20230827152837.2003563-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 9 ++++++++- tools/include/uapi/linux/bpf.h | 9 ++++++++- tools/testing/selftests/bpf/prog_tests/libbpf_str.c | 6 +++++- tools/testing/selftests/bpf/test_bpftool_synctypes.py | 9 +++++++++ 4 files changed, 30 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 8790b3962e4b..73b155e52204 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -932,7 +932,14 @@ enum bpf_map_type { */ BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, - BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED, + /* BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE is available to bpf programs + * attaching to a cgroup. The new mechanism (BPF_MAP_TYPE_CGRP_STORAGE + + * local percpu kptr) supports all BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE + * functionality and more. So mark * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE + * deprecated. + */ + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED, BPF_MAP_TYPE_QUEUE, BPF_MAP_TYPE_STACK, BPF_MAP_TYPE_SK_STORAGE, diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 8790b3962e4b..73b155e52204 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -932,7 +932,14 @@ enum bpf_map_type { */ BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, - BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED, + /* BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE is available to bpf programs + * attaching to a cgroup. The new mechanism (BPF_MAP_TYPE_CGRP_STORAGE + + * local percpu kptr) supports all BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE + * functionality and more. So mark * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE + * deprecated. + */ + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED, BPF_MAP_TYPE_QUEUE, BPF_MAP_TYPE_STACK, BPF_MAP_TYPE_SK_STORAGE, diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c index efb8bd43653c..c440ea3311ed 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c @@ -142,10 +142,14 @@ static void test_libbpf_bpf_map_type_str(void) /* Special case for map_type_name BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED * where it and BPF_MAP_TYPE_CGROUP_STORAGE have the same enum value * (map_type). For this enum value, libbpf_bpf_map_type_str() picks - * BPF_MAP_TYPE_CGROUP_STORAGE. + * BPF_MAP_TYPE_CGROUP_STORAGE. The same for + * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED and + * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE. */ if (strcmp(map_type_name, "BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED") == 0) continue; + if (strcmp(map_type_name, "BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED") == 0) + continue; ASSERT_STREQ(buf, map_type_name, "exp_str_value"); } diff --git a/tools/testing/selftests/bpf/test_bpftool_synctypes.py b/tools/testing/selftests/bpf/test_bpftool_synctypes.py index 0cfece7ff4f8..0ed67b6b31dd 100755 --- a/tools/testing/selftests/bpf/test_bpftool_synctypes.py +++ b/tools/testing/selftests/bpf/test_bpftool_synctypes.py @@ -509,6 +509,15 @@ def main(): source_map_types.remove('cgroup_storage_deprecated') source_map_types.add('cgroup_storage') + # The same applied to BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED and + # BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE which share the same enum value + # and source_map_types picks + # BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED/percpu_cgroup_storage_deprecated. + # Replace 'percpu_cgroup_storage_deprecated' with 'percpu_cgroup_storage' + # so it aligns with what `bpftool map help` shows. + source_map_types.remove('percpu_cgroup_storage_deprecated') + source_map_types.add('percpu_cgroup_storage') + help_map_types = map_info.get_map_help() help_map_options = map_info.get_options() map_info.close() -- cgit From 7cb779a6867fea00b4209bcf6de2f178a743247d Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 11 Sep 2023 12:47:30 -0700 Subject: bpf: Clarify error expectations from bpf_clone_redirect Commit 151e887d8ff9 ("veth: Fixing transmit return status for dropped packets") exposed the fact that bpf_clone_redirect is capable of returning raw NET_XMIT_XXX return codes. This is in the conflict with its UAPI doc which says the following: "0 on success, or a negative error in case of failure." Update the UAPI to reflect the fact that bpf_clone_redirect can return positive error numbers, but don't explicitly define their meaning. Reported-by: Daniel Borkmann Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20230911194731.286342-1-sdf@google.com --- include/uapi/linux/bpf.h | 4 +++- tools/include/uapi/linux/bpf.h | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 8790b3962e4b..0448700890f7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1962,7 +1962,9 @@ union bpf_attr { * performed again, if the helper is used in combination with * direct packet access. * Return - * 0 on success, or a negative error in case of failure. + * 0 on success, or a negative error in case of failure. Positive + * error indicates a potential drop or congestion in the target + * device. The particular positive error codes are not defined. * * u64 bpf_get_current_pid_tgid(void) * Description diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 8790b3962e4b..0448700890f7 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1962,7 +1962,9 @@ union bpf_attr { * performed again, if the helper is used in combination with * direct packet access. * Return - * 0 on success, or a negative error in case of failure. + * 0 on success, or a negative error in case of failure. Positive + * error indicates a potential drop or congestion in the target + * device. The particular positive error codes are not defined. * * u64 bpf_get_current_pid_tgid(void) * Description -- cgit From 744f4990ee0519ebef21fa7db094240bbaf3d746 Mon Sep 17 00:00:00 2001 From: Ramona Bolboaca Date: Tue, 8 Aug 2023 10:50:57 +0300 Subject: iio: Add IIO_DELTA_ANGL channel type The delta angle is defined as a piece-wise integration of angular velocity data. The delta angle represents the amount of angular displacement between two consecutive measurements and it is measured in radians. In order to track the total angular displacement during a desired period of time, simply sum-up the delta angle samples acquired during that time. IIO currently does not offer a suitable channel type for this type of measurements hence this patch adds it. Signed-off-by: Ramona Bolboaca Reviewed-by: Nuno Sa Link: https://lore.kernel.org/r/20230808075059.645525-2-ramona.bolboaca@analog.com Signed-off-by: Jonathan Cameron --- Documentation/ABI/testing/sysfs-bus-iio | 22 ++++++++++++++++++++++ drivers/iio/industrialio-core.c | 1 + include/uapi/linux/iio/types.h | 1 + tools/iio/iio_event_monitor.c | 2 ++ 4 files changed, 26 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index a2854dc9a839..363dd4b09930 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -279,6 +279,20 @@ Description: but should match other such assignments on device). Units after application of scale and offset are m/s^2. +What: /sys/bus/iio/devices/iio:deviceX/in_deltaangl_x_raw +What: /sys/bus/iio/devices/iio:deviceX/in_deltaangl_y_raw +What: /sys/bus/iio/devices/iio:deviceX/in_deltaangl_z_raw +KernelVersion: 6.5 +Contact: linux-iio@vger.kernel.org +Description: + Angular displacement between two consecutive samples on x, y or + z (may be arbitrarily assigned but should match other such + assignments on device). + In order to compute the total angular displacement during a + desired period of time, the application should sum-up the delta + angle samples acquired during that time. + Units after application of scale and offset are radians. + What: /sys/bus/iio/devices/iio:deviceX/in_angl_raw What: /sys/bus/iio/devices/iio:deviceX/in_anglY_raw KernelVersion: 4.17 @@ -461,6 +475,7 @@ What: /sys/bus/iio/devices/iio:deviceX/in_humidityrelative_scale What: /sys/bus/iio/devices/iio:deviceX/in_velocity_sqrt(x^2+y^2+z^2)_scale What: /sys/bus/iio/devices/iio:deviceX/in_illuminance_scale What: /sys/bus/iio/devices/iio:deviceX/in_countY_scale +What: /sys/bus/iio/devices/iio:deviceX/in_deltaangl_scale What: /sys/bus/iio/devices/iio:deviceX/in_angl_scale What: /sys/bus/iio/devices/iio:deviceX/in_intensity_x_scale What: /sys/bus/iio/devices/iio:deviceX/in_intensity_y_scale @@ -1332,6 +1347,9 @@ Description: What: /sys/.../iio:deviceX/bufferY/in_accel_x_en What: /sys/.../iio:deviceX/bufferY/in_accel_y_en What: /sys/.../iio:deviceX/bufferY/in_accel_z_en +What: /sys/.../iio:deviceX/bufferY/in_deltaangl_x_en +What: /sys/.../iio:deviceX/bufferY/in_deltaangl_y_en +What: /sys/.../iio:deviceX/bufferY/in_deltaangl_z_en What: /sys/.../iio:deviceX/bufferY/in_anglvel_x_en What: /sys/.../iio:deviceX/bufferY/in_anglvel_y_en What: /sys/.../iio:deviceX/bufferY/in_anglvel_z_en @@ -1362,6 +1380,7 @@ Description: Scan element control for triggered data capture. What: /sys/.../iio:deviceX/bufferY/in_accel_type +What: /sys/.../iio:deviceX/bufferY/in_deltaangl_type What: /sys/.../iio:deviceX/bufferY/in_anglvel_type What: /sys/.../iio:deviceX/bufferY/in_magn_type What: /sys/.../iio:deviceX/bufferY/in_incli_type @@ -1416,6 +1435,9 @@ What: /sys/.../iio:deviceX/bufferY/in_voltage_q_index What: /sys/.../iio:deviceX/bufferY/in_accel_x_index What: /sys/.../iio:deviceX/bufferY/in_accel_y_index What: /sys/.../iio:deviceX/bufferY/in_accel_z_index +What: /sys/.../iio:deviceX/bufferY/in_deltaangl_x_index +What: /sys/.../iio:deviceX/bufferY/in_deltaangl_y_index +What: /sys/.../iio:deviceX/bufferY/in_deltaangl_z_index What: /sys/.../iio:deviceX/bufferY/in_anglvel_x_index What: /sys/.../iio:deviceX/bufferY/in_anglvel_y_index What: /sys/.../iio:deviceX/bufferY/in_anglvel_z_index diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index d752e9c0499b..11a65030186d 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -90,6 +90,7 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_POSITIONRELATIVE] = "positionrelative", [IIO_PHASE] = "phase", [IIO_MASSCONCENTRATION] = "massconcentration", + [IIO_DELTA_ANGL] = "deltaangl", }; static const char * const iio_modifier_names[] = { diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index c79f2f046a0b..55666a17d311 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -47,6 +47,7 @@ enum iio_chan_type { IIO_POSITIONRELATIVE, IIO_PHASE, IIO_MASSCONCENTRATION, + IIO_DELTA_ANGL, }; enum iio_modifier { diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c index 0a5c2bb60030..3505450060e6 100644 --- a/tools/iio/iio_event_monitor.c +++ b/tools/iio/iio_event_monitor.c @@ -59,6 +59,7 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_POSITIONRELATIVE] = "positionrelative", [IIO_PHASE] = "phase", [IIO_MASSCONCENTRATION] = "massconcentration", + [IIO_DELTA_ANGL] = "deltaangl", }; static const char * const iio_ev_type_text[] = { @@ -173,6 +174,7 @@ static bool event_is_known(struct iio_event_data *event) case IIO_POSITIONRELATIVE: case IIO_PHASE: case IIO_MASSCONCENTRATION: + case IIO_DELTA_ANGL: break; default: return false; -- cgit From 94a39f2c443b3fc5efe31a68502991020eefa3d2 Mon Sep 17 00:00:00 2001 From: Ramona Bolboaca Date: Tue, 8 Aug 2023 10:50:58 +0300 Subject: iio: Add IIO_DELTA_VELOCITY channel type The delta velocity is defined as a piece-wise integration of acceleration data. The delta velocity represents the linear velocity change between two consecutive measurements and it is measured in m / s (meters per second). In order to track the total linear velocity change during a desired period of time, simply sum-up the delta velocity samples acquired during that time. IIO currently does not offer a suitable channel type for this type of measurements hence this patch adds it. Signed-off-by: Ramona Bolboaca Reviewed-by: Nuno Sa Link: https://lore.kernel.org/r/20230808075059.645525-3-ramona.bolboaca@analog.com Signed-off-by: Jonathan Cameron --- Documentation/ABI/testing/sysfs-bus-iio | 23 +++++++++++++++++++++++ drivers/iio/industrialio-core.c | 1 + include/uapi/linux/iio/types.h | 1 + tools/iio/iio_event_monitor.c | 2 ++ 4 files changed, 27 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index 363dd4b09930..59968b745518 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -293,6 +293,21 @@ Description: angle samples acquired during that time. Units after application of scale and offset are radians. +What: /sys/bus/iio/devices/iio:deviceX/in_deltavelocity_x_raw +What: /sys/bus/iio/devices/iio:deviceX/in_deltavelocity_y_raw +What: /sys/bus/iio/devices/iio:deviceX/in_deltavelocity_z_raw +KernelVersion: 6.5 +Contact: linux-iio@vger.kernel.org +Description: + The linear velocity change between two consecutive samples on x, + y or z (may be arbitrarily assigned but should match other such + assignments on device). + In order to compute the total linear velocity change during a + desired period of time, the application should sum-up the delta + velocity samples acquired during that time. + Units after application of scale and offset are meters per + second. + What: /sys/bus/iio/devices/iio:deviceX/in_angl_raw What: /sys/bus/iio/devices/iio:deviceX/in_anglY_raw KernelVersion: 4.17 @@ -476,6 +491,7 @@ What: /sys/bus/iio/devices/iio:deviceX/in_velocity_sqrt(x^2+y^2+z^2)_scale What: /sys/bus/iio/devices/iio:deviceX/in_illuminance_scale What: /sys/bus/iio/devices/iio:deviceX/in_countY_scale What: /sys/bus/iio/devices/iio:deviceX/in_deltaangl_scale +What: /sys/bus/iio/devices/iio:deviceX/in_deltavelocity_scale What: /sys/bus/iio/devices/iio:deviceX/in_angl_scale What: /sys/bus/iio/devices/iio:deviceX/in_intensity_x_scale What: /sys/bus/iio/devices/iio:deviceX/in_intensity_y_scale @@ -1350,6 +1366,9 @@ What: /sys/.../iio:deviceX/bufferY/in_accel_z_en What: /sys/.../iio:deviceX/bufferY/in_deltaangl_x_en What: /sys/.../iio:deviceX/bufferY/in_deltaangl_y_en What: /sys/.../iio:deviceX/bufferY/in_deltaangl_z_en +What: /sys/.../iio:deviceX/bufferY/in_deltavelocity_x_en +What: /sys/.../iio:deviceX/bufferY/in_deltavelocity_y_en +What: /sys/.../iio:deviceX/bufferY/in_deltavelocity_z_en What: /sys/.../iio:deviceX/bufferY/in_anglvel_x_en What: /sys/.../iio:deviceX/bufferY/in_anglvel_y_en What: /sys/.../iio:deviceX/bufferY/in_anglvel_z_en @@ -1381,6 +1400,7 @@ Description: What: /sys/.../iio:deviceX/bufferY/in_accel_type What: /sys/.../iio:deviceX/bufferY/in_deltaangl_type +What: /sys/.../iio:deviceX/bufferY/in_deltavelocity_type What: /sys/.../iio:deviceX/bufferY/in_anglvel_type What: /sys/.../iio:deviceX/bufferY/in_magn_type What: /sys/.../iio:deviceX/bufferY/in_incli_type @@ -1438,6 +1458,9 @@ What: /sys/.../iio:deviceX/bufferY/in_accel_z_index What: /sys/.../iio:deviceX/bufferY/in_deltaangl_x_index What: /sys/.../iio:deviceX/bufferY/in_deltaangl_y_index What: /sys/.../iio:deviceX/bufferY/in_deltaangl_z_index +What: /sys/.../iio:deviceX/bufferY/in_deltavelocity_x_index +What: /sys/.../iio:deviceX/bufferY/in_deltavelocity_y_index +What: /sys/.../iio:deviceX/bufferY/in_deltavelocity_z_index What: /sys/.../iio:deviceX/bufferY/in_anglvel_x_index What: /sys/.../iio:deviceX/bufferY/in_anglvel_y_index What: /sys/.../iio:deviceX/bufferY/in_anglvel_z_index diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 11a65030186d..2ea0bf08caf3 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -91,6 +91,7 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_PHASE] = "phase", [IIO_MASSCONCENTRATION] = "massconcentration", [IIO_DELTA_ANGL] = "deltaangl", + [IIO_DELTA_VELOCITY] = "deltavelocity", }; static const char * const iio_modifier_names[] = { diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index 55666a17d311..9a341bd07702 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -48,6 +48,7 @@ enum iio_chan_type { IIO_PHASE, IIO_MASSCONCENTRATION, IIO_DELTA_ANGL, + IIO_DELTA_VELOCITY, }; enum iio_modifier { diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c index 3505450060e6..7e6761612246 100644 --- a/tools/iio/iio_event_monitor.c +++ b/tools/iio/iio_event_monitor.c @@ -60,6 +60,7 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_PHASE] = "phase", [IIO_MASSCONCENTRATION] = "massconcentration", [IIO_DELTA_ANGL] = "deltaangl", + [IIO_DELTA_VELOCITY] = "deltavelocity", }; static const char * const iio_ev_type_text[] = { @@ -175,6 +176,7 @@ static bool event_is_known(struct iio_event_data *event) case IIO_PHASE: case IIO_MASSCONCENTRATION: case IIO_DELTA_ANGL: + case IIO_DELTA_VELOCITY: break; default: return false; -- cgit From 5add321c329b1746589b51359259666ca3dbe219 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 29 Aug 2023 12:17:43 +0200 Subject: wifi: cfg80211: remove scan_width support There really isn't any support for scanning at different channel widths than 20 MHz since there's no way to set it. Remove this support for now, if somebody wants to maintain this whole thing later we can revisit how it should work. Signed-off-by: Johannes Berg --- drivers/net/wireless/ath/wil6210/wmi.c | 2 - .../broadcom/brcm80211/brcmfmac/cfg80211.c | 1 - include/net/cfg80211.h | 63 +------------------ include/uapi/linux/nl80211.h | 2 +- net/mac80211/ibss.c | 30 ++------- net/mac80211/ieee80211_i.h | 3 +- net/mac80211/ocb.c | 5 +- net/mac80211/scan.c | 71 +++++----------------- net/wireless/mesh.c | 5 +- net/wireless/nl80211.c | 1 - net/wireless/scan.c | 23 +------ net/wireless/trace.h | 6 +- net/wireless/util.c | 14 ++--- 13 files changed, 35 insertions(+), 191 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c index 6a5976a2944c..6fdb77d4c59e 100644 --- a/drivers/net/wireless/ath/wil6210/wmi.c +++ b/drivers/net/wireless/ath/wil6210/wmi.c @@ -870,7 +870,6 @@ static void wmi_evt_rx_mgmt(struct wil6210_vif *vif, int id, void *d, int len) struct cfg80211_bss *bss; struct cfg80211_inform_bss bss_data = { .chan = channel, - .scan_width = NL80211_BSS_CHAN_WIDTH_20, .signal = signal, .boottime_ns = ktime_to_ns(ktime_get_boottime()), }; @@ -1389,7 +1388,6 @@ wmi_evt_sched_scan_result(struct wil6210_vif *vif, int id, void *d, int len) u32 d_len; struct cfg80211_bss *bss; struct cfg80211_inform_bss bss_data = { - .scan_width = NL80211_BSS_CHAN_WIDTH_20, .boottime_ns = ktime_to_ns(ktime_get_boottime()), }; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index 2a90bb24ba77..94b4a7b8793d 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -3367,7 +3367,6 @@ static s32 brcmf_inform_single_bss(struct brcmf_cfg80211_info *cfg, freq = ieee80211_channel_to_frequency(channel, band); bss_data.chan = ieee80211_get_channel(wiphy, freq); - bss_data.scan_width = NL80211_BSS_CHAN_WIDTH_20; bss_data.boottime_ns = ktime_to_ns(ktime_get_boottime()); notify_capability = le16_to_cpu(bi->capability); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 134d9e0b73c9..2d3fa4a29781 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2536,7 +2536,6 @@ struct cfg80211_scan_6ghz_params { * @n_ssids: number of SSIDs * @channels: channels to scan on. * @n_channels: total number of channels to scan - * @scan_width: channel width for scanning * @ie: optional information element(s) to add into Probe Request or %NULL * @ie_len: length of ie in octets * @duration: how long to listen on each channel, in TUs. If @@ -2566,7 +2565,6 @@ struct cfg80211_scan_request { struct cfg80211_ssid *ssids; int n_ssids; u32 n_channels; - enum nl80211_bss_scan_width scan_width; const u8 *ie; size_t ie_len; u16 duration; @@ -2661,7 +2659,6 @@ struct cfg80211_bss_select_adjust { * @ssids: SSIDs to scan for (passed in the probe_reqs in active scans) * @n_ssids: number of SSIDs * @n_channels: total number of channels to scan - * @scan_width: channel width for scanning * @ie: optional information element(s) to add into Probe Request or %NULL * @ie_len: length of ie in octets * @flags: control flags from &enum nl80211_scan_flags @@ -2709,7 +2706,6 @@ struct cfg80211_sched_scan_request { struct cfg80211_ssid *ssids; int n_ssids; u32 n_channels; - enum nl80211_bss_scan_width scan_width; const u8 *ie; size_t ie_len; u32 flags; @@ -2757,7 +2753,6 @@ enum cfg80211_signal_type { /** * struct cfg80211_inform_bss - BSS inform data * @chan: channel the frame was received on - * @scan_width: scan width that was used * @signal: signal strength value, according to the wiphy's * signal type * @boottime_ns: timestamp (CLOCK_BOOTTIME) when the information was @@ -2777,7 +2772,6 @@ enum cfg80211_signal_type { */ struct cfg80211_inform_bss { struct ieee80211_channel *chan; - enum nl80211_bss_scan_width scan_width; s32 signal; u64 boottime_ns; u64 parent_tsf; @@ -2811,7 +2805,6 @@ struct cfg80211_bss_ies { * for use in scan results and similar. * * @channel: channel this BSS is on - * @scan_width: width of the control channel * @bssid: BSSID of the BSS * @beacon_interval: the beacon interval as from the frame * @capability: the capability field in host byte order @@ -2841,7 +2834,6 @@ struct cfg80211_bss_ies { */ struct cfg80211_bss { struct ieee80211_channel *channel; - enum nl80211_bss_scan_width scan_width; const struct cfg80211_bss_ies __rcu *ies; const struct cfg80211_bss_ies __rcu *beacon_ies; @@ -6321,13 +6313,11 @@ ieee80211_get_response_rate(struct ieee80211_supported_band *sband, /** * ieee80211_mandatory_rates - get mandatory rates for a given band * @sband: the band to look for rates in - * @scan_width: width of the control channel * * This function returns a bitmap of the mandatory rates for the given * band, bits are set according to the rate position in the bitrates array. */ -u32 ieee80211_mandatory_rates(struct ieee80211_supported_band *sband, - enum nl80211_bss_scan_width scan_width); +u32 ieee80211_mandatory_rates(struct ieee80211_supported_band *sband); /* * Radiotap parsing functions -- for controlled injection support @@ -6988,22 +6978,6 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, struct ieee80211_mgmt *mgmt, size_t len, gfp_t gfp); -static inline struct cfg80211_bss * __must_check -cfg80211_inform_bss_width_frame(struct wiphy *wiphy, - struct ieee80211_channel *rx_channel, - enum nl80211_bss_scan_width scan_width, - struct ieee80211_mgmt *mgmt, size_t len, - s32 signal, gfp_t gfp) -{ - struct cfg80211_inform_bss data = { - .chan = rx_channel, - .scan_width = scan_width, - .signal = signal, - }; - - return cfg80211_inform_bss_frame_data(wiphy, &data, mgmt, len, gfp); -} - static inline struct cfg80211_bss * __must_check cfg80211_inform_bss_frame(struct wiphy *wiphy, struct ieee80211_channel *rx_channel, @@ -7012,7 +6986,6 @@ cfg80211_inform_bss_frame(struct wiphy *wiphy, { struct cfg80211_inform_bss data = { .chan = rx_channel, - .scan_width = NL80211_BSS_CHAN_WIDTH_20, .signal = signal, }; @@ -7114,26 +7087,6 @@ cfg80211_inform_bss_data(struct wiphy *wiphy, u16 beacon_interval, const u8 *ie, size_t ielen, gfp_t gfp); -static inline struct cfg80211_bss * __must_check -cfg80211_inform_bss_width(struct wiphy *wiphy, - struct ieee80211_channel *rx_channel, - enum nl80211_bss_scan_width scan_width, - enum cfg80211_bss_frame_type ftype, - const u8 *bssid, u64 tsf, u16 capability, - u16 beacon_interval, const u8 *ie, size_t ielen, - s32 signal, gfp_t gfp) -{ - struct cfg80211_inform_bss data = { - .chan = rx_channel, - .scan_width = scan_width, - .signal = signal, - }; - - return cfg80211_inform_bss_data(wiphy, &data, ftype, bssid, tsf, - capability, beacon_interval, ie, ielen, - gfp); -} - static inline struct cfg80211_bss * __must_check cfg80211_inform_bss(struct wiphy *wiphy, struct ieee80211_channel *rx_channel, @@ -7144,7 +7097,6 @@ cfg80211_inform_bss(struct wiphy *wiphy, { struct cfg80211_inform_bss data = { .chan = rx_channel, - .scan_width = NL80211_BSS_CHAN_WIDTH_20, .signal = signal, }; @@ -7229,19 +7181,6 @@ void cfg80211_bss_iter(struct wiphy *wiphy, void *data), void *iter_data); -static inline enum nl80211_bss_scan_width -cfg80211_chandef_to_scan_width(const struct cfg80211_chan_def *chandef) -{ - switch (chandef->width) { - case NL80211_CHAN_WIDTH_5: - return NL80211_BSS_CHAN_WIDTH_5; - case NL80211_CHAN_WIDTH_10: - return NL80211_BSS_CHAN_WIDTH_10; - default: - return NL80211_BSS_CHAN_WIDTH_20; - } -} - /** * cfg80211_rx_mlme_mgmt - notification of processed MLME management frame * @dev: network device diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 88eb85c63029..b628126e06fa 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -5038,7 +5038,7 @@ enum nl80211_bss_scan_width { * elements from a Beacon frame (bin); not present if no Beacon frame has * yet been received * @NL80211_BSS_CHAN_WIDTH: channel width of the control channel - * (u32, enum nl80211_bss_scan_width) + * (u32, enum nl80211_bss_scan_width) - No longer used! * @NL80211_BSS_BEACON_TSF: TSF of the last received beacon (u64) * (not present if no beacon frame has been received yet) * @NL80211_BSS_PRESP_DATA: the data in @NL80211_BSS_INFORMATION_ELEMENTS and diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 9907cea6457c..55ec34602b53 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -377,7 +377,6 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, round_jiffies(jiffies + IEEE80211_IBSS_MERGE_INTERVAL)); bss_meta.chan = chan; - bss_meta.scan_width = cfg80211_chandef_to_scan_width(&chandef); bss = cfg80211_inform_bss_frame_data(local->hw.wiphy, &bss_meta, mgmt, presp->head_len, GFP_KERNEL); @@ -595,7 +594,6 @@ ieee80211_ibss_add_sta(struct ieee80211_sub_if_data *sdata, const u8 *bssid, struct sta_info *sta; struct ieee80211_chanctx_conf *chanctx_conf; struct ieee80211_supported_band *sband; - enum nl80211_bss_scan_width scan_width; int band; /* @@ -624,7 +622,6 @@ ieee80211_ibss_add_sta(struct ieee80211_sub_if_data *sdata, const u8 *bssid, if (WARN_ON_ONCE(!chanctx_conf)) return NULL; band = chanctx_conf->def.chan->band; - scan_width = cfg80211_chandef_to_scan_width(&chanctx_conf->def); rcu_read_unlock(); sta = sta_info_alloc(sdata, addr, GFP_KERNEL); @@ -636,7 +633,7 @@ ieee80211_ibss_add_sta(struct ieee80211_sub_if_data *sdata, const u8 *bssid, /* make sure mandatory rates are always added */ sband = local->hw.wiphy->bands[band]; sta->sta.deflink.supp_rates[band] = supp_rates | - ieee80211_mandatory_rates(sband, scan_width); + ieee80211_mandatory_rates(sband); return ieee80211_ibss_finish_sta(sta); } @@ -975,7 +972,6 @@ static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata, { struct sta_info *sta; enum nl80211_band band = rx_status->band; - enum nl80211_bss_scan_width scan_width; struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; bool rates_updated = false; @@ -1001,15 +997,9 @@ static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata, u32 prev_rates; prev_rates = sta->sta.deflink.supp_rates[band]; - /* make sure mandatory rates are always added */ - scan_width = NL80211_BSS_CHAN_WIDTH_20; - if (rx_status->bw == RATE_INFO_BW_5) - scan_width = NL80211_BSS_CHAN_WIDTH_5; - else if (rx_status->bw == RATE_INFO_BW_10) - scan_width = NL80211_BSS_CHAN_WIDTH_10; sta->sta.deflink.supp_rates[band] = supp_rates | - ieee80211_mandatory_rates(sband, scan_width); + ieee80211_mandatory_rates(sband); if (sta->sta.deflink.supp_rates[band] != prev_rates) { ibss_dbg(sdata, "updated supp_rates set for %pM based on beacon/probe_resp (0x%x -> 0x%x)\n", @@ -1196,7 +1186,6 @@ void ieee80211_ibss_rx_no_sta(struct ieee80211_sub_if_data *sdata, struct sta_info *sta; struct ieee80211_chanctx_conf *chanctx_conf; struct ieee80211_supported_band *sband; - enum nl80211_bss_scan_width scan_width; int band; /* @@ -1222,7 +1211,6 @@ void ieee80211_ibss_rx_no_sta(struct ieee80211_sub_if_data *sdata, return; } band = chanctx_conf->def.chan->band; - scan_width = cfg80211_chandef_to_scan_width(&chanctx_conf->def); rcu_read_unlock(); sta = sta_info_alloc(sdata, addr, GFP_ATOMIC); @@ -1232,7 +1220,7 @@ void ieee80211_ibss_rx_no_sta(struct ieee80211_sub_if_data *sdata, /* make sure mandatory rates are always added */ sband = local->hw.wiphy->bands[band]; sta->sta.deflink.supp_rates[band] = supp_rates | - ieee80211_mandatory_rates(sband, scan_width); + ieee80211_mandatory_rates(sband); spin_lock(&ifibss->incomplete_lock); list_add(&sta->list, &ifibss->incomplete_stations); @@ -1282,7 +1270,6 @@ static void ieee80211_ibss_sta_expire(struct ieee80211_sub_if_data *sdata) static void ieee80211_sta_merge_ibss(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; - enum nl80211_bss_scan_width scan_width; lockdep_assert_wiphy(sdata->local->hw.wiphy); @@ -1304,9 +1291,8 @@ static void ieee80211_sta_merge_ibss(struct ieee80211_sub_if_data *sdata) sdata_info(sdata, "No active IBSS STAs - trying to scan for other IBSS networks with same SSID (merge)\n"); - scan_width = cfg80211_chandef_to_scan_width(&ifibss->chandef); ieee80211_request_ibss_scan(sdata, ifibss->ssid, ifibss->ssid_len, - NULL, 0, scan_width); + NULL, 0); } static void ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata) @@ -1424,7 +1410,6 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) struct cfg80211_bss *cbss; struct ieee80211_channel *chan = NULL; const u8 *bssid = NULL; - enum nl80211_bss_scan_width scan_width; int active_ibss; lockdep_assert_wiphy(sdata->local->hw.wiphy); @@ -1483,8 +1468,6 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) sdata_info(sdata, "Trigger new scan to find an IBSS to join\n"); - scan_width = cfg80211_chandef_to_scan_width(&ifibss->chandef); - if (ifibss->fixed_channel) { num = ieee80211_ibss_setup_scan_channels(local->hw.wiphy, &ifibss->chandef, @@ -1492,11 +1475,10 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) ARRAY_SIZE(channels)); ieee80211_request_ibss_scan(sdata, ifibss->ssid, ifibss->ssid_len, channels, - num, scan_width); + num); } else { ieee80211_request_ibss_scan(sdata, ifibss->ssid, - ifibss->ssid_len, NULL, - 0, scan_width); + ifibss->ssid_len, NULL, 0); } } else { int interval = IEEE80211_SCAN_INTERVAL; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index e7dc4cdcdcde..e443a8e5e9be 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1911,8 +1911,7 @@ void ieee80211_scan_work(struct wiphy *wiphy, struct wiphy_work *work); int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata, const u8 *ssid, u8 ssid_len, struct ieee80211_channel **channels, - unsigned int n_channels, - enum nl80211_bss_scan_width scan_width); + unsigned int n_channels); int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req); void ieee80211_scan_cancel(struct ieee80211_local *local); diff --git a/net/mac80211/ocb.c b/net/mac80211/ocb.c index 6e2965ffb809..449af4e1cca4 100644 --- a/net/mac80211/ocb.c +++ b/net/mac80211/ocb.c @@ -44,7 +44,6 @@ void ieee80211_ocb_rx_no_sta(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct ieee80211_chanctx_conf *chanctx_conf; struct ieee80211_supported_band *sband; - enum nl80211_bss_scan_width scan_width; struct sta_info *sta; int band; @@ -66,7 +65,6 @@ void ieee80211_ocb_rx_no_sta(struct ieee80211_sub_if_data *sdata, return; } band = chanctx_conf->def.chan->band; - scan_width = cfg80211_chandef_to_scan_width(&chanctx_conf->def); rcu_read_unlock(); sta = sta_info_alloc(sdata, addr, GFP_ATOMIC); @@ -75,8 +73,7 @@ void ieee80211_ocb_rx_no_sta(struct ieee80211_sub_if_data *sdata, /* Add only mandatory rates for now */ sband = local->hw.wiphy->bands[band]; - sta->sta.deflink.supp_rates[band] = - ieee80211_mandatory_rates(sband, scan_width); + sta->sta.deflink.supp_rates[band] = ieee80211_mandatory_rates(sband); spin_lock(&ifocb->incomplete_lock); list_add(&sta->list, &ifocb->incomplete_stations); diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 58d525e41f6b..24fa06105378 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -187,12 +187,6 @@ ieee80211_bss_info_update(struct ieee80211_local *local, else if (ieee80211_hw_check(&local->hw, SIGNAL_UNSPEC)) bss_meta.signal = (rx_status->signal * 100) / local->hw.max_signal; - bss_meta.scan_width = NL80211_BSS_CHAN_WIDTH_20; - if (rx_status->bw == RATE_INFO_BW_5) - bss_meta.scan_width = NL80211_BSS_CHAN_WIDTH_5; - else if (rx_status->bw == RATE_INFO_BW_10) - bss_meta.scan_width = NL80211_BSS_CHAN_WIDTH_10; - bss_meta.chan = channel; rcu_read_lock(); @@ -315,22 +309,11 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) ieee80211_rx_bss_put(local, bss); } -static void -ieee80211_prepare_scan_chandef(struct cfg80211_chan_def *chandef, - enum nl80211_bss_scan_width scan_width) +static void ieee80211_prepare_scan_chandef(struct cfg80211_chan_def *chandef) { memset(chandef, 0, sizeof(*chandef)); - switch (scan_width) { - case NL80211_BSS_CHAN_WIDTH_5: - chandef->width = NL80211_CHAN_WIDTH_5; - break; - case NL80211_BSS_CHAN_WIDTH_10: - chandef->width = NL80211_CHAN_WIDTH_10; - break; - default: - chandef->width = NL80211_CHAN_WIDTH_20_NOHT; - break; - } + + chandef->width = NL80211_CHAN_WIDTH_20_NOHT; } /* return false if no more work */ @@ -378,7 +361,7 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_sub_if_data *sdata) } local->hw_scan_req->req.n_channels = n_chans; - ieee80211_prepare_scan_chandef(&chandef, req->scan_width); + ieee80211_prepare_scan_chandef(&chandef); if (req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT) flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT; @@ -919,7 +902,6 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local, { int skip; struct ieee80211_channel *chan; - enum nl80211_bss_scan_width oper_scan_width; struct cfg80211_scan_request *scan_req; scan_req = rcu_dereference_protected(local->scan_req, @@ -933,42 +915,21 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local, local->scan_chandef.freq1_offset = chan->freq_offset; local->scan_chandef.center_freq2 = 0; - /* For scanning on the S1G band, ignore scan_width (which is constant - * across all channels) for now since channel width is specific to each - * channel. Detect the required channel width here and likely revisit - * later. Maybe scan_width could be used to build the channel scan list? + /* For scanning on the S1G band, detect the channel width according to + * the channel being scanned. */ if (chan->band == NL80211_BAND_S1GHZ) { local->scan_chandef.width = ieee80211_s1g_channel_width(chan); goto set_channel; } - switch (scan_req->scan_width) { - case NL80211_BSS_CHAN_WIDTH_5: - local->scan_chandef.width = NL80211_CHAN_WIDTH_5; - break; - case NL80211_BSS_CHAN_WIDTH_10: - local->scan_chandef.width = NL80211_CHAN_WIDTH_10; - break; - default: - case NL80211_BSS_CHAN_WIDTH_20: - /* If scanning on oper channel, use whatever channel-type - * is currently in use. - */ - oper_scan_width = cfg80211_chandef_to_scan_width( - &local->_oper_chandef); - if (chan == local->_oper_chandef.chan && - oper_scan_width == scan_req->scan_width) - local->scan_chandef = local->_oper_chandef; - else - local->scan_chandef.width = NL80211_CHAN_WIDTH_20_NOHT; - break; - case NL80211_BSS_CHAN_WIDTH_1: - case NL80211_BSS_CHAN_WIDTH_2: - /* shouldn't get here, S1G handled above */ - WARN_ON(1); - break; - } + /* If scanning on oper channel, use whatever channel-type + * is currently in use. + */ + if (chan == local->_oper_chandef.chan) + local->scan_chandef = local->_oper_chandef; + else + local->scan_chandef.width = NL80211_CHAN_WIDTH_20_NOHT; set_channel: if (ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL)) @@ -1152,8 +1113,7 @@ int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata, int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata, const u8 *ssid, u8 ssid_len, struct ieee80211_channel **channels, - unsigned int n_channels, - enum nl80211_bss_scan_width scan_width) + unsigned int n_channels) { struct ieee80211_local *local = sdata->local; int ret = -EBUSY, i, n_ch = 0; @@ -1210,7 +1170,6 @@ int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata, local->int_scan_req->ssids = &local->scan_ssid; local->int_scan_req->n_ssids = 1; - local->int_scan_req->scan_width = scan_width; memcpy(local->int_scan_req->ssids[0].ssid, ssid, IEEE80211_MAX_SSID_LEN); local->int_scan_req->ssids[0].ssid_len = ssid_len; @@ -1311,7 +1270,7 @@ int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, goto out; } - ieee80211_prepare_scan_chandef(&chandef, req->scan_width); + ieee80211_prepare_scan_chandef(&chandef); ieee80211_build_preq_ies(sdata, ie, num_bands * iebufsz, &sched_scan_ies, req->ie, diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index dc75abdb8f2e..83306979fbe2 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -172,7 +172,6 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, * basic rates */ if (!setup->basic_rates) { - enum nl80211_bss_scan_width scan_width; struct ieee80211_supported_band *sband = rdev->wiphy.bands[setup->chandef.chan->band]; @@ -193,9 +192,7 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, } } } else { - scan_width = cfg80211_chandef_to_scan_width(&setup->chandef); - setup->basic_rates = ieee80211_mandatory_rates(sband, - scan_width); + setup->basic_rates = ieee80211_mandatory_rates(sband); } } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index ab0aea7dca7d..f2dd4c85a10f 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -10283,7 +10283,6 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, nla_put_u32(msg, NL80211_BSS_FREQUENCY, res->channel->center_freq) || nla_put_u32(msg, NL80211_BSS_FREQUENCY_OFFSET, res->channel->freq_offset) || - nla_put_u32(msg, NL80211_BSS_CHAN_WIDTH, res->scan_width) || nla_put_u32(msg, NL80211_BSS_SEEN_MS_AGO, jiffies_to_msecs(jiffies - intbss->ts))) goto nla_put_failure; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index ae4d000009fe..a5758edf53b8 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1638,8 +1638,6 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev, continue; if (bss->pub.channel != new->pub.channel) continue; - if (bss->pub.scan_width != new->pub.scan_width) - continue; if (rcu_access_pointer(bss->pub.beacon_ies)) continue; ies = rcu_access_pointer(bss->pub.ies); @@ -1936,8 +1934,7 @@ EXPORT_SYMBOL(cfg80211_get_ies_channel_number); */ static struct ieee80211_channel * cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen, - struct ieee80211_channel *channel, - enum nl80211_bss_scan_width scan_width) + struct ieee80211_channel *channel) { u32 freq; int channel_number; @@ -1977,16 +1974,6 @@ cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen, return channel; } - if (scan_width == NL80211_BSS_CHAN_WIDTH_10 || - scan_width == NL80211_BSS_CHAN_WIDTH_5) { - /* - * Ignore channel number in 5 and 10 MHz channels where there - * may not be an n:1 or 1:n mapping between frequencies and - * channel numbers. - */ - return channel; - } - /* * Use the channel determined through the payload channel number * instead of the RX channel reported by the driver. @@ -2046,14 +2033,12 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, channel = data->channel; if (!channel) channel = cfg80211_get_bss_channel(wiphy, data->ie, data->ielen, - drv_data->chan, - drv_data->scan_width); + drv_data->chan); if (!channel) return NULL; memcpy(tmp.pub.bssid, data->bssid, ETH_ALEN); tmp.pub.channel = channel; - tmp.pub.scan_width = drv_data->scan_width; if (data->bss_source != BSS_SOURCE_STA_PROFILE) tmp.pub.signal = drv_data->signal; else @@ -2814,8 +2799,7 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, variable = ext->u.s1g_beacon.variable; } - channel = cfg80211_get_bss_channel(wiphy, variable, - ielen, data->chan, data->scan_width); + channel = cfg80211_get_bss_channel(wiphy, variable, ielen, data->chan); if (!channel) return NULL; @@ -2868,7 +2852,6 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, tmp.pub.beacon_interval = beacon_int; tmp.pub.capability = capability; tmp.pub.channel = channel; - tmp.pub.scan_width = data->scan_width; tmp.pub.signal = data->signal; tmp.ts_boottime = data->boottime_ns; tmp.parent_tsf = data->parent_tsf; diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 617c0d0dfa96..126c3a03e43e 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -3590,7 +3590,6 @@ TRACE_EVENT(cfg80211_inform_bss_frame, TP_STRUCT__entry( WIPHY_ENTRY CHAN_ENTRY - __field(enum nl80211_bss_scan_width, scan_width) __dynamic_array(u8, mgmt, len) __field(s32, signal) __field(u64, ts_boottime) @@ -3600,7 +3599,6 @@ TRACE_EVENT(cfg80211_inform_bss_frame, TP_fast_assign( WIPHY_ASSIGN; CHAN_ASSIGN(data->chan); - __entry->scan_width = data->scan_width; if (mgmt) memcpy(__get_dynamic_array(mgmt), mgmt, len); __entry->signal = data->signal; @@ -3609,8 +3607,8 @@ TRACE_EVENT(cfg80211_inform_bss_frame, MAC_ASSIGN(parent_bssid, data->parent_bssid); ), TP_printk(WIPHY_PR_FMT ", " CHAN_PR_FMT - "(scan_width: %d) signal: %d, tsb:%llu, detect_tsf:%llu, tsf_bssid: %pM", - WIPHY_PR_ARG, CHAN_PR_ARG, __entry->scan_width, + "signal: %d, tsb:%llu, detect_tsf:%llu, tsf_bssid: %pM", + WIPHY_PR_ARG, CHAN_PR_ARG, __entry->signal, (unsigned long long)__entry->ts_boottime, (unsigned long long)__entry->parent_tsf, __entry->parent_bssid) diff --git a/net/wireless/util.c b/net/wireless/util.c index 56cbd9979a3f..213c9405e645 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -43,8 +43,7 @@ ieee80211_get_response_rate(struct ieee80211_supported_band *sband, } EXPORT_SYMBOL(ieee80211_get_response_rate); -u32 ieee80211_mandatory_rates(struct ieee80211_supported_band *sband, - enum nl80211_bss_scan_width scan_width) +u32 ieee80211_mandatory_rates(struct ieee80211_supported_band *sband) { struct ieee80211_rate *bitrates; u32 mandatory_rates = 0; @@ -54,15 +53,10 @@ u32 ieee80211_mandatory_rates(struct ieee80211_supported_band *sband, if (WARN_ON(!sband)) return 1; - if (sband->band == NL80211_BAND_2GHZ) { - if (scan_width == NL80211_BSS_CHAN_WIDTH_5 || - scan_width == NL80211_BSS_CHAN_WIDTH_10) - mandatory_flag = IEEE80211_RATE_MANDATORY_G; - else - mandatory_flag = IEEE80211_RATE_MANDATORY_B; - } else { + if (sband->band == NL80211_BAND_2GHZ) + mandatory_flag = IEEE80211_RATE_MANDATORY_B; + else mandatory_flag = IEEE80211_RATE_MANDATORY_A; - } bitrates = sband->bitrates; for (i = 0; i < sband->n_bitrates; i++) -- cgit From 0cfaec25995ad3be316631b945be7ced81daa4e7 Mon Sep 17 00:00:00 2001 From: Aloka Dixit Date: Thu, 27 Jul 2023 10:40:56 -0700 Subject: wifi: nl80211: fixes to FILS discovery updates Add a new flag 'update' which is set to true during start_ap() if (and only if) one of the following two conditions are met: - Userspace passed an empty nested attribute which indicates that the feature should be disabled and templates deleted. - Userspace passed all the parameters for the nested attribute. Existing configuration will not be changed while the flag remains false. Add similar changes for unsolicited broadcast probe response transmission. Signed-off-by: Aloka Dixit Reviewed-by: Jeff Johnson Link: https://lore.kernel.org/r/20230727174100.11721-2-quic_alokad@quicinc.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 ++++ include/uapi/linux/nl80211.h | 11 +++++++---- net/wireless/nl80211.c | 16 +++++++++++++++- 3 files changed, 26 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 2d3fa4a29781..aa8c4538f93d 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1338,6 +1338,7 @@ struct cfg80211_acl_data { * struct cfg80211_fils_discovery - FILS discovery parameters from * IEEE Std 802.11ai-2016, Annex C.3 MIB detail. * + * @update: Set to true if the feature configuration should be updated. * @min_interval: Minimum packet interval in TUs (0 - 10000) * @max_interval: Maximum packet interval in TUs (0 - 10000) * @tmpl_len: Template length @@ -1345,6 +1346,7 @@ struct cfg80211_acl_data { * frame headers. */ struct cfg80211_fils_discovery { + bool update; u32 min_interval; u32 max_interval; size_t tmpl_len; @@ -1355,6 +1357,7 @@ struct cfg80211_fils_discovery { * struct cfg80211_unsol_bcast_probe_resp - Unsolicited broadcast probe * response parameters in 6GHz. * + * @update: Set to true if the feature configuration should be updated. * @interval: Packet interval in TUs. Maximum allowed is 20 TU, as mentioned * in IEEE P802.11ax/D6.0 26.17.2.3.2 - AP behavior for fast passive * scanning @@ -1362,6 +1365,7 @@ struct cfg80211_fils_discovery { * @tmpl: Template data for probe response */ struct cfg80211_unsol_bcast_probe_resp { + bool update; u32 interval; size_t tmpl_len; const u8 *tmpl; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index b628126e06fa..f797ab7a6547 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2690,11 +2690,13 @@ enum nl80211_commands { * * @NL80211_ATTR_FILS_DISCOVERY: Optional parameter to configure FILS * discovery. It is a nested attribute, see - * &enum nl80211_fils_discovery_attributes. + * &enum nl80211_fils_discovery_attributes. Userspace should pass an empty + * nested attribute to disable this feature and delete the templates. * * @NL80211_ATTR_UNSOL_BCAST_PROBE_RESP: Optional parameter to configure * unsolicited broadcast probe response. It is a nested attribute, see - * &enum nl80211_unsol_bcast_probe_resp_attributes. + * &enum nl80211_unsol_bcast_probe_resp_attributes. Userspace should pass an empty + * nested attribute to disable this feature and delete the templates. * * @NL80211_ATTR_S1G_CAPABILITY: S1G Capability information element (from * association request when used with NL80211_CMD_NEW_STATION) @@ -7606,7 +7608,7 @@ enum nl80211_iftype_akm_attributes { * @NL80211_FILS_DISCOVERY_ATTR_INT_MIN: Minimum packet interval (u32, TU). * Allowed range: 0..10000 (TU = Time Unit) * @NL80211_FILS_DISCOVERY_ATTR_INT_MAX: Maximum packet interval (u32, TU). - * Allowed range: 0..10000 (TU = Time Unit) + * Allowed range: 0..10000 (TU = Time Unit). If set to 0, the feature is disabled. * @NL80211_FILS_DISCOVERY_ATTR_TMPL: Template data for FILS discovery action * frame including the headers. * @@ -7639,7 +7641,8 @@ enum nl80211_fils_discovery_attributes { * * @NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT: Maximum packet interval (u32, TU). * Allowed range: 0..20 (TU = Time Unit). IEEE P802.11ax/D6.0 - * 26.17.2.3.2 (AP behavior for fast passive scanning). + * 26.17.2.3.2 (AP behavior for fast passive scanning). If set to 0, the feature is + * disabled. * @NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL: Unsolicited broadcast probe response * frame template (binary). * diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index f2dd4c85a10f..53618a147907 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5647,6 +5647,13 @@ static int nl80211_parse_fils_discovery(struct cfg80211_registered_device *rdev, if (ret) return ret; + if (!tb[NL80211_FILS_DISCOVERY_ATTR_INT_MIN] && + !tb[NL80211_FILS_DISCOVERY_ATTR_INT_MAX] && + !tb[NL80211_FILS_DISCOVERY_ATTR_TMPL]) { + fd->update = true; + return 0; + } + if (!tb[NL80211_FILS_DISCOVERY_ATTR_INT_MIN] || !tb[NL80211_FILS_DISCOVERY_ATTR_INT_MAX] || !tb[NL80211_FILS_DISCOVERY_ATTR_TMPL]) @@ -5656,7 +5663,7 @@ static int nl80211_parse_fils_discovery(struct cfg80211_registered_device *rdev, fd->tmpl = nla_data(tb[NL80211_FILS_DISCOVERY_ATTR_TMPL]); fd->min_interval = nla_get_u32(tb[NL80211_FILS_DISCOVERY_ATTR_INT_MIN]); fd->max_interval = nla_get_u32(tb[NL80211_FILS_DISCOVERY_ATTR_INT_MAX]); - + fd->update = true; return 0; } @@ -5679,6 +5686,12 @@ nl80211_parse_unsol_bcast_probe_resp(struct cfg80211_registered_device *rdev, if (ret) return ret; + if (!tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT] && + !tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL]) { + presp->update = true; + return 0; + } + if (!tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT] || !tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL]) return -EINVAL; @@ -5686,6 +5699,7 @@ nl80211_parse_unsol_bcast_probe_resp(struct cfg80211_registered_device *rdev, presp->tmpl = nla_data(tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL]); presp->tmpl_len = nla_len(tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL]); presp->interval = nla_get_u32(tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT]); + presp->update = true; return 0; } -- cgit From 531108ec5b5cd45ec6272a6115e73275baef7d22 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 12 Sep 2023 19:23:21 +0300 Subject: uapi: stddef.h: Fix header guard location The #endif for the header guard wasn't at the end of the header. This was harmless since the define that escaped was already testing for its own redefinition. Regardless, move the #endif to the correct place. Signed-off-by: Alexey Dobriyan Fixes: c8248faf3ca2 ("Compiler Attributes: counted_by: Adjust name and identifier expansion") Link: https://lore.kernel.org/r/b1f5081e-339d-421d-81b2-cbb94e1f6f5f@p183 Co-developed-by: Kees Cook Signed-off-by: Kees Cook --- include/uapi/linux/stddef.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 7c3fc3980881..c027b2070d79 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -44,8 +44,9 @@ struct { } __empty_ ## NAME; \ TYPE NAME[]; \ } -#endif #ifndef __counted_by #define __counted_by(m) #endif + +#endif /* _UAPI_LINUX_STDDEF_H */ -- cgit From 32a4ec211d4164e667d9d0b807fadf02053cd2e9 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 12 Sep 2023 19:22:24 +0300 Subject: uapi: stddef.h: Fix __DECLARE_FLEX_ARRAY for C++ __DECLARE_FLEX_ARRAY(T, member) macro expands to struct { struct {} __empty_member; T member[]; }; which is subtly wrong in C++ because sizeof(struct{}) is 1 not 0, changing UAPI structures layouts. This can be fixed by expanding to T member[]; Now g++ doesn't like "T member[]" either, throwing errors on the following code: struct S { union { T1 member1[]; T2 member2[]; }; }; or struct S { T member[]; }; Use "T member[0];" which seems to work and does the right thing wrt structure layout. Signed-off-by: Alexey Dobriyan Fixes: 3080ea5553cc ("stddef: Introduce DECLARE_FLEX_ARRAY() helper") Link: https://lore.kernel.org/r/97242381-f1ec-4a4a-9472-1a464f575657@p183 Signed-off-by: Kees Cook --- include/uapi/linux/stddef.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index c027b2070d79..5c6c4269f7ef 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -29,6 +29,11 @@ struct TAG { MEMBERS } ATTRS NAME; \ } +#ifdef __cplusplus +/* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */ +#define __DECLARE_FLEX_ARRAY(T, member) \ + T member[0] +#else /** * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union * @@ -44,6 +49,7 @@ struct { } __empty_ ## NAME; \ TYPE NAME[]; \ } +#endif #ifndef __counted_by #define __counted_by(m) -- cgit From a9c2a608549bb1a2363d289d63907640afcf22af Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Wed, 13 Sep 2023 10:13:49 -0700 Subject: bpf: expose information about supported xdp metadata kfunc Add new xdp-rx-metadata-features member to netdev netlink which exports a bitmask of supported kfuncs. Most of the patch is autogenerated (headers), the only relevant part is netdev.yaml and the changes in netdev-genl.c to marshal into netlink. Example output on veth: $ ip link add veth0 type veth peer name veth1 # ifndex == 12 $ ./tools/net/ynl/samples/netdev 12 Select ifc ($ifindex; or 0 = dump; or -2 ntf check): 12 veth1[12] xdp-features (23): basic redirect rx-sg xdp-rx-metadata-features (3): timestamp hash xdp-zc-max-segs=0 Cc: netdev@vger.kernel.org Cc: Willem de Bruijn Signed-off-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20230913171350.369987-3-sdf@google.com Signed-off-by: Martin KaFai Lau --- Documentation/netlink/specs/netdev.yaml | 21 +++++++++++++++++++++ Documentation/networking/xdp-rx-metadata.rst | 7 +++++++ include/net/xdp.h | 5 ++++- include/uapi/linux/netdev.h | 16 ++++++++++++++++ kernel/bpf/offload.c | 2 +- net/core/netdev-genl.c | 12 +++++++++++- net/core/xdp.c | 4 ++-- tools/include/uapi/linux/netdev.h | 16 ++++++++++++++++ 8 files changed, 78 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 1c7284fd535b..c46fcc78fc04 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -42,6 +42,19 @@ definitions: doc: This feature informs if netdev implements non-linear XDP buffer support in ndo_xdp_xmit callback. + - + type: flags + name: xdp-rx-metadata + render-max: true + entries: + - + name: timestamp + doc: + Device is capable of exposing receive HW timestamp via bpf_xdp_metadata_rx_timestamp(). + - + name: hash + doc: + Device is capable of exposing receive packet hash via bpf_xdp_metadata_rx_hash(). attribute-sets: - @@ -68,6 +81,13 @@ attribute-sets: type: u32 checks: min: 1 + - + name: xdp-rx-metadata-features + doc: Bitmask of supported XDP receive metadata features. + See Documentation/networking/xdp-rx-metadata.rst for more details. + type: u64 + enum: xdp-rx-metadata + enum-as-flags: true operations: list: @@ -84,6 +104,7 @@ operations: - ifindex - xdp-features - xdp-zc-max-segs + - xdp-rx-metadata-features dump: reply: *dev-all - diff --git a/Documentation/networking/xdp-rx-metadata.rst b/Documentation/networking/xdp-rx-metadata.rst index 25ce72af81c2..205696780b78 100644 --- a/Documentation/networking/xdp-rx-metadata.rst +++ b/Documentation/networking/xdp-rx-metadata.rst @@ -105,6 +105,13 @@ bpf_tail_call Adding programs that access metadata kfuncs to the ``BPF_MAP_TYPE_PROG_ARRAY`` is currently not supported. +Supported Devices +================= + +It is possible to query which kfunc the particular netdev implements via +netlink. See ``xdp-rx-metadata-features`` attribute set in +``Documentation/netlink/specs/netdev.yaml``. + Example ======= diff --git a/include/net/xdp.h b/include/net/xdp.h index d59e12f8f311..349c36fb5fd8 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -386,19 +386,22 @@ void xdp_attachment_setup(struct xdp_attachment_info *info, /* Define the relationship between xdp-rx-metadata kfunc and * various other entities: * - xdp_rx_metadata enum + * - netdev netlink enum (Documentation/netlink/specs/netdev.yaml) * - kfunc name * - xdp_metadata_ops field */ #define XDP_METADATA_KFUNC_xxx \ XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_TIMESTAMP, \ + NETDEV_XDP_RX_METADATA_TIMESTAMP, \ bpf_xdp_metadata_rx_timestamp, \ xmo_rx_timestamp) \ XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_HASH, \ + NETDEV_XDP_RX_METADATA_HASH, \ bpf_xdp_metadata_rx_hash, \ xmo_rx_hash) \ enum xdp_rx_metadata { -#define XDP_METADATA_KFUNC(name, _, __) name, +#define XDP_METADATA_KFUNC(name, _, __, ___) name, XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC MAX_XDP_METADATA_KFUNC, diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index c1634b95c223..2943a151d4f1 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -38,11 +38,27 @@ enum netdev_xdp_act { NETDEV_XDP_ACT_MASK = 127, }; +/** + * enum netdev_xdp_rx_metadata + * @NETDEV_XDP_RX_METADATA_TIMESTAMP: Device is capable of exposing receive HW + * timestamp via bpf_xdp_metadata_rx_timestamp(). + * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet + * hash via bpf_xdp_metadata_rx_hash(). + */ +enum netdev_xdp_rx_metadata { + NETDEV_XDP_RX_METADATA_TIMESTAMP = 1, + NETDEV_XDP_RX_METADATA_HASH = 2, + + /* private: */ + NETDEV_XDP_RX_METADATA_MASK = 3, +}; + enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, NETDEV_A_DEV_XDP_FEATURES, NETDEV_A_DEV_XDP_ZC_MAX_SEGS, + NETDEV_A_DEV_XDP_RX_METADATA_FEATURES, __NETDEV_A_DEV_MAX, NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1) diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 6aa6de8d715d..e7a1752b5a09 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -845,7 +845,7 @@ void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id) if (!ops) goto out; -#define XDP_METADATA_KFUNC(name, _, xmo) \ +#define XDP_METADATA_KFUNC(name, _, __, xmo) \ if (func_id == bpf_xdp_metadata_kfunc_id(name)) p = ops->xmo; XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index c1aea8b756b6..fe61f85bcf33 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -5,6 +5,7 @@ #include #include #include +#include #include "netdev-genl-gen.h" @@ -12,15 +13,24 @@ static int netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp, const struct genl_info *info) { + u64 xdp_rx_meta = 0; void *hdr; hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; +#define XDP_METADATA_KFUNC(_, flag, __, xmo) \ + if (netdev->xdp_metadata_ops && netdev->xdp_metadata_ops->xmo) \ + xdp_rx_meta |= flag; +XDP_METADATA_KFUNC_xxx +#undef XDP_METADATA_KFUNC + if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) || nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_FEATURES, - netdev->xdp_features, NETDEV_A_DEV_PAD)) { + netdev->xdp_features, NETDEV_A_DEV_PAD) || + nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_RX_METADATA_FEATURES, + xdp_rx_meta, NETDEV_A_DEV_PAD)) { genlmsg_cancel(rsp, hdr); return -EINVAL; } diff --git a/net/core/xdp.c b/net/core/xdp.c index bab563b2f812..df4789ab512d 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -741,7 +741,7 @@ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash, __diag_pop(); BTF_SET8_START(xdp_metadata_kfunc_ids) -#define XDP_METADATA_KFUNC(_, name, __) BTF_ID_FLAGS(func, name, KF_TRUSTED_ARGS) +#define XDP_METADATA_KFUNC(_, __, name, ___) BTF_ID_FLAGS(func, name, KF_TRUSTED_ARGS) XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC BTF_SET8_END(xdp_metadata_kfunc_ids) @@ -752,7 +752,7 @@ static const struct btf_kfunc_id_set xdp_metadata_kfunc_set = { }; BTF_ID_LIST(xdp_metadata_kfunc_ids_unsorted) -#define XDP_METADATA_KFUNC(name, str, _) BTF_ID(func, str) +#define XDP_METADATA_KFUNC(name, _, str, __) BTF_ID(func, str) XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index c1634b95c223..2943a151d4f1 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -38,11 +38,27 @@ enum netdev_xdp_act { NETDEV_XDP_ACT_MASK = 127, }; +/** + * enum netdev_xdp_rx_metadata + * @NETDEV_XDP_RX_METADATA_TIMESTAMP: Device is capable of exposing receive HW + * timestamp via bpf_xdp_metadata_rx_timestamp(). + * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet + * hash via bpf_xdp_metadata_rx_hash(). + */ +enum netdev_xdp_rx_metadata { + NETDEV_XDP_RX_METADATA_TIMESTAMP = 1, + NETDEV_XDP_RX_METADATA_HASH = 2, + + /* private: */ + NETDEV_XDP_RX_METADATA_MASK = 3, +}; + enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, NETDEV_A_DEV_XDP_FEATURES, NETDEV_A_DEV_XDP_ZC_MAX_SEGS, + NETDEV_A_DEV_XDP_RX_METADATA_FEATURES, __NETDEV_A_DEV_MAX, NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1) -- cgit From 3868ab0f192581eff978501a05f3dc2e01541d77 Mon Sep 17 00:00:00 2001 From: Aananth V Date: Thu, 14 Sep 2023 14:36:21 +0000 Subject: tcp: new TCP_INFO stats for RTO events The 2023 SIGCOMM paper "Improving Network Availability with Protective ReRoute" has indicated Linux TCP's RTO-triggered txhash rehashing can effectively reduce application disruption during outages. To better measure the efficacy of this feature, this patch adds three more detailed stats during RTO recovery and exports via TCP_INFO. Applications and monitoring systems can leverage this data to measure the network path diversity and end-to-end repair latency during network outages to improve their network infrastructure. The following counters are added to tcp_sock in order to track RTO events over the lifetime of a TCP socket. 1. u16 total_rto - Counts the total number of RTO timeouts. 2. u16 total_rto_recoveries - Counts the total number of RTO recoveries. 3. u32 total_rto_time - Counts the total time spent (ms) in RTO recoveries. (time spent in CA_Loss and CA_Recovery states) To compute total_rto_time, we add a new u32 rto_stamp field to tcp_sock. rto_stamp records the start timestamp (ms) of the last RTO recovery (CA_Loss). Corresponding fields are also added to the tcp_info struct. Signed-off-by: Aananth V Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 8 ++++++++ include/uapi/linux/tcp.h | 12 ++++++++++++ net/ipv4/tcp.c | 9 +++++++++ net/ipv4/tcp_input.c | 15 +++++++++++++++ net/ipv4/tcp_minisocks.c | 4 ++++ net/ipv4/tcp_timer.c | 17 +++++++++++++++-- 6 files changed, 63 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 44d946161d4a..e15452df9804 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -377,6 +377,14 @@ struct tcp_sock { * Total data bytes retransmitted */ u32 total_retrans; /* Total retransmits for entire connection */ + u32 rto_stamp; /* Start time (ms) of last CA_Loss recovery */ + u16 total_rto; /* Total number of RTO timeouts, including + * SYN/SYN-ACK and recurring timeouts. + */ + u16 total_rto_recoveries; /* Total number of RTO recoveries, + * including any unfinished recovery. + */ + u32 total_rto_time; /* ms spent in (completed) RTO recoveries. */ u32 urg_seq; /* Seq of received urgent pointer */ unsigned int keepalive_time; /* time before keep alive takes place */ diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 879eeb0a084b..d1d08da6331a 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -289,6 +289,18 @@ struct tcp_info { */ __u32 tcpi_rehash; /* PLB or timeout triggered rehash attempts */ + + __u16 tcpi_total_rto; /* Total number of RTO timeouts, including + * SYN/SYN-ACK and recurring timeouts. + */ + __u16 tcpi_total_rto_recoveries; /* Total number of RTO + * recoveries, including any + * unfinished recovery. + */ + __u32 tcpi_total_rto_time; /* Total time spent in RTO recoveries + * in milliseconds, including any + * unfinished recovery. + */ }; /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0c3040a63ebd..69b8d7073708 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3818,6 +3818,15 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_rcv_wnd = tp->rcv_wnd; info->tcpi_rehash = tp->plb_rehash + tp->timeout_rehash; info->tcpi_fastopen_client_fail = tp->fastopen_client_fail; + + info->tcpi_total_rto = tp->total_rto; + info->tcpi_total_rto_recoveries = tp->total_rto_recoveries; + info->tcpi_total_rto_time = tp->total_rto_time; + if (tp->rto_stamp) { + info->tcpi_total_rto_time += tcp_time_stamp_raw() - + tp->rto_stamp; + } + unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8d2c91703158..584825ddd0a0 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2088,6 +2088,10 @@ void tcp_clear_retrans(struct tcp_sock *tp) tp->undo_marker = 0; tp->undo_retrans = -1; tp->sacked_out = 0; + tp->rto_stamp = 0; + tp->total_rto = 0; + tp->total_rto_recoveries = 0; + tp->total_rto_time = 0; } static inline void tcp_init_undo(struct tcp_sock *tp) @@ -2825,6 +2829,14 @@ void tcp_enter_recovery(struct sock *sk, bool ece_ack) tcp_set_ca_state(sk, TCP_CA_Recovery); } +static void tcp_update_rto_time(struct tcp_sock *tp) +{ + if (tp->rto_stamp) { + tp->total_rto_time += tcp_time_stamp(tp) - tp->rto_stamp; + tp->rto_stamp = 0; + } +} + /* Process an ACK in CA_Loss state. Move to CA_Open if lost data are * recovered or spurious. Otherwise retransmits more on partial ACKs. */ @@ -3029,6 +3041,8 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, break; case TCP_CA_Loss: tcp_process_loss(sk, flag, num_dupack, rexmit); + if (icsk->icsk_ca_state != TCP_CA_Loss) + tcp_update_rto_time(tp); tcp_identify_packet_loss(sk, ack_flag); if (!(icsk->icsk_ca_state == TCP_CA_Open || (*ack_flag & FLAG_LOST_RETRANS))) @@ -6454,6 +6468,7 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) tcp_try_undo_recovery(sk); /* Reset rtx states to prevent spurious retransmits_timed_out() */ + tcp_update_rto_time(tp); tp->retrans_stamp = 0; inet_csk(sk)->icsk_retransmits = 0; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index b98d476f1594..eee8ab1bfa0e 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -565,6 +565,10 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->undo_marker = treq->snt_isn; newtp->retrans_stamp = div_u64(treq->snt_synack, USEC_PER_SEC / TCP_TS_HZ); + newtp->total_rto = req->num_timeout; + newtp->total_rto_recoveries = 1; + newtp->total_rto_time = tcp_time_stamp_raw() - + newtp->retrans_stamp; } newtp->tsoffset = treq->ts_off; #ifdef CONFIG_TCP_MD5SIG diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index d7d64682b068..3f61c6a70a1f 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -415,6 +415,19 @@ abort: tcp_write_err(sk); } } +static void tcp_update_rto_stats(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + + if (!icsk->icsk_retransmits) { + tp->total_rto_recoveries++; + tp->rto_stamp = tcp_time_stamp(tp); + } + icsk->icsk_retransmits++; + tp->total_rto++; +} + /* * Timer for Fast Open socket to retransmit SYNACK. Note that the * sk here is the child socket, not the parent (listener) socket. @@ -447,7 +460,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) */ inet_rtx_syn_ack(sk, req); req->num_timeout++; - icsk->icsk_retransmits++; + tcp_update_rto_stats(sk); if (!tp->retrans_stamp) tp->retrans_stamp = tcp_time_stamp(tp); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, @@ -575,7 +588,7 @@ void tcp_retransmit_timer(struct sock *sk) tcp_enter_loss(sk); - icsk->icsk_retransmits++; + tcp_update_rto_stats(sk); if (tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1) > 0) { /* Retransmission failed because of local congestion, * Let senders fight for local resources conservatively. -- cgit From 3badff3a25d815e915d89565a0c82dec608a8d2b Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Wed, 13 Sep 2023 21:49:36 +0100 Subject: dpll: spec: Add Netlink spec in YAML Add a protocol spec for DPLL. Add code generated from the spec. Signed-off-by: Jakub Kicinski Signed-off-by: Michal Michalik Signed-off-by: Vadim Fedorenko Signed-off-by: Arkadiusz Kubalewski Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- Documentation/netlink/specs/dpll.yaml | 488 ++++++++++++++++++++++++++++++++++ drivers/dpll/dpll_nl.c | 162 +++++++++++ drivers/dpll/dpll_nl.h | 51 ++++ include/uapi/linux/dpll.h | 201 ++++++++++++++ 4 files changed, 902 insertions(+) create mode 100644 Documentation/netlink/specs/dpll.yaml create mode 100644 drivers/dpll/dpll_nl.c create mode 100644 drivers/dpll/dpll_nl.h create mode 100644 include/uapi/linux/dpll.h (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml new file mode 100644 index 000000000000..8b86b28b47a6 --- /dev/null +++ b/Documentation/netlink/specs/dpll.yaml @@ -0,0 +1,488 @@ +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) + +name: dpll + +doc: DPLL subsystem. + +definitions: + - + type: enum + name: mode + doc: | + working modes a dpll can support, differentiates if and how dpll selects + one of its inputs to syntonize with it, valid values for DPLL_A_MODE + attribute + entries: + - + name: manual + doc: input can be only selected by sending a request to dpll + value: 1 + - + name: automatic + doc: highest prio input pin auto selected by dpll + render-max: true + - + type: enum + name: lock-status + doc: | + provides information of dpll device lock status, valid values for + DPLL_A_LOCK_STATUS attribute + entries: + - + name: unlocked + doc: | + dpll was not yet locked to any valid input (or forced by setting + DPLL_A_MODE to DPLL_MODE_DETACHED) + value: 1 + - + name: locked + doc: | + dpll is locked to a valid signal, but no holdover available + - + name: locked-ho-acq + doc: | + dpll is locked and holdover acquired + - + name: holdover + doc: | + dpll is in holdover state - lost a valid lock or was forced + by disconnecting all the pins (latter possible only + when dpll lock-state was already DPLL_LOCK_STATUS_LOCKED_HO_ACQ, + if dpll lock-state was not DPLL_LOCK_STATUS_LOCKED_HO_ACQ, the + dpll's lock-state shall remain DPLL_LOCK_STATUS_UNLOCKED) + render-max: true + - + type: const + name: temp-divider + value: 1000 + doc: | + temperature divider allowing userspace to calculate the + temperature as float with three digit decimal precision. + Value of (DPLL_A_TEMP / DPLL_TEMP_DIVIDER) is integer part of + temperature value. + Value of (DPLL_A_TEMP % DPLL_TEMP_DIVIDER) is fractional part of + temperature value. + - + type: enum + name: type + doc: type of dpll, valid values for DPLL_A_TYPE attribute + entries: + - + name: pps + doc: dpll produces Pulse-Per-Second signal + value: 1 + - + name: eec + doc: dpll drives the Ethernet Equipment Clock + render-max: true + - + type: enum + name: pin-type + doc: | + defines possible types of a pin, valid values for DPLL_A_PIN_TYPE + attribute + entries: + - + name: mux + doc: aggregates another layer of selectable pins + value: 1 + - + name: ext + doc: external input + - + name: synce-eth-port + doc: ethernet port PHY's recovered clock + - + name: int-oscillator + doc: device internal oscillator + - + name: gnss + doc: GNSS recovered clock + render-max: true + - + type: enum + name: pin-direction + doc: | + defines possible direction of a pin, valid values for + DPLL_A_PIN_DIRECTION attribute + entries: + - + name: input + doc: pin used as a input of a signal + value: 1 + - + name: output + doc: pin used to output the signal + render-max: true + - + type: const + name: pin-frequency-1-hz + value: 1 + - + type: const + name: pin-frequency-10-khz + value: 10000 + - + type: const + name: pin-frequency-77_5-khz + value: 77500 + - + type: const + name: pin-frequency-10-mhz + value: 10000000 + - + type: enum + name: pin-state + doc: | + defines possible states of a pin, valid values for + DPLL_A_PIN_STATE attribute + entries: + - + name: connected + doc: pin connected, active input of phase locked loop + value: 1 + - + name: disconnected + doc: pin disconnected, not considered as a valid input + - + name: selectable + doc: pin enabled for automatic input selection + render-max: true + - + type: flags + name: pin-capabilities + doc: | + defines possible capabilities of a pin, valid flags on + DPLL_A_PIN_CAPABILITIES attribute + entries: + - + name: direction-can-change + doc: pin direction can be changed + - + name: priority-can-change + doc: pin priority can be changed + - + name: state-can-change + doc: pin state can be changed + +attribute-sets: + - + name: dpll + enum-name: dpll_a + attributes: + - + name: id + type: u32 + - + name: module-name + type: string + - + name: pad + type: pad + - + name: clock-id + type: u64 + - + name: mode + type: u32 + enum: mode + - + name: mode-supported + type: u32 + enum: mode + multi-attr: true + - + name: lock-status + type: u32 + enum: lock-status + - + name: temp + type: s32 + - + name: type + type: u32 + enum: type + - + name: pin + enum-name: dpll_a_pin + attributes: + - + name: id + type: u32 + - + name: parent-id + type: u32 + - + name: module-name + type: string + - + name: pad + type: pad + - + name: clock-id + type: u64 + - + name: board-label + type: string + - + name: panel-label + type: string + - + name: package-label + type: string + - + name: type + type: u32 + enum: pin-type + - + name: direction + type: u32 + enum: pin-direction + - + name: frequency + type: u64 + - + name: frequency-supported + type: nest + multi-attr: true + nested-attributes: frequency-range + - + name: frequency-min + type: u64 + - + name: frequency-max + type: u64 + - + name: prio + type: u32 + - + name: state + type: u32 + enum: pin-state + - + name: capabilities + type: u32 + - + name: parent-device + type: nest + multi-attr: true + nested-attributes: pin-parent-device + - + name: parent-pin + type: nest + multi-attr: true + nested-attributes: pin-parent-pin + - + name: pin-parent-device + subset-of: pin + attributes: + - + name: parent-id + type: u32 + - + name: direction + type: u32 + - + name: prio + type: u32 + - + name: state + type: u32 + - + name: pin-parent-pin + subset-of: pin + attributes: + - + name: parent-id + type: u32 + - + name: state + type: u32 + - + name: frequency-range + subset-of: pin + attributes: + - + name: frequency-min + type: u64 + - + name: frequency-max + type: u64 + +operations: + enum-name: dpll_cmd + list: + - + name: device-id-get + doc: | + Get id of dpll device that matches given attributes + attribute-set: dpll + flags: [ admin-perm ] + + do: + pre: dpll-lock-doit + post: dpll-unlock-doit + request: + attributes: + - module-name + - clock-id + - type + reply: + attributes: + - id + + - + name: device-get + doc: | + Get list of DPLL devices (dump) or attributes of a single dpll device + attribute-set: dpll + flags: [ admin-perm ] + + do: + pre: dpll-pre-doit + post: dpll-post-doit + request: + attributes: + - id + reply: &dev-attrs + attributes: + - id + - module-name + - mode + - mode-supported + - lock-status + - temp + - clock-id + - type + + dump: + pre: dpll-lock-dumpit + post: dpll-unlock-dumpit + reply: *dev-attrs + + - + name: device-set + doc: Set attributes for a DPLL device + attribute-set: dpll + flags: [ admin-perm ] + + do: + pre: dpll-pre-doit + post: dpll-post-doit + request: + attributes: + - id + - + name: device-create-ntf + doc: Notification about device appearing + notify: device-get + mcgrp: monitor + - + name: device-delete-ntf + doc: Notification about device disappearing + notify: device-get + mcgrp: monitor + - + name: device-change-ntf + doc: Notification about device configuration being changed + notify: device-get + mcgrp: monitor + - + name: pin-id-get + doc: | + Get id of a pin that matches given attributes + attribute-set: pin + flags: [ admin-perm ] + + do: + pre: dpll-lock-doit + post: dpll-unlock-doit + request: + attributes: + - module-name + - clock-id + - board-label + - panel-label + - package-label + - type + reply: + attributes: + - id + + - + name: pin-get + doc: | + Get list of pins and its attributes. + - dump request without any attributes given - list all the pins in the + system + - dump request with target dpll - list all the pins registered with + a given dpll device + - do request with target dpll and target pin - single pin attributes + attribute-set: pin + flags: [ admin-perm ] + + do: + pre: dpll-pin-pre-doit + post: dpll-pin-post-doit + request: + attributes: + - id + reply: &pin-attrs + attributes: + - id + - board-label + - panel-label + - package-label + - type + - frequency + - frequency-supported + - capabilities + - parent-device + - parent-pin + + dump: + pre: dpll-lock-dumpit + post: dpll-unlock-dumpit + request: + attributes: + - id + reply: *pin-attrs + + - + name: pin-set + doc: Set attributes of a target pin + attribute-set: pin + flags: [ admin-perm ] + + do: + pre: dpll-pin-pre-doit + post: dpll-pin-post-doit + request: + attributes: + - id + - frequency + - direction + - prio + - state + - parent-device + - parent-pin + - + name: pin-create-ntf + doc: Notification about pin appearing + notify: pin-get + mcgrp: monitor + - + name: pin-delete-ntf + doc: Notification about pin disappearing + notify: pin-get + mcgrp: monitor + - + name: pin-change-ntf + doc: Notification about pin configuration being changed + notify: pin-get + mcgrp: monitor + +mcast-groups: + list: + - + name: monitor diff --git a/drivers/dpll/dpll_nl.c b/drivers/dpll/dpll_nl.c new file mode 100644 index 000000000000..14064c8c783b --- /dev/null +++ b/drivers/dpll/dpll_nl.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/dpll.yaml */ +/* YNL-GEN kernel source */ + +#include +#include + +#include "dpll_nl.h" + +#include + +/* Common nested types */ +const struct nla_policy dpll_pin_parent_device_nl_policy[DPLL_A_PIN_STATE + 1] = { + [DPLL_A_PIN_PARENT_ID] = { .type = NLA_U32, }, + [DPLL_A_PIN_DIRECTION] = NLA_POLICY_RANGE(NLA_U32, 1, 2), + [DPLL_A_PIN_PRIO] = { .type = NLA_U32, }, + [DPLL_A_PIN_STATE] = NLA_POLICY_RANGE(NLA_U32, 1, 3), +}; + +const struct nla_policy dpll_pin_parent_pin_nl_policy[DPLL_A_PIN_STATE + 1] = { + [DPLL_A_PIN_PARENT_ID] = { .type = NLA_U32, }, + [DPLL_A_PIN_STATE] = NLA_POLICY_RANGE(NLA_U32, 1, 3), +}; + +/* DPLL_CMD_DEVICE_ID_GET - do */ +static const struct nla_policy dpll_device_id_get_nl_policy[DPLL_A_TYPE + 1] = { + [DPLL_A_MODULE_NAME] = { .type = NLA_NUL_STRING, }, + [DPLL_A_CLOCK_ID] = { .type = NLA_U64, }, + [DPLL_A_TYPE] = NLA_POLICY_RANGE(NLA_U32, 1, 2), +}; + +/* DPLL_CMD_DEVICE_GET - do */ +static const struct nla_policy dpll_device_get_nl_policy[DPLL_A_ID + 1] = { + [DPLL_A_ID] = { .type = NLA_U32, }, +}; + +/* DPLL_CMD_DEVICE_SET - do */ +static const struct nla_policy dpll_device_set_nl_policy[DPLL_A_ID + 1] = { + [DPLL_A_ID] = { .type = NLA_U32, }, +}; + +/* DPLL_CMD_PIN_ID_GET - do */ +static const struct nla_policy dpll_pin_id_get_nl_policy[DPLL_A_PIN_TYPE + 1] = { + [DPLL_A_PIN_MODULE_NAME] = { .type = NLA_NUL_STRING, }, + [DPLL_A_PIN_CLOCK_ID] = { .type = NLA_U64, }, + [DPLL_A_PIN_BOARD_LABEL] = { .type = NLA_NUL_STRING, }, + [DPLL_A_PIN_PANEL_LABEL] = { .type = NLA_NUL_STRING, }, + [DPLL_A_PIN_PACKAGE_LABEL] = { .type = NLA_NUL_STRING, }, + [DPLL_A_PIN_TYPE] = NLA_POLICY_RANGE(NLA_U32, 1, 5), +}; + +/* DPLL_CMD_PIN_GET - do */ +static const struct nla_policy dpll_pin_get_do_nl_policy[DPLL_A_PIN_ID + 1] = { + [DPLL_A_PIN_ID] = { .type = NLA_U32, }, +}; + +/* DPLL_CMD_PIN_GET - dump */ +static const struct nla_policy dpll_pin_get_dump_nl_policy[DPLL_A_PIN_ID + 1] = { + [DPLL_A_PIN_ID] = { .type = NLA_U32, }, +}; + +/* DPLL_CMD_PIN_SET - do */ +static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_PARENT_PIN + 1] = { + [DPLL_A_PIN_ID] = { .type = NLA_U32, }, + [DPLL_A_PIN_FREQUENCY] = { .type = NLA_U64, }, + [DPLL_A_PIN_DIRECTION] = NLA_POLICY_RANGE(NLA_U32, 1, 2), + [DPLL_A_PIN_PRIO] = { .type = NLA_U32, }, + [DPLL_A_PIN_STATE] = NLA_POLICY_RANGE(NLA_U32, 1, 3), + [DPLL_A_PIN_PARENT_DEVICE] = NLA_POLICY_NESTED(dpll_pin_parent_device_nl_policy), + [DPLL_A_PIN_PARENT_PIN] = NLA_POLICY_NESTED(dpll_pin_parent_pin_nl_policy), +}; + +/* Ops table for dpll */ +static const struct genl_split_ops dpll_nl_ops[] = { + { + .cmd = DPLL_CMD_DEVICE_ID_GET, + .pre_doit = dpll_lock_doit, + .doit = dpll_nl_device_id_get_doit, + .post_doit = dpll_unlock_doit, + .policy = dpll_device_id_get_nl_policy, + .maxattr = DPLL_A_TYPE, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DPLL_CMD_DEVICE_GET, + .pre_doit = dpll_pre_doit, + .doit = dpll_nl_device_get_doit, + .post_doit = dpll_post_doit, + .policy = dpll_device_get_nl_policy, + .maxattr = DPLL_A_ID, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DPLL_CMD_DEVICE_GET, + .start = dpll_lock_dumpit, + .dumpit = dpll_nl_device_get_dumpit, + .done = dpll_unlock_dumpit, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP, + }, + { + .cmd = DPLL_CMD_DEVICE_SET, + .pre_doit = dpll_pre_doit, + .doit = dpll_nl_device_set_doit, + .post_doit = dpll_post_doit, + .policy = dpll_device_set_nl_policy, + .maxattr = DPLL_A_ID, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DPLL_CMD_PIN_ID_GET, + .pre_doit = dpll_lock_doit, + .doit = dpll_nl_pin_id_get_doit, + .post_doit = dpll_unlock_doit, + .policy = dpll_pin_id_get_nl_policy, + .maxattr = DPLL_A_PIN_TYPE, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DPLL_CMD_PIN_GET, + .pre_doit = dpll_pin_pre_doit, + .doit = dpll_nl_pin_get_doit, + .post_doit = dpll_pin_post_doit, + .policy = dpll_pin_get_do_nl_policy, + .maxattr = DPLL_A_PIN_ID, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DPLL_CMD_PIN_GET, + .start = dpll_lock_dumpit, + .dumpit = dpll_nl_pin_get_dumpit, + .done = dpll_unlock_dumpit, + .policy = dpll_pin_get_dump_nl_policy, + .maxattr = DPLL_A_PIN_ID, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP, + }, + { + .cmd = DPLL_CMD_PIN_SET, + .pre_doit = dpll_pin_pre_doit, + .doit = dpll_nl_pin_set_doit, + .post_doit = dpll_pin_post_doit, + .policy = dpll_pin_set_nl_policy, + .maxattr = DPLL_A_PIN_PARENT_PIN, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, +}; + +static const struct genl_multicast_group dpll_nl_mcgrps[] = { + [DPLL_NLGRP_MONITOR] = { "monitor", }, +}; + +struct genl_family dpll_nl_family __ro_after_init = { + .name = DPLL_FAMILY_NAME, + .version = DPLL_FAMILY_VERSION, + .netnsok = true, + .parallel_ops = true, + .module = THIS_MODULE, + .split_ops = dpll_nl_ops, + .n_split_ops = ARRAY_SIZE(dpll_nl_ops), + .mcgrps = dpll_nl_mcgrps, + .n_mcgrps = ARRAY_SIZE(dpll_nl_mcgrps), +}; diff --git a/drivers/dpll/dpll_nl.h b/drivers/dpll/dpll_nl.h new file mode 100644 index 000000000000..1f67aaed4742 --- /dev/null +++ b/drivers/dpll/dpll_nl.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/dpll.yaml */ +/* YNL-GEN kernel header */ + +#ifndef _LINUX_DPLL_GEN_H +#define _LINUX_DPLL_GEN_H + +#include +#include + +#include + +/* Common nested types */ +extern const struct nla_policy dpll_pin_parent_device_nl_policy[DPLL_A_PIN_STATE + 1]; +extern const struct nla_policy dpll_pin_parent_pin_nl_policy[DPLL_A_PIN_STATE + 1]; + +int dpll_lock_doit(const struct genl_split_ops *ops, struct sk_buff *skb, + struct genl_info *info); +int dpll_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, + struct genl_info *info); +int dpll_pin_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, + struct genl_info *info); +void +dpll_unlock_doit(const struct genl_split_ops *ops, struct sk_buff *skb, + struct genl_info *info); +void +dpll_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, + struct genl_info *info); +void +dpll_pin_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, + struct genl_info *info); +int dpll_lock_dumpit(struct netlink_callback *cb); +int dpll_unlock_dumpit(struct netlink_callback *cb); + +int dpll_nl_device_id_get_doit(struct sk_buff *skb, struct genl_info *info); +int dpll_nl_device_get_doit(struct sk_buff *skb, struct genl_info *info); +int dpll_nl_device_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int dpll_nl_device_set_doit(struct sk_buff *skb, struct genl_info *info); +int dpll_nl_pin_id_get_doit(struct sk_buff *skb, struct genl_info *info); +int dpll_nl_pin_get_doit(struct sk_buff *skb, struct genl_info *info); +int dpll_nl_pin_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int dpll_nl_pin_set_doit(struct sk_buff *skb, struct genl_info *info); + +enum { + DPLL_NLGRP_MONITOR, +}; + +extern struct genl_family dpll_nl_family; + +#endif /* _LINUX_DPLL_GEN_H */ diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h new file mode 100644 index 000000000000..20ef0718f8dc --- /dev/null +++ b/include/uapi/linux/dpll.h @@ -0,0 +1,201 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/dpll.yaml */ +/* YNL-GEN uapi header */ + +#ifndef _UAPI_LINUX_DPLL_H +#define _UAPI_LINUX_DPLL_H + +#define DPLL_FAMILY_NAME "dpll" +#define DPLL_FAMILY_VERSION 1 + +/** + * enum dpll_mode - working modes a dpll can support, differentiates if and how + * dpll selects one of its inputs to syntonize with it, valid values for + * DPLL_A_MODE attribute + * @DPLL_MODE_MANUAL: input can be only selected by sending a request to dpll + * @DPLL_MODE_AUTOMATIC: highest prio input pin auto selected by dpll + */ +enum dpll_mode { + DPLL_MODE_MANUAL = 1, + DPLL_MODE_AUTOMATIC, + + /* private: */ + __DPLL_MODE_MAX, + DPLL_MODE_MAX = (__DPLL_MODE_MAX - 1) +}; + +/** + * enum dpll_lock_status - provides information of dpll device lock status, + * valid values for DPLL_A_LOCK_STATUS attribute + * @DPLL_LOCK_STATUS_UNLOCKED: dpll was not yet locked to any valid input (or + * forced by setting DPLL_A_MODE to DPLL_MODE_DETACHED) + * @DPLL_LOCK_STATUS_LOCKED: dpll is locked to a valid signal, but no holdover + * available + * @DPLL_LOCK_STATUS_LOCKED_HO_ACQ: dpll is locked and holdover acquired + * @DPLL_LOCK_STATUS_HOLDOVER: dpll is in holdover state - lost a valid lock or + * was forced by disconnecting all the pins (latter possible only when dpll + * lock-state was already DPLL_LOCK_STATUS_LOCKED_HO_ACQ, if dpll lock-state + * was not DPLL_LOCK_STATUS_LOCKED_HO_ACQ, the dpll's lock-state shall remain + * DPLL_LOCK_STATUS_UNLOCKED) + */ +enum dpll_lock_status { + DPLL_LOCK_STATUS_UNLOCKED = 1, + DPLL_LOCK_STATUS_LOCKED, + DPLL_LOCK_STATUS_LOCKED_HO_ACQ, + DPLL_LOCK_STATUS_HOLDOVER, + + /* private: */ + __DPLL_LOCK_STATUS_MAX, + DPLL_LOCK_STATUS_MAX = (__DPLL_LOCK_STATUS_MAX - 1) +}; + +#define DPLL_TEMP_DIVIDER 1000 + +/** + * enum dpll_type - type of dpll, valid values for DPLL_A_TYPE attribute + * @DPLL_TYPE_PPS: dpll produces Pulse-Per-Second signal + * @DPLL_TYPE_EEC: dpll drives the Ethernet Equipment Clock + */ +enum dpll_type { + DPLL_TYPE_PPS = 1, + DPLL_TYPE_EEC, + + /* private: */ + __DPLL_TYPE_MAX, + DPLL_TYPE_MAX = (__DPLL_TYPE_MAX - 1) +}; + +/** + * enum dpll_pin_type - defines possible types of a pin, valid values for + * DPLL_A_PIN_TYPE attribute + * @DPLL_PIN_TYPE_MUX: aggregates another layer of selectable pins + * @DPLL_PIN_TYPE_EXT: external input + * @DPLL_PIN_TYPE_SYNCE_ETH_PORT: ethernet port PHY's recovered clock + * @DPLL_PIN_TYPE_INT_OSCILLATOR: device internal oscillator + * @DPLL_PIN_TYPE_GNSS: GNSS recovered clock + */ +enum dpll_pin_type { + DPLL_PIN_TYPE_MUX = 1, + DPLL_PIN_TYPE_EXT, + DPLL_PIN_TYPE_SYNCE_ETH_PORT, + DPLL_PIN_TYPE_INT_OSCILLATOR, + DPLL_PIN_TYPE_GNSS, + + /* private: */ + __DPLL_PIN_TYPE_MAX, + DPLL_PIN_TYPE_MAX = (__DPLL_PIN_TYPE_MAX - 1) +}; + +/** + * enum dpll_pin_direction - defines possible direction of a pin, valid values + * for DPLL_A_PIN_DIRECTION attribute + * @DPLL_PIN_DIRECTION_INPUT: pin used as a input of a signal + * @DPLL_PIN_DIRECTION_OUTPUT: pin used to output the signal + */ +enum dpll_pin_direction { + DPLL_PIN_DIRECTION_INPUT = 1, + DPLL_PIN_DIRECTION_OUTPUT, + + /* private: */ + __DPLL_PIN_DIRECTION_MAX, + DPLL_PIN_DIRECTION_MAX = (__DPLL_PIN_DIRECTION_MAX - 1) +}; + +#define DPLL_PIN_FREQUENCY_1_HZ 1 +#define DPLL_PIN_FREQUENCY_10_KHZ 10000 +#define DPLL_PIN_FREQUENCY_77_5_KHZ 77500 +#define DPLL_PIN_FREQUENCY_10_MHZ 10000000 + +/** + * enum dpll_pin_state - defines possible states of a pin, valid values for + * DPLL_A_PIN_STATE attribute + * @DPLL_PIN_STATE_CONNECTED: pin connected, active input of phase locked loop + * @DPLL_PIN_STATE_DISCONNECTED: pin disconnected, not considered as a valid + * input + * @DPLL_PIN_STATE_SELECTABLE: pin enabled for automatic input selection + */ +enum dpll_pin_state { + DPLL_PIN_STATE_CONNECTED = 1, + DPLL_PIN_STATE_DISCONNECTED, + DPLL_PIN_STATE_SELECTABLE, + + /* private: */ + __DPLL_PIN_STATE_MAX, + DPLL_PIN_STATE_MAX = (__DPLL_PIN_STATE_MAX - 1) +}; + +/** + * enum dpll_pin_capabilities - defines possible capabilities of a pin, valid + * flags on DPLL_A_PIN_CAPABILITIES attribute + * @DPLL_PIN_CAPABILITIES_DIRECTION_CAN_CHANGE: pin direction can be changed + * @DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE: pin priority can be changed + * @DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE: pin state can be changed + */ +enum dpll_pin_capabilities { + DPLL_PIN_CAPABILITIES_DIRECTION_CAN_CHANGE = 1, + DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE = 2, + DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE = 4, +}; + +enum dpll_a { + DPLL_A_ID = 1, + DPLL_A_MODULE_NAME, + DPLL_A_PAD, + DPLL_A_CLOCK_ID, + DPLL_A_MODE, + DPLL_A_MODE_SUPPORTED, + DPLL_A_LOCK_STATUS, + DPLL_A_TEMP, + DPLL_A_TYPE, + + __DPLL_A_MAX, + DPLL_A_MAX = (__DPLL_A_MAX - 1) +}; + +enum dpll_a_pin { + DPLL_A_PIN_ID = 1, + DPLL_A_PIN_PARENT_ID, + DPLL_A_PIN_MODULE_NAME, + DPLL_A_PIN_PAD, + DPLL_A_PIN_CLOCK_ID, + DPLL_A_PIN_BOARD_LABEL, + DPLL_A_PIN_PANEL_LABEL, + DPLL_A_PIN_PACKAGE_LABEL, + DPLL_A_PIN_TYPE, + DPLL_A_PIN_DIRECTION, + DPLL_A_PIN_FREQUENCY, + DPLL_A_PIN_FREQUENCY_SUPPORTED, + DPLL_A_PIN_FREQUENCY_MIN, + DPLL_A_PIN_FREQUENCY_MAX, + DPLL_A_PIN_PRIO, + DPLL_A_PIN_STATE, + DPLL_A_PIN_CAPABILITIES, + DPLL_A_PIN_PARENT_DEVICE, + DPLL_A_PIN_PARENT_PIN, + + __DPLL_A_PIN_MAX, + DPLL_A_PIN_MAX = (__DPLL_A_PIN_MAX - 1) +}; + +enum dpll_cmd { + DPLL_CMD_DEVICE_ID_GET = 1, + DPLL_CMD_DEVICE_GET, + DPLL_CMD_DEVICE_SET, + DPLL_CMD_DEVICE_CREATE_NTF, + DPLL_CMD_DEVICE_DELETE_NTF, + DPLL_CMD_DEVICE_CHANGE_NTF, + DPLL_CMD_PIN_ID_GET, + DPLL_CMD_PIN_GET, + DPLL_CMD_PIN_SET, + DPLL_CMD_PIN_CREATE_NTF, + DPLL_CMD_PIN_DELETE_NTF, + DPLL_CMD_PIN_CHANGE_NTF, + + __DPLL_CMD_MAX, + DPLL_CMD_MAX = (__DPLL_CMD_MAX - 1) +}; + +#define DPLL_MCGRP_MONITOR "monitor" + +#endif /* _UAPI_LINUX_DPLL_H */ -- cgit From 5f18426928800c59fb0f9bc8fb0c182bb6f5ee24 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 13 Sep 2023 21:49:39 +0100 Subject: netdev: expose DPLL pin handle for netdevice In case netdevice represents a SyncE port, the user needs to understand the connection between netdevice and associated DPLL pin. There might me multiple netdevices pointing to the same pin, in case of VF/SF implementation. Add a IFLA Netlink attribute to nest the DPLL pin handle, similar to how it is implemented for devlink port. Add a struct dpll_pin pointer to netdev and protect access to it by RTNL. Expose netdev_dpll_pin_set() and netdev_dpll_pin_clear() helpers to the drivers so they can set/clear the DPLL pin relationship to netdev. Note that during the lifetime of struct dpll_pin the pin handle does not change. Therefore it is save to access it lockless. It is drivers responsibility to call netdev_dpll_pin_clear() before dpll_pin_put(). Signed-off-by: Jiri Pirko Signed-off-by: Arkadiusz Kubalewski Signed-off-by: Vadim Fedorenko Signed-off-by: David S. Miller --- drivers/dpll/dpll_netlink.c | 16 ++++++++++++++-- include/linux/dpll.h | 15 +++++++++++++++ include/linux/netdevice.h | 21 +++++++++++++++++++++ include/uapi/linux/if_link.h | 2 +- net/core/dev.c | 22 ++++++++++++++++++++++ net/core/rtnetlink.c | 36 ++++++++++++++++++++++++++++++++++++ 6 files changed, 109 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index 9464a6865977..764437a0661b 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -47,6 +47,18 @@ dpll_msg_add_dev_parent_handle(struct sk_buff *msg, u32 id) return 0; } +/** + * dpll_msg_pin_handle_size - get size of pin handle attribute for given pin + * @pin: pin pointer + * + * Return: byte size of pin handle attribute for given pin. + */ +size_t dpll_msg_pin_handle_size(struct dpll_pin *pin) +{ + return pin ? nla_total_size(4) : 0; /* DPLL_A_PIN_ID */ +} +EXPORT_SYMBOL_GPL(dpll_msg_pin_handle_size); + /** * dpll_msg_add_pin_handle - attach pin handle attribute to a given message * @msg: pointer to sk_buff message to attach a pin handle @@ -56,8 +68,7 @@ dpll_msg_add_dev_parent_handle(struct sk_buff *msg, u32 id) * * 0 - success * * -EMSGSIZE - no space in message to attach pin handle */ -static int -dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin) +int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin) { if (!pin) return 0; @@ -65,6 +76,7 @@ dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin) return -EMSGSIZE; return 0; } +EXPORT_SYMBOL_GPL(dpll_msg_add_pin_handle); static int dpll_msg_add_mode(struct sk_buff *msg, struct dpll_device *dpll, diff --git a/include/linux/dpll.h b/include/linux/dpll.h index 2202310c10cd..bbc480cd2932 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -101,6 +101,21 @@ struct dpll_pin_properties { struct dpll_pin_frequency *freq_supported; }; +#if IS_ENABLED(CONFIG_DPLL) +size_t dpll_msg_pin_handle_size(struct dpll_pin *pin); +int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin); +#else +static inline size_t dpll_msg_pin_handle_size(struct dpll_pin *pin) +{ + return 0; +} + +static inline int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin) +{ + return 0; +} +#endif + struct dpll_device * dpll_device_get(u64 clock_id, u32 dev_driver_id, struct module *module); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0896aaa91dd7..db3d8429d50d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -79,6 +79,8 @@ struct xdp_buff; struct xdp_frame; struct xdp_metadata_ops; struct xdp_md; +/* DPLL specific */ +struct dpll_pin; typedef u32 xdp_features_t; @@ -2049,6 +2051,9 @@ enum netdev_ml_priv_type { * SET_NETDEV_DEVLINK_PORT macro. This pointer is static * during the time netdevice is registered. * + * @dpll_pin: Pointer to the SyncE source pin of a DPLL subsystem, + * where the clock is recovered. + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -2405,6 +2410,10 @@ struct net_device { struct rtnl_hw_stats64 *offload_xstats_l3; struct devlink_port *devlink_port; + +#if IS_ENABLED(CONFIG_DPLL) + struct dpll_pin *dpll_pin; +#endif }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -3940,6 +3949,18 @@ int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name); int dev_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse); bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); +void netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin); +void netdev_dpll_pin_clear(struct net_device *dev); + +static inline struct dpll_pin *netdev_dpll_pin(const struct net_device *dev) +{ +#if IS_ENABLED(CONFIG_DPLL) + return dev->dpll_pin; +#else + return NULL; +#endif +} + struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index ce3117df9cec..fac351a93aed 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -376,7 +376,7 @@ enum { IFLA_GSO_IPV4_MAX_SIZE, IFLA_GRO_IPV4_MAX_SIZE, - + IFLA_DPLL_PIN, __IFLA_MAX }; diff --git a/net/core/dev.c b/net/core/dev.c index ccff2b6ef958..cc03a5758d2d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9023,6 +9023,28 @@ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b) } EXPORT_SYMBOL(netdev_port_same_parent_id); +static void netdev_dpll_pin_assign(struct net_device *dev, struct dpll_pin *dpll_pin) +{ +#if IS_ENABLED(CONFIG_DPLL) + rtnl_lock(); + dev->dpll_pin = dpll_pin; + rtnl_unlock(); +#endif +} + +void netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin) +{ + WARN_ON(!dpll_pin); + netdev_dpll_pin_assign(dev, dpll_pin); +} +EXPORT_SYMBOL(netdev_dpll_pin_set); + +void netdev_dpll_pin_clear(struct net_device *dev) +{ + netdev_dpll_pin_assign(dev, NULL); +} +EXPORT_SYMBOL(netdev_dpll_pin_clear); + /** * dev_change_proto_down - set carrier according to proto_down. * diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 4a2ec33bfb51..7452a6d190c5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -57,6 +57,7 @@ #if IS_ENABLED(CONFIG_IPV6) #include #endif +#include #include "dev.h" @@ -1055,6 +1056,15 @@ static size_t rtnl_devlink_port_size(const struct net_device *dev) return size; } +static size_t rtnl_dpll_pin_size(const struct net_device *dev) +{ + size_t size = nla_total_size(0); /* nest IFLA_DPLL_PIN */ + + size += dpll_msg_pin_handle_size(netdev_dpll_pin(dev)); + + return size; +} + static noinline size_t if_nlmsg_size(const struct net_device *dev, u32 ext_filter_mask) { @@ -1111,6 +1121,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + rtnl_prop_list_size(dev) + nla_total_size(MAX_ADDR_LEN) /* IFLA_PERM_ADDRESS */ + rtnl_devlink_port_size(dev) + + rtnl_dpll_pin_size(dev) + 0; } @@ -1774,6 +1785,28 @@ nest_cancel: return ret; } +static int rtnl_fill_dpll_pin(struct sk_buff *skb, + const struct net_device *dev) +{ + struct nlattr *dpll_pin_nest; + int ret; + + dpll_pin_nest = nla_nest_start(skb, IFLA_DPLL_PIN); + if (!dpll_pin_nest) + return -EMSGSIZE; + + ret = dpll_msg_add_pin_handle(skb, netdev_dpll_pin(dev)); + if (ret < 0) + goto nest_cancel; + + nla_nest_end(skb, dpll_pin_nest); + return 0; + +nest_cancel: + nla_nest_cancel(skb, dpll_pin_nest); + return ret; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct net *src_net, int type, u32 pid, u32 seq, u32 change, @@ -1916,6 +1949,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, if (rtnl_fill_devlink_port(skb, dev)) goto nla_put_failure; + if (rtnl_fill_dpll_pin(skb, dev)) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; -- cgit From 0b7a2721e36c11313f8b0f251a508d25a872cd28 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 13 Sep 2023 09:12:39 +0200 Subject: devlink: expose peer SF devlink instance Introduce a new helper devl_port_fn_devlink_set() to be used by driver assigning a devlink instance to the peer devlink port function. Expose this to user over new netlink attribute nested under port function nest to expose devlink handle related to the port function. This is particularly helpful for user to understand the relationship between devlink instances created for SFs and the port functions they belong to. Note that caller of devlink_port_notify() needs to hold devlink instance lock, put the assertion to devl_port_fn_devlink_set() to make this requirement explicit. Also note the limitations that only allow to make this assignment for registered objects. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 3 +++ include/uapi/linux/devlink.h | 1 + net/devlink/port.c | 51 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 55 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/devlink.h b/include/net/devlink.h index 29fd1b4ee654..2655ab6101ec 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -150,6 +150,7 @@ struct devlink_port { struct devlink_rate *devlink_rate; struct devlink_linecard *linecard; + u32 rel_index; }; struct devlink_port_new_attrs { @@ -1697,6 +1698,8 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller, u16 pf, u32 sf, bool external); +int devl_port_fn_devlink_set(struct devlink_port *devlink_port, + struct devlink *fn_devlink); struct devlink_rate * devl_rate_node_create(struct devlink *devlink, void *priv, char *node_name, struct devlink_rate *parent); diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 03875e078be8..cd4b82458d1b 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -680,6 +680,7 @@ enum devlink_port_function_attr { DEVLINK_PORT_FN_ATTR_STATE, /* u8 */ DEVLINK_PORT_FN_ATTR_OPSTATE, /* u8 */ DEVLINK_PORT_FN_ATTR_CAPS, /* bitfield32 */ + DEVLINK_PORT_FN_ATTR_DEVLINK, /* nested */ __DEVLINK_PORT_FUNCTION_ATTR_MAX, DEVLINK_PORT_FUNCTION_ATTR_MAX = __DEVLINK_PORT_FUNCTION_ATTR_MAX - 1 diff --git a/net/devlink/port.c b/net/devlink/port.c index 7b300a322ed9..4e9003242448 100644 --- a/net/devlink/port.c +++ b/net/devlink/port.c @@ -428,6 +428,13 @@ devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *por if (err) goto out; err = devlink_port_fn_state_fill(port, msg, extack, &msg_updated); + if (err) + goto out; + err = devlink_rel_devlink_handle_put(msg, port->devlink, + port->rel_index, + DEVLINK_PORT_FN_ATTR_DEVLINK, + &msg_updated); + out: if (err || !msg_updated) nla_nest_cancel(msg, function_attr); @@ -1392,6 +1399,50 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 contro } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set); +static void devlink_port_rel_notify_cb(struct devlink *devlink, u32 port_index) +{ + struct devlink_port *devlink_port; + + devlink_port = devlink_port_get_by_index(devlink, port_index); + if (!devlink_port) + return; + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); +} + +static void devlink_port_rel_cleanup_cb(struct devlink *devlink, u32 port_index, + u32 rel_index) +{ + struct devlink_port *devlink_port; + + devlink_port = devlink_port_get_by_index(devlink, port_index); + if (devlink_port && devlink_port->rel_index == rel_index) + devlink_port->rel_index = 0; +} + +/** + * devl_port_fn_devlink_set - Attach peer devlink + * instance to port function. + * @devlink_port: devlink port + * @fn_devlink: devlink instance to attach + */ +int devl_port_fn_devlink_set(struct devlink_port *devlink_port, + struct devlink *fn_devlink) +{ + ASSERT_DEVLINK_PORT_REGISTERED(devlink_port); + + if (WARN_ON(devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_SF || + devlink_port->attrs.pci_sf.external)) + return -EINVAL; + + return devlink_rel_nested_in_add(&devlink_port->rel_index, + devlink_port->devlink->index, + devlink_port->index, + devlink_port_rel_notify_cb, + devlink_port_rel_cleanup_cb, + fn_devlink); +} +EXPORT_SYMBOL_GPL(devl_port_fn_devlink_set); + /** * devlink_port_linecard_set - Link port with a linecard * -- cgit From ddd7f45c899f7524bdbe6a32fe4906cde8b07b9b Mon Sep 17 00:00:00 2001 From: Wen Gong Date: Thu, 14 Sep 2023 04:20:26 -0400 Subject: wifi: cfg80211: save power spectral density(psd) of regulatory rule 6 GHz regulatory domains introduces Power Spectral Density (PSD). The PSD value of the regulatory rule should be taken into effect for the ieee80211_channels falling into that particular regulatory rule. Save the values in the channel which has PSD value and add nl80211 attributes accordingly to handle it. Co-developed-by: Aditya Kumar Singh Signed-off-by: Aditya Kumar Singh Signed-off-by: Wen Gong Link: https://lore.kernel.org/r/20230914082026.3709-1-quic_wgong@quicinc.com [use hole in chan flags, reword docs] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 6 +++++- include/net/regulatory.h | 1 + include/uapi/linux/nl80211.h | 9 +++++++++ net/wireless/nl80211.c | 9 +++++++++ net/wireless/reg.c | 17 +++++++++++++++++ 5 files changed, 41 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 8fcfe1869424..9af714431b22 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -76,6 +76,8 @@ struct wiphy; * @IEEE80211_CHAN_DISABLED: This channel is disabled. * @IEEE80211_CHAN_NO_IR: do not initiate radiation, this includes * sending probe requests or beaconing. + * @IEEE80211_CHAN_PSD: Power spectral density (in dBm) is set for this + * channel. * @IEEE80211_CHAN_RADAR: Radar detection is required on this channel. * @IEEE80211_CHAN_NO_HT40PLUS: extension channel above this channel * is not permitted. @@ -119,7 +121,7 @@ struct wiphy; enum ieee80211_channel_flags { IEEE80211_CHAN_DISABLED = 1<<0, IEEE80211_CHAN_NO_IR = 1<<1, - /* hole at 1<<2 */ + IEEE80211_CHAN_PSD = 1<<2, IEEE80211_CHAN_RADAR = 1<<3, IEEE80211_CHAN_NO_HT40PLUS = 1<<4, IEEE80211_CHAN_NO_HT40MINUS = 1<<5, @@ -171,6 +173,7 @@ enum ieee80211_channel_flags { * on this channel. * @dfs_state_entered: timestamp (jiffies) when the dfs state was entered. * @dfs_cac_ms: DFS CAC time in milliseconds, this is valid for DFS channels. + * @psd: power spectral density (in dBm) */ struct ieee80211_channel { enum nl80211_band band; @@ -187,6 +190,7 @@ struct ieee80211_channel { enum nl80211_dfs_state dfs_state; unsigned long dfs_state_entered; unsigned int dfs_cac_ms; + s8 psd; }; /** diff --git a/include/net/regulatory.h b/include/net/regulatory.h index b2cb4a9eb04d..ebf9e028d1ef 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -213,6 +213,7 @@ struct ieee80211_reg_rule { u32 flags; u32 dfs_cac_ms; bool has_wmm; + s8 psd; }; struct ieee80211_regdomain { diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index f797ab7a6547..367e5fbc8930 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4215,6 +4215,8 @@ enum nl80211_wmm_rule { * as the primary or any of the secondary channels isn't possible * @NL80211_FREQUENCY_ATTR_NO_EHT: EHT operation is not allowed on this channel * in current regulatory domain. + * @NL80211_FREQUENCY_ATTR_PSD: Power spectral density (in dBm) that + * is allowed on this channel in current regulatory domain. * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number * currently defined * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use @@ -4253,6 +4255,7 @@ enum nl80211_frequency_attr { NL80211_FREQUENCY_ATTR_16MHZ, NL80211_FREQUENCY_ATTR_NO_320MHZ, NL80211_FREQUENCY_ATTR_NO_EHT, + NL80211_FREQUENCY_ATTR_PSD, /* keep last */ __NL80211_FREQUENCY_ATTR_AFTER_LAST, @@ -4353,6 +4356,8 @@ enum nl80211_reg_type { * a given frequency range. The value is in mBm (100 * dBm). * @NL80211_ATTR_DFS_CAC_TIME: DFS CAC time in milliseconds. * If not present or 0 default CAC time will be used. + * @NL80211_ATTR_POWER_RULE_PSD: power spectral density (in dBm). + * This could be negative. * @NL80211_REG_RULE_ATTR_MAX: highest regulatory rule attribute number * currently defined * @__NL80211_REG_RULE_ATTR_AFTER_LAST: internal use @@ -4370,6 +4375,8 @@ enum nl80211_reg_rule_attr { NL80211_ATTR_DFS_CAC_TIME, + NL80211_ATTR_POWER_RULE_PSD, + /* keep last */ __NL80211_REG_RULE_ATTR_AFTER_LAST, NL80211_REG_RULE_ATTR_MAX = __NL80211_REG_RULE_ATTR_AFTER_LAST - 1 @@ -4453,6 +4460,7 @@ enum nl80211_sched_scan_match_attr { * @NL80211_RRF_NO_HE: HE operation not allowed * @NL80211_RRF_NO_320MHZ: 320MHz operation not allowed * @NL80211_RRF_NO_EHT: EHT operation not allowed + * @NL80211_RRF_PSD: Ruleset has power spectral density value */ enum nl80211_reg_rule_flags { NL80211_RRF_NO_OFDM = 1<<0, @@ -4473,6 +4481,7 @@ enum nl80211_reg_rule_flags { NL80211_RRF_NO_HE = 1<<17, NL80211_RRF_NO_320MHZ = 1<<18, NL80211_RRF_NO_EHT = 1<<19, + NL80211_RRF_PSD = 1<<20, }; #define NL80211_RRF_PASSIVE_SCAN NL80211_RRF_NO_IR diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 218093607b29..e64bf2a58b36 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1115,6 +1115,10 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_OFFSET, chan->freq_offset)) goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_PSD) && + nla_put_s8(msg, NL80211_FREQUENCY_ATTR_PSD, chan->psd)) + goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_DISABLED) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_DISABLED)) goto nla_put_failure; @@ -8529,6 +8533,11 @@ static int nl80211_put_regdom(const struct ieee80211_regdomain *regdom, reg_rule->dfs_cac_ms)) goto nla_put_failure; + if ((reg_rule->flags & NL80211_RRF_PSD) && + nla_put_s8(msg, NL80211_ATTR_POWER_RULE_PSD, + reg_rule->psd)) + goto nla_put_failure; + nla_nest_end(msg, nl_reg_rule); } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 33e2570f2bd6..eb2fa97457b4 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1589,6 +1589,8 @@ static u32 map_regdom_flags(u32 rd_flags) channel_flags |= IEEE80211_CHAN_NO_320MHZ; if (rd_flags & NL80211_RRF_NO_EHT) channel_flags |= IEEE80211_CHAN_NO_EHT; + if (rd_flags & NL80211_RRF_PSD) + channel_flags |= IEEE80211_CHAN_PSD; return channel_flags; } @@ -1795,6 +1797,9 @@ static void handle_channel_single_rule(struct wiphy *wiphy, chan->dfs_cac_ms = reg_rule->dfs_cac_ms; } + if (chan->flags & IEEE80211_CHAN_PSD) + chan->psd = reg_rule->psd; + return; } @@ -1815,6 +1820,9 @@ static void handle_channel_single_rule(struct wiphy *wiphy, chan->dfs_cac_ms = IEEE80211_DFS_MIN_CAC_TIME_MS; } + if (chan->flags & IEEE80211_CHAN_PSD) + chan->psd = reg_rule->psd; + if (chan->orig_mpwr) { /* * Devices that use REGULATORY_COUNTRY_IE_FOLLOW_POWER @@ -1884,6 +1892,12 @@ static void handle_channel_adjacent_rules(struct wiphy *wiphy, rrule2->dfs_cac_ms); } + if ((rrule1->flags & NL80211_RRF_PSD) && + (rrule2->flags & NL80211_RRF_PSD)) + chan->psd = min_t(s8, rrule1->psd, rrule2->psd); + else + chan->flags &= ~NL80211_RRF_PSD; + return; } @@ -2570,6 +2584,9 @@ static void handle_channel_custom(struct wiphy *wiphy, chan->dfs_cac_ms = IEEE80211_DFS_MIN_CAC_TIME_MS; } + if (chan->flags & IEEE80211_CHAN_PSD) + chan->psd = reg_rule->psd; + chan->max_power = chan->max_reg_power; } -- cgit From 2ff477b78250186e611e008320e1de20107e9617 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 11 Sep 2023 17:43:08 +0300 Subject: serial: 8250_port: Introduce UART_IIR_FIFO_ENABLED_16750 The UART_IIR_64BYTE_FIFO is always being used in conjunction with UART_IIR_FIFO_ENABLED. Introduce a joined UART_IIR_FIFO_ENABLED_16750 definition and use it. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230911144308.4169752-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_port.c | 11 +++++------ include/uapi/linux/serial_reg.h | 1 + 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index fb891b67968f..a064698c2be0 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1008,12 +1008,11 @@ static void autoconfig_16550a(struct uart_8250_port *up) serial_out(up, UART_LCR, 0); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR7_64BYTE); - status1 = serial_in(up, UART_IIR) & (UART_IIR_64BYTE_FIFO | - UART_IIR_FIFO_ENABLED); + status1 = serial_in(up, UART_IIR) & UART_IIR_FIFO_ENABLED_16750; serial_out(up, UART_FCR, 0); serial_out(up, UART_LCR, 0); - if (status1 == (UART_IIR_64BYTE_FIFO | UART_IIR_FIFO_ENABLED)) + if (status1 == UART_IIR_FIFO_ENABLED_16750) up->port.type = PORT_16550A_FSL64; else DEBUG_AUTOCONF("Motorola 8xxx DUART "); @@ -1081,12 +1080,12 @@ static void autoconfig_16550a(struct uart_8250_port *up) */ serial_out(up, UART_LCR, 0); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR7_64BYTE); - status1 = serial_in(up, UART_IIR) & (UART_IIR_64BYTE_FIFO | UART_IIR_FIFO_ENABLED); + status1 = serial_in(up, UART_IIR) & UART_IIR_FIFO_ENABLED_16750; serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR7_64BYTE); - status2 = serial_in(up, UART_IIR) & (UART_IIR_64BYTE_FIFO | UART_IIR_FIFO_ENABLED); + status2 = serial_in(up, UART_IIR) & UART_IIR_FIFO_ENABLED_16750; serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO); serial_out(up, UART_LCR, 0); @@ -1094,7 +1093,7 @@ static void autoconfig_16550a(struct uart_8250_port *up) DEBUG_AUTOCONF("iir1=%d iir2=%d ", status1, status2); if (status1 == UART_IIR_FIFO_ENABLED_16550A && - status2 == (UART_IIR_64BYTE_FIFO | UART_IIR_FIFO_ENABLED_16550A)) { + status2 == UART_IIR_FIFO_ENABLED_16750) { up->port.type = PORT_16750; up->capabilities |= UART_CAP_AFE | UART_CAP_SLEEP; return; diff --git a/include/uapi/linux/serial_reg.h b/include/uapi/linux/serial_reg.h index 08b3527e1b93..9c987b04e2d0 100644 --- a/include/uapi/linux/serial_reg.h +++ b/include/uapi/linux/serial_reg.h @@ -49,6 +49,7 @@ #define UART_IIR_FIFO_ENABLED_8250 0x00 /* 8250: no FIFO */ #define UART_IIR_FIFO_ENABLED_16550 0x80 /* 16550: (broken/unusable) FIFO */ #define UART_IIR_FIFO_ENABLED_16550A 0xc0 /* 16550A: FIFO enabled */ +#define UART_IIR_FIFO_ENABLED_16750 0xe0 /* 16750: 64 bytes FIFO enabled */ #define UART_FCR 2 /* Out: FIFO Control Register */ #define UART_FCR_ENABLE_FIFO 0x01 /* Enable the FIFO */ -- cgit From 5f248462c69d5ea7b54a88c62edb73f626d1528d Mon Sep 17 00:00:00 2001 From: David Francis Date: Fri, 21 Jul 2023 11:14:24 -0400 Subject: drm/amdgpu: Add EXT_COHERENT memory allocation flags These flags (for GEM and SVM allocations) allocate memory that allows for system-scope atomic semantics. On GFX943 these flags cause caches to be avoided on non-local memory. On all other ASICs they are identical in functionality to the equivalent COHERENT flags. Corresponding Thunk patch is at https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/pull/88 Reviewed-by: David Yat Sin Signed-off-by: David Francis Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 2 ++ drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 1 + drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 1 + drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c | 1 + drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 5 ++++- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 10 +++++++++- include/uapi/drm/amdgpu_drm.h | 10 +++++++++- include/uapi/linux/kfd_ioctl.h | 3 +++ 8 files changed, 30 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 57189b8bc214..c48ca5adad8a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1691,6 +1691,8 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( if (flags & KFD_IOC_ALLOC_MEM_FLAGS_COHERENT) alloc_flags |= AMDGPU_GEM_CREATE_COHERENT; + if (flags & KFD_IOC_ALLOC_MEM_FLAGS_EXT_COHERENT) + alloc_flags |= AMDGPU_GEM_CREATE_EXT_COHERENT; if (flags & KFD_IOC_ALLOC_MEM_FLAGS_UNCACHED) alloc_flags |= AMDGPU_GEM_CREATE_UNCACHED; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 12210598e5b8..76b618735dc0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -331,6 +331,7 @@ amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf) flags |= other->flags & (AMDGPU_GEM_CREATE_CPU_GTT_USWC | AMDGPU_GEM_CREATE_COHERENT | + AMDGPU_GEM_CREATE_EXT_COHERENT | AMDGPU_GEM_CREATE_UNCACHED); } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index d3da13f4c80e..e582073b57c8 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -635,6 +635,7 @@ static void gmc_v10_0_get_vm_pte(struct amdgpu_device *adev, } if (bo && bo->flags & (AMDGPU_GEM_CREATE_COHERENT | + AMDGPU_GEM_CREATE_EXT_COHERENT | AMDGPU_GEM_CREATE_UNCACHED)) *flags = (*flags & ~AMDGPU_PTE_MTYPE_NV10_MASK) | AMDGPU_PTE_MTYPE_NV10(MTYPE_UC); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index e1f47f9c1881..69f65e9c4f93 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -543,6 +543,7 @@ static void gmc_v11_0_get_vm_pte(struct amdgpu_device *adev, } if (bo && bo->flags & (AMDGPU_GEM_CREATE_COHERENT | + AMDGPU_GEM_CREATE_EXT_COHERENT | AMDGPU_GEM_CREATE_UNCACHED)) *flags = (*flags & ~AMDGPU_PTE_MTYPE_NV10_MASK) | AMDGPU_PTE_MTYPE_NV10(MTYPE_UC); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 268ee533e7c1..2936a0fb7527 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1187,7 +1187,8 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev, { struct amdgpu_device *bo_adev = amdgpu_ttm_adev(bo->tbo.bdev); bool is_vram = bo->tbo.resource->mem_type == TTM_PL_VRAM; - bool coherent = bo->flags & AMDGPU_GEM_CREATE_COHERENT; + bool coherent = bo->flags & (AMDGPU_GEM_CREATE_COHERENT | AMDGPU_GEM_CREATE_EXT_COHERENT); + bool ext_coherent = bo->flags & AMDGPU_GEM_CREATE_EXT_COHERENT; bool uncached = bo->flags & AMDGPU_GEM_CREATE_UNCACHED; struct amdgpu_vm *vm = mapping->bo_va->base.vm; unsigned int mtype_local, mtype; @@ -1257,6 +1258,8 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev, snoop = true; if (uncached) { mtype = MTYPE_UC; + } else if (ext_coherent) { + mtype = is_local ? MTYPE_CC : MTYPE_UC; } else if (adev->flags & AMD_IS_APU) { mtype = is_local ? mtype_local : MTYPE_NC; } else { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index ae5660861133..9a1952114e5b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1189,7 +1189,8 @@ svm_range_get_pte_flags(struct kfd_node *node, uint32_t mapping_flags = 0; uint64_t pte_flags; bool snoop = (domain != SVM_RANGE_VRAM_DOMAIN); - bool coherent = flags & KFD_IOCTL_SVM_FLAG_COHERENT; + bool coherent = flags & (KFD_IOCTL_SVM_FLAG_COHERENT | KFD_IOCTL_SVM_FLAG_EXT_COHERENT); + bool ext_coherent = flags & KFD_IOCTL_SVM_FLAG_EXT_COHERENT; bool uncached = false; /*flags & KFD_IOCTL_SVM_FLAG_UNCACHED;*/ unsigned int mtype_local; @@ -1237,6 +1238,13 @@ svm_range_get_pte_flags(struct kfd_node *node, snoop = true; if (uncached) { mapping_flags |= AMDGPU_VM_MTYPE_UC; + } else if (ext_coherent) { + /* local HBM region close to partition */ + if (bo_node->adev == node->adev && + (!bo_node->xcp || !node->xcp || bo_node->xcp->mem_id == node->xcp->mem_id)) + mapping_flags |= AMDGPU_VM_MTYPE_CC; + else + mapping_flags |= AMDGPU_VM_MTYPE_UC; } else if (domain == SVM_RANGE_VRAM_DOMAIN) { /* local HBM region close to partition */ if (bo_node->adev == node->adev && diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index ec437120b083..984fc16577ca 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -150,7 +150,7 @@ extern "C" { */ #define AMDGPU_GEM_CREATE_DISCARDABLE (1 << 12) /* Flag that BO is shared coherently between multiple devices or CPU threads. - * May depend on GPU instructions to flush caches explicitly + * May depend on GPU instructions to flush caches to system scope explicitly. * * This influences the choice of MTYPE in the PTEs on GFXv9 and later GPUs and * may override the MTYPE selected in AMDGPU_VA_OP_MAP. @@ -163,6 +163,14 @@ extern "C" { * may override the MTYPE selected in AMDGPU_VA_OP_MAP. */ #define AMDGPU_GEM_CREATE_UNCACHED (1 << 14) +/* Flag that BO should be coherent across devices when using device-level + * atomics. May depend on GPU instructions to flush caches to device scope + * explicitly, promoting them to system scope automatically. + * + * This influences the choice of MTYPE in the PTEs on GFXv9 and later GPUs and + * may override the MTYPE selected in AMDGPU_VA_OP_MAP. + */ +#define AMDGPU_GEM_CREATE_EXT_COHERENT (1 << 15) struct drm_amdgpu_gem_create_in { /** the requested memory size */ diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index eeb2fdcbdcb7..f0ed68974c54 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -405,6 +405,7 @@ struct kfd_ioctl_acquire_vm_args { #define KFD_IOC_ALLOC_MEM_FLAGS_AQL_QUEUE_MEM (1 << 27) #define KFD_IOC_ALLOC_MEM_FLAGS_COHERENT (1 << 26) #define KFD_IOC_ALLOC_MEM_FLAGS_UNCACHED (1 << 25) +#define KFD_IOC_ALLOC_MEM_FLAGS_EXT_COHERENT (1 << 24) /* Allocate memory for later SVM (shared virtual memory) mapping. * @@ -659,6 +660,8 @@ enum kfd_mmio_remap { #define KFD_IOCTL_SVM_FLAG_GPU_READ_MOSTLY 0x00000020 /* Keep GPU memory mapping always valid as if XNACK is disable */ #define KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED 0x00000040 +/* Fine grained coherency between all devices using device-scope atomics */ +#define KFD_IOCTL_SVM_FLAG_EXT_COHERENT 0x00000080 /** * kfd_ioctl_svm_op - SVM ioctl operations -- cgit From 4923954bbc4a760e0b2210e0cb5733726ac2e2e9 Mon Sep 17 00:00:00 2001 From: "peterz@infradead.org" Date: Thu, 21 Sep 2023 12:45:06 +0200 Subject: futex: Clarify FUTEX2 flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit sys_futex_waitv() is part of the futex2 series (the first and only so far) of syscalls and has a flags field per futex (as opposed to flags being encoded in the futex op). This new flags field has a new namespace, which unfortunately isn't super explicit. Notably it currently takes FUTEX_32 and FUTEX_PRIVATE_FLAG. Introduce the FUTEX2 namespace to clarify this Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Thomas Gleixner Reviewed-by: André Almeida Link: https://lore.kernel.org/r/20230921105247.507327749@noisy.programming.kicks-ass.net --- include/uapi/linux/futex.h | 16 +++++++++++++--- kernel/futex/syscalls.c | 7 +++---- 2 files changed, 16 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h index 71a5df8d2689..21d4eff41162 100644 --- a/include/uapi/linux/futex.h +++ b/include/uapi/linux/futex.h @@ -44,10 +44,20 @@ FUTEX_PRIVATE_FLAG) /* - * Flags to specify the bit length of the futex word for futex2 syscalls. - * Currently, only 32 is supported. + * Flags for futex2 syscalls. */ -#define FUTEX_32 2 + /* 0x00 */ + /* 0x01 */ +#define FUTEX2_SIZE_U32 0x02 + /* 0x04 */ + /* 0x08 */ + /* 0x10 */ + /* 0x20 */ + /* 0x40 */ +#define FUTEX2_PRIVATE FUTEX_PRIVATE_FLAG + +/* do not use */ +#define FUTEX_32 FUTEX2_SIZE_U32 /* historical accident :-( */ /* * Max numbers of elements in a futex_waitv array diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c index a8074079b09e..ff696b0e2e5c 100644 --- a/kernel/futex/syscalls.c +++ b/kernel/futex/syscalls.c @@ -183,8 +183,7 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } -/* Mask of available flags for each futex in futex_waitv list */ -#define FUTEXV_WAITER_MASK (FUTEX_32 | FUTEX_PRIVATE_FLAG) +#define FUTEX2_VALID_MASK (FUTEX2_SIZE_U32 | FUTEX2_PRIVATE) /** * futex_parse_waitv - Parse a waitv array from userspace @@ -205,10 +204,10 @@ static int futex_parse_waitv(struct futex_vector *futexv, if (copy_from_user(&aux, &uwaitv[i], sizeof(aux))) return -EFAULT; - if ((aux.flags & ~FUTEXV_WAITER_MASK) || aux.__reserved) + if ((aux.flags & ~FUTEX2_VALID_MASK) || aux.__reserved) return -EINVAL; - if (!(aux.flags & FUTEX_32)) + if (!(aux.flags & FUTEX2_SIZE_U32)) return -EINVAL; futexv[i].w.flags = aux.flags; -- cgit From d6d08d24790e82c69a46ef78ae44fe1b1ed30775 Mon Sep 17 00:00:00 2001 From: "peterz@infradead.org" Date: Thu, 21 Sep 2023 12:45:07 +0200 Subject: futex: Extend the FUTEX2 flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add the definition for the missing but always intended extra sizes, and add a NUMA flag for the planned numa extention. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Thomas Gleixner Reviewed-by: André Almeida Link: https://lore.kernel.org/r/20230921105247.617057368@noisy.programming.kicks-ass.net --- include/uapi/linux/futex.h | 21 ++++++++++++++++++--- kernel/futex/syscalls.c | 9 +++++++-- 2 files changed, 25 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h index 21d4eff41162..d2ee625ea189 100644 --- a/include/uapi/linux/futex.h +++ b/include/uapi/linux/futex.h @@ -45,17 +45,32 @@ /* * Flags for futex2 syscalls. + * + * NOTE: these are not pure flags, they can also be seen as: + * + * union { + * u32 flags; + * struct { + * u32 size : 2, + * numa : 1, + * : 4, + * private : 1; + * }; + * }; */ - /* 0x00 */ - /* 0x01 */ +#define FUTEX2_SIZE_U8 0x00 +#define FUTEX2_SIZE_U16 0x01 #define FUTEX2_SIZE_U32 0x02 - /* 0x04 */ +#define FUTEX2_SIZE_U64 0x03 +#define FUTEX2_NUMA 0x04 /* 0x08 */ /* 0x10 */ /* 0x20 */ /* 0x40 */ #define FUTEX2_PRIVATE FUTEX_PRIVATE_FLAG +#define FUTEX2_SIZE_MASK 0x03 + /* do not use */ #define FUTEX_32 FUTEX2_SIZE_U32 /* historical accident :-( */ diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c index ff696b0e2e5c..953f0a49de3a 100644 --- a/kernel/futex/syscalls.c +++ b/kernel/futex/syscalls.c @@ -183,7 +183,7 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } -#define FUTEX2_VALID_MASK (FUTEX2_SIZE_U32 | FUTEX2_PRIVATE) +#define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_PRIVATE) /** * futex_parse_waitv - Parse a waitv array from userspace @@ -207,7 +207,12 @@ static int futex_parse_waitv(struct futex_vector *futexv, if ((aux.flags & ~FUTEX2_VALID_MASK) || aux.__reserved) return -EINVAL; - if (!(aux.flags & FUTEX2_SIZE_U32)) + if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall()) { + if ((aux.flags & FUTEX2_SIZE_MASK) == FUTEX2_SIZE_U64) + return -EINVAL; + } + + if ((aux.flags & FUTEX2_SIZE_MASK) != FUTEX2_SIZE_U32) return -EINVAL; futexv[i].w.flags = aux.flags; -- cgit From fc68fcda049108478ee4704d8a3ad3e05cc72fd0 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 11 Sep 2023 13:35:42 -0600 Subject: io_uring/rw: add support for IORING_OP_READ_MULTISHOT This behaves like IORING_OP_READ, except: 1) It only supports pollable files (eg pipes, sockets, etc). Note that for sockets, you probably want to use recv/recvmsg with multishot instead. 2) It supports multishot mode, meaning it will repeatedly trigger a read and fill a buffer when data is available. This allows similar use to recv/recvmsg but on non-sockets, where a single request will repeatedly post a CQE whenever data is read from it. 3) Because of #2, it must be used with provided buffers. This is uniformly true across any request type that supports multishot and transfers data, with the reason being that it's obviously not possible to pass in a single buffer for the data, as multiple reads may very well trigger before an application has a chance to process previous CQEs and the data passed from them. Reviewed-by: Gabriel Krisman Bertazi Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + io_uring/opdef.c | 13 ++++++++- io_uring/rw.c | 67 +++++++++++++++++++++++++++++++++++++++++++ io_uring/rw.h | 2 ++ 4 files changed, 82 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 8e61f8b7c2ce..d127948b0d8a 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -240,6 +240,7 @@ enum io_uring_op { IORING_OP_URING_CMD, IORING_OP_SEND_ZC, IORING_OP_SENDMSG_ZC, + IORING_OP_READ_MULTISHOT, /* this goes last, obviously */ IORING_OP_LAST, diff --git a/io_uring/opdef.c b/io_uring/opdef.c index f40904065500..a3fb1f9b3998 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -430,9 +430,17 @@ const struct io_issue_def io_issue_defs[] = { .prep = io_eopnotsupp_prep, #endif }, + [IORING_OP_READ_MULTISHOT] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollin = 1, + .buffer_select = 1, + .audit_skip = 1, + .prep = io_read_mshot_prep, + .issue = io_read_mshot, + }, }; - const struct io_cold_def io_cold_defs[] = { [IORING_OP_NOP] = { .name = "NOP", @@ -650,6 +658,9 @@ const struct io_cold_def io_cold_defs[] = { .fail = io_sendrecv_fail, #endif }, + [IORING_OP_READ_MULTISHOT] = { + .name = "READ_MULTISHOT", + }, }; const char *io_uring_get_opcode(u8 opcode) diff --git a/io_uring/rw.c b/io_uring/rw.c index 83ae911c2868..ec0cc38ea682 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -123,6 +123,22 @@ int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } +/* + * Multishot read is prepared just like a normal read/write request, only + * difference is that we set the MULTISHOT flag. + */ +int io_read_mshot_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + int ret; + + ret = io_prep_rw(req, sqe); + if (unlikely(ret)) + return ret; + + req->flags |= REQ_F_APOLL_MULTISHOT; + return 0; +} + void io_readv_writev_cleanup(struct io_kiocb *req) { struct io_async_rw *io = req->async_data; @@ -869,6 +885,57 @@ int io_read(struct io_kiocb *req, unsigned int issue_flags) return ret; } +int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags) +{ + unsigned int cflags = 0; + int ret; + + /* + * Multishot MUST be used on a pollable file + */ + if (!file_can_poll(req->file)) + return -EBADFD; + + ret = __io_read(req, issue_flags); + + /* + * If we get -EAGAIN, recycle our buffer and just let normal poll + * handling arm it. + */ + if (ret == -EAGAIN) { + io_kbuf_recycle(req, issue_flags); + return -EAGAIN; + } + + /* + * Any successful return value will keep the multishot read armed. + */ + if (ret > 0) { + /* + * Put our buffer and post a CQE. If we fail to post a CQE, then + * jump to the termination path. This request is then done. + */ + cflags = io_put_kbuf(req, issue_flags); + + if (io_fill_cqe_req_aux(req, + issue_flags & IO_URING_F_COMPLETE_DEFER, + ret, cflags | IORING_CQE_F_MORE)) { + if (issue_flags & IO_URING_F_MULTISHOT) + return IOU_ISSUE_SKIP_COMPLETE; + return -EAGAIN; + } + } + + /* + * Either an error, or we've hit overflow posting the CQE. For any + * multishot request, hitting overflow will terminate it. + */ + io_req_set_res(req, ret, cflags); + if (issue_flags & IO_URING_F_MULTISHOT) + return IOU_STOP_MULTISHOT; + return IOU_OK; +} + int io_write(struct io_kiocb *req, unsigned int issue_flags) { struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); diff --git a/io_uring/rw.h b/io_uring/rw.h index 4b89f9659366..c5aed03d42a4 100644 --- a/io_uring/rw.h +++ b/io_uring/rw.h @@ -23,3 +23,5 @@ int io_writev_prep_async(struct io_kiocb *req); void io_readv_writev_cleanup(struct io_kiocb *req); void io_rw_fail(struct io_kiocb *req); void io_req_rw_complete(struct io_kiocb *req, struct io_tw_state *ts); +int io_read_mshot_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags); -- cgit From f31ecf671ddc498f20219453395794ff2383e06b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 10 Jul 2023 16:14:37 -0600 Subject: io_uring: add IORING_OP_WAITID support This adds support for an async version of waitid(2), in a fully async version. If an event isn't immediately available, wait for a callback to trigger a retry. The format of the sqe is as follows: sqe->len The 'which', the idtype being queried/waited for. sqe->fd The 'pid' (or id) being waited for. sqe->file_index The 'options' being set. sqe->addr2 A pointer to siginfo_t, if any, being filled in. buf_index, add3, and waitid_flags are reserved/unused for now. waitid_flags will be used for options for this request type. One interesting use case may be to add multi-shot support, so that the request stays armed and posts a notification every time a monitored process state change occurs. Note that this does not support rusage, on Arnd's recommendation. See the waitid(2) man page for details on the arguments. Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 2 + include/uapi/linux/io_uring.h | 2 + io_uring/Makefile | 3 +- io_uring/cancel.c | 5 + io_uring/io_uring.c | 3 + io_uring/opdef.c | 9 + io_uring/waitid.c | 372 +++++++++++++++++++++++++++++++++++++++++ io_uring/waitid.h | 15 ++ 8 files changed, 410 insertions(+), 1 deletion(-) create mode 100644 io_uring/waitid.c create mode 100644 io_uring/waitid.h (limited to 'include/uapi/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 13d19b9be9f4..fe1c5d4ec56c 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -313,6 +313,8 @@ struct io_ring_ctx { struct list_head cq_overflow_list; struct io_hash_table cancel_table; + struct hlist_head waitid_list; + const struct cred *sq_creds; /* cred used for __io_sq_thread() */ struct io_sq_data *sq_data; /* if using sq thread polling */ diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index d127948b0d8a..683ac2b74721 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -65,6 +65,7 @@ struct io_uring_sqe { __u32 xattr_flags; __u32 msg_ring_flags; __u32 uring_cmd_flags; + __u32 waitid_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -241,6 +242,7 @@ enum io_uring_op { IORING_OP_SEND_ZC, IORING_OP_SENDMSG_ZC, IORING_OP_READ_MULTISHOT, + IORING_OP_WAITID, /* this goes last, obviously */ IORING_OP_LAST, diff --git a/io_uring/Makefile b/io_uring/Makefile index 8cc8e5387a75..7bd64e442567 100644 --- a/io_uring/Makefile +++ b/io_uring/Makefile @@ -7,5 +7,6 @@ obj-$(CONFIG_IO_URING) += io_uring.o xattr.o nop.o fs.o splice.o \ openclose.o uring_cmd.o epoll.o \ statx.o net.o msg_ring.o timeout.o \ sqpoll.o fdinfo.o tctx.o poll.o \ - cancel.o kbuf.o rsrc.o rw.o opdef.o notif.o + cancel.o kbuf.o rsrc.o rw.o opdef.o \ + notif.o waitid.o obj-$(CONFIG_IO_WQ) += io-wq.o diff --git a/io_uring/cancel.c b/io_uring/cancel.c index 7b23607cf4af..eb77a51c5a79 100644 --- a/io_uring/cancel.c +++ b/io_uring/cancel.c @@ -15,6 +15,7 @@ #include "tctx.h" #include "poll.h" #include "timeout.h" +#include "waitid.h" #include "cancel.h" struct io_cancel { @@ -119,6 +120,10 @@ int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd, if (ret != -ENOENT) return ret; + ret = io_waitid_cancel(ctx, cd, issue_flags); + if (ret != -ENOENT) + return ret; + spin_lock(&ctx->completion_lock); if (!(cd->flags & IORING_ASYNC_CANCEL_FD)) ret = io_timeout_cancel(ctx, cd); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 783ed0fff71b..2dff4772bf14 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -92,6 +92,7 @@ #include "cancel.h" #include "net.h" #include "notif.h" +#include "waitid.h" #include "timeout.h" #include "poll.h" @@ -348,6 +349,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_LIST_HEAD(&ctx->tctx_list); ctx->submit_state.free_list.next = NULL; INIT_WQ_LIST(&ctx->locked_free_list); + INIT_HLIST_HEAD(&ctx->waitid_list); INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func); INIT_WQ_LIST(&ctx->submit_state.compl_reqs); return ctx; @@ -3303,6 +3305,7 @@ static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, ret |= io_cancel_defer_files(ctx, task, cancel_all); mutex_lock(&ctx->uring_lock); ret |= io_poll_remove_all(ctx, task, cancel_all); + ret |= io_waitid_remove_all(ctx, task, cancel_all); mutex_unlock(&ctx->uring_lock); ret |= io_kill_timeouts(ctx, task, cancel_all); if (task) diff --git a/io_uring/opdef.c b/io_uring/opdef.c index a3fb1f9b3998..aadcbf7136b0 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -33,6 +33,7 @@ #include "poll.h" #include "cancel.h" #include "rw.h" +#include "waitid.h" static int io_no_issue(struct io_kiocb *req, unsigned int issue_flags) { @@ -439,6 +440,10 @@ const struct io_issue_def io_issue_defs[] = { .prep = io_read_mshot_prep, .issue = io_read_mshot, }, + [IORING_OP_WAITID] = { + .prep = io_waitid_prep, + .issue = io_waitid, + }, }; const struct io_cold_def io_cold_defs[] = { @@ -661,6 +666,10 @@ const struct io_cold_def io_cold_defs[] = { [IORING_OP_READ_MULTISHOT] = { .name = "READ_MULTISHOT", }, + [IORING_OP_WAITID] = { + .name = "WAITID", + .async_size = sizeof(struct io_waitid_async), + }, }; const char *io_uring_get_opcode(u8 opcode) diff --git a/io_uring/waitid.c b/io_uring/waitid.c new file mode 100644 index 000000000000..6f851978606d --- /dev/null +++ b/io_uring/waitid.c @@ -0,0 +1,372 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Support for async notification of waitid + */ +#include +#include +#include +#include +#include +#include + +#include + +#include "io_uring.h" +#include "cancel.h" +#include "waitid.h" +#include "../kernel/exit.h" + +static void io_waitid_cb(struct io_kiocb *req, struct io_tw_state *ts); + +#define IO_WAITID_CANCEL_FLAG BIT(31) +#define IO_WAITID_REF_MASK GENMASK(30, 0) + +struct io_waitid { + struct file *file; + int which; + pid_t upid; + int options; + atomic_t refs; + struct wait_queue_head *head; + struct siginfo __user *infop; + struct waitid_info info; +}; + +static void io_waitid_free(struct io_kiocb *req) +{ + struct io_waitid_async *iwa = req->async_data; + + put_pid(iwa->wo.wo_pid); + kfree(req->async_data); + req->async_data = NULL; + req->flags &= ~REQ_F_ASYNC_DATA; +} + +#ifdef CONFIG_COMPAT +static bool io_waitid_compat_copy_si(struct io_waitid *iw, int signo) +{ + struct compat_siginfo __user *infop; + bool ret; + + infop = (struct compat_siginfo __user *) iw->infop; + + if (!user_write_access_begin(infop, sizeof(*infop))) + return false; + + unsafe_put_user(signo, &infop->si_signo, Efault); + unsafe_put_user(0, &infop->si_errno, Efault); + unsafe_put_user(iw->info.cause, &infop->si_code, Efault); + unsafe_put_user(iw->info.pid, &infop->si_pid, Efault); + unsafe_put_user(iw->info.uid, &infop->si_uid, Efault); + unsafe_put_user(iw->info.status, &infop->si_status, Efault); + ret = true; +done: + user_write_access_end(); + return ret; +Efault: + ret = false; + goto done; +} +#endif + +static bool io_waitid_copy_si(struct io_kiocb *req, int signo) +{ + struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + bool ret; + + if (!iw->infop) + return true; + +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + return io_waitid_compat_copy_si(iw, signo); +#endif + + if (!user_write_access_begin(iw->infop, sizeof(*iw->infop))) + return false; + + unsafe_put_user(signo, &iw->infop->si_signo, Efault); + unsafe_put_user(0, &iw->infop->si_errno, Efault); + unsafe_put_user(iw->info.cause, &iw->infop->si_code, Efault); + unsafe_put_user(iw->info.pid, &iw->infop->si_pid, Efault); + unsafe_put_user(iw->info.uid, &iw->infop->si_uid, Efault); + unsafe_put_user(iw->info.status, &iw->infop->si_status, Efault); + ret = true; +done: + user_write_access_end(); + return ret; +Efault: + ret = false; + goto done; +} + +static int io_waitid_finish(struct io_kiocb *req, int ret) +{ + int signo = 0; + + if (ret > 0) { + signo = SIGCHLD; + ret = 0; + } + + if (!io_waitid_copy_si(req, signo)) + ret = -EFAULT; + io_waitid_free(req); + return ret; +} + +static void io_waitid_complete(struct io_kiocb *req, int ret) +{ + struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + struct io_tw_state ts = { .locked = true }; + + /* anyone completing better be holding a reference */ + WARN_ON_ONCE(!(atomic_read(&iw->refs) & IO_WAITID_REF_MASK)); + + lockdep_assert_held(&req->ctx->uring_lock); + + /* + * Did cancel find it meanwhile? + */ + if (hlist_unhashed(&req->hash_node)) + return; + + hlist_del_init(&req->hash_node); + + ret = io_waitid_finish(req, ret); + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + io_req_task_complete(req, &ts); +} + +static bool __io_waitid_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req) +{ + struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + struct io_waitid_async *iwa = req->async_data; + + /* + * Mark us canceled regardless of ownership. This will prevent a + * potential retry from a spurious wakeup. + */ + atomic_or(IO_WAITID_CANCEL_FLAG, &iw->refs); + + /* claim ownership */ + if (atomic_fetch_inc(&iw->refs) & IO_WAITID_REF_MASK) + return false; + + spin_lock_irq(&iw->head->lock); + list_del_init(&iwa->wo.child_wait.entry); + spin_unlock_irq(&iw->head->lock); + io_waitid_complete(req, -ECANCELED); + return true; +} + +int io_waitid_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd, + unsigned int issue_flags) +{ + struct hlist_node *tmp; + struct io_kiocb *req; + int nr = 0; + + if (cd->flags & (IORING_ASYNC_CANCEL_FD|IORING_ASYNC_CANCEL_FD_FIXED)) + return -ENOENT; + + io_ring_submit_lock(ctx, issue_flags); + hlist_for_each_entry_safe(req, tmp, &ctx->waitid_list, hash_node) { + if (req->cqe.user_data != cd->data && + !(cd->flags & IORING_ASYNC_CANCEL_ANY)) + continue; + if (__io_waitid_cancel(ctx, req)) + nr++; + if (!(cd->flags & IORING_ASYNC_CANCEL_ALL)) + break; + } + io_ring_submit_unlock(ctx, issue_flags); + + if (nr) + return nr; + + return -ENOENT; +} + +bool io_waitid_remove_all(struct io_ring_ctx *ctx, struct task_struct *task, + bool cancel_all) +{ + struct hlist_node *tmp; + struct io_kiocb *req; + bool found = false; + + lockdep_assert_held(&ctx->uring_lock); + + hlist_for_each_entry_safe(req, tmp, &ctx->waitid_list, hash_node) { + if (!io_match_task_safe(req, task, cancel_all)) + continue; + __io_waitid_cancel(ctx, req); + found = true; + } + + return found; +} + +static inline bool io_waitid_drop_issue_ref(struct io_kiocb *req) +{ + struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + struct io_waitid_async *iwa = req->async_data; + + if (!atomic_sub_return(1, &iw->refs)) + return false; + + /* + * Wakeup triggered, racing with us. It was prevented from + * completing because of that, queue up the tw to do that. + */ + req->io_task_work.func = io_waitid_cb; + io_req_task_work_add(req); + remove_wait_queue(iw->head, &iwa->wo.child_wait); + return true; +} + +static void io_waitid_cb(struct io_kiocb *req, struct io_tw_state *ts) +{ + struct io_waitid_async *iwa = req->async_data; + struct io_ring_ctx *ctx = req->ctx; + int ret; + + io_tw_lock(ctx, ts); + + ret = __do_wait(&iwa->wo); + + /* + * If we get -ERESTARTSYS here, we need to re-arm and check again + * to ensure we get another callback. If the retry works, then we can + * just remove ourselves from the waitqueue again and finish the + * request. + */ + if (unlikely(ret == -ERESTARTSYS)) { + struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + + /* Don't retry if cancel found it meanwhile */ + ret = -ECANCELED; + if (!(atomic_read(&iw->refs) & IO_WAITID_CANCEL_FLAG)) { + iw->head = ¤t->signal->wait_chldexit; + add_wait_queue(iw->head, &iwa->wo.child_wait); + ret = __do_wait(&iwa->wo); + if (ret == -ERESTARTSYS) { + /* retry armed, drop our ref */ + io_waitid_drop_issue_ref(req); + return; + } + + remove_wait_queue(iw->head, &iwa->wo.child_wait); + } + } + + io_waitid_complete(req, ret); +} + +static int io_waitid_wait(struct wait_queue_entry *wait, unsigned mode, + int sync, void *key) +{ + struct wait_opts *wo = container_of(wait, struct wait_opts, child_wait); + struct io_waitid_async *iwa = container_of(wo, struct io_waitid_async, wo); + struct io_kiocb *req = iwa->req; + struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + struct task_struct *p = key; + + if (!pid_child_should_wake(wo, p)) + return 0; + + /* cancel is in progress */ + if (atomic_fetch_inc(&iw->refs) & IO_WAITID_REF_MASK) + return 1; + + req->io_task_work.func = io_waitid_cb; + io_req_task_work_add(req); + list_del_init(&wait->entry); + return 1; +} + +int io_waitid_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + + if (sqe->addr || sqe->buf_index || sqe->addr3 || sqe->waitid_flags) + return -EINVAL; + + iw->which = READ_ONCE(sqe->len); + iw->upid = READ_ONCE(sqe->fd); + iw->options = READ_ONCE(sqe->file_index); + iw->infop = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + return 0; +} + +int io_waitid(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + struct io_ring_ctx *ctx = req->ctx; + struct io_waitid_async *iwa; + int ret; + + if (io_alloc_async_data(req)) + return -ENOMEM; + + iwa = req->async_data; + iwa->req = req; + + ret = kernel_waitid_prepare(&iwa->wo, iw->which, iw->upid, &iw->info, + iw->options, NULL); + if (ret) + goto done; + + /* + * Mark the request as busy upfront, in case we're racing with the + * wakeup. If we are, then we'll notice when we drop this initial + * reference again after arming. + */ + atomic_set(&iw->refs, 1); + + /* + * Cancel must hold the ctx lock, so there's no risk of cancelation + * finding us until a) we remain on the list, and b) the lock is + * dropped. We only need to worry about racing with the wakeup + * callback. + */ + io_ring_submit_lock(ctx, issue_flags); + hlist_add_head(&req->hash_node, &ctx->waitid_list); + + init_waitqueue_func_entry(&iwa->wo.child_wait, io_waitid_wait); + iwa->wo.child_wait.private = req->task; + iw->head = ¤t->signal->wait_chldexit; + add_wait_queue(iw->head, &iwa->wo.child_wait); + + ret = __do_wait(&iwa->wo); + if (ret == -ERESTARTSYS) { + /* + * Nobody else grabbed a reference, it'll complete when we get + * a waitqueue callback, or if someone cancels it. + */ + if (!io_waitid_drop_issue_ref(req)) { + io_ring_submit_unlock(ctx, issue_flags); + return IOU_ISSUE_SKIP_COMPLETE; + } + + /* + * Wakeup triggered, racing with us. It was prevented from + * completing because of that, queue up the tw to do that. + */ + io_ring_submit_unlock(ctx, issue_flags); + return IOU_ISSUE_SKIP_COMPLETE; + } + + hlist_del_init(&req->hash_node); + remove_wait_queue(iw->head, &iwa->wo.child_wait); + ret = io_waitid_finish(req, ret); + + io_ring_submit_unlock(ctx, issue_flags); +done: + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return IOU_OK; +} diff --git a/io_uring/waitid.h b/io_uring/waitid.h new file mode 100644 index 000000000000..956a8adafe8c --- /dev/null +++ b/io_uring/waitid.h @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "../kernel/exit.h" + +struct io_waitid_async { + struct io_kiocb *req; + struct wait_opts wo; +}; + +int io_waitid_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_waitid(struct io_kiocb *req, unsigned int issue_flags); +int io_waitid_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd, + unsigned int issue_flags); +bool io_waitid_remove_all(struct io_ring_ctx *ctx, struct task_struct *task, + bool cancel_all); -- cgit From 42f311751102ef4884ae7352d7e85bd97280d2d3 Mon Sep 17 00:00:00 2001 From: Basavaraj Natikar Date: Tue, 19 Sep 2023 13:40:47 +0530 Subject: iio: Add channel type light color temperature In most cases, ambient color sensors also support light color temperature, which is measured in kelvin. Thus, add channel type light color temperature. Signed-off-by: Basavaraj Natikar Link: https://lore.kernel.org/r/20230919081054.2050714-3-Basavaraj.Natikar@amd.com Signed-off-by: Jonathan Cameron --- Documentation/ABI/testing/sysfs-bus-iio | 7 +++++++ drivers/iio/industrialio-core.c | 1 + include/uapi/linux/iio/types.h | 1 + tools/iio/iio_event_monitor.c | 2 ++ 4 files changed, 11 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index a2854dc9a839..4cf7ed9ca57b 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -2179,3 +2179,10 @@ Contact: linux-iio@vger.kernel.org Description: Number of conditions that must occur, during a running period, before an event is generated. + +What: /sys/bus/iio/devices/iio:deviceX/in_colortemp_raw +KernelVersion: 6.7 +Contact: linux-iio@vger.kernel.org +Description: + Represents light color temperature, which measures light color + temperature in Kelvin. diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index d752e9c0499b..cba942cadf97 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -90,6 +90,7 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_POSITIONRELATIVE] = "positionrelative", [IIO_PHASE] = "phase", [IIO_MASSCONCENTRATION] = "massconcentration", + [IIO_COLORTEMP] = "colortemp", }; static const char * const iio_modifier_names[] = { diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index c79f2f046a0b..08c20e540c13 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -47,6 +47,7 @@ enum iio_chan_type { IIO_POSITIONRELATIVE, IIO_PHASE, IIO_MASSCONCENTRATION, + IIO_COLORTEMP, }; enum iio_modifier { diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c index 0a5c2bb60030..a63741e43ddf 100644 --- a/tools/iio/iio_event_monitor.c +++ b/tools/iio/iio_event_monitor.c @@ -59,6 +59,7 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_POSITIONRELATIVE] = "positionrelative", [IIO_PHASE] = "phase", [IIO_MASSCONCENTRATION] = "massconcentration", + [IIO_COLORTEMP] = "colortemp", }; static const char * const iio_ev_type_text[] = { @@ -173,6 +174,7 @@ static bool event_is_known(struct iio_event_data *event) case IIO_POSITIONRELATIVE: case IIO_PHASE: case IIO_MASSCONCENTRATION: + case IIO_COLORTEMP: break; default: return false; -- cgit From 06790d4c69d1851573baa4459e5bf6ac986cb0eb Mon Sep 17 00:00:00 2001 From: Basavaraj Natikar Date: Tue, 19 Sep 2023 13:40:51 +0530 Subject: iio: Add channel type for chromaticity In most cases, ambient color sensors also support the x and y light colors, which represent the coordinates on the CIE 1931 chromaticity diagram. Thus, add channel type for chromaticity. Signed-off-by: Basavaraj Natikar Link: https://lore.kernel.org/r/20230919081054.2050714-7-Basavaraj.Natikar@amd.com Signed-off-by: Jonathan Cameron --- Documentation/ABI/testing/sysfs-bus-iio | 8 ++++++++ drivers/iio/industrialio-core.c | 1 + include/uapi/linux/iio/types.h | 1 + tools/iio/iio_event_monitor.c | 2 ++ 4 files changed, 12 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index 4cf7ed9ca57b..0c9389ad3709 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -2186,3 +2186,11 @@ Contact: linux-iio@vger.kernel.org Description: Represents light color temperature, which measures light color temperature in Kelvin. + +What: /sys/bus/iio/devices/iio:deviceX/in_chromaticity_x_raw +What: /sys/bus/iio/devices/iio:deviceX/in_chromaticity_y_raw +KernelVersion: 6.7 +Contact: linux-iio@vger.kernel.org +Description: + The x and y light color coordinate on the CIE 1931 chromaticity + diagram. diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index cba942cadf97..6dc4d2b296bb 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -91,6 +91,7 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_PHASE] = "phase", [IIO_MASSCONCENTRATION] = "massconcentration", [IIO_COLORTEMP] = "colortemp", + [IIO_CHROMATICITY] = "chromaticity", }; static const char * const iio_modifier_names[] = { diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index 08c20e540c13..4832c611c027 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -48,6 +48,7 @@ enum iio_chan_type { IIO_PHASE, IIO_MASSCONCENTRATION, IIO_COLORTEMP, + IIO_CHROMATICITY, }; enum iio_modifier { diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c index a63741e43ddf..a28a86f2bd5b 100644 --- a/tools/iio/iio_event_monitor.c +++ b/tools/iio/iio_event_monitor.c @@ -60,6 +60,7 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_PHASE] = "phase", [IIO_MASSCONCENTRATION] = "massconcentration", [IIO_COLORTEMP] = "colortemp", + [IIO_CHROMATICITY] = "chromaticity", }; static const char * const iio_ev_type_text[] = { @@ -175,6 +176,7 @@ static bool event_is_known(struct iio_event_data *event) case IIO_PHASE: case IIO_MASSCONCENTRATION: case IIO_COLORTEMP: + case IIO_CHROMATICITY: break; default: return false; -- cgit From ff7a65492c4c88010491ca0995a7e072d2c01879 Mon Sep 17 00:00:00 2001 From: Alejandro Colomar Date: Tue, 29 Aug 2023 20:51:22 +0200 Subject: elf, uapi: Remove struct tag 'dynamic' Such a generic struct tag shouldn't have been exposed in a public header. Since it's undocumented, we can assume it's a historical accident. And since no software (at least on Debian) relies on this tag, we can safely remove it. Here are the results of a Debian Code Search[1]: $ # packages that contain 'include [<"]linux/elf\.h[">]' $ curl -s https://codesearch.debian.net/results/e5e7c74dfcdae609/packages.txt > include $ # packages that contain '\bstruct dynamic\b' $ curl -s https://codesearch.debian.net/results/b23577e099048c6a/packages.txt > struct $ cat struct include | sort | uniq -d chromium hurd linux qemu qt6-webengine qtwebengine-opensource-src $ # chromium: Seems to hold a copy of the UAPI header. No uses of the tag. $ # hurd: Same thing as chromium. $ # linux: :) $ # qemu: Same thing as chromium. $ # qt6-webengine: Same thing as all. $ # qtwebengine-opensource-src: Yet another copy. Link: https://codesearch.debian.net/ [1] Link: https://lore.kernel.org/linux-mm/87wmxdokum.fsf@email.froward.int.ebiederm.org/T/ Cc: "Eric W. Biederman" Cc: Matthew Wilcox Cc: David Howells Cc: Rolf Eike Beer Cc: Arnd Bergmann Cc: Thomas Gleixner Cc: "Paul E. McKenney" Cc: Dave Jones Signed-off-by: Alejandro Colomar Signed-off-by: Kees Cook --- include/uapi/linux/elf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 9b731976ce2f..9417309b7230 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -140,7 +140,7 @@ typedef __s64 Elf64_Sxword; #define ELF64_ST_BIND(x) ELF_ST_BIND(x) #define ELF64_ST_TYPE(x) ELF_ST_TYPE(x) -typedef struct dynamic { +typedef struct { Elf32_Sword d_tag; union { Elf32_Sword d_val; -- cgit From 5482c0a28b2634e7a7d8ddaca7feac183e74b528 Mon Sep 17 00:00:00 2001 From: Vinayak Yadawad Date: Fri, 22 Sep 2023 14:55:51 +0530 Subject: wifi: cfg80211: OWE DH IE handling offload Introduce new feature flags for OWE offload that driver can advertise to indicate kernel/application space to avoid DH IE handling. When this flag is advertised, the driver/device will take care of DH IE inclusion and processing of peer DH IE to generate PMK. Signed-off-by: Vinayak Yadawad Link: https://lore.kernel.org/r/f891cce4b52c939dfc6b71bb2f73e560e8cad287.1695374530.git.vinayak.yadawad@broadcom.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 367e5fbc8930..0c64994b118e 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -334,6 +334,15 @@ * use %NL80211_CMD_START_AP or similar functions. */ +/** + * DOC: OWE DH IE handling offload + * + * By setting @NL80211_EXT_FEATURE_OWE_OFFLOAD flag, drivers can indicate + * kernel/application space to avoid DH IE handling. When this flag is + * advertised, the driver/device will take care of DH IE inclusion and + * processing of peer DH IE to generate PMK. + */ + /** * enum nl80211_commands - supported nl80211 commands * @@ -6411,6 +6420,12 @@ enum nl80211_feature_flags { * in authentication and deauthentication frames sent to unassociated peer * using @NL80211_CMD_FRAME. * + * @NL80211_EXT_FEATURE_OWE_OFFLOAD: Driver/Device wants to do OWE DH IE + * handling in station mode. + * + * @NL80211_EXT_FEATURE_OWE_OFFLOAD_AP: Driver/Device wants to do OWE DH IE + * handling in AP mode. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -6482,6 +6497,8 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_PUNCT, NL80211_EXT_FEATURE_SECURE_NAN, NL80211_EXT_FEATURE_AUTH_AND_DEAUTH_RANDOM_TA, + NL80211_EXT_FEATURE_OWE_OFFLOAD, + NL80211_EXT_FEATURE_OWE_OFFLOAD_AP, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, -- cgit From e2b2cd592adbd303bcc02451d32fedd511000fb0 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 20 Sep 2023 23:31:38 +0200 Subject: bpf: Add missed value to kprobe_multi link info Add missed value to kprobe_multi link info to hold the stats of missed kprobe_multi probe. The missed counter gets incremented when fprobe fails the recursion check or there's no rethook available for return probe. In either case the attached bpf program is not executed. Signed-off-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Tested-by: Song Liu Reviewed-by: Song Liu Acked-by: Hou Tao Link: https://lore.kernel.org/bpf/20230920213145.1941596-3-jolsa@kernel.org --- include/uapi/linux/bpf.h | 1 + kernel/trace/bpf_trace.c | 1 + tools/include/uapi/linux/bpf.h | 1 + 3 files changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 5f13db15a3c7..1da5b1bcce71 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6532,6 +6532,7 @@ struct bpf_link_info { __aligned_u64 addrs; __u32 count; /* in/out: kprobe_multi function count */ __u32 flags; + __u64 missed; } kprobe_multi; struct { __u32 type; /* enum bpf_perf_event_type */ diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 54827d04c9a6..6aec6e7d612a 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2614,6 +2614,7 @@ static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link, kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); info->kprobe_multi.count = kmulti_link->cnt; info->kprobe_multi.flags = kmulti_link->flags; + info->kprobe_multi.missed = kmulti_link->fp.nmissed; if (!uaddrs) return 0; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 5f13db15a3c7..1da5b1bcce71 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6532,6 +6532,7 @@ struct bpf_link_info { __aligned_u64 addrs; __u32 count; /* in/out: kprobe_multi function count */ __u32 flags; + __u64 missed; } kprobe_multi; struct { __u32 type; /* enum bpf_perf_event_type */ -- cgit From 3acf8ace68230e9558cf916847f1cc9f208abdf1 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 20 Sep 2023 23:31:39 +0200 Subject: bpf: Add missed value to kprobe perf link info Add missed value to kprobe attached through perf link info to hold the stats of missed kprobe handler execution. The kprobe's missed counter gets incremented when kprobe handler is not executed due to another kprobe running on the same cpu. Signed-off-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20230920213145.1941596-4-jolsa@kernel.org --- include/linux/trace_events.h | 6 ++++-- include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 14 ++++++++------ kernel/trace/bpf_trace.c | 5 +++-- kernel/trace/trace_kprobe.c | 14 +++++++++++--- tools/include/uapi/linux/bpf.h | 1 + 6 files changed, 28 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 21ae37e49319..5eb88a66eb68 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -761,7 +761,8 @@ struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name); void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp); int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, - u64 *probe_offset, u64 *probe_addr); + u64 *probe_offset, u64 *probe_addr, + unsigned long *missed); int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); #else @@ -801,7 +802,7 @@ static inline void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) static inline int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, u64 *probe_offset, - u64 *probe_addr) + u64 *probe_addr, unsigned long *missed) { return -EOPNOTSUPP; } @@ -877,6 +878,7 @@ extern void perf_kprobe_destroy(struct perf_event *event); extern int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, const char **symbol, u64 *probe_offset, u64 *probe_addr, + unsigned long *missed, bool perf_type_tracepoint); #endif #ifdef CONFIG_UPROBE_EVENTS diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1da5b1bcce71..70bfa997e896 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6548,6 +6548,7 @@ struct bpf_link_info { __u32 name_len; __u32 offset; /* offset from func_name */ __u64 addr; + __u64 missed; } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */ struct { __aligned_u64 tp_name; /* in/out */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 85c1d908f70f..6b5280f14a53 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3374,7 +3374,7 @@ static void bpf_perf_link_dealloc(struct bpf_link *link) static int bpf_perf_link_fill_common(const struct perf_event *event, char __user *uname, u32 ulen, u64 *probe_offset, u64 *probe_addr, - u32 *fd_type) + u32 *fd_type, unsigned long *missed) { const char *buf; u32 prog_id; @@ -3385,7 +3385,7 @@ static int bpf_perf_link_fill_common(const struct perf_event *event, return -EINVAL; err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf, - probe_offset, probe_addr); + probe_offset, probe_addr, missed); if (err) return err; if (!uname) @@ -3408,6 +3408,7 @@ static int bpf_perf_link_fill_common(const struct perf_event *event, static int bpf_perf_link_fill_kprobe(const struct perf_event *event, struct bpf_link_info *info) { + unsigned long missed; char __user *uname; u64 addr, offset; u32 ulen, type; @@ -3416,7 +3417,7 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event, uname = u64_to_user_ptr(info->perf_event.kprobe.func_name); ulen = info->perf_event.kprobe.name_len; err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr, - &type); + &type, &missed); if (err) return err; if (type == BPF_FD_TYPE_KRETPROBE) @@ -3425,6 +3426,7 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event, info->perf_event.type = BPF_PERF_EVENT_KPROBE; info->perf_event.kprobe.offset = offset; + info->perf_event.kprobe.missed = missed; if (!kallsyms_show_value(current_cred())) addr = 0; info->perf_event.kprobe.addr = addr; @@ -3444,7 +3446,7 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event, uname = u64_to_user_ptr(info->perf_event.uprobe.file_name); ulen = info->perf_event.uprobe.name_len; err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr, - &type); + &type, NULL); if (err) return err; @@ -3480,7 +3482,7 @@ static int bpf_perf_link_fill_tracepoint(const struct perf_event *event, uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name); ulen = info->perf_event.tracepoint.name_len; info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT; - return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL); + return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL, NULL); } static int bpf_perf_link_fill_perf_event(const struct perf_event *event, @@ -4813,7 +4815,7 @@ static int bpf_task_fd_query(const union bpf_attr *attr, err = bpf_get_perf_event_info(event, &prog_id, &fd_type, &buf, &probe_offset, - &probe_addr); + &probe_addr, NULL); if (!err) err = bpf_task_fd_query_copy(attr, uattr, prog_id, fd_type, buf, diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 6aec6e7d612a..f6a7d2524949 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2384,7 +2384,8 @@ int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog) int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, - u64 *probe_offset, u64 *probe_addr) + u64 *probe_offset, u64 *probe_addr, + unsigned long *missed) { bool is_tracepoint, is_syscall_tp; struct bpf_prog *prog; @@ -2419,7 +2420,7 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, #ifdef CONFIG_KPROBE_EVENTS if (flags & TRACE_EVENT_FL_KPROBE) err = bpf_get_kprobe_info(event, fd_type, buf, - probe_offset, probe_addr, + probe_offset, probe_addr, missed, event->attr.type == PERF_TYPE_TRACEPOINT); #endif #ifdef CONFIG_UPROBE_EVENTS diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 3d7a180a8427..961a78ffd6d2 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1189,6 +1189,12 @@ static const struct file_operations kprobe_events_ops = { .write = probes_write, }; +static unsigned long trace_kprobe_missed(struct trace_kprobe *tk) +{ + return trace_kprobe_is_return(tk) ? + tk->rp.kp.nmissed + tk->rp.nmissed : tk->rp.kp.nmissed; +} + /* Probes profiling interfaces */ static int probes_profile_seq_show(struct seq_file *m, void *v) { @@ -1200,8 +1206,7 @@ static int probes_profile_seq_show(struct seq_file *m, void *v) return 0; tk = to_trace_kprobe(ev); - nmissed = trace_kprobe_is_return(tk) ? - tk->rp.kp.nmissed + tk->rp.nmissed : tk->rp.kp.nmissed; + nmissed = trace_kprobe_missed(tk); seq_printf(m, " %-44s %15lu %15lu\n", trace_probe_name(&tk->tp), trace_kprobe_nhit(tk), @@ -1547,7 +1552,8 @@ NOKPROBE_SYMBOL(kretprobe_perf_func); int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, const char **symbol, u64 *probe_offset, - u64 *probe_addr, bool perf_type_tracepoint) + u64 *probe_addr, unsigned long *missed, + bool perf_type_tracepoint) { const char *pevent = trace_event_name(event->tp_event); const char *group = event->tp_event->class->system; @@ -1566,6 +1572,8 @@ int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, *probe_addr = kallsyms_show_value(current_cred()) ? (unsigned long)tk->rp.kp.addr : 0; *symbol = tk->symbol; + if (missed) + *missed = trace_kprobe_missed(tk); return 0; } #endif /* CONFIG_PERF_EVENTS */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1da5b1bcce71..70bfa997e896 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6548,6 +6548,7 @@ struct bpf_link_info { __u32 name_len; __u32 offset; /* offset from func_name */ __u64 addr; + __u64 missed; } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */ struct { __aligned_u64 tp_name; /* in/out */ -- cgit From 5b11888471806edf699316d4dcb9b426caebbef2 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 24 Sep 2023 22:54:51 -0700 Subject: fscrypt: support crypto data unit size less than filesystem block size Until now, fscrypt has always used the filesystem block size as the granularity of file contents encryption. Two scenarios have come up where a sub-block granularity of contents encryption would be useful: 1. Inline crypto hardware that only supports a crypto data unit size that is less than the filesystem block size. 2. Support for direct I/O at a granularity less than the filesystem block size, for example at the block device's logical block size in order to match the traditional direct I/O alignment requirement. (1) first came up with older eMMC inline crypto hardware that only supports a crypto data unit size of 512 bytes. That specific case ultimately went away because all systems with that hardware continued using out of tree code and never actually upgraded to the upstream inline crypto framework. But, now it's coming back in a new way: some current UFS controllers only support a data unit size of 4096 bytes, and there is a proposal to increase the filesystem block size to 16K. (2) was discussed as a "nice to have" feature, though not essential, when support for direct I/O on encrypted files was being upstreamed. Still, the fact that this feature has come up several times does suggest it would be wise to have available. Therefore, this patch implements it by using one of the reserved bytes in fscrypt_policy_v2 to allow users to select a sub-block data unit size. Supported data unit sizes are powers of 2 between 512 and the filesystem block size, inclusively. Support is implemented for both the FS-layer and inline crypto cases. This patch focuses on the basic support for sub-block data units. Some things are out of scope for this patch but may be addressed later: - Supporting sub-block data units in combination with FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64, in most cases. Unfortunately this combination usually causes data unit indices to exceed 32 bits, and thus fscrypt_supported_policy() correctly disallows it. The users who potentially need this combination are using f2fs. To support it, f2fs would need to provide an option to slightly reduce its max file size. - Supporting sub-block data units in combination with FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32. This has the same problem described above, but also it will need special code to make DUN wraparound still happen on a FS block boundary. - Supporting use case (2) mentioned above. The encrypted direct I/O code will need to stop requiring and assuming FS block alignment. This won't be hard, but it belongs in a separate patch. - Supporting this feature on filesystems other than ext4 and f2fs. (Filesystems declare support for it via their fscrypt_operations.) On UBIFS, sub-block data units don't make sense because UBIFS encrypts variable-length blocks as a result of compression. CephFS could support it, but a bit more work would be needed to make the fscrypt_*_block_inplace functions play nicely with sub-block data units. I don't think there's a use case for this on CephFS anyway. Link: https://lore.kernel.org/r/20230925055451.59499-6-ebiggers@kernel.org Signed-off-by: Eric Biggers --- Documentation/filesystems/fscrypt.rst | 117 ++++++++++++++++++++-------- fs/crypto/bio.c | 39 +++++----- fs/crypto/crypto.c | 139 ++++++++++++++++++---------------- fs/crypto/fscrypt_private.h | 56 +++++++++++--- fs/crypto/inline_crypt.c | 14 ++-- fs/crypto/keysetup.c | 5 ++ fs/crypto/policy.c | 34 ++++++++- fs/ext4/crypto.c | 1 + fs/f2fs/super.c | 1 + include/linux/fscrypt.h | 12 +++ include/uapi/linux/fscrypt.h | 3 +- 11 files changed, 288 insertions(+), 133 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst index a624e92f2687..28700fb41a00 100644 --- a/Documentation/filesystems/fscrypt.rst +++ b/Documentation/filesystems/fscrypt.rst @@ -261,9 +261,9 @@ DIRECT_KEY policies The Adiantum encryption mode (see `Encryption modes and usage`_) is suitable for both contents and filenames encryption, and it accepts -long IVs --- long enough to hold both an 8-byte logical block number -and a 16-byte per-file nonce. Also, the overhead of each Adiantum key -is greater than that of an AES-256-XTS key. +long IVs --- long enough to hold both an 8-byte data unit index and a +16-byte per-file nonce. Also, the overhead of each Adiantum key is +greater than that of an AES-256-XTS key. Therefore, to improve performance and save memory, for Adiantum a "direct key" configuration is supported. When the user has enabled @@ -300,8 +300,8 @@ IV_INO_LBLK_32 policies IV_INO_LBLK_32 policies work like IV_INO_LBLK_64, except that for IV_INO_LBLK_32, the inode number is hashed with SipHash-2-4 (where the -SipHash key is derived from the master key) and added to the file -logical block number mod 2^32 to produce a 32-bit IV. +SipHash key is derived from the master key) and added to the file data +unit index mod 2^32 to produce a 32-bit IV. This format is optimized for use with inline encryption hardware compliant with the eMMC v5.2 standard, which supports only 32 IV bits @@ -451,31 +451,62 @@ acceleration is recommended: Contents encryption ------------------- -For file contents, each filesystem block is encrypted independently. -Starting from Linux kernel 5.5, encryption of filesystems with block -size less than system's page size is supported. - -Each block's IV is set to the logical block number within the file as -a little endian number, except that: - -- With CBC mode encryption, ESSIV is also used. Specifically, each IV - is encrypted with AES-256 where the AES-256 key is the SHA-256 hash - of the file's data encryption key. - -- With `DIRECT_KEY policies`_, the file's nonce is appended to the IV. - Currently this is only allowed with the Adiantum encryption mode. - -- With `IV_INO_LBLK_64 policies`_, the logical block number is limited - to 32 bits and is placed in bits 0-31 of the IV. The inode number - (which is also limited to 32 bits) is placed in bits 32-63. - -- With `IV_INO_LBLK_32 policies`_, the logical block number is limited - to 32 bits and is placed in bits 0-31 of the IV. The inode number - is then hashed and added mod 2^32. - -Note that because file logical block numbers are included in the IVs, -filesystems must enforce that blocks are never shifted around within -encrypted files, e.g. via "collapse range" or "insert range". +For contents encryption, each file's contents is divided into "data +units". Each data unit is encrypted independently. The IV for each +data unit incorporates the zero-based index of the data unit within +the file. This ensures that each data unit within a file is encrypted +differently, which is essential to prevent leaking information. + +Note: the encryption depending on the offset into the file means that +operations like "collapse range" and "insert range" that rearrange the +extent mapping of files are not supported on encrypted files. + +There are two cases for the sizes of the data units: + +* Fixed-size data units. This is how all filesystems other than UBIFS + work. A file's data units are all the same size; the last data unit + is zero-padded if needed. By default, the data unit size is equal + to the filesystem block size. On some filesystems, users can select + a sub-block data unit size via the ``log2_data_unit_size`` field of + the encryption policy; see `FS_IOC_SET_ENCRYPTION_POLICY`_. + +* Variable-size data units. This is what UBIFS does. Each "UBIFS + data node" is treated as a crypto data unit. Each contains variable + length, possibly compressed data, zero-padded to the next 16-byte + boundary. Users cannot select a sub-block data unit size on UBIFS. + +In the case of compression + encryption, the compressed data is +encrypted. UBIFS compression works as described above. f2fs +compression works a bit differently; it compresses a number of +filesystem blocks into a smaller number of filesystem blocks. +Therefore a f2fs-compressed file still uses fixed-size data units, and +it is encrypted in a similar way to a file containing holes. + +As mentioned in `Key hierarchy`_, the default encryption setting uses +per-file keys. In this case, the IV for each data unit is simply the +index of the data unit in the file. However, users can select an +encryption setting that does not use per-file keys. For these, some +kind of file identifier is incorporated into the IVs as follows: + +- With `DIRECT_KEY policies`_, the data unit index is placed in bits + 0-63 of the IV, and the file's nonce is placed in bits 64-191. + +- With `IV_INO_LBLK_64 policies`_, the data unit index is placed in + bits 0-31 of the IV, and the file's inode number is placed in bits + 32-63. This setting is only allowed when data unit indices and + inode numbers fit in 32 bits. + +- With `IV_INO_LBLK_32 policies`_, the file's inode number is hashed + and added to the data unit index. The resulting value is truncated + to 32 bits and placed in bits 0-31 of the IV. This setting is only + allowed when data unit indices and inode numbers fit in 32 bits. + +The byte order of the IV is always little endian. + +If the user selects FSCRYPT_MODE_AES_128_CBC for the contents mode, an +ESSIV layer is automatically included. In this case, before the IV is +passed to AES-128-CBC, it is encrypted with AES-256 where the AES-256 +key is the SHA-256 hash of the file's contents encryption key. Filenames encryption -------------------- @@ -544,7 +575,8 @@ follows:: __u8 contents_encryption_mode; __u8 filenames_encryption_mode; __u8 flags; - __u8 __reserved[4]; + __u8 log2_data_unit_size; + __u8 __reserved[3]; __u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]; }; @@ -586,6 +618,29 @@ This structure must be initialized as follows: The DIRECT_KEY, IV_INO_LBLK_64, and IV_INO_LBLK_32 flags are mutually exclusive. +- ``log2_data_unit_size`` is the log2 of the data unit size in bytes, + or 0 to select the default data unit size. The data unit size is + the granularity of file contents encryption. For example, setting + ``log2_data_unit_size`` to 12 causes file contents be passed to the + underlying encryption algorithm (such as AES-256-XTS) in 4096-byte + data units, each with its own IV. + + Not all filesystems support setting ``log2_data_unit_size``. ext4 + and f2fs support it since Linux v6.7. On filesystems that support + it, the supported nonzero values are 9 through the log2 of the + filesystem block size, inclusively. The default value of 0 selects + the filesystem block size. + + The main use case for ``log2_data_unit_size`` is for selecting a + data unit size smaller than the filesystem block size for + compatibility with inline encryption hardware that only supports + smaller data unit sizes. ``/sys/block/$disk/queue/crypto/`` may be + useful for checking which data unit sizes are supported by a + particular system's inline encryption hardware. + + Leave this field zeroed unless you are certain you need it. Using + an unnecessarily small data unit size reduces performance. + - For v2 encryption policies, ``__reserved`` must be zeroed. - For v1 encryption policies, ``master_key_descriptor`` specifies how diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c index 62e1a3dd8357..c8cf77065272 100644 --- a/fs/crypto/bio.c +++ b/fs/crypto/bio.c @@ -111,10 +111,14 @@ out: int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, sector_t pblk, unsigned int len) { - const unsigned int blockbits = inode->i_blkbits; - const unsigned int blocksize = 1 << blockbits; - const unsigned int blocks_per_page_bits = PAGE_SHIFT - blockbits; - const unsigned int blocks_per_page = 1 << blocks_per_page_bits; + const struct fscrypt_info *ci = inode->i_crypt_info; + const unsigned int du_bits = ci->ci_data_unit_bits; + const unsigned int du_size = 1U << du_bits; + const unsigned int du_per_page_bits = PAGE_SHIFT - du_bits; + const unsigned int du_per_page = 1U << du_per_page_bits; + u64 du_index = (u64)lblk << (inode->i_blkbits - du_bits); + u64 du_remaining = (u64)len << (inode->i_blkbits - du_bits); + sector_t sector = pblk << (inode->i_blkbits - SECTOR_SHIFT); struct page *pages[16]; /* write up to 16 pages at a time */ unsigned int nr_pages; unsigned int i; @@ -130,8 +134,8 @@ int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, len); BUILD_BUG_ON(ARRAY_SIZE(pages) > BIO_MAX_VECS); - nr_pages = min_t(unsigned int, ARRAY_SIZE(pages), - (len + blocks_per_page - 1) >> blocks_per_page_bits); + nr_pages = min_t(u64, ARRAY_SIZE(pages), + (du_remaining + du_per_page - 1) >> du_per_page_bits); /* * We need at least one page for ciphertext. Allocate the first one @@ -154,21 +158,22 @@ int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, bio = bio_alloc(inode->i_sb->s_bdev, nr_pages, REQ_OP_WRITE, GFP_NOFS); do { - bio->bi_iter.bi_sector = pblk << (blockbits - 9); + bio->bi_iter.bi_sector = sector; i = 0; offset = 0; do { - err = fscrypt_crypt_block(inode, FS_ENCRYPT, lblk, - ZERO_PAGE(0), pages[i], - blocksize, offset, GFP_NOFS); + err = fscrypt_crypt_data_unit(ci, FS_ENCRYPT, du_index, + ZERO_PAGE(0), pages[i], + du_size, offset, + GFP_NOFS); if (err) goto out; - lblk++; - pblk++; - len--; - offset += blocksize; - if (offset == PAGE_SIZE || len == 0) { + du_index++; + sector += 1U << (du_bits - SECTOR_SHIFT); + du_remaining--; + offset += du_size; + if (offset == PAGE_SIZE || du_remaining == 0) { ret = bio_add_page(bio, pages[i++], offset, 0); if (WARN_ON_ONCE(ret != offset)) { err = -EIO; @@ -176,13 +181,13 @@ int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, } offset = 0; } - } while (i != nr_pages && len != 0); + } while (i != nr_pages && du_remaining != 0); err = submit_bio_wait(bio); if (err) goto out; bio_reset(bio, inode->i_sb->s_bdev, REQ_OP_WRITE); - } while (len != 0); + } while (du_remaining != 0); err = 0; out: bio_put(bio); diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index aed0c5ea7578..85e2f66dd663 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -77,14 +77,14 @@ void fscrypt_free_bounce_page(struct page *bounce_page) EXPORT_SYMBOL(fscrypt_free_bounce_page); /* - * Generate the IV for the given logical block number within the given file. - * For filenames encryption, lblk_num == 0. + * Generate the IV for the given data unit index within the given file. + * For filenames encryption, index == 0. * * Keep this in sync with fscrypt_limit_io_blocks(). fscrypt_limit_io_blocks() * needs to know about any IV generation methods where the low bits of IV don't - * simply contain the lblk_num (e.g., IV_INO_LBLK_32). + * simply contain the data unit index (e.g., IV_INO_LBLK_32). */ -void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, +void fscrypt_generate_iv(union fscrypt_iv *iv, u64 index, const struct fscrypt_info *ci) { u8 flags = fscrypt_policy_flags(&ci->ci_policy); @@ -92,29 +92,29 @@ void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, memset(iv, 0, ci->ci_mode->ivsize); if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) { - WARN_ON_ONCE(lblk_num > U32_MAX); + WARN_ON_ONCE(index > U32_MAX); WARN_ON_ONCE(ci->ci_inode->i_ino > U32_MAX); - lblk_num |= (u64)ci->ci_inode->i_ino << 32; + index |= (u64)ci->ci_inode->i_ino << 32; } else if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) { - WARN_ON_ONCE(lblk_num > U32_MAX); - lblk_num = (u32)(ci->ci_hashed_ino + lblk_num); + WARN_ON_ONCE(index > U32_MAX); + index = (u32)(ci->ci_hashed_ino + index); } else if (flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) { memcpy(iv->nonce, ci->ci_nonce, FSCRYPT_FILE_NONCE_SIZE); } - iv->lblk_num = cpu_to_le64(lblk_num); + iv->index = cpu_to_le64(index); } -/* Encrypt or decrypt a single filesystem block of file contents */ -int fscrypt_crypt_block(const struct inode *inode, fscrypt_direction_t rw, - u64 lblk_num, struct page *src_page, - struct page *dest_page, unsigned int len, - unsigned int offs, gfp_t gfp_flags) +/* Encrypt or decrypt a single "data unit" of file contents. */ +int fscrypt_crypt_data_unit(const struct fscrypt_info *ci, + fscrypt_direction_t rw, u64 index, + struct page *src_page, struct page *dest_page, + unsigned int len, unsigned int offs, + gfp_t gfp_flags) { union fscrypt_iv iv; struct skcipher_request *req = NULL; DECLARE_CRYPTO_WAIT(wait); struct scatterlist dst, src; - struct fscrypt_info *ci = inode->i_crypt_info; struct crypto_skcipher *tfm = ci->ci_enc_key.tfm; int res = 0; @@ -123,7 +123,7 @@ int fscrypt_crypt_block(const struct inode *inode, fscrypt_direction_t rw, if (WARN_ON_ONCE(len % FSCRYPT_CONTENTS_ALIGNMENT != 0)) return -EINVAL; - fscrypt_generate_iv(&iv, lblk_num, ci); + fscrypt_generate_iv(&iv, index, ci); req = skcipher_request_alloc(tfm, gfp_flags); if (!req) @@ -144,28 +144,29 @@ int fscrypt_crypt_block(const struct inode *inode, fscrypt_direction_t rw, res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait); skcipher_request_free(req); if (res) { - fscrypt_err(inode, "%scryption failed for block %llu: %d", - (rw == FS_DECRYPT ? "De" : "En"), lblk_num, res); + fscrypt_err(ci->ci_inode, + "%scryption failed for data unit %llu: %d", + (rw == FS_DECRYPT ? "De" : "En"), index, res); return res; } return 0; } /** - * fscrypt_encrypt_pagecache_blocks() - Encrypt filesystem blocks from a - * pagecache page - * @page: The locked pagecache page containing the block(s) to encrypt - * @len: Total size of the block(s) to encrypt. Must be a nonzero - * multiple of the filesystem's block size. - * @offs: Byte offset within @page of the first block to encrypt. Must be - * a multiple of the filesystem's block size. - * @gfp_flags: Memory allocation flags. See details below. + * fscrypt_encrypt_pagecache_blocks() - Encrypt data from a pagecache page + * @page: the locked pagecache page containing the data to encrypt + * @len: size of the data to encrypt, in bytes + * @offs: offset within @page of the data to encrypt, in bytes + * @gfp_flags: memory allocation flags; see details below * - * A new bounce page is allocated, and the specified block(s) are encrypted into - * it. In the bounce page, the ciphertext block(s) will be located at the same - * offsets at which the plaintext block(s) were located in the source page; any - * other parts of the bounce page will be left uninitialized. However, normally - * blocksize == PAGE_SIZE and the whole page is encrypted at once. + * This allocates a new bounce page and encrypts the given data into it. The + * length and offset of the data must be aligned to the file's crypto data unit + * size. Alignment to the filesystem block size fulfills this requirement, as + * the filesystem block size is always a multiple of the data unit size. + * + * In the bounce page, the ciphertext data will be located at the same offset at + * which the plaintext data was located in the source page. Any other parts of + * the bounce page will be left uninitialized. * * This is for use by the filesystem's ->writepages() method. * @@ -183,28 +184,29 @@ struct page *fscrypt_encrypt_pagecache_blocks(struct page *page, { const struct inode *inode = page->mapping->host; - const unsigned int blockbits = inode->i_blkbits; - const unsigned int blocksize = 1 << blockbits; + const struct fscrypt_info *ci = inode->i_crypt_info; + const unsigned int du_bits = ci->ci_data_unit_bits; + const unsigned int du_size = 1U << du_bits; struct page *ciphertext_page; - u64 lblk_num = ((u64)page->index << (PAGE_SHIFT - blockbits)) + - (offs >> blockbits); + u64 index = ((u64)page->index << (PAGE_SHIFT - du_bits)) + + (offs >> du_bits); unsigned int i; int err; if (WARN_ON_ONCE(!PageLocked(page))) return ERR_PTR(-EINVAL); - if (WARN_ON_ONCE(len <= 0 || !IS_ALIGNED(len | offs, blocksize))) + if (WARN_ON_ONCE(len <= 0 || !IS_ALIGNED(len | offs, du_size))) return ERR_PTR(-EINVAL); ciphertext_page = fscrypt_alloc_bounce_page(gfp_flags); if (!ciphertext_page) return ERR_PTR(-ENOMEM); - for (i = offs; i < offs + len; i += blocksize, lblk_num++) { - err = fscrypt_crypt_block(inode, FS_ENCRYPT, lblk_num, - page, ciphertext_page, - blocksize, i, gfp_flags); + for (i = offs; i < offs + len; i += du_size, index++) { + err = fscrypt_crypt_data_unit(ci, FS_ENCRYPT, index, + page, ciphertext_page, + du_size, i, gfp_flags); if (err) { fscrypt_free_bounce_page(ciphertext_page); return ERR_PTR(err); @@ -231,30 +233,33 @@ EXPORT_SYMBOL(fscrypt_encrypt_pagecache_blocks); * arbitrary page, not necessarily in the original pagecache page. The @inode * and @lblk_num must be specified, as they can't be determined from @page. * + * This is not compatible with fscrypt_operations::supports_subblock_data_units. + * * Return: 0 on success; -errno on failure */ int fscrypt_encrypt_block_inplace(const struct inode *inode, struct page *page, unsigned int len, unsigned int offs, u64 lblk_num, gfp_t gfp_flags) { - return fscrypt_crypt_block(inode, FS_ENCRYPT, lblk_num, page, page, - len, offs, gfp_flags); + if (WARN_ON_ONCE(inode->i_sb->s_cop->supports_subblock_data_units)) + return -EOPNOTSUPP; + return fscrypt_crypt_data_unit(inode->i_crypt_info, FS_ENCRYPT, + lblk_num, page, page, len, offs, + gfp_flags); } EXPORT_SYMBOL(fscrypt_encrypt_block_inplace); /** - * fscrypt_decrypt_pagecache_blocks() - Decrypt filesystem blocks in a - * pagecache folio - * @folio: The locked pagecache folio containing the block(s) to decrypt - * @len: Total size of the block(s) to decrypt. Must be a nonzero - * multiple of the filesystem's block size. - * @offs: Byte offset within @folio of the first block to decrypt. Must be - * a multiple of the filesystem's block size. + * fscrypt_decrypt_pagecache_blocks() - Decrypt data from a pagecache folio + * @folio: the pagecache folio containing the data to decrypt + * @len: size of the data to decrypt, in bytes + * @offs: offset within @folio of the data to decrypt, in bytes * - * The specified block(s) are decrypted in-place within the pagecache folio, - * which must still be locked and not uptodate. - * - * This is for use by the filesystem's ->readahead() method. + * Decrypt data that has just been read from an encrypted file. The data must + * be located in a pagecache folio that is still locked and not yet uptodate. + * The length and offset of the data must be aligned to the file's crypto data + * unit size. Alignment to the filesystem block size fulfills this requirement, + * as the filesystem block size is always a multiple of the data unit size. * * Return: 0 on success; -errno on failure */ @@ -262,25 +267,26 @@ int fscrypt_decrypt_pagecache_blocks(struct folio *folio, size_t len, size_t offs) { const struct inode *inode = folio->mapping->host; - const unsigned int blockbits = inode->i_blkbits; - const unsigned int blocksize = 1 << blockbits; - u64 lblk_num = ((u64)folio->index << (PAGE_SHIFT - blockbits)) + - (offs >> blockbits); + const struct fscrypt_info *ci = inode->i_crypt_info; + const unsigned int du_bits = ci->ci_data_unit_bits; + const unsigned int du_size = 1U << du_bits; + u64 index = ((u64)folio->index << (PAGE_SHIFT - du_bits)) + + (offs >> du_bits); size_t i; int err; if (WARN_ON_ONCE(!folio_test_locked(folio))) return -EINVAL; - if (WARN_ON_ONCE(len <= 0 || !IS_ALIGNED(len | offs, blocksize))) + if (WARN_ON_ONCE(len <= 0 || !IS_ALIGNED(len | offs, du_size))) return -EINVAL; - for (i = offs; i < offs + len; i += blocksize, lblk_num++) { + for (i = offs; i < offs + len; i += du_size, index++) { struct page *page = folio_page(folio, i >> PAGE_SHIFT); - err = fscrypt_crypt_block(inode, FS_DECRYPT, lblk_num, page, - page, blocksize, i & ~PAGE_MASK, - GFP_NOFS); + err = fscrypt_crypt_data_unit(ci, FS_DECRYPT, index, page, + page, du_size, i & ~PAGE_MASK, + GFP_NOFS); if (err) return err; } @@ -302,14 +308,19 @@ EXPORT_SYMBOL(fscrypt_decrypt_pagecache_blocks); * arbitrary page, not necessarily in the original pagecache page. The @inode * and @lblk_num must be specified, as they can't be determined from @page. * + * This is not compatible with fscrypt_operations::supports_subblock_data_units. + * * Return: 0 on success; -errno on failure */ int fscrypt_decrypt_block_inplace(const struct inode *inode, struct page *page, unsigned int len, unsigned int offs, u64 lblk_num) { - return fscrypt_crypt_block(inode, FS_DECRYPT, lblk_num, page, page, - len, offs, GFP_NOFS); + if (WARN_ON_ONCE(inode->i_sb->s_cop->supports_subblock_data_units)) + return -EOPNOTSUPP; + return fscrypt_crypt_data_unit(inode->i_crypt_info, FS_DECRYPT, + lblk_num, page, page, len, offs, + GFP_NOFS); } EXPORT_SYMBOL(fscrypt_decrypt_block_inplace); diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 4b113214b53a..9c5e83baa3f1 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -47,7 +47,8 @@ struct fscrypt_context_v2 { u8 contents_encryption_mode; u8 filenames_encryption_mode; u8 flags; - u8 __reserved[4]; + u8 log2_data_unit_size; + u8 __reserved[3]; u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]; u8 nonce[FSCRYPT_FILE_NONCE_SIZE]; }; @@ -165,6 +166,26 @@ fscrypt_policy_flags(const union fscrypt_policy *policy) BUG(); } +static inline int +fscrypt_policy_v2_du_bits(const struct fscrypt_policy_v2 *policy, + const struct inode *inode) +{ + return policy->log2_data_unit_size ?: inode->i_blkbits; +} + +static inline int +fscrypt_policy_du_bits(const union fscrypt_policy *policy, + const struct inode *inode) +{ + switch (policy->version) { + case FSCRYPT_POLICY_V1: + return inode->i_blkbits; + case FSCRYPT_POLICY_V2: + return fscrypt_policy_v2_du_bits(&policy->v2, inode); + } + BUG(); +} + /* * For encrypted symlinks, the ciphertext length is stored at the beginning * of the string in little-endian format. @@ -211,6 +232,16 @@ struct fscrypt_info { bool ci_inlinecrypt; #endif + /* + * log2 of the data unit size (granularity of contents encryption) of + * this file. This is computable from ci_policy and ci_inode but is + * cached here for efficiency. Only used for regular files. + */ + u8 ci_data_unit_bits; + + /* Cached value: log2 of number of data units per FS block */ + u8 ci_data_units_per_block_bits; + /* * Encryption mode used for this inode. It corresponds to either the * contents or filenames encryption mode, depending on the inode type. @@ -265,10 +296,11 @@ typedef enum { /* crypto.c */ extern struct kmem_cache *fscrypt_info_cachep; int fscrypt_initialize(struct super_block *sb); -int fscrypt_crypt_block(const struct inode *inode, fscrypt_direction_t rw, - u64 lblk_num, struct page *src_page, - struct page *dest_page, unsigned int len, - unsigned int offs, gfp_t gfp_flags); +int fscrypt_crypt_data_unit(const struct fscrypt_info *ci, + fscrypt_direction_t rw, u64 index, + struct page *src_page, struct page *dest_page, + unsigned int len, unsigned int offs, + gfp_t gfp_flags); struct page *fscrypt_alloc_bounce_page(gfp_t gfp_flags); void __printf(3, 4) __cold @@ -283,8 +315,8 @@ fscrypt_msg(const struct inode *inode, const char *level, const char *fmt, ...); union fscrypt_iv { struct { - /* logical block number within the file */ - __le64 lblk_num; + /* zero-based index of data unit within the file */ + __le64 index; /* per-file nonce; only set in DIRECT_KEY mode */ u8 nonce[FSCRYPT_FILE_NONCE_SIZE]; @@ -293,17 +325,17 @@ union fscrypt_iv { __le64 dun[FSCRYPT_MAX_IV_SIZE / sizeof(__le64)]; }; -void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, +void fscrypt_generate_iv(union fscrypt_iv *iv, u64 index, const struct fscrypt_info *ci); /* - * Return the number of bits used by the maximum file logical block number that - * is possible on the given filesystem. + * Return the number of bits used by the maximum file data unit index that is + * possible on the given filesystem, using the given log2 data unit size. */ static inline int -fscrypt_max_file_lblk_bits(const struct super_block *sb) +fscrypt_max_file_dun_bits(const struct super_block *sb, int du_bits) { - return fls64(sb->s_maxbytes - 1) - sb->s_blocksize_bits; + return fls64(sb->s_maxbytes - 1) - du_bits; } /* fname.c */ diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c index 7d9f6c167de5..8c6d37d6225a 100644 --- a/fs/crypto/inline_crypt.c +++ b/fs/crypto/inline_crypt.c @@ -43,6 +43,7 @@ static unsigned int fscrypt_get_dun_bytes(const struct fscrypt_info *ci) { const struct super_block *sb = ci->ci_inode->i_sb; unsigned int flags = fscrypt_policy_flags(&ci->ci_policy); + int dun_bits; if (flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) return offsetofend(union fscrypt_iv, nonce); @@ -53,8 +54,9 @@ static unsigned int fscrypt_get_dun_bytes(const struct fscrypt_info *ci) if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) return sizeof(__le32); - /* Default case: IVs are just the file logical block number */ - return DIV_ROUND_UP(fscrypt_max_file_lblk_bits(sb), 8); + /* Default case: IVs are just the file data unit index */ + dun_bits = fscrypt_max_file_dun_bits(sb, ci->ci_data_unit_bits); + return DIV_ROUND_UP(dun_bits, 8); } /* @@ -126,7 +128,7 @@ int fscrypt_select_encryption_impl(struct fscrypt_info *ci) * crypto configuration that the file would use. */ crypto_cfg.crypto_mode = ci->ci_mode->blk_crypto_mode; - crypto_cfg.data_unit_size = sb->s_blocksize; + crypto_cfg.data_unit_size = 1U << ci->ci_data_unit_bits; crypto_cfg.dun_bytes = fscrypt_get_dun_bytes(ci); devs = fscrypt_get_devices(sb, &num_devs); @@ -165,7 +167,8 @@ int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key, return -ENOMEM; err = blk_crypto_init_key(blk_key, raw_key, crypto_mode, - fscrypt_get_dun_bytes(ci), sb->s_blocksize); + fscrypt_get_dun_bytes(ci), + 1U << ci->ci_data_unit_bits); if (err) { fscrypt_err(inode, "error %d initializing blk-crypto key", err); goto fail; @@ -232,10 +235,11 @@ EXPORT_SYMBOL_GPL(__fscrypt_inode_uses_inline_crypto); static void fscrypt_generate_dun(const struct fscrypt_info *ci, u64 lblk_num, u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE]) { + u64 index = lblk_num << ci->ci_data_units_per_block_bits; union fscrypt_iv iv; int i; - fscrypt_generate_iv(&iv, lblk_num, ci); + fscrypt_generate_iv(&iv, index, ci); BUILD_BUG_ON(FSCRYPT_MAX_IV_SIZE > BLK_CRYPTO_MAX_IV_SIZE); memset(dun, 0, BLK_CRYPTO_MAX_IV_SIZE); diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index 361f41ef46c7..608599f8aa57 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -580,6 +580,11 @@ fscrypt_setup_encryption_info(struct inode *inode, WARN_ON_ONCE(mode->ivsize > FSCRYPT_MAX_IV_SIZE); crypt_info->ci_mode = mode; + crypt_info->ci_data_unit_bits = + fscrypt_policy_du_bits(&crypt_info->ci_policy, inode); + crypt_info->ci_data_units_per_block_bits = + inode->i_blkbits - crypt_info->ci_data_unit_bits; + res = setup_file_encryption_key(crypt_info, need_dirhash_key, &mk); if (res) goto out; diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index 32709dad9762..2fb3f6a1258e 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -165,10 +165,11 @@ static bool supported_iv_ino_lblk_policy(const struct fscrypt_policy_v2 *policy, } /* - * IV_INO_LBLK_64 and IV_INO_LBLK_32 both require that file logical - * block numbers fit in 32 bits. + * IV_INO_LBLK_64 and IV_INO_LBLK_32 both require that file data unit + * indices fit in 32 bits. */ - if (fscrypt_max_file_lblk_bits(sb) > 32) { + if (fscrypt_max_file_dun_bits(sb, + fscrypt_policy_v2_du_bits(policy, inode)) > 32) { fscrypt_warn(inode, "Can't use %s policy on filesystem '%s' because its maximum file size is too large", type, sb->s_id); @@ -243,6 +244,31 @@ static bool fscrypt_supported_v2_policy(const struct fscrypt_policy_v2 *policy, return false; } + if (policy->log2_data_unit_size) { + if (!inode->i_sb->s_cop->supports_subblock_data_units) { + fscrypt_warn(inode, + "Filesystem does not support configuring crypto data unit size"); + return false; + } + if (policy->log2_data_unit_size > inode->i_blkbits || + policy->log2_data_unit_size < SECTOR_SHIFT /* 9 */) { + fscrypt_warn(inode, + "Unsupported log2_data_unit_size in encryption policy: %d", + policy->log2_data_unit_size); + return false; + } + if (policy->log2_data_unit_size != inode->i_blkbits && + (policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32)) { + /* + * Not safe to enable yet, as we need to ensure that DUN + * wraparound can only occur on a FS block boundary. + */ + fscrypt_warn(inode, + "Sub-block data units not yet supported with IV_INO_LBLK_32"); + return false; + } + } + if ((policy->flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) && !supported_direct_key_modes(inode, policy->contents_encryption_mode, policy->filenames_encryption_mode)) @@ -329,6 +355,7 @@ static int fscrypt_new_context(union fscrypt_context *ctx_u, ctx->filenames_encryption_mode = policy->filenames_encryption_mode; ctx->flags = policy->flags; + ctx->log2_data_unit_size = policy->log2_data_unit_size; memcpy(ctx->master_key_identifier, policy->master_key_identifier, sizeof(ctx->master_key_identifier)); @@ -389,6 +416,7 @@ int fscrypt_policy_from_context(union fscrypt_policy *policy_u, policy->filenames_encryption_mode = ctx->filenames_encryption_mode; policy->flags = ctx->flags; + policy->log2_data_unit_size = ctx->log2_data_unit_size; memcpy(policy->__reserved, ctx->__reserved, sizeof(policy->__reserved)); memcpy(policy->master_key_identifier, diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c index 9e36731701ba..7ae0b61258a7 100644 --- a/fs/ext4/crypto.c +++ b/fs/ext4/crypto.c @@ -235,6 +235,7 @@ static bool ext4_has_stable_inodes(struct super_block *sb) const struct fscrypt_operations ext4_cryptops = { .needs_bounce_pages = 1, .has_32bit_inodes = 1, + .supports_subblock_data_units = 1, .legacy_key_prefix = "ext4:", .get_context = ext4_get_context, .set_context = ext4_set_context, diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index c44915713264..66a5bf4216b7 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3226,6 +3226,7 @@ static struct block_device **f2fs_get_devices(struct super_block *sb, static const struct fscrypt_operations f2fs_cryptops = { .needs_bounce_pages = 1, .has_32bit_inodes = 1, + .supports_subblock_data_units = 1, .legacy_key_prefix = "f2fs:", .get_context = f2fs_get_context, .set_context = f2fs_set_context, diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 09a3cacbf62a..b559e6f77707 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -85,6 +85,18 @@ struct fscrypt_operations { */ unsigned int has_32bit_inodes : 1; + /* + * If set, then fs/crypto/ will allow users to select a crypto data unit + * size that is less than the filesystem block size. This is done via + * the log2_data_unit_size field of the fscrypt policy. This flag is + * not compatible with filesystems that encrypt variable-length blocks + * (i.e. blocks that aren't all equal to filesystem's block size), for + * example as a result of compression. It's also not compatible with + * the fscrypt_encrypt_block_inplace() and + * fscrypt_decrypt_block_inplace() functions. + */ + unsigned int supports_subblock_data_units : 1; + /* * This field exists only for backwards compatibility reasons and should * only be set by the filesystems that are setting it already. It diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h index fd1fb0d5389d..7a8f4c290187 100644 --- a/include/uapi/linux/fscrypt.h +++ b/include/uapi/linux/fscrypt.h @@ -71,7 +71,8 @@ struct fscrypt_policy_v2 { __u8 contents_encryption_mode; __u8 filenames_encryption_mode; __u8 flags; - __u8 __reserved[4]; + __u8 log2_data_unit_size; + __u8 __reserved[3]; __u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]; }; -- cgit From d62d8e7b59f9d7ed9b6eaaa788fee0d727b7d3ad Mon Sep 17 00:00:00 2001 From: Marvin Lin Date: Fri, 22 Sep 2023 14:24:02 +0800 Subject: media: v4l: Add HEXTILE compressed format Add HEXTILE compressed format which is defined in Remote Framebuffer Protocol (RFC 6143, chapter 7.7.4 Hextile Encoding) and is used by Encoding Compression Engine (ECE) present on Nuvoton NPCM SoCs. Signed-off-by: Marvin Lin Reviewed-by: Nicolas Dufresne Signed-off-by: Hans Verkuil --- Documentation/userspace-api/media/v4l/pixfmt-reserved.rst | 7 +++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 1 + include/uapi/linux/videodev2.h | 1 + 3 files changed, 9 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst index 296ad2025e8d..886ba7b08d6b 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst @@ -288,6 +288,13 @@ please make a proposal on the linux-media mailing list. - 'MT2110R' - This format is two-planar 10-Bit raster mode and having similitude with ``V4L2_PIX_FMT_MM21`` in term of alignment and tiling. Used for AVC. + * .. _V4L2-PIX-FMT-HEXTILE: + + - ``V4L2_PIX_FMT_HEXTILE`` + - 'HXTL' + - Compressed format used by Nuvoton NPCM video driver. This format is + defined in Remote Framebuffer Protocol (RFC 6143, chapter 7.7.4 Hextile + Encoding). .. raw:: latex \normalsize diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index f4d9d6279094..9b1de54ce379 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1510,6 +1510,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_AV1_FRAME: descr = "AV1 Frame"; break; case V4L2_PIX_FMT_MT2110T: descr = "Mediatek 10bit Tile Mode"; break; case V4L2_PIX_FMT_MT2110R: descr = "Mediatek 10bit Raster Mode"; break; + case V4L2_PIX_FMT_HEXTILE: descr = "Hextile Compressed Format"; break; default: if (fmt->description[0]) return; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 78260e5d9985..c3d4e490ce7c 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -804,6 +804,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_QC08C v4l2_fourcc('Q', '0', '8', 'C') /* Qualcomm 8-bit compressed */ #define V4L2_PIX_FMT_QC10C v4l2_fourcc('Q', '1', '0', 'C') /* Qualcomm 10-bit compressed */ #define V4L2_PIX_FMT_AJPG v4l2_fourcc('A', 'J', 'P', 'G') /* Aspeed JPEG */ +#define V4L2_PIX_FMT_HEXTILE v4l2_fourcc('H', 'X', 'T', 'L') /* Hextile compressed */ /* 10bit raw packed, 32 bytes for every 25 pixels, last LSB 6 bits unused */ #define V4L2_PIX_FMT_IPU3_SBGGR10 v4l2_fourcc('i', 'p', '3', 'b') /* IPU3 packed 10-bit BGGR bayer */ -- cgit From 2817154cd18942cd89e254d3764a378518a3270f Mon Sep 17 00:00:00 2001 From: Marvin Lin Date: Fri, 22 Sep 2023 14:24:03 +0800 Subject: media: v4l2-ctrls: Add user control base for Nuvoton NPCM controls Add a control base for Nuvoton NPCM driver controls, and reserve 16 controls. Signed-off-by: Marvin Lin Signed-off-by: Hans Verkuil --- include/uapi/linux/v4l2-controls.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index c3604a0a3e30..68db66d4aae8 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -203,6 +203,12 @@ enum v4l2_colorfx { */ #define V4L2_CID_USER_ASPEED_BASE (V4L2_CID_USER_BASE + 0x11a0) +/* + * The base for Nuvoton NPCM driver controls. + * We reserve 16 controls for this driver. + */ +#define V4L2_CID_USER_NPCM_BASE (V4L2_CID_USER_BASE + 0x11b0) + /* MPEG-class control IDs */ /* The MPEG controls are applicable to all codec controls * and the 'MPEG' part of the define is historical */ -- cgit From 1568583b3977f232e6e7a652fd4be95a11d0ecae Mon Sep 17 00:00:00 2001 From: Marvin Lin Date: Fri, 22 Sep 2023 14:24:04 +0800 Subject: media: uapi: Add controls for NPCM video driver Create controls for Nuvoton NPCM video driver to support setting capture mode of Video Capture/Differentiation (VCD) engine and getting the count of HEXTILE rectangles that is compressed by Encoding Compression Engine (ECE). Signed-off-by: Marvin Lin Signed-off-by: Hans Verkuil --- .../userspace-api/media/drivers/index.rst | 1 + .../userspace-api/media/drivers/npcm-video.rst | 66 ++++++++++++++++++++++ include/uapi/linux/npcm-video.h | 41 ++++++++++++++ 3 files changed, 108 insertions(+) create mode 100644 Documentation/userspace-api/media/drivers/npcm-video.rst create mode 100644 include/uapi/linux/npcm-video.h (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/drivers/index.rst b/Documentation/userspace-api/media/drivers/index.rst index 6708d649afd7..783f92f01a4c 100644 --- a/Documentation/userspace-api/media/drivers/index.rst +++ b/Documentation/userspace-api/media/drivers/index.rst @@ -37,6 +37,7 @@ For more details see the file COPYING in the source distribution of Linux. dw100 imx-uapi max2175 + npcm-video omap3isp-uapi st-vgxy61 uvcvideo diff --git a/Documentation/userspace-api/media/drivers/npcm-video.rst b/Documentation/userspace-api/media/drivers/npcm-video.rst new file mode 100644 index 000000000000..b47771dd8b27 --- /dev/null +++ b/Documentation/userspace-api/media/drivers/npcm-video.rst @@ -0,0 +1,66 @@ +.. SPDX-License-Identifier: GPL-2.0 + +.. include:: + +NPCM video driver +================= + +This driver is used to control the Video Capture/Differentiation (VCD) engine +and Encoding Compression Engine (ECE) present on Nuvoton NPCM SoCs. The VCD can +capture a frame from digital video input and compare two frames in memory, and +the ECE can compress the frame data into HEXTILE format. + +Driver-specific Controls +------------------------ + +V4L2_CID_NPCM_CAPTURE_MODE +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The VCD engine supports two modes: + +- COMPLETE mode: + + Capture the next complete frame into memory. + +- DIFF mode: + + Compare the incoming frame with the frame stored in memory, and updates the + differentiated frame in memory. + +Application can use ``V4L2_CID_NPCM_CAPTURE_MODE`` control to set the VCD mode +with different control values (enum v4l2_npcm_capture_mode): + +- ``V4L2_NPCM_CAPTURE_MODE_COMPLETE``: will set VCD to COMPLETE mode. +- ``V4L2_NPCM_CAPTURE_MODE_DIFF``: will set VCD to DIFF mode. + +V4L2_CID_NPCM_RECT_COUNT +~~~~~~~~~~~~~~~~~~~~~~~~ + +If using V4L2_PIX_FMT_HEXTILE format, VCD will capture frame data and then ECE +will compress the data into HEXTILE rectangles and store them in V4L2 video +buffer with the layout defined in Remote Framebuffer Protocol: +:: + + (RFC 6143, https://www.rfc-editor.org/rfc/rfc6143.html#section-7.6.1) + + +--------------+--------------+-------------------+ + | No. of bytes | Type [Value] | Description | + +--------------+--------------+-------------------+ + | 2 | U16 | x-position | + | 2 | U16 | y-position | + | 2 | U16 | width | + | 2 | U16 | height | + | 4 | S32 | encoding-type (5) | + +--------------+--------------+-------------------+ + | HEXTILE rectangle data | + +-------------------------------------------------+ + +Application can get the video buffer through VIDIOC_DQBUF, and followed by +calling ``V4L2_CID_NPCM_RECT_COUNT`` control to get the number of HEXTILE +rectangles in this buffer. + +References +---------- +include/uapi/linux/npcm-video.h + +**Copyright** |copy| 2022 Nuvoton Technologies diff --git a/include/uapi/linux/npcm-video.h b/include/uapi/linux/npcm-video.h new file mode 100644 index 000000000000..1d39f6f38c96 --- /dev/null +++ b/include/uapi/linux/npcm-video.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * Controls header for NPCM video driver + * + * Copyright (C) 2022 Nuvoton Technologies + */ + +#ifndef _UAPI_LINUX_NPCM_VIDEO_H +#define _UAPI_LINUX_NPCM_VIDEO_H + +#include + +/* + * Check Documentation/userspace-api/media/drivers/npcm-video.rst for control + * details. + */ + +/* + * This control is meant to set the mode of NPCM Video Capture/Differentiation + * (VCD) engine. + * + * The VCD engine supports two modes: + * COMPLETE - Capture the next complete frame into memory. + * DIFF - Compare the incoming frame with the frame stored in memory, and + * updates the differentiated frame in memory. + */ +#define V4L2_CID_NPCM_CAPTURE_MODE (V4L2_CID_USER_NPCM_BASE + 0) + +enum v4l2_npcm_capture_mode { + V4L2_NPCM_CAPTURE_MODE_COMPLETE = 0, /* COMPLETE mode */ + V4L2_NPCM_CAPTURE_MODE_DIFF = 1, /* DIFF mode */ +}; + +/* + * This control is meant to get the count of compressed HEXTILE rectangles which + * is relevant to the number of differentiated frames if VCD is in DIFF mode. + * And the count will always be 1 if VCD is in COMPLETE mode. + */ +#define V4L2_CID_NPCM_RECT_COUNT (V4L2_CID_USER_NPCM_BASE + 1) + +#endif /* _UAPI_LINUX_NPCM_VIDEO_H */ -- cgit From 528ce6781726e022bc5dc84034360e6e8f1b89bd Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 28 Sep 2023 20:43:24 +0800 Subject: io_uring: retain top 8bits of uring_cmd flags for kernel internal use Retain top 8bits of uring_cmd flags for kernel internal use, so that we can move IORING_URING_CMD_POLLED out of uapi header. Reviewed-by: Gabriel Krisman Bertazi Reviewed-by: Anuj Gupta Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 3 +++ include/uapi/linux/io_uring.h | 5 ++--- io_uring/io_uring.c | 3 +++ io_uring/uring_cmd.c | 2 +- 4 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 106cdc55ff3b..ae08d6f66e62 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -22,6 +22,9 @@ enum io_uring_cmd_flags { IO_URING_F_IOPOLL = (1 << 10), }; +/* only top 8 bits of sqe->uring_cmd_flags for kernel internal use */ +#define IORING_URING_CMD_POLLED (1U << 31) + struct io_uring_cmd { struct file *file; const struct io_uring_sqe *sqe; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 683ac2b74721..425f64eee44e 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -249,13 +249,12 @@ enum io_uring_op { }; /* - * sqe->uring_cmd_flags + * sqe->uring_cmd_flags top 8bits aren't available for userspace * IORING_URING_CMD_FIXED use registered buffer; pass this flag * along with setting sqe->buf_index. - * IORING_URING_CMD_POLLED driver use only */ #define IORING_URING_CMD_FIXED (1U << 0) -#define IORING_URING_CMD_POLLED (1U << 31) +#define IORING_URING_CMD_MASK IORING_URING_CMD_FIXED /* diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 2dff4772bf14..cb6bd9907045 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -4669,6 +4669,9 @@ static int __init io_uring_init(void) BUILD_BUG_ON(sizeof(atomic_t) != sizeof(u32)); + /* top 8bits are for internal use */ + BUILD_BUG_ON((IORING_URING_CMD_MASK & 0xff000000) != 0); + io_uring_optable_init(); /* diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 537795fddc87..a0b0ec5473bf 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -91,7 +91,7 @@ int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EINVAL; ioucmd->flags = READ_ONCE(sqe->uring_cmd_flags); - if (ioucmd->flags & ~IORING_URING_CMD_FIXED) + if (ioucmd->flags & ~IORING_URING_CMD_MASK) return -EINVAL; if (ioucmd->flags & IORING_URING_CMD_FIXED) { -- cgit From f59a7b6af012619199c55f587a6c4ed681639b32 Mon Sep 17 00:00:00 2001 From: Nipun Gupta Date: Fri, 15 Sep 2023 10:24:22 +0530 Subject: vfio: add bus master feature to device feature ioctl add bus mastering control to VFIO_DEVICE_FEATURE IOCTL. The VFIO user can use this feature to enable or disable the Bus Mastering of a device bound to VFIO. Co-developed-by: Shubham Rohila Signed-off-by: Shubham Rohila Signed-off-by: Nipun Gupta Link: https://lore.kernel.org/r/20230915045423.31630-2-nipun.gupta@amd.com Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index afc1369216d9..b177424149f4 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1434,6 +1434,27 @@ struct vfio_device_feature_mig_data_size { #define VFIO_DEVICE_FEATURE_MIG_DATA_SIZE 9 +/** + * Upon VFIO_DEVICE_FEATURE_SET, set or clear the BUS mastering for the device + * based on the operation specified in op flag. + * + * The functionality is incorporated for devices that needs bus master control, + * but the in-band device interface lacks the support. Consequently, it is not + * applicable to PCI devices, as bus master control for PCI devices is managed + * in-band through the configuration space. At present, this feature is supported + * only for CDX devices. + * When the device's BUS MASTER setting is configured as CLEAR, it will result in + * blocking all incoming DMA requests from the device. On the other hand, configuring + * the device's BUS MASTER setting as SET (enable) will grant the device the + * capability to perform DMA to the host memory. + */ +struct vfio_device_feature_bus_master { + __u32 op; +#define VFIO_DEVICE_FEATURE_CLEAR_MASTER 0 /* Clear Bus Master */ +#define VFIO_DEVICE_FEATURE_SET_MASTER 1 /* Set Bus Master */ +}; +#define VFIO_DEVICE_FEATURE_BUS_MASTER 10 + /* -------- API for Type1 VFIO IOMMU -------- */ /** -- cgit From 2f8d25fa8aed030d7d049f0aef1b78713f431a79 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Mon, 18 Sep 2023 16:56:15 -0400 Subject: vfio: trivially use __aligned_u64 for ioctl structs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit u64 alignment behaves differently depending on the architecture and so offers __aligned_u64 to achieve consistent behavior in kernel<->userspace ABIs. There are structs in that can trivially be updated to __aligned_u64 because the struct sizes are multiples of 8 bytes. There is no change in memory layout on any CPU architecture and therefore this change is safe. The commits that follow this one handle the trickier cases where explanation about ABI breakage is necessary. Suggested-by: Jason Gunthorpe Reviewed-by: Jason Gunthorpe Reviewed-by: Philippe Mathieu-Daudé Reviewed-by: Kevin Tian Signed-off-by: Stefan Hajnoczi Link: https://lore.kernel.org/r/20230918205617.1478722-2-stefanha@redhat.com Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index b177424149f4..325df3246691 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -277,8 +277,8 @@ struct vfio_region_info { #define VFIO_REGION_INFO_FLAG_CAPS (1 << 3) /* Info supports caps */ __u32 index; /* Region index */ __u32 cap_offset; /* Offset within info struct of first cap */ - __u64 size; /* Region size (bytes) */ - __u64 offset; /* Region offset from start of device fd */ + __aligned_u64 size; /* Region size (bytes) */ + __aligned_u64 offset; /* Region offset from start of device fd */ }; #define VFIO_DEVICE_GET_REGION_INFO _IO(VFIO_TYPE, VFIO_BASE + 8) @@ -294,8 +294,8 @@ struct vfio_region_info { #define VFIO_REGION_INFO_CAP_SPARSE_MMAP 1 struct vfio_region_sparse_mmap_area { - __u64 offset; /* Offset of mmap'able area within region */ - __u64 size; /* Size of mmap'able area */ + __aligned_u64 offset; /* Offset of mmap'able area within region */ + __aligned_u64 size; /* Size of mmap'able area */ }; struct vfio_region_info_cap_sparse_mmap { @@ -450,9 +450,9 @@ struct vfio_device_migration_info { VFIO_DEVICE_STATE_V1_RESUMING) __u32 reserved; - __u64 pending_bytes; - __u64 data_offset; - __u64 data_size; + __aligned_u64 pending_bytes; + __aligned_u64 data_offset; + __aligned_u64 data_size; }; /* @@ -476,7 +476,7 @@ struct vfio_device_migration_info { struct vfio_region_info_cap_nvlink2_ssatgt { struct vfio_info_cap_header header; - __u64 tgt; + __aligned_u64 tgt; }; /* @@ -1470,7 +1470,7 @@ struct vfio_iommu_type1_info { __u32 flags; #define VFIO_IOMMU_INFO_PGSIZES (1 << 0) /* supported page sizes info */ #define VFIO_IOMMU_INFO_CAPS (1 << 1) /* Info supports caps */ - __u64 iova_pgsizes; /* Bitmap of supported page sizes */ + __aligned_u64 iova_pgsizes; /* Bitmap of supported page sizes */ __u32 cap_offset; /* Offset within info struct of first cap */ __u32 pad; }; -- cgit From a7bea9f4fecce0afd37ee58a552eef71d8b4ab9f Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Mon, 18 Sep 2023 16:56:16 -0400 Subject: vfio: use __aligned_u64 in struct vfio_device_gfx_plane_info The memory layout of struct vfio_device_gfx_plane_info is architecture-dependent due to a u64 field and a struct size that is not a multiple of 8 bytes: - On x86_64 the struct size is padded to a multiple of 8 bytes. - On x32 the struct size is only a multiple of 4 bytes, not 8. - Other architectures may vary. Use __aligned_u64 to make memory layout consistent. This reduces the chance of 32-bit userspace on a 64-bit kernel breakage. This patch increases the struct size on x32 but this is safe because of the struct's argsz field. The kernel may grow the struct as long as it still supports smaller argsz values from userspace (e.g. applications compiled against older kernel headers). Suggested-by: Jason Gunthorpe Reviewed-by: Kevin Tian Signed-off-by: Stefan Hajnoczi Link: https://lore.kernel.org/r/20230918205617.1478722-3-stefanha@redhat.com Signed-off-by: Alex Williamson --- drivers/gpu/drm/i915/gvt/kvmgt.c | 2 +- include/uapi/linux/vfio.h | 3 ++- samples/vfio-mdev/mbochs.c | 2 +- samples/vfio-mdev/mdpy.c | 2 +- 4 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 42ce20e72db7..faf21be724c3 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -1379,7 +1379,7 @@ static long intel_vgpu_ioctl(struct vfio_device *vfio_dev, unsigned int cmd, intel_gvt_reset_vgpu(vgpu); return 0; } else if (cmd == VFIO_DEVICE_QUERY_GFX_PLANE) { - struct vfio_device_gfx_plane_info dmabuf; + struct vfio_device_gfx_plane_info dmabuf = {}; int ret = 0; minsz = offsetofend(struct vfio_device_gfx_plane_info, diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 325df3246691..8a3f83e0bdc1 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -816,7 +816,7 @@ struct vfio_device_gfx_plane_info { __u32 drm_plane_type; /* type of plane: DRM_PLANE_TYPE_* */ /* out */ __u32 drm_format; /* drm format of plane */ - __u64 drm_format_mod; /* tiled mode */ + __aligned_u64 drm_format_mod; /* tiled mode */ __u32 width; /* width of plane */ __u32 height; /* height of plane */ __u32 stride; /* stride of plane */ @@ -829,6 +829,7 @@ struct vfio_device_gfx_plane_info { __u32 region_index; /* region index */ __u32 dmabuf_id; /* dma-buf id */ }; + __u32 reserved; }; #define VFIO_DEVICE_QUERY_GFX_PLANE _IO(VFIO_TYPE, VFIO_BASE + 14) diff --git a/samples/vfio-mdev/mbochs.c b/samples/vfio-mdev/mbochs.c index 3764d1911b51..93405264ff23 100644 --- a/samples/vfio-mdev/mbochs.c +++ b/samples/vfio-mdev/mbochs.c @@ -1262,7 +1262,7 @@ static long mbochs_ioctl(struct vfio_device *vdev, unsigned int cmd, case VFIO_DEVICE_QUERY_GFX_PLANE: { - struct vfio_device_gfx_plane_info plane; + struct vfio_device_gfx_plane_info plane = {}; minsz = offsetofend(struct vfio_device_gfx_plane_info, region_index); diff --git a/samples/vfio-mdev/mdpy.c b/samples/vfio-mdev/mdpy.c index 064e1c0a7aa8..72ea5832c927 100644 --- a/samples/vfio-mdev/mdpy.c +++ b/samples/vfio-mdev/mdpy.c @@ -591,7 +591,7 @@ static long mdpy_ioctl(struct vfio_device *vdev, unsigned int cmd, case VFIO_DEVICE_QUERY_GFX_PLANE: { - struct vfio_device_gfx_plane_info plane; + struct vfio_device_gfx_plane_info plane = {}; minsz = offsetofend(struct vfio_device_gfx_plane_info, region_index); -- cgit From 61050c73441be7933d2170642c3f3e36313e56c8 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Mon, 18 Sep 2023 16:56:17 -0400 Subject: vfio: use __aligned_u64 in struct vfio_device_ioeventfd The memory layout of struct vfio_device_ioeventfd is architecture-dependent due to a u64 field and a struct size that is not a multiple of 8 bytes: - On x86_64 the struct size is padded to a multiple of 8 bytes. - On x32 the struct size is only a multiple of 4 bytes, not 8. - Other architectures may vary. Use __aligned_u64 to make memory layout consistent. This reduces the chance that 32-bit userspace on a 64-bit kernel breakage. This patch increases the struct size on x32 but this is safe because of the struct's argsz field. The kernel may grow the struct as long as it still supports smaller argsz values from userspace (e.g. applications compiled against older kernel headers). The code that uses struct vfio_device_ioeventfd already works correctly when the struct size grows, so only the struct definition needs to be changed. Suggested-by: Jason Gunthorpe Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Signed-off-by: Stefan Hajnoczi Link: https://lore.kernel.org/r/20230918205617.1478722-4-stefanha@redhat.com Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 8a3f83e0bdc1..7f5fb010226d 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -864,9 +864,10 @@ struct vfio_device_ioeventfd { #define VFIO_DEVICE_IOEVENTFD_32 (1 << 2) /* 4-byte write */ #define VFIO_DEVICE_IOEVENTFD_64 (1 << 3) /* 8-byte write */ #define VFIO_DEVICE_IOEVENTFD_SIZE_MASK (0xf) - __u64 offset; /* device fd offset of write */ - __u64 data; /* data to be written */ + __aligned_u64 offset; /* device fd offset of write */ + __aligned_u64 data; /* data to be written */ __s32 fd; /* -1 for de-assignment */ + __u32 reserved; }; #define VFIO_DEVICE_IOEVENTFD _IO(VFIO_TYPE, VFIO_BASE + 16) -- cgit From 194bb58c6090e39bd7d9b9c888a079213628e1f6 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 8 Jun 2023 11:57:40 -0600 Subject: io_uring: add support for futex wake and wait Add support for FUTEX_WAKE/WAIT primitives. IORING_OP_FUTEX_WAKE is mix of FUTEX_WAKE and FUTEX_WAKE_BITSET, as it does support passing in a bitset. Similary, IORING_OP_FUTEX_WAIT is a mix of FUTEX_WAIT and FUTEX_WAIT_BITSET. For both of them, they are using the futex2 interface. FUTEX_WAKE is straight forward, as those can always be done directly from the io_uring submission without needing async handling. For FUTEX_WAIT, things are a bit more complicated. If the futex isn't ready, then we rely on a callback via futex_queue->wake() when someone wakes up the futex. From that calback, we queue up task_work with the original task, which will post a CQE and wake it, if necessary. Cancelations are supported, both from the application point-of-view, but also to be able to cancel pending waits if the ring exits before all events have occurred. The return value of futex_unqueue() is used to gate who wins the potential race between cancelation and futex wakeups. Whomever gets a 'ret == 1' return from that claims ownership of the io_uring futex request. This is just the barebones wait/wake support. PI or REQUEUE support is not added at this point, unclear if we might look into that later. Likewise, explicit timeouts are not supported either. It is expected that users that need timeouts would do so via the usual io_uring mechanism to do that using linked timeouts. The SQE format is as follows: `addr` Address of futex `fd` futex2(2) FUTEX2_* flags `futex_flags` io_uring specific command flags. None valid now. `addr2` Value of futex `addr3` Mask to wake/wait Acked-by: Peter Zijlstra (Intel) Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 5 + include/uapi/linux/io_uring.h | 3 + io_uring/Makefile | 1 + io_uring/cancel.c | 5 + io_uring/cancel.h | 4 + io_uring/futex.c | 235 +++++++++++++++++++++++++++++++++++++++++ io_uring/futex.h | 34 ++++++ io_uring/io_uring.c | 7 ++ io_uring/opdef.c | 23 ++++ 9 files changed, 317 insertions(+) create mode 100644 io_uring/futex.c create mode 100644 io_uring/futex.h (limited to 'include/uapi/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index e178461fa513..990984614fca 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -321,6 +321,11 @@ struct io_ring_ctx { struct hlist_head waitid_list; +#ifdef CONFIG_FUTEX + struct hlist_head futex_list; + struct io_alloc_cache futex_cache; +#endif + const struct cred *sq_creds; /* cred used for __io_sq_thread() */ struct io_sq_data *sq_data; /* if using sq thread polling */ diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 425f64eee44e..04f9fba38d4b 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -66,6 +66,7 @@ struct io_uring_sqe { __u32 msg_ring_flags; __u32 uring_cmd_flags; __u32 waitid_flags; + __u32 futex_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -243,6 +244,8 @@ enum io_uring_op { IORING_OP_SENDMSG_ZC, IORING_OP_READ_MULTISHOT, IORING_OP_WAITID, + IORING_OP_FUTEX_WAIT, + IORING_OP_FUTEX_WAKE, /* this goes last, obviously */ IORING_OP_LAST, diff --git a/io_uring/Makefile b/io_uring/Makefile index 7bd64e442567..e5be47e4fc3b 100644 --- a/io_uring/Makefile +++ b/io_uring/Makefile @@ -10,3 +10,4 @@ obj-$(CONFIG_IO_URING) += io_uring.o xattr.o nop.o fs.o splice.o \ cancel.o kbuf.o rsrc.o rw.o opdef.o \ notif.o waitid.o obj-$(CONFIG_IO_WQ) += io-wq.o +obj-$(CONFIG_FUTEX) += futex.o diff --git a/io_uring/cancel.c b/io_uring/cancel.c index eb77a51c5a79..3c19cccb1aec 100644 --- a/io_uring/cancel.c +++ b/io_uring/cancel.c @@ -16,6 +16,7 @@ #include "poll.h" #include "timeout.h" #include "waitid.h" +#include "futex.h" #include "cancel.h" struct io_cancel { @@ -124,6 +125,10 @@ int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd, if (ret != -ENOENT) return ret; + ret = io_futex_cancel(ctx, cd, issue_flags); + if (ret != -ENOENT) + return ret; + spin_lock(&ctx->completion_lock); if (!(cd->flags & IORING_ASYNC_CANCEL_FD)) ret = io_timeout_cancel(ctx, cd); diff --git a/io_uring/cancel.h b/io_uring/cancel.h index fc98622e6166..c0a8e7c520b6 100644 --- a/io_uring/cancel.h +++ b/io_uring/cancel.h @@ -1,4 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 +#ifndef IORING_CANCEL_H +#define IORING_CANCEL_H #include @@ -22,3 +24,5 @@ void init_hash_table(struct io_hash_table *table, unsigned size); int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg); bool io_cancel_req_match(struct io_kiocb *req, struct io_cancel_data *cd); + +#endif diff --git a/io_uring/futex.c b/io_uring/futex.c new file mode 100644 index 000000000000..eb4406ac46fb --- /dev/null +++ b/io_uring/futex.c @@ -0,0 +1,235 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include + +#include + +#include "../kernel/futex/futex.h" +#include "io_uring.h" +#include "rsrc.h" +#include "futex.h" + +struct io_futex { + struct file *file; + u32 __user *uaddr; + unsigned long futex_val; + unsigned long futex_mask; + u32 futex_flags; +}; + +struct io_futex_data { + union { + struct futex_q q; + struct io_cache_entry cache; + }; + struct io_kiocb *req; +}; + +void io_futex_cache_init(struct io_ring_ctx *ctx) +{ + io_alloc_cache_init(&ctx->futex_cache, IO_NODE_ALLOC_CACHE_MAX, + sizeof(struct io_futex_data)); +} + +static void io_futex_cache_entry_free(struct io_cache_entry *entry) +{ + kfree(container_of(entry, struct io_futex_data, cache)); +} + +void io_futex_cache_free(struct io_ring_ctx *ctx) +{ + io_alloc_cache_free(&ctx->futex_cache, io_futex_cache_entry_free); +} + +static void io_futex_complete(struct io_kiocb *req, struct io_tw_state *ts) +{ + struct io_futex_data *ifd = req->async_data; + struct io_ring_ctx *ctx = req->ctx; + + io_tw_lock(ctx, ts); + if (!io_alloc_cache_put(&ctx->futex_cache, &ifd->cache)) + kfree(ifd); + req->async_data = NULL; + hlist_del_init(&req->hash_node); + io_req_task_complete(req, ts); +} + +static bool __io_futex_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req) +{ + struct io_futex_data *ifd = req->async_data; + + /* futex wake already done or in progress */ + if (!futex_unqueue(&ifd->q)) + return false; + + hlist_del_init(&req->hash_node); + io_req_set_res(req, -ECANCELED, 0); + req->io_task_work.func = io_futex_complete; + io_req_task_work_add(req); + return true; +} + +int io_futex_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd, + unsigned int issue_flags) +{ + struct hlist_node *tmp; + struct io_kiocb *req; + int nr = 0; + + if (cd->flags & (IORING_ASYNC_CANCEL_FD|IORING_ASYNC_CANCEL_FD_FIXED)) + return -ENOENT; + + io_ring_submit_lock(ctx, issue_flags); + hlist_for_each_entry_safe(req, tmp, &ctx->futex_list, hash_node) { + if (req->cqe.user_data != cd->data && + !(cd->flags & IORING_ASYNC_CANCEL_ANY)) + continue; + if (__io_futex_cancel(ctx, req)) + nr++; + if (!(cd->flags & IORING_ASYNC_CANCEL_ALL)) + break; + } + io_ring_submit_unlock(ctx, issue_flags); + + if (nr) + return nr; + + return -ENOENT; +} + +bool io_futex_remove_all(struct io_ring_ctx *ctx, struct task_struct *task, + bool cancel_all) +{ + struct hlist_node *tmp; + struct io_kiocb *req; + bool found = false; + + lockdep_assert_held(&ctx->uring_lock); + + hlist_for_each_entry_safe(req, tmp, &ctx->futex_list, hash_node) { + if (!io_match_task_safe(req, task, cancel_all)) + continue; + __io_futex_cancel(ctx, req); + found = true; + } + + return found; +} + +int io_futex_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); + u32 flags; + + if (unlikely(sqe->len || sqe->futex_flags || sqe->buf_index || + sqe->file_index)) + return -EINVAL; + + iof->uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr)); + iof->futex_val = READ_ONCE(sqe->addr2); + iof->futex_mask = READ_ONCE(sqe->addr3); + flags = READ_ONCE(sqe->fd); + + if (flags & ~FUTEX2_VALID_MASK) + return -EINVAL; + + iof->futex_flags = futex2_to_flags(flags); + if (!futex_flags_valid(iof->futex_flags)) + return -EINVAL; + + if (!futex_validate_input(iof->futex_flags, iof->futex_val) || + !futex_validate_input(iof->futex_flags, iof->futex_mask)) + return -EINVAL; + + return 0; +} + +static void io_futex_wake_fn(struct wake_q_head *wake_q, struct futex_q *q) +{ + struct io_futex_data *ifd = container_of(q, struct io_futex_data, q); + struct io_kiocb *req = ifd->req; + + if (unlikely(!__futex_wake_mark(q))) + return; + + io_req_set_res(req, 0, 0); + req->io_task_work.func = io_futex_complete; + io_req_task_work_add(req); +} + +static struct io_futex_data *io_alloc_ifd(struct io_ring_ctx *ctx) +{ + struct io_cache_entry *entry; + + entry = io_alloc_cache_get(&ctx->futex_cache); + if (entry) + return container_of(entry, struct io_futex_data, cache); + + return kmalloc(sizeof(struct io_futex_data), GFP_NOWAIT); +} + +int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); + struct io_ring_ctx *ctx = req->ctx; + struct io_futex_data *ifd = NULL; + struct futex_hash_bucket *hb; + int ret; + + if (!iof->futex_mask) { + ret = -EINVAL; + goto done; + } + + io_ring_submit_lock(ctx, issue_flags); + ifd = io_alloc_ifd(ctx); + if (!ifd) { + ret = -ENOMEM; + goto done_unlock; + } + + req->async_data = ifd; + ifd->q = futex_q_init; + ifd->q.bitset = iof->futex_mask; + ifd->q.wake = io_futex_wake_fn; + ifd->req = req; + + ret = futex_wait_setup(iof->uaddr, iof->futex_val, iof->futex_flags, + &ifd->q, &hb); + if (!ret) { + hlist_add_head(&req->hash_node, &ctx->futex_list); + io_ring_submit_unlock(ctx, issue_flags); + + futex_queue(&ifd->q, hb); + return IOU_ISSUE_SKIP_COMPLETE; + } + +done_unlock: + io_ring_submit_unlock(ctx, issue_flags); +done: + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + kfree(ifd); + return IOU_OK; +} + +int io_futex_wake(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); + int ret; + + /* + * Strict flags - ensure that waking 0 futexes yields a 0 result. + * See commit 43adf8449510 ("futex: FLAGS_STRICT") for details. + */ + ret = futex_wake(iof->uaddr, FLAGS_STRICT | iof->futex_flags, + iof->futex_val, iof->futex_mask); + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return IOU_OK; +} diff --git a/io_uring/futex.h b/io_uring/futex.h new file mode 100644 index 000000000000..ddc9e0d73c52 --- /dev/null +++ b/io_uring/futex.h @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "cancel.h" + +int io_futex_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags); +int io_futex_wake(struct io_kiocb *req, unsigned int issue_flags); + +#if defined(CONFIG_FUTEX) +int io_futex_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd, + unsigned int issue_flags); +bool io_futex_remove_all(struct io_ring_ctx *ctx, struct task_struct *task, + bool cancel_all); +void io_futex_cache_init(struct io_ring_ctx *ctx); +void io_futex_cache_free(struct io_ring_ctx *ctx); +#else +static inline int io_futex_cancel(struct io_ring_ctx *ctx, + struct io_cancel_data *cd, + unsigned int issue_flags) +{ + return 0; +} +static inline bool io_futex_remove_all(struct io_ring_ctx *ctx, + struct task_struct *task, bool cancel_all) +{ + return false; +} +static inline void io_futex_cache_init(struct io_ring_ctx *ctx) +{ +} +static inline void io_futex_cache_free(struct io_ring_ctx *ctx) +{ +} +#endif diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 08c9ea46bb95..3c1c111d02cb 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -93,6 +93,7 @@ #include "net.h" #include "notif.h" #include "waitid.h" +#include "futex.h" #include "timeout.h" #include "poll.h" @@ -330,6 +331,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) sizeof(struct async_poll)); io_alloc_cache_init(&ctx->netmsg_cache, IO_ALLOC_CACHE_MAX, sizeof(struct io_async_msghdr)); + io_futex_cache_init(ctx); init_completion(&ctx->ref_comp); xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1); mutex_init(&ctx->uring_lock); @@ -350,6 +352,9 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) ctx->submit_state.free_list.next = NULL; INIT_WQ_LIST(&ctx->locked_free_list); INIT_HLIST_HEAD(&ctx->waitid_list); +#ifdef CONFIG_FUTEX + INIT_HLIST_HEAD(&ctx->futex_list); +#endif INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func); INIT_WQ_LIST(&ctx->submit_state.compl_reqs); INIT_HLIST_HEAD(&ctx->cancelable_uring_cmd); @@ -2895,6 +2900,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) io_eventfd_unregister(ctx); io_alloc_cache_free(&ctx->apoll_cache, io_apoll_cache_free); io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free); + io_futex_cache_free(ctx); io_destroy_buffers(ctx); mutex_unlock(&ctx->uring_lock); if (ctx->sq_creds) @@ -3338,6 +3344,7 @@ static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, mutex_lock(&ctx->uring_lock); ret |= io_poll_remove_all(ctx, task, cancel_all); ret |= io_waitid_remove_all(ctx, task, cancel_all); + ret |= io_futex_remove_all(ctx, task, cancel_all); ret |= io_uring_try_cancel_uring_cmd(ctx, task, cancel_all); mutex_unlock(&ctx->uring_lock); ret |= io_kill_timeouts(ctx, task, cancel_all); diff --git a/io_uring/opdef.c b/io_uring/opdef.c index aadcbf7136b0..31a3a421e94d 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -34,6 +34,7 @@ #include "cancel.h" #include "rw.h" #include "waitid.h" +#include "futex.h" static int io_no_issue(struct io_kiocb *req, unsigned int issue_flags) { @@ -444,6 +445,22 @@ const struct io_issue_def io_issue_defs[] = { .prep = io_waitid_prep, .issue = io_waitid, }, + [IORING_OP_FUTEX_WAIT] = { +#if defined(CONFIG_FUTEX) + .prep = io_futex_prep, + .issue = io_futex_wait, +#else + .prep = io_eopnotsupp_prep, +#endif + }, + [IORING_OP_FUTEX_WAKE] = { +#if defined(CONFIG_FUTEX) + .prep = io_futex_prep, + .issue = io_futex_wake, +#else + .prep = io_eopnotsupp_prep, +#endif + }, }; const struct io_cold_def io_cold_defs[] = { @@ -670,6 +687,12 @@ const struct io_cold_def io_cold_defs[] = { .name = "WAITID", .async_size = sizeof(struct io_waitid_async), }, + [IORING_OP_FUTEX_WAIT] = { + .name = "FUTEX_WAIT", + }, + [IORING_OP_FUTEX_WAKE] = { + .name = "FUTEX_WAKE", + }, }; const char *io_uring_get_opcode(u8 opcode) -- cgit From 8f350194d5cfd7016d4cd44e433df0faa4d4a703 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 12 Jun 2023 19:04:32 -0600 Subject: io_uring: add support for vectored futex waits This adds support for IORING_OP_FUTEX_WAITV, which allows registering a notification for a number of futexes at once. If one of the futexes are woken, then the request will complete with the index of the futex that got woken as the result. This is identical to what the normal vectored futex waitv operation does. Use like IORING_OP_FUTEX_WAIT, except sqe->addr must now contain a pointer to a struct futex_waitv array, and sqe->off must now contain the number of elements in that array. As flags are passed in the futex_vector array, and likewise for the value and futex address(es), sqe->addr2 and sqe->addr3 are also reserved for IORING_OP_FUTEX_WAITV. For cancelations, FUTEX_WAITV does not rely on the futex_unqueue() return value as we're dealing with multiple futexes. Instead, a separate per io_uring request atomic is used to claim ownership of the request. Waiting on N futexes could be done with IORING_OP_FUTEX_WAIT as well, but that punts a lot of the work to the application: 1) Application would need to submit N IORING_OP_FUTEX_WAIT requests, rather than just a single IORING_OP_FUTEX_WAITV. 2) When one futex is woken, application would need to cancel the remaining N-1 requests that didn't trigger. While this is of course doable, having a single vectored futex wait makes for much simpler application code. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + io_uring/futex.c | 169 +++++++++++++++++++++++++++++++++++++++--- io_uring/futex.h | 2 + io_uring/opdef.c | 11 +++ 4 files changed, 174 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 04f9fba38d4b..92be89a871fc 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -246,6 +246,7 @@ enum io_uring_op { IORING_OP_WAITID, IORING_OP_FUTEX_WAIT, IORING_OP_FUTEX_WAKE, + IORING_OP_FUTEX_WAITV, /* this goes last, obviously */ IORING_OP_LAST, diff --git a/io_uring/futex.c b/io_uring/futex.c index eb4406ac46fb..3c3575303c3d 100644 --- a/io_uring/futex.c +++ b/io_uring/futex.c @@ -14,10 +14,16 @@ struct io_futex { struct file *file; - u32 __user *uaddr; + union { + u32 __user *uaddr; + struct futex_waitv __user *uwaitv; + }; unsigned long futex_val; unsigned long futex_mask; + unsigned long futexv_owned; u32 futex_flags; + unsigned int futex_nr; + bool futexv_unqueued; }; struct io_futex_data { @@ -44,6 +50,13 @@ void io_futex_cache_free(struct io_ring_ctx *ctx) io_alloc_cache_free(&ctx->futex_cache, io_futex_cache_entry_free); } +static void __io_futex_complete(struct io_kiocb *req, struct io_tw_state *ts) +{ + req->async_data = NULL; + hlist_del_init(&req->hash_node); + io_req_task_complete(req, ts); +} + static void io_futex_complete(struct io_kiocb *req, struct io_tw_state *ts) { struct io_futex_data *ifd = req->async_data; @@ -52,22 +65,56 @@ static void io_futex_complete(struct io_kiocb *req, struct io_tw_state *ts) io_tw_lock(ctx, ts); if (!io_alloc_cache_put(&ctx->futex_cache, &ifd->cache)) kfree(ifd); - req->async_data = NULL; - hlist_del_init(&req->hash_node); - io_req_task_complete(req, ts); + __io_futex_complete(req, ts); } -static bool __io_futex_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req) +static void io_futexv_complete(struct io_kiocb *req, struct io_tw_state *ts) { - struct io_futex_data *ifd = req->async_data; + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); + struct futex_vector *futexv = req->async_data; - /* futex wake already done or in progress */ - if (!futex_unqueue(&ifd->q)) + io_tw_lock(req->ctx, ts); + + if (!iof->futexv_unqueued) { + int res; + + res = futex_unqueue_multiple(futexv, iof->futex_nr); + if (res != -1) + io_req_set_res(req, res, 0); + } + + kfree(req->async_data); + req->flags &= ~REQ_F_ASYNC_DATA; + __io_futex_complete(req, ts); +} + +static bool io_futexv_claim(struct io_futex *iof) +{ + if (test_bit(0, &iof->futexv_owned) || + test_and_set_bit_lock(0, &iof->futexv_owned)) return false; + return true; +} + +static bool __io_futex_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req) +{ + /* futex wake already done or in progress */ + if (req->opcode == IORING_OP_FUTEX_WAIT) { + struct io_futex_data *ifd = req->async_data; + + if (!futex_unqueue(&ifd->q)) + return false; + req->io_task_work.func = io_futex_complete; + } else { + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); + + if (!io_futexv_claim(iof)) + return false; + req->io_task_work.func = io_futexv_complete; + } hlist_del_init(&req->hash_node); io_req_set_res(req, -ECANCELED, 0); - req->io_task_work.func = io_futex_complete; io_req_task_work_add(req); return true; } @@ -147,6 +194,55 @@ int io_futex_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } +static void io_futex_wakev_fn(struct wake_q_head *wake_q, struct futex_q *q) +{ + struct io_kiocb *req = q->wake_data; + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); + + if (!io_futexv_claim(iof)) + return; + if (unlikely(!__futex_wake_mark(q))) + return; + + io_req_set_res(req, 0, 0); + req->io_task_work.func = io_futexv_complete; + io_req_task_work_add(req); +} + +int io_futexv_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); + struct futex_vector *futexv; + int ret; + + /* No flags or mask supported for waitv */ + if (unlikely(sqe->fd || sqe->buf_index || sqe->file_index || + sqe->addr2 || sqe->futex_flags || sqe->addr3)) + return -EINVAL; + + iof->uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr)); + iof->futex_nr = READ_ONCE(sqe->len); + if (!iof->futex_nr || iof->futex_nr > FUTEX_WAITV_MAX) + return -EINVAL; + + futexv = kcalloc(iof->futex_nr, sizeof(*futexv), GFP_KERNEL); + if (!futexv) + return -ENOMEM; + + ret = futex_parse_waitv(futexv, iof->uwaitv, iof->futex_nr, + io_futex_wakev_fn, req); + if (ret) { + kfree(futexv); + return ret; + } + + iof->futexv_owned = 0; + iof->futexv_unqueued = 0; + req->flags |= REQ_F_ASYNC_DATA; + req->async_data = futexv; + return 0; +} + static void io_futex_wake_fn(struct wake_q_head *wake_q, struct futex_q *q) { struct io_futex_data *ifd = container_of(q, struct io_futex_data, q); @@ -171,6 +267,61 @@ static struct io_futex_data *io_alloc_ifd(struct io_ring_ctx *ctx) return kmalloc(sizeof(struct io_futex_data), GFP_NOWAIT); } +int io_futexv_wait(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); + struct futex_vector *futexv = req->async_data; + struct io_ring_ctx *ctx = req->ctx; + int ret, woken = -1; + + io_ring_submit_lock(ctx, issue_flags); + + ret = futex_wait_multiple_setup(futexv, iof->futex_nr, &woken); + + /* + * Error case, ret is < 0. Mark the request as failed. + */ + if (unlikely(ret < 0)) { + io_ring_submit_unlock(ctx, issue_flags); + req_set_fail(req); + io_req_set_res(req, ret, 0); + kfree(futexv); + req->async_data = NULL; + req->flags &= ~REQ_F_ASYNC_DATA; + return IOU_OK; + } + + /* + * 0 return means that we successfully setup the waiters, and that + * nobody triggered a wakeup while we were doing so. If the wakeup + * happened post setup, the task_work will be run post this issue and + * under the submission lock. 1 means We got woken while setting up, + * let that side do the completion. Note that + * futex_wait_multiple_setup() will have unqueued all the futexes in + * this case. Mark us as having done that already, since this is + * different from normal wakeup. + */ + if (!ret) { + /* + * If futex_wait_multiple_setup() returns 0 for a + * successful setup, then the task state will not be + * runnable. This is fine for the sync syscall, as + * it'll be blocking unless we already got one of the + * futexes woken, but it obviously won't work for an + * async invocation. Mark us runnable again. + */ + __set_current_state(TASK_RUNNING); + hlist_add_head(&req->hash_node, &ctx->futex_list); + } else { + iof->futexv_unqueued = 1; + if (woken != -1) + io_req_set_res(req, woken, 0); + } + + io_ring_submit_unlock(ctx, issue_flags); + return IOU_ISSUE_SKIP_COMPLETE; +} + int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags) { struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); diff --git a/io_uring/futex.h b/io_uring/futex.h index ddc9e0d73c52..0847e9e8a127 100644 --- a/io_uring/futex.h +++ b/io_uring/futex.h @@ -3,7 +3,9 @@ #include "cancel.h" int io_futex_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_futexv_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags); +int io_futexv_wait(struct io_kiocb *req, unsigned int issue_flags); int io_futex_wake(struct io_kiocb *req, unsigned int issue_flags); #if defined(CONFIG_FUTEX) diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 31a3a421e94d..25a3515a177c 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -459,6 +459,14 @@ const struct io_issue_def io_issue_defs[] = { .issue = io_futex_wake, #else .prep = io_eopnotsupp_prep, +#endif + }, + [IORING_OP_FUTEX_WAITV] = { +#if defined(CONFIG_FUTEX) + .prep = io_futexv_prep, + .issue = io_futexv_wait, +#else + .prep = io_eopnotsupp_prep, #endif }, }; @@ -693,6 +701,9 @@ const struct io_cold_def io_cold_defs[] = { [IORING_OP_FUTEX_WAKE] = { .name = "FUTEX_WAKE", }, + [IORING_OP_FUTEX_WAITV] = { + .name = "FUTEX_WAITV", + }, }; const char *io_uring_get_opcode(u8 opcode) -- cgit From 076433bd78d719b34d465c1e69eef512036b534c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 20 Sep 2023 20:17:14 +0000 Subject: net_sched: sch_fq: add fast path for mostly idle qdisc TCQ_F_CAN_BYPASS can be used by few qdiscs. Idea is that if we queue a packet to an empty qdisc, following dequeue() would pick it immediately. FQ can not use the generic TCQ_F_CAN_BYPASS code, because some additional checks need to be performed. This patch adds a similar fast path to FQ. Most of the time, qdisc is not throttled, and many packets can avoid bringing/touching at least four cache lines, and consuming 128bytes of memory to store the state of a flow. After this patch, netperf can send UDP packets about 13 % faster, and pktgen goes 30 % faster (when FQ is in the way), on a fast NIC. TCP traffic is also improved, thanks to a reduction of cache line misses. I have measured a 5 % increase of throughput on a tcp_rr intensive workload. tc -s -d qd sh dev eth1 ... qdisc fq 8004: parent 1:2 limit 10000p flow_limit 100p buckets 1024 orphan_mask 1023 quantum 3028b initial_quantum 15140b low_rate_threshold 550Kbit refill_delay 40ms timer_slack 10us horizon 10s horizon_drop Sent 5646784384 bytes 1985161 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 flows 122 (inactive 122 throttled 0) gc 0 highprio 0 fastpath 659990 throttled 27762 latency 8.57us Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 1 + net/sched/sch_fq.c | 128 +++++++++++++++++++++++++++++------------ 2 files changed, 92 insertions(+), 37 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 3f85ae578056..579f641846b8 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -962,6 +962,7 @@ struct tc_fq_qd_stats { __u64 ce_mark; /* packets above ce_threshold */ __u64 horizon_drops; __u64 horizon_caps; + __u64 fastpath_packets; }; /* Heavy-Hitter Filter */ diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 4af43a401dbb..5cf3b50a24d5 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -2,7 +2,7 @@ /* * net/sched/sch_fq.c Fair Queue Packet Scheduler (per flow pacing) * - * Copyright (C) 2013-2015 Eric Dumazet + * Copyright (C) 2013-2023 Eric Dumazet * * Meant to be mostly used for locally generated traffic : * Fast classification depends on skb->sk being set before reaching us. @@ -73,7 +73,13 @@ struct fq_flow { struct sk_buff *tail; /* last skb in the list */ unsigned long age; /* (jiffies | 1UL) when flow was emptied, for gc */ }; - struct rb_node fq_node; /* anchor in fq_root[] trees */ + union { + struct rb_node fq_node; /* anchor in fq_root[] trees */ + /* Following field is only used for q->internal, + * because q->internal is not hashed in fq_root[] + */ + u64 stat_fastpath_packets; + }; struct sock *sk; u32 socket_hash; /* sk_hash */ int qlen; /* number of packets in flow queue */ @@ -134,7 +140,7 @@ struct fq_sched_data { /* Seldom used fields. */ - u64 stat_internal_packets; + u64 stat_internal_packets; /* aka highprio */ u64 stat_ce_mark; u64 stat_horizon_drops; u64 stat_horizon_caps; @@ -266,17 +272,64 @@ static void fq_gc(struct fq_sched_data *q, kmem_cache_free_bulk(fq_flow_cachep, fcnt, tofree); } -static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) +/* Fast path can be used if : + * 1) Packet tstamp is in the past. + * 2) FQ qlen == 0 OR + * (no flow is currently eligible for transmit, + * AND fast path queue has less than 8 packets) + * 3) No SO_MAX_PACING_RATE on the socket (if any). + * 4) No @maxrate attribute on this qdisc, + * + * FQ can not use generic TCQ_F_CAN_BYPASS infrastructure. + */ +static bool fq_fastpath_check(const struct Qdisc *sch, struct sk_buff *skb) +{ + const struct fq_sched_data *q = qdisc_priv(sch); + const struct sock *sk; + + if (fq_skb_cb(skb)->time_to_send > q->ktime_cache) + return false; + + if (sch->q.qlen != 0) { + /* Even if some packets are stored in this qdisc, + * we can still enable fast path if all of them are + * scheduled in the future (ie no flows are eligible) + * or in the fast path queue. + */ + if (q->flows != q->inactive_flows + q->throttled_flows) + return false; + + /* Do not allow fast path queue to explode, we want Fair Queue mode + * under pressure. + */ + if (q->internal.qlen >= 8) + return false; + } + + sk = skb->sk; + if (sk && sk_fullsock(sk) && !sk_is_tcp(sk) && + sk->sk_max_pacing_rate != ~0UL) + return false; + + if (q->flow_max_rate != ~0UL) + return false; + + return true; +} + +static struct fq_flow *fq_classify(struct Qdisc *sch, struct sk_buff *skb) { + struct fq_sched_data *q = qdisc_priv(sch); struct rb_node **p, *parent; struct sock *sk = skb->sk; struct rb_root *root; struct fq_flow *f; /* warning: no starvation prevention... */ - if (unlikely((skb->priority & TC_PRIO_MAX) == TC_PRIO_CONTROL)) + if (unlikely((skb->priority & TC_PRIO_MAX) == TC_PRIO_CONTROL)) { + q->stat_internal_packets++; /* highprio packet */ return &q->internal; - + } /* SYNACK messages are attached to a TCP_NEW_SYN_RECV request socket * or a listener (SYNCOOKIE mode) * 1) request sockets are not full blown, @@ -307,6 +360,11 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) sk = (struct sock *)((hash << 1) | 1UL); } + if (fq_fastpath_check(sch, skb)) { + q->internal.stat_fastpath_packets++; + return &q->internal; + } + root = &q->fq_root[hash_ptr(sk, q->fq_trees_log)]; if (q->flows >= (2U << q->fq_trees_log) && @@ -402,12 +460,8 @@ static void fq_erase_head(struct Qdisc *sch, struct fq_flow *flow, static void fq_dequeue_skb(struct Qdisc *sch, struct fq_flow *flow, struct sk_buff *skb) { - struct fq_sched_data *q = qdisc_priv(sch); - fq_erase_head(sch, flow, skb); skb_mark_not_on_list(skb); - if (--flow->qlen == 0) - q->inactive_flows++; qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; } @@ -459,49 +513,45 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (unlikely(sch->q.qlen >= sch->limit)) return qdisc_drop(skb, sch, to_free); + q->ktime_cache = ktime_get_ns(); if (!skb->tstamp) { - fq_skb_cb(skb)->time_to_send = q->ktime_cache = ktime_get_ns(); + fq_skb_cb(skb)->time_to_send = q->ktime_cache; } else { - /* Check if packet timestamp is too far in the future. - * Try first if our cached value, to avoid ktime_get_ns() - * cost in most cases. - */ + /* Check if packet timestamp is too far in the future. */ if (fq_packet_beyond_horizon(skb, q)) { - /* Refresh our cache and check another time */ - q->ktime_cache = ktime_get_ns(); - if (fq_packet_beyond_horizon(skb, q)) { - if (q->horizon_drop) { + if (q->horizon_drop) { q->stat_horizon_drops++; return qdisc_drop(skb, sch, to_free); - } - q->stat_horizon_caps++; - skb->tstamp = q->ktime_cache + q->horizon; } + q->stat_horizon_caps++; + skb->tstamp = q->ktime_cache + q->horizon; } fq_skb_cb(skb)->time_to_send = skb->tstamp; } - f = fq_classify(skb, q); - if (unlikely(f->qlen >= q->flow_plimit && f != &q->internal)) { - q->stat_flows_plimit++; - return qdisc_drop(skb, sch, to_free); - } + f = fq_classify(sch, skb); - if (f->qlen++ == 0) - q->inactive_flows--; - qdisc_qstats_backlog_inc(sch, skb); - if (fq_flow_is_detached(f)) { - fq_flow_add_tail(&q->new_flows, f); - if (time_after(jiffies, f->age + q->flow_refill_delay)) - f->credit = max_t(u32, f->credit, q->quantum); + if (f != &q->internal) { + if (unlikely(f->qlen >= q->flow_plimit)) { + q->stat_flows_plimit++; + return qdisc_drop(skb, sch, to_free); + } + + if (fq_flow_is_detached(f)) { + fq_flow_add_tail(&q->new_flows, f); + if (time_after(jiffies, f->age + q->flow_refill_delay)) + f->credit = max_t(u32, f->credit, q->quantum); + } + + if (f->qlen == 0) + q->inactive_flows--; } + f->qlen++; /* Note: this overwrites f->age */ flow_queue_add(f, skb); - if (unlikely(f == &q->internal)) { - q->stat_internal_packets++; - } + qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; return NET_XMIT_SUCCESS; @@ -549,6 +599,7 @@ static struct sk_buff *fq_dequeue(struct Qdisc *sch) skb = fq_peek(&q->internal); if (unlikely(skb)) { + q->internal.qlen--; fq_dequeue_skb(sch, &q->internal, skb); goto out; } @@ -592,6 +643,8 @@ begin: INET_ECN_set_ce(skb); q->stat_ce_mark++; } + if (--f->qlen == 0) + q->inactive_flows++; fq_dequeue_skb(sch, f, skb); } else { head->first = f->next; @@ -1024,6 +1077,7 @@ static int fq_dump_stats(struct Qdisc *sch, struct gnet_dump *d) st.gc_flows = q->stat_gc_flows; st.highprio_packets = q->stat_internal_packets; + st.fastpath_packets = q->internal.stat_fastpath_packets; st.tcp_retrans = 0; st.throttled = q->stat_throttled; st.flows_plimit = q->stat_flows_plimit; -- cgit From b37e6b680e3a4fad40d8c7b92cfe9b2806c6248e Mon Sep 17 00:00:00 2001 From: Tianrui Zhao Date: Mon, 2 Oct 2023 10:01:20 +0800 Subject: LoongArch: KVM: Add kvm related header files Add LoongArch KVM related header files, including kvm.h, kvm_host.h and kvm_types.h. All of those are about LoongArch virtualization features and kvm interfaces. Reviewed-by: Bibo Mao Tested-by: Huacai Chen Signed-off-by: Tianrui Zhao Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/kvm_host.h | 237 +++++++++++++++++++++++++++++++++ arch/loongarch/include/asm/kvm_types.h | 11 ++ arch/loongarch/include/uapi/asm/kvm.h | 108 +++++++++++++++ include/uapi/linux/kvm.h | 9 ++ 4 files changed, 365 insertions(+) create mode 100644 arch/loongarch/include/asm/kvm_host.h create mode 100644 arch/loongarch/include/asm/kvm_types.h create mode 100644 arch/loongarch/include/uapi/asm/kvm.h (limited to 'include/uapi/linux') diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h new file mode 100644 index 000000000000..11328700d4fa --- /dev/null +++ b/arch/loongarch/include/asm/kvm_host.h @@ -0,0 +1,237 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020-2023 Loongson Technology Corporation Limited + */ + +#ifndef __ASM_LOONGARCH_KVM_HOST_H__ +#define __ASM_LOONGARCH_KVM_HOST_H__ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +/* Loongarch KVM register ids */ +#define KVM_GET_IOC_CSR_IDX(id) ((id & KVM_CSR_IDX_MASK) >> LOONGARCH_REG_SHIFT) +#define KVM_GET_IOC_CPUCFG_IDX(id) ((id & KVM_CPUCFG_IDX_MASK) >> LOONGARCH_REG_SHIFT) + +#define KVM_MAX_VCPUS 256 +#define KVM_MAX_CPUCFG_REGS 21 +/* memory slots that does not exposed to userspace */ +#define KVM_PRIVATE_MEM_SLOTS 0 + +#define KVM_HALT_POLL_NS_DEFAULT 500000 + +struct kvm_vm_stat { + struct kvm_vm_stat_generic generic; + u64 pages; + u64 hugepages; +}; + +struct kvm_vcpu_stat { + struct kvm_vcpu_stat_generic generic; + u64 int_exits; + u64 idle_exits; + u64 cpucfg_exits; + u64 signal_exits; +}; + +struct kvm_arch_memory_slot { +}; + +struct kvm_context { + unsigned long vpid_cache; + struct kvm_vcpu *last_vcpu; +}; + +struct kvm_world_switch { + int (*exc_entry)(void); + int (*enter_guest)(struct kvm_run *run, struct kvm_vcpu *vcpu); + unsigned long page_order; +}; + +#define MAX_PGTABLE_LEVELS 4 + +struct kvm_arch { + /* Guest physical mm */ + kvm_pte_t *pgd; + unsigned long gpa_size; + unsigned long invalid_ptes[MAX_PGTABLE_LEVELS]; + unsigned int pte_shifts[MAX_PGTABLE_LEVELS]; + unsigned int root_level; + + s64 time_offset; + struct kvm_context __percpu *vmcs; +}; + +#define CSR_MAX_NUMS 0x800 + +struct loongarch_csrs { + unsigned long csrs[CSR_MAX_NUMS]; +}; + +/* Resume Flags */ +#define RESUME_HOST 0 +#define RESUME_GUEST 1 + +enum emulation_result { + EMULATE_DONE, /* no further processing */ + EMULATE_DO_MMIO, /* kvm_run filled with MMIO request */ + EMULATE_DO_IOCSR, /* handle IOCSR request */ + EMULATE_FAIL, /* can't emulate this instruction */ + EMULATE_EXCEPT, /* A guest exception has been generated */ +}; + +#define KVM_LARCH_FPU (0x1 << 0) +#define KVM_LARCH_SWCSR_LATEST (0x1 << 1) +#define KVM_LARCH_HWCSR_USABLE (0x1 << 2) + +struct kvm_vcpu_arch { + /* + * Switch pointer-to-function type to unsigned long + * for loading the value into register directly. + */ + unsigned long host_eentry; + unsigned long guest_eentry; + + /* Pointers stored here for easy accessing from assembly code */ + int (*handle_exit)(struct kvm_run *run, struct kvm_vcpu *vcpu); + + /* Host registers preserved across guest mode execution */ + unsigned long host_sp; + unsigned long host_tp; + unsigned long host_pgd; + + /* Host CSRs are used when handling exits from guest */ + unsigned long badi; + unsigned long badv; + unsigned long host_ecfg; + unsigned long host_estat; + unsigned long host_percpu; + + /* GPRs */ + unsigned long gprs[32]; + unsigned long pc; + + /* Which auxiliary state is loaded (KVM_LARCH_*) */ + unsigned int aux_inuse; + + /* FPU state */ + struct loongarch_fpu fpu FPU_ALIGN; + + /* CSR state */ + struct loongarch_csrs *csr; + + /* GPR used as IO source/target */ + u32 io_gpr; + + /* KVM register to control count timer */ + u32 count_ctl; + struct hrtimer swtimer; + + /* Bitmask of intr that are pending */ + unsigned long irq_pending; + /* Bitmask of pending intr to be cleared */ + unsigned long irq_clear; + + /* Bitmask of exceptions that are pending */ + unsigned long exception_pending; + unsigned int esubcode; + + /* Cache for pages needed inside spinlock regions */ + struct kvm_mmu_memory_cache mmu_page_cache; + + /* vcpu's vpid */ + u64 vpid; + + /* Frequency of stable timer in Hz */ + u64 timer_mhz; + ktime_t expire; + + /* Last CPU the vCPU state was loaded on */ + int last_sched_cpu; + /* mp state */ + struct kvm_mp_state mp_state; + /* cpucfg */ + u32 cpucfg[KVM_MAX_CPUCFG_REGS]; +}; + +static inline unsigned long readl_sw_gcsr(struct loongarch_csrs *csr, int reg) +{ + return csr->csrs[reg]; +} + +static inline void writel_sw_gcsr(struct loongarch_csrs *csr, int reg, unsigned long val) +{ + csr->csrs[reg] = val; +} + +/* Debug: dump vcpu state */ +int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu); + +/* MMU handling */ +void kvm_flush_tlb_all(void); +void kvm_flush_tlb_gpa(struct kvm_vcpu *vcpu, unsigned long gpa); +int kvm_handle_mm_fault(struct kvm_vcpu *vcpu, unsigned long badv, bool write); + +#define KVM_ARCH_WANT_MMU_NOTIFIER +void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, bool blockable); +int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); + +static inline void update_pc(struct kvm_vcpu_arch *arch) +{ + arch->pc += 4; +} + +/* + * kvm_is_ifetch_fault() - Find whether a TLBL exception is due to ifetch fault. + * @vcpu: Virtual CPU. + * + * Returns: Whether the TLBL exception was likely due to an instruction + * fetch fault rather than a data load fault. + */ +static inline bool kvm_is_ifetch_fault(struct kvm_vcpu_arch *arch) +{ + return arch->pc == arch->badv; +} + +/* Misc */ +static inline void kvm_arch_hardware_unsetup(void) {} +static inline void kvm_arch_sync_events(struct kvm *kvm) {} +static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} +static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} +static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} +static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} +static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} +static inline void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) {} +void kvm_check_vpid(struct kvm_vcpu *vcpu); +enum hrtimer_restart kvm_swtimer_wakeup(struct hrtimer *timer); +void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, const struct kvm_memory_slot *memslot); +void kvm_init_vmcs(struct kvm *kvm); +void kvm_exc_entry(void); +int kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu); + +extern unsigned long vpid_mask; +extern const unsigned long kvm_exception_size; +extern const unsigned long kvm_enter_guest_size; +extern struct kvm_world_switch *kvm_loongarch_ops; + +#define SW_GCSR (1 << 0) +#define HW_GCSR (1 << 1) +#define INVALID_GCSR (1 << 2) + +int get_gcsr_flag(int csr); +void set_hw_gcsr(int csr_id, unsigned long val); + +#endif /* __ASM_LOONGARCH_KVM_HOST_H__ */ diff --git a/arch/loongarch/include/asm/kvm_types.h b/arch/loongarch/include/asm/kvm_types.h new file mode 100644 index 000000000000..2fe1d4bdff66 --- /dev/null +++ b/arch/loongarch/include/asm/kvm_types.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020-2023 Loongson Technology Corporation Limited + */ + +#ifndef _ASM_LOONGARCH_KVM_TYPES_H +#define _ASM_LOONGARCH_KVM_TYPES_H + +#define KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE 40 + +#endif /* _ASM_LOONGARCH_KVM_TYPES_H */ diff --git a/arch/loongarch/include/uapi/asm/kvm.h b/arch/loongarch/include/uapi/asm/kvm.h new file mode 100644 index 000000000000..c6ad2ee6106c --- /dev/null +++ b/arch/loongarch/include/uapi/asm/kvm.h @@ -0,0 +1,108 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (C) 2020-2023 Loongson Technology Corporation Limited + */ + +#ifndef __UAPI_ASM_LOONGARCH_KVM_H +#define __UAPI_ASM_LOONGARCH_KVM_H + +#include + +/* + * KVM LoongArch specific structures and definitions. + * + * Some parts derived from the x86 version of this file. + */ + +#define __KVM_HAVE_READONLY_MEM + +#define KVM_COALESCED_MMIO_PAGE_OFFSET 1 +#define KVM_DIRTY_LOG_PAGE_OFFSET 64 + +/* + * for KVM_GET_REGS and KVM_SET_REGS + */ +struct kvm_regs { + /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */ + __u64 gpr[32]; + __u64 pc; +}; + +/* + * for KVM_GET_FPU and KVM_SET_FPU + */ +struct kvm_fpu { + __u32 fcsr; + __u64 fcc; /* 8x8 */ + struct kvm_fpureg { + __u64 val64[4]; + } fpr[32]; +}; + +/* + * For LoongArch, we use KVM_SET_ONE_REG and KVM_GET_ONE_REG to access various + * registers. The id field is broken down as follows: + * + * bits[63..52] - As per linux/kvm.h + * bits[51..32] - Must be zero. + * bits[31..16] - Register set. + * + * Register set = 0: GP registers from kvm_regs (see definitions below). + * + * Register set = 1: CSR registers. + * + * Register set = 2: KVM specific registers (see definitions below). + * + * Register set = 3: FPU / SIMD registers (see definitions below). + * + * Other sets registers may be added in the future. Each set would + * have its own identifier in bits[31..16]. + */ + +#define KVM_REG_LOONGARCH_GPR (KVM_REG_LOONGARCH | 0x00000ULL) +#define KVM_REG_LOONGARCH_CSR (KVM_REG_LOONGARCH | 0x10000ULL) +#define KVM_REG_LOONGARCH_KVM (KVM_REG_LOONGARCH | 0x20000ULL) +#define KVM_REG_LOONGARCH_FPSIMD (KVM_REG_LOONGARCH | 0x30000ULL) +#define KVM_REG_LOONGARCH_CPUCFG (KVM_REG_LOONGARCH | 0x40000ULL) +#define KVM_REG_LOONGARCH_MASK (KVM_REG_LOONGARCH | 0x70000ULL) +#define KVM_CSR_IDX_MASK 0x7fff +#define KVM_CPUCFG_IDX_MASK 0x7fff + +/* + * KVM_REG_LOONGARCH_KVM - KVM specific control registers. + */ + +#define KVM_REG_LOONGARCH_COUNTER (KVM_REG_LOONGARCH_KVM | KVM_REG_SIZE_U64 | 1) +#define KVM_REG_LOONGARCH_VCPU_RESET (KVM_REG_LOONGARCH_KVM | KVM_REG_SIZE_U64 | 2) + +#define LOONGARCH_REG_SHIFT 3 +#define LOONGARCH_REG_64(TYPE, REG) (TYPE | KVM_REG_SIZE_U64 | (REG << LOONGARCH_REG_SHIFT)) +#define KVM_IOC_CSRID(REG) LOONGARCH_REG_64(KVM_REG_LOONGARCH_CSR, REG) +#define KVM_IOC_CPUCFG(REG) LOONGARCH_REG_64(KVM_REG_LOONGARCH_CPUCFG, REG) + +struct kvm_debug_exit_arch { +}; + +/* for KVM_SET_GUEST_DEBUG */ +struct kvm_guest_debug_arch { +}; + +/* definition of registers in kvm_run */ +struct kvm_sync_regs { +}; + +/* dummy definition */ +struct kvm_sregs { +}; + +struct kvm_iocsr_entry { + __u32 addr; + __u32 pad; + __u64 data; +}; + +#define KVM_NR_IRQCHIPS 1 +#define KVM_IRQCHIP_NUM_PINS 64 +#define KVM_MAX_CORES 256 + +#endif /* __UAPI_ASM_LOONGARCH_KVM_H */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 13065dd96132..863f84619a15 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -264,6 +264,7 @@ struct kvm_xen_exit { #define KVM_EXIT_RISCV_SBI 35 #define KVM_EXIT_RISCV_CSR 36 #define KVM_EXIT_NOTIFY 37 +#define KVM_EXIT_LOONGARCH_IOCSR 38 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -336,6 +337,13 @@ struct kvm_run { __u32 len; __u8 is_write; } mmio; + /* KVM_EXIT_LOONGARCH_IOCSR */ + struct { + __u64 phys_addr; + __u8 data[8]; + __u32 len; + __u8 is_write; + } iocsr_io; /* KVM_EXIT_HYPERCALL */ struct { __u64 nr; @@ -1362,6 +1370,7 @@ struct kvm_dirty_tlb { #define KVM_REG_ARM64 0x6000000000000000ULL #define KVM_REG_MIPS 0x7000000000000000ULL #define KVM_REG_RISCV 0x8000000000000000ULL +#define KVM_REG_LOONGARCH 0x9000000000000000ULL #define KVM_REG_SIZE_SHIFT 52 #define KVM_REG_SIZE_MASK 0x00f0000000000000ULL -- cgit From d844fe65f0957024c3e1b0bf2a0615246184d9bc Mon Sep 17 00:00:00 2001 From: Kir Kolyshkin Date: Mon, 7 Aug 2023 20:03:57 -0700 Subject: sched/headers: Move 'struct sched_param' out of uapi, to work around glibc/musl breakage MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Both glibc and musl define 'struct sched_param' in sched.h, while kernel has it in uapi/linux/sched/types.h, making it cumbersome to use sched_getattr(2) or sched_setattr(2) from userspace. For example, something like this: #include #include struct sched_attr sa; will result in "error: redefinition of ‘struct sched_param’" (note the code doesn't need sched_param at all -- it needs struct sched_attr plus some stuff from sched.h). The situation is, glibc is not going to provide a wrapper for sched_{get,set}attr, thus the need to include linux/sched_types.h directly, which leads to the above problem. Thus, the userspace is left with a few sub-par choices when it wants to use e.g. sched_setattr(2), such as maintaining a copy of struct sched_attr definition, or using some other ugly tricks. OTOH, 'struct sched_param' is well known, defined in POSIX, and it won't be ever changed (as that would break backward compatibility). So, while 'struct sched_param' is indeed part of the kernel uapi, exposing it the way it's done now creates an issue, and hiding it (like this patch does) fixes that issue, hopefully without creating another one: common userspace software rely on libc headers, and as for "special" software (like libc), it looks like glibc and musl do not rely on kernel headers for 'struct sched_param' definition (but let's Cc their mailing lists in case it's otherwise). The alternative to this patch would be to move struct sched_attr to, say, linux/sched.h, or linux/sched/attr.h (the new file). Oh, and here is the previous attempt to fix the issue: https://lore.kernel.org/all/20200528135552.GA87103@google.com/ While I support Linus arguments, the issue is still here and needs to be fixed. [ mingo: Linus is right, this shouldn't be needed - but on the other hand I agree that this header is not really helpful to user-space as-is. So let's pretend that is only about sched_attr, and call this commit a workaround for user-space breakage that it in reality is ... Also, remove the Fixes tag. ] Signed-off-by: Kir Kolyshkin Signed-off-by: Ingo Molnar Cc: Linus Torvalds Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230808030357.1213829-1-kolyshkin@gmail.com --- include/linux/sched.h | 5 ++++- include/uapi/linux/sched/types.h | 4 ---- 2 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index dc37ae787e33..e4235bbfad77 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -63,7 +63,6 @@ struct robust_list_head; struct root_domain; struct rq; struct sched_attr; -struct sched_param; struct seq_file; struct sighand_struct; struct signal_struct; @@ -370,6 +369,10 @@ extern struct root_domain def_root_domain; extern struct mutex sched_domains_mutex; #endif +struct sched_param { + int sched_priority; +}; + struct sched_info { #ifdef CONFIG_SCHED_INFO /* Cumulative counters: */ diff --git a/include/uapi/linux/sched/types.h b/include/uapi/linux/sched/types.h index f2c4589d4dbf..90662385689b 100644 --- a/include/uapi/linux/sched/types.h +++ b/include/uapi/linux/sched/types.h @@ -4,10 +4,6 @@ #include -struct sched_param { - int sched_priority; -}; - #define SCHED_ATTR_SIZE_VER0 48 /* sizeof first published struct */ #define SCHED_ATTR_SIZE_VER1 56 /* add: util_{min,max} */ -- cgit From b02d006194938593373f189f8d0e84991e6949a2 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 22 Sep 2023 08:36:41 +0200 Subject: serial: core: remove cruft from uapi header Remove the GPL boilerplate since we have a valid SPDX entry. Also, remove the outdated filename from the comment. Signed-off-by: Wolfram Sang Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230922063642.4120-2-wsa+renesas@sang-engineering.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/serial_core.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index add349889d0a..92e3dd56f631 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -1,22 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* - * linux/drivers/char/serial_core.h - * * Copyright (C) 2000 Deep Blue Solutions Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _UAPILINUX_SERIAL_CORE_H #define _UAPILINUX_SERIAL_CORE_H -- cgit From 00c77bcf2a624e6863121ea0eeb37e35c58ca5d0 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 22 Sep 2023 08:36:42 +0200 Subject: serial: core: add comment about definitely used port types When port type 18 was removed, it was deduced that the code could go but its define has to stay because it is used in userspace. Share that knowledge by adding a comment about it. Signed-off-by: Wolfram Sang Link: https://lore.kernel.org/r/20230922063642.4120-3-wsa+renesas@sang-engineering.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/serial_core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index 92e3dd56f631..46e06c483899 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -11,6 +11,8 @@ * The type definitions. These are from Ted Ts'o's serial.h * By historical reasons the values from 0 to 13 are defined * in the include/uapi/linux/serial.h, do not define them here. + * Values 0 to 19 are used by setserial from busybox and must never + * be modified. */ #define PORT_NS16550A 14 #define PORT_XSCALE 15 -- cgit From bdca03a271f2de2c24ea56756fd9bbcff35173fb Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Tue, 3 Oct 2023 15:52:59 +0300 Subject: PCI: Add PCI_HEADER_TYPE_MFD definition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add PCI_HEADER_TYPE_MFD so we can replace literals in the code. Link: https://lore.kernel.org/r/20231003125300.5541-3-ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen Signed-off-by: Bjorn Helgaas --- include/uapi/linux/pci_regs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index e5f558d96493..06df65f11c39 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -80,6 +80,7 @@ #define PCI_HEADER_TYPE_NORMAL 0 #define PCI_HEADER_TYPE_BRIDGE 1 #define PCI_HEADER_TYPE_CARDBUS 2 +#define PCI_HEADER_TYPE_MFD 0x80 /* Multi-Function Device (possible) */ #define PCI_BIST 0x0f /* 8 bits */ #define PCI_BIST_CODE_MASK 0x0f /* Return result */ -- cgit From 5dbd04eddb2c0841d1b3930e0a9944a2343c9cac Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 12 Sep 2023 18:07:02 +0000 Subject: tracing/user_events: Allow events to persist for perfmon_capable users There are several scenarios that have come up where having a user_event persist even if the process that registered it exits. The main one is having a daemon create events on bootup that shouldn't get deleted if the daemon has to exit or reload. Another is within OpenTelemetry exporters, they wish to potentially check if a user_event exists on the system to determine if exporting the data out should occur. The user_event in this case must exist even in the absence of the owning process running (such as the above daemon case). Expose the previously internal flag USER_EVENT_REG_PERSIST to user processes. Upon register or delete of events with this flag, ensure the user is perfmon_capable to prevent random user processes with access to tracefs from creating events that persist after exit. Link: https://lkml.kernel.org/r/20230912180704.1284-2-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/uapi/linux/user_events.h | 11 ++++++++++- kernel/trace/trace_events_user.c | 36 ++++++++++++++++++++++-------------- 2 files changed, 32 insertions(+), 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/user_events.h b/include/uapi/linux/user_events.h index 2984aae4a2b4..f74f3aedd49c 100644 --- a/include/uapi/linux/user_events.h +++ b/include/uapi/linux/user_events.h @@ -17,6 +17,15 @@ /* Create dynamic location entry within a 32-bit value */ #define DYN_LOC(offset, size) ((size) << 16 | (offset)) +/* List of supported registration flags */ +enum user_reg_flag { + /* Event will not delete upon last reference closing */ + USER_EVENT_REG_PERSIST = 1U << 0, + + /* This value or above is currently non-ABI */ + USER_EVENT_REG_MAX = 1U << 1, +}; + /* * Describes an event registration and stores the results of the registration. * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum @@ -33,7 +42,7 @@ struct user_reg { /* Input: Enable size in bytes at address */ __u8 enable_size; - /* Input: Flags for future use, set to 0 */ + /* Input: Flags to use, if any */ __u16 flags; /* Input: Address to update when enabled */ diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index b87f41187c6a..9365ce407426 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -49,18 +49,6 @@ #define EVENT_STATUS_PERF BIT(1) #define EVENT_STATUS_OTHER BIT(7) -/* - * User register flags are not allowed yet, keep them here until we are - * ready to expose them out to the user ABI. - */ -enum user_reg_flag { - /* Event will not delete upon last reference closing */ - USER_EVENT_REG_PERSIST = 1U << 0, - - /* This value or above is currently non-ABI */ - USER_EVENT_REG_MAX = 1U << 1, -}; - /* * Stores the system name, tables, and locks for a group of events. This * allows isolation for events by various means. @@ -220,6 +208,17 @@ static u32 user_event_key(char *name) return jhash(name, strlen(name), 0); } +static bool user_event_capable(u16 reg_flags) +{ + /* Persistent events require CAP_PERFMON / CAP_SYS_ADMIN */ + if (reg_flags & USER_EVENT_REG_PERSIST) { + if (!perfmon_capable()) + return false; + } + + return true; +} + static struct user_event *user_event_get(struct user_event *user) { refcount_inc(&user->refcnt); @@ -1811,6 +1810,9 @@ static int user_event_free(struct dyn_event *ev) if (!user_event_last_ref(user)) return -EBUSY; + if (!user_event_capable(user->reg_flags)) + return -EPERM; + return destroy_user_event(user); } @@ -1926,10 +1928,13 @@ static int user_event_parse(struct user_event_group *group, char *name, int argc = 0; char **argv; - /* User register flags are not ready yet */ - if (reg_flags != 0 || flags != NULL) + /* Currently don't support any text based flags */ + if (flags != NULL) return -EINVAL; + if (!user_event_capable(reg_flags)) + return -EPERM; + /* Prevent dyn_event from racing */ mutex_lock(&event_mutex); user = find_user_event(group, name, &key); @@ -2062,6 +2067,9 @@ static int delete_user_event(struct user_event_group *group, char *name) if (!user_event_last_ref(user)) return -EBUSY; + if (!user_event_capable(user->reg_flags)) + return -EPERM; + return destroy_user_event(user); } -- cgit From 7af1e0aceeb321cbc90fcf6fa0bec8870290377f Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 8 Sep 2023 13:10:45 -0700 Subject: dmaengine: idxd: add wq driver name support for accel-config user tool With the possibility of multiple wq drivers that can be bound to the wq, the user config tool accel-config needs a way to know which wq driver to bind to the wq. Introduce per wq driver_name sysfs attribute where the user can indicate the driver to be bound to the wq. This allows accel-config to just bind to the driver using wq->driver_name. Signed-off-by: Dave Jiang Signed-off-by: Tom Zanussi Reviewed-by: Fenghua Yu Acked-by: Vinod Koul Link: https://lore.kernel.org/r/20230908201045.4115614-1-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- Documentation/ABI/stable/sysfs-driver-dma-idxd | 6 +++++ drivers/dma/idxd/cdev.c | 7 ++++++ drivers/dma/idxd/dma.c | 6 +++++ drivers/dma/idxd/idxd.h | 9 +++++++ drivers/dma/idxd/sysfs.c | 34 ++++++++++++++++++++++++++ include/uapi/linux/idxd.h | 1 + 6 files changed, 63 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/ABI/stable/sysfs-driver-dma-idxd b/Documentation/ABI/stable/sysfs-driver-dma-idxd index 825e619250bf..f2ec42949a54 100644 --- a/Documentation/ABI/stable/sysfs-driver-dma-idxd +++ b/Documentation/ABI/stable/sysfs-driver-dma-idxd @@ -270,6 +270,12 @@ Description: Shows the operation capability bits displayed in bitmap format correlates to the operations allowed. It's visible only on platforms that support the capability. +What: /sys/bus/dsa/devices/wq./driver_name +Date: Sept 8, 2023 +KernelVersion: 6.7.0 +Contact: dmaengine@vger.kernel.org +Description: Name of driver to be bounded to the wq. + What: /sys/bus/dsa/devices/engine./group_id Date: Oct 25, 2019 KernelVersion: 5.6.0 diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index d32deb9b4e3d..0423655f5a88 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -509,6 +509,7 @@ void idxd_wq_del_cdev(struct idxd_wq *wq) static int idxd_user_drv_probe(struct idxd_dev *idxd_dev) { + struct device *dev = &idxd_dev->conf_dev; struct idxd_wq *wq = idxd_dev_to_wq(idxd_dev); struct idxd_device *idxd = wq->idxd; int rc; @@ -536,6 +537,12 @@ static int idxd_user_drv_probe(struct idxd_dev *idxd_dev) mutex_lock(&wq->wq_lock); + if (!idxd_wq_driver_name_match(wq, dev)) { + idxd->cmd_status = IDXD_SCMD_WQ_NO_DRV_NAME; + rc = -ENODEV; + goto wq_err; + } + wq->wq = create_workqueue(dev_name(wq_confdev(wq))); if (!wq->wq) { rc = -ENOMEM; diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c index 07623fb0f52f..47a01893cfdb 100644 --- a/drivers/dma/idxd/dma.c +++ b/drivers/dma/idxd/dma.c @@ -306,6 +306,12 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev) return -ENXIO; mutex_lock(&wq->wq_lock); + if (!idxd_wq_driver_name_match(wq, dev)) { + idxd->cmd_status = IDXD_SCMD_WQ_NO_DRV_NAME; + rc = -ENODEV; + goto err; + } + wq->type = IDXD_WQT_KERNEL; rc = drv_enable_wq(wq); diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index e269ca1f4862..1e89c80a07fc 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -159,6 +159,8 @@ struct idxd_cdev { int minor; }; +#define DRIVER_NAME_SIZE 128 + #define IDXD_ALLOCATED_BATCH_SIZE 128U #define WQ_NAME_SIZE 1024 #define WQ_TYPE_SIZE 10 @@ -227,6 +229,8 @@ struct idxd_wq { /* Lock to protect upasid_xa access. */ struct mutex uc_lock; struct xarray upasid_xa; + + char driver_name[DRIVER_NAME_SIZE + 1]; }; struct idxd_engine { @@ -646,6 +650,11 @@ static inline void idxd_wqcfg_set_max_batch_shift(int idxd_type, union wqcfg *wq wqcfg->max_batch_shift = max_batch_shift; } +static inline int idxd_wq_driver_name_match(struct idxd_wq *wq, struct device *dev) +{ + return (strncmp(wq->driver_name, dev->driver->name, strlen(dev->driver->name)) == 0); +} + int __must_check __idxd_driver_register(struct idxd_device_driver *idxd_drv, struct module *module, const char *mod_name); #define idxd_driver_register(driver) \ diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 7caba90d85b3..523ae0dff7d4 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -1259,6 +1259,39 @@ err: static struct device_attribute dev_attr_wq_op_config = __ATTR(op_config, 0644, wq_op_config_show, wq_op_config_store); +static ssize_t wq_driver_name_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct idxd_wq *wq = confdev_to_wq(dev); + + return sysfs_emit(buf, "%s\n", wq->driver_name); +} + +static ssize_t wq_driver_name_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct idxd_wq *wq = confdev_to_wq(dev); + char *input, *pos; + + if (wq->state != IDXD_WQ_DISABLED) + return -EPERM; + + if (strlen(buf) > DRIVER_NAME_SIZE || strlen(buf) == 0) + return -EINVAL; + + input = kstrndup(buf, count, GFP_KERNEL); + if (!input) + return -ENOMEM; + + pos = strim(input); + memset(wq->driver_name, 0, DRIVER_NAME_SIZE + 1); + sprintf(wq->driver_name, "%s", pos); + kfree(input); + return count; +} + +static struct device_attribute dev_attr_wq_driver_name = + __ATTR(driver_name, 0644, wq_driver_name_show, wq_driver_name_store); + static struct attribute *idxd_wq_attributes[] = { &dev_attr_wq_clients.attr, &dev_attr_wq_state.attr, @@ -1278,6 +1311,7 @@ static struct attribute *idxd_wq_attributes[] = { &dev_attr_wq_occupancy.attr, &dev_attr_wq_enqcmds_retries.attr, &dev_attr_wq_op_config.attr, + &dev_attr_wq_driver_name.attr, NULL, }; diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index 606b52e88ce3..3d1987e1bb2d 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -31,6 +31,7 @@ enum idxd_scmd_stat { IDXD_SCMD_WQ_IRQ_ERR = 0x80100000, IDXD_SCMD_WQ_USER_NO_IOMMU = 0x80110000, IDXD_SCMD_DEV_EVL_ERR = 0x80120000, + IDXD_SCMD_WQ_NO_DRV_NAME = 0x80200000, }; #define IDXD_SCMD_SOFTERR_MASK 0x80000000 -- cgit From 3f9cd0ca848413fd368278310d2cdd6c2bef48b2 Mon Sep 17 00:00:00 2001 From: Jing Zhang Date: Tue, 3 Oct 2023 23:03:57 +0000 Subject: KVM: arm64: Allow userspace to get the writable masks for feature ID registers While the Feature ID range is well defined and pretty large, it isn't inconceivable that the architecture will eventually grow some other ranges that will need to similarly be described to userspace. Add a VM ioctl to allow userspace to get writable masks for feature ID registers in below system register space: op0 = 3, op1 = {0, 1, 3}, CRn = 0, CRm = {0 - 7}, op2 = {0 - 7} This is used to support mix-and-match userspace and kernels for writable ID registers, where userspace may want to know upfront whether it can actually tweak the contents of an idreg or not. Add a new capability (KVM_CAP_ARM_SUPPORTED_FEATURE_ID_RANGES) that returns a bitmap of the valid ranges, which can subsequently be retrieved, one at a time by setting the index of the set bit as the range identifier. Suggested-by: Marc Zyngier Suggested-by: Cornelia Huck Signed-off-by: Jing Zhang Reviewed-by: Cornelia Huck Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20231003230408.3405722-2-oliver.upton@linux.dev Signed-off-by: Oliver Upton --- arch/arm64/include/asm/kvm_host.h | 2 ++ arch/arm64/include/uapi/asm/kvm.h | 32 +++++++++++++++++++ arch/arm64/kvm/arm.c | 10 ++++++ arch/arm64/kvm/sys_regs.c | 66 +++++++++++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 2 ++ 5 files changed, 112 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index af06ccb7ee34..5e3f778f81db 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -1078,6 +1078,8 @@ int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, struct kvm_arm_copy_mte_tags *copy_tags); int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm, struct kvm_arm_counter_offset *offset); +int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm, + struct reg_mask_range *range); /* Guest/host FPSIMD coordination helpers */ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index f7ddd73a8c0f..89d2fc872d9f 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -505,6 +505,38 @@ struct kvm_smccc_filter { #define KVM_HYPERCALL_EXIT_SMC (1U << 0) #define KVM_HYPERCALL_EXIT_16BIT (1U << 1) +/* + * Get feature ID registers userspace writable mask. + * + * From DDI0487J.a, D19.2.66 ("ID_AA64MMFR2_EL1, AArch64 Memory Model + * Feature Register 2"): + * + * "The Feature ID space is defined as the System register space in + * AArch64 with op0==3, op1=={0, 1, 3}, CRn==0, CRm=={0-7}, + * op2=={0-7}." + * + * This covers all currently known R/O registers that indicate + * anything useful feature wise, including the ID registers. + * + * If we ever need to introduce a new range, it will be described as + * such in the range field. + */ +#define KVM_ARM_FEATURE_ID_RANGE_IDX(op0, op1, crn, crm, op2) \ + ({ \ + __u64 __op1 = (op1) & 3; \ + __op1 -= (__op1 == 3); \ + (__op1 << 6 | ((crm) & 7) << 3 | (op2)); \ + }) + +#define KVM_ARM_FEATURE_ID_RANGE 0 +#define KVM_ARM_FEATURE_ID_RANGE_SIZE (3 * 8 * 8) + +struct reg_mask_range { + __u64 addr; /* Pointer to mask array */ + __u32 range; /* Requested range */ + __u32 reserved[13]; +}; + #endif #endif /* __ARM_KVM_H__ */ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 4866b3f7b4ea..f48430ed5b8b 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -317,6 +317,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES: r = kvm_supported_block_sizes(); break; + case KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES: + r = BIT(0); + break; default: r = 0; } @@ -1629,6 +1632,13 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) return kvm_vm_set_attr(kvm, &attr); } + case KVM_ARM_GET_REG_WRITABLE_MASKS: { + struct reg_mask_range range; + + if (copy_from_user(&range, argp, sizeof(range))) + return -EFAULT; + return kvm_vm_ioctl_get_reg_writable_masks(kvm, &range); + } default: return -EINVAL; } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index e92ec810d449..5b0e94367f74 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1373,6 +1373,13 @@ static inline bool is_id_reg(u32 id) sys_reg_CRm(id) < 8); } +static inline bool is_aa32_id_reg(u32 id) +{ + return (sys_reg_Op0(id) == 3 && sys_reg_Op1(id) == 0 && + sys_reg_CRn(id) == 0 && sys_reg_CRm(id) >= 1 && + sys_reg_CRm(id) <= 3); +} + static unsigned int id_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { @@ -3572,6 +3579,65 @@ int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) return write_demux_regids(uindices); } +#define KVM_ARM_FEATURE_ID_RANGE_INDEX(r) \ + KVM_ARM_FEATURE_ID_RANGE_IDX(sys_reg_Op0(r), \ + sys_reg_Op1(r), \ + sys_reg_CRn(r), \ + sys_reg_CRm(r), \ + sys_reg_Op2(r)) + +static bool is_feature_id_reg(u32 encoding) +{ + return (sys_reg_Op0(encoding) == 3 && + (sys_reg_Op1(encoding) < 2 || sys_reg_Op1(encoding) == 3) && + sys_reg_CRn(encoding) == 0 && + sys_reg_CRm(encoding) <= 7); +} + +int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm, struct reg_mask_range *range) +{ + const void *zero_page = page_to_virt(ZERO_PAGE(0)); + u64 __user *masks = (u64 __user *)range->addr; + + /* Only feature id range is supported, reserved[13] must be zero. */ + if (range->range || + memcmp(range->reserved, zero_page, sizeof(range->reserved))) + return -EINVAL; + + /* Wipe the whole thing first */ + if (clear_user(masks, KVM_ARM_FEATURE_ID_RANGE_SIZE * sizeof(__u64))) + return -EFAULT; + + for (int i = 0; i < ARRAY_SIZE(sys_reg_descs); i++) { + const struct sys_reg_desc *reg = &sys_reg_descs[i]; + u32 encoding = reg_to_encoding(reg); + u64 val; + + if (!is_feature_id_reg(encoding) || !reg->set_user) + continue; + + /* + * For ID registers, we return the writable mask. Other feature + * registers return a full 64bit mask. That's not necessary + * compliant with a given revision of the architecture, but the + * RES0/RES1 definitions allow us to do that. + */ + if (is_id_reg(encoding)) { + if (!reg->val || + (is_aa32_id_reg(encoding) && !kvm_supports_32bit_el0())) + continue; + val = reg->val; + } else { + val = ~0UL; + } + + if (put_user(val, (masks + KVM_ARM_FEATURE_ID_RANGE_INDEX(encoding)))) + return -EFAULT; + } + + return 0; +} + int __init kvm_sys_reg_table_init(void) { struct sys_reg_params params; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 13065dd96132..f49c84487200 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1192,6 +1192,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_COUNTER_OFFSET 227 #define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228 #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229 +#define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230 #ifdef KVM_CAP_IRQ_ROUTING @@ -1562,6 +1563,7 @@ struct kvm_s390_ucas_mapping { #define KVM_ARM_MTE_COPY_TAGS _IOR(KVMIO, 0xb4, struct kvm_arm_copy_mte_tags) /* Available with KVM_CAP_COUNTER_OFFSET */ #define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO, 0xb5, struct kvm_arm_counter_offset) +#define KVM_ARM_GET_REG_WRITABLE_MASKS _IOR(KVMIO, 0xb6, struct reg_mask_range) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) -- cgit From 1d495f1c896cfa8c78e7a858119e2fbfcbd0925e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 3 Oct 2023 16:18:28 -0700 Subject: xfrm: Annotate struct xfrm_sec_ctx with __counted_by Prepare for the coming implementation by GCC and Clang of the __counted_by attribute. Flexible array members annotated with __counted_by can have their accesses bounds-checked at run-time via CONFIG_UBSAN_BOUNDS (for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family functions). As found with Coccinelle[1], add __counted_by for struct xfrm_sec_ctx. Cc: Steffen Klassert Cc: Herbert Xu Cc: "David S. Miller" Cc: netdev@vger.kernel.org Link: https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci [1] Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Signed-off-by: Steffen Klassert --- include/uapi/linux/xfrm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 23543c33fee8..6a77328be114 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -4,6 +4,7 @@ #include #include +#include /* All of the structures in this file may not change size as they are * passed into the kernel from userspace via netlink sockets. @@ -33,7 +34,7 @@ struct xfrm_sec_ctx { __u8 ctx_alg; __u16 ctx_len; __u32 ctx_sid; - char ctx_str[]; + char ctx_str[] __counted_by(ctx_len); }; /* Security Context Domains of Interpretation */ -- cgit From 29f834aa326e659ed354c406056e94ea3d29706a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 2 Oct 2023 13:17:37 +0000 Subject: net_sched: sch_fq: add 3 bands and WRR scheduling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Before Google adopted FQ for its production servers, we had to ensure AF4 packets would get a higher share than BE1 ones. As discussed this week in Netconf 2023 in Paris, it is time to upstream this for public use. After this patch FQ can replace pfifo_fast, with the following differences : - FQ uses WRR instead of strict prio, to avoid starvation of low priority packets. - We make sure each band/prio tracks its own usage against sch->limit. This was done to make sure flood of low priority packets would not prevent AF4 packets to be queued. Contributed by Willem. - priomap can be changed, if needed (default value are the ones coming from pfifo_fast). In this patch, we set default band weights so that : - high prio (band=0) packets get 90% of the bandwidth if they compete with low prio (band=2) packets. - high prio packets get 75% of the bandwidth if they compete with medium prio (band=1) packets. Following patch in this series adds the possibility to tune the per-band weights. As we added many fields in 'struct fq_sched_data', we had to make sure to have the first cache line read-mostly, and avoid wasting precious cache lines. More optimizations are possible but will be sent separately. Signed-off-by: Eric Dumazet Acked-by: Dave Taht Reviewed-by: Willem de Bruijn Acked-by: Soheil Hassas Yeganeh Reviewed-by: Toke Høiland-Jørgensen Signed-off-by: Paolo Abeni --- include/uapi/linux/pkt_sched.h | 11 ++- net/sched/sch_fq.c | 204 ++++++++++++++++++++++++++++++++--------- 2 files changed, 171 insertions(+), 44 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 579f641846b8..ec5ab44d41a2 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -941,15 +941,19 @@ enum { TCA_FQ_HORIZON_DROP, /* drop packets beyond horizon, or cap their EDT */ + TCA_FQ_PRIOMAP, /* prio2band */ + __TCA_FQ_MAX }; #define TCA_FQ_MAX (__TCA_FQ_MAX - 1) +#define FQ_BANDS 3 + struct tc_fq_qd_stats { __u64 gc_flows; - __u64 highprio_packets; - __u64 tcp_retrans; + __u64 highprio_packets; /* obsolete */ + __u64 tcp_retrans; /* obsolete */ __u64 throttled; __u64 flows_plimit; __u64 pkts_too_long; @@ -963,6 +967,9 @@ struct tc_fq_qd_stats { __u64 horizon_drops; __u64 horizon_caps; __u64 fastpath_packets; + __u64 band_drops[FQ_BANDS]; + __u32 band_pkt_count[FQ_BANDS]; + __u32 pad; }; /* Heavy-Hitter Filter */ diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 818ac786379d..081105801fa6 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -51,7 +51,8 @@ #include struct fq_skb_cb { - u64 time_to_send; + u64 time_to_send; + u8 band; }; static inline struct fq_skb_cb *fq_skb_cb(struct sk_buff *skb) @@ -84,32 +85,28 @@ struct fq_flow { u32 socket_hash; /* sk_hash */ int qlen; /* number of packets in flow queue */ -/* Second cache line, used in fq_dequeue() */ +/* Second cache line */ int credit; - /* 32bit hole on 64bit arches */ - + int band; struct fq_flow *next; /* next pointer in RR lists */ struct rb_node rate_node; /* anchor in q->delayed tree */ u64 time_next_packet; -} ____cacheline_aligned_in_smp; +}; struct fq_flow_head { struct fq_flow *first; struct fq_flow *last; }; -struct fq_sched_data { +struct fq_perband_flows { struct fq_flow_head new_flows; - struct fq_flow_head old_flows; + int credit; + int quantum; /* based on band nr : 576KB, 192KB, 64KB */ +}; - struct rb_root delayed; /* for rate limited flows */ - u64 time_next_delayed_flow; - unsigned long unthrottle_latency_ns; - - struct fq_flow internal; /* for non classified or high prio packets */ - +struct fq_sched_data { /* Read mostly cache line */ u32 quantum; @@ -125,10 +122,21 @@ struct fq_sched_data { u8 rate_enable; u8 fq_trees_log; u8 horizon_drop; + u8 prio2band[(TC_PRIO_MAX + 1) >> 2]; u32 timer_slack; /* hrtimer slack in ns */ /* Read/Write fields. */ + unsigned int band_nr; /* band being serviced in fq_dequeue() */ + + struct fq_perband_flows band_flows[FQ_BANDS]; + + struct fq_flow internal; /* fastpath queue. */ + struct rb_root delayed; /* for rate limited flows */ + u64 time_next_delayed_flow; + unsigned long unthrottle_latency_ns; + + u32 band_pkt_count[FQ_BANDS]; u32 flows; u32 inactive_flows; /* Flows with no packet to send. */ u32 throttled_flows; @@ -139,7 +147,7 @@ struct fq_sched_data { /* Seldom used fields. */ - u64 stat_internal_packets; /* aka highprio */ + u64 stat_band_drops[FQ_BANDS]; u64 stat_ce_mark; u64 stat_horizon_drops; u64 stat_horizon_caps; @@ -148,6 +156,12 @@ struct fq_sched_data { u64 stat_allocation_errors; }; +/* return the i-th 2-bit value ("crumb") */ +static u8 fq_prio2band(const u8 *prio2band, unsigned int prio) +{ + return (prio2band[prio / 4] >> (2 * (prio & 0x3))) & 0x3; +} + /* * f->tail and f->age share the same location. * We can use the low order bit to differentiate if this location points @@ -172,8 +186,19 @@ static bool fq_flow_is_throttled(const struct fq_flow *f) return f->next == &throttled; } -static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow) +enum new_flow { + NEW_FLOW, + OLD_FLOW +}; + +static void fq_flow_add_tail(struct fq_sched_data *q, struct fq_flow *flow, + enum new_flow list_sel) { + struct fq_perband_flows *pband = &q->band_flows[flow->band]; + struct fq_flow_head *head = (list_sel == NEW_FLOW) ? + &pband->new_flows : + &pband->old_flows; + if (head->first) head->last->next = flow; else @@ -186,7 +211,7 @@ static void fq_flow_unset_throttled(struct fq_sched_data *q, struct fq_flow *f) { rb_erase(&f->rate_node, &q->delayed); q->throttled_flows--; - fq_flow_add_tail(&q->old_flows, f); + fq_flow_add_tail(q, f, OLD_FLOW); } static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f) @@ -326,11 +351,6 @@ static struct fq_flow *fq_classify(struct Qdisc *sch, struct sk_buff *skb, struct rb_root *root; struct fq_flow *f; - /* warning: no starvation prevention... */ - if (unlikely((skb->priority & TC_PRIO_MAX) == TC_PRIO_CONTROL)) { - q->stat_internal_packets++; /* highprio packet */ - return &q->internal; - } /* SYNACK messages are attached to a TCP_NEW_SYN_RECV request socket * or a listener (SYNCOOKIE mode) * 1) request sockets are not full blown, @@ -509,9 +529,13 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct fq_sched_data *q = qdisc_priv(sch); struct fq_flow *f; u64 now; + u8 band; - if (unlikely(sch->q.qlen >= sch->limit)) + band = fq_prio2band(q->prio2band, skb->priority & TC_PRIO_MAX); + if (unlikely(q->band_pkt_count[band] >= sch->limit)) { + q->stat_band_drops[band]++; return qdisc_drop(skb, sch, to_free); + } now = ktime_get_ns(); if (!skb->tstamp) { @@ -538,11 +562,14 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, } if (fq_flow_is_detached(f)) { - fq_flow_add_tail(&q->new_flows, f); + fq_flow_add_tail(q, f, NEW_FLOW); if (time_after(jiffies, f->age + q->flow_refill_delay)) f->credit = max_t(u32, f->credit, q->quantum); } + f->band = band; + q->band_pkt_count[band]++; + fq_skb_cb(skb)->band = band; if (f->qlen == 0) q->inactive_flows--; } @@ -584,13 +611,26 @@ static void fq_check_throttled(struct fq_sched_data *q, u64 now) } } +static struct fq_flow_head *fq_pband_head_select(struct fq_perband_flows *pband) +{ + if (pband->credit <= 0) + return NULL; + + if (pband->new_flows.first) + return &pband->new_flows; + + return pband->old_flows.first ? &pband->old_flows : NULL; +} + static struct sk_buff *fq_dequeue(struct Qdisc *sch) { struct fq_sched_data *q = qdisc_priv(sch); + struct fq_perband_flows *pband; struct fq_flow_head *head; struct sk_buff *skb; struct fq_flow *f; unsigned long rate; + int retry; u32 plen; u64 now; @@ -606,24 +646,31 @@ static struct sk_buff *fq_dequeue(struct Qdisc *sch) now = ktime_get_ns(); fq_check_throttled(q, now); + retry = 0; + pband = &q->band_flows[q->band_nr]; begin: - head = &q->new_flows; - if (!head->first) { - head = &q->old_flows; - if (!head->first) { - if (q->time_next_delayed_flow != ~0ULL) - qdisc_watchdog_schedule_range_ns(&q->watchdog, + head = fq_pband_head_select(pband); + if (!head) { + while (++retry < FQ_BANDS) { + if (++q->band_nr == FQ_BANDS) + q->band_nr = 0; + pband = &q->band_flows[q->band_nr]; + pband->credit = min(pband->credit + pband->quantum, + pband->quantum); + goto begin; + } + if (q->time_next_delayed_flow != ~0ULL) + qdisc_watchdog_schedule_range_ns(&q->watchdog, q->time_next_delayed_flow, q->timer_slack); - return NULL; - } + return NULL; } f = head->first; - + retry = 0; if (f->credit <= 0) { f->credit += q->quantum; head->first = f->next; - fq_flow_add_tail(&q->old_flows, f); + fq_flow_add_tail(q, f, OLD_FLOW); goto begin; } @@ -645,12 +692,13 @@ begin: } if (--f->qlen == 0) q->inactive_flows++; + q->band_pkt_count[fq_skb_cb(skb)->band]--; fq_dequeue_skb(sch, f, skb); } else { head->first = f->next; /* force a pass through old_flows to prevent starvation */ - if ((head == &q->new_flows) && q->old_flows.first) { - fq_flow_add_tail(&q->old_flows, f); + if (head == &pband->new_flows) { + fq_flow_add_tail(q, f, OLD_FLOW); } else { fq_flow_set_detached(f); } @@ -658,6 +706,7 @@ begin: } plen = qdisc_pkt_len(skb); f->credit -= plen; + pband->credit -= plen; if (!q->rate_enable) goto out; @@ -749,8 +798,10 @@ static void fq_reset(struct Qdisc *sch) kmem_cache_free(fq_flow_cachep, f); } } - q->new_flows.first = NULL; - q->old_flows.first = NULL; + for (idx = 0; idx < FQ_BANDS; idx++) { + q->band_flows[idx].new_flows.first = NULL; + q->band_flows[idx].old_flows.first = NULL; + } q->delayed = RB_ROOT; q->flows = 0; q->inactive_flows = 0; @@ -864,8 +915,54 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = { [TCA_FQ_TIMER_SLACK] = { .type = NLA_U32 }, [TCA_FQ_HORIZON] = { .type = NLA_U32 }, [TCA_FQ_HORIZON_DROP] = { .type = NLA_U8 }, + [TCA_FQ_PRIOMAP] = { + .type = NLA_BINARY, + .len = sizeof(struct tc_prio_qopt), + }, }; +/* compress a u8 array with all elems <= 3 to an array of 2-bit fields */ +static void fq_prio2band_compress_crumb(const u8 *in, u8 *out) +{ + const int num_elems = TC_PRIO_MAX + 1; + int i; + + memset(out, 0, num_elems / 4); + for (i = 0; i < num_elems; i++) + out[i / 4] |= in[i] << (2 * (i & 0x3)); +} + +static void fq_prio2band_decompress_crumb(const u8 *in, u8 *out) +{ + const int num_elems = TC_PRIO_MAX + 1; + int i; + + for (i = 0; i < num_elems; i++) + out[i] = fq_prio2band(in, i); +} + +static int fq_load_priomap(struct fq_sched_data *q, + const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + const struct tc_prio_qopt *map = nla_data(attr); + int i; + + if (map->bands != FQ_BANDS) { + NL_SET_ERR_MSG_MOD(extack, "FQ only supports 3 bands"); + return -EINVAL; + } + for (i = 0; i < TC_PRIO_MAX + 1; i++) { + if (map->priomap[i] >= FQ_BANDS) { + NL_SET_ERR_MSG_FMT_MOD(extack, "FQ priomap field %d maps to a too high band %d", + i, map->priomap[i]); + return -EINVAL; + } + } + fq_prio2band_compress_crumb(map->priomap, q->prio2band); + return 0; +} + static int fq_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -940,6 +1037,9 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, q->flow_refill_delay = usecs_to_jiffies(usecs_delay); } + if (!err && tb[TCA_FQ_PRIOMAP]) + err = fq_load_priomap(q, tb[TCA_FQ_PRIOMAP], extack); + if (tb[TCA_FQ_ORPHAN_MASK]) q->orphan_mask = nla_get_u32(tb[TCA_FQ_ORPHAN_MASK]); @@ -991,7 +1091,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct fq_sched_data *q = qdisc_priv(sch); - int err; + int i, err; sch->limit = 10000; q->flow_plimit = 100; @@ -1001,8 +1101,13 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt, q->flow_max_rate = ~0UL; q->time_next_delayed_flow = ~0ULL; q->rate_enable = 1; - q->new_flows.first = NULL; - q->old_flows.first = NULL; + for (i = 0; i < FQ_BANDS; i++) { + q->band_flows[i].new_flows.first = NULL; + q->band_flows[i].old_flows.first = NULL; + } + q->band_flows[0].quantum = 9 << 16; + q->band_flows[1].quantum = 3 << 16; + q->band_flows[2].quantum = 1 << 16; q->delayed = RB_ROOT; q->fq_root = NULL; q->fq_trees_log = ilog2(1024); @@ -1017,6 +1122,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt, /* Default ce_threshold of 4294 seconds */ q->ce_threshold = (u64)NSEC_PER_USEC * ~0U; + fq_prio2band_compress_crumb(sch_default_prio2band, q->prio2band); qdisc_watchdog_init_clockid(&q->watchdog, sch, CLOCK_MONOTONIC); if (opt) @@ -1031,6 +1137,9 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) { struct fq_sched_data *q = qdisc_priv(sch); u64 ce_threshold = q->ce_threshold; + struct tc_prio_qopt prio = { + .bands = FQ_BANDS, + }; u64 horizon = q->horizon; struct nlattr *opts; @@ -1062,6 +1171,10 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) nla_put_u8(skb, TCA_FQ_HORIZON_DROP, q->horizon_drop)) goto nla_put_failure; + fq_prio2band_decompress_crumb(q->prio2band, prio.priomap); + if (nla_put(skb, TCA_FQ_PRIOMAP, sizeof(prio), &prio)) + goto nla_put_failure; + return nla_nest_end(skb, opts); nla_put_failure: @@ -1072,11 +1185,14 @@ static int fq_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct fq_sched_data *q = qdisc_priv(sch); struct tc_fq_qd_stats st; + int i; + + st.pad = 0; sch_tree_lock(sch); st.gc_flows = q->stat_gc_flows; - st.highprio_packets = q->stat_internal_packets; + st.highprio_packets = 0; st.fastpath_packets = q->internal.stat_fastpath_packets; st.tcp_retrans = 0; st.throttled = q->stat_throttled; @@ -1093,6 +1209,10 @@ static int fq_dump_stats(struct Qdisc *sch, struct gnet_dump *d) st.ce_mark = q->stat_ce_mark; st.horizon_drops = q->stat_horizon_drops; st.horizon_caps = q->stat_horizon_caps; + for (i = 0; i < FQ_BANDS; i++) { + st.band_drops[i] = q->stat_band_drops[i]; + st.band_pkt_count[i] = q->band_pkt_count[i]; + } sch_tree_unlock(sch); return gnet_stats_copy_app(d, &st, sizeof(st)); @@ -1120,7 +1240,7 @@ static int __init fq_module_init(void) fq_flow_cachep = kmem_cache_create("fq_flow_cache", sizeof(struct fq_flow), - 0, 0, NULL); + 0, SLAB_HWCACHE_ALIGN, NULL); if (!fq_flow_cachep) return -ENOMEM; -- cgit From 49e7265fd098fdade2bbdd9331e6b914cda7fa83 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 2 Oct 2023 13:17:38 +0000 Subject: net_sched: sch_fq: add TCA_FQ_WEIGHTS attribute MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This attribute can be used to tune the per band weight and report them in "tc qdisc show" output: qdisc fq 802f: parent 1:9 limit 100000p flow_limit 500p buckets 1024 orphan_mask 1023 quantum 8364b initial_quantum 41820b low_rate_threshold 550Kbit refill_delay 40ms timer_slack 10us horizon 10s horizon_drop bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 weights 589824 196608 65536 Sent 236460814 bytes 792991 pkt (dropped 0, overlimits 0 requeues 0) rate 25816bit 10pps backlog 0b 0p requeues 0 flows 4 (inactive 4 throttled 0) gc 0 throttled 19 latency 17.6us fastpath 773882 Signed-off-by: Eric Dumazet Acked-by: Dave Taht Reviewed-by: Willem de Bruijn Reviewed-by: Toke Høiland-Jørgensen Signed-off-by: Paolo Abeni --- include/uapi/linux/pkt_sched.h | 3 +++ net/sched/sch_fq.c | 33 +++++++++++++++++++++++++++++++++ 2 files changed, 36 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index ec5ab44d41a2..f762a10bfb78 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -943,12 +943,15 @@ enum { TCA_FQ_PRIOMAP, /* prio2band */ + TCA_FQ_WEIGHTS, /* Weights for each band */ + __TCA_FQ_MAX }; #define TCA_FQ_MAX (__TCA_FQ_MAX - 1) #define FQ_BANDS 3 +#define FQ_MIN_WEIGHT 16384 struct tc_fq_qd_stats { __u64 gc_flows; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 081105801fa6..8eacdb54e72f 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -919,6 +919,10 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = { .type = NLA_BINARY, .len = sizeof(struct tc_prio_qopt), }, + [TCA_FQ_WEIGHTS] = { + .type = NLA_BINARY, + .len = FQ_BANDS * sizeof(s32), + }, }; /* compress a u8 array with all elems <= 3 to an array of 2-bit fields */ @@ -941,6 +945,25 @@ static void fq_prio2band_decompress_crumb(const u8 *in, u8 *out) out[i] = fq_prio2band(in, i); } +static int fq_load_weights(struct fq_sched_data *q, + const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + s32 *weights = nla_data(attr); + int i; + + for (i = 0; i < FQ_BANDS; i++) { + if (weights[i] < FQ_MIN_WEIGHT) { + NL_SET_ERR_MSG_FMT_MOD(extack, "Weight %d less that minimum allowed %d", + weights[i], FQ_MIN_WEIGHT); + return -EINVAL; + } + } + for (i = 0; i < FQ_BANDS; i++) + q->band_flows[i].quantum = weights[i]; + return 0; +} + static int fq_load_priomap(struct fq_sched_data *q, const struct nlattr *attr, struct netlink_ext_ack *extack) @@ -1040,6 +1063,9 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, if (!err && tb[TCA_FQ_PRIOMAP]) err = fq_load_priomap(q, tb[TCA_FQ_PRIOMAP], extack); + if (!err && tb[TCA_FQ_WEIGHTS]) + err = fq_load_weights(q, tb[TCA_FQ_WEIGHTS], extack); + if (tb[TCA_FQ_ORPHAN_MASK]) q->orphan_mask = nla_get_u32(tb[TCA_FQ_ORPHAN_MASK]); @@ -1142,6 +1168,7 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) }; u64 horizon = q->horizon; struct nlattr *opts; + s32 weights[3]; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) @@ -1175,6 +1202,12 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put(skb, TCA_FQ_PRIOMAP, sizeof(prio), &prio)) goto nla_put_failure; + weights[0] = q->band_flows[0].quantum; + weights[1] = q->band_flows[1].quantum; + weights[2] = q->band_flows[2].quantum; + if (nla_put(skb, TCA_FQ_WEIGHTS, sizeof(weights), &weights)) + goto nla_put_failure; + return nla_nest_end(skb, opts); nla_put_failure: -- cgit From bd4da04c79346cc7e6b2d4e158adb7d2a4bac53b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 30 Sep 2023 15:14:28 -0700 Subject: mei: fix doc typos Fix grammar and punctuation. Signed-off-by: Randy Dunlap Cc: Tomas Winkler Cc: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20230930221428.18463-3-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/mei.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mei.h b/include/uapi/linux/mei.h index 6e57743628c0..171c5cce3641 100644 --- a/include/uapi/linux/mei.h +++ b/include/uapi/linux/mei.h @@ -14,8 +14,8 @@ * FW Client (given by UUID). This opens a communication channel * between a host client and a FW client. From this point every read and write * will communicate with the associated FW client. - * Only in close() (file_operation release()) the communication between - * the clients is disconnected + * Only in close() (file_operation release()) is the communication between + * the clients disconnected. * * The IOCTL argument is a struct with a union that contains * the input parameter and the output parameter for this IOCTL. @@ -51,7 +51,7 @@ struct mei_connect_client_data { * DOC: set and unset event notification for a connected client * * The IOCTL argument is 1 for enabling event notification and 0 for - * disabling the service + * disabling the service. * Return: -EOPNOTSUPP if the devices doesn't support the feature */ #define IOCTL_MEI_NOTIFY_SET _IOW('H', 0x02, __u32) @@ -59,8 +59,8 @@ struct mei_connect_client_data { /** * DOC: retrieve notification * - * The IOCTL output argument is 1 if an event was is pending and 0 otherwise - * the ioctl has to be called in order to acknowledge pending event + * The IOCTL output argument is 1 if an event was pending and 0 otherwise. + * The ioctl has to be called in order to acknowledge pending event. * * Return: -EOPNOTSUPP if the devices doesn't support the feature */ @@ -98,14 +98,14 @@ struct mei_connect_client_data_vtag { * FW Client (given by UUID), and virtual tag (vtag). * The IOCTL opens a communication channel between a host client and * a FW client on a tagged channel. From this point on, every read - * and write will communicate with the associated FW client with + * and write will communicate with the associated FW client * on the tagged channel. * Upone close() the communication is terminated. * * The IOCTL argument is a struct with a union that contains * the input parameter and the output parameter for this IOCTL. * - * The input parameter is UUID of the FW Client, a vtag [0,255] + * The input parameter is UUID of the FW Client, a vtag [0,255]. * The output parameter is the properties of the FW client * (FW protocool version and max message size). * -- cgit From 0da668333fb07805c2836d5d50e26eda915b24a1 Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Mon, 28 Aug 2023 17:08:56 +0200 Subject: mm: make PR_MDWE_REFUSE_EXEC_GAIN an unsigned long Defining a prctl flag as an int is a footgun because on a 64 bit machine and with a variadic implementation of prctl (like in musl and glibc), when used directly as a prctl argument, it can get casted to long with garbage upper bits which would result in unexpected behaviors. This patch changes the constant to an unsigned long to eliminate that possibilities. This does not break UAPI. I think that a stable backport would be "nice to have": to reduce the chances that users build binaries that could end up with garbage bits in their MDWE prctl arguments. We are not aware of anyone having yet encountered this corner case with MDWE prctls but a backport would reduce the likelihood it happens, since this sort of issues has happened with other prctls. But If this is perceived as a backporting burden, I suppose we could also live without a stable backport. Link: https://lkml.kernel.org/r/20230828150858.393570-5-revest@chromium.org Fixes: b507808ebce2 ("mm: implement memory-deny-write-execute as a prctl") Signed-off-by: Florent Revest Suggested-by: Alexey Izbyshev Reviewed-by: David Hildenbrand Reviewed-by: Kees Cook Acked-by: Catalin Marinas Cc: Anshuman Khandual Cc: Ayush Jain Cc: Greg Thelen Cc: Joey Gouly Cc: KP Singh Cc: Mark Brown Cc: Michal Hocko Cc: Peter Xu Cc: Ryan Roberts Cc: Szabolcs Nagy Cc: Topi Miettinen Cc: Signed-off-by: Andrew Morton --- include/uapi/linux/prctl.h | 2 +- tools/include/uapi/linux/prctl.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 3c36aeade991..9a85c69782bd 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -283,7 +283,7 @@ struct prctl_mm_map { /* Memory deny write / execute */ #define PR_SET_MDWE 65 -# define PR_MDWE_REFUSE_EXEC_GAIN 1 +# define PR_MDWE_REFUSE_EXEC_GAIN (1UL << 0) #define PR_GET_MDWE 66 diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 3c36aeade991..9a85c69782bd 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -283,7 +283,7 @@ struct prctl_mm_map { /* Memory deny write / execute */ #define PR_SET_MDWE 65 -# define PR_MDWE_REFUSE_EXEC_GAIN 1 +# define PR_MDWE_REFUSE_EXEC_GAIN (1UL << 0) #define PR_GET_MDWE 66 -- cgit From 24e41bf8a6b424c76c5902fb999e9eca61bdf83d Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Mon, 28 Aug 2023 17:08:57 +0200 Subject: mm: add a NO_INHERIT flag to the PR_SET_MDWE prctl This extends the current PR_SET_MDWE prctl arg with a bit to indicate that the process doesn't want MDWE protection to propagate to children. To implement this no-inherit mode, the tag in current->mm->flags must be absent from MMF_INIT_MASK. This means that the encoding for "MDWE but without inherit" is different in the prctl than in the mm flags. This leads to a bit of bit-mangling in the prctl implementation. Link: https://lkml.kernel.org/r/20230828150858.393570-6-revest@chromium.org Signed-off-by: Florent Revest Reviewed-by: Kees Cook Reviewed-by: Catalin Marinas Cc: Alexey Izbyshev Cc: Anshuman Khandual Cc: Ayush Jain Cc: David Hildenbrand Cc: Greg Thelen Cc: Joey Gouly Cc: KP Singh Cc: Mark Brown Cc: Michal Hocko Cc: Peter Xu Cc: Ryan Roberts Cc: Szabolcs Nagy Cc: Topi Miettinen Signed-off-by: Andrew Morton --- include/linux/sched/coredump.h | 10 ++++++++++ include/uapi/linux/prctl.h | 1 + kernel/fork.c | 2 +- kernel/sys.c | 32 ++++++++++++++++++++++++++------ tools/include/uapi/linux/prctl.h | 1 + 5 files changed, 39 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 0ee96ea7a0e9..1b37fa8fc723 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -91,4 +91,14 @@ static inline int get_dumpable(struct mm_struct *mm) MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK) #define MMF_VM_MERGE_ANY 29 +#define MMF_HAS_MDWE_NO_INHERIT 30 + +static inline unsigned long mmf_init_flags(unsigned long flags) +{ + if (flags & (1UL << MMF_HAS_MDWE_NO_INHERIT)) + flags &= ~((1UL << MMF_HAS_MDWE) | + (1UL << MMF_HAS_MDWE_NO_INHERIT)); + return flags & MMF_INIT_MASK; +} + #endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 9a85c69782bd..370ed14b1ae0 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -284,6 +284,7 @@ struct prctl_mm_map { /* Memory deny write / execute */ #define PR_SET_MDWE 65 # define PR_MDWE_REFUSE_EXEC_GAIN (1UL << 0) +# define PR_MDWE_NO_INHERIT (1UL << 1) #define PR_GET_MDWE 66 diff --git a/kernel/fork.c b/kernel/fork.c index 1779183a7cb3..e45a4457ba83 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1288,7 +1288,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, hugetlb_count_init(mm); if (current->mm) { - mm->flags = current->mm->flags & MMF_INIT_MASK; + mm->flags = mmf_init_flags(current->mm->flags); mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; } else { mm->flags = default_dump_filter; diff --git a/kernel/sys.c b/kernel/sys.c index 2410e3999ebe..4a8073c1b255 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2368,19 +2368,41 @@ static int prctl_set_vma(unsigned long opt, unsigned long start, } #endif /* CONFIG_ANON_VMA_NAME */ +static inline unsigned long get_current_mdwe(void) +{ + unsigned long ret = 0; + + if (test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) + ret |= PR_MDWE_REFUSE_EXEC_GAIN; + if (test_bit(MMF_HAS_MDWE_NO_INHERIT, ¤t->mm->flags)) + ret |= PR_MDWE_NO_INHERIT; + + return ret; +} + static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3, unsigned long arg4, unsigned long arg5) { + unsigned long current_bits; + if (arg3 || arg4 || arg5) return -EINVAL; - if (bits & ~(PR_MDWE_REFUSE_EXEC_GAIN)) + if (bits & ~(PR_MDWE_REFUSE_EXEC_GAIN | PR_MDWE_NO_INHERIT)) + return -EINVAL; + + /* NO_INHERIT only makes sense with REFUSE_EXEC_GAIN */ + if (bits & PR_MDWE_NO_INHERIT && !(bits & PR_MDWE_REFUSE_EXEC_GAIN)) return -EINVAL; + current_bits = get_current_mdwe(); + if (current_bits && current_bits != bits) + return -EPERM; /* Cannot unset the flags */ + + if (bits & PR_MDWE_NO_INHERIT) + set_bit(MMF_HAS_MDWE_NO_INHERIT, ¤t->mm->flags); if (bits & PR_MDWE_REFUSE_EXEC_GAIN) set_bit(MMF_HAS_MDWE, ¤t->mm->flags); - else if (test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) - return -EPERM; /* Cannot unset the flag */ return 0; } @@ -2390,9 +2412,7 @@ static inline int prctl_get_mdwe(unsigned long arg2, unsigned long arg3, { if (arg2 || arg3 || arg4 || arg5) return -EINVAL; - - return test_bit(MMF_HAS_MDWE, ¤t->mm->flags) ? - PR_MDWE_REFUSE_EXEC_GAIN : 0; + return get_current_mdwe(); } static int prctl_get_auxv(void __user *addr, unsigned long len) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 9a85c69782bd..370ed14b1ae0 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -284,6 +284,7 @@ struct prctl_mm_map { /* Memory deny write / execute */ #define PR_SET_MDWE 65 # define PR_MDWE_REFUSE_EXEC_GAIN (1UL << 0) +# define PR_MDWE_NO_INHERIT (1UL << 1) #define PR_GET_MDWE 66 -- cgit From d6247ecb6c1e17d7a33317090627f5bfe563cbb2 Mon Sep 17 00:00:00 2001 From: David Vernet Date: Wed, 4 Oct 2023 11:23:38 -0500 Subject: bpf: Add ability to pin bpf timer to calling CPU BPF supports creating high resolution timers using bpf_timer_* helper functions. Currently, only the BPF_F_TIMER_ABS flag is supported, which specifies that the timeout should be interpreted as absolute time. It would also be useful to be able to pin that timer to a core. For example, if you wanted to make a subset of cores run without timer interrupts, and only have the timer be invoked on a single core. This patch adds support for this with a new BPF_F_TIMER_CPU_PIN flag. When specified, the HRTIMER_MODE_PINNED flag is passed to hrtimer_start(). A subsequent patch will update selftests to validate. Signed-off-by: David Vernet Signed-off-by: Daniel Borkmann Acked-by: Song Liu Acked-by: Hou Tao Link: https://lore.kernel.org/bpf/20231004162339.200702-2-void@manifault.com --- include/uapi/linux/bpf.h | 4 ++++ kernel/bpf/helpers.c | 5 ++++- tools/include/uapi/linux/bpf.h | 4 ++++ 3 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 70bfa997e896..a7d4a1a69f21 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5096,6 +5096,8 @@ union bpf_attr { * **BPF_F_TIMER_ABS** * Start the timer in absolute expire value instead of the * default relative one. + * **BPF_F_TIMER_CPU_PIN** + * Timer will be pinned to the CPU of the caller. * * Return * 0 on success. @@ -7309,9 +7311,11 @@ struct bpf_core_relo { * Flags to control bpf_timer_start() behaviour. * - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is * relative to current time. + * - BPF_F_TIMER_CPU_PIN: Timer will be pinned to the CPU of the caller. */ enum { BPF_F_TIMER_ABS = (1ULL << 0), + BPF_F_TIMER_CPU_PIN = (1ULL << 1), }; /* BPF numbers iterator state */ diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index dd1c69ee3375..d2840dd5b00d 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1272,7 +1272,7 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla if (in_nmi()) return -EOPNOTSUPP; - if (flags > BPF_F_TIMER_ABS) + if (flags & ~(BPF_F_TIMER_ABS | BPF_F_TIMER_CPU_PIN)) return -EINVAL; __bpf_spin_lock_irqsave(&timer->lock); t = timer->timer; @@ -1286,6 +1286,9 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla else mode = HRTIMER_MODE_REL_SOFT; + if (flags & BPF_F_TIMER_CPU_PIN) + mode |= HRTIMER_MODE_PINNED; + hrtimer_start(&t->timer, ns_to_ktime(nsecs), mode); out: __bpf_spin_unlock_irqrestore(&timer->lock); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 70bfa997e896..a7d4a1a69f21 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5096,6 +5096,8 @@ union bpf_attr { * **BPF_F_TIMER_ABS** * Start the timer in absolute expire value instead of the * default relative one. + * **BPF_F_TIMER_CPU_PIN** + * Timer will be pinned to the CPU of the caller. * * Return * 0 on success. @@ -7309,9 +7311,11 @@ struct bpf_core_relo { * Flags to control bpf_timer_start() behaviour. * - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is * relative to current time. + * - BPF_F_TIMER_CPU_PIN: Timer will be pinned to the CPU of the caller. */ enum { BPF_F_TIMER_ABS = (1ULL << 0), + BPF_F_TIMER_CPU_PIN = (1ULL << 1), }; /* BPF numbers iterator state */ -- cgit From dab4e1f06cabb6834de14264394ccab197007302 Mon Sep 17 00:00:00 2001 From: Martynas Pumputis Date: Sat, 7 Oct 2023 10:14:14 +0200 Subject: bpf: Derive source IP addr via bpf_*_fib_lookup() Extend the bpf_fib_lookup() helper by making it to return the source IPv4/IPv6 address if the BPF_FIB_LOOKUP_SRC flag is set. For example, the following snippet can be used to derive the desired source IP address: struct bpf_fib_lookup p = { .ipv4_dst = ip4->daddr }; ret = bpf_skb_fib_lookup(skb, p, sizeof(p), BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_SKIP_NEIGH); if (ret != BPF_FIB_LKUP_RET_SUCCESS) return TC_ACT_SHOT; /* the p.ipv4_src now contains the source address */ The inability to derive the proper source address may cause malfunctions in BPF-based dataplanes for hosts containing netdevs with more than one routable IP address or for multi-homed hosts. For example, Cilium implements packet masquerading in BPF. If an egressing netdev to which the Cilium's BPF prog is attached has multiple IP addresses, then only one [hardcoded] IP address can be used for masquerading. This breaks connectivity if any other IP address should have been selected instead, for example, when a public and private addresses are attached to the same egress interface. The change was tested with Cilium [1]. Nikolay Aleksandrov helped to figure out the IPv6 addr selection. [1]: https://github.com/cilium/cilium/pull/28283 Signed-off-by: Martynas Pumputis Link: https://lore.kernel.org/r/20231007081415.33502-2-m@lambda.lt Signed-off-by: Martin KaFai Lau --- include/net/ipv6_stubs.h | 5 +++++ include/uapi/linux/bpf.h | 10 ++++++++++ net/core/filter.c | 18 +++++++++++++++++- net/ipv6/af_inet6.c | 1 + tools/include/uapi/linux/bpf.h | 10 ++++++++++ 5 files changed, 43 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index c48186bf4737..21da31e1dff5 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -85,6 +85,11 @@ struct ipv6_bpf_stub { sockptr_t optval, unsigned int optlen); int (*ipv6_getsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); + int (*ipv6_dev_get_saddr)(struct net *net, + const struct net_device *dst_dev, + const struct in6_addr *daddr, + unsigned int prefs, + struct in6_addr *saddr); }; extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a7d4a1a69f21..e0aa457f94a9 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3264,6 +3264,11 @@ union bpf_attr { * and *params*->smac will not be set as output. A common * use case is to call **bpf_redirect_neigh**\ () after * doing **bpf_fib_lookup**\ (). + * **BPF_FIB_LOOKUP_SRC** + * Derive and set source IP addr in *params*->ipv{4,6}_src + * for the nexthop. If the src addr cannot be derived, + * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this + * case, *params*->dmac and *params*->smac are not set either. * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -6964,6 +6969,7 @@ enum { BPF_FIB_LOOKUP_OUTPUT = (1U << 1), BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), BPF_FIB_LOOKUP_TBID = (1U << 3), + BPF_FIB_LOOKUP_SRC = (1U << 4), }; enum { @@ -6976,6 +6982,7 @@ enum { BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */ BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */ BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */ + BPF_FIB_LKUP_RET_NO_SRC_ADDR, /* failed to derive IP src addr */ }; struct bpf_fib_lookup { @@ -7010,6 +7017,9 @@ struct bpf_fib_lookup { __u32 rt_metric; }; + /* input: source address to consider for lookup + * output: source address result from lookup + */ union { __be32 ipv4_src; __u32 ipv6_src[4]; /* in6_addr; network order */ diff --git a/net/core/filter.c b/net/core/filter.c index a094694899c9..3880bf0b740d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5850,6 +5850,9 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, params->rt_metric = res.fi->fib_priority; params->ifindex = dev->ifindex; + if (flags & BPF_FIB_LOOKUP_SRC) + params->ipv4_src = fib_result_prefsrc(net, &res); + /* xdp and cls_bpf programs are run in RCU-bh so * rcu_read_lock_bh is not needed here */ @@ -5992,6 +5995,18 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, params->rt_metric = res.f6i->fib6_metric; params->ifindex = dev->ifindex; + if (flags & BPF_FIB_LOOKUP_SRC) { + if (res.f6i->fib6_prefsrc.plen) { + *src = res.f6i->fib6_prefsrc.addr; + } else { + err = ipv6_bpf_stub->ipv6_dev_get_saddr(net, dev, + &fl6.daddr, 0, + src); + if (err) + return BPF_FIB_LKUP_RET_NO_SRC_ADDR; + } + } + if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH) goto set_fwd_params; @@ -6010,7 +6025,8 @@ set_fwd_params: #endif #define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \ - BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID) + BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID | \ + BPF_FIB_LOOKUP_SRC) BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx, struct bpf_fib_lookup *, params, int, plen, u32, flags) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index c6ad0d6e99b5..6337fb4504fd 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1061,6 +1061,7 @@ static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = { .udp6_lib_lookup = __udp6_lib_lookup, .ipv6_setsockopt = do_ipv6_setsockopt, .ipv6_getsockopt = do_ipv6_getsockopt, + .ipv6_dev_get_saddr = ipv6_dev_get_saddr, }; static int __init inet6_init(void) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a7d4a1a69f21..e0aa457f94a9 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3264,6 +3264,11 @@ union bpf_attr { * and *params*->smac will not be set as output. A common * use case is to call **bpf_redirect_neigh**\ () after * doing **bpf_fib_lookup**\ (). + * **BPF_FIB_LOOKUP_SRC** + * Derive and set source IP addr in *params*->ipv{4,6}_src + * for the nexthop. If the src addr cannot be derived, + * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this + * case, *params*->dmac and *params*->smac are not set either. * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -6964,6 +6969,7 @@ enum { BPF_FIB_LOOKUP_OUTPUT = (1U << 1), BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), BPF_FIB_LOOKUP_TBID = (1U << 3), + BPF_FIB_LOOKUP_SRC = (1U << 4), }; enum { @@ -6976,6 +6982,7 @@ enum { BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */ BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */ BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */ + BPF_FIB_LKUP_RET_NO_SRC_ADDR, /* failed to derive IP src addr */ }; struct bpf_fib_lookup { @@ -7010,6 +7017,9 @@ struct bpf_fib_lookup { __u32 rt_metric; }; + /* input: source address to consider for lookup + * output: source address result from lookup + */ union { __be32 ipv4_src; __u32 ipv6_src[4]; /* in6_addr; network order */ -- cgit From c7c5be58620a3b1e5fbaf4daea59f2eb6f8fe034 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Sat, 7 Oct 2023 17:18:04 -0700 Subject: serial: add PORT_GENERIC definition Current pattern in the linux kernel is that every new serial driver adds one or more new PORT_ definitions because uart_ops::config_port() callback documentation prescribes setting port->type according to the type of port found, or to PORT_UNKNOWN if no port was detected. When the specific type of the port is not important to the userspace there's no need for a unique PORT_ value, but so far there's no suitable identifier for that case. Provide generic port type identifier other than PORT_UNKNOWN for ports which type is not important to userspace. Suggested-by: Arnd Bergmann Suggested-by: Greg Kroah-Hartman Signed-off-by: Max Filippov Suggested-by: Jiri Slaby Reviewed-by: Jiri Slaby Link: https://lore.kernel.org/r/20231008001804.889727-1-jcmvbkbc@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/serial_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index 46e06c483899..9c007a106330 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -231,4 +231,7 @@ /* Sunplus UART */ #define PORT_SUNPLUS 123 +/* Generic type identifier for ports which type is not important to userspace. */ +#define PORT_GENERIC (-1) + #endif /* _UAPILINUX_SERIAL_CORE_H */ -- cgit From 4ff542163397073f86eda484318d61980ff1031d Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Thu, 28 Sep 2023 00:15:26 -0700 Subject: iommufd: Support allocating nested parent domain Extend IOMMU_HWPT_ALLOC to allocate domains to be used as parent (stage-2) in nested translation. Add IOMMU_HWPT_ALLOC_NEST_PARENT to the uAPI. Link: https://lore.kernel.org/r/20230928071528.26258-5-yi.l.liu@intel.com Signed-off-by: Yi Liu Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommufd/hw_pagetable.c | 5 ++++- include/uapi/linux/iommufd.h | 12 +++++++++++- 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index 5be7a31cbd9c..8b3d2875d642 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -83,6 +83,9 @@ iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, lockdep_assert_held(&ioas->mutex); + if (flags && !ops->domain_alloc_user) + return ERR_PTR(-EOPNOTSUPP); + hwpt = iommufd_object_alloc(ictx, hwpt, IOMMUFD_OBJ_HW_PAGETABLE); if (IS_ERR(hwpt)) return hwpt; @@ -154,7 +157,7 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd) struct iommufd_ioas *ioas; int rc; - if (cmd->flags || cmd->__reserved) + if ((cmd->flags & (~IOMMU_HWPT_ALLOC_NEST_PARENT)) || cmd->__reserved) return -EOPNOTSUPP; idev = iommufd_get_device(ucmd, cmd->dev_id); diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index b4ba0c0cbab6..4a7c5c8fdbb4 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -347,10 +347,20 @@ struct iommu_vfio_ioas { }; #define IOMMU_VFIO_IOAS _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VFIO_IOAS) +/** + * enum iommufd_hwpt_alloc_flags - Flags for HWPT allocation + * @IOMMU_HWPT_ALLOC_NEST_PARENT: If set, allocate a domain which can serve + * as the parent domain in the nesting + * configuration. + */ +enum iommufd_hwpt_alloc_flags { + IOMMU_HWPT_ALLOC_NEST_PARENT = 1 << 0, +}; + /** * struct iommu_hwpt_alloc - ioctl(IOMMU_HWPT_ALLOC) * @size: sizeof(struct iommu_hwpt_alloc) - * @flags: Must be 0 + * @flags: Combination of enum iommufd_hwpt_alloc_flags * @dev_id: The device to allocate this HWPT for * @pt_id: The IOAS to connect this HWPT to * @out_hwpt_id: The ID of the new HWPT -- cgit From 1a11074be2e94736d12e49a9a562b0a54e8a423d Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Sep 2023 18:57:46 +0300 Subject: PCI: Add PCI_L1SS_CTL2 fields MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add L1 PM Substates Control 2 Register fields (PCI_L1SS_CTL2_*). Link: https://lore.kernel.org/r/20230915155752.84640-2-ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen Signed-off-by: Bjorn Helgaas --- include/uapi/linux/pci_regs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index e5f558d96493..3a7ea9581568 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -1088,6 +1088,8 @@ #define PCI_L1SS_CTL1_LTR_L12_TH_VALUE 0x03ff0000 /* LTR_L1.2_THRESHOLD_Value */ #define PCI_L1SS_CTL1_LTR_L12_TH_SCALE 0xe0000000 /* LTR_L1.2_THRESHOLD_Scale */ #define PCI_L1SS_CTL2 0x0c /* Control 2 Register */ +#define PCI_L1SS_CTL2_T_PWR_ON_SCALE 0x00000003 /* T_POWER_ON Scale */ +#define PCI_L1SS_CTL2_T_PWR_ON_VALUE 0x000000f8 /* T_POWER_ON Value */ /* Designated Vendor-Specific (DVSEC, PCI_EXT_CAP_ID_DVSEC) */ #define PCI_DVSEC_HEADER1 0x4 /* Designated Vendor-Specific Header1 */ -- cgit From 859051dd165ec6cc915f0f2114699021144fd249 Mon Sep 17 00:00:00 2001 From: Daan De Meyer Date: Wed, 11 Oct 2023 20:51:06 +0200 Subject: bpf: Implement cgroup sockaddr hooks for unix sockets These hooks allows intercepting connect(), getsockname(), getpeername(), sendmsg() and recvmsg() for unix sockets. The unix socket hooks get write access to the address length because the address length is not fixed when dealing with unix sockets and needs to be modified when a unix socket address is modified by the hook. Because abstract socket unix addresses start with a NUL byte, we cannot recalculate the socket address in kernelspace after running the hook by calculating the length of the unix socket path using strlen(). These hooks can be used when users want to multiplex syscall to a single unix socket to multiple different processes behind the scenes by redirecting the connect() and other syscalls to process specific sockets. We do not implement support for intercepting bind() because when using bind() with unix sockets with a pathname address, this creates an inode in the filesystem which must be cleaned up. If we rewrite the address, the user might try to clean up the wrong file, leaking the socket in the filesystem where it is never cleaned up. Until we figure out a solution for this (and a use case for intercepting bind()), we opt to not allow rewriting the sockaddr in bind() calls. We also implement recvmsg() support for connected streams so that after a connect() that is modified by a sockaddr hook, any corresponding recmvsg() on the connected socket can also be modified to make the connected program think it is connected to the "intended" remote. Reviewed-by: Kuniyuki Iwashima Signed-off-by: Daan De Meyer Link: https://lore.kernel.org/r/20231011185113.140426-5-daan.j.demeyer@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf-cgroup-defs.h | 5 +++++ include/linux/bpf-cgroup.h | 17 +++++++++++++++++ include/uapi/linux/bpf.h | 13 +++++++++---- kernel/bpf/cgroup.c | 11 +++++++++-- kernel/bpf/syscall.c | 15 +++++++++++++++ kernel/bpf/verifier.c | 5 ++++- net/core/filter.c | 14 ++++++++++++-- net/unix/af_unix.c | 35 ++++++++++++++++++++++++++++++++++- tools/include/uapi/linux/bpf.h | 13 +++++++++---- 9 files changed, 114 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf-cgroup-defs.h b/include/linux/bpf-cgroup-defs.h index 7b121bd780eb..0985221d5478 100644 --- a/include/linux/bpf-cgroup-defs.h +++ b/include/linux/bpf-cgroup-defs.h @@ -28,19 +28,24 @@ enum cgroup_bpf_attach_type { CGROUP_INET6_BIND, CGROUP_INET4_CONNECT, CGROUP_INET6_CONNECT, + CGROUP_UNIX_CONNECT, CGROUP_INET4_POST_BIND, CGROUP_INET6_POST_BIND, CGROUP_UDP4_SENDMSG, CGROUP_UDP6_SENDMSG, + CGROUP_UNIX_SENDMSG, CGROUP_SYSCTL, CGROUP_UDP4_RECVMSG, CGROUP_UDP6_RECVMSG, + CGROUP_UNIX_RECVMSG, CGROUP_GETSOCKOPT, CGROUP_SETSOCKOPT, CGROUP_INET4_GETPEERNAME, CGROUP_INET6_GETPEERNAME, + CGROUP_UNIX_GETPEERNAME, CGROUP_INET4_GETSOCKNAME, CGROUP_INET6_GETSOCKNAME, + CGROUP_UNIX_GETSOCKNAME, CGROUP_INET_SOCK_RELEASE, CGROUP_LSM_START, CGROUP_LSM_END = CGROUP_LSM_START + CGROUP_LSM_NUM - 1, diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 31561e789715..98b8cea904fe 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -48,19 +48,24 @@ to_cgroup_bpf_attach_type(enum bpf_attach_type attach_type) CGROUP_ATYPE(CGROUP_INET6_BIND); CGROUP_ATYPE(CGROUP_INET4_CONNECT); CGROUP_ATYPE(CGROUP_INET6_CONNECT); + CGROUP_ATYPE(CGROUP_UNIX_CONNECT); CGROUP_ATYPE(CGROUP_INET4_POST_BIND); CGROUP_ATYPE(CGROUP_INET6_POST_BIND); CGROUP_ATYPE(CGROUP_UDP4_SENDMSG); CGROUP_ATYPE(CGROUP_UDP6_SENDMSG); + CGROUP_ATYPE(CGROUP_UNIX_SENDMSG); CGROUP_ATYPE(CGROUP_SYSCTL); CGROUP_ATYPE(CGROUP_UDP4_RECVMSG); CGROUP_ATYPE(CGROUP_UDP6_RECVMSG); + CGROUP_ATYPE(CGROUP_UNIX_RECVMSG); CGROUP_ATYPE(CGROUP_GETSOCKOPT); CGROUP_ATYPE(CGROUP_SETSOCKOPT); CGROUP_ATYPE(CGROUP_INET4_GETPEERNAME); CGROUP_ATYPE(CGROUP_INET6_GETPEERNAME); + CGROUP_ATYPE(CGROUP_UNIX_GETPEERNAME); CGROUP_ATYPE(CGROUP_INET4_GETSOCKNAME); CGROUP_ATYPE(CGROUP_INET6_GETSOCKNAME); + CGROUP_ATYPE(CGROUP_UNIX_GETSOCKNAME); CGROUP_ATYPE(CGROUP_INET_SOCK_RELEASE); default: return CGROUP_BPF_ATTACH_TYPE_INVALID; @@ -289,18 +294,27 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT, NULL) +#define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_CONNECT, NULL) + #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_SENDMSG, t_ctx) #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_SENDMSG, t_ctx) +#define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_SENDMSG, t_ctx) + #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_RECVMSG, NULL) #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_RECVMSG, NULL) +#define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_RECVMSG, NULL) + /* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a * fullsock and its parent fullsock cannot be traced by * sk_to_full_sk(). @@ -492,10 +506,13 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; }) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e0aa457f94a9..7ba61b75bc0e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1047,6 +1047,11 @@ enum bpf_attach_type { BPF_TCX_INGRESS, BPF_TCX_EGRESS, BPF_TRACE_UPROBE_MULTI, + BPF_CGROUP_UNIX_CONNECT, + BPF_CGROUP_UNIX_SENDMSG, + BPF_CGROUP_UNIX_RECVMSG, + BPF_CGROUP_UNIX_GETPEERNAME, + BPF_CGROUP_UNIX_GETSOCKNAME, __MAX_BPF_ATTACH_TYPE }; @@ -2704,8 +2709,8 @@ union bpf_attr { * *bpf_socket* should be one of the following: * * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. - * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** - * and **BPF_CGROUP_INET6_CONNECT**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**, + * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**. * * This helper actually implements a subset of **setsockopt()**. * It supports the following *level*\ s: @@ -2943,8 +2948,8 @@ union bpf_attr { * *bpf_socket* should be one of the following: * * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. - * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** - * and **BPF_CGROUP_INET6_CONNECT**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**, + * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**. * * This helper actually implements a subset of **getsockopt()**. * It supports the same set of *optname*\ s that is supported by diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index ac37bd53aee0..74ad2215e1ba 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1458,7 +1458,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); * @flags: Pointer to u32 which contains higher bits of BPF program * return value (OR'ed together). * - * socket is expected to be of type INET or INET6. + * socket is expected to be of type INET, INET6 or UNIX. * * This function will return %-EPERM if an attached program is found and * returned value != 1 during execution. In all other cases, 0 is returned. @@ -1482,7 +1482,8 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, /* Check socket family since not all sockets represent network * endpoint (e.g. AF_UNIX). */ - if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) + if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6 && + sk->sk_family != AF_UNIX) return 0; if (!ctx.uaddr) { @@ -2533,10 +2534,13 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: return NULL; default: return &bpf_get_retval_proto; @@ -2548,10 +2552,13 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: return NULL; default: return &bpf_set_retval_proto; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 6b5280f14a53..8677837f3deb 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2446,14 +2446,19 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: return 0; default: return -EINVAL; @@ -3678,14 +3683,19 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: return BPF_PROG_TYPE_CGROUP_SOCK_ADDR; case BPF_CGROUP_SOCK_OPS: return BPF_PROG_TYPE_SOCK_OPS; @@ -3942,14 +3952,19 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_INET6_POST_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_DEVICE: case BPF_CGROUP_SYSCTL: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index eed7350e15f4..e777f50401b6 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -14797,10 +14797,13 @@ static int check_return_code(struct bpf_verifier_env *env, int regno) case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG || + env->prog->expected_attach_type == BPF_CGROUP_UNIX_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME || env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME || + env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETPEERNAME || env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME || - env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME) + env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME || + env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETSOCKNAME) range = tnum_range(1, 1); if (env->prog->expected_attach_type == BPF_CGROUP_INET4_BIND || env->prog->expected_attach_type == BPF_CGROUP_INET6_BIND) diff --git a/net/core/filter.c b/net/core/filter.c index ff0bd9f20b95..cc2e4babc85f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7875,14 +7875,19 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: return &bpf_sock_addr_setsockopt_proto; default: return NULL; @@ -7893,14 +7898,19 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: return &bpf_sock_addr_getsockopt_proto; default: return NULL; @@ -8948,8 +8958,8 @@ static bool sock_addr_is_valid_access(int off, int size, if (off % size != 0) return false; - /* Disallow access to IPv6 fields from IPv4 contex and vise - * versa. + /* Disallow access to fields not belonging to the attach type's address + * family. */ switch (off) { case bpf_ctx_range(struct bpf_sock_addr, user_ip4): diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 3e8a04a13668..e10d07c76044 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -116,6 +116,7 @@ #include #include #include +#include #include "scm.h" @@ -1381,6 +1382,10 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, if (err) goto out; + err = BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, addr, &alen); + if (err) + goto out; + if ((test_bit(SOCK_PASSCRED, &sock->flags) || test_bit(SOCK_PASSPIDFD, &sock->flags)) && !unix_sk(sk)->addr) { @@ -1490,6 +1495,10 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, if (err) goto out; + err = BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, &addr_len); + if (err) + goto out; + if ((test_bit(SOCK_PASSCRED, &sock->flags) || test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) { err = unix_autobind(sk); @@ -1770,6 +1779,13 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) } else { err = addr->len; memcpy(sunaddr, addr->name, addr->len); + + if (peer) + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, &err, + CGROUP_UNIX_GETPEERNAME); + else + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, &err, + CGROUP_UNIX_GETSOCKNAME); } sock_put(sk); out: @@ -1922,6 +1938,13 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, err = unix_validate_addr(sunaddr, msg->msg_namelen); if (err) goto out; + + err = BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, + msg->msg_name, + &msg->msg_namelen, + NULL); + if (err) + goto out; } else { sunaddr = NULL; err = -ENOTCONN; @@ -2390,9 +2413,14 @@ int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); - if (msg->msg_name) + if (msg->msg_name) { unix_copy_addr(msg, skb->sk); + BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, + msg->msg_name, + &msg->msg_namelen); + } + if (size > skb->len - skip) size = skb->len - skip; else if (size < skb->len - skip) @@ -2744,6 +2772,11 @@ unlock: DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, state->msg->msg_name); unix_copy_addr(state->msg, skb->sk); + + BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, + state->msg->msg_name, + &state->msg->msg_namelen); + sunaddr = NULL; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e0aa457f94a9..7ba61b75bc0e 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1047,6 +1047,11 @@ enum bpf_attach_type { BPF_TCX_INGRESS, BPF_TCX_EGRESS, BPF_TRACE_UPROBE_MULTI, + BPF_CGROUP_UNIX_CONNECT, + BPF_CGROUP_UNIX_SENDMSG, + BPF_CGROUP_UNIX_RECVMSG, + BPF_CGROUP_UNIX_GETPEERNAME, + BPF_CGROUP_UNIX_GETSOCKNAME, __MAX_BPF_ATTACH_TYPE }; @@ -2704,8 +2709,8 @@ union bpf_attr { * *bpf_socket* should be one of the following: * * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. - * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** - * and **BPF_CGROUP_INET6_CONNECT**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**, + * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**. * * This helper actually implements a subset of **setsockopt()**. * It supports the following *level*\ s: @@ -2943,8 +2948,8 @@ union bpf_attr { * *bpf_socket* should be one of the following: * * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. - * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** - * and **BPF_CGROUP_INET6_CONNECT**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**, + * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**. * * This helper actually implements a subset of **getsockopt()**. * It supports the same set of *optname*\ s that is supported by -- cgit From e2bca4870fdaf855651ee80b083d892599c5d982 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 9 Oct 2023 08:31:52 -0700 Subject: af_packet: Fix fortified memcpy() without flex array. Sergei Trofimovich reported a regression [0] caused by commit a0ade8404c3b ("af_packet: Fix warning of fortified memcpy() in packet_getname()."). It introduced a flex array sll_addr_flex in struct sockaddr_ll as a union-ed member with sll_addr to work around the fortified memcpy() check. However, a userspace program uses a struct that has struct sockaddr_ll in the middle, where a flex array is illegal to exist. include/linux/if_packet.h:24:17: error: flexible array member 'sockaddr_ll::::::sll_addr_flex' not at end of 'struct packet_info_t' 24 | __DECLARE_FLEX_ARRAY(unsigned char, sll_addr_flex); | ^~~~~~~~~~~~~~~~~~~~ To fix the regression, let's go back to the first attempt [1] telling memcpy() the actual size of the array. Reported-by: Sergei Trofimovich Closes: https://github.com/NixOS/nixpkgs/pull/252587#issuecomment-1741733002 [0] Link: https://lore.kernel.org/netdev/20230720004410.87588-3-kuniyu@amazon.com/ [1] Fixes: a0ade8404c3b ("af_packet: Fix warning of fortified memcpy() in packet_getname().") Signed-off-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20231009153151.75688-1-kuniyu@amazon.com Signed-off-by: Paolo Abeni --- include/uapi/linux/if_packet.h | 6 +----- net/packet/af_packet.c | 7 ++++++- 2 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index 4d0ad22f83b5..9efc42382fdb 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -18,11 +18,7 @@ struct sockaddr_ll { unsigned short sll_hatype; unsigned char sll_pkttype; unsigned char sll_halen; - union { - unsigned char sll_addr[8]; - /* Actual length is in sll_halen. */ - __DECLARE_FLEX_ARRAY(unsigned char, sll_addr_flex); - }; + unsigned char sll_addr[8]; }; /* Packet types */ diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 8f97648d652f..a84e00b5904b 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3607,7 +3607,12 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr, if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; - memcpy(sll->sll_addr_flex, dev->dev_addr, dev->addr_len); + + /* Let __fortify_memcpy_chk() know the actual buffer size. */ + memcpy(((struct sockaddr_storage *)sll)->__data + + offsetof(struct sockaddr_ll, sll_addr) - + offsetofend(struct sockaddr_ll, sll_family), + dev->dev_addr, dev->addr_len); } else { sll->sll_hatype = 0; /* Bad: we have no ARPHRD_UNSPEC */ sll->sll_halen = 0; -- cgit From ee1293308e01d359688243d665138f35a6f1f9b8 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Thu, 14 Sep 2023 09:06:56 -0700 Subject: btrfs: add raid stripe tree definitions Add definitions for the raid stripe tree. This tree will hold information about the on-disk layout of the stripes in a RAID set. Each stripe extent has a 1:1 relationship with an on-disk extent item and is doing the logical to per-drive physical address translation for the extent item in question. Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/accessors.h | 8 ++++++++ fs/btrfs/locking.c | 1 + include/uapi/linux/btrfs_tree.h | 29 +++++++++++++++++++++++++++++ 3 files changed, 38 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h index f958eccff477..ce18e261c861 100644 --- a/fs/btrfs/accessors.h +++ b/fs/btrfs/accessors.h @@ -306,6 +306,14 @@ BTRFS_SETGET_FUNCS(timespec_nsec, struct btrfs_timespec, nsec, 32); BTRFS_SETGET_STACK_FUNCS(stack_timespec_sec, struct btrfs_timespec, sec, 64); BTRFS_SETGET_STACK_FUNCS(stack_timespec_nsec, struct btrfs_timespec, nsec, 32); +BTRFS_SETGET_FUNCS(stripe_extent_encoding, struct btrfs_stripe_extent, encoding, 8); +BTRFS_SETGET_FUNCS(raid_stride_devid, struct btrfs_raid_stride, devid, 64); +BTRFS_SETGET_FUNCS(raid_stride_physical, struct btrfs_raid_stride, physical, 64); +BTRFS_SETGET_STACK_FUNCS(stack_stripe_extent_encoding, + struct btrfs_stripe_extent, encoding, 8); +BTRFS_SETGET_STACK_FUNCS(stack_raid_stride_devid, struct btrfs_raid_stride, devid, 64); +BTRFS_SETGET_STACK_FUNCS(stack_raid_stride_physical, struct btrfs_raid_stride, physical, 64); + /* struct btrfs_dev_extent */ BTRFS_SETGET_FUNCS(dev_extent_chunk_tree, struct btrfs_dev_extent, chunk_tree, 64); BTRFS_SETGET_FUNCS(dev_extent_chunk_objectid, struct btrfs_dev_extent, diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 6ac4fd8cc8dc..74d8e2003f58 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -74,6 +74,7 @@ static struct btrfs_lockdep_keyset { { .id = BTRFS_UUID_TREE_OBJECTID, DEFINE_NAME("uuid") }, { .id = BTRFS_FREE_SPACE_TREE_OBJECTID, DEFINE_NAME("free-space") }, { .id = BTRFS_BLOCK_GROUP_TREE_OBJECTID, DEFINE_NAME("block-group") }, + { .id = BTRFS_RAID_STRIPE_TREE_OBJECTID, DEFINE_NAME("raid-stripe") }, { .id = 0, DEFINE_NAME("tree") }, }; diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index fc3c32186d7e..ca65d7b7a6ca 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -73,6 +73,9 @@ /* Holds the block group items for extent tree v2. */ #define BTRFS_BLOCK_GROUP_TREE_OBJECTID 11ULL +/* Tracks RAID stripes in block groups. */ +#define BTRFS_RAID_STRIPE_TREE_OBJECTID 12ULL + /* device stats in the device tree */ #define BTRFS_DEV_STATS_OBJECTID 0ULL @@ -261,6 +264,8 @@ #define BTRFS_DEV_ITEM_KEY 216 #define BTRFS_CHUNK_ITEM_KEY 228 +#define BTRFS_RAID_STRIPE_KEY 230 + /* * Records the overall state of the qgroups. * There's only one instance of this key present, @@ -719,6 +724,30 @@ struct btrfs_free_space_header { __le64 num_bitmaps; } __attribute__ ((__packed__)); +struct btrfs_raid_stride { + /* The id of device this raid extent lives on. */ + __le64 devid; + /* The physical location on disk. */ + __le64 physical; +} __attribute__ ((__packed__)); + +/* The stripe_extent::encoding, 1:1 mapping of enum btrfs_raid_types. */ +#define BTRFS_STRIPE_RAID0 1 +#define BTRFS_STRIPE_RAID1 2 +#define BTRFS_STRIPE_DUP 3 +#define BTRFS_STRIPE_RAID10 4 +#define BTRFS_STRIPE_RAID5 5 +#define BTRFS_STRIPE_RAID6 6 +#define BTRFS_STRIPE_RAID1C3 7 +#define BTRFS_STRIPE_RAID1C4 8 + +struct btrfs_stripe_extent { + __u8 encoding; + __u8 reserved[7]; + /* An array of raid strides this stripe is composed of. */ + struct btrfs_raid_stride strides[]; +} __attribute__ ((__packed__)); + #define BTRFS_HEADER_FLAG_WRITTEN (1ULL << 0) #define BTRFS_HEADER_FLAG_RELOC (1ULL << 1) -- cgit From 515020900d447796bc2f0f57064663617a11b65d Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Thu, 14 Sep 2023 09:06:57 -0700 Subject: btrfs: read raid stripe tree from disk If we find the raid-stripe-tree on mount, read it from disk. This is a backward incompatible feature. The rescue=ignorebadroots mount option will skip this tree. Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/block-rsv.c | 6 ++++++ fs/btrfs/disk-io.c | 18 ++++++++++++++++++ fs/btrfs/fs.h | 1 + include/uapi/linux/btrfs.h | 1 + 4 files changed, 26 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c index 6a8f9629bbbd..ceb5f586a2d5 100644 --- a/fs/btrfs/block-rsv.c +++ b/fs/btrfs/block-rsv.c @@ -356,6 +356,11 @@ void btrfs_update_global_block_rsv(struct btrfs_fs_info *fs_info) min_items++; } + if (btrfs_fs_incompat(fs_info, RAID_STRIPE_TREE)) { + num_bytes += btrfs_root_used(&fs_info->stripe_root->root_item); + min_items++; + } + /* * But we also want to reserve enough space so we can do the fallback * global reserve for an unlink, which is an additional @@ -407,6 +412,7 @@ void btrfs_init_root_block_rsv(struct btrfs_root *root) case BTRFS_EXTENT_TREE_OBJECTID: case BTRFS_FREE_SPACE_TREE_OBJECTID: case BTRFS_BLOCK_GROUP_TREE_OBJECTID: + case BTRFS_RAID_STRIPE_TREE_OBJECTID: root->block_rsv = &fs_info->delayed_refs_rsv; break; case BTRFS_ROOT_TREE_OBJECTID: diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 163f37ad1b27..dc577b3c53f6 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1179,6 +1179,8 @@ static struct btrfs_root *btrfs_get_global_root(struct btrfs_fs_info *fs_info, return btrfs_grab_root(fs_info->block_group_root); case BTRFS_FREE_SPACE_TREE_OBJECTID: return btrfs_grab_root(btrfs_global_root(fs_info, &key)); + case BTRFS_RAID_STRIPE_TREE_OBJECTID: + return btrfs_grab_root(fs_info->stripe_root); default: return NULL; } @@ -1259,6 +1261,7 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) btrfs_put_root(fs_info->fs_root); btrfs_put_root(fs_info->data_reloc_root); btrfs_put_root(fs_info->block_group_root); + btrfs_put_root(fs_info->stripe_root); btrfs_check_leaked_roots(fs_info); btrfs_extent_buffer_leak_debug_check(fs_info); kfree(fs_info->super_copy); @@ -1804,6 +1807,7 @@ static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root) free_root_extent_buffers(info->fs_root); free_root_extent_buffers(info->data_reloc_root); free_root_extent_buffers(info->block_group_root); + free_root_extent_buffers(info->stripe_root); if (free_chunk_root) free_root_extent_buffers(info->chunk_root); } @@ -2280,6 +2284,20 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info) fs_info->uuid_root = root; } + if (btrfs_fs_incompat(fs_info, RAID_STRIPE_TREE)) { + location.objectid = BTRFS_RAID_STRIPE_TREE_OBJECTID; + root = btrfs_read_tree_root(tree_root, &location); + if (IS_ERR(root)) { + if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { + ret = PTR_ERR(root); + goto out; + } + } else { + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->stripe_root = root; + } + } + return 0; out: btrfs_warn(fs_info, "failed to read root (objectid=%llu): %d", diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index 5559c33cd53a..b1914a9eb9f6 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -373,6 +373,7 @@ struct btrfs_fs_info { struct btrfs_root *uuid_root; struct btrfs_root *data_reloc_root; struct btrfs_root *block_group_root; + struct btrfs_root *stripe_root; /* The log root tree is a directory of all the other log roots */ struct btrfs_root *log_root_tree; diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index dbb8b96da50d..b9a1d9af8ae8 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -333,6 +333,7 @@ struct btrfs_ioctl_fs_info_args { #define BTRFS_FEATURE_INCOMPAT_RAID1C34 (1ULL << 11) #define BTRFS_FEATURE_INCOMPAT_ZONED (1ULL << 12) #define BTRFS_FEATURE_INCOMPAT_EXTENT_TREE_V2 (1ULL << 13) +#define BTRFS_FEATURE_INCOMPAT_RAID_STRIPE_TREE (1ULL << 14) struct btrfs_ioctl_feature_flags { __u64 compat_flags; -- cgit From 182940f4f4dbd932776414744c8de64333957725 Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Tue, 16 May 2023 16:35:45 -0700 Subject: btrfs: qgroup: add new quota mode for simple quotas Add a new quota mode called "simple quotas". It can be enabled by the existing quota enable ioctl via a new command, and sets an incompat bit, as the implementation of simple quotas will make backwards incompatible changes to the disk format of the extent tree. Signed-off-by: Boris Burkov Signed-off-by: David Sterba --- fs/btrfs/delayed-ref.c | 6 +-- fs/btrfs/fs.h | 3 +- fs/btrfs/ioctl.c | 3 +- fs/btrfs/qgroup.c | 110 +++++++++++++++++++++++++++++----------- fs/btrfs/qgroup.h | 17 +++++-- fs/btrfs/root-tree.c | 2 +- fs/btrfs/transaction.c | 7 ++- include/uapi/linux/btrfs.h | 2 + include/uapi/linux/btrfs_tree.h | 10 +++- 9 files changed, 115 insertions(+), 45 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 25d0cdf85a91..0a80224c8784 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -959,8 +959,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, return -ENOMEM; } - if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) && - !generic_ref->skip_qgroup) { + if (btrfs_qgroup_enabled(fs_info) && !generic_ref->skip_qgroup) { record = kzalloc(sizeof(*record), GFP_NOFS); if (!record) { kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref); @@ -1063,8 +1062,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, return -ENOMEM; } - if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) && - !generic_ref->skip_qgroup) { + if (btrfs_qgroup_enabled(fs_info) && !generic_ref->skip_qgroup) { record = kzalloc(sizeof(*record), GFP_NOFS); if (!record) { kmem_cache_free(btrfs_delayed_data_ref_cachep, ref); diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index 19f9a444bcd8..e8fcf34f208a 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -220,7 +220,8 @@ enum { BTRFS_FEATURE_INCOMPAT_NO_HOLES | \ BTRFS_FEATURE_INCOMPAT_METADATA_UUID | \ BTRFS_FEATURE_INCOMPAT_RAID1C34 | \ - BTRFS_FEATURE_INCOMPAT_ZONED) + BTRFS_FEATURE_INCOMPAT_ZONED | \ + BTRFS_FEATURE_INCOMPAT_SIMPLE_QUOTA) #ifdef CONFIG_BTRFS_DEBUG /* diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 5dbc3de66193..58189d99a22c 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3697,7 +3697,8 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg) switch (sa->cmd) { case BTRFS_QUOTA_CTL_ENABLE: - ret = btrfs_quota_enable(fs_info); + case BTRFS_QUOTA_CTL_ENABLE_SIMPLE_QUOTA: + ret = btrfs_quota_enable(fs_info, sa); break; case BTRFS_QUOTA_CTL_DISABLE: ret = btrfs_quota_disable(fs_info); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 69787b87a4f8..1c0efc1757c1 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -34,9 +34,21 @@ enum btrfs_qgroup_mode btrfs_qgroup_mode(struct btrfs_fs_info *fs_info) { if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) return BTRFS_QGROUP_MODE_DISABLED; + if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE) + return BTRFS_QGROUP_MODE_SIMPLE; return BTRFS_QGROUP_MODE_FULL; } +bool btrfs_qgroup_enabled(struct btrfs_fs_info *fs_info) +{ + return btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_DISABLED; +} + +bool btrfs_qgroup_full_accounting(struct btrfs_fs_info *fs_info) +{ + return btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_FULL; +} + /* * Helpers to access qgroup reservation * @@ -350,6 +362,8 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid, static void qgroup_mark_inconsistent(struct btrfs_fs_info *fs_info) { + if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE) + return; fs_info->qgroup_flags |= (BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT | BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN | BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING); @@ -370,8 +384,9 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info) int ret = 0; u64 flags = 0; u64 rescan_progress = 0; + bool simple; - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) + if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED) return 0; fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL); @@ -421,14 +436,14 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info) "old qgroup version, quota disabled"); goto out; } + fs_info->qgroup_flags = btrfs_qgroup_status_flags(l, ptr); + simple = (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE); if (btrfs_qgroup_status_generation(l, ptr) != - fs_info->generation) { + fs_info->generation && !simple) { qgroup_mark_inconsistent(fs_info); btrfs_err(fs_info, "qgroup generation mismatch, marked as inconsistent"); } - fs_info->qgroup_flags = btrfs_qgroup_status_flags(l, - ptr); rescan_progress = btrfs_qgroup_status_rescan(l, ptr); goto next1; } @@ -571,7 +586,7 @@ bool btrfs_check_quota_leak(struct btrfs_fs_info *fs_info) struct rb_node *node; bool ret = false; - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) + if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED) return ret; /* * Since we're unmounting, there is no race and no need to grab qgroup @@ -970,7 +985,8 @@ out: return ret; } -int btrfs_quota_enable(struct btrfs_fs_info *fs_info) +int btrfs_quota_enable(struct btrfs_fs_info *fs_info, + struct btrfs_ioctl_quota_ctl_args *quota_ctl_args) { struct btrfs_root *quota_root; struct btrfs_root *tree_root = fs_info->tree_root; @@ -983,6 +999,7 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) struct btrfs_qgroup *prealloc = NULL; struct btrfs_trans_handle *trans = NULL; struct ulist *ulist = NULL; + const bool simple = (quota_ctl_args->cmd == BTRFS_QUOTA_CTL_ENABLE_SIMPLE_QUOTA); int ret = 0; int slot; @@ -1085,8 +1102,11 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) struct btrfs_qgroup_status_item); btrfs_set_qgroup_status_generation(leaf, ptr, trans->transid); btrfs_set_qgroup_status_version(leaf, ptr, BTRFS_QGROUP_STATUS_VERSION); - fs_info->qgroup_flags = BTRFS_QGROUP_STATUS_FLAG_ON | - BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; + fs_info->qgroup_flags = BTRFS_QGROUP_STATUS_FLAG_ON; + if (simple) + fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE; + else + fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; btrfs_set_qgroup_status_flags(leaf, ptr, fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAGS_MASK); btrfs_set_qgroup_status_rescan(leaf, ptr, 0); @@ -1214,8 +1234,14 @@ out_add_root: spin_lock(&fs_info->qgroup_lock); fs_info->quota_root = quota_root; set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); + if (simple) + btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA); spin_unlock(&fs_info->qgroup_lock); + /* Skip rescan for simple qgroups. */ + if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE) + goto out_free_path; + ret = qgroup_rescan_init(fs_info, 0, 1); if (!ret) { qgroup_rescan_zero_tracking(fs_info); @@ -1330,6 +1356,7 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) quota_root = fs_info->quota_root; fs_info->quota_root = NULL; fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON; + fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE; fs_info->qgroup_drop_subtree_thres = BTRFS_MAX_LEVEL; spin_unlock(&fs_info->qgroup_lock); @@ -1810,6 +1837,9 @@ int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info, struct btrfs_qgroup_extent_record *entry; u64 bytenr = record->bytenr; + if (!btrfs_qgroup_full_accounting(fs_info)) + return 0; + lockdep_assert_held(&delayed_refs->lock); trace_btrfs_qgroup_trace_extent(fs_info, record); @@ -1863,6 +1893,8 @@ int btrfs_qgroup_trace_extent_post(struct btrfs_trans_handle *trans, struct btrfs_backref_walk_ctx ctx = { 0 }; int ret; + if (!btrfs_qgroup_full_accounting(trans->fs_info)) + return 0; /* * We are always called in a context where we are already holding a * transaction handle. Often we are called when adding a data delayed @@ -1931,8 +1963,7 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr, struct btrfs_delayed_ref_root *delayed_refs; int ret; - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) - || bytenr == 0 || num_bytes == 0) + if (!btrfs_qgroup_full_accounting(fs_info) || bytenr == 0 || num_bytes == 0) return 0; record = kzalloc(sizeof(*record), GFP_NOFS); if (!record) @@ -1970,7 +2001,7 @@ int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans, u64 bytenr, num_bytes; /* We can be called directly from walk_up_proc() */ - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) + if (!btrfs_qgroup_full_accounting(fs_info)) return 0; for (i = 0; i < nr; i++) { @@ -2346,7 +2377,7 @@ static int qgroup_trace_subtree_swap(struct btrfs_trans_handle *trans, int level; int ret; - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) + if (!btrfs_qgroup_full_accounting(fs_info)) return 0; /* Wrong parameter order */ @@ -2413,7 +2444,7 @@ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans, BUG_ON(root_level < 0 || root_level >= BTRFS_MAX_LEVEL); BUG_ON(root_eb == NULL); - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) + if (!btrfs_qgroup_full_accounting(fs_info)) return 0; spin_lock(&fs_info->qgroup_lock); @@ -2747,7 +2778,7 @@ int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr, * If quotas get disabled meanwhile, the resources need to be freed and * we can't just exit here. */ - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) || + if (!btrfs_qgroup_full_accounting(fs_info) || fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING) goto out_free; @@ -2816,6 +2847,9 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) u64 qgroup_to_skip; int ret = 0; + if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE) + return 0; + delayed_refs = &trans->transaction->delayed_refs; qgroup_to_skip = delayed_refs->qgroup_to_skip; while ((node = rb_first(&delayed_refs->dirty_extent_root))) { @@ -2931,7 +2965,7 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans) qgroup_mark_inconsistent(fs_info); spin_lock(&fs_info->qgroup_lock); } - if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) + if (btrfs_qgroup_enabled(fs_info)) fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_ON; else fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON; @@ -2990,7 +3024,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, if (!committing) mutex_lock(&fs_info->qgroup_ioctl_lock); - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) + if (!btrfs_qgroup_enabled(fs_info)) goto out; quota_root = fs_info->quota_root; @@ -3076,7 +3110,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, qgroup_dirty(fs_info, dstgroup); } - if (srcid) { + if (srcid && btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_FULL) { srcgroup = find_qgroup_rb(fs_info, srcid); if (!srcgroup) goto unlock; @@ -3339,6 +3373,9 @@ static int qgroup_rescan_leaf(struct btrfs_trans_handle *trans, int slot; int ret; + if (!btrfs_qgroup_full_accounting(fs_info)) + return 1; + mutex_lock(&fs_info->qgroup_rescan_lock); extent_root = btrfs_extent_root(fs_info, fs_info->qgroup_rescan_progress.objectid); @@ -3419,10 +3456,15 @@ out: static bool rescan_should_stop(struct btrfs_fs_info *fs_info) { - return btrfs_fs_closing(fs_info) || - test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state) || - !test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) || - fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN; + if (btrfs_fs_closing(fs_info)) + return true; + if (test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state)) + return true; + if (!btrfs_qgroup_enabled(fs_info)) + return true; + if (fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN) + return true; + return false; } static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) @@ -3436,6 +3478,9 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) bool stopped = false; bool did_leaf_rescans = false; + if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE) + return; + path = btrfs_alloc_path(); if (!path) goto out; @@ -3539,6 +3584,11 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, { int ret = 0; + if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE) { + btrfs_warn(fs_info, "qgroup rescan init failed, running in simple mode"); + return -EINVAL; + } + if (!init_flags) { /* we're resuming qgroup rescan at mount time */ if (!(fs_info->qgroup_flags & @@ -3569,7 +3619,7 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, btrfs_warn(fs_info, "qgroup rescan init failed, qgroup is not enabled"); ret = -EINVAL; - } else if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) { + } else if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED) { /* Quota disable is in progress */ ret = -EBUSY; } @@ -3828,7 +3878,7 @@ static int qgroup_reserve_data(struct btrfs_inode *inode, u64 to_reserve; int ret; - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &root->fs_info->flags) || + if (btrfs_qgroup_mode(root->fs_info) == BTRFS_QGROUP_MODE_DISABLED || !is_fstree(root->root_key.objectid) || len == 0) return 0; @@ -3960,7 +4010,7 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, int trace_op = QGROUP_RELEASE; int ret; - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &inode->root->fs_info->flags)) + if (btrfs_qgroup_mode(inode->root->fs_info) == BTRFS_QGROUP_MODE_DISABLED) return 0; /* In release case, we shouldn't have @reserved */ @@ -4071,7 +4121,7 @@ int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, struct btrfs_fs_info *fs_info = root->fs_info; int ret; - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) || + if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED || !is_fstree(root->root_key.objectid) || num_bytes == 0) return 0; @@ -4116,7 +4166,7 @@ void btrfs_qgroup_free_meta_all_pertrans(struct btrfs_root *root) { struct btrfs_fs_info *fs_info = root->fs_info; - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) || + if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED || !is_fstree(root->root_key.objectid)) return; @@ -4132,7 +4182,7 @@ void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes, { struct btrfs_fs_info *fs_info = root->fs_info; - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) || + if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED || !is_fstree(root->root_key.objectid)) return; @@ -4191,7 +4241,7 @@ void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes) { struct btrfs_fs_info *fs_info = root->fs_info; - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) || + if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED || !is_fstree(root->root_key.objectid)) return; /* Same as btrfs_qgroup_free_meta_prealloc() */ @@ -4299,7 +4349,7 @@ int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans, int level = btrfs_header_level(subvol_parent) - 1; int ret = 0; - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) + if (!btrfs_qgroup_full_accounting(fs_info)) return 0; if (btrfs_node_ptr_generation(subvol_parent, subvol_slot) > @@ -4409,7 +4459,7 @@ int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans, int ret = 0; int i; - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) + if (!btrfs_qgroup_full_accounting(fs_info)) return 0; if (!is_fstree(root->root_key.objectid) || !root->reloc_root) return 0; diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index aed611774047..0441d2ff5a49 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -101,8 +101,15 @@ * subtree rescan for them. */ -#define BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN (1UL << 3) -#define BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING (1UL << 4) +/* + * These flags share the flags field of the btrfs_qgroup_status_item with the + * persisted flags defined in btrfs_tree.h. + * + * To minimize the chance of collision with new persisted status flags, these + * count backwards from the MSB. + */ +#define BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN (1ULL << 63) +#define BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING (1ULL << 62) /* * Record a dirty extent, and info qgroup to update quota on it @@ -276,13 +283,17 @@ enum { ENUM_BIT(QGROUP_FREE), }; -int btrfs_quota_enable(struct btrfs_fs_info *fs_info); enum btrfs_qgroup_mode { BTRFS_QGROUP_MODE_DISABLED, BTRFS_QGROUP_MODE_FULL, + BTRFS_QGROUP_MODE_SIMPLE }; enum btrfs_qgroup_mode btrfs_qgroup_mode(struct btrfs_fs_info *fs_info); +bool btrfs_qgroup_enabled(struct btrfs_fs_info *fs_info); +bool btrfs_qgroup_full_accounting(struct btrfs_fs_info *fs_info); +int btrfs_quota_enable(struct btrfs_fs_info *fs_info, + struct btrfs_ioctl_quota_ctl_args *quota_ctl_args); int btrfs_quota_disable(struct btrfs_fs_info *fs_info); int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info); void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 7c9d87b9b72e..603ad1459368 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -510,7 +510,7 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; - if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) { + if (btrfs_qgroup_enabled(fs_info)) { /* One for parent inode, two for dir entries */ qgroup_num_bytes = 3 * fs_info->nodesize; ret = btrfs_qgroup_reserve_meta_prealloc(root, diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 3f9f933039c6..f5c3ea01c3d6 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1620,11 +1620,10 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans, int ret; /* - * Save some performance in the case that qgroups are not - * enabled. If this check races with the ioctl, rescan will - * kick in anyway. + * Save some performance in the case that full qgroups are not enabled. + * If this check races with the ioctl, rescan will kick in anyway. */ - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) + if (!btrfs_qgroup_full_accounting(fs_info)) return 0; /* diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index b9a1d9af8ae8..7c29d82db9ee 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -334,6 +334,7 @@ struct btrfs_ioctl_fs_info_args { #define BTRFS_FEATURE_INCOMPAT_ZONED (1ULL << 12) #define BTRFS_FEATURE_INCOMPAT_EXTENT_TREE_V2 (1ULL << 13) #define BTRFS_FEATURE_INCOMPAT_RAID_STRIPE_TREE (1ULL << 14) +#define BTRFS_FEATURE_INCOMPAT_SIMPLE_QUOTA (1ULL << 16) struct btrfs_ioctl_feature_flags { __u64 compat_flags; @@ -754,6 +755,7 @@ struct btrfs_ioctl_get_dev_stats { #define BTRFS_QUOTA_CTL_ENABLE 1 #define BTRFS_QUOTA_CTL_DISABLE 2 #define BTRFS_QUOTA_CTL_RESCAN__NOTUSED 3 +#define BTRFS_QUOTA_CTL_ENABLE_SIMPLE_QUOTA 4 struct btrfs_ioctl_quota_ctl_args { __u64 cmd; __u64 status; diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index ca65d7b7a6ca..a1d5347f6adb 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -1233,9 +1233,17 @@ static inline __u16 btrfs_qgroup_level(__u64 qgroupid) */ #define BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT (1ULL << 2) +/* + * Whether or not this filesystem is using simple quotas. Not exactly the + * incompat bit, because we support using simple quotas, disabling it, then + * going back to full qgroup quotas. + */ +#define BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE (1ULL << 3) + #define BTRFS_QGROUP_STATUS_FLAGS_MASK (BTRFS_QGROUP_STATUS_FLAG_ON | \ BTRFS_QGROUP_STATUS_FLAG_RESCAN | \ - BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT) + BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT | \ + BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE) #define BTRFS_QGROUP_STATUS_VERSION 1 -- cgit From d9a620f77e33f2b0e9a5f131f3ee3c66d3285c57 Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Mon, 30 Jan 2023 14:45:55 -0800 Subject: btrfs: new inline ref storing owning subvol of data extents In order to implement simple quota groups, we need to be able to associate a data extent with the subvolume that created it. Once you account for reflink, this information cannot be recovered without explicitly storing it. Options for storing it are: - a new key/item - a new extent inline ref item The former is backwards compatible, but wastes space, the latter is incompat, but is efficient in space and reuses the existing inline ref machinery, while only abusing it a tiny amount -- specifically, the new item is not a ref, per-se. Signed-off-by: Boris Burkov Signed-off-by: David Sterba --- fs/btrfs/accessors.h | 5 ++++ fs/btrfs/backref.c | 3 +++ fs/btrfs/extent-tree.c | 57 +++++++++++++++++++++++++++++++++-------- fs/btrfs/print-tree.c | 12 +++++++++ fs/btrfs/ref-verify.c | 3 +++ fs/btrfs/tree-checker.c | 3 +++ include/uapi/linux/btrfs_tree.h | 12 +++++++++ 7 files changed, 84 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h index ce18e261c861..fb1c1a1983f2 100644 --- a/fs/btrfs/accessors.h +++ b/fs/btrfs/accessors.h @@ -358,6 +358,9 @@ BTRFS_SETGET_FUNCS(extent_data_ref_count, struct btrfs_extent_data_ref, count, 3 BTRFS_SETGET_FUNCS(shared_data_ref_count, struct btrfs_shared_data_ref, count, 32); +BTRFS_SETGET_FUNCS(extent_owner_ref_root_id, struct btrfs_extent_owner_ref, + root_id, 64); + BTRFS_SETGET_FUNCS(extent_inline_ref_type, struct btrfs_extent_inline_ref, type, 8); BTRFS_SETGET_FUNCS(extent_inline_ref_offset, struct btrfs_extent_inline_ref, @@ -374,6 +377,8 @@ static inline u32 btrfs_extent_inline_ref_size(int type) if (type == BTRFS_EXTENT_DATA_REF_KEY) return sizeof(struct btrfs_extent_data_ref) + offsetof(struct btrfs_extent_inline_ref, offset); + if (type == BTRFS_EXTENT_OWNER_REF_KEY) + return sizeof(struct btrfs_extent_inline_ref); return 0; } diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index b7d54efb4728..0cde873bdee2 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1129,6 +1129,9 @@ static int add_inline_refs(struct btrfs_backref_walk_ctx *ctx, count, sc, GFP_NOFS); break; } + case BTRFS_EXTENT_OWNER_REF_KEY: + ASSERT(btrfs_fs_incompat(ctx->fs_info, SIMPLE_QUOTA)); + break; default: WARN_ON(1); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 2dda3ecb49e6..8bd556c8bca4 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -345,9 +345,15 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb, struct btrfs_extent_inline_ref *iref, enum btrfs_inline_ref_type is_data) { + struct btrfs_fs_info *fs_info = eb->fs_info; int type = btrfs_extent_inline_ref_type(eb, iref); u64 offset = btrfs_extent_inline_ref_offset(eb, iref); + if (type == BTRFS_EXTENT_OWNER_REF_KEY) { + ASSERT(btrfs_fs_incompat(fs_info, SIMPLE_QUOTA)); + return type; + } + if (type == BTRFS_TREE_BLOCK_REF_KEY || type == BTRFS_SHARED_BLOCK_REF_KEY || type == BTRFS_SHARED_DATA_REF_KEY || @@ -356,26 +362,25 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb, if (type == BTRFS_TREE_BLOCK_REF_KEY) return type; if (type == BTRFS_SHARED_BLOCK_REF_KEY) { - ASSERT(eb->fs_info); + ASSERT(fs_info); /* * Every shared one has parent tree block, * which must be aligned to sector size. */ - if (offset && - IS_ALIGNED(offset, eb->fs_info->sectorsize)) + if (offset && IS_ALIGNED(offset, fs_info->sectorsize)) return type; } } else if (is_data == BTRFS_REF_TYPE_DATA) { if (type == BTRFS_EXTENT_DATA_REF_KEY) return type; if (type == BTRFS_SHARED_DATA_REF_KEY) { - ASSERT(eb->fs_info); + ASSERT(fs_info); /* * Every shared one has parent tree block, * which must be aligned to sector size. */ if (offset && - IS_ALIGNED(offset, eb->fs_info->sectorsize)) + IS_ALIGNED(offset, fs_info->sectorsize)) return type; } } else { @@ -386,7 +391,7 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb, WARN_ON(1); btrfs_print_leaf(eb); - btrfs_err(eb->fs_info, + btrfs_err(fs_info, "eb %llu iref 0x%lx invalid extent inline ref type %d", eb->start, (unsigned long)iref, type); @@ -887,6 +892,11 @@ again: while (ptr < end) { iref = (struct btrfs_extent_inline_ref *)ptr; type = btrfs_get_extent_inline_ref_type(leaf, iref, needed); + if (type == BTRFS_EXTENT_OWNER_REF_KEY) { + ASSERT(btrfs_fs_incompat(fs_info, SIMPLE_QUOTA)); + ptr += btrfs_extent_inline_ref_size(type); + continue; + } if (type == BTRFS_REF_TYPE_INVALID) { ret = -EUCLEAN; goto out; @@ -1742,6 +1752,8 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans, node->type == BTRFS_SHARED_DATA_REF_KEY) ret = run_delayed_data_ref(trans, node, extent_op, insert_reserved); + else if (node->type == BTRFS_EXTENT_OWNER_REF_KEY) + ret = 0; else BUG(); if (ret && insert_reserved) @@ -2313,6 +2325,7 @@ static noinline int check_committed_ref(struct btrfs_root *root, struct btrfs_extent_item *ei; struct btrfs_key key; u32 item_size; + u32 expected_size; int type; int ret; @@ -2339,10 +2352,22 @@ static noinline int check_committed_ref(struct btrfs_root *root, ret = 1; item_size = btrfs_item_size(leaf, path->slots[0]); ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); + expected_size = sizeof(*ei) + btrfs_extent_inline_ref_size(BTRFS_EXTENT_DATA_REF_KEY); + + /* No inline refs; we need to bail before checking for owner ref. */ + if (item_size == sizeof(*ei)) + goto out; + + /* Check for an owner ref; skip over it to the real inline refs. */ + iref = (struct btrfs_extent_inline_ref *)(ei + 1); + type = btrfs_get_extent_inline_ref_type(leaf, iref, BTRFS_REF_TYPE_DATA); + if (btrfs_fs_incompat(fs_info, SIMPLE_QUOTA) && type == BTRFS_EXTENT_OWNER_REF_KEY) { + expected_size += btrfs_extent_inline_ref_size(BTRFS_EXTENT_OWNER_REF_KEY); + iref = (struct btrfs_extent_inline_ref *)(iref + 1); + } /* If extent item has more than 1 inline ref then it's shared */ - if (item_size != sizeof(*ei) + - btrfs_extent_inline_ref_size(BTRFS_EXTENT_DATA_REF_KEY)) + if (item_size != expected_size) goto out; /* @@ -2354,8 +2379,6 @@ static noinline int check_committed_ref(struct btrfs_root *root, btrfs_root_last_snapshot(&root->root_item))) goto out; - iref = (struct btrfs_extent_inline_ref *)(ei + 1); - /* If this extent has SHARED_DATA_REF then it's shared */ type = btrfs_get_extent_inline_ref_type(leaf, iref, BTRFS_REF_TYPE_DATA); if (type != BTRFS_EXTENT_DATA_REF_KEY) @@ -4617,18 +4640,23 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans, struct btrfs_root *extent_root; int ret; struct btrfs_extent_item *extent_item; + struct btrfs_extent_owner_ref *oref; struct btrfs_extent_inline_ref *iref; struct btrfs_path *path; struct extent_buffer *leaf; int type; u32 size; + const bool simple_quota = (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE); if (parent > 0) type = BTRFS_SHARED_DATA_REF_KEY; else type = BTRFS_EXTENT_DATA_REF_KEY; - size = sizeof(*extent_item) + btrfs_extent_inline_ref_size(type); + size = sizeof(*extent_item); + if (simple_quota) + size += btrfs_extent_inline_ref_size(BTRFS_EXTENT_OWNER_REF_KEY); + size += btrfs_extent_inline_ref_size(type); path = btrfs_alloc_path(); if (!path) @@ -4650,7 +4678,14 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans, flags | BTRFS_EXTENT_FLAG_DATA); iref = (struct btrfs_extent_inline_ref *)(extent_item + 1); + if (simple_quota) { + btrfs_set_extent_inline_ref_type(leaf, iref, BTRFS_EXTENT_OWNER_REF_KEY); + oref = (struct btrfs_extent_owner_ref *)(&iref->offset); + btrfs_set_extent_owner_ref_root_id(leaf, oref, root_objectid); + iref = (struct btrfs_extent_inline_ref *)(oref + 1); + } btrfs_set_extent_inline_ref_type(leaf, iref, type); + if (parent > 0) { struct btrfs_shared_data_ref *ref; ref = (struct btrfs_shared_data_ref *)(iref + 1); diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index 75042a7fcf30..7e46aa8a0444 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -83,12 +83,20 @@ static void print_extent_data_ref(const struct extent_buffer *eb, btrfs_extent_data_ref_count(eb, ref)); } +static void print_extent_owner_ref(const struct extent_buffer *eb, + const struct btrfs_extent_owner_ref *ref) +{ + ASSERT(btrfs_fs_incompat(eb->fs_info, SIMPLE_QUOTA)); + pr_cont("extent data owner root %llu\n", btrfs_extent_owner_ref_root_id(eb, ref)); +} + static void print_extent_item(const struct extent_buffer *eb, int slot, int type) { struct btrfs_extent_item *ei; struct btrfs_extent_inline_ref *iref; struct btrfs_extent_data_ref *dref; struct btrfs_shared_data_ref *sref; + struct btrfs_extent_owner_ref *oref; struct btrfs_disk_key key; unsigned long end; unsigned long ptr; @@ -164,6 +172,10 @@ static void print_extent_item(const struct extent_buffer *eb, int slot, int type "\t\t\t(parent %llu not aligned to sectorsize %u)\n", offset, eb->fs_info->sectorsize); break; + case BTRFS_EXTENT_OWNER_REF_KEY: + oref = (struct btrfs_extent_owner_ref *)(&iref->offset); + print_extent_owner_ref(eb, oref); + break; default: pr_cont("(extent %llu has INVALID ref type %d)\n", eb->start, type); diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index e9e1ebd8dd6a..1f62976bee82 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -485,6 +485,9 @@ static int process_extent_item(struct btrfs_fs_info *fs_info, ret = add_shared_data_ref(fs_info, offset, count, key->objectid, key->offset); break; + case BTRFS_EXTENT_OWNER_REF_KEY: + WARN_ON(!btrfs_fs_incompat(fs_info, SIMPLE_QUOTA)); + break; default: btrfs_err(fs_info, "invalid key type in iref"); ret = -EINVAL; diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 1547090bf2c0..1f2c389b0bfa 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1467,6 +1467,9 @@ static int check_extent_item(struct extent_buffer *leaf, } inline_refs += btrfs_shared_data_ref_count(leaf, sref); break; + case BTRFS_EXTENT_OWNER_REF_KEY: + WARN_ON(!btrfs_fs_incompat(fs_info, SIMPLE_QUOTA)); + break; default: extent_err(leaf, slot, "unknown inline ref type: %u", inline_type); diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index a1d5347f6adb..8b4def6aee52 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -233,6 +233,14 @@ #define BTRFS_SHARED_DATA_REF_KEY 184 +/* + * Special inline ref key which stores the id of the subvolume which originally + * created the extent. This subvolume owns the extent permanently from the + * perspective of simple quotas. Needed to know which subvolume to free quota + * usage from when the extent is deleted. + */ +#define BTRFS_EXTENT_OWNER_REF_KEY 188 + /* * block groups give us hints into the extent allocation trees. Which * blocks are free etc etc @@ -816,6 +824,10 @@ struct btrfs_shared_data_ref { __le32 count; } __attribute__ ((__packed__)); +struct btrfs_extent_owner_ref { + __le64 root_id; +} __attribute__ ((__packed__)); + struct btrfs_extent_inline_ref { __u8 type; __le64 offset; -- cgit From bd7c1ea3a302aba727a1ced9937ec84c6407724e Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Tue, 28 Mar 2023 15:45:20 -0700 Subject: btrfs: qgroup: check generation when recording simple quota delta Simple quotas count extents only from the moment the feature is enabled. Therefore, if we do something like: 1. create subvol S 2. write F in S 3. enable quotas 4. remove F 5. write G in S then after 3. and 4. we would expect the simple quota usage of S to be 0 (putting aside some metadata extents that might be written) and after 5., it should be the size of G plus metadata. Therefore, we need to be able to determine whether a particular quota delta we are processing predates simple quota enablement. To do this, store the transaction id when quotas were enabled. In fs_info for immediate use and in the quota status item to make it recoverable on mount. When we see a delta, check if the generation of the extent item is less than that of quota enablement. If so, we should ignore the delta from this extent. Signed-off-by: Boris Burkov Signed-off-by: David Sterba --- fs/btrfs/accessors.h | 2 ++ fs/btrfs/extent-tree.c | 4 ++++ fs/btrfs/fs.h | 1 + fs/btrfs/qgroup.c | 28 ++++++++++++++++++++++------ fs/btrfs/qgroup.h | 2 ++ include/uapi/linux/btrfs_tree.h | 9 +++++++++ 6 files changed, 40 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h index fb1c1a1983f2..aa0844535644 100644 --- a/fs/btrfs/accessors.h +++ b/fs/btrfs/accessors.h @@ -980,6 +980,8 @@ BTRFS_SETGET_FUNCS(qgroup_status_flags, struct btrfs_qgroup_status_item, flags, 64); BTRFS_SETGET_FUNCS(qgroup_status_rescan, struct btrfs_qgroup_status_item, rescan, 64); +BTRFS_SETGET_FUNCS(qgroup_status_enable_gen, struct btrfs_qgroup_status_item, + enable_gen, 64); /* btrfs_qgroup_info_item */ BTRFS_SETGET_FUNCS(qgroup_info_generation, struct btrfs_qgroup_info_item, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 865c74dffe82..8372d065aef4 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1566,6 +1566,7 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans, .rsv_bytes = href->reserved_bytes, .is_data = true, .is_inc = true, + .generation = trans->transid, }; if (extent_op) @@ -1738,6 +1739,7 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans, .rsv_bytes = 0, .is_data = false, .is_inc = true, + .generation = trans->transid, }; BUG_ON(!extent_op || !extent_op->update_flags); @@ -3287,6 +3289,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, .rsv_bytes = 0, .is_data = is_data, .is_inc = false, + .generation = btrfs_extent_generation(leaf, ei), }; /* In this branch refs == 1 */ @@ -4924,6 +4927,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, struct btrfs_squota_delta delta = { .root = root_objectid, .num_bytes = ins->offset, + .generation = trans->transid, .rsv_bytes = 0, .is_data = true, .is_inc = true, diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index e8fcf34f208a..2bd9bedc7095 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -687,6 +687,7 @@ struct btrfs_fs_info { /* Protected by qgroup_rescan_lock */ bool qgroup_rescan_running; u8 qgroup_drop_subtree_thres; + u64 qgroup_enable_gen; /* * If this is not 0, then it indicates a serious filesystem error has diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 5b3ad2f15039..f11f0fc8a9ff 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -369,6 +369,15 @@ static void qgroup_mark_inconsistent(struct btrfs_fs_info *fs_info) BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING); } +static void qgroup_read_enable_gen(struct btrfs_fs_info *fs_info, + struct extent_buffer *leaf, int slot, + struct btrfs_qgroup_status_item *ptr) +{ + ASSERT(btrfs_fs_incompat(fs_info, SIMPLE_QUOTA)); + ASSERT(btrfs_item_size(leaf, slot) >= sizeof(*ptr)); + fs_info->qgroup_enable_gen = btrfs_qgroup_status_enable_gen(leaf, ptr); +} + /* * The full config is read in one go, only called from open_ctree() * It doesn't use any locking, as at this point we're still single-threaded @@ -384,7 +393,6 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info) int ret = 0; u64 flags = 0; u64 rescan_progress = 0; - bool simple; if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED) return 0; @@ -437,9 +445,9 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info) goto out; } fs_info->qgroup_flags = btrfs_qgroup_status_flags(l, ptr); - simple = (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE); - if (btrfs_qgroup_status_generation(l, ptr) != - fs_info->generation && !simple) { + if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE) { + qgroup_read_enable_gen(fs_info, l, slot, ptr); + } else if (btrfs_qgroup_status_generation(l, ptr) != fs_info->generation) { qgroup_mark_inconsistent(fs_info); btrfs_err(fs_info, "qgroup generation mismatch, marked as inconsistent"); @@ -1103,10 +1111,12 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info, btrfs_set_qgroup_status_generation(leaf, ptr, trans->transid); btrfs_set_qgroup_status_version(leaf, ptr, BTRFS_QGROUP_STATUS_VERSION); fs_info->qgroup_flags = BTRFS_QGROUP_STATUS_FLAG_ON; - if (simple) + if (simple) { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE; - else + btrfs_set_qgroup_status_enable_gen(leaf, ptr, trans->transid); + } else { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; + } btrfs_set_qgroup_status_flags(leaf, ptr, fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAGS_MASK); btrfs_set_qgroup_status_rescan(leaf, ptr, 0); @@ -1210,6 +1220,8 @@ out_add_root: goto out_free_path; } + fs_info->qgroup_enable_gen = trans->transid; + mutex_unlock(&fs_info->qgroup_ioctl_lock); /* * Commit the transaction while not holding qgroup_ioctl_lock, to avoid @@ -4655,6 +4667,10 @@ int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info, if (!is_fstree(root)) return 0; + /* If the extent predates enabling quotas, don't count it. */ + if (delta->generation < fs_info->qgroup_enable_gen) + return 0; + spin_lock(&fs_info->qgroup_lock); qgroup = find_qgroup_rb(fs_info, root); if (!qgroup) { diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 9858244eef20..855a4f978761 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -276,6 +276,8 @@ struct btrfs_squota_delta { u64 num_bytes; /* The number of bytes reserved for this extent. */ u64 rsv_bytes; + /* The generation the extent was created in. */ + u64 generation; /* Whether we are using or freeing the extent. */ bool is_inc; /* Whether the extent is data or metadata. */ diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index 8b4def6aee52..c25fc9614594 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -1277,6 +1277,15 @@ struct btrfs_qgroup_status_item { * of the scan. It contains a logical address */ __le64 rescan; + + /* + * The generation when quotas were last enabled. Used by simple quotas to + * avoid decrementing when freeing an extent that was written before + * enable. + * + * Set only if flags contain BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE. + */ + __le64 enable_gen; } __attribute__ ((__packed__)); struct btrfs_qgroup_info_item { -- cgit From 49dbe25adac42d3e06f65d1420946bec65896222 Mon Sep 17 00:00:00 2001 From: Arseniy Krasnov Date: Tue, 10 Oct 2023 22:15:14 +0300 Subject: vsock: read from socket's error queue This adds handling of MSG_ERRQUEUE input flag in receive call. This flag is used to read socket's error queue instead of data queue. Possible scenario of error queue usage is receiving completions for transmission with MSG_ZEROCOPY flag. This patch also adds new defines: 'SOL_VSOCK' and 'VSOCK_RECVERR'. Signed-off-by: Arseniy Krasnov Reviewed-by: Stefano Garzarella Signed-off-by: David S. Miller --- include/linux/socket.h | 1 + include/uapi/linux/vm_sockets.h | 17 +++++++++++++++++ net/vmw_vsock/af_vsock.c | 6 ++++++ 3 files changed, 24 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 39b74d83c7c4..cfcb7e2c3813 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -383,6 +383,7 @@ struct ucred { #define SOL_MPTCP 284 #define SOL_MCTP 285 #define SOL_SMC 286 +#define SOL_VSOCK 287 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/uapi/linux/vm_sockets.h b/include/uapi/linux/vm_sockets.h index c60ca33eac59..ed07181d4eff 100644 --- a/include/uapi/linux/vm_sockets.h +++ b/include/uapi/linux/vm_sockets.h @@ -191,4 +191,21 @@ struct sockaddr_vm { #define IOCTL_VM_SOCKETS_GET_LOCAL_CID _IO(7, 0xb9) +/* MSG_ZEROCOPY notifications are encoded in the standard error format, + * sock_extended_err. See Documentation/networking/msg_zerocopy.rst in + * kernel source tree for more details. + */ + +/* 'cmsg_level' field value of 'struct cmsghdr' for notification parsing + * when MSG_ZEROCOPY flag is used on transmissions. + */ + +#define SOL_VSOCK 287 + +/* 'cmsg_type' field value of 'struct cmsghdr' for notification parsing + * when MSG_ZEROCOPY flag is used on transmissions. + */ + +#define VSOCK_RECVERR 1 + #endif /* _UAPI_VM_SOCKETS_H */ diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index d841f4de33b0..38486efd3d05 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -89,6 +89,7 @@ #include #include #include +#include #include #include #include @@ -110,6 +111,7 @@ #include #include #include +#include static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr); static void vsock_sk_destruct(struct sock *sk); @@ -2137,6 +2139,10 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int err; sk = sock->sk; + + if (unlikely(flags & MSG_ERRQUEUE)) + return sock_recv_errqueue(sk, msg, len, SOL_VSOCK, VSOCK_RECVERR); + vsk = vsock_sk(sk); err = 0; -- cgit From c3c6ab95c397134bf5948f18743b3ba8008e7c47 Mon Sep 17 00:00:00 2001 From: Arkadiusz Kubalewski Date: Wed, 11 Oct 2023 12:12:33 +0200 Subject: dpll: spec: add support for pin-dpll signal phase offset/adjust Add attributes for providing the user with: - measurement of signals phase offset between pin and dpll - ability to adjust the phase of pin signal Signed-off-by: Arkadiusz Kubalewski Signed-off-by: David S. Miller --- Documentation/netlink/specs/dpll.yaml | 30 ++++++++++++++++++++++++++++++ drivers/dpll/dpll_nl.c | 8 +++++--- drivers/dpll/dpll_nl.h | 2 +- include/uapi/linux/dpll.h | 6 ++++++ 4 files changed, 42 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index 1c1b53136c7b..cf8abe1c0550 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -164,6 +164,18 @@ definitions: - name: state-can-change doc: pin state can be changed + - + type: const + name: phase-offset-divider + value: 1000 + doc: | + phase offset divider allows userspace to calculate a value of + measured signal phase difference between a pin and dpll device + as a fractional value with three digit decimal precision. + Value of (DPLL_A_PHASE_OFFSET / DPLL_PHASE_OFFSET_DIVIDER) is an + integer part of a measured phase offset value. + Value of (DPLL_A_PHASE_OFFSET % DPLL_PHASE_OFFSET_DIVIDER) is a + fractional part of a measured phase offset value. attribute-sets: - @@ -272,6 +284,18 @@ attribute-sets: type: nest multi-attr: true nested-attributes: pin-parent-pin + - + name: phase-adjust-min + type: s32 + - + name: phase-adjust-max + type: s32 + - + name: phase-adjust + type: s32 + - + name: phase-offset + type: s64 - name: pin-parent-device subset-of: pin @@ -284,6 +308,8 @@ attribute-sets: name: prio - name: state + - + name: phase-offset - name: pin-parent-pin subset-of: pin @@ -431,6 +457,9 @@ operations: - capabilities - parent-device - parent-pin + - phase-adjust-min + - phase-adjust-max + - phase-adjust dump: pre: dpll-lock-dumpit @@ -458,6 +487,7 @@ operations: - state - parent-device - parent-pin + - phase-adjust - name: pin-create-ntf doc: Notification about pin appearing diff --git a/drivers/dpll/dpll_nl.c b/drivers/dpll/dpll_nl.c index 14064c8c783b..eaee5be7aa64 100644 --- a/drivers/dpll/dpll_nl.c +++ b/drivers/dpll/dpll_nl.c @@ -11,11 +11,12 @@ #include /* Common nested types */ -const struct nla_policy dpll_pin_parent_device_nl_policy[DPLL_A_PIN_STATE + 1] = { +const struct nla_policy dpll_pin_parent_device_nl_policy[DPLL_A_PIN_PHASE_OFFSET + 1] = { [DPLL_A_PIN_PARENT_ID] = { .type = NLA_U32, }, [DPLL_A_PIN_DIRECTION] = NLA_POLICY_RANGE(NLA_U32, 1, 2), [DPLL_A_PIN_PRIO] = { .type = NLA_U32, }, [DPLL_A_PIN_STATE] = NLA_POLICY_RANGE(NLA_U32, 1, 3), + [DPLL_A_PIN_PHASE_OFFSET] = { .type = NLA_S64, }, }; const struct nla_policy dpll_pin_parent_pin_nl_policy[DPLL_A_PIN_STATE + 1] = { @@ -61,7 +62,7 @@ static const struct nla_policy dpll_pin_get_dump_nl_policy[DPLL_A_PIN_ID + 1] = }; /* DPLL_CMD_PIN_SET - do */ -static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_PARENT_PIN + 1] = { +static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_PHASE_ADJUST + 1] = { [DPLL_A_PIN_ID] = { .type = NLA_U32, }, [DPLL_A_PIN_FREQUENCY] = { .type = NLA_U64, }, [DPLL_A_PIN_DIRECTION] = NLA_POLICY_RANGE(NLA_U32, 1, 2), @@ -69,6 +70,7 @@ static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_PARENT_PIN + 1] [DPLL_A_PIN_STATE] = NLA_POLICY_RANGE(NLA_U32, 1, 3), [DPLL_A_PIN_PARENT_DEVICE] = NLA_POLICY_NESTED(dpll_pin_parent_device_nl_policy), [DPLL_A_PIN_PARENT_PIN] = NLA_POLICY_NESTED(dpll_pin_parent_pin_nl_policy), + [DPLL_A_PIN_PHASE_ADJUST] = { .type = NLA_S32, }, }; /* Ops table for dpll */ @@ -140,7 +142,7 @@ static const struct genl_split_ops dpll_nl_ops[] = { .doit = dpll_nl_pin_set_doit, .post_doit = dpll_pin_post_doit, .policy = dpll_pin_set_nl_policy, - .maxattr = DPLL_A_PIN_PARENT_PIN, + .maxattr = DPLL_A_PIN_PHASE_ADJUST, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, }; diff --git a/drivers/dpll/dpll_nl.h b/drivers/dpll/dpll_nl.h index 1f67aaed4742..92d4c9c4f788 100644 --- a/drivers/dpll/dpll_nl.h +++ b/drivers/dpll/dpll_nl.h @@ -12,7 +12,7 @@ #include /* Common nested types */ -extern const struct nla_policy dpll_pin_parent_device_nl_policy[DPLL_A_PIN_STATE + 1]; +extern const struct nla_policy dpll_pin_parent_device_nl_policy[DPLL_A_PIN_PHASE_OFFSET + 1]; extern const struct nla_policy dpll_pin_parent_pin_nl_policy[DPLL_A_PIN_STATE + 1]; int dpll_lock_doit(const struct genl_split_ops *ops, struct sk_buff *skb, diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h index 20ef0718f8dc..715a491d2727 100644 --- a/include/uapi/linux/dpll.h +++ b/include/uapi/linux/dpll.h @@ -138,6 +138,8 @@ enum dpll_pin_capabilities { DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE = 4, }; +#define DPLL_PHASE_OFFSET_DIVIDER 1000 + enum dpll_a { DPLL_A_ID = 1, DPLL_A_MODULE_NAME, @@ -173,6 +175,10 @@ enum dpll_a_pin { DPLL_A_PIN_CAPABILITIES, DPLL_A_PIN_PARENT_DEVICE, DPLL_A_PIN_PARENT_PIN, + DPLL_A_PIN_PHASE_ADJUST_MIN, + DPLL_A_PIN_PHASE_ADJUST_MAX, + DPLL_A_PIN_PHASE_ADJUST, + DPLL_A_PIN_PHASE_OFFSET, __DPLL_A_PIN_MAX, DPLL_A_PIN_MAX = (__DPLL_A_PIN_MAX - 1) -- cgit From c5a445b1e9347b14752b01f1a304bd7a2f260acc Mon Sep 17 00:00:00 2001 From: Xabier Marquiegui Date: Thu, 12 Oct 2023 00:39:56 +0200 Subject: ptp: support event queue reader channel masks On systems with multiple timestamp event channels, some readers might want to receive only a subset of those channels. Add the necessary modifications to support timestamp event channel filtering, including two IOCTL operations: - Clear all channels - Enable one channel The mask modification operations will be applied exclusively on the event queue assigned to the file descriptor used on the IOCTL operation, so the typical procedure to have a reader receiving only a subset of the enabled channels would be: - Open device file - ioctl: clear all channels - ioctl: enable one channel - start reading Calling the enable one channel ioctl more than once will result in multiple enabled channels. Signed-off-by: Xabier Marquiegui Suggested-by: Richard Cochran Suggested-by: Vinicius Costa Gomes Signed-off-by: David S. Miller --- drivers/ptp/ptp_chardev.c | 26 ++++++++++++++++++++++++++ drivers/ptp/ptp_clock.c | 12 ++++++++++-- drivers/ptp/ptp_private.h | 3 +++ include/uapi/linux/ptp_clock.h | 2 ++ 4 files changed, 41 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index abe94bb80cf6..ac2f2b5ea0b7 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -110,6 +110,12 @@ int ptp_open(struct posix_clock_context *pccontext, fmode_t fmode) queue = kzalloc(sizeof(*queue), GFP_KERNEL); if (!queue) return -EINVAL; + queue->mask = bitmap_alloc(PTP_MAX_CHANNELS, GFP_KERNEL); + if (!queue->mask) { + kfree(queue); + return -EINVAL; + } + bitmap_set(queue->mask, 0, PTP_MAX_CHANNELS); spin_lock_init(&queue->lock); list_add_tail(&queue->qlist, &ptp->tsevqs); pccontext->private_clkdata = queue; @@ -126,6 +132,7 @@ int ptp_release(struct posix_clock_context *pccontext) spin_lock_irqsave(&queue->lock, flags); list_del(&queue->qlist); spin_unlock_irqrestore(&queue->lock, flags); + bitmap_free(queue->mask); kfree(queue); } return 0; @@ -141,6 +148,7 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd, struct system_device_crosststamp xtstamp; struct ptp_clock_info *ops = ptp->info; struct ptp_sys_offset *sysoff = NULL; + struct timestamp_event_queue *tsevq; struct ptp_system_timestamp sts; struct ptp_clock_request req; struct ptp_clock_caps caps; @@ -150,6 +158,8 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd, struct timespec64 ts; int enable, err = 0; + tsevq = pccontext->private_clkdata; + switch (cmd) { case PTP_CLOCK_GETCAPS: @@ -448,6 +458,22 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd, mutex_unlock(&ptp->pincfg_mux); break; + case PTP_MASK_CLEAR_ALL: + bitmap_clear(tsevq->mask, 0, PTP_MAX_CHANNELS); + break; + + case PTP_MASK_EN_SINGLE: + if (copy_from_user(&i, (void __user *)arg, sizeof(i))) { + err = -EFAULT; + break; + } + if (i >= PTP_MAX_CHANNELS) { + err = -EFAULT; + break; + } + set_bit(i, tsevq->mask); + break; + default: err = -ENOTTY; break; diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 74f1ce2dbccb..ed16d9787ce9 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -183,6 +183,7 @@ static void ptp_clock_release(struct device *dev) spin_lock_irqsave(&tsevq->lock, flags); list_del(&tsevq->qlist); spin_unlock_irqrestore(&tsevq->lock, flags); + bitmap_free(tsevq->mask); kfree(tsevq); ida_free(&ptp_clocks_map, ptp->index); kfree(ptp); @@ -243,6 +244,10 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, if (!queue) goto no_memory_queue; list_add_tail(&queue->qlist, &ptp->tsevqs); + queue->mask = bitmap_alloc(PTP_MAX_CHANNELS, GFP_KERNEL); + if (!queue->mask) + goto no_memory_bitmap; + bitmap_set(queue->mask, 0, PTP_MAX_CHANNELS); spin_lock_init(&queue->lock); mutex_init(&ptp->pincfg_mux); mutex_init(&ptp->n_vclocks_mux); @@ -346,6 +351,8 @@ no_mem_for_vclocks: kworker_err: mutex_destroy(&ptp->pincfg_mux); mutex_destroy(&ptp->n_vclocks_mux); + bitmap_free(queue->mask); +no_memory_bitmap: list_del(&queue->qlist); kfree(queue); no_memory_queue: @@ -400,9 +407,10 @@ void ptp_clock_event(struct ptp_clock *ptp, struct ptp_clock_event *event) break; case PTP_CLOCK_EXTTS: - /* Enqueue timestamp on all queues */ + /* Enqueue timestamp on selected queues */ list_for_each_entry(tsevq, &ptp->tsevqs, qlist) { - enqueue_external_timestamp(tsevq, event); + if (test_bit((unsigned int)event->index, tsevq->mask)) + enqueue_external_timestamp(tsevq, event); } wake_up_interruptible(&ptp->tsev_wq); break; diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index 9d5f3d95058e..ad4ce1b25c86 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -16,10 +16,12 @@ #include #include #include +#include #define PTP_MAX_TIMESTAMPS 128 #define PTP_BUF_TIMESTAMPS 30 #define PTP_DEFAULT_MAX_VCLOCKS 20 +#define PTP_MAX_CHANNELS 2048 struct timestamp_event_queue { struct ptp_extts_event buf[PTP_MAX_TIMESTAMPS]; @@ -27,6 +29,7 @@ struct timestamp_event_queue { int tail; spinlock_t lock; struct list_head qlist; + unsigned long *mask; }; struct ptp_clock { diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h index 05cc35fc94ac..da700999cad4 100644 --- a/include/uapi/linux/ptp_clock.h +++ b/include/uapi/linux/ptp_clock.h @@ -224,6 +224,8 @@ struct ptp_pin_desc { _IOWR(PTP_CLK_MAGIC, 17, struct ptp_sys_offset_precise) #define PTP_SYS_OFFSET_EXTENDED2 \ _IOWR(PTP_CLK_MAGIC, 18, struct ptp_sys_offset_extended) +#define PTP_MASK_CLEAR_ALL _IO(PTP_CLK_MAGIC, 19) +#define PTP_MASK_EN_SINGLE _IOW(PTP_CLK_MAGIC, 20, unsigned int) struct ptp_extts_event { struct ptp_clock_time t; /* Time event occured. */ -- cgit From c68ab8b5ea53aa0895f7ec5b72c87e0f7097761e Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 15 Sep 2023 10:53:18 +0200 Subject: media: uapi: Add MEDIA_BUS_FMT_RGB666_2X9_BE format Add the RGB666 9:9 format MEDIA_BUS_FMT_RGB666_2X9_BE, which is supported by the SH-Mobile LCD Controller. Reviewed-by: Laurent Pinchart Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/8b421cc391ac511c07cb1e243c1ba18bb95f7f98.1694767209.git.geert+renesas@glider.be --- .../userspace-api/media/v4l/subdev-formats.rst | 72 ++++++++++++++++++++++ include/uapi/linux/media-bus-format.h | 3 +- 2 files changed, 74 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/subdev-formats.rst b/Documentation/userspace-api/media/v4l/subdev-formats.rst index a3a35eeed708..eb3cd20b0cf2 100644 --- a/Documentation/userspace-api/media/v4l/subdev-formats.rst +++ b/Documentation/userspace-api/media/v4l/subdev-formats.rst @@ -949,6 +949,78 @@ The following tables list existing packed RGB formats. - b\ :sub:`2` - b\ :sub:`1` - b\ :sub:`0` + * .. _MEDIA-BUS-FMT-RGB666-2X9-BE: + + - MEDIA_BUS_FMT_RGB666_2X9_BE + - 0x1025 + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - r\ :sub:`5` + - r\ :sub:`4` + - r\ :sub:`3` + - r\ :sub:`2` + - r\ :sub:`1` + - r\ :sub:`0` + - g\ :sub:`5` + - g\ :sub:`4` + - g\ :sub:`3` + * - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - g\ :sub:`2` + - g\ :sub:`1` + - g\ :sub:`0` + - b\ :sub:`5` + - b\ :sub:`4` + - b\ :sub:`3` + - b\ :sub:`2` + - b\ :sub:`1` + - b\ :sub:`0` * .. _MEDIA-BUS-FMT-BGR666-1X18: - MEDIA_BUS_FMT_BGR666_1X18 diff --git a/include/uapi/linux/media-bus-format.h b/include/uapi/linux/media-bus-format.h index a03c543cb072..f05f747e444d 100644 --- a/include/uapi/linux/media-bus-format.h +++ b/include/uapi/linux/media-bus-format.h @@ -34,7 +34,7 @@ #define MEDIA_BUS_FMT_FIXED 0x0001 -/* RGB - next is 0x1025 */ +/* RGB - next is 0x1026 */ #define MEDIA_BUS_FMT_RGB444_1X12 0x1016 #define MEDIA_BUS_FMT_RGB444_2X8_PADHI_BE 0x1001 #define MEDIA_BUS_FMT_RGB444_2X8_PADHI_LE 0x1002 @@ -46,6 +46,7 @@ #define MEDIA_BUS_FMT_RGB565_2X8_BE 0x1007 #define MEDIA_BUS_FMT_RGB565_2X8_LE 0x1008 #define MEDIA_BUS_FMT_RGB666_1X18 0x1009 +#define MEDIA_BUS_FMT_RGB666_2X9_BE 0x1025 #define MEDIA_BUS_FMT_BGR666_1X18 0x1023 #define MEDIA_BUS_FMT_RBG888_1X24 0x100e #define MEDIA_BUS_FMT_RGB666_1X24_CPADHI 0x1015 -- cgit From 7904cdf1397c9391178ce53a7ebfa099c6bc4a59 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Tue, 29 Aug 2023 15:40:23 +0200 Subject: counter: chrdev: remove a typo in header file comment Replace COUNTER_COUNT_SCOPE that doesn't exist by the defined COUNTER_SCOPE_COUNT. Signed-off-by: Fabrice Gasnier Link: https://lore.kernel.org/r/20230829134029.2402868-3-fabrice.gasnier@foss.st.com Signed-off-by: William Breathitt Gray --- include/uapi/linux/counter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/counter.h b/include/uapi/linux/counter.h index fc248ef00e86..008a691c254b 100644 --- a/include/uapi/linux/counter.h +++ b/include/uapi/linux/counter.h @@ -38,7 +38,7 @@ enum counter_scope { * * For example, if the Count 2 ceiling extension of Counter device 4 is desired, * set type equal to COUNTER_COMPONENT_EXTENSION, scope equal to - * COUNTER_COUNT_SCOPE, parent equal to 2, and id equal to the value provided by + * COUNTER_SCOPE_COUNT, parent equal to 2, and id equal to the value provided by * the respective /sys/bus/counter/devices/counter4/count2/ceiling_component_id * sysfs attribute. */ -- cgit From 13727f85b49babcc40db805118e665605cd040dc Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 11 Sep 2023 14:49:44 +0200 Subject: NFSD: introduce netlink stubs Generate stubs and uAPI for nfsd netlink protocol. For the moment, the new protocol has one operation: rpc_status. The generated header and source files are created by running: tools/net/ynl/ynl-regen.sh Tested-by: Jeff Layton Signed-off-by: Lorenzo Bianconi Acked-by: Jeff Layton Signed-off-by: Chuck Lever --- Documentation/netlink/specs/nfsd.yaml | 89 +++++++++++++++++++++++++++++++++++ fs/nfsd/Makefile | 3 +- fs/nfsd/netlink.c | 32 +++++++++++++ fs/nfsd/netlink.h | 22 +++++++++ fs/nfsd/nfsctl.c | 17 +++++++ include/uapi/linux/nfsd_netlink.h | 39 +++++++++++++++ 6 files changed, 201 insertions(+), 1 deletion(-) create mode 100644 Documentation/netlink/specs/nfsd.yaml create mode 100644 fs/nfsd/netlink.c create mode 100644 fs/nfsd/netlink.h create mode 100644 include/uapi/linux/nfsd_netlink.h (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml new file mode 100644 index 000000000000..05acc73e2e33 --- /dev/null +++ b/Documentation/netlink/specs/nfsd.yaml @@ -0,0 +1,89 @@ +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) + +name: nfsd +protocol: genetlink +uapi-header: linux/nfsd_netlink.h + +doc: NFSD configuration over generic netlink. + +attribute-sets: + - + name: rpc-status + attributes: + - + name: xid + type: u32 + byte-order: big-endian + - + name: flags + type: u32 + - + name: prog + type: u32 + - + name: version + type: u8 + - + name: proc + type: u32 + - + name: service_time + type: s64 + - + name: pad + type: pad + - + name: saddr4 + type: u32 + byte-order: big-endian + display-hint: ipv4 + - + name: daddr4 + type: u32 + byte-order: big-endian + display-hint: ipv4 + - + name: saddr6 + type: binary + display-hint: ipv6 + - + name: daddr6 + type: binary + display-hint: ipv6 + - + name: sport + type: u16 + byte-order: big-endian + - + name: dport + type: u16 + byte-order: big-endian + - + name: compound-ops + type: u32 + multi-attr: true + +operations: + list: + - + name: rpc-status-get + doc: dump pending nfsd rpc + attribute-set: rpc-status + dump: + pre: nfsd-nl-rpc-status-get-start + post: nfsd-nl-rpc-status-get-done + reply: + attributes: + - xid + - flags + - prog + - version + - proc + - service_time + - saddr4 + - daddr4 + - saddr6 + - daddr6 + - sport + - dport + - compound-ops diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile index 6fffc8f03f74..b8736a82e57c 100644 --- a/fs/nfsd/Makefile +++ b/fs/nfsd/Makefile @@ -12,7 +12,8 @@ nfsd-y += trace.o nfsd-y += nfssvc.o nfsctl.o nfsfh.o vfs.o \ export.o auth.o lockd.o nfscache.o \ - stats.o filecache.o nfs3proc.o nfs3xdr.o + stats.o filecache.o nfs3proc.o nfs3xdr.o \ + netlink.o nfsd-$(CONFIG_NFSD_V2) += nfsproc.o nfsxdr.o nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o diff --git a/fs/nfsd/netlink.c b/fs/nfsd/netlink.c new file mode 100644 index 000000000000..0e1d635ec5f9 --- /dev/null +++ b/fs/nfsd/netlink.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/nfsd.yaml */ +/* YNL-GEN kernel source */ + +#include +#include + +#include "netlink.h" + +#include + +/* Ops table for nfsd */ +static const struct genl_split_ops nfsd_nl_ops[] = { + { + .cmd = NFSD_CMD_RPC_STATUS_GET, + .start = nfsd_nl_rpc_status_get_start, + .dumpit = nfsd_nl_rpc_status_get_dumpit, + .done = nfsd_nl_rpc_status_get_done, + .flags = GENL_CMD_CAP_DUMP, + }, +}; + +struct genl_family nfsd_nl_family __ro_after_init = { + .name = NFSD_FAMILY_NAME, + .version = NFSD_FAMILY_VERSION, + .netnsok = true, + .parallel_ops = true, + .module = THIS_MODULE, + .split_ops = nfsd_nl_ops, + .n_split_ops = ARRAY_SIZE(nfsd_nl_ops), +}; diff --git a/fs/nfsd/netlink.h b/fs/nfsd/netlink.h new file mode 100644 index 000000000000..d83dd6bdee92 --- /dev/null +++ b/fs/nfsd/netlink.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/nfsd.yaml */ +/* YNL-GEN kernel header */ + +#ifndef _LINUX_NFSD_GEN_H +#define _LINUX_NFSD_GEN_H + +#include +#include + +#include + +int nfsd_nl_rpc_status_get_start(struct netlink_callback *cb); +int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb); + +int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); + +extern struct genl_family nfsd_nl_family; + +#endif /* _LINUX_NFSD_GEN_H */ diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 7ed02fb88a36..364ccd0be1c1 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -26,6 +26,7 @@ #include "pnfs.h" #include "filecache.h" #include "trace.h" +#include "netlink.h" /* * We have a single directory with several nodes in it. @@ -1495,6 +1496,22 @@ static int create_proc_exports_entry(void) unsigned int nfsd_net_id; +int nfsd_nl_rpc_status_get_start(struct netlink_callback *cb) +{ + return 0; +} + +int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return 0; +} + +int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb) +{ + return 0; +} + /** * nfsd_net_init - Prepare the nfsd_net portion of a new net namespace * @net: a freshly-created network namespace diff --git a/include/uapi/linux/nfsd_netlink.h b/include/uapi/linux/nfsd_netlink.h new file mode 100644 index 000000000000..c8ae72466ee6 --- /dev/null +++ b/include/uapi/linux/nfsd_netlink.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/nfsd.yaml */ +/* YNL-GEN uapi header */ + +#ifndef _UAPI_LINUX_NFSD_H +#define _UAPI_LINUX_NFSD_H + +#define NFSD_FAMILY_NAME "nfsd" +#define NFSD_FAMILY_VERSION 1 + +enum { + NFSD_A_RPC_STATUS_XID = 1, + NFSD_A_RPC_STATUS_FLAGS, + NFSD_A_RPC_STATUS_PROG, + NFSD_A_RPC_STATUS_VERSION, + NFSD_A_RPC_STATUS_PROC, + NFSD_A_RPC_STATUS_SERVICE_TIME, + NFSD_A_RPC_STATUS_PAD, + NFSD_A_RPC_STATUS_SADDR4, + NFSD_A_RPC_STATUS_DADDR4, + NFSD_A_RPC_STATUS_SADDR6, + NFSD_A_RPC_STATUS_DADDR6, + NFSD_A_RPC_STATUS_SPORT, + NFSD_A_RPC_STATUS_DPORT, + NFSD_A_RPC_STATUS_COMPOUND_OPS, + + __NFSD_A_RPC_STATUS_MAX, + NFSD_A_RPC_STATUS_MAX = (__NFSD_A_RPC_STATUS_MAX - 1) +}; + +enum { + NFSD_CMD_RPC_STATUS_GET = 1, + + __NFSD_CMD_MAX, + NFSD_CMD_MAX = (__NFSD_CMD_MAX - 1) +}; + +#endif /* _UAPI_LINUX_NFSD_H */ -- cgit From ddd1ad68826d8ff61a2e47733959570aa4d39a16 Mon Sep 17 00:00:00 2001 From: Johannes Nixdorf Date: Mon, 16 Oct 2023 15:27:22 +0200 Subject: net: bridge: Add netlink knobs for number / max learned FDB entries The previous patch added accounting and a limit for the number of dynamically learned FDB entries per bridge. However it did not provide means to actually configure those bounds or read back the count. This patch does that. Two new netlink attributes are added for the accounting and limit of dynamically learned FDB entries: - IFLA_BR_FDB_N_LEARNED (RO) for the number of entries accounted for a single bridge. - IFLA_BR_FDB_MAX_LEARNED (RW) for the configured limit of entries for the bridge. The new attributes are used like this: # ip link add name br up type bridge fdb_max_learned 256 # ip link add name v1 up master br type veth peer v2 # ip link set up dev v2 # mausezahn -a rand -c 1024 v2 0.01 seconds (90877 packets per second # bridge fdb | grep -v permanent | wc -l 256 # ip -d link show dev br 13: br: mtu 1500 [...] [...] fdb_n_learned 256 fdb_max_learned 256 Signed-off-by: Johannes Nixdorf Acked-by: Nikolay Aleksandrov Reviewed-by: Ido Schimmel Link: https://lore.kernel.org/r/20231016-fdb_limit-v5-3-32cddff87758@avm.de Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_link.h | 2 ++ net/bridge/br_netlink.c | 15 ++++++++++++++- 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index fac351a93aed..9f8a3da0f14f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -510,6 +510,8 @@ enum { IFLA_BR_VLAN_STATS_PER_PORT, IFLA_BR_MULTI_BOOLOPT, IFLA_BR_MCAST_QUERIER_STATE, + IFLA_BR_FDB_N_LEARNED, + IFLA_BR_FDB_MAX_LEARNED, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 10f0d33d8ccf..0c3cf6e6dea2 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1265,6 +1265,8 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_VLAN_STATS_PER_PORT] = { .type = NLA_U8 }, [IFLA_BR_MULTI_BOOLOPT] = NLA_POLICY_EXACT_LEN(sizeof(struct br_boolopt_multi)), + [IFLA_BR_FDB_N_LEARNED] = { .type = NLA_REJECT }, + [IFLA_BR_FDB_MAX_LEARNED] = { .type = NLA_U32 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -1539,6 +1541,12 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], return err; } + if (data[IFLA_BR_FDB_MAX_LEARNED]) { + u32 val = nla_get_u32(data[IFLA_BR_FDB_MAX_LEARNED]); + + WRITE_ONCE(br->fdb_max_learned, val); + } + return 0; } @@ -1593,6 +1601,8 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_TOPOLOGY_CHANGE_TIMER */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_GC_TIMER */ nla_total_size(ETH_ALEN) + /* IFLA_BR_GROUP_ADDR */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_FDB_N_LEARNED */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_FDB_MAX_LEARNED */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_ROUTER */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */ @@ -1668,7 +1678,10 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE_DETECTED, br->topology_change_detected) || nla_put(skb, IFLA_BR_GROUP_ADDR, ETH_ALEN, br->group_addr) || - nla_put(skb, IFLA_BR_MULTI_BOOLOPT, sizeof(bm), &bm)) + nla_put(skb, IFLA_BR_MULTI_BOOLOPT, sizeof(bm), &bm) || + nla_put_u32(skb, IFLA_BR_FDB_N_LEARNED, + atomic_read(&br->fdb_n_learned)) || + nla_put_u32(skb, IFLA_BR_FDB_MAX_LEARNED, br->fdb_max_learned)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING -- cgit From d61ea1cb009532dcbd77a9d44b812704cec60146 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 21 Aug 2023 19:15:13 +0500 Subject: userfaultfd: UFFD_FEATURE_WP_ASYNC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "Implement IOCTL to get and optionally clear info about PTEs", v33. *Motivation* The real motivation for adding PAGEMAP_SCAN IOCTL is to emulate Windows GetWriteWatch() and ResetWriteWatch() syscalls [1]. The GetWriteWatch() retrieves the addresses of the pages that are written to in a region of virtual memory. This syscall is used in Windows applications and games etc. This syscall is being emulated in pretty slow manner in userspace. Our purpose is to enhance the kernel such that we translate it efficiently in a better way. Currently some out of tree hack patches are being used to efficiently emulate it in some kernels. We intend to replace those with these patches. So the whole gaming on Linux can effectively get benefit from this. It means there would be tons of users of this code. CRIU use case [2] was mentioned by Andrei and Danylo: > Use cases for migrating sparse VMAs are binaries sanitized with ASAN, > MSAN or TSAN [3]. All of these sanitizers produce sparse mappings of > shadow memory [4]. Being able to migrate such binaries allows to highly > reduce the amount of work needed to identify and fix post-migration > crashes, which happen constantly. Andrei defines the following uses of this code: * it is more granular and allows us to track changed pages more effectively. The current interface can clear dirty bits for the entire process only. In addition, reading info about pages is a separate operation. It means we must freeze the process to read information about all its pages, reset dirty bits, only then we can start dumping pages. The information about pages becomes more and more outdated, while we are processing pages. The new interface solves both these downsides. First, it allows us to read pte bits and clear the soft-dirty bit atomically. It means that CRIU will not need to freeze processes to pre-dump their memory. Second, it clears soft-dirty bits for a specified region of memory. It means CRIU will have actual info about pages to the moment of dumping them. * The new interface has to be much faster because basic page filtering is happening in the kernel. With the old interface, we have to read pagemap for each page. *Implementation Evolution (Short Summary)* From the definition of GetWriteWatch(), we feel like kernel's soft-dirty feature can be used under the hood with some additions like: * reset soft-dirty flag for only a specific region of memory instead of clearing the flag for the entire process * get and clear soft-dirty flag for a specific region atomically So we decided to use ioctl on pagemap file to read or/and reset soft-dirty flag. But using soft-dirty flag, sometimes we get extra pages which weren't even written. They had become soft-dirty because of VMA merging and VM_SOFTDIRTY flag. This breaks the definition of GetWriteWatch(). We were able to by-pass this short coming by ignoring VM_SOFTDIRTY until David reported that mprotect etc messes up the soft-dirty flag while ignoring VM_SOFTDIRTY [5]. This wasn't happening until [6] got introduced. We discussed if we can revert these patches. But we could not reach to any conclusion. So at this point, I made couple of tries to solve this whole VM_SOFTDIRTY issue by correcting the soft-dirty implementation: * [7] Correct the bug fixed wrongly back in 2014. It had potential to cause regression. We left it behind. * [8] Keep a list of soft-dirty part of a VMA across splits and merges. I got the reply don't increase the size of the VMA by 8 bytes. At this point, we left soft-dirty considering it is too much delicate and userfaultfd [9] seemed like the only way forward. From there onward, we have been basing soft-dirty emulation on userfaultfd wp feature where kernel resolves the faults itself when WP_ASYNC feature is used. It was straight forward to add WP_ASYNC feature in userfautlfd. Now we get only those pages dirty or written-to which are really written in reality. (PS There is another WP_UNPOPULATED userfautfd feature is required which is needed to avoid pre-faulting memory before write-protecting [9].) All the different masks were added on the request of CRIU devs to create interface more generic and better. [1] https://learn.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-getwritewatch [2] https://lore.kernel.org/all/20221014134802.1361436-1-mdanylo@google.com [3] https://github.com/google/sanitizers [4] https://github.com/google/sanitizers/wiki/AddressSanitizerAlgorithm#64-bit [5] https://lore.kernel.org/all/bfcae708-db21-04b4-0bbe-712badd03071@redhat.com [6] https://lore.kernel.org/all/20220725142048.30450-1-peterx@redhat.com/ [7] https://lore.kernel.org/all/20221122115007.2787017-1-usama.anjum@collabora.com [8] https://lore.kernel.org/all/20221220162606.1595355-1-usama.anjum@collabora.com [9] https://lore.kernel.org/all/20230306213925.617814-1-peterx@redhat.com [10] https://lore.kernel.org/all/20230125144529.1630917-1-mdanylo@google.com This patch (of 6): Add a new userfaultfd-wp feature UFFD_FEATURE_WP_ASYNC, that allows userfaultfd wr-protect faults to be resolved by the kernel directly. It can be used like a high accuracy version of soft-dirty, without vma modifications during tracking, and also with ranged support by default rather than for a whole mm when reset the protections due to existence of ioctl(UFFDIO_WRITEPROTECT). Several goals of such a dirty tracking interface: 1. All types of memory should be supported and tracable. This is nature for soft-dirty but should mention when the context is userfaultfd, because it used to only support anon/shmem/hugetlb. The problem is for a dirty tracking purpose these three types may not be enough, and it's legal to track anything e.g. any page cache writes from mmap. 2. Protections can be applied to partial of a memory range, without vma split/merge fuss. The hope is that the tracking itself should not affect any vma layout change. It also helps when reset happens because the reset will not need mmap write lock which can block the tracee. 3. Accuracy needs to be maintained. This means we need pte markers to work on any type of VMA. One could question that, the whole concept of async dirty tracking is not really close to fundamentally what userfaultfd used to be: it's not "a fault to be serviced by userspace" anymore. However, using userfaultfd-wp here as a framework is convenient for us in at least: 1. VM_UFFD_WP vma flag, which has a very good name to suite something like this, so we don't need VM_YET_ANOTHER_SOFT_DIRTY. Just use a new feature bit to identify from a sync version of uffd-wp registration. 2. PTE markers logic can be leveraged across the whole kernel to maintain the uffd-wp bit as long as an arch supports, this also applies to this case where uffd-wp bit will be a hint to dirty information and it will not go lost easily (e.g. when some page cache ptes got zapped). 3. Reuse ioctl(UFFDIO_WRITEPROTECT) interface for either starting or resetting a range of memory, while there's no counterpart in the old soft-dirty world, hence if this is wanted in a new design we'll need a new interface otherwise. We can somehow understand that commonality because uffd-wp was fundamentally a similar idea of write-protecting pages just like soft-dirty. This implementation allows WP_ASYNC to imply WP_UNPOPULATED, because so far WP_ASYNC seems to not usable if without WP_UNPOPULATE. This also gives us chance to modify impl of WP_ASYNC just in case it could be not depending on WP_UNPOPULATED anymore in the future kernels. It's also fine to imply that because both features will rely on PTE_MARKER_UFFD_WP config option, so they'll show up together (or both missing) in an UFFDIO_API probe. vma_can_userfault() now allows any VMA if the userfaultfd registration is only about async uffd-wp. So we can track dirty for all kinds of memory including generic file systems (like XFS, EXT4 or BTRFS). One trick worth mention in do_wp_page() is that we need to manually update vmf->orig_pte here because it can be used later with a pte_same() check - this path always has FAULT_FLAG_ORIG_PTE_VALID set in the flags. The major defect of this approach of dirty tracking is we need to populate the pgtables when tracking starts. Soft-dirty doesn't do it like that. It's unwanted in the case where the range of memory to track is huge and unpopulated (e.g., tracking updates on a 10G file with mmap() on top, without having any page cache installed yet). One way to improve this is to allow pte markers exist for larger than PTE level for PMD+. That will not change the interface if to implemented, so we can leave that for later. Link: https://lkml.kernel.org/r/20230821141518.870589-1-usama.anjum@collabora.com Link: https://lkml.kernel.org/r/20230821141518.870589-2-usama.anjum@collabora.com Signed-off-by: Peter Xu Co-developed-by: Muhammad Usama Anjum Signed-off-by: Muhammad Usama Anjum Cc: Alex Sierra Cc: Al Viro Cc: Andrei Vagin Cc: Axel Rasmussen Cc: Christian Brauner Cc: Cyrill Gorcunov Cc: Dan Williams Cc: David Hildenbrand Cc: Greg Kroah-Hartman Cc: Gustavo A. R. Silva Cc: "Liam R. Howlett" Cc: Matthew Wilcox Cc: Michal Miroslaw Cc: Mike Rapoport (IBM) Cc: Nadav Amit Cc: Pasha Tatashin Cc: Paul Gofman Cc: Shuah Khan Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Yang Shi Cc: Yun Zhou Cc: Michał Mirosław Signed-off-by: Andrew Morton --- Documentation/admin-guide/mm/userfaultfd.rst | 35 ++++++++++++++++++++++++++++ fs/userfaultfd.c | 26 +++++++++++++++++---- include/linux/userfaultfd_k.h | 21 ++++++++++++++++- include/uapi/linux/userfaultfd.h | 9 ++++++- mm/hugetlb.c | 32 ++++++++++++++----------- mm/memory.c | 28 +++++++++++++++++++--- 6 files changed, 129 insertions(+), 22 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/admin-guide/mm/userfaultfd.rst b/Documentation/admin-guide/mm/userfaultfd.rst index 4349a8c2b978..203e26da5f92 100644 --- a/Documentation/admin-guide/mm/userfaultfd.rst +++ b/Documentation/admin-guide/mm/userfaultfd.rst @@ -244,6 +244,41 @@ write-protected (so future writes will also result in a WP fault). These ioctls support a mode flag (``UFFDIO_COPY_MODE_WP`` or ``UFFDIO_CONTINUE_MODE_WP`` respectively) to configure the mapping this way. +If the userfaultfd context has ``UFFD_FEATURE_WP_ASYNC`` feature bit set, +any vma registered with write-protection will work in async mode rather +than the default sync mode. + +In async mode, there will be no message generated when a write operation +happens, meanwhile the write-protection will be resolved automatically by +the kernel. It can be seen as a more accurate version of soft-dirty +tracking and it can be different in a few ways: + + - The dirty result will not be affected by vma changes (e.g. vma + merging) because the dirty is only tracked by the pte. + + - It supports range operations by default, so one can enable tracking on + any range of memory as long as page aligned. + + - Dirty information will not get lost if the pte was zapped due to + various reasons (e.g. during split of a shmem transparent huge page). + + - Due to a reverted meaning of soft-dirty (page clean when uffd-wp bit + set; dirty when uffd-wp bit cleared), it has different semantics on + some of the memory operations. For example: ``MADV_DONTNEED`` on + anonymous (or ``MADV_REMOVE`` on a file mapping) will be treated as + dirtying of memory by dropping uffd-wp bit during the procedure. + +The user app can collect the "written/dirty" status by looking up the +uffd-wp bit for the pages being interested in /proc/pagemap. + +The page will not be under track of uffd-wp async mode until the page is +explicitly write-protected by ``ioctl(UFFDIO_WRITEPROTECT)`` with the mode +flag ``UFFDIO_WRITEPROTECT_MODE_WP`` set. Trying to resolve a page fault +that was tracked by async mode userfaultfd-wp is invalid. + +When userfaultfd-wp async mode is used alone, it can be applied to all +kinds of memory. + Memory Poisioning Emulation --------------------------- diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 56eaae9dac1a..a7c6ef764e63 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -123,6 +123,11 @@ static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx) return ctx->features & UFFD_FEATURE_INITIALIZED; } +static bool userfaultfd_wp_async_ctx(struct userfaultfd_ctx *ctx) +{ + return ctx && (ctx->features & UFFD_FEATURE_WP_ASYNC); +} + /* * Whether WP_UNPOPULATED is enabled on the uffd context. It is only * meaningful when userfaultfd_wp()==true on the vma and when it's @@ -1325,6 +1330,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, bool basic_ioctls; unsigned long start, end, vma_end; struct vma_iterator vmi; + bool wp_async = userfaultfd_wp_async_ctx(ctx); pgoff_t pgoff; user_uffdio_register = (struct uffdio_register __user *) arg; @@ -1399,7 +1405,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, /* check not compatible vmas */ ret = -EINVAL; - if (!vma_can_userfault(cur, vm_flags)) + if (!vma_can_userfault(cur, vm_flags, wp_async)) goto out_unlock; /* @@ -1460,7 +1466,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, for_each_vma_range(vmi, vma, end) { cond_resched(); - BUG_ON(!vma_can_userfault(vma, vm_flags)); + BUG_ON(!vma_can_userfault(vma, vm_flags, wp_async)); BUG_ON(vma->vm_userfaultfd_ctx.ctx && vma->vm_userfaultfd_ctx.ctx != ctx); WARN_ON(!(vma->vm_flags & VM_MAYWRITE)); @@ -1561,6 +1567,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, unsigned long start, end, vma_end; const void __user *buf = (void __user *)arg; struct vma_iterator vmi; + bool wp_async = userfaultfd_wp_async_ctx(ctx); pgoff_t pgoff; ret = -EFAULT; @@ -1615,7 +1622,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, * provides for more strict behavior to notice * unregistration errors. */ - if (!vma_can_userfault(cur, cur->vm_flags)) + if (!vma_can_userfault(cur, cur->vm_flags, wp_async)) goto out_unlock; found = true; @@ -1631,7 +1638,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, for_each_vma_range(vmi, vma, end) { cond_resched(); - BUG_ON(!vma_can_userfault(vma, vma->vm_flags)); + BUG_ON(!vma_can_userfault(vma, vma->vm_flags, wp_async)); /* * Nothing to do: this vma is already registered into this @@ -2018,6 +2025,11 @@ out: return ret; } +bool userfaultfd_wp_async(struct vm_area_struct *vma) +{ + return userfaultfd_wp_async_ctx(vma->vm_userfaultfd_ctx.ctx); +} + static inline unsigned int uffd_ctx_features(__u64 user_features) { /* @@ -2051,6 +2063,11 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, ret = -EPERM; if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE)) goto err_out; + + /* WP_ASYNC relies on WP_UNPOPULATED, choose it unconditionally */ + if (features & UFFD_FEATURE_WP_ASYNC) + features |= UFFD_FEATURE_WP_UNPOPULATED; + /* report all available features and ioctls to userland */ uffdio_api.features = UFFD_API_FEATURES; #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR @@ -2063,6 +2080,7 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, #ifndef CONFIG_PTE_MARKER_UFFD_WP uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM; uffdio_api.features &= ~UFFD_FEATURE_WP_UNPOPULATED; + uffdio_api.features &= ~UFFD_FEATURE_WP_ASYNC; #endif uffdio_api.ioctls = UFFD_API_IOCTLS; ret = -EFAULT; diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index ac8c6854097c..c98df391bfd8 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -161,11 +161,22 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma) } static inline bool vma_can_userfault(struct vm_area_struct *vma, - unsigned long vm_flags) + unsigned long vm_flags, + bool wp_async) { + vm_flags &= __VM_UFFD_FLAGS; + if ((vm_flags & VM_UFFD_MINOR) && (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma))) return false; + + /* + * If wp async enabled, and WP is the only mode enabled, allow any + * memory type. + */ + if (wp_async && (vm_flags == VM_UFFD_WP)) + return true; + #ifndef CONFIG_PTE_MARKER_UFFD_WP /* * If user requested uffd-wp but not enabled pte markers for @@ -175,6 +186,8 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, if ((vm_flags & VM_UFFD_WP) && !vma_is_anonymous(vma)) return false; #endif + + /* By default, allow any of anon|shmem|hugetlb */ return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) || vma_is_shmem(vma); } @@ -197,6 +210,7 @@ extern int userfaultfd_unmap_prep(struct vm_area_struct *vma, extern void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf); extern bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma); +extern bool userfaultfd_wp_async(struct vm_area_struct *vma); #else /* CONFIG_USERFAULTFD */ @@ -297,6 +311,11 @@ static inline bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma) return false; } +static inline bool userfaultfd_wp_async(struct vm_area_struct *vma) +{ + return false; +} + #endif /* CONFIG_USERFAULTFD */ static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma) diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 62151706c5a3..0dbc81015018 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -40,7 +40,8 @@ UFFD_FEATURE_EXACT_ADDRESS | \ UFFD_FEATURE_WP_HUGETLBFS_SHMEM | \ UFFD_FEATURE_WP_UNPOPULATED | \ - UFFD_FEATURE_POISON) + UFFD_FEATURE_POISON | \ + UFFD_FEATURE_WP_ASYNC) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -216,6 +217,11 @@ struct uffdio_api { * (i.e. empty ptes). This will be the default behavior for shmem * & hugetlbfs, so this flag only affects anonymous memory behavior * when userfault write-protection mode is registered. + * + * UFFD_FEATURE_WP_ASYNC indicates that userfaultfd write-protection + * asynchronous mode is supported in which the write fault is + * automatically resolved and write-protection is un-set. + * It implies UFFD_FEATURE_WP_UNPOPULATED. */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) @@ -232,6 +238,7 @@ struct uffdio_api { #define UFFD_FEATURE_WP_HUGETLBFS_SHMEM (1<<12) #define UFFD_FEATURE_WP_UNPOPULATED (1<<13) #define UFFD_FEATURE_POISON (1<<14) +#define UFFD_FEATURE_WP_ASYNC (1<<15) __u64 features; __u64 ioctls; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index dfb4534834f5..bc654b36df9f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6247,21 +6247,27 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, /* Handle userfault-wp first, before trying to lock more pages */ if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(ptep)) && (flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) { - struct vm_fault vmf = { - .vma = vma, - .address = haddr, - .real_address = address, - .flags = flags, - }; + if (!userfaultfd_wp_async(vma)) { + struct vm_fault vmf = { + .vma = vma, + .address = haddr, + .real_address = address, + .flags = flags, + }; - spin_unlock(ptl); - if (pagecache_folio) { - folio_unlock(pagecache_folio); - folio_put(pagecache_folio); + spin_unlock(ptl); + if (pagecache_folio) { + folio_unlock(pagecache_folio); + folio_put(pagecache_folio); + } + hugetlb_vma_unlock_read(vma); + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + return handle_userfault(&vmf, VM_UFFD_WP); } - hugetlb_vma_unlock_read(vma); - mutex_unlock(&hugetlb_fault_mutex_table[hash]); - return handle_userfault(&vmf, VM_UFFD_WP); + + entry = huge_pte_clear_uffd_wp(entry); + set_huge_pte_at(mm, haddr, ptep, entry); + /* Fallthrough to CoW */ } /* diff --git a/mm/memory.c b/mm/memory.c index 2d209bc4d18c..d0f61d729fb4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1,3 +1,4 @@ + // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/memory.c @@ -3349,11 +3350,28 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; struct vm_area_struct *vma = vmf->vma; struct folio *folio = NULL; + pte_t pte; if (likely(!unshare)) { if (userfaultfd_pte_wp(vma, ptep_get(vmf->pte))) { - pte_unmap_unlock(vmf->pte, vmf->ptl); - return handle_userfault(vmf, VM_UFFD_WP); + if (!userfaultfd_wp_async(vma)) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return handle_userfault(vmf, VM_UFFD_WP); + } + + /* + * Nothing needed (cache flush, TLB invalidations, + * etc.) because we're only removing the uffd-wp bit, + * which is completely invisible to the user. + */ + pte = pte_clear_uffd_wp(ptep_get(vmf->pte)); + + set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); + /* + * Update this to be prepared for following up CoW + * handling + */ + vmf->orig_pte = pte; } /* @@ -4879,8 +4897,11 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf) if (vma_is_anonymous(vma)) { if (likely(!unshare) && - userfaultfd_huge_pmd_wp(vma, vmf->orig_pmd)) + userfaultfd_huge_pmd_wp(vma, vmf->orig_pmd)) { + if (userfaultfd_wp_async(vmf->vma)) + goto split; return handle_userfault(vmf, VM_UFFD_WP); + } return do_huge_pmd_wp_page(vmf); } @@ -4892,6 +4913,7 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf) } } +split: /* COW or write-notify handled on pte level: split pmd. */ __split_huge_pmd(vma, vmf->pmd, vmf->address, false, NULL); -- cgit From 52526ca7fdb905a768a93f8faa418e9b988fc34b Mon Sep 17 00:00:00 2001 From: Muhammad Usama Anjum Date: Mon, 21 Aug 2023 19:15:14 +0500 Subject: fs/proc/task_mmu: implement IOCTL to get and optionally clear info about PTEs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The PAGEMAP_SCAN IOCTL on the pagemap file can be used to get or optionally clear the info about page table entries. The following operations are supported in this IOCTL: - Scan the address range and get the memory ranges matching the provided criteria. This is performed when the output buffer is specified. - Write-protect the pages. The PM_SCAN_WP_MATCHING is used to write-protect the pages of interest. The PM_SCAN_CHECK_WPASYNC aborts the operation if non-Async Write Protected pages are found. The ``PM_SCAN_WP_MATCHING`` can be used with or without PM_SCAN_CHECK_WPASYNC. - Both of those operations can be combined into one atomic operation where we can get and write protect the pages as well. Following flags about pages are currently supported: - PAGE_IS_WPALLOWED - Page has async-write-protection enabled - PAGE_IS_WRITTEN - Page has been written to from the time it was write protected - PAGE_IS_FILE - Page is file backed - PAGE_IS_PRESENT - Page is present in the memory - PAGE_IS_SWAPPED - Page is in swapped - PAGE_IS_PFNZERO - Page has zero PFN - PAGE_IS_HUGE - Page is THP or Hugetlb backed This IOCTL can be extended to get information about more PTE bits. The entire address range passed by user [start, end) is scanned until either the user provided buffer is full or max_pages have been found. [akpm@linux-foundation.org: update it for "mm: hugetlb: add huge page size param to set_huge_pte_at()"] [akpm@linux-foundation.org: fix CONFIG_HUGETLB_PAGE=n warning] [arnd@arndb.de: hide unused pagemap_scan_backout_range() function] Link: https://lkml.kernel.org/r/20230927060257.2975412-1-arnd@kernel.org [sfr@canb.auug.org.au: fix "fs/proc/task_mmu: hide unused pagemap_scan_backout_range() function"] Link: https://lkml.kernel.org/r/20230928092223.0625c6bf@canb.auug.org.au Link: https://lkml.kernel.org/r/20230821141518.870589-3-usama.anjum@collabora.com Signed-off-by: Muhammad Usama Anjum Signed-off-by: Michał Mirosław Signed-off-by: Arnd Bergmann Signed-off-by: Stephen Rothwell Reviewed-by: Andrei Vagin Reviewed-by: Michał Mirosław Cc: Alex Sierra Cc: Al Viro Cc: Axel Rasmussen Cc: Christian Brauner Cc: Cyrill Gorcunov Cc: Dan Williams Cc: David Hildenbrand Cc: Greg Kroah-Hartman Cc: Gustavo A. R. Silva Cc: "Liam R. Howlett" Cc: Matthew Wilcox Cc: Michal Miroslaw Cc: Mike Rapoport (IBM) Cc: Nadav Amit Cc: Pasha Tatashin Cc: Paul Gofman Cc: Peter Xu Cc: Shuah Khan Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Yang Shi Cc: Yun Zhou Signed-off-by: Andrew Morton --- fs/proc/task_mmu.c | 692 ++++++++++++++++++++++++++++++++++++++++++ include/linux/hugetlb.h | 1 + include/linux/userfaultfd_k.h | 7 + include/uapi/linux/fs.h | 59 ++++ mm/hugetlb.c | 5 +- 5 files changed, 762 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 3dd5be96691b..d4ef9a2bf95d 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -20,6 +20,8 @@ #include #include #include +#include +#include #include #include @@ -1761,11 +1763,701 @@ static int pagemap_release(struct inode *inode, struct file *file) return 0; } +#define PM_SCAN_CATEGORIES (PAGE_IS_WPALLOWED | PAGE_IS_WRITTEN | \ + PAGE_IS_FILE | PAGE_IS_PRESENT | \ + PAGE_IS_SWAPPED | PAGE_IS_PFNZERO | \ + PAGE_IS_HUGE) +#define PM_SCAN_FLAGS (PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC) + +struct pagemap_scan_private { + struct pm_scan_arg arg; + unsigned long masks_of_interest, cur_vma_category; + struct page_region *vec_buf; + unsigned long vec_buf_len, vec_buf_index, found_pages; + struct page_region __user *vec_out; +}; + +static unsigned long pagemap_page_category(struct pagemap_scan_private *p, + struct vm_area_struct *vma, + unsigned long addr, pte_t pte) +{ + unsigned long categories = 0; + + if (pte_present(pte)) { + struct page *page; + + categories |= PAGE_IS_PRESENT; + if (!pte_uffd_wp(pte)) + categories |= PAGE_IS_WRITTEN; + + if (p->masks_of_interest & PAGE_IS_FILE) { + page = vm_normal_page(vma, addr, pte); + if (page && !PageAnon(page)) + categories |= PAGE_IS_FILE; + } + + if (is_zero_pfn(pte_pfn(pte))) + categories |= PAGE_IS_PFNZERO; + } else if (is_swap_pte(pte)) { + swp_entry_t swp; + + categories |= PAGE_IS_SWAPPED; + if (!pte_swp_uffd_wp_any(pte)) + categories |= PAGE_IS_WRITTEN; + + if (p->masks_of_interest & PAGE_IS_FILE) { + swp = pte_to_swp_entry(pte); + if (is_pfn_swap_entry(swp) && + !PageAnon(pfn_swap_entry_to_page(swp))) + categories |= PAGE_IS_FILE; + } + } + + return categories; +} + +static void make_uffd_wp_pte(struct vm_area_struct *vma, + unsigned long addr, pte_t *pte) +{ + pte_t ptent = ptep_get(pte); + + if (pte_present(ptent)) { + pte_t old_pte; + + old_pte = ptep_modify_prot_start(vma, addr, pte); + ptent = pte_mkuffd_wp(ptent); + ptep_modify_prot_commit(vma, addr, pte, old_pte, ptent); + } else if (is_swap_pte(ptent)) { + ptent = pte_swp_mkuffd_wp(ptent); + set_pte_at(vma->vm_mm, addr, pte, ptent); + } else { + set_pte_at(vma->vm_mm, addr, pte, + make_pte_marker(PTE_MARKER_UFFD_WP)); + } +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static unsigned long pagemap_thp_category(struct pagemap_scan_private *p, + struct vm_area_struct *vma, + unsigned long addr, pmd_t pmd) +{ + unsigned long categories = PAGE_IS_HUGE; + + if (pmd_present(pmd)) { + struct page *page; + + categories |= PAGE_IS_PRESENT; + if (!pmd_uffd_wp(pmd)) + categories |= PAGE_IS_WRITTEN; + + if (p->masks_of_interest & PAGE_IS_FILE) { + page = vm_normal_page_pmd(vma, addr, pmd); + if (page && !PageAnon(page)) + categories |= PAGE_IS_FILE; + } + + if (is_zero_pfn(pmd_pfn(pmd))) + categories |= PAGE_IS_PFNZERO; + } else if (is_swap_pmd(pmd)) { + swp_entry_t swp; + + categories |= PAGE_IS_SWAPPED; + if (!pmd_swp_uffd_wp(pmd)) + categories |= PAGE_IS_WRITTEN; + + if (p->masks_of_interest & PAGE_IS_FILE) { + swp = pmd_to_swp_entry(pmd); + if (is_pfn_swap_entry(swp) && + !PageAnon(pfn_swap_entry_to_page(swp))) + categories |= PAGE_IS_FILE; + } + } + + return categories; +} + +static void make_uffd_wp_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp) +{ + pmd_t old, pmd = *pmdp; + + if (pmd_present(pmd)) { + old = pmdp_invalidate_ad(vma, addr, pmdp); + pmd = pmd_mkuffd_wp(old); + set_pmd_at(vma->vm_mm, addr, pmdp, pmd); + } else if (is_migration_entry(pmd_to_swp_entry(pmd))) { + pmd = pmd_swp_mkuffd_wp(pmd); + set_pmd_at(vma->vm_mm, addr, pmdp, pmd); + } +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#ifdef CONFIG_HUGETLB_PAGE +static unsigned long pagemap_hugetlb_category(pte_t pte) +{ + unsigned long categories = PAGE_IS_HUGE; + + /* + * According to pagemap_hugetlb_range(), file-backed HugeTLB + * page cannot be swapped. So PAGE_IS_FILE is not checked for + * swapped pages. + */ + if (pte_present(pte)) { + categories |= PAGE_IS_PRESENT; + if (!huge_pte_uffd_wp(pte)) + categories |= PAGE_IS_WRITTEN; + if (!PageAnon(pte_page(pte))) + categories |= PAGE_IS_FILE; + if (is_zero_pfn(pte_pfn(pte))) + categories |= PAGE_IS_PFNZERO; + } else if (is_swap_pte(pte)) { + categories |= PAGE_IS_SWAPPED; + if (!pte_swp_uffd_wp_any(pte)) + categories |= PAGE_IS_WRITTEN; + } + + return categories; +} + +static void make_uffd_wp_huge_pte(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t ptent) +{ + unsigned long psize; + + if (is_hugetlb_entry_hwpoisoned(ptent) || is_pte_marker(ptent)) + return; + + psize = huge_page_size(hstate_vma(vma)); + + if (is_hugetlb_entry_migration(ptent)) + set_huge_pte_at(vma->vm_mm, addr, ptep, + pte_swp_mkuffd_wp(ptent), psize); + else if (!huge_pte_none(ptent)) + huge_ptep_modify_prot_commit(vma, addr, ptep, ptent, + huge_pte_mkuffd_wp(ptent)); + else + set_huge_pte_at(vma->vm_mm, addr, ptep, + make_pte_marker(PTE_MARKER_UFFD_WP), psize); +} +#endif /* CONFIG_HUGETLB_PAGE */ + +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE) +static void pagemap_scan_backout_range(struct pagemap_scan_private *p, + unsigned long addr, unsigned long end) +{ + struct page_region *cur_buf = &p->vec_buf[p->vec_buf_index]; + + if (cur_buf->start != addr) + cur_buf->end = addr; + else + cur_buf->start = cur_buf->end = 0; + + p->found_pages -= (end - addr) / PAGE_SIZE; +} +#endif + +static bool pagemap_scan_is_interesting_page(unsigned long categories, + const struct pagemap_scan_private *p) +{ + categories ^= p->arg.category_inverted; + if ((categories & p->arg.category_mask) != p->arg.category_mask) + return false; + if (p->arg.category_anyof_mask && !(categories & p->arg.category_anyof_mask)) + return false; + + return true; +} + +static bool pagemap_scan_is_interesting_vma(unsigned long categories, + const struct pagemap_scan_private *p) +{ + unsigned long required = p->arg.category_mask & PAGE_IS_WPALLOWED; + + categories ^= p->arg.category_inverted; + if ((categories & required) != required) + return false; + + return true; +} + +static int pagemap_scan_test_walk(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + struct pagemap_scan_private *p = walk->private; + struct vm_area_struct *vma = walk->vma; + unsigned long vma_category = 0; + + if (userfaultfd_wp_async(vma) && userfaultfd_wp_use_markers(vma)) + vma_category |= PAGE_IS_WPALLOWED; + else if (p->arg.flags & PM_SCAN_CHECK_WPASYNC) + return -EPERM; + + if (vma->vm_flags & VM_PFNMAP) + return 1; + + if (!pagemap_scan_is_interesting_vma(vma_category, p)) + return 1; + + p->cur_vma_category = vma_category; + + return 0; +} + +static bool pagemap_scan_push_range(unsigned long categories, + struct pagemap_scan_private *p, + unsigned long addr, unsigned long end) +{ + struct page_region *cur_buf = &p->vec_buf[p->vec_buf_index]; + + /* + * When there is no output buffer provided at all, the sentinel values + * won't match here. There is no other way for `cur_buf->end` to be + * non-zero other than it being non-empty. + */ + if (addr == cur_buf->end && categories == cur_buf->categories) { + cur_buf->end = end; + return true; + } + + if (cur_buf->end) { + if (p->vec_buf_index >= p->vec_buf_len - 1) + return false; + + cur_buf = &p->vec_buf[++p->vec_buf_index]; + } + + cur_buf->start = addr; + cur_buf->end = end; + cur_buf->categories = categories; + + return true; +} + +static int pagemap_scan_output(unsigned long categories, + struct pagemap_scan_private *p, + unsigned long addr, unsigned long *end) +{ + unsigned long n_pages, total_pages; + int ret = 0; + + if (!p->vec_buf) + return 0; + + categories &= p->arg.return_mask; + + n_pages = (*end - addr) / PAGE_SIZE; + if (check_add_overflow(p->found_pages, n_pages, &total_pages) || + total_pages > p->arg.max_pages) { + size_t n_too_much = total_pages - p->arg.max_pages; + *end -= n_too_much * PAGE_SIZE; + n_pages -= n_too_much; + ret = -ENOSPC; + } + + if (!pagemap_scan_push_range(categories, p, addr, *end)) { + *end = addr; + n_pages = 0; + ret = -ENOSPC; + } + + p->found_pages += n_pages; + if (ret) + p->arg.walk_end = *end; + + return ret; +} + +static int pagemap_scan_thp_entry(pmd_t *pmd, unsigned long start, + unsigned long end, struct mm_walk *walk) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + struct pagemap_scan_private *p = walk->private; + struct vm_area_struct *vma = walk->vma; + unsigned long categories; + spinlock_t *ptl; + int ret = 0; + + ptl = pmd_trans_huge_lock(pmd, vma); + if (!ptl) + return -ENOENT; + + categories = p->cur_vma_category | + pagemap_thp_category(p, vma, start, *pmd); + + if (!pagemap_scan_is_interesting_page(categories, p)) + goto out_unlock; + + ret = pagemap_scan_output(categories, p, start, &end); + if (start == end) + goto out_unlock; + + if (~p->arg.flags & PM_SCAN_WP_MATCHING) + goto out_unlock; + if (~categories & PAGE_IS_WRITTEN) + goto out_unlock; + + /* + * Break huge page into small pages if the WP operation + * needs to be performed on a portion of the huge page. + */ + if (end != start + HPAGE_SIZE) { + spin_unlock(ptl); + split_huge_pmd(vma, pmd, start); + pagemap_scan_backout_range(p, start, end); + /* Report as if there was no THP */ + return -ENOENT; + } + + make_uffd_wp_pmd(vma, start, pmd); + flush_tlb_range(vma, start, end); +out_unlock: + spin_unlock(ptl); + return ret; +#else /* !CONFIG_TRANSPARENT_HUGEPAGE */ + return -ENOENT; +#endif +} + +static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start, + unsigned long end, struct mm_walk *walk) +{ + struct pagemap_scan_private *p = walk->private; + struct vm_area_struct *vma = walk->vma; + unsigned long addr, flush_end = 0; + pte_t *pte, *start_pte; + spinlock_t *ptl; + int ret; + + arch_enter_lazy_mmu_mode(); + + ret = pagemap_scan_thp_entry(pmd, start, end, walk); + if (ret != -ENOENT) { + arch_leave_lazy_mmu_mode(); + return ret; + } + + ret = 0; + start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, start, &ptl); + if (!pte) { + arch_leave_lazy_mmu_mode(); + walk->action = ACTION_AGAIN; + return 0; + } + + for (addr = start; addr != end; pte++, addr += PAGE_SIZE) { + unsigned long categories = p->cur_vma_category | + pagemap_page_category(p, vma, addr, ptep_get(pte)); + unsigned long next = addr + PAGE_SIZE; + + if (!pagemap_scan_is_interesting_page(categories, p)) + continue; + + ret = pagemap_scan_output(categories, p, addr, &next); + if (next == addr) + break; + + if (~p->arg.flags & PM_SCAN_WP_MATCHING) + continue; + if (~categories & PAGE_IS_WRITTEN) + continue; + + make_uffd_wp_pte(vma, addr, pte); + if (!flush_end) + start = addr; + flush_end = next; + } + + if (flush_end) + flush_tlb_range(vma, start, addr); + + pte_unmap_unlock(start_pte, ptl); + arch_leave_lazy_mmu_mode(); + + cond_resched(); + return ret; +} + +#ifdef CONFIG_HUGETLB_PAGE +static int pagemap_scan_hugetlb_entry(pte_t *ptep, unsigned long hmask, + unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + struct pagemap_scan_private *p = walk->private; + struct vm_area_struct *vma = walk->vma; + unsigned long categories; + spinlock_t *ptl; + int ret = 0; + pte_t pte; + + if (~p->arg.flags & PM_SCAN_WP_MATCHING) { + /* Go the short route when not write-protecting pages. */ + + pte = huge_ptep_get(ptep); + categories = p->cur_vma_category | pagemap_hugetlb_category(pte); + + if (!pagemap_scan_is_interesting_page(categories, p)) + return 0; + + return pagemap_scan_output(categories, p, start, &end); + } + + i_mmap_lock_write(vma->vm_file->f_mapping); + ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, ptep); + + pte = huge_ptep_get(ptep); + categories = p->cur_vma_category | pagemap_hugetlb_category(pte); + + if (!pagemap_scan_is_interesting_page(categories, p)) + goto out_unlock; + + ret = pagemap_scan_output(categories, p, start, &end); + if (start == end) + goto out_unlock; + + if (~categories & PAGE_IS_WRITTEN) + goto out_unlock; + + if (end != start + HPAGE_SIZE) { + /* Partial HugeTLB page WP isn't possible. */ + pagemap_scan_backout_range(p, start, end); + p->arg.walk_end = start; + ret = 0; + goto out_unlock; + } + + make_uffd_wp_huge_pte(vma, start, ptep, pte); + flush_hugetlb_tlb_range(vma, start, end); + +out_unlock: + spin_unlock(ptl); + i_mmap_unlock_write(vma->vm_file->f_mapping); + + return ret; +} +#else +#define pagemap_scan_hugetlb_entry NULL +#endif + +static int pagemap_scan_pte_hole(unsigned long addr, unsigned long end, + int depth, struct mm_walk *walk) +{ + struct pagemap_scan_private *p = walk->private; + struct vm_area_struct *vma = walk->vma; + int ret, err; + + if (!vma || !pagemap_scan_is_interesting_page(p->cur_vma_category, p)) + return 0; + + ret = pagemap_scan_output(p->cur_vma_category, p, addr, &end); + if (addr == end) + return ret; + + if (~p->arg.flags & PM_SCAN_WP_MATCHING) + return ret; + + err = uffd_wp_range(vma, addr, end - addr, true); + if (err < 0) + ret = err; + + return ret; +} + +static const struct mm_walk_ops pagemap_scan_ops = { + .test_walk = pagemap_scan_test_walk, + .pmd_entry = pagemap_scan_pmd_entry, + .pte_hole = pagemap_scan_pte_hole, + .hugetlb_entry = pagemap_scan_hugetlb_entry, +}; + +static int pagemap_scan_get_args(struct pm_scan_arg *arg, + unsigned long uarg) +{ + if (copy_from_user(arg, (void __user *)uarg, sizeof(*arg))) + return -EFAULT; + + if (arg->size != sizeof(struct pm_scan_arg)) + return -EINVAL; + + /* Validate requested features */ + if (arg->flags & ~PM_SCAN_FLAGS) + return -EINVAL; + if ((arg->category_inverted | arg->category_mask | + arg->category_anyof_mask | arg->return_mask) & ~PM_SCAN_CATEGORIES) + return -EINVAL; + + arg->start = untagged_addr((unsigned long)arg->start); + arg->end = untagged_addr((unsigned long)arg->end); + arg->vec = untagged_addr((unsigned long)arg->vec); + + /* Validate memory pointers */ + if (!IS_ALIGNED(arg->start, PAGE_SIZE)) + return -EINVAL; + if (!access_ok((void __user *)(long)arg->start, arg->end - arg->start)) + return -EFAULT; + if (!arg->vec && arg->vec_len) + return -EINVAL; + if (arg->vec && !access_ok((void __user *)(long)arg->vec, + arg->vec_len * sizeof(struct page_region))) + return -EFAULT; + + /* Fixup default values */ + arg->end = ALIGN(arg->end, PAGE_SIZE); + arg->walk_end = 0; + if (!arg->max_pages) + arg->max_pages = ULONG_MAX; + + return 0; +} + +static int pagemap_scan_writeback_args(struct pm_scan_arg *arg, + unsigned long uargl) +{ + struct pm_scan_arg __user *uarg = (void __user *)uargl; + + if (copy_to_user(&uarg->walk_end, &arg->walk_end, sizeof(arg->walk_end))) + return -EFAULT; + + return 0; +} + +static int pagemap_scan_init_bounce_buffer(struct pagemap_scan_private *p) +{ + if (!p->arg.vec_len) + return 0; + + p->vec_buf_len = min_t(size_t, PAGEMAP_WALK_SIZE >> PAGE_SHIFT, + p->arg.vec_len); + p->vec_buf = kmalloc_array(p->vec_buf_len, sizeof(*p->vec_buf), + GFP_KERNEL); + if (!p->vec_buf) + return -ENOMEM; + + p->vec_buf->start = p->vec_buf->end = 0; + p->vec_out = (struct page_region __user *)(long)p->arg.vec; + + return 0; +} + +static long pagemap_scan_flush_buffer(struct pagemap_scan_private *p) +{ + const struct page_region *buf = p->vec_buf; + long n = p->vec_buf_index; + + if (!p->vec_buf) + return 0; + + if (buf[n].end != buf[n].start) + n++; + + if (!n) + return 0; + + if (copy_to_user(p->vec_out, buf, n * sizeof(*buf))) + return -EFAULT; + + p->arg.vec_len -= n; + p->vec_out += n; + + p->vec_buf_index = 0; + p->vec_buf_len = min_t(size_t, p->vec_buf_len, p->arg.vec_len); + p->vec_buf->start = p->vec_buf->end = 0; + + return n; +} + +static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg) +{ + struct mmu_notifier_range range; + struct pagemap_scan_private p = {0}; + unsigned long walk_start; + size_t n_ranges_out = 0; + int ret; + + ret = pagemap_scan_get_args(&p.arg, uarg); + if (ret) + return ret; + + p.masks_of_interest = p.arg.category_mask | p.arg.category_anyof_mask | + p.arg.return_mask; + ret = pagemap_scan_init_bounce_buffer(&p); + if (ret) + return ret; + + /* Protection change for the range is going to happen. */ + if (p.arg.flags & PM_SCAN_WP_MATCHING) { + mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0, + mm, p.arg.start, p.arg.end); + mmu_notifier_invalidate_range_start(&range); + } + + for (walk_start = p.arg.start; walk_start < p.arg.end; + walk_start = p.arg.walk_end) { + long n_out; + + if (fatal_signal_pending(current)) { + ret = -EINTR; + break; + } + + ret = mmap_read_lock_killable(mm); + if (ret) + break; + ret = walk_page_range(mm, walk_start, p.arg.end, + &pagemap_scan_ops, &p); + mmap_read_unlock(mm); + + n_out = pagemap_scan_flush_buffer(&p); + if (n_out < 0) + ret = n_out; + else + n_ranges_out += n_out; + + if (ret != -ENOSPC) + break; + + if (p.arg.vec_len == 0 || p.found_pages == p.arg.max_pages) + break; + } + + /* ENOSPC signifies early stop (buffer full) from the walk. */ + if (!ret || ret == -ENOSPC) + ret = n_ranges_out; + + /* The walk_end isn't set when ret is zero */ + if (!p.arg.walk_end) + p.arg.walk_end = p.arg.end; + if (pagemap_scan_writeback_args(&p.arg, uarg)) + ret = -EFAULT; + + if (p.arg.flags & PM_SCAN_WP_MATCHING) + mmu_notifier_invalidate_range_end(&range); + + kfree(p.vec_buf); + return ret; +} + +static long do_pagemap_cmd(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct mm_struct *mm = file->private_data; + + switch (cmd) { + case PAGEMAP_SCAN: + return do_pagemap_scan(mm, arg); + + default: + return -EINVAL; + } +} + const struct file_operations proc_pagemap_operations = { .llseek = mem_lseek, /* borrow this */ .read = pagemap_read, .open = pagemap_open, .release = pagemap_release, + .unlocked_ioctl = do_pagemap_cmd, + .compat_ioctl = do_pagemap_cmd, }; #endif /* CONFIG_PROC_PAGE_MONITOR */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index e5b9f7e62eeb..205469aa0613 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -280,6 +280,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long cp_flags); bool is_hugetlb_entry_migration(pte_t pte); +bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index c98df391bfd8..f2dc19f40d05 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -221,6 +221,13 @@ static inline vm_fault_t handle_userfault(struct vm_fault *vmf, return VM_FAULT_SIGBUS; } +static inline long uffd_wp_range(struct vm_area_struct *vma, + unsigned long start, unsigned long len, + bool enable_wp) +{ + return false; +} + static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, struct vm_userfaultfd_ctx vm_ctx) { diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index b7b56871029c..da43810b7485 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -305,4 +305,63 @@ typedef int __bitwise __kernel_rwf_t; #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ RWF_APPEND) +/* Pagemap ioctl */ +#define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg) + +/* Bitmasks provided in pm_scan_args masks and reported in page_region.categories. */ +#define PAGE_IS_WPALLOWED (1 << 0) +#define PAGE_IS_WRITTEN (1 << 1) +#define PAGE_IS_FILE (1 << 2) +#define PAGE_IS_PRESENT (1 << 3) +#define PAGE_IS_SWAPPED (1 << 4) +#define PAGE_IS_PFNZERO (1 << 5) +#define PAGE_IS_HUGE (1 << 6) + +/* + * struct page_region - Page region with flags + * @start: Start of the region + * @end: End of the region (exclusive) + * @categories: PAGE_IS_* category bitmask for the region + */ +struct page_region { + __u64 start; + __u64 end; + __u64 categories; +}; + +/* Flags for PAGEMAP_SCAN ioctl */ +#define PM_SCAN_WP_MATCHING (1 << 0) /* Write protect the pages matched. */ +#define PM_SCAN_CHECK_WPASYNC (1 << 1) /* Abort the scan when a non-WP-enabled page is found. */ + +/* + * struct pm_scan_arg - Pagemap ioctl argument + * @size: Size of the structure + * @flags: Flags for the IOCTL + * @start: Starting address of the region + * @end: Ending address of the region + * @walk_end Address where the scan stopped (written by kernel). + * walk_end == end (address tags cleared) informs that the scan completed on entire range. + * @vec: Address of page_region struct array for output + * @vec_len: Length of the page_region struct array + * @max_pages: Optional limit for number of returned pages (0 = disabled) + * @category_inverted: PAGE_IS_* categories which values match if 0 instead of 1 + * @category_mask: Skip pages for which any category doesn't match + * @category_anyof_mask: Skip pages for which no category matches + * @return_mask: PAGE_IS_* categories that are to be reported in `page_region`s returned + */ +struct pm_scan_arg { + __u64 size; + __u64 flags; + __u64 start; + __u64 end; + __u64 walk_end; + __u64 vec; + __u64 vec_len; + __u64 max_pages; + __u64 category_inverted; + __u64 category_mask; + __u64 category_anyof_mask; + __u64 return_mask; +}; + #endif /* _UAPI_LINUX_FS_H */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index bc654b36df9f..2878e0e6bac5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5044,7 +5044,7 @@ bool is_hugetlb_entry_migration(pte_t pte) return false; } -static bool is_hugetlb_entry_hwpoisoned(pte_t pte) +bool is_hugetlb_entry_hwpoisoned(pte_t pte) { swp_entry_t swp; @@ -6266,7 +6266,8 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, } entry = huge_pte_clear_uffd_wp(entry); - set_huge_pte_at(mm, haddr, ptep, entry); + set_huge_pte_at(mm, haddr, ptep, entry, + huge_page_size(hstate_vma(vma))); /* Fallthrough to CoW */ } -- cgit From a5d2f99aff6b6f9cd6a1ab6907d8be8066114791 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Mon, 16 Oct 2023 06:47:47 -0700 Subject: io_uring/cmd: Introduce SOCKET_URING_OP_GETSOCKOPT Add support for getsockopt command (SOCKET_URING_OP_GETSOCKOPT), where level is SOL_SOCKET. This is leveraging the sockptr_t infrastructure, where a sockptr_t is either userspace or kernel space, and handled as such. Differently from the getsockopt(2), the optlen field is not a userspace pointers. In getsockopt(2), userspace provides optlen pointer, which is overwritten by the kernel. In this implementation, userspace passes a u32, and the new value is returned in cqe->res. I.e., optlen is not a pointer. Important to say that userspace needs to keep the pointer alive until the CQE is completed. Signed-off-by: Breno Leitao Reviewed-by: Gabriel Krisman Bertazi Link: https://lore.kernel.org/r/20231016134750.1381153-10-leitao@debian.org Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 7 +++++++ io_uring/uring_cmd.c | 28 ++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 425f64eee44e..dcf7272463e9 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -43,6 +43,10 @@ struct io_uring_sqe { union { __u64 addr; /* pointer to buffer or iovecs */ __u64 splice_off_in; + struct { + __u32 level; + __u32 optname; + }; }; __u32 len; /* buffer size or number of iovecs */ union { @@ -80,6 +84,7 @@ struct io_uring_sqe { union { __s32 splice_fd_in; __u32 file_index; + __u32 optlen; struct { __u16 addr_len; __u16 __pad3[1]; @@ -90,6 +95,7 @@ struct io_uring_sqe { __u64 addr3; __u64 __pad2[1]; }; + __u64 optval; /* * If the ring is initialized with IORING_SETUP_SQE128, then * this field is used for 80 bytes of arbitrary command data @@ -736,6 +742,7 @@ struct io_uring_recvmsg_out { enum { SOCKET_URING_OP_SIOCINQ = 0, SOCKET_URING_OP_SIOCOUTQ, + SOCKET_URING_OP_GETSOCKOPT, }; #ifdef __cplusplus diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 42694c07d8fd..8b045830b0d9 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -214,6 +214,32 @@ int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, } EXPORT_SYMBOL_GPL(io_uring_cmd_import_fixed); +static inline int io_uring_cmd_getsockopt(struct socket *sock, + struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + bool compat = !!(issue_flags & IO_URING_F_COMPAT); + int optlen, optname, level, err; + void __user *optval; + + level = READ_ONCE(cmd->sqe->level); + if (level != SOL_SOCKET) + return -EOPNOTSUPP; + + optval = u64_to_user_ptr(READ_ONCE(cmd->sqe->optval)); + optname = READ_ONCE(cmd->sqe->optname); + optlen = READ_ONCE(cmd->sqe->optlen); + + err = do_sock_getsockopt(sock, compat, level, optname, + USER_SOCKPTR(optval), + KERNEL_SOCKPTR(&optlen)); + if (err) + return err; + + /* On success, return optlen */ + return optlen; +} + #if defined(CONFIG_NET) int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags) { @@ -236,6 +262,8 @@ int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags) if (ret) return ret; return arg; + case SOCKET_URING_OP_GETSOCKOPT: + return io_uring_cmd_getsockopt(sock, cmd, issue_flags); default: return -EOPNOTSUPP; } -- cgit From 4232c6e349f3a591fd0f432e6b858d32095adce6 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Mon, 16 Oct 2023 06:47:48 -0700 Subject: io_uring/cmd: Introduce SOCKET_URING_OP_SETSOCKOPT Add initial support for SOCKET_URING_OP_SETSOCKOPT. This new command is similar to setsockopt. This implementation leverages the function do_sock_setsockopt(), which is shared with the setsockopt() system call path. Important to say that userspace needs to keep the pointer's memory alive until the operation is completed. I.e, the memory could not be deallocated before the CQE is returned to userspace. Signed-off-by: Breno Leitao Reviewed-by: Gabriel Krisman Bertazi Link: https://lore.kernel.org/r/20231016134750.1381153-11-leitao@debian.org Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + io_uring/uring_cmd.c | 21 +++++++++++++++++++++ 2 files changed, 22 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index dcf7272463e9..0f7f6acd0e5a 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -743,6 +743,7 @@ enum { SOCKET_URING_OP_SIOCINQ = 0, SOCKET_URING_OP_SIOCOUTQ, SOCKET_URING_OP_GETSOCKOPT, + SOCKET_URING_OP_SETSOCKOPT, }; #ifdef __cplusplus diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 8b045830b0d9..acbc2924ecd2 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -240,6 +240,25 @@ static inline int io_uring_cmd_getsockopt(struct socket *sock, return optlen; } +static inline int io_uring_cmd_setsockopt(struct socket *sock, + struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + bool compat = !!(issue_flags & IO_URING_F_COMPAT); + int optname, optlen, level; + void __user *optval; + sockptr_t optval_s; + + optval = u64_to_user_ptr(READ_ONCE(cmd->sqe->optval)); + optname = READ_ONCE(cmd->sqe->optname); + optlen = READ_ONCE(cmd->sqe->optlen); + level = READ_ONCE(cmd->sqe->level); + optval_s = USER_SOCKPTR(optval); + + return do_sock_setsockopt(sock, compat, level, optname, optval_s, + optlen); +} + #if defined(CONFIG_NET) int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags) { @@ -264,6 +283,8 @@ int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags) return arg; case SOCKET_URING_OP_GETSOCKOPT: return io_uring_cmd_getsockopt(sock, cmd, issue_flags); + case SOCKET_URING_OP_SETSOCKOPT: + return io_uring_cmd_setsockopt(sock, cmd, issue_flags); default: return -EOPNOTSUPP; } -- cgit From f47906782c76294b3468f7584f666bc114927aa1 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 10 Oct 2023 20:03:19 -0700 Subject: virt: sevguest: Add TSM_REPORTS support for SNP_GET_EXT_REPORT The sevguest driver was a first mover in the confidential computing space. As a first mover that afforded some leeway to build the driver without concern for common infrastructure. Now that sevguest is no longer a singleton [1] the common operation of building and transmitting attestation report blobs can / should be made common. In this model the so called "TSM-provider" implementations can share a common envelope ABI even if the contents of that envelope remain vendor-specific. When / if the industry agrees on an attestation record format, that definition can also fit in the same ABI. In the meantime the kernel's maintenance burden is reduced and collaboration on the commons is increased. Convert sevguest to use CONFIG_TSM_REPORTS to retrieve the data that the SNP_GET_EXT_REPORT ioctl produces. An example flow follows for retrieving the report blob via the TSM interface utility, assuming no nonce and VMPL==2: report=/sys/kernel/config/tsm/report/report0 mkdir $report echo 2 > $report/privlevel dd if=/dev/urandom bs=64 count=1 > $report/inblob hexdump -C $report/outblob # SNP report hexdump -C $report/auxblob # cert_table rmdir $report Given that the platform implementation is free to return empty certificate data if none is available it lets configfs-tsm be simplified as it only needs to worry about wrapping SNP_GET_EXT_REPORT, and leave SNP_GET_REPORT alone. The old ioctls can be lazily deprecated, the main motivation of this effort is to stop the proliferation of new ioctls, and to increase cross-vendor collaboration. Link: http://lore.kernel.org/r/64961c3baf8ce_142af829436@dwillia2-xfh.jf.intel.com.notmuch [1] Cc: Borislav Petkov Cc: Tom Lendacky Cc: Dionna Glaze Cc: Jeremi Piotrowski Tested-by: Kuppuswamy Sathyanarayanan Tested-by: Alexey Kardashevskiy Reviewed-by: Tom Lendacky Signed-off-by: Dan Williams --- drivers/virt/coco/sev-guest/Kconfig | 1 + drivers/virt/coco/sev-guest/sev-guest.c | 135 ++++++++++++++++++++++++++++++++ include/uapi/linux/psp-sev.h | 1 + include/uapi/linux/sev-guest.h | 4 +- 4 files changed, 140 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/virt/coco/sev-guest/Kconfig b/drivers/virt/coco/sev-guest/Kconfig index da2d7ca531f0..1cffc72c41cb 100644 --- a/drivers/virt/coco/sev-guest/Kconfig +++ b/drivers/virt/coco/sev-guest/Kconfig @@ -5,6 +5,7 @@ config SEV_GUEST select CRYPTO select CRYPTO_AEAD2 select CRYPTO_GCM + select TSM_REPORTS help SEV-SNP firmware provides the guest a mechanism to communicate with the PSP without risk from a malicious hypervisor who wishes to read, diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c index e5f8f115f4af..bc564adcf499 100644 --- a/drivers/virt/coco/sev-guest/sev-guest.c +++ b/drivers/virt/coco/sev-guest/sev-guest.c @@ -16,10 +16,13 @@ #include #include #include +#include #include #include #include #include +#include +#include #include #include @@ -768,6 +771,130 @@ static u8 *get_vmpck(int id, struct snp_secrets_page_layout *layout, u32 **seqno return key; } +struct snp_msg_report_resp_hdr { + u32 status; + u32 report_size; + u8 rsvd[24]; +}; + +struct snp_msg_cert_entry { + guid_t guid; + u32 offset; + u32 length; +}; + +static int sev_report_new(struct tsm_report *report, void *data) +{ + struct snp_msg_cert_entry *cert_table; + struct tsm_desc *desc = &report->desc; + struct snp_guest_dev *snp_dev = data; + struct snp_msg_report_resp_hdr hdr; + const u32 report_size = SZ_4K; + const u32 ext_size = SEV_FW_BLOB_MAX_SIZE; + u32 certs_size, i, size = report_size + ext_size; + int ret; + + if (desc->inblob_len != SNP_REPORT_USER_DATA_SIZE) + return -EINVAL; + + void *buf __free(kvfree) = kvzalloc(size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + guard(mutex)(&snp_cmd_mutex); + + /* Check if the VMPCK is not empty */ + if (is_vmpck_empty(snp_dev)) { + dev_err_ratelimited(snp_dev->dev, "VMPCK is disabled\n"); + return -ENOTTY; + } + + cert_table = buf + report_size; + struct snp_ext_report_req ext_req = { + .data = { .vmpl = desc->privlevel }, + .certs_address = (__u64)cert_table, + .certs_len = ext_size, + }; + memcpy(&ext_req.data.user_data, desc->inblob, desc->inblob_len); + + struct snp_guest_request_ioctl input = { + .msg_version = 1, + .req_data = (__u64)&ext_req, + .resp_data = (__u64)buf, + .exitinfo2 = 0xff, + }; + struct snp_req_resp io = { + .req_data = KERNEL_SOCKPTR(&ext_req), + .resp_data = KERNEL_SOCKPTR(buf), + }; + + ret = get_ext_report(snp_dev, &input, &io); + if (ret) + return ret; + + memcpy(&hdr, buf, sizeof(hdr)); + if (hdr.status == SEV_RET_INVALID_PARAM) + return -EINVAL; + if (hdr.status == SEV_RET_INVALID_KEY) + return -EINVAL; + if (hdr.status) + return -ENXIO; + if ((hdr.report_size + sizeof(hdr)) > report_size) + return -ENOMEM; + + void *rbuf __free(kvfree) = kvzalloc(hdr.report_size, GFP_KERNEL); + if (!rbuf) + return -ENOMEM; + + memcpy(rbuf, buf + sizeof(hdr), hdr.report_size); + report->outblob = no_free_ptr(rbuf); + report->outblob_len = hdr.report_size; + + certs_size = 0; + for (i = 0; i < ext_size / sizeof(struct snp_msg_cert_entry); i++) { + struct snp_msg_cert_entry *ent = &cert_table[i]; + + if (guid_is_null(&ent->guid) && !ent->offset && !ent->length) + break; + certs_size = max(certs_size, ent->offset + ent->length); + } + + /* Suspicious that the response populated entries without populating size */ + if (!certs_size && i) + dev_warn_ratelimited(snp_dev->dev, "certificate slots conveyed without size\n"); + + /* No certs to report */ + if (!certs_size) + return 0; + + /* Suspicious that the certificate blob size contract was violated + */ + if (certs_size > ext_size) { + dev_warn_ratelimited(snp_dev->dev, "certificate data truncated\n"); + certs_size = ext_size; + } + + void *cbuf __free(kvfree) = kvzalloc(certs_size, GFP_KERNEL); + if (!cbuf) + return -ENOMEM; + + memcpy(cbuf, cert_table, certs_size); + report->auxblob = no_free_ptr(cbuf); + report->auxblob_len = certs_size; + + return 0; +} + +static const struct tsm_ops sev_tsm_ops = { + .name = KBUILD_MODNAME, + .report_new = sev_report_new, +}; + +static void unregister_sev_tsm(void *data) +{ + tsm_unregister(&sev_tsm_ops); +} + static int __init sev_guest_probe(struct platform_device *pdev) { struct snp_secrets_page_layout *layout; @@ -841,6 +968,14 @@ static int __init sev_guest_probe(struct platform_device *pdev) snp_dev->input.resp_gpa = __pa(snp_dev->response); snp_dev->input.data_gpa = __pa(snp_dev->certs_data); + ret = tsm_register(&sev_tsm_ops, snp_dev, &tsm_report_extra_type); + if (ret) + goto e_free_cert_data; + + ret = devm_add_action_or_reset(&pdev->dev, unregister_sev_tsm, NULL); + if (ret) + goto e_free_cert_data; + ret = misc_register(misc); if (ret) goto e_free_cert_data; diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index 1c9da485318f..b44ba7dcdefc 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -68,6 +68,7 @@ typedef enum { SEV_RET_INVALID_PARAM, SEV_RET_RESOURCE_LIMIT, SEV_RET_SECURE_DATA_INVALID, + SEV_RET_INVALID_KEY = 0x27, SEV_RET_MAX, } sev_ret_code; diff --git a/include/uapi/linux/sev-guest.h b/include/uapi/linux/sev-guest.h index 2aa39112cf8d..154a87a1eca9 100644 --- a/include/uapi/linux/sev-guest.h +++ b/include/uapi/linux/sev-guest.h @@ -14,9 +14,11 @@ #include +#define SNP_REPORT_USER_DATA_SIZE 64 + struct snp_report_req { /* user data that should be included in the report */ - __u8 user_data[64]; + __u8 user_data[SNP_REPORT_USER_DATA_SIZE]; /* The vmpl level to be included in the report */ __u32 vmpl; -- cgit From 374d345d9b5e13380c66d7042f9533a6ac6d1195 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 18 Oct 2023 14:39:20 -0700 Subject: netlink: add variable-length / auto integers We currently push everyone to use padding to align 64b values in netlink. Un-padded nla_put_u64() doesn't even exist any more. The story behind this possibly start with this thread: https://lore.kernel.org/netdev/20121204.130914.1457976839967676240.davem@davemloft.net/ where DaveM was concerned about the alignment of a structure containing 64b stats. If user space tries to access such struct directly: struct some_stats *stats = nla_data(attr); printf("A: %llu", stats->a); lack of alignment may become problematic for some architectures. These days we most often put every single member in a separate attribute, meaning that the code above would use a helper like nla_get_u64(), which can deal with alignment internally. Even for arches which don't have good unaligned access - access aligned to 4B should be pretty efficient. Kernel and well known libraries deal with unaligned input already. Padded 64b is quite space-inefficient (64b + pad means at worst 16B per attr vs 32b which takes 8B). It is also more typing: if (nla_put_u64_pad(rsp, NETDEV_A_SOMETHING_SOMETHING, value, NETDEV_A_SOMETHING_PAD)) Create a new attribute type which will use 32 bits at netlink level if value is small enough (probably most of the time?), and (4B-aligned) 64 bits otherwise. Kernel API is just: if (nla_put_uint(rsp, NETDEV_A_SOMETHING_SOMETHING, value)) Calling this new type "just" sint / uint with no specific size will hopefully also make people more comfortable with using it. Currently telling people "don't use u8, you may need the bits, and netlink will round up to 4B, anyway" is the #1 comment we give to newcomers. In terms of netlink layout it looks like this: 0 4 8 12 16 32b: [nlattr][ u32 ] 64b: [ pad ][nlattr][ u64 ] uint(32) [nlattr][ u32 ] uint(64) [nlattr][ u64 ] Signed-off-by: Jakub Kicinski Acked-by: Nicolas Dichtel Signed-off-by: David S. Miller --- Documentation/userspace-api/netlink/specs.rst | 18 ++++++- include/net/netlink.h | 69 ++++++++++++++++++++++++++- include/uapi/linux/netlink.h | 5 ++ lib/nlattr.c | 22 +++++++++ net/netlink/policy.c | 14 ++++-- 5 files changed, 121 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/netlink/specs.rst b/Documentation/userspace-api/netlink/specs.rst index 40dd7442d2c3..c1b951649113 100644 --- a/Documentation/userspace-api/netlink/specs.rst +++ b/Documentation/userspace-api/netlink/specs.rst @@ -403,10 +403,21 @@ This section describes the attribute types supported by the ``genetlink`` compatibility level. Refer to documentation of different levels for additional attribute types. -Scalar integer types +Common integer types -------------------- -Fixed-width integer types: +``sint`` and ``uint`` represent signed and unsigned 64 bit integers. +If the value can fit on 32 bits only 32 bits are carried in netlink +messages, otherwise full 64 bits are carried. Note that the payload +is only aligned to 4B, so the full 64 bit value may be unaligned! + +Common integer types should be preferred over fix-width types in majority +of cases. + +Fix-width integer types +----------------------- + +Fixed-width integer types include: ``u8``, ``u16``, ``u32``, ``u64``, ``s8``, ``s16``, ``s32``, ``s64``. Note that types smaller than 32 bit should be avoided as using them @@ -416,6 +427,9 @@ See :ref:`pad_type` for padding of 64 bit attributes. The payload of the attribute is the integer in host order unless ``byte-order`` specifies otherwise. +64 bit values are usually aligned by the kernel but it is recommended +that the user space is able to deal with unaligned values. + .. _pad_type: pad diff --git a/include/net/netlink.h b/include/net/netlink.h index 8a7cd1170e1f..aba2b162a226 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -128,6 +128,8 @@ * nla_len(nla) length of attribute payload * * Attribute Payload Access for Basic Types: + * nla_get_uint(nla) get payload for a uint attribute + * nla_get_sint(nla) get payload for a sint attribute * nla_get_u8(nla) get payload for a u8 attribute * nla_get_u16(nla) get payload for a u16 attribute * nla_get_u32(nla) get payload for a u32 attribute @@ -183,6 +185,8 @@ enum { NLA_REJECT, NLA_BE16, NLA_BE32, + NLA_SINT, + NLA_UINT, __NLA_TYPE_MAX, }; @@ -229,6 +233,7 @@ enum nla_policy_validation { * nested header (or empty); len field is used if * nested_policy is also used, for the max attr * number in the nested policy. + * NLA_SINT, NLA_UINT, * NLA_U8, NLA_U16, * NLA_U32, NLA_U64, * NLA_S8, NLA_S16, @@ -260,12 +265,14 @@ enum nla_policy_validation { * while an array has the nested attributes at another * level down and the attribute types directly in the * nesting don't matter. + * NLA_UINT, * NLA_U8, * NLA_U16, * NLA_U32, * NLA_U64, * NLA_BE16, * NLA_BE32, + * NLA_SINT, * NLA_S8, * NLA_S16, * NLA_S32, @@ -280,6 +287,7 @@ enum nla_policy_validation { * or NLA_POLICY_FULL_RANGE_SIGNED() macros instead. * Use the NLA_POLICY_MIN(), NLA_POLICY_MAX() and * NLA_POLICY_RANGE() macros. + * NLA_UINT, * NLA_U8, * NLA_U16, * NLA_U32, @@ -288,6 +296,7 @@ enum nla_policy_validation { * to a struct netlink_range_validation that indicates * the min/max values. * Use NLA_POLICY_FULL_RANGE(). + * NLA_SINT, * NLA_S8, * NLA_S16, * NLA_S32, @@ -377,9 +386,11 @@ struct nla_policy { #define __NLA_IS_UINT_TYPE(tp) \ (tp == NLA_U8 || tp == NLA_U16 || tp == NLA_U32 || \ - tp == NLA_U64 || tp == NLA_BE16 || tp == NLA_BE32) + tp == NLA_U64 || tp == NLA_UINT || \ + tp == NLA_BE16 || tp == NLA_BE32) #define __NLA_IS_SINT_TYPE(tp) \ - (tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64) + (tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64 || \ + tp == NLA_SINT) #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) #define NLA_ENSURE_UINT_TYPE(tp) \ @@ -1357,6 +1368,22 @@ static inline int nla_put_u32(struct sk_buff *skb, int attrtype, u32 value) return nla_put(skb, attrtype, sizeof(u32), &tmp); } +/** + * nla_put_uint - Add a variable-size unsigned int to a socket buffer + * @skb: socket buffer to add attribute to + * @attrtype: attribute type + * @value: numeric value + */ +static inline int nla_put_uint(struct sk_buff *skb, int attrtype, u64 value) +{ + u64 tmp64 = value; + u32 tmp32 = value; + + if (tmp64 == tmp32) + return nla_put_u32(skb, attrtype, tmp32); + return nla_put(skb, attrtype, sizeof(u64), &tmp64); +} + /** * nla_put_be32 - Add a __be32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to @@ -1511,6 +1538,22 @@ static inline int nla_put_s64(struct sk_buff *skb, int attrtype, s64 value, return nla_put_64bit(skb, attrtype, sizeof(s64), &tmp, padattr); } +/** + * nla_put_sint - Add a variable-size signed int to a socket buffer + * @skb: socket buffer to add attribute to + * @attrtype: attribute type + * @value: numeric value + */ +static inline int nla_put_sint(struct sk_buff *skb, int attrtype, s64 value) +{ + s64 tmp64 = value; + s32 tmp32 = value; + + if (tmp64 == tmp32) + return nla_put_s32(skb, attrtype, tmp32); + return nla_put(skb, attrtype, sizeof(s64), &tmp64); +} + /** * nla_put_string - Add a string netlink attribute to a socket buffer * @skb: socket buffer to add attribute to @@ -1667,6 +1710,17 @@ static inline u64 nla_get_u64(const struct nlattr *nla) return tmp; } +/** + * nla_get_uint - return payload of uint attribute + * @nla: uint netlink attribute + */ +static inline u64 nla_get_uint(const struct nlattr *nla) +{ + if (nla_len(nla) == sizeof(u32)) + return nla_get_u32(nla); + return nla_get_u64(nla); +} + /** * nla_get_be64 - return payload of __be64 attribute * @nla: __be64 netlink attribute @@ -1729,6 +1783,17 @@ static inline s64 nla_get_s64(const struct nlattr *nla) return tmp; } +/** + * nla_get_sint - return payload of uint attribute + * @nla: uint netlink attribute + */ +static inline s64 nla_get_sint(const struct nlattr *nla) +{ + if (nla_len(nla) == sizeof(s32)) + return nla_get_s32(nla); + return nla_get_s64(nla); +} + /** * nla_get_flag - return payload of flag attribute * @nla: flag netlink attribute diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index e2ae82e3f9f7..f87aaf28a649 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -298,6 +298,8 @@ struct nla_bitfield32 { * entry has attributes again, the policy for those inner ones * and the corresponding maxtype may be specified. * @NL_ATTR_TYPE_BITFIELD32: &struct nla_bitfield32 attribute + * @NL_ATTR_TYPE_SINT: 32-bit or 64-bit signed attribute, aligned to 4B + * @NL_ATTR_TYPE_UINT: 32-bit or 64-bit unsigned attribute, aligned to 4B */ enum netlink_attribute_type { NL_ATTR_TYPE_INVALID, @@ -322,6 +324,9 @@ enum netlink_attribute_type { NL_ATTR_TYPE_NESTED_ARRAY, NL_ATTR_TYPE_BITFIELD32, + + NL_ATTR_TYPE_SINT, + NL_ATTR_TYPE_UINT, }; /** diff --git a/lib/nlattr.c b/lib/nlattr.c index 7a2b6c38fd59..dc15e7888fc1 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -134,6 +134,7 @@ void nla_get_range_unsigned(const struct nla_policy *pt, range->max = U32_MAX; break; case NLA_U64: + case NLA_UINT: case NLA_MSECS: range->max = U64_MAX; break; @@ -183,6 +184,9 @@ static int nla_validate_range_unsigned(const struct nla_policy *pt, case NLA_U64: value = nla_get_u64(nla); break; + case NLA_UINT: + value = nla_get_uint(nla); + break; case NLA_MSECS: value = nla_get_u64(nla); break; @@ -248,6 +252,7 @@ void nla_get_range_signed(const struct nla_policy *pt, range->max = S32_MAX; break; case NLA_S64: + case NLA_SINT: range->min = S64_MIN; range->max = S64_MAX; break; @@ -295,6 +300,9 @@ static int nla_validate_int_range_signed(const struct nla_policy *pt, case NLA_S64: value = nla_get_s64(nla); break; + case NLA_SINT: + value = nla_get_sint(nla); + break; default: return -EINVAL; } @@ -320,6 +328,7 @@ static int nla_validate_int_range(const struct nla_policy *pt, case NLA_U16: case NLA_U32: case NLA_U64: + case NLA_UINT: case NLA_MSECS: case NLA_BINARY: case NLA_BE16: @@ -329,6 +338,7 @@ static int nla_validate_int_range(const struct nla_policy *pt, case NLA_S16: case NLA_S32: case NLA_S64: + case NLA_SINT: return nla_validate_int_range_signed(pt, nla, extack); default: WARN_ON(1); @@ -355,6 +365,9 @@ static int nla_validate_mask(const struct nla_policy *pt, case NLA_U64: value = nla_get_u64(nla); break; + case NLA_UINT: + value = nla_get_uint(nla); + break; case NLA_BE16: value = ntohs(nla_get_be16(nla)); break; @@ -433,6 +446,15 @@ static int validate_nla(const struct nlattr *nla, int maxtype, goto out_err; break; + case NLA_SINT: + case NLA_UINT: + if (attrlen != sizeof(u32) && attrlen != sizeof(u64)) { + NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, + "invalid attribute length"); + return -EINVAL; + } + break; + case NLA_BITFIELD32: if (attrlen != sizeof(struct nla_bitfield32)) goto out_err; diff --git a/net/netlink/policy.c b/net/netlink/policy.c index e2f111edf66c..1f8909c16f14 100644 --- a/net/netlink/policy.c +++ b/net/netlink/policy.c @@ -230,6 +230,8 @@ int netlink_policy_dump_attr_size_estimate(const struct nla_policy *pt) case NLA_S16: case NLA_S32: case NLA_S64: + case NLA_SINT: + case NLA_UINT: /* maximum is common, u64 min/max with padding */ return common + 2 * (nla_attr_size(0) + nla_attr_size(sizeof(u64))); @@ -288,6 +290,7 @@ __netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state, case NLA_U16: case NLA_U32: case NLA_U64: + case NLA_UINT: case NLA_MSECS: { struct netlink_range_validation range; @@ -297,8 +300,10 @@ __netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state, type = NL_ATTR_TYPE_U16; else if (pt->type == NLA_U32) type = NL_ATTR_TYPE_U32; - else + else if (pt->type == NLA_U64) type = NL_ATTR_TYPE_U64; + else + type = NL_ATTR_TYPE_UINT; if (pt->validation_type == NLA_VALIDATE_MASK) { if (nla_put_u64_64bit(skb, NL_POLICY_TYPE_ATTR_MASK, @@ -320,7 +325,8 @@ __netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state, case NLA_S8: case NLA_S16: case NLA_S32: - case NLA_S64: { + case NLA_S64: + case NLA_SINT: { struct netlink_range_validation_signed range; if (pt->type == NLA_S8) @@ -329,8 +335,10 @@ __netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state, type = NL_ATTR_TYPE_S16; else if (pt->type == NLA_S32) type = NL_ATTR_TYPE_S32; - else + else if (pt->type == NLA_S64) type = NL_ATTR_TYPE_S64; + else + type = NL_ATTR_TYPE_SINT; nla_get_range_signed(pt, &range); -- cgit From b4a11b2033b7d3dfdd46592f7036a775b18cecd1 Mon Sep 17 00:00:00 2001 From: Heng Guo Date: Thu, 19 Oct 2023 09:20:53 +0800 Subject: net: fix IPSTATS_MIB_OUTPKGS increment in OutForwDatagrams. Reproduce environment: network with 3 VM linuxs is connected as below: VM1<---->VM2(latest kernel 6.5.0-rc7)<---->VM3 VM1: eth0 ip: 192.168.122.207 MTU 1500 VM2: eth0 ip: 192.168.122.208, eth1 ip: 192.168.123.224 MTU 1500 VM3: eth0 ip: 192.168.123.240 MTU 1500 Reproduce: VM1 send 1400 bytes UDP data to VM3 using tools scapy with flags=0. scapy command: send(IP(dst="192.168.123.240",flags=0)/UDP()/str('0'*1400),count=1, inter=1.000000) Result: Before IP data is sent. ---------------------------------------------------------------------- root@qemux86-64:~# cat /proc/net/snmp Ip: Forwarding DefaultTTL InReceives InHdrErrors InAddrErrors ForwDatagrams InUnknownProtos InDiscards InDelivers OutRequests OutDiscards OutNoRoutes ReasmTimeout ReasmReqds ReasmOKs ReasmFails FragOKs FragFails FragCreates Ip: 1 64 11 0 3 4 0 0 4 7 0 0 0 0 0 0 0 0 0 ...... ---------------------------------------------------------------------- After IP data is sent. ---------------------------------------------------------------------- root@qemux86-64:~# cat /proc/net/snmp Ip: Forwarding DefaultTTL InReceives InHdrErrors InAddrErrors ForwDatagrams InUnknownProtos InDiscards InDelivers OutRequests OutDiscards OutNoRoutes ReasmTimeout ReasmReqds ReasmOKs ReasmFails FragOKs FragFails FragCreates Ip: 1 64 12 0 3 5 0 0 4 8 0 0 0 0 0 0 0 0 0 ...... ---------------------------------------------------------------------- "ForwDatagrams" increase from 4 to 5 and "OutRequests" also increase from 7 to 8. Issue description and patch: IPSTATS_MIB_OUTPKTS("OutRequests") is counted with IPSTATS_MIB_OUTOCTETS ("OutOctets") in ip_finish_output2(). According to RFC 4293, it is "OutOctets" counted with "OutTransmits" but not "OutRequests". "OutRequests" does not include any datagrams counted in "ForwDatagrams". ipSystemStatsOutOctets OBJECT-TYPE DESCRIPTION "The total number of octets in IP datagrams delivered to the lower layers for transmission. Octets from datagrams counted in ipIfStatsOutTransmits MUST be counted here. ipSystemStatsOutRequests OBJECT-TYPE DESCRIPTION "The total number of IP datagrams that local IP user- protocols (including ICMP) supplied to IP in requests for transmission. Note that this counter does not include any datagrams counted in ipSystemStatsOutForwDatagrams. So do patch to define IPSTATS_MIB_OUTPKTS to "OutTransmits" and add IPSTATS_MIB_OUTREQUESTS for "OutRequests". Add IPSTATS_MIB_OUTREQUESTS counter in __ip_local_out() for ipv4 and add IPSTATS_MIB_OUT counter in ip6_finish_output2() for ipv6. Test result with patch: Before IP data is sent. ---------------------------------------------------------------------- root@qemux86-64:~# cat /proc/net/snmp Ip: Forwarding DefaultTTL InReceives InHdrErrors InAddrErrors ForwDatagrams InUnknownProtos InDiscards InDelivers OutRequests OutDiscards OutNoRoutes ReasmTimeout ReasmReqds ReasmOKs ReasmFails FragOKs FragFails FragCreates OutTransmits Ip: 1 64 9 0 5 1 0 0 3 3 0 0 0 0 0 0 0 0 0 4 ...... root@qemux86-64:~# cat /proc/net/netstat ...... IpExt: InNoRoutes InTruncatedPkts InMcastPkts OutMcastPkts InBcastPkts OutBcastPkts InOctets OutOctets InMcastOctets OutMcastOctets InBcastOctets OutBcastOctets InCsumErrors InNoECTPkts InECT1Pkts InECT0Pkts InCEPkts ReasmOverlaps IpExt: 0 0 0 0 0 0 2976 1896 0 0 0 0 0 9 0 0 0 0 ---------------------------------------------------------------------- After IP data is sent. ---------------------------------------------------------------------- root@qemux86-64:~# cat /proc/net/snmp Ip: Forwarding DefaultTTL InReceives InHdrErrors InAddrErrors ForwDatagrams InUnknownProtos InDiscards InDelivers OutRequests OutDiscards OutNoRoutes ReasmTimeout ReasmReqds ReasmOKs ReasmFails FragOKs FragFails FragCreates OutTransmits Ip: 1 64 10 0 5 2 0 0 3 3 0 0 0 0 0 0 0 0 0 5 ...... root@qemux86-64:~# cat /proc/net/netstat ...... IpExt: InNoRoutes InTruncatedPkts InMcastPkts OutMcastPkts InBcastPkts OutBcastPkts InOctets OutOctets InMcastOctets OutMcastOctets InBcastOctets OutBcastOctets InCsumErrors InNoECTPkts InECT1Pkts InECT0Pkts InCEPkts ReasmOverlaps IpExt: 0 0 0 0 0 0 4404 3324 0 0 0 0 0 10 0 0 0 0 ---------------------------------------------------------------------- "ForwDatagrams" increase from 1 to 2 and "OutRequests" is keeping 3. "OutTransmits" increase from 4 to 5 and "OutOctets" increase 1428. Signed-off-by: Heng Guo Reviewed-by: Kun Song Reviewed-by: Filip Pudak Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/uapi/linux/snmp.h | 3 ++- net/ipv4/ip_output.c | 2 ++ net/ipv4/proc.c | 3 ++- net/ipv6/ip6_output.c | 6 ++++-- net/ipv6/mcast.c | 5 ++--- net/ipv6/ndisc.c | 2 +- net/ipv6/proc.c | 3 ++- net/ipv6/raw.c | 2 +- 8 files changed, 16 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 26f33a4c253d..b2b72886cb6d 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -24,7 +24,7 @@ enum IPSTATS_MIB_INOCTETS, /* InOctets */ IPSTATS_MIB_INDELIVERS, /* InDelivers */ IPSTATS_MIB_OUTFORWDATAGRAMS, /* OutForwDatagrams */ - IPSTATS_MIB_OUTPKTS, /* OutRequests */ + IPSTATS_MIB_OUTREQUESTS, /* OutRequests */ IPSTATS_MIB_OUTOCTETS, /* OutOctets */ /* other fields */ IPSTATS_MIB_INHDRERRORS, /* InHdrErrors */ @@ -57,6 +57,7 @@ enum IPSTATS_MIB_ECT0PKTS, /* InECT0Pkts */ IPSTATS_MIB_CEPKTS, /* InCEPkts */ IPSTATS_MIB_REASM_OVERLAPS, /* ReasmOverlaps */ + IPSTATS_MIB_OUTPKTS, /* OutTransmits */ __IPSTATS_MIB_MAX }; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 89e62ed08dad..b06f678b03a1 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -101,6 +101,8 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); + IP_INC_STATS(net, IPSTATS_MIB_OUTREQUESTS); + iph_set_totlen(iph, skb->len); ip_send_check(iph); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index eaf1d3113b62..a85b0aba3646 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -83,7 +83,7 @@ static const struct snmp_mib snmp4_ipstats_list[] = { SNMP_MIB_ITEM("InUnknownProtos", IPSTATS_MIB_INUNKNOWNPROTOS), SNMP_MIB_ITEM("InDiscards", IPSTATS_MIB_INDISCARDS), SNMP_MIB_ITEM("InDelivers", IPSTATS_MIB_INDELIVERS), - SNMP_MIB_ITEM("OutRequests", IPSTATS_MIB_OUTPKTS), + SNMP_MIB_ITEM("OutRequests", IPSTATS_MIB_OUTREQUESTS), SNMP_MIB_ITEM("OutDiscards", IPSTATS_MIB_OUTDISCARDS), SNMP_MIB_ITEM("OutNoRoutes", IPSTATS_MIB_OUTNOROUTES), SNMP_MIB_ITEM("ReasmTimeout", IPSTATS_MIB_REASMTIMEOUT), @@ -93,6 +93,7 @@ static const struct snmp_mib snmp4_ipstats_list[] = { SNMP_MIB_ITEM("FragOKs", IPSTATS_MIB_FRAGOKS), SNMP_MIB_ITEM("FragFails", IPSTATS_MIB_FRAGFAILS), SNMP_MIB_ITEM("FragCreates", IPSTATS_MIB_FRAGCREATES), + SNMP_MIB_ITEM("OutTransmits", IPSTATS_MIB_OUTPKTS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a471c7e91761..571c10fb00b1 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -117,6 +117,8 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * return res; } + IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); + rcu_read_lock(); nexthop = rt6_nexthop((struct rt6_info *)dst, daddr); neigh = __ipv6_neigh_lookup_noref(dev, nexthop); @@ -328,7 +330,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, mtu = dst_mtu(dst); if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) { - IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing @@ -1987,7 +1989,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, skb->tstamp = cork->base.transmit_time; ip6_cork_steal_dst(skb, cork); - IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); + IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); u8 icmp6_type; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 99e28b444a4c..b75d3c9d41bb 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1789,7 +1789,7 @@ static void mld_sendpack(struct sk_buff *skb) rcu_read_lock(); idev = __in6_dev_get(skb->dev); - IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); payload_len = (skb_tail_pointer(skb) - skb_network_header(skb)) - sizeof(*pip6); @@ -2147,8 +2147,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) full_len = sizeof(struct ipv6hdr) + payload_len; rcu_read_lock(); - IP6_UPD_PO_STATS(net, __in6_dev_get(dev), - IPSTATS_MIB_OUT, full_len); + IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_OUTREQUESTS); rcu_read_unlock(); skb = sock_alloc_send_skb(sk, hlen + tlen + full_len, 1, &err); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 679443d7ecb5..a19999b30bc0 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -504,7 +504,7 @@ void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, rcu_read_lock(); idev = __in6_dev_get(dst->dev); - IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, dst->dev, diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index e20b3705c2d2..6d1d9221649d 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -61,7 +61,7 @@ static const struct snmp_mib snmp6_ipstats_list[] = { SNMP_MIB_ITEM("Ip6InDiscards", IPSTATS_MIB_INDISCARDS), SNMP_MIB_ITEM("Ip6InDelivers", IPSTATS_MIB_INDELIVERS), SNMP_MIB_ITEM("Ip6OutForwDatagrams", IPSTATS_MIB_OUTFORWDATAGRAMS), - SNMP_MIB_ITEM("Ip6OutRequests", IPSTATS_MIB_OUTPKTS), + SNMP_MIB_ITEM("Ip6OutRequests", IPSTATS_MIB_OUTREQUESTS), SNMP_MIB_ITEM("Ip6OutDiscards", IPSTATS_MIB_OUTDISCARDS), SNMP_MIB_ITEM("Ip6OutNoRoutes", IPSTATS_MIB_OUTNOROUTES), SNMP_MIB_ITEM("Ip6ReasmTimeout", IPSTATS_MIB_REASMTIMEOUT), @@ -84,6 +84,7 @@ static const struct snmp_mib snmp6_ipstats_list[] = { SNMP_MIB_ITEM("Ip6InECT1Pkts", IPSTATS_MIB_ECT1PKTS), SNMP_MIB_ITEM("Ip6InECT0Pkts", IPSTATS_MIB_ECT0PKTS), SNMP_MIB_ITEM("Ip6InCEPkts", IPSTATS_MIB_CEPKTS), + SNMP_MIB_ITEM("Ip6OutTransmits", IPSTATS_MIB_OUTPKTS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index a2aa54a2baae..dd0a4e73e602 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -651,7 +651,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, * have been queued for deletion. */ rcu_read_lock(); - IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); + IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, dst_output); if (err > 0) -- cgit From b5f9e63278d6f32789478acf1ed41d21d92b36cf Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Tue, 17 Oct 2023 11:15:52 -0700 Subject: iommufd: Correct IOMMU_HWPT_ALLOC_NEST_PARENT description The IOMMU_HWPT_ALLOC_NEST_PARENT flag is used to allocate a HWPT. Though a HWPT holds a domain in the core structure, it is still quite confusing to describe it using "domain" in the uAPI kdoc. Correct it to "HWPT". Fixes: 4ff542163397 ("iommufd: Support allocating nested parent domain") Link: https://lore.kernel.org/r/20231017181552.12667-1-nicolinc@nvidia.com Signed-off-by: Nicolin Chen Signed-off-by: Jason Gunthorpe --- include/uapi/linux/iommufd.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 4a7c5c8fdbb4..be7a95042677 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -349,9 +349,8 @@ struct iommu_vfio_ioas { /** * enum iommufd_hwpt_alloc_flags - Flags for HWPT allocation - * @IOMMU_HWPT_ALLOC_NEST_PARENT: If set, allocate a domain which can serve - * as the parent domain in the nesting - * configuration. + * @IOMMU_HWPT_ALLOC_NEST_PARENT: If set, allocate a HWPT that can serve as + * the parent HWPT in a nesting configuration. */ enum iommufd_hwpt_alloc_flags { IOMMU_HWPT_ALLOC_NEST_PARENT = 1 << 0, -- cgit From 3d44de9a10ea2b1658dfaed8ea6d3d7b6e0defbb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 20 Oct 2023 12:57:45 +0000 Subject: tcp: add RTAX_FEATURE_TCP_USEC_TS This new dst feature flag will be used to allow TCP to use usec based timestamps instead of msec ones. ip route .... feature tcp_usec_ts Also document that RTAX_FEATURE_SACK and RTAX_FEATURE_TIMESTAMP are unused. RTAX_FEATURE_ALLFRAG is also going away soon. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 5 +++++ include/uapi/linux/rtnetlink.h | 18 +++++++++++------- 2 files changed, 16 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index e15452df9804..04a0e647ef74 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -576,4 +576,9 @@ void tcp_sock_set_quickack(struct sock *sk, int val); int tcp_sock_set_syncnt(struct sock *sk, int val); int tcp_sock_set_user_timeout(struct sock *sk, int val); +static inline bool dst_tcp_usec_ts(const struct dst_entry *dst) +{ + return dst_feature(dst, RTAX_FEATURE_TCP_USEC_TS); +} + #endif /* _LINUX_TCP_H */ diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 51c13cf9c5ae..aa2482a0614a 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -502,13 +502,17 @@ enum { #define RTAX_MAX (__RTAX_MAX - 1) -#define RTAX_FEATURE_ECN (1 << 0) -#define RTAX_FEATURE_SACK (1 << 1) -#define RTAX_FEATURE_TIMESTAMP (1 << 2) -#define RTAX_FEATURE_ALLFRAG (1 << 3) - -#define RTAX_FEATURE_MASK (RTAX_FEATURE_ECN | RTAX_FEATURE_SACK | \ - RTAX_FEATURE_TIMESTAMP | RTAX_FEATURE_ALLFRAG) +#define RTAX_FEATURE_ECN (1 << 0) +#define RTAX_FEATURE_SACK (1 << 1) /* unused */ +#define RTAX_FEATURE_TIMESTAMP (1 << 2) /* unused */ +#define RTAX_FEATURE_ALLFRAG (1 << 3) +#define RTAX_FEATURE_TCP_USEC_TS (1 << 4) + +#define RTAX_FEATURE_MASK (RTAX_FEATURE_ECN | \ + RTAX_FEATURE_SACK | \ + RTAX_FEATURE_TIMESTAMP | \ + RTAX_FEATURE_ALLFRAG | \ + RTAX_FEATURE_TCP_USEC_TS) struct rta_session { __u8 proto; -- cgit From a77a0f5c7f23a8a4981a2a3ff47baa91ceaf1f53 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 20 Oct 2023 12:57:48 +0000 Subject: tcp: add TCPI_OPT_USEC_TS Add the ability to report in tcp_info.tcpi_options if a flow is using usec resolution in TCP TS val. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/uapi/linux/tcp.h | 1 + net/ipv4/tcp.c | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index d1d08da6331a..8aa3916e14f6 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -170,6 +170,7 @@ enum tcp_fastopen_client_fail { #define TCPI_OPT_ECN 8 /* ECN was negociated at TCP session init */ #define TCPI_OPT_ECN_SEEN 16 /* we received at least one packet with ECT */ #define TCPI_OPT_SYN_DATA 32 /* SYN-ACK acked data in SYN sent or rcvd */ +#define TCPI_OPT_USEC_TS 64 /* usec timestamps */ /* * Sender's congestion state indicating normal or abnormal situations diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b961364b4961..a86d8200a1e8 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3760,6 +3760,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_options |= TCPI_OPT_ECN_SEEN; if (tp->syn_data_acked) info->tcpi_options |= TCPI_OPT_SYN_DATA; + if (tp->tcp_usec_ts) + info->tcpi_options |= TCPI_OPT_USEC_TS; info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto); info->tcpi_ato = jiffies_to_usecs(min_t(u32, icsk->icsk_ack.ato, -- cgit From 8c90b8b4e8eb671929dc684b96e059cd862c067f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 1 Oct 2023 12:16:33 -0700 Subject: wifi: nl80211: fix doc typos Correct some typos. Signed-off-by: Randy Dunlap Cc: Johannes Berg Cc: Kalle Valo Cc: linux-wireless@vger.kernel.org Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: netdev@vger.kernel.org Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20231001191633.19090-3-rdunlap@infradead.org Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 0c64994b118e..dced2c49daec 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -167,7 +167,7 @@ * following events occur. * a) Expiration of hardware timer whose expiration time is set to maximum * coalescing delay of matching coalesce rule. - * b) Coalescing buffer in hardware reaches it's limit. + * b) Coalescing buffer in hardware reaches its limit. * c) Packet doesn't match any of the configured coalesce rules. * * User needs to configure following parameters for creating a coalesce @@ -326,7 +326,7 @@ /** * DOC: Multi-Link Operation * - * In Multi-Link Operation, a connection between to MLDs utilizes multiple + * In Multi-Link Operation, a connection between two MLDs utilizes multiple * links. To use this in nl80211, various commands and responses now need * to or will include the new %NL80211_ATTR_MLO_LINKS attribute. * Additionally, various commands that need to operate on a specific link -- cgit From e3570f040836b2f6332ce5cb4db0fd070448aeb5 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sat, 21 Oct 2023 13:27:07 +0200 Subject: devlink: make devlink_flash_overwrite enum named one Since this enum is going to be used in generated userspace file, name it properly. Signed-off-by: Jiri Pirko Reviewed-by: Jacob Keller Link: https://lore.kernel.org/r/20231021112711.660606-7-jiri@resnulli.us Signed-off-by: Jakub Kicinski --- include/uapi/linux/devlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index cd4b82458d1b..b3c8383d342d 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -265,7 +265,7 @@ enum { * Documentation/networking/devlink/devlink-flash.rst * */ -enum { +enum devlink_flash_overwrite { DEVLINK_FLASH_OVERWRITE_SETTINGS_BIT, DEVLINK_FLASH_OVERWRITE_IDENTIFIERS_BIT, -- cgit From adc8df12d91a2b8350b0cd4c7fec3e8546c9d1f8 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 22 Oct 2023 22:25:17 +0200 Subject: gtp: uapi: fix GTPA_MAX Subtract one to __GTPA_MAX, otherwise GTPA_MAX is off by 2. Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Paolo Abeni --- include/uapi/linux/gtp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h index 2f61298a7b77..3dcdb9e33cba 100644 --- a/include/uapi/linux/gtp.h +++ b/include/uapi/linux/gtp.h @@ -33,6 +33,6 @@ enum gtp_attrs { GTPA_PAD, __GTPA_MAX, }; -#define GTPA_MAX (__GTPA_MAX + 1) +#define GTPA_MAX (__GTPA_MAX - 1) #endif /* _UAPI_LINUX_GTP_H_ */ -- cgit From 5f9bdbf4c65860cc8b9c544d92bfd76fbea8d9c5 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:50:56 +0100 Subject: iommufd: Add a flag to enforce dirty tracking on attach Throughout IOMMU domain lifetime that wants to use dirty tracking, some guarantees are needed such that any device attached to the iommu_domain supports dirty tracking. The idea is to handle a case where IOMMU in the system are assymetric feature-wise and thus the capability may not be supported for all devices. The enforcement is done by adding a flag into HWPT_ALLOC namely: IOMMU_HWPT_ALLOC_DIRTY_TRACKING .. Passed in HWPT_ALLOC ioctl() flags. The enforcement is done by creating a iommu_domain via domain_alloc_user() and validating the requested flags with what the device IOMMU supports (and failing accordingly) advertised). Advertising the new IOMMU domain feature flag requires that the individual iommu driver capability is supported when a future device attachment happens. Link: https://lore.kernel.org/r/20231024135109.73787-6-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommufd/hw_pagetable.c | 4 +++- include/uapi/linux/iommufd.h | 3 +++ 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index 8b3d2875d642..dd50ca9e2c09 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -157,7 +157,9 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd) struct iommufd_ioas *ioas; int rc; - if ((cmd->flags & (~IOMMU_HWPT_ALLOC_NEST_PARENT)) || cmd->__reserved) + if ((cmd->flags & ~(IOMMU_HWPT_ALLOC_NEST_PARENT | + IOMMU_HWPT_ALLOC_DIRTY_TRACKING)) || + cmd->__reserved) return -EOPNOTSUPP; idev = iommufd_get_device(ucmd, cmd->dev_id); diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index be7a95042677..c76248410120 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -351,9 +351,12 @@ struct iommu_vfio_ioas { * enum iommufd_hwpt_alloc_flags - Flags for HWPT allocation * @IOMMU_HWPT_ALLOC_NEST_PARENT: If set, allocate a HWPT that can serve as * the parent HWPT in a nesting configuration. + * @IOMMU_HWPT_ALLOC_DIRTY_TRACKING: Dirty tracking support for device IOMMU is + * enforced on device attachment */ enum iommufd_hwpt_alloc_flags { IOMMU_HWPT_ALLOC_NEST_PARENT = 1 << 0, + IOMMU_HWPT_ALLOC_DIRTY_TRACKING = 1 << 1, }; /** -- cgit From e2a4b294784957fc28ecb1fed8a7e69da18eb18d Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:50:57 +0100 Subject: iommufd: Add IOMMU_HWPT_SET_DIRTY_TRACKING Every IOMMU driver should be able to implement the needed iommu domain ops to control dirty tracking. Connect a hw_pagetable to the IOMMU core dirty tracking ops, specifically the ability to enable/disable dirty tracking on an IOMMU domain (hw_pagetable id). To that end add an io_pagetable kernel API to toggle dirty tracking: * iopt_set_dirty_tracking(iopt, [domain], state) The intended caller of this is via the hw_pagetable object that is created. Internally it will ensure the leftover dirty state is cleared /right before/ dirty tracking starts. This is also useful for iommu drivers which may decide that dirty tracking is always-enabled at boot without wanting to toggle dynamically via corresponding iommu domain op. Link: https://lore.kernel.org/r/20231024135109.73787-7-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommufd/hw_pagetable.c | 24 +++++++++++++++ drivers/iommu/iommufd/io_pagetable.c | 54 +++++++++++++++++++++++++++++++++ drivers/iommu/iommufd/iommufd_private.h | 12 ++++++++ drivers/iommu/iommufd/main.c | 3 ++ include/uapi/linux/iommufd.h | 28 +++++++++++++++++ 5 files changed, 121 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index dd50ca9e2c09..c3b7bd9bfcbb 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -196,3 +196,27 @@ out_put_idev: iommufd_put_object(&idev->obj); return rc; } + +int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd) +{ + struct iommu_hwpt_set_dirty_tracking *cmd = ucmd->cmd; + struct iommufd_hw_pagetable *hwpt; + struct iommufd_ioas *ioas; + int rc = -EOPNOTSUPP; + bool enable; + + if (cmd->flags & ~IOMMU_HWPT_DIRTY_TRACKING_ENABLE) + return rc; + + hwpt = iommufd_get_hwpt(ucmd, cmd->hwpt_id); + if (IS_ERR(hwpt)) + return PTR_ERR(hwpt); + + ioas = hwpt->ioas; + enable = cmd->flags & IOMMU_HWPT_DIRTY_TRACKING_ENABLE; + + rc = iopt_set_dirty_tracking(&ioas->iopt, hwpt->domain, enable); + + iommufd_put_object(&hwpt->obj); + return rc; +} diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c index 3a598182b761..41c2efb6ff15 100644 --- a/drivers/iommu/iommufd/io_pagetable.c +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -412,6 +412,60 @@ int iopt_map_user_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt, return 0; } +static int iopt_clear_dirty_data(struct io_pagetable *iopt, + struct iommu_domain *domain) +{ + const struct iommu_dirty_ops *ops = domain->dirty_ops; + struct iommu_iotlb_gather gather; + struct iommu_dirty_bitmap dirty; + struct iopt_area *area; + int ret = 0; + + lockdep_assert_held_read(&iopt->iova_rwsem); + + iommu_dirty_bitmap_init(&dirty, NULL, &gather); + + for (area = iopt_area_iter_first(iopt, 0, ULONG_MAX); area; + area = iopt_area_iter_next(area, 0, ULONG_MAX)) { + if (!area->pages) + continue; + + ret = ops->read_and_clear_dirty(domain, iopt_area_iova(area), + iopt_area_length(area), 0, + &dirty); + if (ret) + break; + } + + iommu_iotlb_sync(domain, &gather); + return ret; +} + +int iopt_set_dirty_tracking(struct io_pagetable *iopt, + struct iommu_domain *domain, bool enable) +{ + const struct iommu_dirty_ops *ops = domain->dirty_ops; + int ret = 0; + + if (!ops) + return -EOPNOTSUPP; + + down_read(&iopt->iova_rwsem); + + /* Clear dirty bits from PTEs to ensure a clean snapshot */ + if (enable) { + ret = iopt_clear_dirty_data(iopt, domain); + if (ret) + goto out_unlock; + } + + ret = ops->set_dirty_tracking(domain, enable); + +out_unlock: + up_read(&iopt->iova_rwsem); + return ret; +} + int iopt_get_pages(struct io_pagetable *iopt, unsigned long iova, unsigned long length, struct list_head *pages_list) { diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 3064997a0181..b09750848da6 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -8,6 +8,7 @@ #include #include #include +#include struct iommu_domain; struct iommu_group; @@ -70,6 +71,9 @@ int iopt_unmap_iova(struct io_pagetable *iopt, unsigned long iova, unsigned long length, unsigned long *unmapped); int iopt_unmap_all(struct io_pagetable *iopt, unsigned long *unmapped); +int iopt_set_dirty_tracking(struct io_pagetable *iopt, + struct iommu_domain *domain, bool enable); + void iommufd_access_notify_unmap(struct io_pagetable *iopt, unsigned long iova, unsigned long length); int iopt_table_add_domain(struct io_pagetable *iopt, @@ -240,6 +244,14 @@ struct iommufd_hw_pagetable { struct list_head hwpt_item; }; +static inline struct iommufd_hw_pagetable * +iommufd_get_hwpt(struct iommufd_ucmd *ucmd, u32 id) +{ + return container_of(iommufd_get_object(ucmd->ictx, id, + IOMMUFD_OBJ_HW_PAGETABLE), + struct iommufd_hw_pagetable, obj); +} +int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd); struct iommufd_hw_pagetable * iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, struct iommufd_device *idev, u32 flags, diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index e71523cbd0de..46fedd779714 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -307,6 +307,7 @@ union ucmd_buffer { struct iommu_destroy destroy; struct iommu_hw_info info; struct iommu_hwpt_alloc hwpt; + struct iommu_hwpt_set_dirty_tracking set_dirty_tracking; struct iommu_ioas_alloc alloc; struct iommu_ioas_allow_iovas allow_iovas; struct iommu_ioas_copy ioas_copy; @@ -342,6 +343,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { __reserved), IOCTL_OP(IOMMU_HWPT_ALLOC, iommufd_hwpt_alloc, struct iommu_hwpt_alloc, __reserved), + IOCTL_OP(IOMMU_HWPT_SET_DIRTY_TRACKING, iommufd_hwpt_set_dirty_tracking, + struct iommu_hwpt_set_dirty_tracking, __reserved), IOCTL_OP(IOMMU_IOAS_ALLOC, iommufd_ioas_alloc_ioctl, struct iommu_ioas_alloc, out_ioas_id), IOCTL_OP(IOMMU_IOAS_ALLOW_IOVAS, iommufd_ioas_allow_iovas, diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index c76248410120..5c82b68c88f3 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -47,6 +47,7 @@ enum { IOMMUFD_CMD_VFIO_IOAS, IOMMUFD_CMD_HWPT_ALLOC, IOMMUFD_CMD_GET_HW_INFO, + IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING, }; /** @@ -453,4 +454,31 @@ struct iommu_hw_info { __u32 __reserved; }; #define IOMMU_GET_HW_INFO _IO(IOMMUFD_TYPE, IOMMUFD_CMD_GET_HW_INFO) + +/* + * enum iommufd_hwpt_set_dirty_tracking_flags - Flags for steering dirty + * tracking + * @IOMMU_HWPT_DIRTY_TRACKING_ENABLE: Enable dirty tracking + */ +enum iommufd_hwpt_set_dirty_tracking_flags { + IOMMU_HWPT_DIRTY_TRACKING_ENABLE = 1, +}; + +/** + * struct iommu_hwpt_set_dirty_tracking - ioctl(IOMMU_HWPT_SET_DIRTY_TRACKING) + * @size: sizeof(struct iommu_hwpt_set_dirty_tracking) + * @flags: Combination of enum iommufd_hwpt_set_dirty_tracking_flags + * @hwpt_id: HW pagetable ID that represents the IOMMU domain + * @__reserved: Must be 0 + * + * Toggle dirty tracking on an HW pagetable. + */ +struct iommu_hwpt_set_dirty_tracking { + __u32 size; + __u32 flags; + __u32 hwpt_id; + __u32 __reserved; +}; +#define IOMMU_HWPT_SET_DIRTY_TRACKING _IO(IOMMUFD_TYPE, \ + IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING) #endif -- cgit From b9a60d6f850e4470017b60f731220a58cda199aa Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:50:58 +0100 Subject: iommufd: Add IOMMU_HWPT_GET_DIRTY_BITMAP Connect a hw_pagetable to the IOMMU core dirty tracking read_and_clear_dirty iommu domain op. It exposes all of the functionality for the UAPI that read the dirtied IOVAs while clearing the Dirty bits from the PTEs. In doing so, add an IO pagetable API iopt_read_and_clear_dirty_data() that performs the reading of dirty IOPTEs for a given IOVA range and then copying back to userspace bitmap. Underneath it uses the IOMMU domain kernel API which will read the dirty bits, as well as atomically clearing the IOPTE dirty bit and flushing the IOTLB at the end. The IOVA bitmaps usage takes care of the iteration of the bitmaps user pages efficiently and without copies. Within the iterator function we iterate over io-pagetable contigous areas that have been mapped. Contrary to past incantation of a similar interface in VFIO the IOVA range to be scanned is tied in to the bitmap size, thus the application needs to pass a appropriately sized bitmap address taking into account the iova range being passed *and* page size ... as opposed to allowing bitmap-iova != iova. Link: https://lore.kernel.org/r/20231024135109.73787-8-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommufd/hw_pagetable.c | 22 +++++++ drivers/iommu/iommufd/io_pagetable.c | 113 ++++++++++++++++++++++++++++++++ drivers/iommu/iommufd/iommufd_private.h | 10 +++ drivers/iommu/iommufd/main.c | 4 ++ include/uapi/linux/iommufd.h | 35 ++++++++++ 5 files changed, 184 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index c3b7bd9bfcbb..7316f69110ef 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -220,3 +220,25 @@ int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd) iommufd_put_object(&hwpt->obj); return rc; } + +int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd) +{ + struct iommu_hwpt_get_dirty_bitmap *cmd = ucmd->cmd; + struct iommufd_hw_pagetable *hwpt; + struct iommufd_ioas *ioas; + int rc = -EOPNOTSUPP; + + if ((cmd->flags || cmd->__reserved)) + return -EOPNOTSUPP; + + hwpt = iommufd_get_hwpt(ucmd, cmd->hwpt_id); + if (IS_ERR(hwpt)) + return PTR_ERR(hwpt); + + ioas = hwpt->ioas; + rc = iopt_read_and_clear_dirty_data(&ioas->iopt, hwpt->domain, + cmd->flags, cmd); + + iommufd_put_object(&hwpt->obj); + return rc; +} diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c index 41c2efb6ff15..255264e796fb 100644 --- a/drivers/iommu/iommufd/io_pagetable.c +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -15,6 +15,7 @@ #include #include #include +#include #include "io_pagetable.h" #include "double_span.h" @@ -412,6 +413,118 @@ int iopt_map_user_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt, return 0; } +struct iova_bitmap_fn_arg { + struct io_pagetable *iopt; + struct iommu_domain *domain; + struct iommu_dirty_bitmap *dirty; +}; + +static int __iommu_read_and_clear_dirty(struct iova_bitmap *bitmap, + unsigned long iova, size_t length, + void *opaque) +{ + struct iopt_area *area; + struct iopt_area_contig_iter iter; + struct iova_bitmap_fn_arg *arg = opaque; + struct iommu_domain *domain = arg->domain; + struct iommu_dirty_bitmap *dirty = arg->dirty; + const struct iommu_dirty_ops *ops = domain->dirty_ops; + unsigned long last_iova = iova + length - 1; + int ret; + + iopt_for_each_contig_area(&iter, area, arg->iopt, iova, last_iova) { + unsigned long last = min(last_iova, iopt_area_last_iova(area)); + + ret = ops->read_and_clear_dirty(domain, iter.cur_iova, + last - iter.cur_iova + 1, 0, + dirty); + if (ret) + return ret; + } + + if (!iopt_area_contig_done(&iter)) + return -EINVAL; + return 0; +} + +static int +iommu_read_and_clear_dirty(struct iommu_domain *domain, + struct io_pagetable *iopt, unsigned long flags, + struct iommu_hwpt_get_dirty_bitmap *bitmap) +{ + const struct iommu_dirty_ops *ops = domain->dirty_ops; + struct iommu_iotlb_gather gather; + struct iommu_dirty_bitmap dirty; + struct iova_bitmap_fn_arg arg; + struct iova_bitmap *iter; + int ret = 0; + + if (!ops || !ops->read_and_clear_dirty) + return -EOPNOTSUPP; + + iter = iova_bitmap_alloc(bitmap->iova, bitmap->length, + bitmap->page_size, + u64_to_user_ptr(bitmap->data)); + if (IS_ERR(iter)) + return -ENOMEM; + + iommu_dirty_bitmap_init(&dirty, iter, &gather); + + arg.iopt = iopt; + arg.domain = domain; + arg.dirty = &dirty; + iova_bitmap_for_each(iter, &arg, __iommu_read_and_clear_dirty); + + iommu_iotlb_sync(domain, &gather); + iova_bitmap_free(iter); + + return ret; +} + +int iommufd_check_iova_range(struct io_pagetable *iopt, + struct iommu_hwpt_get_dirty_bitmap *bitmap) +{ + size_t iommu_pgsize = iopt->iova_alignment; + u64 last_iova; + + if (check_add_overflow(bitmap->iova, bitmap->length - 1, &last_iova)) + return -EOVERFLOW; + + if (bitmap->iova > ULONG_MAX || last_iova > ULONG_MAX) + return -EOVERFLOW; + + if ((bitmap->iova & (iommu_pgsize - 1)) || + ((last_iova + 1) & (iommu_pgsize - 1))) + return -EINVAL; + + if (!bitmap->page_size) + return -EINVAL; + + if ((bitmap->iova & (bitmap->page_size - 1)) || + ((last_iova + 1) & (bitmap->page_size - 1))) + return -EINVAL; + + return 0; +} + +int iopt_read_and_clear_dirty_data(struct io_pagetable *iopt, + struct iommu_domain *domain, + unsigned long flags, + struct iommu_hwpt_get_dirty_bitmap *bitmap) +{ + int ret; + + ret = iommufd_check_iova_range(iopt, bitmap); + if (ret) + return ret; + + down_read(&iopt->iova_rwsem); + ret = iommu_read_and_clear_dirty(domain, iopt, flags, bitmap); + up_read(&iopt->iova_rwsem); + + return ret; +} + static int iopt_clear_dirty_data(struct io_pagetable *iopt, struct iommu_domain *domain) { diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index b09750848da6..034129130db3 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -8,6 +8,8 @@ #include #include #include +#include +#include #include struct iommu_domain; @@ -71,6 +73,10 @@ int iopt_unmap_iova(struct io_pagetable *iopt, unsigned long iova, unsigned long length, unsigned long *unmapped); int iopt_unmap_all(struct io_pagetable *iopt, unsigned long *unmapped); +int iopt_read_and_clear_dirty_data(struct io_pagetable *iopt, + struct iommu_domain *domain, + unsigned long flags, + struct iommu_hwpt_get_dirty_bitmap *bitmap); int iopt_set_dirty_tracking(struct io_pagetable *iopt, struct iommu_domain *domain, bool enable); @@ -226,6 +232,8 @@ int iommufd_option_rlimit_mode(struct iommu_option *cmd, struct iommufd_ctx *ictx); int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd); +int iommufd_check_iova_range(struct io_pagetable *iopt, + struct iommu_hwpt_get_dirty_bitmap *bitmap); /* * A HW pagetable is called an iommu_domain inside the kernel. This user object @@ -252,6 +260,8 @@ iommufd_get_hwpt(struct iommufd_ucmd *ucmd, u32 id) struct iommufd_hw_pagetable, obj); } int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd); +int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd); + struct iommufd_hw_pagetable * iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, struct iommufd_device *idev, u32 flags, diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index 46fedd779714..d50f42a730aa 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -307,6 +307,7 @@ union ucmd_buffer { struct iommu_destroy destroy; struct iommu_hw_info info; struct iommu_hwpt_alloc hwpt; + struct iommu_hwpt_get_dirty_bitmap get_dirty_bitmap; struct iommu_hwpt_set_dirty_tracking set_dirty_tracking; struct iommu_ioas_alloc alloc; struct iommu_ioas_allow_iovas allow_iovas; @@ -343,6 +344,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { __reserved), IOCTL_OP(IOMMU_HWPT_ALLOC, iommufd_hwpt_alloc, struct iommu_hwpt_alloc, __reserved), + IOCTL_OP(IOMMU_HWPT_GET_DIRTY_BITMAP, iommufd_hwpt_get_dirty_bitmap, + struct iommu_hwpt_get_dirty_bitmap, data), IOCTL_OP(IOMMU_HWPT_SET_DIRTY_TRACKING, iommufd_hwpt_set_dirty_tracking, struct iommu_hwpt_set_dirty_tracking, __reserved), IOCTL_OP(IOMMU_IOAS_ALLOC, iommufd_ioas_alloc_ioctl, @@ -555,5 +558,6 @@ MODULE_ALIAS_MISCDEV(VFIO_MINOR); MODULE_ALIAS("devname:vfio/vfio"); #endif MODULE_IMPORT_NS(IOMMUFD_INTERNAL); +MODULE_IMPORT_NS(IOMMUFD); MODULE_DESCRIPTION("I/O Address Space Management for passthrough devices"); MODULE_LICENSE("GPL"); diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 5c82b68c88f3..dce38e32ca84 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -48,6 +48,7 @@ enum { IOMMUFD_CMD_HWPT_ALLOC, IOMMUFD_CMD_GET_HW_INFO, IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING, + IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP, }; /** @@ -481,4 +482,38 @@ struct iommu_hwpt_set_dirty_tracking { }; #define IOMMU_HWPT_SET_DIRTY_TRACKING _IO(IOMMUFD_TYPE, \ IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING) + +/** + * struct iommu_hwpt_get_dirty_bitmap - ioctl(IOMMU_HWPT_GET_DIRTY_BITMAP) + * @size: sizeof(struct iommu_hwpt_get_dirty_bitmap) + * @hwpt_id: HW pagetable ID that represents the IOMMU domain + * @flags: Must be zero + * @__reserved: Must be 0 + * @iova: base IOVA of the bitmap first bit + * @length: IOVA range size + * @page_size: page size granularity of each bit in the bitmap + * @data: bitmap where to set the dirty bits. The bitmap bits each + * represent a page_size which you deviate from an arbitrary iova. + * + * Checking a given IOVA is dirty: + * + * data[(iova / page_size) / 64] & (1ULL << ((iova / page_size) % 64)) + * + * Walk the IOMMU pagetables for a given IOVA range to return a bitmap + * with the dirty IOVAs. In doing so it will also by default clear any + * dirty bit metadata set in the IOPTE. + */ +struct iommu_hwpt_get_dirty_bitmap { + __u32 size; + __u32 hwpt_id; + __u32 flags; + __u32 __reserved; + __aligned_u64 iova; + __aligned_u64 length; + __aligned_u64 page_size; + __aligned_u64 data; +}; +#define IOMMU_HWPT_GET_DIRTY_BITMAP _IO(IOMMUFD_TYPE, \ + IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP) + #endif -- cgit From 7623683857e52b75184d37862c70f1230aef2edd Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:50:59 +0100 Subject: iommufd: Add capabilities to IOMMU_GET_HW_INFO Extend IOMMUFD_CMD_GET_HW_INFO op to query generic iommu capabilities for a given device. Capabilities are IOMMU agnostic and use device_iommu_capable() API passing one of the IOMMU_CAP_*. Enumerate IOMMU_CAP_DIRTY_TRACKING for now in the out_capabilities field returned back to userspace. Link: https://lore.kernel.org/r/20231024135109.73787-9-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommufd/device.c | 4 ++++ include/uapi/linux/iommufd.h | 17 +++++++++++++++++ 2 files changed, 21 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index e88fa73a45e6..2a41fd2b6ef8 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -1185,6 +1185,10 @@ int iommufd_get_hw_info(struct iommufd_ucmd *ucmd) */ cmd->data_len = data_len; + cmd->out_capabilities = 0; + if (device_iommu_capable(idev->dev, IOMMU_CAP_DIRTY_TRACKING)) + cmd->out_capabilities |= IOMMU_HW_CAP_DIRTY_TRACKING; + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); out_free: kfree(data); diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index dce38e32ca84..036ebc6c19cf 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -418,6 +418,20 @@ enum iommu_hw_info_type { IOMMU_HW_INFO_TYPE_INTEL_VTD, }; +/** + * enum iommufd_hw_capabilities + * @IOMMU_HW_CAP_DIRTY_TRACKING: IOMMU hardware support for dirty tracking + * If available, it means the following APIs + * are supported: + * + * IOMMU_HWPT_GET_DIRTY_BITMAP + * IOMMU_HWPT_SET_DIRTY_TRACKING + * + */ +enum iommufd_hw_capabilities { + IOMMU_HW_CAP_DIRTY_TRACKING = 1 << 0, +}; + /** * struct iommu_hw_info - ioctl(IOMMU_GET_HW_INFO) * @size: sizeof(struct iommu_hw_info) @@ -429,6 +443,8 @@ enum iommu_hw_info_type { * the iommu type specific hardware information data * @out_data_type: Output the iommu hardware info type as defined in the enum * iommu_hw_info_type. + * @out_capabilities: Output the generic iommu capability info type as defined + * in the enum iommu_hw_capabilities. * @__reserved: Must be 0 * * Query an iommu type specific hardware information data from an iommu behind @@ -453,6 +469,7 @@ struct iommu_hw_info { __aligned_u64 data_uptr; __u32 out_data_type; __u32 __reserved; + __aligned_u64 out_capabilities; }; #define IOMMU_GET_HW_INFO _IO(IOMMUFD_TYPE, IOMMUFD_CMD_GET_HW_INFO) -- cgit From 609848132c71316df3260d1ec066539c21bba585 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:51:00 +0100 Subject: iommufd: Add a flag to skip clearing of IOPTE dirty VFIO has an operation where it unmaps an IOVA while returning a bitmap with the dirty data. In reality the operation doesn't quite query the IO pagetables that the PTE was dirty or not. Instead it marks as dirty on anything that was mapped, and doing so in one syscall. In IOMMUFD the equivalent is done in two operations by querying with GET_DIRTY_IOVA followed by UNMAP_IOVA. However, this would incur two TLB flushes given that after clearing dirty bits IOMMU implementations require invalidating their IOTLB, plus another invalidation needed for the UNMAP. To allow dirty bits to be queried faster, add a flag (IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR) that requests to not clear the dirty bits from the PTE (but just reading them), under the expectation that the next operation is the unmap. An alternative is to unmap and just perpectually mark as dirty as that's the same behaviour as today. So here equivalent functionally can be provided with unmap alone, and if real dirty info is required it will amortize the cost while querying. There's still a race against DMA where in theory the unmap of the IOVA (when the guest invalidates the IOTLB via emulated iommu) would race against the VF performing DMA on the same IOVA. As discussed in [0], we are accepting to resolve this race as throwing away the DMA and it doesn't matter if it hit physical DRAM or not, the VM can't tell if we threw it away because the DMA was blocked or because we failed to copy the DRAM. [0] https://lore.kernel.org/linux-iommu/20220502185239.GR8364@nvidia.com/ Link: https://lore.kernel.org/r/20231024135109.73787-10-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommufd/hw_pagetable.c | 3 ++- drivers/iommu/iommufd/io_pagetable.c | 9 +++++++-- include/uapi/linux/iommufd.h | 15 ++++++++++++++- 3 files changed, 23 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index 7316f69110ef..72a5269984b0 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -228,7 +228,8 @@ int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd) struct iommufd_ioas *ioas; int rc = -EOPNOTSUPP; - if ((cmd->flags || cmd->__reserved)) + if ((cmd->flags & ~(IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR)) || + cmd->__reserved) return -EOPNOTSUPP; hwpt = iommufd_get_hwpt(ucmd, cmd->hwpt_id); diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c index 255264e796fb..9f060abe53b6 100644 --- a/drivers/iommu/iommufd/io_pagetable.c +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -414,6 +414,7 @@ int iopt_map_user_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt, } struct iova_bitmap_fn_arg { + unsigned long flags; struct io_pagetable *iopt; struct iommu_domain *domain; struct iommu_dirty_bitmap *dirty; @@ -430,13 +431,14 @@ static int __iommu_read_and_clear_dirty(struct iova_bitmap *bitmap, struct iommu_dirty_bitmap *dirty = arg->dirty; const struct iommu_dirty_ops *ops = domain->dirty_ops; unsigned long last_iova = iova + length - 1; + unsigned long flags = arg->flags; int ret; iopt_for_each_contig_area(&iter, area, arg->iopt, iova, last_iova) { unsigned long last = min(last_iova, iopt_area_last_iova(area)); ret = ops->read_and_clear_dirty(domain, iter.cur_iova, - last - iter.cur_iova + 1, 0, + last - iter.cur_iova + 1, flags, dirty); if (ret) return ret; @@ -470,12 +472,15 @@ iommu_read_and_clear_dirty(struct iommu_domain *domain, iommu_dirty_bitmap_init(&dirty, iter, &gather); + arg.flags = flags; arg.iopt = iopt; arg.domain = domain; arg.dirty = &dirty; iova_bitmap_for_each(iter, &arg, __iommu_read_and_clear_dirty); - iommu_iotlb_sync(domain, &gather); + if (!(flags & IOMMU_DIRTY_NO_CLEAR)) + iommu_iotlb_sync(domain, &gather); + iova_bitmap_free(iter); return ret; diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 036ebc6c19cf..c44eecf5d318 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -500,11 +500,24 @@ struct iommu_hwpt_set_dirty_tracking { #define IOMMU_HWPT_SET_DIRTY_TRACKING _IO(IOMMUFD_TYPE, \ IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING) +/** + * enum iommufd_hwpt_get_dirty_bitmap_flags - Flags for getting dirty bits + * @IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR: Just read the PTEs without clearing + * any dirty bits metadata. This flag + * can be passed in the expectation + * where the next operation is an unmap + * of the same IOVA range. + * + */ +enum iommufd_hwpt_get_dirty_bitmap_flags { + IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR = 1, +}; + /** * struct iommu_hwpt_get_dirty_bitmap - ioctl(IOMMU_HWPT_GET_DIRTY_BITMAP) * @size: sizeof(struct iommu_hwpt_get_dirty_bitmap) * @hwpt_id: HW pagetable ID that represents the IOMMU domain - * @flags: Must be zero + * @flags: Combination of enum iommufd_hwpt_get_dirty_bitmap_flags * @__reserved: Must be 0 * @iova: base IOVA of the bitmap first bit * @length: IOVA range size -- cgit From 92af77ca26f75f7874634c8ac2f744f86ec56e88 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Tue, 24 Oct 2023 14:03:36 +0300 Subject: PCI: dwc: Use FIELD_GET/PREP() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Convert open-coded variants of PCI field access into FIELD_GET/PREP() to make the code easier to understand. Add two missing defines into pci_regs.h. Logically, the Max No-Snoop Latency Register is a separate word sized register in the PCIe spec, but the pre-existing LTR defines in pci_regs.h with dword long values seem to consider the registers together (the same goes for the only user). Thus, follow the custom and make the new values also take both word long LTR registers as a joint dword register. Link: https://lore.kernel.org/r/20231024110336.26264-1-ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen Signed-off-by: Bjorn Helgaas --- drivers/pci/controller/dwc/pcie-designware-ep.c | 7 ++++--- drivers/pci/controller/dwc/pcie-tegra194.c | 10 +++++++--- include/uapi/linux/pci_regs.h | 2 ++ 3 files changed, 13 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index f9182f8d552f..20bef1436bfb 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -6,6 +6,7 @@ * Author: Kishon Vijay Abraham I */ +#include #include #include @@ -334,7 +335,7 @@ static int dw_pcie_ep_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no) if (!(val & PCI_MSI_FLAGS_ENABLE)) return -EINVAL; - val = (val & PCI_MSI_FLAGS_QSIZE) >> 4; + val = FIELD_GET(PCI_MSI_FLAGS_QSIZE, val); return val; } @@ -357,7 +358,7 @@ static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no, reg = ep_func->msi_cap + func_offset + PCI_MSI_FLAGS; val = dw_pcie_readw_dbi(pci, reg); val &= ~PCI_MSI_FLAGS_QMASK; - val |= (interrupts << 1) & PCI_MSI_FLAGS_QMASK; + val |= FIELD_PREP(PCI_MSI_FLAGS_QMASK, interrupts); dw_pcie_dbi_ro_wr_en(pci); dw_pcie_writew_dbi(pci, reg, val); dw_pcie_dbi_ro_wr_dis(pci); @@ -584,7 +585,7 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, reg = ep_func->msix_cap + func_offset + PCI_MSIX_TABLE; tbl_offset = dw_pcie_readl_dbi(pci, reg); - bir = (tbl_offset & PCI_MSIX_TABLE_BIR); + bir = FIELD_GET(PCI_MSIX_TABLE_BIR, tbl_offset); tbl_offset &= PCI_MSIX_TABLE_OFFSET; msix_tbl = ep->epf_bar[bir]->addr + tbl_offset; diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index 248cd9347e8f..f2a515b639ab 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -126,7 +126,7 @@ #define APPL_LTR_MSG_1 0xC4 #define LTR_MSG_REQ BIT(15) -#define LTR_MST_NO_SNOOP_SHIFT 16 +#define LTR_NOSNOOP_MSG_REQ BIT(31) #define APPL_LTR_MSG_2 0xC8 #define APPL_LTR_MSG_2_LTR_MSG_REQ_STATE BIT(3) @@ -496,8 +496,12 @@ static irqreturn_t tegra_pcie_ep_irq_thread(int irq, void *arg) ktime_t timeout; /* 110us for both snoop and no-snoop */ - val = 110 | (2 << PCI_LTR_SCALE_SHIFT) | LTR_MSG_REQ; - val |= (val << LTR_MST_NO_SNOOP_SHIFT); + val = FIELD_PREP(PCI_LTR_VALUE_MASK, 110) | + FIELD_PREP(PCI_LTR_SCALE_MASK, 2) | + LTR_MSG_REQ | + FIELD_PREP(PCI_LTR_NOSNOOP_VALUE, 110) | + FIELD_PREP(PCI_LTR_NOSNOOP_SCALE, 2) | + LTR_NOSNOOP_MSG_REQ; appl_writel(pcie, val, APPL_LTR_MSG_1); /* Send LTR upstream */ diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index e5f558d96493..495f0ae4ecd5 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -975,6 +975,8 @@ #define PCI_LTR_VALUE_MASK 0x000003ff #define PCI_LTR_SCALE_MASK 0x00001c00 #define PCI_LTR_SCALE_SHIFT 10 +#define PCI_LTR_NOSNOOP_VALUE 0x03ff0000 /* Max No-Snoop Latency Value */ +#define PCI_LTR_NOSNOOP_SCALE 0x1c000000 /* Scale for Max Value */ #define PCI_EXT_CAP_LTR_SIZEOF 8 /* Access Control Service */ -- cgit From 9a9eec4765737b9b2a8d6ae03de6480a5f12dd5c Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 18 Oct 2023 14:32:51 +0300 Subject: PCI/DPC: Use FIELD_GET() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use FIELD_GET() to remove dependencies on the field position, i.e., the shift value. No functional change intended. Link: https://lore.kernel.org/r/20231018113254.17616-5-ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen Signed-off-by: Bjorn Helgaas --- drivers/pci/pcie/dpc.c | 5 +++-- drivers/pci/quirks.c | 2 +- include/uapi/linux/pci_regs.h | 1 + 3 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c index 3ceed8e3de41..a5c259ada9ea 100644 --- a/drivers/pci/pcie/dpc.c +++ b/drivers/pci/pcie/dpc.c @@ -9,6 +9,7 @@ #define dev_fmt(fmt) "DPC: " fmt #include +#include #include #include #include @@ -202,7 +203,7 @@ static void dpc_process_rp_pio_error(struct pci_dev *pdev) /* Get First Error Pointer */ pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &dpc_status); - first_error = (dpc_status & 0x1f00) >> 8; + first_error = FIELD_GET(PCI_EXP_DPC_RP_PIO_FEP, dpc_status); for (i = 0; i < ARRAY_SIZE(rp_pio_error_string); i++) { if ((status & ~mask) & (1 << i)) @@ -338,7 +339,7 @@ void pci_dpc_init(struct pci_dev *pdev) /* Quirks may set dpc_rp_log_size if device or firmware is buggy */ if (!pdev->dpc_rp_log_size) { pdev->dpc_rp_log_size = - (cap & PCI_EXP_DPC_RP_PIO_LOG_SIZE) >> 8; + FIELD_GET(PCI_EXP_DPC_RP_PIO_LOG_SIZE, cap); if (pdev->dpc_rp_log_size < 4 || pdev->dpc_rp_log_size > 9) { pci_err(pdev, "RP PIO log size %u is invalid\n", pdev->dpc_rp_log_size); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index eeec1d6f9023..a9fdc2e3f110 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -6154,7 +6154,7 @@ static void dpc_log_size(struct pci_dev *dev) if (!(val & PCI_EXP_DPC_CAP_RP_EXT)) return; - if (!((val & PCI_EXP_DPC_RP_PIO_LOG_SIZE) >> 8)) { + if (FIELD_GET(PCI_EXP_DPC_RP_PIO_LOG_SIZE, val) == 0) { pci_info(dev, "Overriding RP PIO Log Size to 4\n"); dev->dpc_rp_log_size = 4; } diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 495f0ae4ecd5..6c1bad2cb04a 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -1047,6 +1047,7 @@ #define PCI_EXP_DPC_STATUS_INTERRUPT 0x0008 /* Interrupt Status */ #define PCI_EXP_DPC_RP_BUSY 0x0010 /* Root Port Busy */ #define PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT 0x0060 /* Trig Reason Extension */ +#define PCI_EXP_DPC_RP_PIO_FEP 0x1f00 /* RP PIO First Err Ptr */ #define PCI_EXP_DPC_SOURCE_ID 0x0A /* DPC Source Identifier */ -- cgit From 74f0b5ffe172f913c56e4f5291678bad2a55b6b1 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Wed, 18 Oct 2023 14:32:53 +0300 Subject: PCI/DPC: Use defines with DPC reason fields MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add new defines for DPC reason fields and use them instead of literals. Link: https://lore.kernel.org/r/20231018113254.17616-7-ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen [bhelgaas: shorten comments] Signed-off-by: Bjorn Helgaas --- drivers/pci/pcie/dpc.c | 27 +++++++++++++++++---------- include/uapi/linux/pci_regs.h | 6 ++++++ 2 files changed, 23 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c index 0048a11bd119..94111e438241 100644 --- a/drivers/pci/pcie/dpc.c +++ b/drivers/pci/pcie/dpc.c @@ -274,20 +274,27 @@ void dpc_process_error(struct pci_dev *pdev) pci_info(pdev, "containment event, status:%#06x source:%#06x\n", status, source); - reason = (status & PCI_EXP_DPC_STATUS_TRIGGER_RSN) >> 1; - ext_reason = (status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT) >> 5; + reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN; + ext_reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT; pci_warn(pdev, "%s detected\n", - (reason == 0) ? "unmasked uncorrectable error" : - (reason == 1) ? "ERR_NONFATAL" : - (reason == 2) ? "ERR_FATAL" : - (ext_reason == 0) ? "RP PIO error" : - (ext_reason == 1) ? "software trigger" : - "reserved error"); + (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR) ? + "unmasked uncorrectable error" : + (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_NFE) ? + "ERR_NONFATAL" : + (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE) ? + "ERR_FATAL" : + (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO) ? + "RP PIO error" : + (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_SW_TRIGGER) ? + "software trigger" : + "reserved error"); /* show RP PIO error detail information */ - if (pdev->dpc_rp_extensions && reason == 3 && ext_reason == 0) + if (pdev->dpc_rp_extensions && + reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_IN_EXT && + ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO) dpc_process_rp_pio_error(pdev); - else if (reason == 0 && + else if (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR && dpc_get_aer_uncorrect_severity(pdev, &info) && aer_get_device_error_info(pdev, &info)) { aer_print_error(pdev, &info); diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 6c1bad2cb04a..0fd621505246 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -1044,9 +1044,15 @@ #define PCI_EXP_DPC_STATUS 0x08 /* DPC Status */ #define PCI_EXP_DPC_STATUS_TRIGGER 0x0001 /* Trigger Status */ #define PCI_EXP_DPC_STATUS_TRIGGER_RSN 0x0006 /* Trigger Reason */ +#define PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR 0x0000 /* Uncorrectable error */ +#define PCI_EXP_DPC_STATUS_TRIGGER_RSN_NFE 0x0002 /* Rcvd ERR_NONFATAL */ +#define PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE 0x0004 /* Rcvd ERR_FATAL */ +#define PCI_EXP_DPC_STATUS_TRIGGER_RSN_IN_EXT 0x0006 /* Reason in Trig Reason Extension field */ #define PCI_EXP_DPC_STATUS_INTERRUPT 0x0008 /* Interrupt Status */ #define PCI_EXP_DPC_RP_BUSY 0x0010 /* Root Port Busy */ #define PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT 0x0060 /* Trig Reason Extension */ +#define PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO 0x0000 /* RP PIO error */ +#define PCI_EXP_DPC_STATUS_TRIGGER_RSN_SW_TRIGGER 0x0020 /* DPC SW Trigger bit */ #define PCI_EXP_DPC_RP_PIO_FEP 0x1f00 /* RP PIO First Err Ptr */ #define PCI_EXP_DPC_SOURCE_ID 0x0A /* DPC Source Identifier */ -- cgit From 1d0507f46843b14b0cb051fe50ebc7e6432111ab Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Mon, 23 Oct 2023 11:17:07 -0700 Subject: net: mptcp: convert netlink from small_ops to ops in the current MPTCP control plane, all operations use a netlink attribute of the same type "MPTCP_PM_ATTR". However, add/del/get/flush operations only parse the first element in the message _ the one that describes MPTCP endpoints (that was named MPTCP_PM_ATTR_ADDR and mostly used in ADD_ADDR operations _ probably the similarity of "attr", "addr" and "add" might cause some confusion to human readers). Convert MPTCP from 'small_ops' to 'ops', thus allowing different attributes for each single operation, hopefully makes all this clearer to human readers. - use a separate attribute set for add/del/get/flush address operation, binary compatible with the existing one, to store the endpoint address. MPTCP_PM_ENDPOINT_ADDR is added to the uAPI (with the same value as MPTCP_PM_ATTR_ADDR) for these operations. - convert mptcp_pm_ops[] and add policy files accordingly. this prepares MPTCP control plane to be described as YAML spec. Link: https://github.com/multipath-tcp/mptcp_net-next/issues/340 Acked-by: Paolo Abeni Signed-off-by: Davide Caratti Signed-off-by: Mat Martineau Link: https://lore.kernel.org/r/20231023-send-net-next-20231023-1-v2-3-16b1f701f900@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 8 ++ net/mptcp/pm_netlink.c | 191 ++++++++++++++++++++++++++++++--------------- 2 files changed, 135 insertions(+), 64 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index ee9c49f949a2..0e62937ab17c 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -65,6 +65,14 @@ enum { #define MPTCP_PM_ATTR_MAX (__MPTCP_PM_ATTR_MAX - 1) +enum { + MPTCP_PM_ENDPOINT_ADDR = 1, + + __MPTCP_PM_ENDPOINT_MAX +}; + +#define MPTCP_PM_ENDPOINT_MAX (__MPTCP_PM_ENDPOINT_MAX - 1) + enum { MPTCP_PM_ADDR_ATTR_UNSPEC, diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 9661f3812682..fd4e843505e5 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -48,6 +48,60 @@ struct pm_nl_pernet { #define MPTCP_PM_ADDR_MAX 8 #define ADD_ADDR_RETRANS_MAX 3 +static +const struct nla_policy mptcp_pm_address_nl_policy[MPTCP_PM_ADDR_ATTR_IF_IDX + 1] = { + [MPTCP_PM_ADDR_ATTR_FAMILY] = { .type = NLA_U16, }, + [MPTCP_PM_ADDR_ATTR_ID] = { .type = NLA_U8, }, + [MPTCP_PM_ADDR_ATTR_ADDR4] = { .type = NLA_U32, }, + [MPTCP_PM_ADDR_ATTR_ADDR6] = NLA_POLICY_EXACT_LEN(16), + [MPTCP_PM_ADDR_ATTR_PORT] = { .type = NLA_U16, }, + [MPTCP_PM_ADDR_ATTR_FLAGS] = { .type = NLA_U32, }, + [MPTCP_PM_ADDR_ATTR_IF_IDX] = { .type = NLA_S32, }, +}; + +/* MPTCP_PM_CMD_ADD_ADDR / DEL / GET / FLUSH - do */ +static +const struct nla_policy mptcp_pm_endpoint_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1] = { + [MPTCP_PM_ENDPOINT_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_SET_LIMITS - do */ +static +const struct nla_policy mptcp_pm_set_limits_nl_policy[MPTCP_PM_ATTR_SUBFLOWS + 1] = { + [MPTCP_PM_ATTR_RCV_ADD_ADDRS] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_SUBFLOWS] = { .type = NLA_U32, }, +}; + +/* MPTCP_PM_CMD_SET_FLAGS - do */ +static +const struct nla_policy mptcp_pm_set_flags_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1] = { + [MPTCP_PM_ATTR_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_ADDR_REMOTE] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_ANNOUNCE - do */ +static +const struct nla_policy mptcp_pm_announce_nl_policy[MPTCP_PM_ATTR_TOKEN + 1] = { + [MPTCP_PM_ATTR_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, +}; + +/* MPTCP_PM_CMD_REMOVE - do */ +static +const struct nla_policy mptcp_pm_remove_nl_policy[MPTCP_PM_ATTR_LOC_ID + 1] = { + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_LOC_ID] = { .type = NLA_U8, }, +}; + +/* MPTCP_PM_CMD_SUBFLOW_CREATE / DESTROY - do */ +static +const struct nla_policy mptcp_pm_subflow_create_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1] = { + [MPTCP_PM_ATTR_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_ADDR_REMOTE] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + static struct pm_nl_pernet *pm_nl_get_pernet(const struct net *net) { return net_generic(net, pm_nl_pernet_id); @@ -1104,29 +1158,6 @@ static const struct genl_multicast_group mptcp_pm_mcgrps[] = { }, }; -static const struct nla_policy -mptcp_pm_addr_policy[MPTCP_PM_ADDR_ATTR_MAX + 1] = { - [MPTCP_PM_ADDR_ATTR_FAMILY] = { .type = NLA_U16, }, - [MPTCP_PM_ADDR_ATTR_ID] = { .type = NLA_U8, }, - [MPTCP_PM_ADDR_ATTR_ADDR4] = { .type = NLA_U32, }, - [MPTCP_PM_ADDR_ATTR_ADDR6] = - NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), - [MPTCP_PM_ADDR_ATTR_PORT] = { .type = NLA_U16 }, - [MPTCP_PM_ADDR_ATTR_FLAGS] = { .type = NLA_U32 }, - [MPTCP_PM_ADDR_ATTR_IF_IDX] = { .type = NLA_S32 }, -}; - -static const struct nla_policy mptcp_pm_policy[MPTCP_PM_ATTR_MAX + 1] = { - [MPTCP_PM_ATTR_ADDR] = - NLA_POLICY_NESTED(mptcp_pm_addr_policy), - [MPTCP_PM_ATTR_RCV_ADD_ADDRS] = { .type = NLA_U32, }, - [MPTCP_PM_ATTR_SUBFLOWS] = { .type = NLA_U32, }, - [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, - [MPTCP_PM_ATTR_LOC_ID] = { .type = NLA_U8, }, - [MPTCP_PM_ATTR_ADDR_REMOTE] = - NLA_POLICY_NESTED(mptcp_pm_addr_policy), -}; - void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) { struct mptcp_subflow_context *iter, *subflow = mptcp_subflow_ctx(ssk); @@ -1188,7 +1219,7 @@ static int mptcp_pm_parse_pm_addr_attr(struct nlattr *tb[], /* no validation needed - was already done via nested policy */ err = nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr, - mptcp_pm_addr_policy, info->extack); + mptcp_pm_address_nl_policy, info->extack); if (err) return err; @@ -1305,7 +1336,7 @@ next: static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; int ret; @@ -1486,7 +1517,7 @@ next: static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; unsigned int addr_max; @@ -1677,7 +1708,7 @@ nla_put_failure: static int mptcp_nl_cmd_get_addr(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; struct sk_buff *msg; @@ -2283,72 +2314,104 @@ nla_put_failure: nlmsg_free(skb); } -static const struct genl_small_ops mptcp_pm_ops[] = { +static const struct genl_ops mptcp_pm_ops[] = { { - .cmd = MPTCP_PM_CMD_ADD_ADDR, - .doit = mptcp_nl_cmd_add_addr, - .flags = GENL_UNS_ADMIN_PERM, + .cmd = MPTCP_PM_CMD_ADD_ADDR, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_nl_cmd_add_addr, + .policy = mptcp_pm_endpoint_nl_policy, + .maxattr = MPTCP_PM_ENDPOINT_ADDR, + .flags = GENL_UNS_ADMIN_PERM, }, { - .cmd = MPTCP_PM_CMD_DEL_ADDR, - .doit = mptcp_nl_cmd_del_addr, - .flags = GENL_UNS_ADMIN_PERM, + .cmd = MPTCP_PM_CMD_DEL_ADDR, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_nl_cmd_del_addr, + .policy = mptcp_pm_endpoint_nl_policy, + .maxattr = MPTCP_PM_ENDPOINT_ADDR, + .flags = GENL_UNS_ADMIN_PERM, }, { - .cmd = MPTCP_PM_CMD_FLUSH_ADDRS, - .doit = mptcp_nl_cmd_flush_addrs, - .flags = GENL_UNS_ADMIN_PERM, + .cmd = MPTCP_PM_CMD_GET_ADDR, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_nl_cmd_get_addr, + .dumpit = mptcp_nl_cmd_dump_addrs, + .policy = mptcp_pm_endpoint_nl_policy, + .maxattr = MPTCP_PM_ENDPOINT_ADDR, + .flags = GENL_UNS_ADMIN_PERM, }, { - .cmd = MPTCP_PM_CMD_GET_ADDR, - .doit = mptcp_nl_cmd_get_addr, - .dumpit = mptcp_nl_cmd_dump_addrs, + .cmd = MPTCP_PM_CMD_FLUSH_ADDRS, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_nl_cmd_flush_addrs, + .policy = mptcp_pm_endpoint_nl_policy, + .maxattr = MPTCP_PM_ENDPOINT_ADDR, + .flags = GENL_UNS_ADMIN_PERM, }, { - .cmd = MPTCP_PM_CMD_SET_LIMITS, - .doit = mptcp_nl_cmd_set_limits, - .flags = GENL_UNS_ADMIN_PERM, + .cmd = MPTCP_PM_CMD_SET_LIMITS, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_nl_cmd_set_limits, + .policy = mptcp_pm_set_limits_nl_policy, + .maxattr = MPTCP_PM_ATTR_SUBFLOWS, + .flags = GENL_UNS_ADMIN_PERM, }, { - .cmd = MPTCP_PM_CMD_GET_LIMITS, - .doit = mptcp_nl_cmd_get_limits, + .cmd = MPTCP_PM_CMD_GET_LIMITS, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_nl_cmd_get_limits, + .policy = mptcp_pm_set_limits_nl_policy, + .maxattr = MPTCP_PM_ATTR_SUBFLOWS, }, { - .cmd = MPTCP_PM_CMD_SET_FLAGS, - .doit = mptcp_nl_cmd_set_flags, - .flags = GENL_UNS_ADMIN_PERM, + .cmd = MPTCP_PM_CMD_SET_FLAGS, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_nl_cmd_set_flags, + .policy = mptcp_pm_set_flags_nl_policy, + .maxattr = MPTCP_PM_ATTR_ADDR_REMOTE, + .flags = GENL_UNS_ADMIN_PERM, }, { - .cmd = MPTCP_PM_CMD_ANNOUNCE, - .doit = mptcp_nl_cmd_announce, - .flags = GENL_UNS_ADMIN_PERM, + .cmd = MPTCP_PM_CMD_ANNOUNCE, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_nl_cmd_announce, + .policy = mptcp_pm_announce_nl_policy, + .maxattr = MPTCP_PM_ATTR_TOKEN, + .flags = GENL_UNS_ADMIN_PERM, }, { - .cmd = MPTCP_PM_CMD_REMOVE, - .doit = mptcp_nl_cmd_remove, - .flags = GENL_UNS_ADMIN_PERM, + .cmd = MPTCP_PM_CMD_REMOVE, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_nl_cmd_remove, + .policy = mptcp_pm_remove_nl_policy, + .maxattr = MPTCP_PM_ATTR_LOC_ID, + .flags = GENL_UNS_ADMIN_PERM, }, { - .cmd = MPTCP_PM_CMD_SUBFLOW_CREATE, - .doit = mptcp_nl_cmd_sf_create, - .flags = GENL_UNS_ADMIN_PERM, + .cmd = MPTCP_PM_CMD_SUBFLOW_CREATE, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_nl_cmd_sf_create, + .policy = mptcp_pm_subflow_create_nl_policy, + .maxattr = MPTCP_PM_ATTR_ADDR_REMOTE, + .flags = GENL_UNS_ADMIN_PERM, }, { - .cmd = MPTCP_PM_CMD_SUBFLOW_DESTROY, - .doit = mptcp_nl_cmd_sf_destroy, - .flags = GENL_UNS_ADMIN_PERM, + .cmd = MPTCP_PM_CMD_SUBFLOW_DESTROY, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_nl_cmd_sf_destroy, + .policy = mptcp_pm_subflow_create_nl_policy, + .maxattr = MPTCP_PM_ATTR_ADDR_REMOTE, + .flags = GENL_UNS_ADMIN_PERM, }, }; static struct genl_family mptcp_genl_family __ro_after_init = { .name = MPTCP_PM_NAME, .version = MPTCP_PM_VER, - .maxattr = MPTCP_PM_ATTR_MAX, - .policy = mptcp_pm_policy, .netnsok = true, .module = THIS_MODULE, - .small_ops = mptcp_pm_ops, - .n_small_ops = ARRAY_SIZE(mptcp_pm_ops), + .ops = mptcp_pm_ops, + .n_ops = ARRAY_SIZE(mptcp_pm_ops), .resv_start_op = MPTCP_PM_CMD_SUBFLOW_DESTROY + 1, .mcgrps = mptcp_pm_mcgrps, .n_mcgrps = ARRAY_SIZE(mptcp_pm_mcgrps), -- cgit From 9d1ed17f93ce873cda16698267bdee096a768839 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Mon, 23 Oct 2023 11:17:09 -0700 Subject: uapi: mptcp: use header file generated from YAML spec generated with: $ ./tools/net/ynl/ynl-gen-c.py --mode uapi \ > --spec Documentation/netlink/specs/mptcp.yaml \ > --header -o include/uapi/linux/mptcp_pm.h Link: https://github.com/multipath-tcp/mptcp_net-next/issues/340 Acked-by: Paolo Abeni Signed-off-by: Davide Caratti Signed-off-by: Mat Martineau Link: https://lore.kernel.org/r/20231023-send-net-next-20231023-1-v2-5-16b1f701f900@kernel.org Signed-off-by: Jakub Kicinski --- MAINTAINERS | 2 +- include/uapi/linux/mptcp.h | 182 +++--------------------------------------- include/uapi/linux/mptcp_pm.h | 150 ++++++++++++++++++++++++++++++++++ 3 files changed, 161 insertions(+), 173 deletions(-) create mode 100644 include/uapi/linux/mptcp_pm.h (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 977de4624fe0..b2f53d5cae06 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14964,7 +14964,7 @@ F: Documentation/netlink/specs/mptcp.yaml F: Documentation/networking/mptcp-sysctl.rst F: include/net/mptcp.h F: include/trace/events/mptcp.h -F: include/uapi/linux/mptcp.h +F: include/uapi/linux/mptcp*.h F: net/mptcp/ F: tools/testing/selftests/bpf/*/*mptcp*.c F: tools/testing/selftests/net/mptcp/ diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 0e62937ab17c..64ecc8a3f9f2 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -23,99 +23,24 @@ #define MPTCP_SUBFLOW_FLAG_CONNECTED _BITUL(7) #define MPTCP_SUBFLOW_FLAG_MAPVALID _BITUL(8) -enum { - MPTCP_SUBFLOW_ATTR_UNSPEC, - MPTCP_SUBFLOW_ATTR_TOKEN_REM, - MPTCP_SUBFLOW_ATTR_TOKEN_LOC, - MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ, - MPTCP_SUBFLOW_ATTR_MAP_SEQ, - MPTCP_SUBFLOW_ATTR_MAP_SFSEQ, - MPTCP_SUBFLOW_ATTR_SSN_OFFSET, - MPTCP_SUBFLOW_ATTR_MAP_DATALEN, - MPTCP_SUBFLOW_ATTR_FLAGS, - MPTCP_SUBFLOW_ATTR_ID_REM, - MPTCP_SUBFLOW_ATTR_ID_LOC, - MPTCP_SUBFLOW_ATTR_PAD, - __MPTCP_SUBFLOW_ATTR_MAX -}; - -#define MPTCP_SUBFLOW_ATTR_MAX (__MPTCP_SUBFLOW_ATTR_MAX - 1) - -/* netlink interface */ -#define MPTCP_PM_NAME "mptcp_pm" #define MPTCP_PM_CMD_GRP_NAME "mptcp_pm_cmds" #define MPTCP_PM_EV_GRP_NAME "mptcp_pm_events" -#define MPTCP_PM_VER 0x1 - -/* - * ATTR types defined for MPTCP - */ -enum { - MPTCP_PM_ATTR_UNSPEC, - - MPTCP_PM_ATTR_ADDR, /* nested address */ - MPTCP_PM_ATTR_RCV_ADD_ADDRS, /* u32 */ - MPTCP_PM_ATTR_SUBFLOWS, /* u32 */ - MPTCP_PM_ATTR_TOKEN, /* u32 */ - MPTCP_PM_ATTR_LOC_ID, /* u8 */ - MPTCP_PM_ATTR_ADDR_REMOTE, /* nested address */ - - __MPTCP_PM_ATTR_MAX -}; - -#define MPTCP_PM_ATTR_MAX (__MPTCP_PM_ATTR_MAX - 1) - -enum { - MPTCP_PM_ENDPOINT_ADDR = 1, - - __MPTCP_PM_ENDPOINT_MAX -}; - -#define MPTCP_PM_ENDPOINT_MAX (__MPTCP_PM_ENDPOINT_MAX - 1) - -enum { - MPTCP_PM_ADDR_ATTR_UNSPEC, - - MPTCP_PM_ADDR_ATTR_FAMILY, /* u16 */ - MPTCP_PM_ADDR_ATTR_ID, /* u8 */ - MPTCP_PM_ADDR_ATTR_ADDR4, /* struct in_addr */ - MPTCP_PM_ADDR_ATTR_ADDR6, /* struct in6_addr */ - MPTCP_PM_ADDR_ATTR_PORT, /* u16 */ - MPTCP_PM_ADDR_ATTR_FLAGS, /* u32 */ - MPTCP_PM_ADDR_ATTR_IF_IDX, /* s32 */ - - __MPTCP_PM_ADDR_ATTR_MAX -}; -#define MPTCP_PM_ADDR_ATTR_MAX (__MPTCP_PM_ADDR_ATTR_MAX - 1) +#include -#define MPTCP_PM_ADDR_FLAG_SIGNAL (1 << 0) -#define MPTCP_PM_ADDR_FLAG_SUBFLOW (1 << 1) -#define MPTCP_PM_ADDR_FLAG_BACKUP (1 << 2) -#define MPTCP_PM_ADDR_FLAG_FULLMESH (1 << 3) -#define MPTCP_PM_ADDR_FLAG_IMPLICIT (1 << 4) - -enum { - MPTCP_PM_CMD_UNSPEC, - - MPTCP_PM_CMD_ADD_ADDR, - MPTCP_PM_CMD_DEL_ADDR, - MPTCP_PM_CMD_GET_ADDR, - MPTCP_PM_CMD_FLUSH_ADDRS, - MPTCP_PM_CMD_SET_LIMITS, - MPTCP_PM_CMD_GET_LIMITS, - MPTCP_PM_CMD_SET_FLAGS, - MPTCP_PM_CMD_ANNOUNCE, - MPTCP_PM_CMD_REMOVE, - MPTCP_PM_CMD_SUBFLOW_CREATE, - MPTCP_PM_CMD_SUBFLOW_DESTROY, - - __MPTCP_PM_CMD_AFTER_LAST -}; +/* for backward compatibility */ +#define __MPTCP_PM_CMD_AFTER_LAST __MPTCP_PM_CMD_MAX +#define __MPTCP_ATTR_AFTER_LAST __MPTCP_ATTR_MAX #define MPTCP_INFO_FLAG_FALLBACK _BITUL(0) #define MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED _BITUL(1) +#define MPTCP_PM_ADDR_FLAG_SIGNAL (1 << 0) +#define MPTCP_PM_ADDR_FLAG_SUBFLOW (1 << 1) +#define MPTCP_PM_ADDR_FLAG_BACKUP (1 << 2) +#define MPTCP_PM_ADDR_FLAG_FULLMESH (1 << 3) +#define MPTCP_PM_ADDR_FLAG_IMPLICIT (1 << 4) + struct mptcp_info { __u8 mptcpi_subflows; __u8 mptcpi_add_addr_signal; @@ -138,93 +63,6 @@ struct mptcp_info { __u64 mptcpi_bytes_acked; }; -/* - * MPTCP_EVENT_CREATED: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport - * A new MPTCP connection has been created. It is the good time to allocate - * memory and send ADD_ADDR if needed. Depending on the traffic-patterns - * it can take a long time until the MPTCP_EVENT_ESTABLISHED is sent. - * - * MPTCP_EVENT_ESTABLISHED: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport - * A MPTCP connection is established (can start new subflows). - * - * MPTCP_EVENT_CLOSED: token - * A MPTCP connection has stopped. - * - * MPTCP_EVENT_ANNOUNCED: token, rem_id, family, daddr4 | daddr6 [, dport] - * A new address has been announced by the peer. - * - * MPTCP_EVENT_REMOVED: token, rem_id - * An address has been lost by the peer. - * - * MPTCP_EVENT_SUB_ESTABLISHED: token, family, loc_id, rem_id, - * saddr4 | saddr6, daddr4 | daddr6, sport, - * dport, backup, if_idx [, error] - * A new subflow has been established. 'error' should not be set. - * - * MPTCP_EVENT_SUB_CLOSED: token, family, loc_id, rem_id, saddr4 | saddr6, - * daddr4 | daddr6, sport, dport, backup, if_idx - * [, error] - * A subflow has been closed. An error (copy of sk_err) could be set if an - * error has been detected for this subflow. - * - * MPTCP_EVENT_SUB_PRIORITY: token, family, loc_id, rem_id, saddr4 | saddr6, - * daddr4 | daddr6, sport, dport, backup, if_idx - * [, error] - * The priority of a subflow has changed. 'error' should not be set. - * - * MPTCP_EVENT_LISTENER_CREATED: family, sport, saddr4 | saddr6 - * A new PM listener is created. - * - * MPTCP_EVENT_LISTENER_CLOSED: family, sport, saddr4 | saddr6 - * A PM listener is closed. - */ -enum mptcp_event_type { - MPTCP_EVENT_UNSPEC = 0, - MPTCP_EVENT_CREATED = 1, - MPTCP_EVENT_ESTABLISHED = 2, - MPTCP_EVENT_CLOSED = 3, - - MPTCP_EVENT_ANNOUNCED = 6, - MPTCP_EVENT_REMOVED = 7, - - MPTCP_EVENT_SUB_ESTABLISHED = 10, - MPTCP_EVENT_SUB_CLOSED = 11, - - MPTCP_EVENT_SUB_PRIORITY = 13, - - MPTCP_EVENT_LISTENER_CREATED = 15, - MPTCP_EVENT_LISTENER_CLOSED = 16, -}; - -enum mptcp_event_attr { - MPTCP_ATTR_UNSPEC = 0, - - MPTCP_ATTR_TOKEN, /* u32 */ - MPTCP_ATTR_FAMILY, /* u16 */ - MPTCP_ATTR_LOC_ID, /* u8 */ - MPTCP_ATTR_REM_ID, /* u8 */ - MPTCP_ATTR_SADDR4, /* be32 */ - MPTCP_ATTR_SADDR6, /* struct in6_addr */ - MPTCP_ATTR_DADDR4, /* be32 */ - MPTCP_ATTR_DADDR6, /* struct in6_addr */ - MPTCP_ATTR_SPORT, /* be16 */ - MPTCP_ATTR_DPORT, /* be16 */ - MPTCP_ATTR_BACKUP, /* u8 */ - MPTCP_ATTR_ERROR, /* u8 */ - MPTCP_ATTR_FLAGS, /* u16 */ - MPTCP_ATTR_TIMEOUT, /* u32 */ - MPTCP_ATTR_IF_IDX, /* s32 */ - MPTCP_ATTR_RESET_REASON,/* u32 */ - MPTCP_ATTR_RESET_FLAGS, /* u32 */ - MPTCP_ATTR_SERVER_SIDE, /* u8 */ - - __MPTCP_ATTR_AFTER_LAST -}; - -#define MPTCP_ATTR_MAX (__MPTCP_ATTR_AFTER_LAST - 1) - /* MPTCP Reset reason codes, rfc8684 */ #define MPTCP_RST_EUNSPEC 0 #define MPTCP_RST_EMPTCP 1 diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h new file mode 100644 index 000000000000..0ad598fe940b --- /dev/null +++ b/include/uapi/linux/mptcp_pm.h @@ -0,0 +1,150 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/mptcp.yaml */ +/* YNL-GEN uapi header */ + +#ifndef _UAPI_LINUX_MPTCP_PM_H +#define _UAPI_LINUX_MPTCP_PM_H + +#define MPTCP_PM_NAME "mptcp_pm" +#define MPTCP_PM_VER 1 + +/** + * enum mptcp_event_type + * @MPTCP_EVENT_UNSPEC: unused event + * @MPTCP_EVENT_CREATED: token, family, saddr4 | saddr6, daddr4 | daddr6, + * sport, dport A new MPTCP connection has been created. It is the good time + * to allocate memory and send ADD_ADDR if needed. Depending on the + * traffic-patterns it can take a long time until the MPTCP_EVENT_ESTABLISHED + * is sent. + * @MPTCP_EVENT_ESTABLISHED: token, family, saddr4 | saddr6, daddr4 | daddr6, + * sport, dport A MPTCP connection is established (can start new subflows). + * @MPTCP_EVENT_CLOSED: token A MPTCP connection has stopped. + * @MPTCP_EVENT_ANNOUNCED: token, rem_id, family, daddr4 | daddr6 [, dport] A + * new address has been announced by the peer. + * @MPTCP_EVENT_REMOVED: token, rem_id An address has been lost by the peer. + * @MPTCP_EVENT_SUB_ESTABLISHED: token, family, loc_id, rem_id, saddr4 | + * saddr6, daddr4 | daddr6, sport, dport, backup, if_idx [, error] A new + * subflow has been established. 'error' should not be set. + * @MPTCP_EVENT_SUB_CLOSED: token, family, loc_id, rem_id, saddr4 | saddr6, + * daddr4 | daddr6, sport, dport, backup, if_idx [, error] A subflow has been + * closed. An error (copy of sk_err) could be set if an error has been + * detected for this subflow. + * @MPTCP_EVENT_SUB_PRIORITY: token, family, loc_id, rem_id, saddr4 | saddr6, + * daddr4 | daddr6, sport, dport, backup, if_idx [, error] The priority of a + * subflow has changed. 'error' should not be set. + * @MPTCP_EVENT_LISTENER_CREATED: family, sport, saddr4 | saddr6 A new PM + * listener is created. + * @MPTCP_EVENT_LISTENER_CLOSED: family, sport, saddr4 | saddr6 A PM listener + * is closed. + */ +enum mptcp_event_type { + MPTCP_EVENT_UNSPEC, + MPTCP_EVENT_CREATED, + MPTCP_EVENT_ESTABLISHED, + MPTCP_EVENT_CLOSED, + MPTCP_EVENT_ANNOUNCED = 6, + MPTCP_EVENT_REMOVED, + MPTCP_EVENT_SUB_ESTABLISHED = 10, + MPTCP_EVENT_SUB_CLOSED, + MPTCP_EVENT_SUB_PRIORITY = 13, + MPTCP_EVENT_LISTENER_CREATED = 15, + MPTCP_EVENT_LISTENER_CLOSED, +}; + +enum { + MPTCP_PM_ADDR_ATTR_UNSPEC, + MPTCP_PM_ADDR_ATTR_FAMILY, + MPTCP_PM_ADDR_ATTR_ID, + MPTCP_PM_ADDR_ATTR_ADDR4, + MPTCP_PM_ADDR_ATTR_ADDR6, + MPTCP_PM_ADDR_ATTR_PORT, + MPTCP_PM_ADDR_ATTR_FLAGS, + MPTCP_PM_ADDR_ATTR_IF_IDX, + + __MPTCP_PM_ADDR_ATTR_MAX +}; +#define MPTCP_PM_ADDR_ATTR_MAX (__MPTCP_PM_ADDR_ATTR_MAX - 1) + +enum { + MPTCP_SUBFLOW_ATTR_UNSPEC, + MPTCP_SUBFLOW_ATTR_TOKEN_REM, + MPTCP_SUBFLOW_ATTR_TOKEN_LOC, + MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ, + MPTCP_SUBFLOW_ATTR_MAP_SEQ, + MPTCP_SUBFLOW_ATTR_MAP_SFSEQ, + MPTCP_SUBFLOW_ATTR_SSN_OFFSET, + MPTCP_SUBFLOW_ATTR_MAP_DATALEN, + MPTCP_SUBFLOW_ATTR_FLAGS, + MPTCP_SUBFLOW_ATTR_ID_REM, + MPTCP_SUBFLOW_ATTR_ID_LOC, + MPTCP_SUBFLOW_ATTR_PAD, + + __MPTCP_SUBFLOW_ATTR_MAX +}; +#define MPTCP_SUBFLOW_ATTR_MAX (__MPTCP_SUBFLOW_ATTR_MAX - 1) + +enum { + MPTCP_PM_ENDPOINT_ADDR = 1, + + __MPTCP_PM_ENDPOINT_MAX +}; +#define MPTCP_PM_ENDPOINT_MAX (__MPTCP_PM_ENDPOINT_MAX - 1) + +enum { + MPTCP_PM_ATTR_UNSPEC, + MPTCP_PM_ATTR_ADDR, + MPTCP_PM_ATTR_RCV_ADD_ADDRS, + MPTCP_PM_ATTR_SUBFLOWS, + MPTCP_PM_ATTR_TOKEN, + MPTCP_PM_ATTR_LOC_ID, + MPTCP_PM_ATTR_ADDR_REMOTE, + + __MPTCP_PM_ATTR_MAX +}; +#define MPTCP_PM_ATTR_MAX (__MPTCP_PM_ATTR_MAX - 1) + +enum mptcp_event_attr { + MPTCP_ATTR_UNSPEC, + MPTCP_ATTR_TOKEN, + MPTCP_ATTR_FAMILY, + MPTCP_ATTR_LOC_ID, + MPTCP_ATTR_REM_ID, + MPTCP_ATTR_SADDR4, + MPTCP_ATTR_SADDR6, + MPTCP_ATTR_DADDR4, + MPTCP_ATTR_DADDR6, + MPTCP_ATTR_SPORT, + MPTCP_ATTR_DPORT, + MPTCP_ATTR_BACKUP, + MPTCP_ATTR_ERROR, + MPTCP_ATTR_FLAGS, + MPTCP_ATTR_TIMEOUT, + MPTCP_ATTR_IF_IDX, + MPTCP_ATTR_RESET_REASON, + MPTCP_ATTR_RESET_FLAGS, + MPTCP_ATTR_SERVER_SIDE, + + __MPTCP_ATTR_MAX +}; +#define MPTCP_ATTR_MAX (__MPTCP_ATTR_MAX - 1) + +enum { + MPTCP_PM_CMD_UNSPEC, + MPTCP_PM_CMD_ADD_ADDR, + MPTCP_PM_CMD_DEL_ADDR, + MPTCP_PM_CMD_GET_ADDR, + MPTCP_PM_CMD_FLUSH_ADDRS, + MPTCP_PM_CMD_SET_LIMITS, + MPTCP_PM_CMD_GET_LIMITS, + MPTCP_PM_CMD_SET_FLAGS, + MPTCP_PM_CMD_ANNOUNCE, + MPTCP_PM_CMD_REMOVE, + MPTCP_PM_CMD_SUBFLOW_CREATE, + MPTCP_PM_CMD_SUBFLOW_DESTROY, + + __MPTCP_PM_CMD_MAX +}; +#define MPTCP_PM_CMD_MAX (__MPTCP_PM_CMD_MAX - 1) + +#endif /* _UAPI_LINUX_MPTCP_PM_H */ -- cgit From 87cd83714f30ef2f19f0390e98beb8d78e173f0f Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 23 Oct 2023 11:17:29 -0700 Subject: net: dsa: Rename IFLA_DSA_MASTER to IFLA_DSA_CONDUIT This preserves the existing IFLA_DSA_MASTER which is part of the uAPI and creates an alias named IFLA_DSA_CONDUIT. Reviewed-by: Andrew Lunn Reviewed-by: Vladimir Oltean Signed-off-by: Florian Fainelli Link: https://lore.kernel.org/r/20231023181729.1191071-3-florian.fainelli@broadcom.com Signed-off-by: Jakub Kicinski --- Documentation/networking/dsa/configuration.rst | 4 ++-- include/uapi/linux/if_link.h | 4 +++- net/dsa/netlink.c | 10 +++++----- 3 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/dsa/configuration.rst b/Documentation/networking/dsa/configuration.rst index e6c9719874b0..6cc4ded3cc23 100644 --- a/Documentation/networking/dsa/configuration.rst +++ b/Documentation/networking/dsa/configuration.rst @@ -393,7 +393,7 @@ description which has an ``ethernet`` property. It is up to the user to configure the system for the switch to use other conduits. DSA uses the ``rtnl_link_ops`` mechanism (with a "dsa" ``kind``) to allow -changing the DSA conduit of a user port. The ``IFLA_DSA_MASTER`` u32 netlink +changing the DSA conduit of a user port. The ``IFLA_DSA_CONDUIT`` u32 netlink attribute contains the ifindex of the conduit device that handles each user device. The DSA conduit must be a valid candidate based on firmware node information, or a LAG interface which contains only slaves which are valid @@ -435,7 +435,7 @@ Using iproute2, the following manipulations are possible: dsa master bond0 Notice that in the case of CPU ports under a LAG, the use of the -``IFLA_DSA_MASTER`` netlink attribute is not strictly needed, but rather, DSA +``IFLA_DSA_CONDUIT`` netlink attribute is not strictly needed, but rather, DSA reacts to the ``IFLA_MASTER`` attribute change of its present conduit (``eth0``) and migrates all user ports to the new upper of ``eth0``, ``bond0``. Similarly, when ``bond0`` is destroyed using ``RTM_DELLINK``, DSA migrates the user ports diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 9f8a3da0f14f..f4191be137a4 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1394,7 +1394,9 @@ enum { enum { IFLA_DSA_UNSPEC, - IFLA_DSA_MASTER, + IFLA_DSA_CONDUIT, + /* Deprecated, use IFLA_DSA_CONDUIT instead */ + IFLA_DSA_MASTER = IFLA_DSA_CONDUIT, __IFLA_DSA_MAX, }; diff --git a/net/dsa/netlink.c b/net/dsa/netlink.c index f56f90a25b99..1332e56349e5 100644 --- a/net/dsa/netlink.c +++ b/net/dsa/netlink.c @@ -8,7 +8,7 @@ #include "user.h" static const struct nla_policy dsa_policy[IFLA_DSA_MAX + 1] = { - [IFLA_DSA_MASTER] = { .type = NLA_U32 }, + [IFLA_DSA_CONDUIT] = { .type = NLA_U32 }, }; static int dsa_changelink(struct net_device *dev, struct nlattr *tb[], @@ -20,8 +20,8 @@ static int dsa_changelink(struct net_device *dev, struct nlattr *tb[], if (!data) return 0; - if (data[IFLA_DSA_MASTER]) { - u32 ifindex = nla_get_u32(data[IFLA_DSA_MASTER]); + if (data[IFLA_DSA_CONDUIT]) { + u32 ifindex = nla_get_u32(data[IFLA_DSA_CONDUIT]); struct net_device *conduit; conduit = __dev_get_by_index(dev_net(dev), ifindex); @@ -38,7 +38,7 @@ static int dsa_changelink(struct net_device *dev, struct nlattr *tb[], static size_t dsa_get_size(const struct net_device *dev) { - return nla_total_size(sizeof(u32)) + /* IFLA_DSA_MASTER */ + return nla_total_size(sizeof(u32)) + /* IFLA_DSA_CONDUIT */ 0; } @@ -46,7 +46,7 @@ static int dsa_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct net_device *conduit = dsa_user_to_conduit(dev); - if (nla_put_u32(skb, IFLA_DSA_MASTER, conduit->ifindex)) + if (nla_put_u32(skb, IFLA_DSA_CONDUIT, conduit->ifindex)) return -EMSGSIZE; return 0; -- cgit From d30fea25845ff65ea1fb255d7b615cd02b65095b Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 10 Oct 2023 15:44:30 -0500 Subject: PCI/ATS: Show PASID Capability register width in bitmasks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The PASID Capability and Control registers are both 16 bits wide. Use 16-bit wide constants in field names to match the register width. No functional change intended. Link: https://lore.kernel.org/r/20231010204436.1000644-5-helgaas@kernel.org Signed-off-by: Bjorn Helgaas Reviewed-by: Ilpo Järvinen Reviewed-by: Jonathan Cameron Reviewed-by: Kuppuswamy Sathyanarayanan --- include/uapi/linux/pci_regs.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 0fd621505246..f35d73efe223 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -930,12 +930,12 @@ /* Process Address Space ID */ #define PCI_PASID_CAP 0x04 /* PASID feature register */ -#define PCI_PASID_CAP_EXEC 0x02 /* Exec permissions Supported */ -#define PCI_PASID_CAP_PRIV 0x04 /* Privilege Mode Supported */ +#define PCI_PASID_CAP_EXEC 0x0002 /* Exec permissions Supported */ +#define PCI_PASID_CAP_PRIV 0x0004 /* Privilege Mode Supported */ #define PCI_PASID_CTRL 0x06 /* PASID control register */ -#define PCI_PASID_CTRL_ENABLE 0x01 /* Enable bit */ -#define PCI_PASID_CTRL_EXEC 0x02 /* Exec permissions Enable */ -#define PCI_PASID_CTRL_PRIV 0x04 /* Privilege Mode Enable */ +#define PCI_PASID_CTRL_ENABLE 0x0001 /* Enable bit */ +#define PCI_PASID_CTRL_EXEC 0x0002 /* Exec permissions Enable */ +#define PCI_PASID_CTRL_PRIV 0x0004 /* Privilege Mode Enable */ #define PCI_EXT_CAP_PASID_SIZEOF 8 /* Single Root I/O Virtualization */ -- cgit From e0701bd0e6669e4c4b0d11254f5948ebf8d0b732 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 10 Oct 2023 15:44:31 -0500 Subject: PCI/ATS: Use FIELD_GET() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use FIELD_GET() to remove dependences on the field position, i.e., the shift value. No functional change intended. Link: https://lore.kernel.org/r/20231010204436.1000644-6-helgaas@kernel.org Signed-off-by: Bjorn Helgaas Reviewed-by: Jonathan Cameron Reviewed-by: Ilpo Järvinen Reviewed-by: Kuppuswamy Sathyanarayanan --- drivers/pci/ats.c | 7 ++----- include/uapi/linux/pci_regs.h | 1 + 2 files changed, 3 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index f9cc2e10b676..c570892b2090 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -9,6 +9,7 @@ * Copyright (C) 2011 Advanced Micro Devices, */ +#include #include #include #include @@ -480,8 +481,6 @@ int pci_pasid_features(struct pci_dev *pdev) } EXPORT_SYMBOL_GPL(pci_pasid_features); -#define PASID_NUMBER_SHIFT 8 -#define PASID_NUMBER_MASK (0x1f << PASID_NUMBER_SHIFT) /** * pci_max_pasids - Get maximum number of PASIDs supported by device * @pdev: PCI device structure @@ -503,9 +502,7 @@ int pci_max_pasids(struct pci_dev *pdev) pci_read_config_word(pdev, pasid + PCI_PASID_CAP, &supported); - supported = (supported & PASID_NUMBER_MASK) >> PASID_NUMBER_SHIFT; - - return (1 << supported); + return (1 << FIELD_GET(PCI_PASID_CAP_WIDTH, supported)); } EXPORT_SYMBOL_GPL(pci_max_pasids); #endif /* CONFIG_PCI_PASID */ diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index f35d73efe223..4f226db4c1dc 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -932,6 +932,7 @@ #define PCI_PASID_CAP 0x04 /* PASID feature register */ #define PCI_PASID_CAP_EXEC 0x0002 /* Exec permissions Supported */ #define PCI_PASID_CAP_PRIV 0x0004 /* Privilege Mode Supported */ +#define PCI_PASID_CAP_WIDTH 0x1f00 #define PCI_PASID_CTRL 0x06 /* PASID control register */ #define PCI_PASID_CTRL_ENABLE 0x0001 /* Enable bit */ #define PCI_PASID_CTRL_EXEC 0x0002 /* Exec permissions Enable */ -- cgit From ec302b118a59785511d6f90592a8be097d67341c Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 10 Oct 2023 15:44:33 -0500 Subject: PCI/PME: Use FIELD_GET() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use FIELD_GET() to remove dependences on the field position, i.e., the shift value. No functional change intended. Link: https://lore.kernel.org/r/20231010204436.1000644-8-helgaas@kernel.org Signed-off-by: Bjorn Helgaas Reviewed-by: Ilpo Järvinen Reviewed-by: Jonathan Cameron Reviewed-by: Kuppuswamy Sathyanarayanan --- drivers/pci/pcie/pme.c | 4 +++- include/uapi/linux/pci_regs.h | 1 + 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c index ef8ce436ead9..a2daebd9806c 100644 --- a/drivers/pci/pcie/pme.c +++ b/drivers/pci/pcie/pme.c @@ -9,6 +9,7 @@ #define dev_fmt(fmt) "PME: " fmt +#include #include #include #include @@ -235,7 +236,8 @@ static void pcie_pme_work_fn(struct work_struct *work) pcie_clear_root_pme_status(port); spin_unlock_irq(&data->lock); - pcie_pme_handle_request(port, rtsta & 0xffff); + pcie_pme_handle_request(port, + FIELD_GET(PCI_EXP_RTSTA_PME_RQ_ID, rtsta)); spin_lock_irq(&data->lock); continue; diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 4f226db4c1dc..532d30770ee5 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -637,6 +637,7 @@ #define PCI_EXP_RTCAP 0x1e /* Root Capabilities */ #define PCI_EXP_RTCAP_CRSVIS 0x0001 /* CRS Software Visibility capability */ #define PCI_EXP_RTSTA 0x20 /* Root Status */ +#define PCI_EXP_RTSTA_PME_RQ_ID 0x0000ffff /* PME Requester ID */ #define PCI_EXP_RTSTA_PME 0x00010000 /* PME status */ #define PCI_EXP_RTSTA_PENDING 0x00020000 /* PME pending */ /* -- cgit From 35dfaad7188cdc043fde31709c796f5a692ba2bd Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 24 Oct 2023 23:48:58 +0200 Subject: netkit, bpf: Add bpf programmable net device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This work adds a new, minimal BPF-programmable device called "netkit" (former PoC code-name "meta") we recently presented at LSF/MM/BPF. The core idea is that BPF programs are executed within the drivers xmit routine and therefore e.g. in case of containers/Pods moving BPF processing closer to the source. One of the goals was that in case of Pod egress traffic, this allows to move BPF programs from hostns tcx ingress into the device itself, providing earlier drop or forward mechanisms, for example, if the BPF program determines that the skb must be sent out of the node, then a redirect to the physical device can take place directly without going through per-CPU backlog queue. This helps to shift processing for such traffic from softirq to process context, leading to better scheduling decisions/performance (see measurements in the slides). In this initial version, the netkit device ships as a pair, but we plan to extend this further so it can also operate in single device mode. The pair comes with a primary and a peer device. Only the primary device, typically residing in hostns, can manage BPF programs for itself and its peer. The peer device is designated for containers/Pods and cannot attach/detach BPF programs. Upon the device creation, the user can set the default policy to 'pass' or 'drop' for the case when no BPF program is attached. Additionally, the device can be operated in L3 (default) or L2 mode. The management of BPF programs is done via bpf_mprog, so that multi-attach is supported right from the beginning with similar API and dependency controls as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic attach/detach/query API for multi-progs"). tc BPF compatibility is provided, so that existing programs can be easily migrated. Going forward, we plan to use netkit devices in Cilium as the main device type for connecting Pods. They will be operated in L3 mode in order to simplify a Pod's neighbor management and the peer will operate in default drop mode, so that no traffic is leaving between the time when a Pod is brought up by the CNI plugin and programs attached by the agent. Additionally, the programs we attach via tcx on the physical devices are using bpf_redirect_peer() for inbound traffic into netkit device, hence the latter is also supporting the ndo_get_peer_dev callback. Similarly, we use bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device directly. Also, BIG TCP is supported on netkit device. For the follow-up work in single device mode, we plan to convert Cilium's cilium_host/_net devices into a single one. An extensive test suite for checking device operations and the BPF program and link management API comes as BPF selftests in this series. Co-developed-by: Nikolay Aleksandrov Signed-off-by: Nikolay Aleksandrov Signed-off-by: Daniel Borkmann Reviewed-by: Toke Høiland-Jørgensen Acked-by: Stanislav Fomichev Acked-by: Martin KaFai Lau Link: https://github.com/borkmann/iproute2/tree/pr/netkit Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.) Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net Signed-off-by: Martin KaFai Lau --- MAINTAINERS | 9 + drivers/net/Kconfig | 9 + drivers/net/Makefile | 1 + drivers/net/netkit.c | 940 +++++++++++++++++++++++++++++++++++++++++ include/net/netkit.h | 38 ++ include/uapi/linux/bpf.h | 14 + include/uapi/linux/if_link.h | 24 ++ kernel/bpf/syscall.c | 30 +- tools/include/uapi/linux/bpf.h | 14 + 9 files changed, 1074 insertions(+), 5 deletions(-) create mode 100644 drivers/net/netkit.c create mode 100644 include/net/netkit.h (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index ed33b9df8b3d..43be6197e655 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3795,6 +3795,15 @@ L: bpf@vger.kernel.org S: Odd Fixes K: (?:\b|_)bpf(?:\b|_) +BPF [NETKIT] (BPF-programmable network device) +M: Daniel Borkmann +M: Nikolay Aleksandrov +L: bpf@vger.kernel.org +L: netdev@vger.kernel.org +S: Supported +F: drivers/net/netkit.c +F: include/net/netkit.h + BPF [NETWORKING] (struct_ops, reuseport) M: Martin KaFai Lau L: bpf@vger.kernel.org diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 44eeb5d61ba9..af0da4bb429b 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -448,6 +448,15 @@ config NLMON diagnostics, etc. This is mostly intended for developers or support to debug netlink issues. If unsure, say N. +config NETKIT + bool "BPF-programmable network device" + depends on BPF_SYSCALL + help + The netkit device is a virtual networking device where BPF programs + can be attached to the device(s) transmission routine in order to + implement the driver's internal logic. The device can be configured + to operate in L3 or L2 mode. If unsure, say N. + config NET_VRF tristate "Virtual Routing and Forwarding (Lite)" depends on IP_MULTIPLE_TABLES diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 8a83db32509d..7cab36f94782 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -22,6 +22,7 @@ obj-$(CONFIG_MDIO) += mdio.o obj-$(CONFIG_NET) += loopback.o obj-$(CONFIG_NETDEV_LEGACY_INIT) += Space.o obj-$(CONFIG_NETCONSOLE) += netconsole.o +obj-$(CONFIG_NETKIT) += netkit.o obj-y += phy/ obj-y += pse-pd/ obj-y += mdio/ diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c new file mode 100644 index 000000000000..7e484f9fd3ae --- /dev/null +++ b/drivers/net/netkit.c @@ -0,0 +1,940 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2023 Isovalent */ + +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#define DRV_NAME "netkit" + +struct netkit { + /* Needed in fast-path */ + struct net_device __rcu *peer; + struct bpf_mprog_entry __rcu *active; + enum netkit_action policy; + struct bpf_mprog_bundle bundle; + + /* Needed in slow-path */ + enum netkit_mode mode; + bool primary; + u32 headroom; +}; + +struct netkit_link { + struct bpf_link link; + struct net_device *dev; + u32 location; +}; + +static __always_inline int +netkit_run(const struct bpf_mprog_entry *entry, struct sk_buff *skb, + enum netkit_action ret) +{ + const struct bpf_mprog_fp *fp; + const struct bpf_prog *prog; + + bpf_mprog_foreach_prog(entry, fp, prog) { + bpf_compute_data_pointers(skb); + ret = bpf_prog_run(prog, skb); + if (ret != NETKIT_NEXT) + break; + } + return ret; +} + +static void netkit_prep_forward(struct sk_buff *skb, bool xnet) +{ + skb_scrub_packet(skb, xnet); + skb->priority = 0; + nf_skip_egress(skb, true); +} + +static struct netkit *netkit_priv(const struct net_device *dev) +{ + return netdev_priv(dev); +} + +static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct netkit *nk = netkit_priv(dev); + enum netkit_action ret = READ_ONCE(nk->policy); + netdev_tx_t ret_dev = NET_XMIT_SUCCESS; + const struct bpf_mprog_entry *entry; + struct net_device *peer; + + rcu_read_lock(); + peer = rcu_dereference(nk->peer); + if (unlikely(!peer || !(peer->flags & IFF_UP) || + !pskb_may_pull(skb, ETH_HLEN) || + skb_orphan_frags(skb, GFP_ATOMIC))) + goto drop; + netkit_prep_forward(skb, !net_eq(dev_net(dev), dev_net(peer))); + skb->dev = peer; + entry = rcu_dereference(nk->active); + if (entry) + ret = netkit_run(entry, skb, ret); + switch (ret) { + case NETKIT_NEXT: + case NETKIT_PASS: + skb->protocol = eth_type_trans(skb, skb->dev); + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); + __netif_rx(skb); + break; + case NETKIT_REDIRECT: + skb_do_redirect(skb); + break; + case NETKIT_DROP: + default: +drop: + kfree_skb(skb); + dev_core_stats_tx_dropped_inc(dev); + ret_dev = NET_XMIT_DROP; + break; + } + rcu_read_unlock(); + return ret_dev; +} + +static int netkit_open(struct net_device *dev) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer = rtnl_dereference(nk->peer); + + if (!peer) + return -ENOTCONN; + if (peer->flags & IFF_UP) { + netif_carrier_on(dev); + netif_carrier_on(peer); + } + return 0; +} + +static int netkit_close(struct net_device *dev) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer = rtnl_dereference(nk->peer); + + netif_carrier_off(dev); + if (peer) + netif_carrier_off(peer); + return 0; +} + +static int netkit_get_iflink(const struct net_device *dev) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer; + int iflink = 0; + + rcu_read_lock(); + peer = rcu_dereference(nk->peer); + if (peer) + iflink = peer->ifindex; + rcu_read_unlock(); + return iflink; +} + +static void netkit_set_multicast(struct net_device *dev) +{ + /* Nothing to do, we receive whatever gets pushed to us! */ +} + +static void netkit_set_headroom(struct net_device *dev, int headroom) +{ + struct netkit *nk = netkit_priv(dev), *nk2; + struct net_device *peer; + + if (headroom < 0) + headroom = NET_SKB_PAD; + + rcu_read_lock(); + peer = rcu_dereference(nk->peer); + if (unlikely(!peer)) + goto out; + + nk2 = netkit_priv(peer); + nk->headroom = headroom; + headroom = max(nk->headroom, nk2->headroom); + + peer->needed_headroom = headroom; + dev->needed_headroom = headroom; +out: + rcu_read_unlock(); +} + +static struct net_device *netkit_peer_dev(struct net_device *dev) +{ + return rcu_dereference(netkit_priv(dev)->peer); +} + +static void netkit_uninit(struct net_device *dev); + +static const struct net_device_ops netkit_netdev_ops = { + .ndo_open = netkit_open, + .ndo_stop = netkit_close, + .ndo_start_xmit = netkit_xmit, + .ndo_set_rx_mode = netkit_set_multicast, + .ndo_set_rx_headroom = netkit_set_headroom, + .ndo_get_iflink = netkit_get_iflink, + .ndo_get_peer_dev = netkit_peer_dev, + .ndo_uninit = netkit_uninit, + .ndo_features_check = passthru_features_check, +}; + +static void netkit_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) +{ + strscpy(info->driver, DRV_NAME, sizeof(info->driver)); +} + +static const struct ethtool_ops netkit_ethtool_ops = { + .get_drvinfo = netkit_get_drvinfo, +}; + +static void netkit_setup(struct net_device *dev) +{ + static const netdev_features_t netkit_features_hw_vlan = + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_STAG_TX | + NETIF_F_HW_VLAN_STAG_RX; + static const netdev_features_t netkit_features = + netkit_features_hw_vlan | + NETIF_F_SG | + NETIF_F_FRAGLIST | + NETIF_F_HW_CSUM | + NETIF_F_RXCSUM | + NETIF_F_SCTP_CRC | + NETIF_F_HIGHDMA | + NETIF_F_GSO_SOFTWARE | + NETIF_F_GSO_ENCAP_ALL; + + ether_setup(dev); + dev->max_mtu = ETH_MAX_MTU; + + dev->flags |= IFF_NOARP; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + dev->priv_flags |= IFF_PHONY_HEADROOM; + dev->priv_flags |= IFF_NO_QUEUE; + + dev->ethtool_ops = &netkit_ethtool_ops; + dev->netdev_ops = &netkit_netdev_ops; + + dev->features |= netkit_features | NETIF_F_LLTX; + dev->hw_features = netkit_features; + dev->hw_enc_features = netkit_features; + dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE; + dev->vlan_features = dev->features & ~netkit_features_hw_vlan; + + dev->needs_free_netdev = true; + + netif_set_tso_max_size(dev, GSO_MAX_SIZE); +} + +static struct net *netkit_get_link_net(const struct net_device *dev) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer = rtnl_dereference(nk->peer); + + return peer ? dev_net(peer) : dev_net(dev); +} + +static int netkit_check_policy(int policy, struct nlattr *tb, + struct netlink_ext_ack *extack) +{ + switch (policy) { + case NETKIT_PASS: + case NETKIT_DROP: + return 0; + default: + NL_SET_ERR_MSG_ATTR(extack, tb, + "Provided default xmit policy not supported"); + return -EINVAL; + } +} + +static int netkit_check_mode(int mode, struct nlattr *tb, + struct netlink_ext_ack *extack) +{ + switch (mode) { + case NETKIT_L2: + case NETKIT_L3: + return 0; + default: + NL_SET_ERR_MSG_ATTR(extack, tb, + "Provided device mode can only be L2 or L3"); + return -EINVAL; + } +} + +static int netkit_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct nlattr *attr = tb[IFLA_ADDRESS]; + + if (!attr) + return 0; + NL_SET_ERR_MSG_ATTR(extack, attr, + "Setting Ethernet address is not supported"); + return -EOPNOTSUPP; +} + +static struct rtnl_link_ops netkit_link_ops; + +static int netkit_new_link(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct nlattr *peer_tb[IFLA_MAX + 1], **tbp = tb, *attr; + enum netkit_action default_prim = NETKIT_PASS; + enum netkit_action default_peer = NETKIT_PASS; + enum netkit_mode mode = NETKIT_L3; + unsigned char ifname_assign_type; + struct ifinfomsg *ifmp = NULL; + struct net_device *peer; + char ifname[IFNAMSIZ]; + struct netkit *nk; + struct net *net; + int err; + + if (data) { + if (data[IFLA_NETKIT_MODE]) { + attr = data[IFLA_NETKIT_MODE]; + mode = nla_get_u32(attr); + err = netkit_check_mode(mode, attr, extack); + if (err < 0) + return err; + } + if (data[IFLA_NETKIT_PEER_INFO]) { + attr = data[IFLA_NETKIT_PEER_INFO]; + ifmp = nla_data(attr); + err = rtnl_nla_parse_ifinfomsg(peer_tb, attr, extack); + if (err < 0) + return err; + err = netkit_validate(peer_tb, NULL, extack); + if (err < 0) + return err; + tbp = peer_tb; + } + if (data[IFLA_NETKIT_POLICY]) { + attr = data[IFLA_NETKIT_POLICY]; + default_prim = nla_get_u32(attr); + err = netkit_check_policy(default_prim, attr, extack); + if (err < 0) + return err; + } + if (data[IFLA_NETKIT_PEER_POLICY]) { + attr = data[IFLA_NETKIT_PEER_POLICY]; + default_peer = nla_get_u32(attr); + err = netkit_check_policy(default_peer, attr, extack); + if (err < 0) + return err; + } + } + + if (ifmp && tbp[IFLA_IFNAME]) { + nla_strscpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ); + ifname_assign_type = NET_NAME_USER; + } else { + strscpy(ifname, "nk%d", IFNAMSIZ); + ifname_assign_type = NET_NAME_ENUM; + } + + net = rtnl_link_get_net(src_net, tbp); + if (IS_ERR(net)) + return PTR_ERR(net); + + peer = rtnl_create_link(net, ifname, ifname_assign_type, + &netkit_link_ops, tbp, extack); + if (IS_ERR(peer)) { + put_net(net); + return PTR_ERR(peer); + } + + netif_inherit_tso_max(peer, dev); + + if (mode == NETKIT_L2) + eth_hw_addr_random(peer); + if (ifmp && dev->ifindex) + peer->ifindex = ifmp->ifi_index; + + nk = netkit_priv(peer); + nk->primary = false; + nk->policy = default_peer; + nk->mode = mode; + bpf_mprog_bundle_init(&nk->bundle); + RCU_INIT_POINTER(nk->active, NULL); + RCU_INIT_POINTER(nk->peer, NULL); + + err = register_netdevice(peer); + put_net(net); + if (err < 0) + goto err_register_peer; + netif_carrier_off(peer); + if (mode == NETKIT_L2) + dev_change_flags(peer, peer->flags & ~IFF_NOARP, NULL); + + err = rtnl_configure_link(peer, NULL, 0, NULL); + if (err < 0) + goto err_configure_peer; + + if (mode == NETKIT_L2) + eth_hw_addr_random(dev); + if (tb[IFLA_IFNAME]) + nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ); + else + strscpy(dev->name, "nk%d", IFNAMSIZ); + + nk = netkit_priv(dev); + nk->primary = true; + nk->policy = default_prim; + nk->mode = mode; + bpf_mprog_bundle_init(&nk->bundle); + RCU_INIT_POINTER(nk->active, NULL); + RCU_INIT_POINTER(nk->peer, NULL); + + err = register_netdevice(dev); + if (err < 0) + goto err_configure_peer; + netif_carrier_off(dev); + if (mode == NETKIT_L2) + dev_change_flags(dev, dev->flags & ~IFF_NOARP, NULL); + + rcu_assign_pointer(netkit_priv(dev)->peer, peer); + rcu_assign_pointer(netkit_priv(peer)->peer, dev); + return 0; +err_configure_peer: + unregister_netdevice(peer); + return err; +err_register_peer: + free_netdev(peer); + return err; +} + +static struct bpf_mprog_entry *netkit_entry_fetch(struct net_device *dev, + bool bundle_fallback) +{ + struct netkit *nk = netkit_priv(dev); + struct bpf_mprog_entry *entry; + + ASSERT_RTNL(); + entry = rcu_dereference_rtnl(nk->active); + if (entry) + return entry; + if (bundle_fallback) + return &nk->bundle.a; + return NULL; +} + +static void netkit_entry_update(struct net_device *dev, + struct bpf_mprog_entry *entry) +{ + struct netkit *nk = netkit_priv(dev); + + ASSERT_RTNL(); + rcu_assign_pointer(nk->active, entry); +} + +static void netkit_entry_sync(void) +{ + synchronize_rcu(); +} + +static struct net_device *netkit_dev_fetch(struct net *net, u32 ifindex, u32 which) +{ + struct net_device *dev; + struct netkit *nk; + + ASSERT_RTNL(); + + switch (which) { + case BPF_NETKIT_PRIMARY: + case BPF_NETKIT_PEER: + break; + default: + return ERR_PTR(-EINVAL); + } + + dev = __dev_get_by_index(net, ifindex); + if (!dev) + return ERR_PTR(-ENODEV); + if (dev->netdev_ops != &netkit_netdev_ops) + return ERR_PTR(-ENXIO); + + nk = netkit_priv(dev); + if (!nk->primary) + return ERR_PTR(-EACCES); + if (which == BPF_NETKIT_PEER) { + dev = rcu_dereference_rtnl(nk->peer); + if (!dev) + return ERR_PTR(-ENODEV); + } + return dev; +} + +int netkit_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_mprog_entry *entry, *entry_new; + struct bpf_prog *replace_prog = NULL; + struct net_device *dev; + int ret; + + rtnl_lock(); + dev = netkit_dev_fetch(current->nsproxy->net_ns, attr->target_ifindex, + attr->attach_type); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto out; + } + entry = netkit_entry_fetch(dev, true); + if (attr->attach_flags & BPF_F_REPLACE) { + replace_prog = bpf_prog_get_type(attr->replace_bpf_fd, + prog->type); + if (IS_ERR(replace_prog)) { + ret = PTR_ERR(replace_prog); + replace_prog = NULL; + goto out; + } + } + ret = bpf_mprog_attach(entry, &entry_new, prog, NULL, replace_prog, + attr->attach_flags, attr->relative_fd, + attr->expected_revision); + if (!ret) { + if (entry != entry_new) { + netkit_entry_update(dev, entry_new); + netkit_entry_sync(); + } + bpf_mprog_commit(entry); + } +out: + if (replace_prog) + bpf_prog_put(replace_prog); + rtnl_unlock(); + return ret; +} + +int netkit_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev; + int ret; + + rtnl_lock(); + dev = netkit_dev_fetch(current->nsproxy->net_ns, attr->target_ifindex, + attr->attach_type); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto out; + } + entry = netkit_entry_fetch(dev, false); + if (!entry) { + ret = -ENOENT; + goto out; + } + ret = bpf_mprog_detach(entry, &entry_new, prog, NULL, attr->attach_flags, + attr->relative_fd, attr->expected_revision); + if (!ret) { + if (!bpf_mprog_total(entry_new)) + entry_new = NULL; + netkit_entry_update(dev, entry_new); + netkit_entry_sync(); + bpf_mprog_commit(entry); + } +out: + rtnl_unlock(); + return ret; +} + +int netkit_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) +{ + struct net_device *dev; + int ret; + + rtnl_lock(); + dev = netkit_dev_fetch(current->nsproxy->net_ns, + attr->query.target_ifindex, + attr->query.attach_type); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto out; + } + ret = bpf_mprog_query(attr, uattr, netkit_entry_fetch(dev, false)); +out: + rtnl_unlock(); + return ret; +} + +static struct netkit_link *netkit_link(const struct bpf_link *link) +{ + return container_of(link, struct netkit_link, link); +} + +static int netkit_link_prog_attach(struct bpf_link *link, u32 flags, + u32 id_or_fd, u64 revision) +{ + struct netkit_link *nkl = netkit_link(link); + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev = nkl->dev; + int ret; + + ASSERT_RTNL(); + entry = netkit_entry_fetch(dev, true); + ret = bpf_mprog_attach(entry, &entry_new, link->prog, link, NULL, flags, + id_or_fd, revision); + if (!ret) { + if (entry != entry_new) { + netkit_entry_update(dev, entry_new); + netkit_entry_sync(); + } + bpf_mprog_commit(entry); + } + return ret; +} + +static void netkit_link_release(struct bpf_link *link) +{ + struct netkit_link *nkl = netkit_link(link); + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + dev = nkl->dev; + if (!dev) + goto out; + entry = netkit_entry_fetch(dev, false); + if (!entry) { + ret = -ENOENT; + goto out; + } + ret = bpf_mprog_detach(entry, &entry_new, link->prog, link, 0, 0, 0); + if (!ret) { + if (!bpf_mprog_total(entry_new)) + entry_new = NULL; + netkit_entry_update(dev, entry_new); + netkit_entry_sync(); + bpf_mprog_commit(entry); + nkl->dev = NULL; + } +out: + WARN_ON_ONCE(ret); + rtnl_unlock(); +} + +static int netkit_link_update(struct bpf_link *link, struct bpf_prog *nprog, + struct bpf_prog *oprog) +{ + struct netkit_link *nkl = netkit_link(link); + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + dev = nkl->dev; + if (!dev) { + ret = -ENOLINK; + goto out; + } + if (oprog && link->prog != oprog) { + ret = -EPERM; + goto out; + } + oprog = link->prog; + if (oprog == nprog) { + bpf_prog_put(nprog); + goto out; + } + entry = netkit_entry_fetch(dev, false); + if (!entry) { + ret = -ENOENT; + goto out; + } + ret = bpf_mprog_attach(entry, &entry_new, nprog, link, oprog, + BPF_F_REPLACE | BPF_F_ID, + link->prog->aux->id, 0); + if (!ret) { + WARN_ON_ONCE(entry != entry_new); + oprog = xchg(&link->prog, nprog); + bpf_prog_put(oprog); + bpf_mprog_commit(entry); + } +out: + rtnl_unlock(); + return ret; +} + +static void netkit_link_dealloc(struct bpf_link *link) +{ + kfree(netkit_link(link)); +} + +static void netkit_link_fdinfo(const struct bpf_link *link, struct seq_file *seq) +{ + const struct netkit_link *nkl = netkit_link(link); + u32 ifindex = 0; + + rtnl_lock(); + if (nkl->dev) + ifindex = nkl->dev->ifindex; + rtnl_unlock(); + + seq_printf(seq, "ifindex:\t%u\n", ifindex); + seq_printf(seq, "attach_type:\t%u (%s)\n", + nkl->location, + nkl->location == BPF_NETKIT_PRIMARY ? "primary" : "peer"); +} + +static int netkit_link_fill_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + const struct netkit_link *nkl = netkit_link(link); + u32 ifindex = 0; + + rtnl_lock(); + if (nkl->dev) + ifindex = nkl->dev->ifindex; + rtnl_unlock(); + + info->netkit.ifindex = ifindex; + info->netkit.attach_type = nkl->location; + return 0; +} + +static int netkit_link_detach(struct bpf_link *link) +{ + netkit_link_release(link); + return 0; +} + +static const struct bpf_link_ops netkit_link_lops = { + .release = netkit_link_release, + .detach = netkit_link_detach, + .dealloc = netkit_link_dealloc, + .update_prog = netkit_link_update, + .show_fdinfo = netkit_link_fdinfo, + .fill_link_info = netkit_link_fill_info, +}; + +static int netkit_link_init(struct netkit_link *nkl, + struct bpf_link_primer *link_primer, + const union bpf_attr *attr, + struct net_device *dev, + struct bpf_prog *prog) +{ + bpf_link_init(&nkl->link, BPF_LINK_TYPE_NETKIT, + &netkit_link_lops, prog); + nkl->location = attr->link_create.attach_type; + nkl->dev = dev; + return bpf_link_prime(&nkl->link, link_primer); +} + +int netkit_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_link_primer link_primer; + struct netkit_link *nkl; + struct net_device *dev; + int ret; + + rtnl_lock(); + dev = netkit_dev_fetch(current->nsproxy->net_ns, + attr->link_create.target_ifindex, + attr->link_create.attach_type); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto out; + } + nkl = kzalloc(sizeof(*nkl), GFP_KERNEL_ACCOUNT); + if (!nkl) { + ret = -ENOMEM; + goto out; + } + ret = netkit_link_init(nkl, &link_primer, attr, dev, prog); + if (ret) { + kfree(nkl); + goto out; + } + ret = netkit_link_prog_attach(&nkl->link, + attr->link_create.flags, + attr->link_create.netkit.relative_fd, + attr->link_create.netkit.expected_revision); + if (ret) { + nkl->dev = NULL; + bpf_link_cleanup(&link_primer); + goto out; + } + ret = bpf_link_settle(&link_primer); +out: + rtnl_unlock(); + return ret; +} + +static void netkit_release_all(struct net_device *dev) +{ + struct bpf_mprog_entry *entry; + struct bpf_tuple tuple = {}; + struct bpf_mprog_fp *fp; + struct bpf_mprog_cp *cp; + + entry = netkit_entry_fetch(dev, false); + if (!entry) + return; + netkit_entry_update(dev, NULL); + netkit_entry_sync(); + bpf_mprog_foreach_tuple(entry, fp, cp, tuple) { + if (tuple.link) + netkit_link(tuple.link)->dev = NULL; + else + bpf_prog_put(tuple.prog); + } +} + +static void netkit_uninit(struct net_device *dev) +{ + netkit_release_all(dev); +} + +static void netkit_del_link(struct net_device *dev, struct list_head *head) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer = rtnl_dereference(nk->peer); + + RCU_INIT_POINTER(nk->peer, NULL); + unregister_netdevice_queue(dev, head); + if (peer) { + nk = netkit_priv(peer); + RCU_INIT_POINTER(nk->peer, NULL); + unregister_netdevice_queue(peer, head); + } +} + +static int netkit_change_link(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer = rtnl_dereference(nk->peer); + enum netkit_action policy; + struct nlattr *attr; + int err; + + if (!nk->primary) { + NL_SET_ERR_MSG(extack, + "netkit link settings can be changed only through the primary device"); + return -EACCES; + } + + if (data[IFLA_NETKIT_MODE]) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_NETKIT_MODE], + "netkit link operating mode cannot be changed after device creation"); + return -EACCES; + } + + if (data[IFLA_NETKIT_POLICY]) { + attr = data[IFLA_NETKIT_POLICY]; + policy = nla_get_u32(attr); + err = netkit_check_policy(policy, attr, extack); + if (err) + return err; + WRITE_ONCE(nk->policy, policy); + } + + if (data[IFLA_NETKIT_PEER_POLICY]) { + err = -EOPNOTSUPP; + attr = data[IFLA_NETKIT_PEER_POLICY]; + policy = nla_get_u32(attr); + if (peer) + err = netkit_check_policy(policy, attr, extack); + if (err) + return err; + nk = netkit_priv(peer); + WRITE_ONCE(nk->policy, policy); + } + + return 0; +} + +static size_t netkit_get_size(const struct net_device *dev) +{ + return nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_POLICY */ + nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_PEER_POLICY */ + nla_total_size(sizeof(u8)) + /* IFLA_NETKIT_PRIMARY */ + nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_MODE */ + 0; +} + +static int netkit_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer = rtnl_dereference(nk->peer); + + if (nla_put_u8(skb, IFLA_NETKIT_PRIMARY, nk->primary)) + return -EMSGSIZE; + if (nla_put_u32(skb, IFLA_NETKIT_POLICY, nk->policy)) + return -EMSGSIZE; + if (nla_put_u32(skb, IFLA_NETKIT_MODE, nk->mode)) + return -EMSGSIZE; + + if (peer) { + nk = netkit_priv(peer); + if (nla_put_u32(skb, IFLA_NETKIT_PEER_POLICY, nk->policy)) + return -EMSGSIZE; + } + + return 0; +} + +static const struct nla_policy netkit_policy[IFLA_NETKIT_MAX + 1] = { + [IFLA_NETKIT_PEER_INFO] = { .len = sizeof(struct ifinfomsg) }, + [IFLA_NETKIT_POLICY] = { .type = NLA_U32 }, + [IFLA_NETKIT_MODE] = { .type = NLA_U32 }, + [IFLA_NETKIT_PEER_POLICY] = { .type = NLA_U32 }, + [IFLA_NETKIT_PRIMARY] = { .type = NLA_REJECT, + .reject_message = "Primary attribute is read-only" }, +}; + +static struct rtnl_link_ops netkit_link_ops = { + .kind = DRV_NAME, + .priv_size = sizeof(struct netkit), + .setup = netkit_setup, + .newlink = netkit_new_link, + .dellink = netkit_del_link, + .changelink = netkit_change_link, + .get_link_net = netkit_get_link_net, + .get_size = netkit_get_size, + .fill_info = netkit_fill_info, + .policy = netkit_policy, + .validate = netkit_validate, + .maxtype = IFLA_NETKIT_MAX, +}; + +static __init int netkit_init(void) +{ + BUILD_BUG_ON((int)NETKIT_NEXT != (int)TCX_NEXT || + (int)NETKIT_PASS != (int)TCX_PASS || + (int)NETKIT_DROP != (int)TCX_DROP || + (int)NETKIT_REDIRECT != (int)TCX_REDIRECT); + + return rtnl_link_register(&netkit_link_ops); +} + +static __exit void netkit_exit(void) +{ + rtnl_link_unregister(&netkit_link_ops); +} + +module_init(netkit_init); +module_exit(netkit_exit); + +MODULE_DESCRIPTION("BPF-programmable network device"); +MODULE_AUTHOR("Daniel Borkmann "); +MODULE_AUTHOR("Nikolay Aleksandrov "); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK(DRV_NAME); diff --git a/include/net/netkit.h b/include/net/netkit.h new file mode 100644 index 000000000000..0ba2e6b847ca --- /dev/null +++ b/include/net/netkit.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2023 Isovalent */ +#ifndef __NET_NETKIT_H +#define __NET_NETKIT_H + +#include + +#ifdef CONFIG_NETKIT +int netkit_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); +int netkit_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); +int netkit_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog); +int netkit_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); +#else +static inline int netkit_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + return -EINVAL; +} + +static inline int netkit_link_attach(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + return -EINVAL; +} + +static inline int netkit_prog_detach(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + return -EINVAL; +} + +static inline int netkit_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EINVAL; +} +#endif /* CONFIG_NETKIT */ +#endif /* __NET_NETKIT_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7ba61b75bc0e..0f6cdf52b1da 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1052,6 +1052,8 @@ enum bpf_attach_type { BPF_CGROUP_UNIX_RECVMSG, BPF_CGROUP_UNIX_GETPEERNAME, BPF_CGROUP_UNIX_GETSOCKNAME, + BPF_NETKIT_PRIMARY, + BPF_NETKIT_PEER, __MAX_BPF_ATTACH_TYPE }; @@ -1071,6 +1073,7 @@ enum bpf_link_type { BPF_LINK_TYPE_NETFILTER = 10, BPF_LINK_TYPE_TCX = 11, BPF_LINK_TYPE_UPROBE_MULTI = 12, + BPF_LINK_TYPE_NETKIT = 13, MAX_BPF_LINK_TYPE, }; @@ -1656,6 +1659,13 @@ union bpf_attr { __u32 flags; __u32 pid; } uprobe_multi; + struct { + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; + } netkit; }; } link_create; @@ -6576,6 +6586,10 @@ struct bpf_link_info { __u32 ifindex; __u32 attach_type; } tcx; + struct { + __u32 ifindex; + __u32 attach_type; + } netkit; }; } __attribute__((aligned(8))); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index fac351a93aed..a0aa05a28cf2 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -756,6 +756,30 @@ struct tunnel_msg { __u32 ifindex; }; +/* netkit section */ +enum netkit_action { + NETKIT_NEXT = -1, + NETKIT_PASS = 0, + NETKIT_DROP = 2, + NETKIT_REDIRECT = 7, +}; + +enum netkit_mode { + NETKIT_L2, + NETKIT_L3, +}; + +enum { + IFLA_NETKIT_UNSPEC, + IFLA_NETKIT_PEER_INFO, + IFLA_NETKIT_PRIMARY, + IFLA_NETKIT_POLICY, + IFLA_NETKIT_PEER_POLICY, + IFLA_NETKIT_MODE, + __IFLA_NETKIT_MAX, +}; +#define IFLA_NETKIT_MAX (__IFLA_NETKIT_MAX - 1) + /* VXLAN section */ /* include statistics in the dump */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a9b2cb500bf7..0ed286b8a0f0 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -35,8 +35,9 @@ #include #include #include -#include +#include +#include #include #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ @@ -3730,6 +3731,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) return BPF_PROG_TYPE_LSM; case BPF_TCX_INGRESS: case BPF_TCX_EGRESS: + case BPF_NETKIT_PRIMARY: + case BPF_NETKIT_PEER: return BPF_PROG_TYPE_SCHED_CLS; default: return BPF_PROG_TYPE_UNSPEC; @@ -3781,7 +3784,9 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, return 0; case BPF_PROG_TYPE_SCHED_CLS: if (attach_type != BPF_TCX_INGRESS && - attach_type != BPF_TCX_EGRESS) + attach_type != BPF_TCX_EGRESS && + attach_type != BPF_NETKIT_PRIMARY && + attach_type != BPF_NETKIT_PEER) return -EINVAL; return 0; default: @@ -3864,7 +3869,11 @@ static int bpf_prog_attach(const union bpf_attr *attr) ret = cgroup_bpf_prog_attach(attr, ptype, prog); break; case BPF_PROG_TYPE_SCHED_CLS: - ret = tcx_prog_attach(attr, prog); + if (attr->attach_type == BPF_TCX_INGRESS || + attr->attach_type == BPF_TCX_EGRESS) + ret = tcx_prog_attach(attr, prog); + else + ret = netkit_prog_attach(attr, prog); break; default: ret = -EINVAL; @@ -3925,7 +3934,11 @@ static int bpf_prog_detach(const union bpf_attr *attr) ret = cgroup_bpf_prog_detach(attr, ptype); break; case BPF_PROG_TYPE_SCHED_CLS: - ret = tcx_prog_detach(attr, prog); + if (attr->attach_type == BPF_TCX_INGRESS || + attr->attach_type == BPF_TCX_EGRESS) + ret = tcx_prog_detach(attr, prog); + else + ret = netkit_prog_detach(attr, prog); break; default: ret = -EINVAL; @@ -3992,6 +4005,9 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_TCX_INGRESS: case BPF_TCX_EGRESS: return tcx_prog_query(attr, uattr); + case BPF_NETKIT_PRIMARY: + case BPF_NETKIT_PEER: + return netkit_prog_query(attr, uattr); default: return -EINVAL; } @@ -4973,7 +4989,11 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) ret = bpf_xdp_link_attach(attr, prog); break; case BPF_PROG_TYPE_SCHED_CLS: - ret = tcx_link_attach(attr, prog); + if (attr->link_create.attach_type == BPF_TCX_INGRESS || + attr->link_create.attach_type == BPF_TCX_EGRESS) + ret = tcx_link_attach(attr, prog); + else + ret = netkit_link_attach(attr, prog); break; case BPF_PROG_TYPE_NETFILTER: ret = bpf_nf_link_attach(attr, prog); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7ba61b75bc0e..0f6cdf52b1da 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1052,6 +1052,8 @@ enum bpf_attach_type { BPF_CGROUP_UNIX_RECVMSG, BPF_CGROUP_UNIX_GETPEERNAME, BPF_CGROUP_UNIX_GETSOCKNAME, + BPF_NETKIT_PRIMARY, + BPF_NETKIT_PEER, __MAX_BPF_ATTACH_TYPE }; @@ -1071,6 +1073,7 @@ enum bpf_link_type { BPF_LINK_TYPE_NETFILTER = 10, BPF_LINK_TYPE_TCX = 11, BPF_LINK_TYPE_UPROBE_MULTI = 12, + BPF_LINK_TYPE_NETKIT = 13, MAX_BPF_LINK_TYPE, }; @@ -1656,6 +1659,13 @@ union bpf_attr { __u32 flags; __u32 pid; } uprobe_multi; + struct { + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; + } netkit; }; } link_create; @@ -6576,6 +6586,10 @@ struct bpf_link_info { __u32 ifindex; __u32 attach_type; } tcx; + struct { + __u32 ifindex; + __u32 attach_type; + } netkit; }; } __attribute__((aligned(8))); -- cgit From 2cafb582173f3870240af90de3f31d18b0728882 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 3 Oct 2023 02:24:18 -0700 Subject: mempolicy: remove confusing MPOL_MF_LAZY dead code v3.8 commit b24f53a0bea3 ("mm: mempolicy: Add MPOL_MF_LAZY") introduced MPOL_MF_LAZY, and included it in the MPOL_MF_VALID flags; but a720094ded8 ("mm: mempolicy: Hide MPOL_NOOP and MPOL_MF_LAZY from userspace for now") immediately removed it from MPOL_MF_VALID flags, pending further review. "This will need to be revisited", but it has not been reinstated. The present state is confusing: there is dead code in mm/mempolicy.c to handle MPOL_MF_LAZY cases which can never occur. Remove that: it can be resurrected later if necessary. But keep the definition of MPOL_MF_LAZY, which must remain in the UAPI, even though it always fails with EINVAL. https://lore.kernel.org/linux-mm/1553041659-46787-1-git-send-email-yang.shi@linux.alibaba.com/ links to a previous request to remove MPOL_MF_LAZY. Link: https://lkml.kernel.org/r/80c9665c-1c3f-17ba-21a3-f6115cebf7d@google.com Signed-off-by: Hugh Dickins Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Yang Shi Cc: Andi Kleen Cc: Christoph Lameter Cc: David Hildenbrand Cc: Greg Kroah-Hartman Cc: "Huang, Ying" Cc: Kefeng Wang Cc: Mel Gorman Cc: Michal Hocko Cc: Mike Kravetz Cc: Nhat Pham Cc: Sidhartha Kumar Cc: Suren Baghdasaryan Cc: Tejun heo Cc: Vishal Moola (Oracle) Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- include/uapi/linux/mempolicy.h | 2 +- mm/mempolicy.c | 18 ------------------ 2 files changed, 1 insertion(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h index 046d0ccba4cd..a8963f7ef4c2 100644 --- a/include/uapi/linux/mempolicy.h +++ b/include/uapi/linux/mempolicy.h @@ -48,7 +48,7 @@ enum { #define MPOL_MF_MOVE (1<<1) /* Move pages owned by this process to conform to policy */ #define MPOL_MF_MOVE_ALL (1<<2) /* Move every page to conform to policy */ -#define MPOL_MF_LAZY (1<<3) /* Modifies '_MOVE: lazy migrate on fault */ +#define MPOL_MF_LAZY (1<<3) /* UNSUPPORTED FLAG: Lazy migrate on fault */ #define MPOL_MF_INTERNAL (1<<4) /* Internal flags start here */ #define MPOL_MF_VALID (MPOL_MF_STRICT | \ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index b6461d7d200e..e01d3f807f77 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -636,12 +636,6 @@ unsigned long change_prot_numa(struct vm_area_struct *vma, return nr_updated; } -#else -static unsigned long change_prot_numa(struct vm_area_struct *vma, - unsigned long addr, unsigned long end) -{ - return 0; -} #endif /* CONFIG_NUMA_BALANCING */ static int queue_pages_test_walk(unsigned long start, unsigned long end, @@ -680,14 +674,6 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, if (endvma > end) endvma = end; - if (flags & MPOL_MF_LAZY) { - /* Similar to task_numa_work, skip inaccessible VMAs */ - if (!is_vm_hugetlb_page(vma) && vma_is_accessible(vma) && - !(vma->vm_flags & VM_MIXEDMAP)) - change_prot_numa(vma, start, endvma); - return 1; - } - /* * Check page nodes, and queue pages to move, in the current vma. * But if no moving, and no strict checking, the scan can be skipped. @@ -1254,9 +1240,6 @@ static long do_mbind(unsigned long start, unsigned long len, if (IS_ERR(new)) return PTR_ERR(new); - if (flags & MPOL_MF_LAZY) - new->flags |= MPOL_F_MOF; - /* * If we are using the default policy then operation * on discontinuous address spaces is okay after all @@ -1301,7 +1284,6 @@ static long do_mbind(unsigned long start, unsigned long len, if (!err) { if (!list_empty(&pagelist)) { - WARN_ON_ONCE(flags & MPOL_MF_LAZY); nr_failed |= migrate_pages(&pagelist, new_folio, NULL, start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND, NULL); } -- cgit From e57a34478586fe3562560ccebd655b707a5b4a56 Mon Sep 17 00:00:00 2001 From: Yan Zhai Date: Tue, 24 Oct 2023 07:26:33 -0700 Subject: ipv6: drop feature RTAX_FEATURE_ALLFRAG RTAX_FEATURE_ALLFRAG was added before the first git commit: https://www.mail-archive.com/bk-commits-head@vger.kernel.org/msg03399.html The feature would send packets to the fragmentation path if a box receives a PMTU value with less than 1280 byte. However, since commit 9d289715eb5c ("ipv6: stop sending PTB packets for MTU < 1280"), such message would be simply discarded. The feature flag is neither supported in iproute2 utility. In theory one can still manipulate it with direct netlink message, but it is not ideal because it was based on obsoleted guidance of RFC-2460 (replaced by RFC-8200). The feature would always test false at the moment, so remove related code or mark them as unused. Signed-off-by: Yan Zhai Reviewed-by: Florian Westphal Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/d78e44dcd9968a252143ffe78460446476a472a1.1698156966.git.yan@cloudflare.com Signed-off-by: Jakub Kicinski --- include/net/dst.h | 7 ------- include/net/inet_connection_sock.h | 1 - include/net/inet_sock.h | 1 - include/uapi/linux/rtnetlink.h | 2 +- net/ipv4/tcp_output.c | 20 +------------------- net/ipv6/ip6_output.c | 15 ++------------- net/ipv6/tcp_ipv6.c | 1 - net/ipv6/xfrm6_output.c | 2 +- net/mptcp/subflow.c | 1 - 9 files changed, 5 insertions(+), 45 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/dst.h b/include/net/dst.h index f8b8599a0600..f5dfc8fb7b37 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -222,13 +222,6 @@ static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metr return msecs_to_jiffies(dst_metric(dst, metric)); } -static inline u32 -dst_allfrag(const struct dst_entry *dst) -{ - int ret = dst_feature(dst, RTAX_FEATURE_ALLFRAG); - return ret; -} - static inline int dst_metric_locked(const struct dst_entry *dst, int metric) { diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 086d1193c9ef..d0a2f827d5f2 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -44,7 +44,6 @@ struct inet_connection_sock_af_ops { struct request_sock *req_unhash, bool *own_req); u16 net_header_len; - u16 net_frag_header_len; u16 sockaddr_len; int (*setsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 98e11958cdff..74db6d97cae1 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -244,7 +244,6 @@ struct inet_sock { }; #define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */ -#define IPCORK_ALLFRAG 2 /* always fragment (for ipv6 for now) */ enum { INET_FLAGS_PKTINFO = 0, diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index aa2482a0614a..3b687d20c9ed 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -505,7 +505,7 @@ enum { #define RTAX_FEATURE_ECN (1 << 0) #define RTAX_FEATURE_SACK (1 << 1) /* unused */ #define RTAX_FEATURE_TIMESTAMP (1 << 2) /* unused */ -#define RTAX_FEATURE_ALLFRAG (1 << 3) +#define RTAX_FEATURE_ALLFRAG (1 << 3) /* unused */ #define RTAX_FEATURE_TCP_USEC_TS (1 << 4) #define RTAX_FEATURE_MASK (RTAX_FEATURE_ECN | \ diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 2866ccbccde0..ca4d7594efd4 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1698,14 +1698,6 @@ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) */ mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr); - /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ - if (icsk->icsk_af_ops->net_frag_header_len) { - const struct dst_entry *dst = __sk_dst_get(sk); - - if (dst && dst_allfrag(dst)) - mss_now -= icsk->icsk_af_ops->net_frag_header_len; - } - /* Clamp it (mss_clamp does not include tcp options) */ if (mss_now > tp->rx_opt.mss_clamp) mss_now = tp->rx_opt.mss_clamp; @@ -1733,21 +1725,11 @@ int tcp_mss_to_mtu(struct sock *sk, int mss) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); - int mtu; - mtu = mss + + return mss + tp->tcp_header_len + icsk->icsk_ext_hdr_len + icsk->icsk_af_ops->net_header_len; - - /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ - if (icsk->icsk_af_ops->net_frag_header_len) { - const struct dst_entry *dst = __sk_dst_get(sk); - - if (dst && dst_allfrag(dst)) - mtu += icsk->icsk_af_ops->net_frag_header_len; - } - return mtu; } EXPORT_SYMBOL(tcp_mss_to_mtu); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 3c7de89d6755..86efd901ee5a 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -191,7 +191,6 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu); if ((skb->len > mtu && !skb_is_gso(skb)) || - dst_allfrag(skb_dst(skb)) || (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size)) return ip6_fragment(net, sk, skb, ip6_finish_output2); else @@ -1017,9 +1016,6 @@ slow_path: return err; fail_toobig: - if (skb->sk && dst_allfrag(skb_dst(skb))) - sk_gso_disable(skb->sk); - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); err = -EMSGSIZE; @@ -1384,10 +1380,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, cork->base.mark = ipc6->sockc.mark; sock_tx_timestamp(sk, ipc6->sockc.tsflags, &cork->base.tx_flags); - if (dst_allfrag(xfrm_dst_path(&rt->dst))) - cork->base.flags |= IPCORK_ALLFRAG; cork->base.length = 0; - cork->base.transmit_time = ipc6->sockc.transmit_time; return 0; @@ -1444,8 +1437,6 @@ static int __ip6_append_data(struct sock *sk, headersize = sizeof(struct ipv6hdr) + (opt ? opt->opt_flen + opt->opt_nflen : 0) + - (dst_allfrag(&rt->dst) ? - sizeof(struct frag_hdr) : 0) + rt->rt6i_nfheader_len; if (mtu <= fragheaderlen || @@ -1555,7 +1546,7 @@ emsgsize: while (length > 0) { /* Check if the remaining data fits into current packet. */ - copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len; + copy = (cork->length <= mtu ? mtu : maxfraglen) - skb->len; if (copy < length) copy = maxfraglen - skb->len; @@ -1586,7 +1577,7 @@ alloc_new_skb: */ datalen = length + fraggap; - if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen) + if (datalen > (cork->length <= mtu ? mtu : maxfraglen) - fragheaderlen) datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len; fraglen = datalen + fragheaderlen; pagedlen = 0; @@ -1835,7 +1826,6 @@ static void ip6_cork_steal_dst(struct sk_buff *skb, struct inet_cork_full *cork) struct dst_entry *dst = cork->base.dst; cork->base.dst = NULL; - cork->base.flags &= ~IPCORK_ALLFRAG; skb_dst_set(skb, dst); } @@ -1856,7 +1846,6 @@ static void ip6_cork_release(struct inet_cork_full *cork, if (cork->base.dst) { dst_release(cork->base.dst); cork->base.dst = NULL; - cork->base.flags &= ~IPCORK_ALLFRAG; } } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0c8a14ba104f..dc27988512a6 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1895,7 +1895,6 @@ const struct inet_connection_sock_af_ops ipv6_specific = { .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, .net_header_len = sizeof(struct ipv6hdr), - .net_frag_header_len = sizeof(struct frag_hdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .addr2sockaddr = inet6_csk_addr2sockaddr, diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index ad07904642ca..5f7b1fdbffe6 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -95,7 +95,7 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) return -EMSGSIZE; } - if (toobig || dst_allfrag(skb_dst(skb))) + if (toobig) return ip6_fragment(net, sk, skb, __xfrm6_output_finish); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 2b43577f952e..e120e9616454 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -2051,7 +2051,6 @@ void __init mptcp_subflow_init(void) subflow_v6m_specific.send_check = ipv4_specific.send_check; subflow_v6m_specific.net_header_len = ipv4_specific.net_header_len; subflow_v6m_specific.mtu_reduced = ipv4_specific.mtu_reduced; - subflow_v6m_specific.net_frag_header_len = 0; subflow_v6m_specific.rebuild_header = subflow_rebuild_header; tcpv6_prot_override = tcpv6_prot; -- cgit From bd529dbb661d62bd9f03e44c9fc837d98a190499 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Wed, 25 Oct 2023 21:39:35 -0700 Subject: iommufd: Add a nested HW pagetable object IOMMU_HWPT_ALLOC already supports iommu_domain allocation for usersapce. But it can only allocate a hw_pagetable that associates to a given IOAS, i.e. only a kernel-managed hw_pagetable of IOMMUFD_OBJ_HWPT_PAGING type. IOMMU drivers can now support user-managed hw_pagetables, for two-stage translation use cases that require user data input from the user space. Add a new IOMMUFD_OBJ_HWPT_NESTED type with its abort/destroy(). Pair it with a new iommufd_hwpt_nested structure and its to_hwpt_nested() helper. Update the to_hwpt_paging() helper, so a NESTED-type hw_pagetable can be handled in the callers, for example iommufd_hw_pagetable_enforce_rr(). Screen the inputs including the parent PAGING-type hw_pagetable that has a need of a new nest_parent flag in the iommufd_hwpt_paging structure. Extend the IOMMU_HWPT_ALLOC ioctl to accept an IOMMU driver specific data input which is tagged by the enum iommu_hwpt_data_type. Also, update the @pt_id to accept hwpt_id too besides an ioas_id. Then, use them to allocate a hw_pagetable of IOMMUFD_OBJ_HWPT_NESTED type using the iommufd_hw_pagetable_alloc_nested() allocator. Link: https://lore.kernel.org/r/20231026043938.63898-8-yi.l.liu@intel.com Signed-off-by: Nicolin Chen Co-developed-by: Yi Liu Signed-off-by: Yi Liu Reviewed-by: Kevin Tian Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommufd/device.c | 3 +- drivers/iommu/iommufd/hw_pagetable.c | 109 ++++++++++++++++++++++++++++++-- drivers/iommu/iommufd/iommufd_private.h | 28 ++++++-- drivers/iommu/iommufd/main.c | 4 ++ include/uapi/linux/iommufd.h | 31 ++++++++- 5 files changed, 159 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index a99ce4547353..59d3a07300d9 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -588,7 +588,7 @@ iommufd_device_auto_get_domain(struct iommufd_device *idev, } hwpt_paging = iommufd_hwpt_paging_alloc(idev->ictx, ioas, idev, 0, - immediate_attach); + immediate_attach, NULL); if (IS_ERR(hwpt_paging)) { destroy_hwpt = ERR_CAST(hwpt_paging); goto out_unlock; @@ -628,6 +628,7 @@ static int iommufd_device_change_pt(struct iommufd_device *idev, u32 *pt_id, return PTR_ERR(pt_obj); switch (pt_obj->type) { + case IOMMUFD_OBJ_HWPT_NESTED: case IOMMUFD_OBJ_HWPT_PAGING: { struct iommufd_hw_pagetable *hwpt = container_of(pt_obj, struct iommufd_hw_pagetable, obj); diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index 198ecbd536f7..2abbeafdbd22 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -44,6 +44,22 @@ void iommufd_hwpt_paging_abort(struct iommufd_object *obj) iommufd_hwpt_paging_destroy(obj); } +void iommufd_hwpt_nested_destroy(struct iommufd_object *obj) +{ + struct iommufd_hwpt_nested *hwpt_nested = + container_of(obj, struct iommufd_hwpt_nested, common.obj); + + if (hwpt_nested->common.domain) + iommu_domain_free(hwpt_nested->common.domain); + + refcount_dec(&hwpt_nested->parent->common.obj.users); +} + +void iommufd_hwpt_nested_abort(struct iommufd_object *obj) +{ + iommufd_hwpt_nested_destroy(obj); +} + static int iommufd_hwpt_paging_enforce_cc(struct iommufd_hwpt_paging *hwpt_paging) { @@ -68,6 +84,8 @@ iommufd_hwpt_paging_enforce_cc(struct iommufd_hwpt_paging *hwpt_paging) * @idev: Device to get an iommu_domain for * @flags: Flags from userspace * @immediate_attach: True if idev should be attached to the hwpt + * @user_data: The user provided driver specific data describing the domain to + * create * * Allocate a new iommu_domain and return it as a hw_pagetable. The HWPT * will be linked to the given ioas and upon return the underlying iommu_domain @@ -80,7 +98,8 @@ iommufd_hwpt_paging_enforce_cc(struct iommufd_hwpt_paging *hwpt_paging) struct iommufd_hwpt_paging * iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, struct iommufd_device *idev, u32 flags, - bool immediate_attach) + bool immediate_attach, + const struct iommu_user_data *user_data) { const u32 valid_flags = IOMMU_HWPT_ALLOC_NEST_PARENT | IOMMU_HWPT_ALLOC_DIRTY_TRACKING; @@ -91,7 +110,7 @@ iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, lockdep_assert_held(&ioas->mutex); - if (flags && !ops->domain_alloc_user) + if ((flags || user_data) && !ops->domain_alloc_user) return ERR_PTR(-EOPNOTSUPP); if (flags & ~valid_flags) return ERR_PTR(-EOPNOTSUPP); @@ -106,10 +125,11 @@ iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, /* Pairs with iommufd_hw_pagetable_destroy() */ refcount_inc(&ioas->obj.users); hwpt_paging->ioas = ioas; + hwpt_paging->nest_parent = flags & IOMMU_HWPT_ALLOC_NEST_PARENT; if (ops->domain_alloc_user) { - hwpt->domain = - ops->domain_alloc_user(idev->dev, flags, NULL, NULL); + hwpt->domain = ops->domain_alloc_user(idev->dev, flags, NULL, + user_data); if (IS_ERR(hwpt->domain)) { rc = PTR_ERR(hwpt->domain); hwpt->domain = NULL; @@ -169,9 +189,70 @@ out_abort: return ERR_PTR(rc); } +/** + * iommufd_hwpt_nested_alloc() - Get a NESTED iommu_domain for a device + * @ictx: iommufd context + * @parent: Parent PAGING-type hwpt to associate the domain with + * @idev: Device to get an iommu_domain for + * @flags: Flags from userspace + * @user_data: user_data pointer. Must be valid + * + * Allocate a new iommu_domain (must be IOMMU_DOMAIN_NESTED) and return it as + * a NESTED hw_pagetable. The given parent PAGING-type hwpt must be capable of + * being a parent. + */ +static struct iommufd_hwpt_nested * +iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx, + struct iommufd_hwpt_paging *parent, + struct iommufd_device *idev, u32 flags, + const struct iommu_user_data *user_data) +{ + const struct iommu_ops *ops = dev_iommu_ops(idev->dev); + struct iommufd_hwpt_nested *hwpt_nested; + struct iommufd_hw_pagetable *hwpt; + int rc; + + if (flags || !user_data->len || !ops->domain_alloc_user) + return ERR_PTR(-EOPNOTSUPP); + if (parent->auto_domain || !parent->nest_parent) + return ERR_PTR(-EINVAL); + + hwpt_nested = __iommufd_object_alloc( + ictx, hwpt_nested, IOMMUFD_OBJ_HWPT_NESTED, common.obj); + if (IS_ERR(hwpt_nested)) + return ERR_CAST(hwpt_nested); + hwpt = &hwpt_nested->common; + + refcount_inc(&parent->common.obj.users); + hwpt_nested->parent = parent; + + hwpt->domain = ops->domain_alloc_user(idev->dev, flags, + parent->common.domain, user_data); + if (IS_ERR(hwpt->domain)) { + rc = PTR_ERR(hwpt->domain); + hwpt->domain = NULL; + goto out_abort; + } + + if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED)) { + rc = -EINVAL; + goto out_abort; + } + return hwpt_nested; + +out_abort: + iommufd_object_abort_and_destroy(ictx, &hwpt->obj); + return ERR_PTR(rc); +} + int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd) { struct iommu_hwpt_alloc *cmd = ucmd->cmd; + const struct iommu_user_data user_data = { + .type = cmd->data_type, + .uptr = u64_to_user_ptr(cmd->data_uptr), + .len = cmd->data_len, + }; struct iommufd_hw_pagetable *hwpt; struct iommufd_ioas *ioas = NULL; struct iommufd_object *pt_obj; @@ -180,6 +261,8 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd) if (cmd->__reserved) return -EOPNOTSUPP; + if (cmd->data_type == IOMMU_HWPT_DATA_NONE && cmd->data_len) + return -EINVAL; idev = iommufd_get_device(ucmd, cmd->dev_id); if (IS_ERR(idev)) @@ -196,13 +279,27 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd) ioas = container_of(pt_obj, struct iommufd_ioas, obj); mutex_lock(&ioas->mutex); - hwpt_paging = iommufd_hwpt_paging_alloc(ucmd->ictx, ioas, idev, - cmd->flags, false); + hwpt_paging = iommufd_hwpt_paging_alloc( + ucmd->ictx, ioas, idev, cmd->flags, false, + user_data.len ? &user_data : NULL); if (IS_ERR(hwpt_paging)) { rc = PTR_ERR(hwpt_paging); goto out_unlock; } hwpt = &hwpt_paging->common; + } else if (pt_obj->type == IOMMUFD_OBJ_HWPT_PAGING) { + struct iommufd_hwpt_nested *hwpt_nested; + + hwpt_nested = iommufd_hwpt_nested_alloc( + ucmd->ictx, + container_of(pt_obj, struct iommufd_hwpt_paging, + common.obj), + idev, cmd->flags, &user_data); + if (IS_ERR(hwpt_nested)) { + rc = PTR_ERR(hwpt_nested); + goto out_unlock; + } + hwpt = &hwpt_nested->common; } else { rc = -EINVAL; goto out_put_pt; diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index cd8da289ed0b..a74cfefffbc6 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -124,6 +124,7 @@ enum iommufd_object_type { IOMMUFD_OBJ_ANY = IOMMUFD_OBJ_NONE, IOMMUFD_OBJ_DEVICE, IOMMUFD_OBJ_HWPT_PAGING, + IOMMUFD_OBJ_HWPT_NESTED, IOMMUFD_OBJ_IOAS, IOMMUFD_OBJ_ACCESS, #ifdef CONFIG_IOMMUFD_TEST @@ -255,10 +256,16 @@ struct iommufd_hwpt_paging { bool auto_domain : 1; bool enforce_cache_coherency : 1; bool msi_cookie : 1; + bool nest_parent : 1; /* Head at iommufd_ioas::hwpt_list */ struct list_head hwpt_item; }; +struct iommufd_hwpt_nested { + struct iommufd_hw_pagetable common; + struct iommufd_hwpt_paging *parent; +}; + static inline bool hwpt_is_paging(struct iommufd_hw_pagetable *hwpt) { return hwpt->obj.type == IOMMUFD_OBJ_HWPT_PAGING; @@ -283,25 +290,32 @@ int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd); struct iommufd_hwpt_paging * iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, struct iommufd_device *idev, u32 flags, - bool immediate_attach); + bool immediate_attach, + const struct iommu_user_data *user_data); int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt, struct iommufd_device *idev); struct iommufd_hw_pagetable * iommufd_hw_pagetable_detach(struct iommufd_device *idev); void iommufd_hwpt_paging_destroy(struct iommufd_object *obj); void iommufd_hwpt_paging_abort(struct iommufd_object *obj); +void iommufd_hwpt_nested_destroy(struct iommufd_object *obj); +void iommufd_hwpt_nested_abort(struct iommufd_object *obj); int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd); static inline void iommufd_hw_pagetable_put(struct iommufd_ctx *ictx, struct iommufd_hw_pagetable *hwpt) { - struct iommufd_hwpt_paging *hwpt_paging = to_hwpt_paging(hwpt); + if (hwpt->obj.type == IOMMUFD_OBJ_HWPT_PAGING) { + struct iommufd_hwpt_paging *hwpt_paging = to_hwpt_paging(hwpt); - lockdep_assert_not_held(&hwpt_paging->ioas->mutex); - if (hwpt_paging->auto_domain) - iommufd_object_deref_user(ictx, &hwpt->obj); - else - refcount_dec(&hwpt->obj.users); + lockdep_assert_not_held(&hwpt_paging->ioas->mutex); + + if (hwpt_paging->auto_domain) { + iommufd_object_deref_user(ictx, &hwpt->obj); + return; + } + } + refcount_dec(&hwpt->obj.users); } struct iommufd_group { diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index ab6675a7f6b4..45b9d40773b1 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -492,6 +492,10 @@ static const struct iommufd_object_ops iommufd_object_ops[] = { .destroy = iommufd_hwpt_paging_destroy, .abort = iommufd_hwpt_paging_abort, }, + [IOMMUFD_OBJ_HWPT_NESTED] = { + .destroy = iommufd_hwpt_nested_destroy, + .abort = iommufd_hwpt_nested_abort, + }, #ifdef CONFIG_IOMMUFD_TEST [IOMMUFD_OBJ_SELFTEST] = { .destroy = iommufd_selftest_destroy, diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index c44eecf5d318..d816deac906f 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -361,20 +361,44 @@ enum iommufd_hwpt_alloc_flags { IOMMU_HWPT_ALLOC_DIRTY_TRACKING = 1 << 1, }; +/** + * enum iommu_hwpt_data_type - IOMMU HWPT Data Type + * @IOMMU_HWPT_DATA_NONE: no data + */ +enum iommu_hwpt_data_type { + IOMMU_HWPT_DATA_NONE, +}; + /** * struct iommu_hwpt_alloc - ioctl(IOMMU_HWPT_ALLOC) * @size: sizeof(struct iommu_hwpt_alloc) * @flags: Combination of enum iommufd_hwpt_alloc_flags * @dev_id: The device to allocate this HWPT for - * @pt_id: The IOAS to connect this HWPT to + * @pt_id: The IOAS or HWPT to connect this HWPT to * @out_hwpt_id: The ID of the new HWPT * @__reserved: Must be 0 + * @data_type: One of enum iommu_hwpt_data_type + * @data_len: Length of the type specific data + * @data_uptr: User pointer to the type specific data * * Explicitly allocate a hardware page table object. This is the same object * type that is returned by iommufd_device_attach() and represents the * underlying iommu driver's iommu_domain kernel object. * - * A HWPT will be created with the IOVA mappings from the given IOAS. + * A kernel-managed HWPT will be created with the mappings from the given + * IOAS via the @pt_id. The @data_type for this allocation must be set to + * IOMMU_HWPT_DATA_NONE. The HWPT can be allocated as a parent HWPT for a + * nesting configuration by passing IOMMU_HWPT_ALLOC_NEST_PARENT via @flags. + * + * A user-managed nested HWPT will be created from a given parent HWPT via + * @pt_id, in which the parent HWPT must be allocated previously via the + * same ioctl from a given IOAS (@pt_id). In this case, the @data_type + * must be set to a pre-defined type corresponding to an I/O page table + * type supported by the underlying IOMMU hardware. + * + * If the @data_type is set to IOMMU_HWPT_DATA_NONE, @data_len and + * @data_uptr should be zero. Otherwise, both @data_len and @data_uptr + * must be given. */ struct iommu_hwpt_alloc { __u32 size; @@ -383,6 +407,9 @@ struct iommu_hwpt_alloc { __u32 pt_id; __u32 out_hwpt_id; __u32 __reserved; + __u32 data_type; + __u32 data_len; + __aligned_u64 data_uptr; }; #define IOMMU_HWPT_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_ALLOC) -- cgit From 82b6661c9c35e60946dee536545b4848f25eafab Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Wed, 25 Oct 2023 21:42:09 -0700 Subject: iommufd: Add data structure for Intel VT-d stage-1 domain allocation This adds IOMMU_HWPT_DATA_VTD_S1 for stage-1 hw_pagetable of Intel VT-d and the corressponding data structure for userspace specified parameter for the domain allocation. Link: https://lore.kernel.org/r/20231026044216.64964-2-yi.l.liu@intel.com Reviewed-by: Kevin Tian Signed-off-by: Yi Liu Signed-off-by: Jason Gunthorpe --- include/uapi/linux/iommufd.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index d816deac906f..3ce5ee5f09b6 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -361,12 +361,42 @@ enum iommufd_hwpt_alloc_flags { IOMMU_HWPT_ALLOC_DIRTY_TRACKING = 1 << 1, }; +/** + * enum iommu_hwpt_vtd_s1_flags - Intel VT-d stage-1 page table + * entry attributes + * @IOMMU_VTD_S1_SRE: Supervisor request + * @IOMMU_VTD_S1_EAFE: Extended access enable + * @IOMMU_VTD_S1_WPE: Write protect enable + */ +enum iommu_hwpt_vtd_s1_flags { + IOMMU_VTD_S1_SRE = 1 << 0, + IOMMU_VTD_S1_EAFE = 1 << 1, + IOMMU_VTD_S1_WPE = 1 << 2, +}; + +/** + * struct iommu_hwpt_vtd_s1 - Intel VT-d stage-1 page table + * info (IOMMU_HWPT_DATA_VTD_S1) + * @flags: Combination of enum iommu_hwpt_vtd_s1_flags + * @pgtbl_addr: The base address of the stage-1 page table. + * @addr_width: The address width of the stage-1 page table + * @__reserved: Must be 0 + */ +struct iommu_hwpt_vtd_s1 { + __aligned_u64 flags; + __aligned_u64 pgtbl_addr; + __u32 addr_width; + __u32 __reserved; +}; + /** * enum iommu_hwpt_data_type - IOMMU HWPT Data Type * @IOMMU_HWPT_DATA_NONE: no data + * @IOMMU_HWPT_DATA_VTD_S1: Intel VT-d stage-1 page table */ enum iommu_hwpt_data_type { IOMMU_HWPT_DATA_NONE, + IOMMU_HWPT_DATA_VTD_S1, }; /** -- cgit From 03476e687eb07b94f7cdb07cd3c7c4304b6c58b3 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 25 Oct 2023 21:42:16 -0700 Subject: iommu/vt-d: Disallow read-only mappings to nest parent domain When remapping hardware is configured by system software in scalable mode as Nested (PGTT=011b) and with PWSNP field Set in the PASID-table-entry, it may Set Accessed bit and Dirty bit (and Extended Access bit if enabled) in first-stage page-table entries even when second-stage mappings indicate that corresponding first-stage page-table is Read-Only. As the result, contents of pages designated by VMM as Read-Only can be modified by IOMMU via PML5E (PML4E for 4-level tables) access as part of address translation process due to DMAs issued by Guest. This disallows read-only mappings in the domain that is supposed to be used as nested parent. Reference from Sapphire Rapids Specification Update [1], errata details, SPR17. Userspace should know this limitation by checking the IOMMU_HW_INFO_VTD_ERRATA_772415_SPR17 flag reported in the IOMMU_GET_HW_INFO ioctl. [1] https://www.intel.com/content/www/us/en/content-details/772415/content-details.html Link: https://lore.kernel.org/r/20231026044216.64964-9-yi.l.liu@intel.com Reviewed-by: Kevin Tian Signed-off-by: Lu Baolu Signed-off-by: Yi Liu Signed-off-by: Jason Gunthorpe --- drivers/iommu/intel/iommu.c | 6 ++++++ include/uapi/linux/iommufd.h | 12 +++++++++++- 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 4ce372d5d4f3..a2c429855cc0 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2194,6 +2194,11 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, if ((prot & (DMA_PTE_READ|DMA_PTE_WRITE)) == 0) return -EINVAL; + if (!(prot & DMA_PTE_WRITE) && domain->nested_parent) { + pr_err_ratelimited("Read-only mapping is disallowed on the domain which serves as the parent in a nested configuration, due to HW errata (ERRATA_772415_SPR17)\n"); + return -EINVAL; + } + attr = prot & (DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP); attr |= DMA_FL_PTE_PRESENT; if (domain->use_first_level) { @@ -4850,6 +4855,7 @@ static void *intel_iommu_hw_info(struct device *dev, u32 *length, u32 *type) if (!vtd) return ERR_PTR(-ENOMEM); + vtd->flags = IOMMU_HW_INFO_VTD_ERRATA_772415_SPR17; vtd->cap_reg = iommu->cap; vtd->ecap_reg = iommu->ecap; *length = sizeof(*vtd); diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 3ce5ee5f09b6..0b2bc6252e2c 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -443,10 +443,20 @@ struct iommu_hwpt_alloc { }; #define IOMMU_HWPT_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_ALLOC) +/** + * enum iommu_hw_info_vtd_flags - Flags for VT-d hw_info + * @IOMMU_HW_INFO_VTD_ERRATA_772415_SPR17: If set, disallow read-only mappings + * on a nested_parent domain. + * https://www.intel.com/content/www/us/en/content-details/772415/content-details.html + */ +enum iommu_hw_info_vtd_flags { + IOMMU_HW_INFO_VTD_ERRATA_772415_SPR17 = 1 << 0, +}; + /** * struct iommu_hw_info_vtd - Intel VT-d hardware information * - * @flags: Must be 0 + * @flags: Combination of enum iommu_hw_info_vtd_flags * @__reserved: Must be 0 * * @cap_reg: Value of Intel VT-d capability register defined in VT-d spec -- cgit From fff69fb03dde1dfa348cfdb74b13287dabe42c25 Mon Sep 17 00:00:00 2001 From: Konstantin Meskhidze Date: Thu, 26 Oct 2023 09:47:47 +0800 Subject: landlock: Support network rules with TCP bind and connect MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add network rules support in the ruleset management helpers and the landlock_create_ruleset() syscall. Extend user space API to support network actions: * Add new network access rights: LANDLOCK_ACCESS_NET_BIND_TCP and LANDLOCK_ACCESS_NET_CONNECT_TCP. * Add a new network rule type: LANDLOCK_RULE_NET_PORT tied to struct landlock_net_port_attr. The allowed_access field contains the network access rights, and the port field contains the port value according to the controlled protocol. This field can take up to a 64-bit value but the maximum value depends on the related protocol (e.g. 16-bit value for TCP). Network port is in host endianness [1]. * Add a new handled_access_net field to struct landlock_ruleset_attr that contains network access rights. * Increment the Landlock ABI version to 4. Implement socket_bind() and socket_connect() LSM hooks, which enable to control TCP socket binding and connection to specific ports. Expand access_masks_t from u16 to u32 to be able to store network access rights alongside filesystem access rights for rulesets' handled access rights. Access rights are not tied to socket file descriptors but checked at bind() or connect() call time against the caller's Landlock domain. For the filesystem, a file descriptor is a direct access to a file/data. However, for network sockets, we cannot identify for which data or peer a newly created socket will give access to. Indeed, we need to wait for a connect or bind request to identify the use case for this socket. Likewise a directory file descriptor may enable to open another file (i.e. a new data item), but this opening is also restricted by the caller's domain, not the file descriptor's access rights [2]. [1] https://lore.kernel.org/r/278ab07f-7583-a4e0-3d37-1bacd091531d@digikod.net [2] https://lore.kernel.org/r/263c1eb3-602f-57fe-8450-3f138581bee7@digikod.net Signed-off-by: Konstantin Meskhidze Link: https://lore.kernel.org/r/20231026014751.414649-9-konstantin.meskhidze@huawei.com [mic: Extend commit message, fix typo in comments, and specify endianness in the documentation] Co-developed-by: Mickaël Salaün Signed-off-by: Mickaël Salaün --- include/uapi/linux/landlock.h | 55 ++++++++ security/landlock/Kconfig | 1 + security/landlock/Makefile | 2 + security/landlock/limits.h | 5 + security/landlock/net.c | 200 +++++++++++++++++++++++++++ security/landlock/net.h | 33 +++++ security/landlock/ruleset.c | 61 +++++++- security/landlock/ruleset.h | 62 +++++++-- security/landlock/setup.c | 2 + security/landlock/syscalls.c | 72 ++++++++-- tools/testing/selftests/landlock/base_test.c | 2 +- 11 files changed, 470 insertions(+), 25 deletions(-) create mode 100644 security/landlock/net.c create mode 100644 security/landlock/net.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index 81d09ef9aa50..25c8d7677539 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -31,6 +31,12 @@ struct landlock_ruleset_attr { * this access right. */ __u64 handled_access_fs; + /** + * @handled_access_net: Bitmask of actions (cf. `Network flags`_) + * that is handled by this ruleset and should then be forbidden if no + * rule explicitly allow them. + */ + __u64 handled_access_net; }; /* @@ -54,6 +60,11 @@ enum landlock_rule_type { * landlock_path_beneath_attr . */ LANDLOCK_RULE_PATH_BENEATH = 1, + /** + * @LANDLOCK_RULE_NET_PORT: Type of a &struct + * landlock_net_port_attr . + */ + LANDLOCK_RULE_NET_PORT, }; /** @@ -79,6 +90,31 @@ struct landlock_path_beneath_attr { */ } __attribute__((packed)); +/** + * struct landlock_net_port_attr - Network port definition + * + * Argument of sys_landlock_add_rule(). + */ +struct landlock_net_port_attr { + /** + * @allowed_access: Bitmask of allowed access network for a port + * (cf. `Network flags`_). + */ + __u64 allowed_access; + /** + * @port: Network port in host endianness. + * + * It should be noted that port 0 passed to :manpage:`bind(2)` will + * bind to an available port from a specific port range. This can be + * configured thanks to the ``/proc/sys/net/ipv4/ip_local_port_range`` + * sysctl (also used for IPv6). A Landlock rule with port 0 and the + * ``LANDLOCK_ACCESS_NET_BIND_TCP`` right means that requesting to bind + * on port 0 is allowed and it will automatically translate to binding + * on the related port range. + */ + __u64 port; +}; + /** * DOC: fs_access * @@ -189,4 +225,23 @@ struct landlock_path_beneath_attr { #define LANDLOCK_ACCESS_FS_TRUNCATE (1ULL << 14) /* clang-format on */ +/** + * DOC: net_access + * + * Network flags + * ~~~~~~~~~~~~~~~~ + * + * These flags enable to restrict a sandboxed process to a set of network + * actions. This is supported since the Landlock ABI version 4. + * + * TCP sockets with allowed actions: + * + * - %LANDLOCK_ACCESS_NET_BIND_TCP: Bind a TCP socket to a local port. + * - %LANDLOCK_ACCESS_NET_CONNECT_TCP: Connect an active TCP socket to + * a remote port. + */ +/* clang-format off */ +#define LANDLOCK_ACCESS_NET_BIND_TCP (1ULL << 0) +#define LANDLOCK_ACCESS_NET_CONNECT_TCP (1ULL << 1) +/* clang-format on */ #endif /* _UAPI_LINUX_LANDLOCK_H */ diff --git a/security/landlock/Kconfig b/security/landlock/Kconfig index c1e862a38410..c4bf0d5eff39 100644 --- a/security/landlock/Kconfig +++ b/security/landlock/Kconfig @@ -3,6 +3,7 @@ config SECURITY_LANDLOCK bool "Landlock support" depends on SECURITY + select SECURITY_NETWORK select SECURITY_PATH help Landlock is a sandboxing mechanism that enables processes to restrict diff --git a/security/landlock/Makefile b/security/landlock/Makefile index 7bbd2f413b3e..c2e116f2a299 100644 --- a/security/landlock/Makefile +++ b/security/landlock/Makefile @@ -2,3 +2,5 @@ obj-$(CONFIG_SECURITY_LANDLOCK) := landlock.o landlock-y := setup.o syscalls.o object.o ruleset.o \ cred.o ptrace.o fs.o + +landlock-$(CONFIG_INET) += net.o diff --git a/security/landlock/limits.h b/security/landlock/limits.h index bafb3b8dc677..93c9c6f91556 100644 --- a/security/landlock/limits.h +++ b/security/landlock/limits.h @@ -23,6 +23,11 @@ #define LANDLOCK_NUM_ACCESS_FS __const_hweight64(LANDLOCK_MASK_ACCESS_FS) #define LANDLOCK_SHIFT_ACCESS_FS 0 +#define LANDLOCK_LAST_ACCESS_NET LANDLOCK_ACCESS_NET_CONNECT_TCP +#define LANDLOCK_MASK_ACCESS_NET ((LANDLOCK_LAST_ACCESS_NET << 1) - 1) +#define LANDLOCK_NUM_ACCESS_NET __const_hweight64(LANDLOCK_MASK_ACCESS_NET) +#define LANDLOCK_SHIFT_ACCESS_NET LANDLOCK_NUM_ACCESS_FS + /* clang-format on */ #endif /* _SECURITY_LANDLOCK_LIMITS_H */ diff --git a/security/landlock/net.c b/security/landlock/net.c new file mode 100644 index 000000000000..aaa92c2b1f08 --- /dev/null +++ b/security/landlock/net.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Landlock LSM - Network management and hooks + * + * Copyright © 2022-2023 Huawei Tech. Co., Ltd. + * Copyright © 2022-2023 Microsoft Corporation + */ + +#include +#include +#include +#include + +#include "common.h" +#include "cred.h" +#include "limits.h" +#include "net.h" +#include "ruleset.h" + +int landlock_append_net_rule(struct landlock_ruleset *const ruleset, + const u16 port, access_mask_t access_rights) +{ + int err; + const struct landlock_id id = { + .key.data = (__force uintptr_t)htons(port), + .type = LANDLOCK_KEY_NET_PORT, + }; + + BUILD_BUG_ON(sizeof(port) > sizeof(id.key.data)); + + /* Transforms relative access rights to absolute ones. */ + access_rights |= LANDLOCK_MASK_ACCESS_NET & + ~landlock_get_net_access_mask(ruleset, 0); + + mutex_lock(&ruleset->lock); + err = landlock_insert_rule(ruleset, id, access_rights); + mutex_unlock(&ruleset->lock); + + return err; +} + +static access_mask_t +get_raw_handled_net_accesses(const struct landlock_ruleset *const domain) +{ + access_mask_t access_dom = 0; + size_t layer_level; + + for (layer_level = 0; layer_level < domain->num_layers; layer_level++) + access_dom |= landlock_get_net_access_mask(domain, layer_level); + return access_dom; +} + +static const struct landlock_ruleset *get_current_net_domain(void) +{ + const struct landlock_ruleset *const dom = + landlock_get_current_domain(); + + if (!dom || !get_raw_handled_net_accesses(dom)) + return NULL; + + return dom; +} + +static int current_check_access_socket(struct socket *const sock, + struct sockaddr *const address, + const int addrlen, + const access_mask_t access_request) +{ + __be16 port; + layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_NET] = {}; + const struct landlock_rule *rule; + access_mask_t handled_access; + struct landlock_id id = { + .type = LANDLOCK_KEY_NET_PORT, + }; + const struct landlock_ruleset *const dom = get_current_net_domain(); + + if (!dom) + return 0; + if (WARN_ON_ONCE(dom->num_layers < 1)) + return -EACCES; + + /* Checks if it's a (potential) TCP socket. */ + if (sock->type != SOCK_STREAM) + return 0; + + /* Checks for minimal header length to safely read sa_family. */ + if (addrlen < offsetofend(typeof(*address), sa_family)) + return -EINVAL; + + switch (address->sa_family) { + case AF_UNSPEC: + case AF_INET: + if (addrlen < sizeof(struct sockaddr_in)) + return -EINVAL; + port = ((struct sockaddr_in *)address)->sin_port; + break; + +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + if (addrlen < SIN6_LEN_RFC2133) + return -EINVAL; + port = ((struct sockaddr_in6 *)address)->sin6_port; + break; +#endif /* IS_ENABLED(CONFIG_IPV6) */ + + default: + return 0; + } + + /* Specific AF_UNSPEC handling. */ + if (address->sa_family == AF_UNSPEC) { + /* + * Connecting to an address with AF_UNSPEC dissolves the TCP + * association, which have the same effect as closing the + * connection while retaining the socket object (i.e., the file + * descriptor). As for dropping privileges, closing + * connections is always allowed. + * + * For a TCP access control system, this request is legitimate. + * Let the network stack handle potential inconsistencies and + * return -EINVAL if needed. + */ + if (access_request == LANDLOCK_ACCESS_NET_CONNECT_TCP) + return 0; + + /* + * For compatibility reason, accept AF_UNSPEC for bind + * accesses (mapped to AF_INET) only if the address is + * INADDR_ANY (cf. __inet_bind). Checking the address is + * required to not wrongfully return -EACCES instead of + * -EAFNOSUPPORT. + * + * We could return 0 and let the network stack handle these + * checks, but it is safer to return a proper error and test + * consistency thanks to kselftest. + */ + if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP) { + /* addrlen has already been checked for AF_UNSPEC. */ + const struct sockaddr_in *const sockaddr = + (struct sockaddr_in *)address; + + if (sock->sk->__sk_common.skc_family != AF_INET) + return -EINVAL; + + if (sockaddr->sin_addr.s_addr != htonl(INADDR_ANY)) + return -EAFNOSUPPORT; + } + } else { + /* + * Checks sa_family consistency to not wrongfully return + * -EACCES instead of -EINVAL. Valid sa_family changes are + * only (from AF_INET or AF_INET6) to AF_UNSPEC. + * + * We could return 0 and let the network stack handle this + * check, but it is safer to return a proper error and test + * consistency thanks to kselftest. + */ + if (address->sa_family != sock->sk->__sk_common.skc_family) + return -EINVAL; + } + + id.key.data = (__force uintptr_t)port; + BUILD_BUG_ON(sizeof(port) > sizeof(id.key.data)); + + rule = landlock_find_rule(dom, id); + handled_access = landlock_init_layer_masks( + dom, access_request, &layer_masks, LANDLOCK_KEY_NET_PORT); + if (landlock_unmask_layers(rule, handled_access, &layer_masks, + ARRAY_SIZE(layer_masks))) + return 0; + + return -EACCES; +} + +static int hook_socket_bind(struct socket *const sock, + struct sockaddr *const address, const int addrlen) +{ + return current_check_access_socket(sock, address, addrlen, + LANDLOCK_ACCESS_NET_BIND_TCP); +} + +static int hook_socket_connect(struct socket *const sock, + struct sockaddr *const address, + const int addrlen) +{ + return current_check_access_socket(sock, address, addrlen, + LANDLOCK_ACCESS_NET_CONNECT_TCP); +} + +static struct security_hook_list landlock_hooks[] __ro_after_init = { + LSM_HOOK_INIT(socket_bind, hook_socket_bind), + LSM_HOOK_INIT(socket_connect, hook_socket_connect), +}; + +__init void landlock_add_net_hooks(void) +{ + security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks), + LANDLOCK_NAME); +} diff --git a/security/landlock/net.h b/security/landlock/net.h new file mode 100644 index 000000000000..09960c237a13 --- /dev/null +++ b/security/landlock/net.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Landlock LSM - Network management and hooks + * + * Copyright © 2022-2023 Huawei Tech. Co., Ltd. + */ + +#ifndef _SECURITY_LANDLOCK_NET_H +#define _SECURITY_LANDLOCK_NET_H + +#include "common.h" +#include "ruleset.h" +#include "setup.h" + +#if IS_ENABLED(CONFIG_INET) +__init void landlock_add_net_hooks(void); + +int landlock_append_net_rule(struct landlock_ruleset *const ruleset, + const u16 port, access_mask_t access_rights); +#else /* IS_ENABLED(CONFIG_INET) */ +static inline void landlock_add_net_hooks(void) +{ +} + +static inline int +landlock_append_net_rule(struct landlock_ruleset *const ruleset, const u16 port, + access_mask_t access_rights) +{ + return -EAFNOSUPPORT; +} +#endif /* IS_ENABLED(CONFIG_INET) */ + +#endif /* _SECURITY_LANDLOCK_NET_H */ diff --git a/security/landlock/ruleset.c b/security/landlock/ruleset.c index e36c5c332242..ffedc99f2b68 100644 --- a/security/landlock/ruleset.c +++ b/security/landlock/ruleset.c @@ -36,6 +36,11 @@ static struct landlock_ruleset *create_ruleset(const u32 num_layers) refcount_set(&new_ruleset->usage, 1); mutex_init(&new_ruleset->lock); new_ruleset->root_inode = RB_ROOT; + +#if IS_ENABLED(CONFIG_INET) + new_ruleset->root_net_port = RB_ROOT; +#endif /* IS_ENABLED(CONFIG_INET) */ + new_ruleset->num_layers = num_layers; /* * hierarchy = NULL @@ -46,16 +51,21 @@ static struct landlock_ruleset *create_ruleset(const u32 num_layers) } struct landlock_ruleset * -landlock_create_ruleset(const access_mask_t fs_access_mask) +landlock_create_ruleset(const access_mask_t fs_access_mask, + const access_mask_t net_access_mask) { struct landlock_ruleset *new_ruleset; /* Informs about useless ruleset. */ - if (!fs_access_mask) + if (!fs_access_mask && !net_access_mask) return ERR_PTR(-ENOMSG); new_ruleset = create_ruleset(1); - if (!IS_ERR(new_ruleset)) + if (IS_ERR(new_ruleset)) + return new_ruleset; + if (fs_access_mask) landlock_add_fs_access_mask(new_ruleset, fs_access_mask, 0); + if (net_access_mask) + landlock_add_net_access_mask(new_ruleset, net_access_mask, 0); return new_ruleset; } @@ -74,6 +84,11 @@ static bool is_object_pointer(const enum landlock_key_type key_type) case LANDLOCK_KEY_INODE: return true; +#if IS_ENABLED(CONFIG_INET) + case LANDLOCK_KEY_NET_PORT: + return false; +#endif /* IS_ENABLED(CONFIG_INET) */ + default: WARN_ON_ONCE(1); return false; @@ -126,6 +141,11 @@ static struct rb_root *get_root(struct landlock_ruleset *const ruleset, case LANDLOCK_KEY_INODE: return &ruleset->root_inode; +#if IS_ENABLED(CONFIG_INET) + case LANDLOCK_KEY_NET_PORT: + return &ruleset->root_net_port; +#endif /* IS_ENABLED(CONFIG_INET) */ + default: WARN_ON_ONCE(1); return ERR_PTR(-EINVAL); @@ -154,7 +174,8 @@ static void build_check_ruleset(void) BUILD_BUG_ON(ruleset.num_rules < LANDLOCK_MAX_NUM_RULES); BUILD_BUG_ON(ruleset.num_layers < LANDLOCK_MAX_NUM_LAYERS); BUILD_BUG_ON(access_masks < - (LANDLOCK_MASK_ACCESS_FS << LANDLOCK_SHIFT_ACCESS_FS)); + ((LANDLOCK_MASK_ACCESS_FS << LANDLOCK_SHIFT_ACCESS_FS) | + (LANDLOCK_MASK_ACCESS_NET << LANDLOCK_SHIFT_ACCESS_NET))); } /** @@ -371,6 +392,13 @@ static int merge_ruleset(struct landlock_ruleset *const dst, if (err) goto out_unlock; +#if IS_ENABLED(CONFIG_INET) + /* Merges the @src network port tree. */ + err = merge_tree(dst, src, LANDLOCK_KEY_NET_PORT); + if (err) + goto out_unlock; +#endif /* IS_ENABLED(CONFIG_INET) */ + out_unlock: mutex_unlock(&src->lock); mutex_unlock(&dst->lock); @@ -427,6 +455,13 @@ static int inherit_ruleset(struct landlock_ruleset *const parent, if (err) goto out_unlock; +#if IS_ENABLED(CONFIG_INET) + /* Copies the @parent network port tree. */ + err = inherit_tree(parent, child, LANDLOCK_KEY_NET_PORT); + if (err) + goto out_unlock; +#endif /* IS_ENABLED(CONFIG_INET) */ + if (WARN_ON_ONCE(child->num_layers <= parent->num_layers)) { err = -EINVAL; goto out_unlock; @@ -456,6 +491,13 @@ static void free_ruleset(struct landlock_ruleset *const ruleset) rbtree_postorder_for_each_entry_safe(freeme, next, &ruleset->root_inode, node) free_rule(freeme, LANDLOCK_KEY_INODE); + +#if IS_ENABLED(CONFIG_INET) + rbtree_postorder_for_each_entry_safe(freeme, next, + &ruleset->root_net_port, node) + free_rule(freeme, LANDLOCK_KEY_NET_PORT); +#endif /* IS_ENABLED(CONFIG_INET) */ + put_hierarchy(ruleset->hierarchy); kfree(ruleset); } @@ -636,7 +678,8 @@ get_access_mask_t(const struct landlock_ruleset *const ruleset, * * @domain: The domain that defines the current restrictions. * @access_request: The requested access rights to check. - * @layer_masks: The layer masks to populate. + * @layer_masks: It must contain %LANDLOCK_NUM_ACCESS_FS or + * %LANDLOCK_NUM_ACCESS_NET elements according to @key_type. * @key_type: The key type to switch between access masks of different types. * * Returns: An access mask where each access right bit is set which is handled @@ -657,6 +700,14 @@ landlock_init_layer_masks(const struct landlock_ruleset *const domain, get_access_mask = landlock_get_fs_access_mask; num_access = LANDLOCK_NUM_ACCESS_FS; break; + +#if IS_ENABLED(CONFIG_INET) + case LANDLOCK_KEY_NET_PORT: + get_access_mask = landlock_get_net_access_mask; + num_access = LANDLOCK_NUM_ACCESS_NET; + break; +#endif /* IS_ENABLED(CONFIG_INET) */ + default: WARN_ON_ONCE(1); return 0; diff --git a/security/landlock/ruleset.h b/security/landlock/ruleset.h index 7107ce7da39d..c7f1526784fd 100644 --- a/security/landlock/ruleset.h +++ b/security/landlock/ruleset.h @@ -33,13 +33,16 @@ typedef u16 access_mask_t; /* Makes sure all filesystem access rights can be stored. */ static_assert(BITS_PER_TYPE(access_mask_t) >= LANDLOCK_NUM_ACCESS_FS); +/* Makes sure all network access rights can be stored. */ +static_assert(BITS_PER_TYPE(access_mask_t) >= LANDLOCK_NUM_ACCESS_NET); /* Makes sure for_each_set_bit() and for_each_clear_bit() calls are OK. */ static_assert(sizeof(unsigned long) >= sizeof(access_mask_t)); /* Ruleset access masks. */ -typedef u16 access_masks_t; +typedef u32 access_masks_t; /* Makes sure all ruleset access rights can be stored. */ -static_assert(BITS_PER_TYPE(access_masks_t) >= LANDLOCK_NUM_ACCESS_FS); +static_assert(BITS_PER_TYPE(access_masks_t) >= + LANDLOCK_NUM_ACCESS_FS + LANDLOCK_NUM_ACCESS_NET); typedef u16 layer_mask_t; /* Makes sure all layers can be checked. */ @@ -84,6 +87,11 @@ enum landlock_key_type { * keys. */ LANDLOCK_KEY_INODE = 1, + /** + * @LANDLOCK_KEY_NET_PORT: Type of &landlock_ruleset.root_net_port's + * node keys. + */ + LANDLOCK_KEY_NET_PORT, }; /** @@ -158,6 +166,17 @@ struct landlock_ruleset { * reaches zero. */ struct rb_root root_inode; + +#if IS_ENABLED(CONFIG_INET) + /** + * @root_net_port: Root of a red-black tree containing &struct + * landlock_rule nodes with network port. Once a ruleset is tied to a + * process (i.e. as a domain), this tree is immutable until @usage + * reaches zero. + */ + struct rb_root root_net_port; +#endif /* IS_ENABLED(CONFIG_INET) */ + /** * @hierarchy: Enables hierarchy identification even when a parent * domain vanishes. This is needed for the ptrace protection. @@ -196,13 +215,13 @@ struct landlock_ruleset { */ u32 num_layers; /** - * @access_masks: Contains the subset of filesystem - * actions that are restricted by a ruleset. A domain - * saves all layers of merged rulesets in a stack - * (FAM), starting from the first layer to the last - * one. These layers are used when merging rulesets, - * for user space backward compatibility (i.e. - * future-proof), and to properly handle merged + * @access_masks: Contains the subset of filesystem and + * network actions that are restricted by a ruleset. + * A domain saves all layers of merged rulesets in a + * stack (FAM), starting from the first layer to the + * last one. These layers are used when merging + * rulesets, for user space backward compatibility + * (i.e. future-proof), and to properly handle merged * rulesets without overlapping access rights. These * layers are set once and never changed for the * lifetime of the ruleset. @@ -213,7 +232,8 @@ struct landlock_ruleset { }; struct landlock_ruleset * -landlock_create_ruleset(const access_mask_t access_mask); +landlock_create_ruleset(const access_mask_t access_mask_fs, + const access_mask_t access_mask_net); void landlock_put_ruleset(struct landlock_ruleset *const ruleset); void landlock_put_ruleset_deferred(struct landlock_ruleset *const ruleset); @@ -249,6 +269,19 @@ landlock_add_fs_access_mask(struct landlock_ruleset *const ruleset, (fs_mask << LANDLOCK_SHIFT_ACCESS_FS); } +static inline void +landlock_add_net_access_mask(struct landlock_ruleset *const ruleset, + const access_mask_t net_access_mask, + const u16 layer_level) +{ + access_mask_t net_mask = net_access_mask & LANDLOCK_MASK_ACCESS_NET; + + /* Should already be checked in sys_landlock_create_ruleset(). */ + WARN_ON_ONCE(net_access_mask != net_mask); + ruleset->access_masks[layer_level] |= + (net_mask << LANDLOCK_SHIFT_ACCESS_NET); +} + static inline access_mask_t landlock_get_raw_fs_access_mask(const struct landlock_ruleset *const ruleset, const u16 layer_level) @@ -267,6 +300,15 @@ landlock_get_fs_access_mask(const struct landlock_ruleset *const ruleset, LANDLOCK_ACCESS_FS_INITIALLY_DENIED; } +static inline access_mask_t +landlock_get_net_access_mask(const struct landlock_ruleset *const ruleset, + const u16 layer_level) +{ + return (ruleset->access_masks[layer_level] >> + LANDLOCK_SHIFT_ACCESS_NET) & + LANDLOCK_MASK_ACCESS_NET; +} + bool landlock_unmask_layers(const struct landlock_rule *const rule, const access_mask_t access_request, layer_mask_t (*const layer_masks)[], diff --git a/security/landlock/setup.c b/security/landlock/setup.c index 0f6113528fa4..3e11d303542f 100644 --- a/security/landlock/setup.c +++ b/security/landlock/setup.c @@ -12,6 +12,7 @@ #include "common.h" #include "cred.h" #include "fs.h" +#include "net.h" #include "ptrace.h" #include "setup.h" @@ -29,6 +30,7 @@ static int __init landlock_init(void) landlock_add_cred_hooks(); landlock_add_ptrace_hooks(); landlock_add_fs_hooks(); + landlock_add_net_hooks(); landlock_initialized = true; pr_info("Up and running.\n"); return 0; diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c index e87f572e0251..898358f57fa0 100644 --- a/security/landlock/syscalls.c +++ b/security/landlock/syscalls.c @@ -29,6 +29,7 @@ #include "cred.h" #include "fs.h" #include "limits.h" +#include "net.h" #include "ruleset.h" #include "setup.h" @@ -74,7 +75,8 @@ static void build_check_abi(void) { struct landlock_ruleset_attr ruleset_attr; struct landlock_path_beneath_attr path_beneath_attr; - size_t ruleset_size, path_beneath_size; + struct landlock_net_port_attr net_port_attr; + size_t ruleset_size, path_beneath_size, net_port_size; /* * For each user space ABI structures, first checks that there is no @@ -82,13 +84,19 @@ static void build_check_abi(void) * struct size. */ ruleset_size = sizeof(ruleset_attr.handled_access_fs); + ruleset_size += sizeof(ruleset_attr.handled_access_net); BUILD_BUG_ON(sizeof(ruleset_attr) != ruleset_size); - BUILD_BUG_ON(sizeof(ruleset_attr) != 8); + BUILD_BUG_ON(sizeof(ruleset_attr) != 16); path_beneath_size = sizeof(path_beneath_attr.allowed_access); path_beneath_size += sizeof(path_beneath_attr.parent_fd); BUILD_BUG_ON(sizeof(path_beneath_attr) != path_beneath_size); BUILD_BUG_ON(sizeof(path_beneath_attr) != 12); + + net_port_size = sizeof(net_port_attr.allowed_access); + net_port_size += sizeof(net_port_attr.port); + BUILD_BUG_ON(sizeof(net_port_attr) != net_port_size); + BUILD_BUG_ON(sizeof(net_port_attr) != 16); } /* Ruleset handling */ @@ -129,7 +137,7 @@ static const struct file_operations ruleset_fops = { .write = fop_dummy_write, }; -#define LANDLOCK_ABI_VERSION 3 +#define LANDLOCK_ABI_VERSION 4 /** * sys_landlock_create_ruleset - Create a new ruleset @@ -188,8 +196,14 @@ SYSCALL_DEFINE3(landlock_create_ruleset, LANDLOCK_MASK_ACCESS_FS) return -EINVAL; + /* Checks network content (and 32-bits cast). */ + if ((ruleset_attr.handled_access_net | LANDLOCK_MASK_ACCESS_NET) != + LANDLOCK_MASK_ACCESS_NET) + return -EINVAL; + /* Checks arguments and transforms to kernel struct. */ - ruleset = landlock_create_ruleset(ruleset_attr.handled_access_fs); + ruleset = landlock_create_ruleset(ruleset_attr.handled_access_fs, + ruleset_attr.handled_access_net); if (IS_ERR(ruleset)) return PTR_ERR(ruleset); @@ -282,7 +296,7 @@ static int add_rule_path_beneath(struct landlock_ruleset *const ruleset, int res, err; access_mask_t mask; - /* Copies raw user space buffer, only one type for now. */ + /* Copies raw user space buffer. */ res = copy_from_user(&path_beneath_attr, rule_attr, sizeof(path_beneath_attr)); if (res) @@ -312,13 +326,46 @@ static int add_rule_path_beneath(struct landlock_ruleset *const ruleset, return err; } +static int add_rule_net_port(struct landlock_ruleset *ruleset, + const void __user *const rule_attr) +{ + struct landlock_net_port_attr net_port_attr; + int res; + access_mask_t mask; + + /* Copies raw user space buffer. */ + res = copy_from_user(&net_port_attr, rule_attr, sizeof(net_port_attr)); + if (res) + return -EFAULT; + + /* + * Informs about useless rule: empty allowed_access (i.e. deny rules) + * are ignored by network actions. + */ + if (!net_port_attr.allowed_access) + return -ENOMSG; + + /* Checks that allowed_access matches the @ruleset constraints. */ + mask = landlock_get_net_access_mask(ruleset, 0); + if ((net_port_attr.allowed_access | mask) != mask) + return -EINVAL; + + /* Denies inserting a rule with port greater than 65535. */ + if (net_port_attr.port > U16_MAX) + return -EINVAL; + + /* Imports the new rule. */ + return landlock_append_net_rule(ruleset, net_port_attr.port, + net_port_attr.allowed_access); +} + /** * sys_landlock_add_rule - Add a new rule to a ruleset * * @ruleset_fd: File descriptor tied to the ruleset that should be extended * with the new rule. - * @rule_type: Identify the structure type pointed to by @rule_attr (only - * %LANDLOCK_RULE_PATH_BENEATH for now). + * @rule_type: Identify the structure type pointed to by @rule_attr: + * %LANDLOCK_RULE_PATH_BENEATH or %LANDLOCK_RULE_NET_PORT. * @rule_attr: Pointer to a rule (only of type &struct * landlock_path_beneath_attr for now). * @flags: Must be 0. @@ -329,9 +376,13 @@ static int add_rule_path_beneath(struct landlock_ruleset *const ruleset, * Possible returned errors are: * * - %EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time; + * - %EAFNOSUPPORT: @rule_type is %LANDLOCK_RULE_NET_PORT but TCP/IP is not + * supported by the running kernel; * - %EINVAL: @flags is not 0, or inconsistent access in the rule (i.e. - * &landlock_path_beneath_attr.allowed_access is not a subset of the - * ruleset handled accesses); + * &landlock_path_beneath_attr.allowed_access or + * &landlock_net_port_attr.allowed_access is not a subset of the + * ruleset handled accesses), or &landlock_net_port_attr.port is + * greater than 65535; * - %ENOMSG: Empty accesses (e.g. &landlock_path_beneath_attr.allowed_access); * - %EBADF: @ruleset_fd is not a file descriptor for the current thread, or a * member of @rule_attr is not a file descriptor as expected; @@ -363,6 +414,9 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd, case LANDLOCK_RULE_PATH_BENEATH: err = add_rule_path_beneath(ruleset, rule_attr); break; + case LANDLOCK_RULE_NET_PORT: + err = add_rule_net_port(ruleset, rule_attr); + break; default: err = -EINVAL; break; diff --git a/tools/testing/selftests/landlock/base_test.c b/tools/testing/selftests/landlock/base_test.c index 792c3f0a59b4..646f778dfb1e 100644 --- a/tools/testing/selftests/landlock/base_test.c +++ b/tools/testing/selftests/landlock/base_test.c @@ -75,7 +75,7 @@ TEST(abi_version) const struct landlock_ruleset_attr ruleset_attr = { .handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE, }; - ASSERT_EQ(3, landlock_create_ruleset(NULL, 0, + ASSERT_EQ(4, landlock_create_ruleset(NULL, 0, LANDLOCK_CREATE_RULESET_VERSION)); ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, 0, -- cgit From e6b3d55b67d00c084a2b98c594330411fb4ebeac Mon Sep 17 00:00:00 2001 From: Daniel Starke Date: Fri, 27 Oct 2023 07:39:03 +0200 Subject: tty: n_gsm: add copyright Siemens Mobility GmbH More than 1/3 of the n_gsm code has been contributed by us in the last 1.5 years, completing conformance with the standard and stabilizing the driver: - added UI (unnumbered information) frame support - added PN (parameter negotiation) message handling and function support - added optional keep-alive control link supervision via test messages - added TIOCM_OUT1 and TIOCM_OUT2 to allow responder to operate as modem - added TIOCMIWAIT support on virtual ttys - added additional ioctls and parameters to configure the new functions - added overall locking mechanism to avoid data race conditions - added outgoing data flow to decouple physical from virtual tty handling for better performance and to avoid dead-locks - fixed advanced option mode implementation - fixed convergence layer type 2 implementation - fixed handling of CLD (multiplexer close down) messages - fixed broken muxer close down procedure - and many more bug fixes With this most of our initial RFC has been implemented. It gives the driver a quality boost unseen in the decade before. Add a copyright notice to the n_gsm files to highlight this contribution. Link: https://lore.kernel.org/all/20220225080758.2869-1-daniel.starke@siemens.com/ Signed-off-by: Daniel Starke Link: https://lore.kernel.org/r/20231027053903.1886-1-daniel.starke@siemens.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_gsm.c | 1 + include/uapi/linux/gsmmux.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 0ee7531c9201..a3ab3946e4ad 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -2,6 +2,7 @@ /* * n_gsm.c GSM 0710 tty multiplexor * Copyright (c) 2009/10 Intel Corporation + * Copyright (c) 2022/23 Siemens Mobility GmbH * * * THIS IS A DEVELOPMENT SNAPSHOT IT IS NOT A FINAL RELEASE * * diff --git a/include/uapi/linux/gsmmux.h b/include/uapi/linux/gsmmux.h index 4c878d84dbda..3a93f17ca943 100644 --- a/include/uapi/linux/gsmmux.h +++ b/include/uapi/linux/gsmmux.h @@ -1,4 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (c) 2022/23 Siemens Mobility GmbH */ #ifndef _LINUX_GSMMUX_H #define _LINUX_GSMMUX_H -- cgit From c845f5f3590ef4669fe5464f8a42be6442cd174b Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 23 Oct 2023 20:21:54 +0100 Subject: net/tcp: Add TCP-AO config and structures Introduce new kernel config option and common structures as well as helpers to be used by TCP-AO code. Co-developed-by: Francesco Ruggeri Signed-off-by: Francesco Ruggeri Co-developed-by: Salam Noureddine Signed-off-by: Salam Noureddine Signed-off-by: Dmitry Safonov Acked-by: David Ahern Signed-off-by: David S. Miller --- include/linux/tcp.h | 9 +++-- include/net/tcp.h | 8 ++--- include/net/tcp_ao.h | 90 ++++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/tcp.h | 2 ++ net/ipv4/Kconfig | 13 +++++++ 5 files changed, 114 insertions(+), 8 deletions(-) create mode 100644 include/net/tcp_ao.h (limited to 'include/uapi/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 6df715b6e51d..64e7b560fa79 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -447,13 +447,18 @@ struct tcp_sock { bool syn_smc; /* SYN includes SMC */ #endif -#ifdef CONFIG_TCP_MD5SIG -/* TCP AF-Specific parts; only used by MD5 Signature support so far */ +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) +/* TCP AF-Specific parts; only used by TCP-AO/MD5 Signature support so far */ const struct tcp_sock_af_ops *af_specific; +#ifdef CONFIG_TCP_MD5SIG /* TCP MD5 Signature Option information */ struct tcp_md5sig_info __rcu *md5sig_info; #endif +#ifdef CONFIG_TCP_AO + struct tcp_ao_info __rcu *ao_info; +#endif +#endif /* TCP fastopen related information */ struct tcp_fastopen_request *fastopen_req; diff --git a/include/net/tcp.h b/include/net/tcp.h index f6e2db5292b5..3153712faa3d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -37,6 +37,7 @@ #include #include #include +#include #include #include #include @@ -1688,12 +1689,7 @@ static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp) tp->retransmit_skb_hint = NULL; } -union tcp_md5_addr { - struct in_addr a4; -#if IS_ENABLED(CONFIG_IPV6) - struct in6_addr a6; -#endif -}; +#define tcp_md5_addr tcp_ao_addr /* - key database */ struct tcp_md5sig_key { diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h new file mode 100644 index 000000000000..af76e1c47bea --- /dev/null +++ b/include/net/tcp_ao.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _TCP_AO_H +#define _TCP_AO_H + +#define TCP_AO_KEY_ALIGN 1 +#define __tcp_ao_key_align __aligned(TCP_AO_KEY_ALIGN) + +union tcp_ao_addr { + struct in_addr a4; +#if IS_ENABLED(CONFIG_IPV6) + struct in6_addr a6; +#endif +}; + +struct tcp_ao_hdr { + u8 kind; + u8 length; + u8 keyid; + u8 rnext_keyid; +}; + +struct tcp_ao_key { + struct hlist_node node; + union tcp_ao_addr addr; + u8 key[TCP_AO_MAXKEYLEN] __tcp_ao_key_align; + unsigned int tcp_sigpool_id; + unsigned int digest_size; + u8 prefixlen; + u8 family; + u8 keylen; + u8 keyflags; + u8 sndid; + u8 rcvid; + u8 maclen; + struct rcu_head rcu; + u8 traffic_keys[]; +}; + +static inline u8 *rcv_other_key(struct tcp_ao_key *key) +{ + return key->traffic_keys; +} + +static inline u8 *snd_other_key(struct tcp_ao_key *key) +{ + return key->traffic_keys + key->digest_size; +} + +static inline int tcp_ao_maclen(const struct tcp_ao_key *key) +{ + return key->maclen; +} + +static inline int tcp_ao_len(const struct tcp_ao_key *key) +{ + return tcp_ao_maclen(key) + sizeof(struct tcp_ao_hdr); +} + +static inline unsigned int tcp_ao_digest_size(struct tcp_ao_key *key) +{ + return key->digest_size; +} + +static inline int tcp_ao_sizeof_key(const struct tcp_ao_key *key) +{ + return sizeof(struct tcp_ao_key) + (key->digest_size << 1); +} + +struct tcp_ao_info { + /* List of tcp_ao_key's */ + struct hlist_head head; + /* current_key and rnext_key aren't maintained on listen sockets. + * Their purpose is to cache keys on established connections, + * saving needless lookups. Never dereference any of them from + * listen sockets. + * ::current_key may change in RX to the key that was requested by + * the peer, please use READ_ONCE()/WRITE_ONCE() in order to avoid + * load/store tearing. + * Do the same for ::rnext_key, if you don't hold socket lock + * (it's changed only by userspace request in setsockopt()). + */ + struct tcp_ao_key *current_key; + struct tcp_ao_key *rnext_key; + u32 flags; + __be32 lisn; + __be32 risn; + struct rcu_head rcu; +}; + +#endif /* _TCP_AO_H */ diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 8aa3916e14f6..74a1267baac5 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -361,6 +361,8 @@ struct tcp_diag_md5sig { __u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; }; +#define TCP_AO_MAXKEYLEN 80 + /* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */ #define TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT 0x1 diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 89e2ab023272..8e94ed7c56a0 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -744,6 +744,19 @@ config DEFAULT_TCP_CONG config TCP_SIGPOOL tristate +config TCP_AO + bool "TCP: Authentication Option (RFC5925)" + select CRYPTO + select TCP_SIGPOOL + depends on 64BIT && IPV6 != m # seq-number extension needs WRITE_ONCE(u64) + help + TCP-AO specifies the use of stronger Message Authentication Codes (MACs), + protects against replays for long-lived TCP connections, and + provides more details on the association of security with TCP + connections than TCP MD5 (See RFC5925) + + If unsure, say N. + config TCP_MD5SIG bool "TCP: MD5 Signature Option support (RFC2385)" select CRYPTO -- cgit From 4954f17ddefc51d218625dcdfaf422a253dad3fa Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 23 Oct 2023 20:21:55 +0100 Subject: net/tcp: Introduce TCP_AO setsockopt()s Add 3 setsockopt()s: 1. TCP_AO_ADD_KEY to add a new Master Key Tuple (MKT) on a socket 2. TCP_AO_DEL_KEY to delete present MKT from a socket 3. TCP_AO_INFO to change flags, Current_key/RNext_key on a TCP-AO sk Userspace has to introduce keys on every socket it wants to use TCP-AO option on, similarly to TCP_MD5SIG/TCP_MD5SIG_EXT. RFC5925 prohibits definition of MKTs that would match the same peer, so do sanity checks on the data provided by userspace. Be as conservative as possible, including refusal of defining MKT on an established connection with no AO, removing the key in-use and etc. (1) and (2) are to be used by userspace key manager to add/remove keys. (3) main purpose is to set RNext_key, which (as prescribed by RFC5925) is the KeyID that will be requested in TCP-AO header from the peer to sign their segments with. At this moment the life of ao_info ends in tcp_v4_destroy_sock(). Co-developed-by: Francesco Ruggeri Signed-off-by: Francesco Ruggeri Co-developed-by: Salam Noureddine Signed-off-by: Salam Noureddine Signed-off-by: Dmitry Safonov Acked-by: David Ahern Signed-off-by: David S. Miller --- include/linux/sockptr.h | 23 ++ include/net/tcp.h | 3 + include/net/tcp_ao.h | 17 +- include/uapi/linux/tcp.h | 46 +++ net/ipv4/Makefile | 1 + net/ipv4/tcp.c | 17 + net/ipv4/tcp_ao.c | 794 +++++++++++++++++++++++++++++++++++++++++++++++ net/ipv4/tcp_ipv4.c | 10 +- net/ipv6/Makefile | 1 + net/ipv6/tcp_ao.c | 19 ++ net/ipv6/tcp_ipv6.c | 39 ++- 11 files changed, 952 insertions(+), 18 deletions(-) create mode 100644 net/ipv4/tcp_ao.c create mode 100644 net/ipv6/tcp_ao.c (limited to 'include/uapi/linux') diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index bae5e2369b4f..307961b41541 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -55,6 +55,29 @@ static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) return copy_from_sockptr_offset(dst, src, 0, size); } +static inline int copy_struct_from_sockptr(void *dst, size_t ksize, + sockptr_t src, size_t usize) +{ + size_t size = min(ksize, usize); + size_t rest = max(ksize, usize) - size; + + if (!sockptr_is_kernel(src)) + return copy_struct_from_user(dst, ksize, src.user, size); + + if (usize < ksize) { + memset(dst + size, 0, rest); + } else if (usize > ksize) { + char *p = src.kernel; + + while (rest--) { + if (*p++) + return -E2BIG; + } + } + memcpy(dst, src.kernel, size); + return 0; +} + static inline int copy_to_sockptr_offset(sockptr_t dst, size_t offset, const void *src, size_t size) { diff --git a/include/net/tcp.h b/include/net/tcp.h index 3153712faa3d..ff204471d451 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2175,6 +2175,9 @@ struct tcp_sock_af_ops { sockptr_t optval, int optlen); #endif +#ifdef CONFIG_TCP_AO + int (*ao_parse)(struct sock *sk, int optname, sockptr_t optval, int optlen); +#endif }; struct tcp_request_sock_ops { diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h index af76e1c47bea..a81e40fd255a 100644 --- a/include/net/tcp_ao.h +++ b/include/net/tcp_ao.h @@ -81,10 +81,25 @@ struct tcp_ao_info { */ struct tcp_ao_key *current_key; struct tcp_ao_key *rnext_key; - u32 flags; + u32 ao_required :1, + __unused :31; __be32 lisn; __be32 risn; struct rcu_head rcu; }; +#ifdef CONFIG_TCP_AO +int tcp_parse_ao(struct sock *sk, int cmd, unsigned short int family, + sockptr_t optval, int optlen); +void tcp_ao_destroy_sock(struct sock *sk); +/* ipv4 specific functions */ +int tcp_v4_parse_ao(struct sock *sk, int cmd, sockptr_t optval, int optlen); +/* ipv6 specific functions */ +int tcp_v6_parse_ao(struct sock *sk, int cmd, sockptr_t optval, int optlen); +#else +static inline void tcp_ao_destroy_sock(struct sock *sk) +{ +} +#endif + #endif /* _TCP_AO_H */ diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 74a1267baac5..fa49f03e62fe 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -129,6 +129,9 @@ enum { #define TCP_TX_DELAY 37 /* delay outgoing packets by XX usec */ +#define TCP_AO_ADD_KEY 38 /* Add/Set MKT */ +#define TCP_AO_DEL_KEY 39 /* Delete MKT */ +#define TCP_AO_INFO 40 /* Modify TCP-AO per-socket options */ #define TCP_REPAIR_ON 1 #define TCP_REPAIR_OFF 0 @@ -363,6 +366,49 @@ struct tcp_diag_md5sig { #define TCP_AO_MAXKEYLEN 80 +#define TCP_AO_KEYF_IFINDEX (1 << 0) /* L3 ifindex for VRF */ + +struct tcp_ao_add { /* setsockopt(TCP_AO_ADD_KEY) */ + struct __kernel_sockaddr_storage addr; /* peer's address for the key */ + char alg_name[64]; /* crypto hash algorithm to use */ + __s32 ifindex; /* L3 dev index for VRF */ + __u32 set_current :1, /* set key as Current_key at once */ + set_rnext :1, /* request it from peer with RNext_key */ + reserved :30; /* must be 0 */ + __u16 reserved2; /* padding, must be 0 */ + __u8 prefix; /* peer's address prefix */ + __u8 sndid; /* SendID for outgoing segments */ + __u8 rcvid; /* RecvID to match for incoming seg */ + __u8 maclen; /* length of authentication code (hash) */ + __u8 keyflags; /* see TCP_AO_KEYF_ */ + __u8 keylen; /* length of ::key */ + __u8 key[TCP_AO_MAXKEYLEN]; +} __attribute__((aligned(8))); + +struct tcp_ao_del { /* setsockopt(TCP_AO_DEL_KEY) */ + struct __kernel_sockaddr_storage addr; /* peer's address for the key */ + __s32 ifindex; /* L3 dev index for VRF */ + __u32 set_current :1, /* corresponding ::current_key */ + set_rnext :1, /* corresponding ::rnext */ + reserved :30; /* must be 0 */ + __u16 reserved2; /* padding, must be 0 */ + __u8 prefix; /* peer's address prefix */ + __u8 sndid; /* SendID for outgoing segments */ + __u8 rcvid; /* RecvID to match for incoming seg */ + __u8 current_key; /* KeyID to set as Current_key */ + __u8 rnext; /* KeyID to set as Rnext_key */ + __u8 keyflags; /* see TCP_AO_KEYF_ */ +} __attribute__((aligned(8))); + +struct tcp_ao_info_opt { /* setsockopt(TCP_AO_INFO) */ + __u32 set_current :1, /* corresponding ::current_key */ + set_rnext :1, /* corresponding ::rnext */ + ao_required :1, /* don't accept non-AO connects */ + reserved :29; /* must be 0 */ + __u8 current_key; /* KeyID to set as Current_key */ + __u8 rnext; /* KeyID to set as Rnext_key */ +} __attribute__((aligned(8))); + /* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */ #define TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT 0x1 diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index cd760793cfcb..e144a02a6a61 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -69,6 +69,7 @@ obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ xfrm4_output.o xfrm4_protocol.o +obj-$(CONFIG_TCP_AO) += tcp_ao.o ifeq ($(CONFIG_BPF_JIT),y) obj-$(CONFIG_BPF_SYSCALL) += bpf_tcp_ca.o diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index dca9ca2f1081..b6faee8a1e67 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3593,6 +3593,23 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, __tcp_sock_set_quickack(sk, val); break; +#ifdef CONFIG_TCP_AO + case TCP_AO_ADD_KEY: + case TCP_AO_DEL_KEY: + case TCP_AO_INFO: { + /* If this is the first TCP-AO setsockopt() on the socket, + * sk_state has to be LISTEN or CLOSE + */ + if (((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) || + rcu_dereference_protected(tcp_sk(sk)->ao_info, + lockdep_sock_is_held(sk))) + err = tp->af_specific->ao_parse(sk, optname, optval, + optlen); + else + err = -EISCONN; + break; + } +#endif #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: case TCP_MD5SIG_EXT: diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c new file mode 100644 index 000000000000..3c2d005a37ce --- /dev/null +++ b/net/ipv4/tcp_ao.c @@ -0,0 +1,794 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * INET An implementation of the TCP Authentication Option (TCP-AO). + * See RFC5925. + * + * Authors: Dmitry Safonov + * Francesco Ruggeri + * Salam Noureddine + */ +#define pr_fmt(fmt) "TCP: " fmt + +#include +#include +#include + +#include +#include + +/* Optimized version of tcp_ao_do_lookup(): only for sockets for which + * it's known that the keys in ao_info are matching peer's + * family/address/VRF/etc. + */ +static struct tcp_ao_key *tcp_ao_established_key(struct tcp_ao_info *ao, + int sndid, int rcvid) +{ + struct tcp_ao_key *key; + + hlist_for_each_entry_rcu(key, &ao->head, node) { + if ((sndid >= 0 && key->sndid != sndid) || + (rcvid >= 0 && key->rcvid != rcvid)) + continue; + return key; + } + + return NULL; +} + +static int ipv4_prefix_cmp(const struct in_addr *addr1, + const struct in_addr *addr2, + unsigned int prefixlen) +{ + __be32 mask = inet_make_mask(prefixlen); + __be32 a1 = addr1->s_addr & mask; + __be32 a2 = addr2->s_addr & mask; + + if (a1 == a2) + return 0; + return memcmp(&a1, &a2, sizeof(a1)); +} + +static int __tcp_ao_key_cmp(const struct tcp_ao_key *key, + const union tcp_ao_addr *addr, u8 prefixlen, + int family, int sndid, int rcvid) +{ + if (sndid >= 0 && key->sndid != sndid) + return (key->sndid > sndid) ? 1 : -1; + if (rcvid >= 0 && key->rcvid != rcvid) + return (key->rcvid > rcvid) ? 1 : -1; + + if (family == AF_UNSPEC) + return 0; + if (key->family != family) + return (key->family > family) ? 1 : -1; + + if (family == AF_INET) { + if (ntohl(key->addr.a4.s_addr) == INADDR_ANY) + return 0; + if (ntohl(addr->a4.s_addr) == INADDR_ANY) + return 0; + return ipv4_prefix_cmp(&key->addr.a4, &addr->a4, prefixlen); +#if IS_ENABLED(CONFIG_IPV6) + } else { + if (ipv6_addr_any(&key->addr.a6) || ipv6_addr_any(&addr->a6)) + return 0; + if (ipv6_prefix_equal(&key->addr.a6, &addr->a6, prefixlen)) + return 0; + return memcmp(&key->addr.a6, &addr->a6, sizeof(addr->a6)); +#endif + } + return -1; +} + +static int tcp_ao_key_cmp(const struct tcp_ao_key *key, + const union tcp_ao_addr *addr, u8 prefixlen, + int family, int sndid, int rcvid) +{ +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6 && ipv6_addr_v4mapped(&addr->a6)) { + __be32 addr4 = addr->a6.s6_addr32[3]; + + return __tcp_ao_key_cmp(key, (union tcp_ao_addr *)&addr4, + prefixlen, AF_INET, sndid, rcvid); + } +#endif + return __tcp_ao_key_cmp(key, addr, prefixlen, family, sndid, rcvid); +} + +static struct tcp_ao_key *__tcp_ao_do_lookup(const struct sock *sk, + const union tcp_ao_addr *addr, int family, u8 prefix, + int sndid, int rcvid) +{ + struct tcp_ao_key *key; + struct tcp_ao_info *ao; + + ao = rcu_dereference_check(tcp_sk(sk)->ao_info, + lockdep_sock_is_held(sk)); + if (!ao) + return NULL; + + hlist_for_each_entry_rcu(key, &ao->head, node) { + u8 prefixlen = min(prefix, key->prefixlen); + + if (!tcp_ao_key_cmp(key, addr, prefixlen, family, sndid, rcvid)) + return key; + } + return NULL; +} + +static struct tcp_ao_info *tcp_ao_alloc_info(gfp_t flags) +{ + struct tcp_ao_info *ao; + + ao = kzalloc(sizeof(*ao), flags); + if (!ao) + return NULL; + INIT_HLIST_HEAD(&ao->head); + + return ao; +} + +static void tcp_ao_link_mkt(struct tcp_ao_info *ao, struct tcp_ao_key *mkt) +{ + hlist_add_head_rcu(&mkt->node, &ao->head); +} + +static void tcp_ao_key_free_rcu(struct rcu_head *head) +{ + struct tcp_ao_key *key = container_of(head, struct tcp_ao_key, rcu); + + tcp_sigpool_release(key->tcp_sigpool_id); + kfree_sensitive(key); +} + +void tcp_ao_destroy_sock(struct sock *sk) +{ + struct tcp_ao_info *ao; + struct tcp_ao_key *key; + struct hlist_node *n; + + ao = rcu_dereference_protected(tcp_sk(sk)->ao_info, 1); + tcp_sk(sk)->ao_info = NULL; + + if (!ao) + return; + + hlist_for_each_entry_safe(key, n, &ao->head, node) { + hlist_del_rcu(&key->node); + atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc); + call_rcu(&key->rcu, tcp_ao_key_free_rcu); + } + + kfree_rcu(ao, rcu); +} + +static bool tcp_ao_can_set_current_rnext(struct sock *sk) +{ + /* There aren't current/rnext keys on TCP_LISTEN sockets */ + if (sk->sk_state == TCP_LISTEN) + return false; + return true; +} + +static int tcp_ao_verify_ipv4(struct sock *sk, struct tcp_ao_add *cmd, + union tcp_ao_addr **addr) +{ + struct sockaddr_in *sin = (struct sockaddr_in *)&cmd->addr; + struct inet_sock *inet = inet_sk(sk); + + if (sin->sin_family != AF_INET) + return -EINVAL; + + /* Currently matching is not performed on port (or port ranges) */ + if (sin->sin_port != 0) + return -EINVAL; + + /* Check prefix and trailing 0's in addr */ + if (cmd->prefix != 0) { + __be32 mask; + + if (ntohl(sin->sin_addr.s_addr) == INADDR_ANY) + return -EINVAL; + if (cmd->prefix > 32) + return -EINVAL; + + mask = inet_make_mask(cmd->prefix); + if (sin->sin_addr.s_addr & ~mask) + return -EINVAL; + + /* Check that MKT address is consistent with socket */ + if (ntohl(inet->inet_daddr) != INADDR_ANY && + (inet->inet_daddr & mask) != sin->sin_addr.s_addr) + return -EINVAL; + } else { + if (ntohl(sin->sin_addr.s_addr) != INADDR_ANY) + return -EINVAL; + } + + *addr = (union tcp_ao_addr *)&sin->sin_addr; + return 0; +} + +static int tcp_ao_parse_crypto(struct tcp_ao_add *cmd, struct tcp_ao_key *key) +{ + unsigned int syn_tcp_option_space; + bool is_kdf_aes_128_cmac = false; + struct crypto_ahash *tfm; + struct tcp_sigpool hp; + void *tmp_key = NULL; + int err; + + /* RFC5926, 3.1.1.2. KDF_AES_128_CMAC */ + if (!strcmp("cmac(aes128)", cmd->alg_name)) { + strscpy(cmd->alg_name, "cmac(aes)", sizeof(cmd->alg_name)); + is_kdf_aes_128_cmac = (cmd->keylen != 16); + tmp_key = kmalloc(cmd->keylen, GFP_KERNEL); + if (!tmp_key) + return -ENOMEM; + } + + key->maclen = cmd->maclen ?: 12; /* 12 is the default in RFC5925 */ + + /* Check: maclen + tcp-ao header <= (MAX_TCP_OPTION_SPACE - mss + * - tstamp - wscale - sackperm), + * see tcp_syn_options(), tcp_synack_options(), commit 33ad798c924b. + * + * In order to allow D-SACK with TCP-AO, the header size should be: + * (MAX_TCP_OPTION_SPACE - TCPOLEN_TSTAMP_ALIGNED + * - TCPOLEN_SACK_BASE_ALIGNED + * - 2 * TCPOLEN_SACK_PERBLOCK) = 8 (maclen = 4), + * see tcp_established_options(). + * + * RFC5925, 2.2: + * Typical MACs are 96-128 bits (12-16 bytes), but any length + * that fits in the header of the segment being authenticated + * is allowed. + * + * RFC5925, 7.6: + * TCP-AO continues to consume 16 bytes in non-SYN segments, + * leaving a total of 24 bytes for other options, of which + * the timestamp consumes 10. This leaves 14 bytes, of which 10 + * are used for a single SACK block. When two SACK blocks are used, + * such as to handle D-SACK, a smaller TCP-AO MAC would be required + * to make room for the additional SACK block (i.e., to leave 18 + * bytes for the D-SACK variant of the SACK option) [RFC2883]. + * Note that D-SACK is not supportable in TCP MD5 in the presence + * of timestamps, because TCP MD5’s MAC length is fixed and too + * large to leave sufficient option space. + */ + syn_tcp_option_space = MAX_TCP_OPTION_SPACE; + syn_tcp_option_space -= TCPOLEN_TSTAMP_ALIGNED; + syn_tcp_option_space -= TCPOLEN_WSCALE_ALIGNED; + syn_tcp_option_space -= TCPOLEN_SACKPERM_ALIGNED; + if (tcp_ao_len(key) > syn_tcp_option_space) { + err = -EMSGSIZE; + goto err_kfree; + } + + key->keylen = cmd->keylen; + memcpy(key->key, cmd->key, cmd->keylen); + + err = tcp_sigpool_start(key->tcp_sigpool_id, &hp); + if (err) + goto err_kfree; + + tfm = crypto_ahash_reqtfm(hp.req); + if (is_kdf_aes_128_cmac) { + void *scratch = hp.scratch; + struct scatterlist sg; + + memcpy(tmp_key, cmd->key, cmd->keylen); + sg_init_one(&sg, tmp_key, cmd->keylen); + + /* Using zero-key of 16 bytes as described in RFC5926 */ + memset(scratch, 0, 16); + err = crypto_ahash_setkey(tfm, scratch, 16); + if (err) + goto err_pool_end; + + err = crypto_ahash_init(hp.req); + if (err) + goto err_pool_end; + + ahash_request_set_crypt(hp.req, &sg, key->key, cmd->keylen); + err = crypto_ahash_update(hp.req); + if (err) + goto err_pool_end; + + err |= crypto_ahash_final(hp.req); + if (err) + goto err_pool_end; + key->keylen = 16; + } + + err = crypto_ahash_setkey(tfm, key->key, key->keylen); + if (err) + goto err_pool_end; + + tcp_sigpool_end(&hp); + kfree_sensitive(tmp_key); + + if (tcp_ao_maclen(key) > key->digest_size) + return -EINVAL; + + return 0; + +err_pool_end: + tcp_sigpool_end(&hp); +err_kfree: + kfree_sensitive(tmp_key); + return err; +} + +#if IS_ENABLED(CONFIG_IPV6) +static int tcp_ao_verify_ipv6(struct sock *sk, struct tcp_ao_add *cmd, + union tcp_ao_addr **paddr, + unsigned short int *family) +{ + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd->addr; + struct in6_addr *addr = &sin6->sin6_addr; + u8 prefix = cmd->prefix; + + if (sin6->sin6_family != AF_INET6) + return -EINVAL; + + /* Currently matching is not performed on port (or port ranges) */ + if (sin6->sin6_port != 0) + return -EINVAL; + + /* Check prefix and trailing 0's in addr */ + if (cmd->prefix != 0 && ipv6_addr_v4mapped(addr)) { + __be32 addr4 = addr->s6_addr32[3]; + __be32 mask; + + if (prefix > 32 || ntohl(addr4) == INADDR_ANY) + return -EINVAL; + + mask = inet_make_mask(prefix); + if (addr4 & ~mask) + return -EINVAL; + + /* Check that MKT address is consistent with socket */ + if (!ipv6_addr_any(&sk->sk_v6_daddr)) { + __be32 daddr4 = sk->sk_v6_daddr.s6_addr32[3]; + + if (!ipv6_addr_v4mapped(&sk->sk_v6_daddr)) + return -EINVAL; + if ((daddr4 & mask) != addr4) + return -EINVAL; + } + + *paddr = (union tcp_ao_addr *)&addr->s6_addr32[3]; + *family = AF_INET; + return 0; + } else if (cmd->prefix != 0) { + struct in6_addr pfx; + + if (ipv6_addr_any(addr) || prefix > 128) + return -EINVAL; + + ipv6_addr_prefix(&pfx, addr, prefix); + if (ipv6_addr_cmp(&pfx, addr)) + return -EINVAL; + + /* Check that MKT address is consistent with socket */ + if (!ipv6_addr_any(&sk->sk_v6_daddr) && + !ipv6_prefix_equal(&sk->sk_v6_daddr, addr, prefix)) + + return -EINVAL; + } else { + if (!ipv6_addr_any(addr)) + return -EINVAL; + } + + *paddr = (union tcp_ao_addr *)addr; + return 0; +} +#else +static int tcp_ao_verify_ipv6(struct sock *sk, struct tcp_ao_add *cmd, + union tcp_ao_addr **paddr, + unsigned short int *family) +{ + return -EOPNOTSUPP; +} +#endif + +static struct tcp_ao_info *setsockopt_ao_info(struct sock *sk) +{ + if (sk_fullsock(sk)) { + return rcu_dereference_protected(tcp_sk(sk)->ao_info, + lockdep_sock_is_held(sk)); + } + return ERR_PTR(-ESOCKTNOSUPPORT); +} + +#define TCP_AO_KEYF_ALL (0) + +static struct tcp_ao_key *tcp_ao_key_alloc(struct sock *sk, + struct tcp_ao_add *cmd) +{ + const char *algo = cmd->alg_name; + unsigned int digest_size; + struct crypto_ahash *tfm; + struct tcp_ao_key *key; + struct tcp_sigpool hp; + int err, pool_id; + size_t size; + + /* Force null-termination of alg_name */ + cmd->alg_name[ARRAY_SIZE(cmd->alg_name) - 1] = '\0'; + + /* RFC5926, 3.1.1.2. KDF_AES_128_CMAC */ + if (!strcmp("cmac(aes128)", algo)) + algo = "cmac(aes)"; + + /* Full TCP header (th->doff << 2) should fit into scratch area, + * see tcp_ao_hash_header(). + */ + pool_id = tcp_sigpool_alloc_ahash(algo, 60); + if (pool_id < 0) + return ERR_PTR(pool_id); + + err = tcp_sigpool_start(pool_id, &hp); + if (err) + goto err_free_pool; + + tfm = crypto_ahash_reqtfm(hp.req); + if (crypto_ahash_alignmask(tfm) > TCP_AO_KEY_ALIGN) { + err = -EOPNOTSUPP; + goto err_pool_end; + } + digest_size = crypto_ahash_digestsize(tfm); + tcp_sigpool_end(&hp); + + size = sizeof(struct tcp_ao_key) + (digest_size << 1); + key = sock_kmalloc(sk, size, GFP_KERNEL); + if (!key) { + err = -ENOMEM; + goto err_free_pool; + } + + key->tcp_sigpool_id = pool_id; + key->digest_size = digest_size; + return key; + +err_pool_end: + tcp_sigpool_end(&hp); +err_free_pool: + tcp_sigpool_release(pool_id); + return ERR_PTR(err); +} + +static int tcp_ao_add_cmd(struct sock *sk, unsigned short int family, + sockptr_t optval, int optlen) +{ + struct tcp_ao_info *ao_info; + union tcp_ao_addr *addr; + struct tcp_ao_key *key; + struct tcp_ao_add cmd; + bool first = false; + int ret; + + if (optlen < sizeof(cmd)) + return -EINVAL; + + ret = copy_struct_from_sockptr(&cmd, sizeof(cmd), optval, optlen); + if (ret) + return ret; + + if (cmd.keylen > TCP_AO_MAXKEYLEN) + return -EINVAL; + + if (cmd.reserved != 0 || cmd.reserved2 != 0) + return -EINVAL; + + if (family == AF_INET) + ret = tcp_ao_verify_ipv4(sk, &cmd, &addr); + else + ret = tcp_ao_verify_ipv6(sk, &cmd, &addr, &family); + if (ret) + return ret; + + if (cmd.keyflags & ~TCP_AO_KEYF_ALL) + return -EINVAL; + + if (cmd.set_current || cmd.set_rnext) { + if (!tcp_ao_can_set_current_rnext(sk)) + return -EINVAL; + } + + ao_info = setsockopt_ao_info(sk); + if (IS_ERR(ao_info)) + return PTR_ERR(ao_info); + + if (!ao_info) { + ao_info = tcp_ao_alloc_info(GFP_KERNEL); + if (!ao_info) + return -ENOMEM; + first = true; + } else { + /* Check that neither RecvID nor SendID match any + * existing key for the peer, RFC5925 3.1: + * > The IDs of MKTs MUST NOT overlap where their + * > TCP connection identifiers overlap. + */ + if (__tcp_ao_do_lookup(sk, addr, family, + cmd.prefix, -1, cmd.rcvid)) + return -EEXIST; + if (__tcp_ao_do_lookup(sk, addr, family, + cmd.prefix, cmd.sndid, -1)) + return -EEXIST; + } + + key = tcp_ao_key_alloc(sk, &cmd); + if (IS_ERR(key)) { + ret = PTR_ERR(key); + goto err_free_ao; + } + + INIT_HLIST_NODE(&key->node); + memcpy(&key->addr, addr, (family == AF_INET) ? sizeof(struct in_addr) : + sizeof(struct in6_addr)); + key->prefixlen = cmd.prefix; + key->family = family; + key->keyflags = cmd.keyflags; + key->sndid = cmd.sndid; + key->rcvid = cmd.rcvid; + + ret = tcp_ao_parse_crypto(&cmd, key); + if (ret < 0) + goto err_free_sock; + + tcp_ao_link_mkt(ao_info, key); + if (first) { + sk_gso_disable(sk); + rcu_assign_pointer(tcp_sk(sk)->ao_info, ao_info); + } + + if (cmd.set_current) + WRITE_ONCE(ao_info->current_key, key); + if (cmd.set_rnext) + WRITE_ONCE(ao_info->rnext_key, key); + return 0; + +err_free_sock: + atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc); + tcp_sigpool_release(key->tcp_sigpool_id); + kfree_sensitive(key); +err_free_ao: + if (first) + kfree(ao_info); + return ret; +} + +static int tcp_ao_delete_key(struct sock *sk, struct tcp_ao_info *ao_info, + struct tcp_ao_key *key, + struct tcp_ao_key *new_current, + struct tcp_ao_key *new_rnext) +{ + int err; + + hlist_del_rcu(&key->node); + + /* At this moment another CPU could have looked this key up + * while it was unlinked from the list. Wait for RCU grace period, + * after which the key is off-list and can't be looked up again; + * the rx path [just before RCU came] might have used it and set it + * as current_key (very unlikely). + */ + synchronize_rcu(); + if (new_current) + WRITE_ONCE(ao_info->current_key, new_current); + if (new_rnext) + WRITE_ONCE(ao_info->rnext_key, new_rnext); + + if (unlikely(READ_ONCE(ao_info->current_key) == key || + READ_ONCE(ao_info->rnext_key) == key)) { + err = -EBUSY; + goto add_key; + } + + atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc); + call_rcu(&key->rcu, tcp_ao_key_free_rcu); + + return 0; +add_key: + hlist_add_head_rcu(&key->node, &ao_info->head); + return err; +} + +static int tcp_ao_del_cmd(struct sock *sk, unsigned short int family, + sockptr_t optval, int optlen) +{ + struct tcp_ao_key *key, *new_current = NULL, *new_rnext = NULL; + struct tcp_ao_info *ao_info; + union tcp_ao_addr *addr; + struct tcp_ao_del cmd; + int addr_len; + __u8 prefix; + u16 port; + int err; + + if (optlen < sizeof(cmd)) + return -EINVAL; + + err = copy_struct_from_sockptr(&cmd, sizeof(cmd), optval, optlen); + if (err) + return err; + + if (cmd.reserved != 0 || cmd.reserved2 != 0) + return -EINVAL; + + if (cmd.set_current || cmd.set_rnext) { + if (!tcp_ao_can_set_current_rnext(sk)) + return -EINVAL; + } + + ao_info = setsockopt_ao_info(sk); + if (IS_ERR(ao_info)) + return PTR_ERR(ao_info); + if (!ao_info) + return -ENOENT; + + /* For sockets in TCP_CLOSED it's possible set keys that aren't + * matching the future peer (address/VRF/etc), + * tcp_ao_connect_init() will choose a correct matching MKT + * if there's any. + */ + if (cmd.set_current) { + new_current = tcp_ao_established_key(ao_info, cmd.current_key, -1); + if (!new_current) + return -ENOENT; + } + if (cmd.set_rnext) { + new_rnext = tcp_ao_established_key(ao_info, -1, cmd.rnext); + if (!new_rnext) + return -ENOENT; + } + + if (family == AF_INET) { + struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.addr; + + addr = (union tcp_ao_addr *)&sin->sin_addr; + addr_len = sizeof(struct in_addr); + port = ntohs(sin->sin_port); + } else { + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.addr; + struct in6_addr *addr6 = &sin6->sin6_addr; + + if (ipv6_addr_v4mapped(addr6)) { + addr = (union tcp_ao_addr *)&addr6->s6_addr32[3]; + addr_len = sizeof(struct in_addr); + family = AF_INET; + } else { + addr = (union tcp_ao_addr *)addr6; + addr_len = sizeof(struct in6_addr); + } + port = ntohs(sin6->sin6_port); + } + prefix = cmd.prefix; + + /* Currently matching is not performed on port (or port ranges) */ + if (port != 0) + return -EINVAL; + + /* We could choose random present key here for current/rnext + * but that's less predictable. Let's be strict and don't + * allow removing a key that's in use. RFC5925 doesn't + * specify how-to coordinate key removal, but says: + * "It is presumed that an MKT affecting a particular + * connection cannot be destroyed during an active connection" + */ + hlist_for_each_entry_rcu(key, &ao_info->head, node) { + if (cmd.sndid != key->sndid || + cmd.rcvid != key->rcvid) + continue; + + if (family != key->family || + prefix != key->prefixlen || + memcmp(addr, &key->addr, addr_len)) + continue; + + if (key == new_current || key == new_rnext) + continue; + + return tcp_ao_delete_key(sk, ao_info, key, + new_current, new_rnext); + } + return -ENOENT; +} + +static int tcp_ao_info_cmd(struct sock *sk, unsigned short int family, + sockptr_t optval, int optlen) +{ + struct tcp_ao_key *new_current = NULL, *new_rnext = NULL; + struct tcp_ao_info *ao_info; + struct tcp_ao_info_opt cmd; + bool first = false; + int err; + + if (optlen < sizeof(cmd)) + return -EINVAL; + + err = copy_struct_from_sockptr(&cmd, sizeof(cmd), optval, optlen); + if (err) + return err; + + if (cmd.set_current || cmd.set_rnext) { + if (!tcp_ao_can_set_current_rnext(sk)) + return -EINVAL; + } + + if (cmd.reserved != 0) + return -EINVAL; + + ao_info = setsockopt_ao_info(sk); + if (IS_ERR(ao_info)) + return PTR_ERR(ao_info); + if (!ao_info) { + ao_info = tcp_ao_alloc_info(GFP_KERNEL); + if (!ao_info) + return -ENOMEM; + first = true; + } + + /* For sockets in TCP_CLOSED it's possible set keys that aren't + * matching the future peer (address/port/VRF/etc), + * tcp_ao_connect_init() will choose a correct matching MKT + * if there's any. + */ + if (cmd.set_current) { + new_current = tcp_ao_established_key(ao_info, cmd.current_key, -1); + if (!new_current) { + err = -ENOENT; + goto out; + } + } + if (cmd.set_rnext) { + new_rnext = tcp_ao_established_key(ao_info, -1, cmd.rnext); + if (!new_rnext) { + err = -ENOENT; + goto out; + } + } + + ao_info->ao_required = cmd.ao_required; + if (new_current) + WRITE_ONCE(ao_info->current_key, new_current); + if (new_rnext) + WRITE_ONCE(ao_info->rnext_key, new_rnext); + if (first) { + sk_gso_disable(sk); + rcu_assign_pointer(tcp_sk(sk)->ao_info, ao_info); + } + return 0; +out: + if (first) + kfree(ao_info); + return err; +} + +int tcp_parse_ao(struct sock *sk, int cmd, unsigned short int family, + sockptr_t optval, int optlen) +{ + if (WARN_ON_ONCE(family != AF_INET && family != AF_INET6)) + return -EAFNOSUPPORT; + + switch (cmd) { + case TCP_AO_ADD_KEY: + return tcp_ao_add_cmd(sk, family, optval, optlen); + case TCP_AO_DEL_KEY: + return tcp_ao_del_cmd(sk, family, optval, optlen); + case TCP_AO_INFO: + return tcp_ao_info_cmd(sk, family, optval, optlen); + default: + WARN_ON_ONCE(1); + return -EINVAL; + } +} + +int tcp_v4_parse_ao(struct sock *sk, int cmd, sockptr_t optval, int optlen) +{ + return tcp_parse_ao(sk, cmd, AF_INET, optval, optlen); +} + diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7d81e90b6f5c..a4746c27f38a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2271,11 +2271,16 @@ const struct inet_connection_sock_af_ops ipv4_specific = { }; EXPORT_SYMBOL(ipv4_specific); -#ifdef CONFIG_TCP_MD5SIG +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = { +#ifdef CONFIG_TCP_MD5SIG .md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, .md5_parse = tcp_v4_parse_md5_keys, +#endif +#ifdef CONFIG_TCP_AO + .ao_parse = tcp_v4_parse_ao, +#endif }; #endif @@ -2290,7 +2295,7 @@ static int tcp_v4_init_sock(struct sock *sk) icsk->icsk_af_ops = &ipv4_specific; -#ifdef CONFIG_TCP_MD5SIG +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tcp_sk(sk)->af_specific = &tcp_sock_ipv4_specific; #endif @@ -2341,6 +2346,7 @@ void tcp_v4_destroy_sock(struct sock *sk) rcu_assign_pointer(tp->md5sig_info, NULL); } #endif + tcp_ao_destroy_sock(sk); /* Clean up a referenced TCP bind bucket. */ if (inet_csk(sk)->icsk_bind_hash) diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 3036a45e8a1e..d283c59df4c1 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -52,4 +52,5 @@ obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o ifneq ($(CONFIG_IPV6),) obj-$(CONFIG_NET_UDP_TUNNEL) += ip6_udp_tunnel.o obj-y += mcast_snoop.o +obj-$(CONFIG_TCP_AO) += tcp_ao.o endif diff --git a/net/ipv6/tcp_ao.c b/net/ipv6/tcp_ao.c new file mode 100644 index 000000000000..049ddbabe049 --- /dev/null +++ b/net/ipv6/tcp_ao.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * INET An implementation of the TCP Authentication Option (TCP-AO). + * See RFC5925. + * + * Authors: Dmitry Safonov + * Francesco Ruggeri + * Salam Noureddine + */ +#include + +#include +#include + +int tcp_v6_parse_ao(struct sock *sk, int cmd, + sockptr_t optval, int optlen) +{ + return tcp_parse_ao(sk, cmd, AF_INET6, optval, optlen); +} diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index ee53dad20a59..30bd17d03239 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -76,16 +76,9 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); static const struct inet_connection_sock_af_ops ipv6_mapped; const struct inet_connection_sock_af_ops ipv6_specific; -#ifdef CONFIG_TCP_MD5SIG +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv6_specific; static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific; -#else -static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk, - const struct in6_addr *addr, - int l3index) -{ - return NULL; -} #endif /* Helper returning the inet6 address from a given tcp socket. @@ -239,7 +232,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (sk_is_mptcp(sk)) mptcpv6_handle_mapped(sk, true); sk->sk_backlog_rcv = tcp_v4_do_rcv; -#ifdef CONFIG_TCP_MD5SIG +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tp->af_specific = &tcp_sock_ipv6_mapped_specific; #endif @@ -252,7 +245,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (sk_is_mptcp(sk)) mptcpv6_handle_mapped(sk, false); sk->sk_backlog_rcv = tcp_v6_do_rcv; -#ifdef CONFIG_TCP_MD5SIG +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tp->af_specific = &tcp_sock_ipv6_specific; #endif goto failure; @@ -769,7 +762,13 @@ clear_hash_nostart: memset(md5_hash, 0, 16); return 1; } - +#else /* CONFIG_TCP_MD5SIG */ +static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk, + const struct in6_addr *addr, + int l3index) +{ + return NULL; +} #endif static void tcp_v6_init_req(struct request_sock *req, @@ -1228,7 +1227,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * if (sk_is_mptcp(newsk)) mptcpv6_handle_mapped(newsk, true); newsk->sk_backlog_rcv = tcp_v4_do_rcv; -#ifdef CONFIG_TCP_MD5SIG +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) newtp->af_specific = &tcp_sock_ipv6_mapped_specific; #endif @@ -1896,11 +1895,16 @@ const struct inet_connection_sock_af_ops ipv6_specific = { .mtu_reduced = tcp_v6_mtu_reduced, }; -#ifdef CONFIG_TCP_MD5SIG +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv6_specific = { +#ifdef CONFIG_TCP_MD5SIG .md5_lookup = tcp_v6_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, .md5_parse = tcp_v6_parse_md5_keys, +#endif +#ifdef CONFIG_TCP_AO + .ao_parse = tcp_v6_parse_ao, +#endif }; #endif @@ -1922,11 +1926,16 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = { .mtu_reduced = tcp_v4_mtu_reduced, }; -#ifdef CONFIG_TCP_MD5SIG +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = { +#ifdef CONFIG_TCP_MD5SIG .md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, .md5_parse = tcp_v6_parse_md5_keys, +#endif +#ifdef CONFIG_TCP_AO + .ao_parse = tcp_v6_parse_ao, +#endif }; #endif @@ -1941,7 +1950,7 @@ static int tcp_v6_init_sock(struct sock *sk) icsk->icsk_af_ops = &ipv6_specific; -#ifdef CONFIG_TCP_MD5SIG +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tcp_sk(sk)->af_specific = &tcp_sock_ipv6_specific; #endif -- cgit From af09a341dcf63b34ce742295ad1ce876246c5de2 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 23 Oct 2023 20:22:05 +0100 Subject: net/tcp: Add TCP-AO segments counters Introduce segment counters that are useful for troubleshooting/debugging as well as for writing tests. Now there are global snmp counters as well as per-socket and per-key. Co-developed-by: Francesco Ruggeri Signed-off-by: Francesco Ruggeri Co-developed-by: Salam Noureddine Signed-off-by: Salam Noureddine Signed-off-by: Dmitry Safonov Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/dropreason-core.h | 15 +++++++++++---- include/net/tcp.h | 15 +++++++++++---- include/net/tcp_ao.h | 10 ++++++++++ include/uapi/linux/snmp.h | 4 ++++ include/uapi/linux/tcp.h | 8 +++++++- net/ipv4/proc.c | 4 ++++ net/ipv4/tcp_ao.c | 30 +++++++++++++++++++++++++++--- net/ipv4/tcp_ipv4.c | 2 +- net/ipv6/tcp_ipv6.c | 4 ++-- 9 files changed, 77 insertions(+), 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index 7637137ae33e..3c70ad53a49c 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -168,17 +168,24 @@ enum skb_drop_reason { */ SKB_DROP_REASON_TCP_MD5FAILURE, /** - * @SKB_DROP_REASON_TCP_AONOTFOUND: no TCP-AO hash and one was expected + * @SKB_DROP_REASON_TCP_AONOTFOUND: no TCP-AO hash and one was expected, + * corresponding to LINUX_MIB_TCPAOREQUIRED */ SKB_DROP_REASON_TCP_AONOTFOUND, /** * @SKB_DROP_REASON_TCP_AOUNEXPECTED: TCP-AO hash is present and it - * was not expected. + * was not expected, corresponding to LINUX_MIB_TCPAOKEYNOTFOUND */ SKB_DROP_REASON_TCP_AOUNEXPECTED, - /** @SKB_DROP_REASON_TCP_AOKEYNOTFOUND: TCP-AO key is unknown */ + /** + * @SKB_DROP_REASON_TCP_AOKEYNOTFOUND: TCP-AO key is unknown, + * corresponding to LINUX_MIB_TCPAOKEYNOTFOUND + */ SKB_DROP_REASON_TCP_AOKEYNOTFOUND, - /** @SKB_DROP_REASON_TCP_AOFAILURE: TCP-AO hash is wrong */ + /** + * @SKB_DROP_REASON_TCP_AOFAILURE: TCP-AO hash is wrong, + * corresponding to LINUX_MIB_TCPAOBAD + */ SKB_DROP_REASON_TCP_AOFAILURE, /** * @SKB_DROP_REASON_SOCKET_BACKLOG: failed to add skb to socket backlog ( diff --git a/include/net/tcp.h b/include/net/tcp.h index 8e1f835bad22..50ae1ed244e5 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2712,7 +2712,7 @@ static inline int tcp_parse_auth_options(const struct tcphdr *th, } static inline bool tcp_ao_required(struct sock *sk, const void *saddr, - int family) + int family, bool stat_inc) { #ifdef CONFIG_TCP_AO struct tcp_ao_info *ao_info; @@ -2724,8 +2724,13 @@ static inline bool tcp_ao_required(struct sock *sk, const void *saddr, return false; ao_key = tcp_ao_do_lookup(sk, saddr, family, -1, -1); - if (ao_info->ao_required || ao_key) + if (ao_info->ao_required || ao_key) { + if (stat_inc) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOREQUIRED); + atomic64_inc(&ao_info->counters.ao_required); + } return true; + } #endif return false; } @@ -2747,8 +2752,10 @@ tcp_inbound_hash(struct sock *sk, const struct request_sock *req, return SKB_DROP_REASON_TCP_AUTH_HDR; if (req) { - if (tcp_rsk_used_ao(req) != !!aoh) + if (tcp_rsk_used_ao(req) != !!aoh) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); return SKB_DROP_REASON_TCP_AOFAILURE; + } } /* sdif set, means packet ingressed via a device @@ -2763,7 +2770,7 @@ tcp_inbound_hash(struct sock *sk, const struct request_sock *req, * the last key is impossible to remove, so there's * always at least one current_key. */ - if (tcp_ao_required(sk, saddr, family)) + if (tcp_ao_required(sk, saddr, family, true)) return SKB_DROP_REASON_TCP_AONOTFOUND; if (unlikely(tcp_md5_do_lookup(sk, l3index, saddr, family))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h index 1c7c0a5d1877..cfb55bd9411b 100644 --- a/include/net/tcp_ao.h +++ b/include/net/tcp_ao.h @@ -19,6 +19,13 @@ struct tcp_ao_hdr { u8 rnext_keyid; }; +struct tcp_ao_counters { + atomic64_t pkt_good; + atomic64_t pkt_bad; + atomic64_t key_not_found; + atomic64_t ao_required; +}; + struct tcp_ao_key { struct hlist_node node; union tcp_ao_addr addr; @@ -33,6 +40,8 @@ struct tcp_ao_key { u8 rcvid; u8 maclen; struct rcu_head rcu; + atomic64_t pkt_good; + atomic64_t pkt_bad; u8 traffic_keys[]; }; @@ -81,6 +90,7 @@ struct tcp_ao_info { */ struct tcp_ao_key *current_key; struct tcp_ao_key *rnext_key; + struct tcp_ao_counters counters; u32 ao_required :1, __unused :31; __be32 lisn; diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index b2b72886cb6d..3d5ea841bffe 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -297,6 +297,10 @@ enum LINUX_MIB_TCPMIGRATEREQSUCCESS, /* TCPMigrateReqSuccess */ LINUX_MIB_TCPMIGRATEREQFAILURE, /* TCPMigrateReqFailure */ LINUX_MIB_TCPPLBREHASH, /* TCPPLBRehash */ + LINUX_MIB_TCPAOREQUIRED, /* TCPAORequired */ + LINUX_MIB_TCPAOBAD, /* TCPAOBad */ + LINUX_MIB_TCPAOKEYNOTFOUND, /* TCPAOKeyNotFound */ + LINUX_MIB_TCPAOGOOD, /* TCPAOGood */ __LINUX_MIB_MAX }; diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index fa49f03e62fe..9c48964849d1 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -404,9 +404,15 @@ struct tcp_ao_info_opt { /* setsockopt(TCP_AO_INFO) */ __u32 set_current :1, /* corresponding ::current_key */ set_rnext :1, /* corresponding ::rnext */ ao_required :1, /* don't accept non-AO connects */ - reserved :29; /* must be 0 */ + set_counters :1, /* set/clear ::pkt_* counters */ + reserved :28; /* must be 0 */ + __u16 reserved2; /* padding, must be 0 */ __u8 current_key; /* KeyID to set as Current_key */ __u8 rnext; /* KeyID to set as Rnext_key */ + __u64 pkt_good; /* verified segments */ + __u64 pkt_bad; /* failed verification */ + __u64 pkt_key_not_found; /* could not find a key to verify */ + __u64 pkt_ao_required; /* segments missing TCP-AO sign */ } __attribute__((aligned(8))); /* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */ diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index a85b0aba3646..f5b37ebc18c0 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -299,6 +299,10 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPMigrateReqSuccess", LINUX_MIB_TCPMIGRATEREQSUCCESS), SNMP_MIB_ITEM("TCPMigrateReqFailure", LINUX_MIB_TCPMIGRATEREQFAILURE), SNMP_MIB_ITEM("TCPPLBRehash", LINUX_MIB_TCPPLBREHASH), + SNMP_MIB_ITEM("TCPAORequired", LINUX_MIB_TCPAOREQUIRED), + SNMP_MIB_ITEM("TCPAOBad", LINUX_MIB_TCPAOBAD), + SNMP_MIB_ITEM("TCPAOKeyNotFound", LINUX_MIB_TCPAOKEYNOTFOUND), + SNMP_MIB_ITEM("TCPAOGood", LINUX_MIB_TCPAOGOOD), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 6c5815713b73..1097e99a9ad6 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -182,6 +182,8 @@ static struct tcp_ao_key *tcp_ao_copy_key(struct sock *sk, *new_key = *key; INIT_HLIST_NODE(&new_key->node); tcp_sigpool_get(new_key->tcp_sigpool_id); + atomic64_set(&new_key->pkt_good, 0); + atomic64_set(&new_key->pkt_bad, 0); return new_key; } @@ -771,8 +773,12 @@ tcp_ao_verify_hash(const struct sock *sk, const struct sk_buff *skb, const struct tcphdr *th = tcp_hdr(skb); void *hash_buf = NULL; - if (maclen != tcp_ao_maclen(key)) + if (maclen != tcp_ao_maclen(key)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); + atomic64_inc(&info->counters.pkt_bad); + atomic64_inc(&key->pkt_bad); return SKB_DROP_REASON_TCP_AOFAILURE; + } hash_buf = kmalloc(tcp_ao_digest_size(key), GFP_ATOMIC); if (!hash_buf) @@ -782,9 +788,15 @@ tcp_ao_verify_hash(const struct sock *sk, const struct sk_buff *skb, tcp_ao_hash_skb(family, hash_buf, key, sk, skb, traffic_key, (phash - (u8 *)th), sne); if (memcmp(phash, hash_buf, maclen)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); + atomic64_inc(&info->counters.pkt_bad); + atomic64_inc(&key->pkt_bad); kfree(hash_buf); return SKB_DROP_REASON_TCP_AOFAILURE; } + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOGOOD); + atomic64_inc(&info->counters.pkt_good); + atomic64_inc(&key->pkt_good); kfree(hash_buf); return SKB_NOT_DROPPED_YET; } @@ -804,8 +816,10 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, u32 sne = 0; info = rcu_dereference(tcp_sk(sk)->ao_info); - if (!info) + if (!info) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOKEYNOTFOUND); return SKB_DROP_REASON_TCP_AOUNEXPECTED; + } if (unlikely(th->syn)) { sisn = th->seq; @@ -900,6 +914,8 @@ verify_hash: return ret; key_not_found: + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOKEYNOTFOUND); + atomic64_inc(&info->counters.key_not_found); return SKB_DROP_REASON_TCP_AOKEYNOTFOUND; } @@ -1483,6 +1499,8 @@ static int tcp_ao_add_cmd(struct sock *sk, unsigned short int family, key->keyflags = cmd.keyflags; key->sndid = cmd.sndid; key->rcvid = cmd.rcvid; + atomic64_set(&key->pkt_good, 0); + atomic64_set(&key->pkt_bad, 0); ret = tcp_ao_parse_crypto(&cmd, key); if (ret < 0) @@ -1699,7 +1717,7 @@ static int tcp_ao_info_cmd(struct sock *sk, unsigned short int family, return -EINVAL; } - if (cmd.reserved != 0) + if (cmd.reserved != 0 || cmd.reserved2 != 0) return -EINVAL; ao_info = setsockopt_ao_info(sk); @@ -1734,6 +1752,12 @@ static int tcp_ao_info_cmd(struct sock *sk, unsigned short int family, goto out; } } + if (cmd.set_counters) { + atomic64_set(&ao_info->counters.pkt_good, cmd.pkt_good); + atomic64_set(&ao_info->counters.pkt_bad, cmd.pkt_bad); + atomic64_set(&ao_info->counters.key_not_found, cmd.pkt_key_not_found); + atomic64_set(&ao_info->counters.ao_required, cmd.pkt_ao_required); + } ao_info->ao_required = cmd.ao_required; if (new_current) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f39ccefa78dc..ece95d5138e1 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1531,7 +1531,7 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, /* Don't allow keys for peers that have a matching TCP-AO key. * See the comment in tcp_ao_add_cmd() */ - if (tcp_ao_required(sk, addr, AF_INET)) + if (tcp_ao_required(sk, addr, AF_INET, false)) return -EKEYREJECTED; return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, flags, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d2724383d263..cc899caf348e 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -661,7 +661,7 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, /* Don't allow keys for peers that have a matching TCP-AO key. * See the comment in tcp_ao_add_cmd() */ - if (tcp_ao_required(sk, addr, AF_INET)) + if (tcp_ao_required(sk, addr, AF_INET, false)) return -EKEYREJECTED; return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, flags, @@ -673,7 +673,7 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, /* Don't allow keys for peers that have a matching TCP-AO key. * See the comment in tcp_ao_add_cmd() */ - if (tcp_ao_required(sk, addr, AF_INET6)) + if (tcp_ao_required(sk, addr, AF_INET6, false)) return -EKEYREJECTED; return tcp_md5_do_add(sk, addr, AF_INET6, prefixlen, l3index, flags, -- cgit From 953af8e3acb68d2db11937cec3bc5da31de5c12e Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 23 Oct 2023 20:22:08 +0100 Subject: net/tcp: Ignore specific ICMPs for TCP-AO connections MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Similarly to IPsec, RFC5925 prescribes: ">> A TCP-AO implementation MUST default to ignore incoming ICMPv4 messages of Type 3 (destination unreachable), Codes 2-4 (protocol unreachable, port unreachable, and fragmentation needed -- ’hard errors’), and ICMPv6 Type 1 (destination unreachable), Code 1 (administratively prohibited) and Code 4 (port unreachable) intended for connections in synchronized states (ESTABLISHED, FIN-WAIT-1, FIN- WAIT-2, CLOSE-WAIT, CLOSING, LAST-ACK, TIME-WAIT) that match MKTs." A selftest (later in patch series) verifies that this attack is not possible in this TCP-AO implementation. Co-developed-by: Francesco Ruggeri Signed-off-by: Francesco Ruggeri Co-developed-by: Salam Noureddine Signed-off-by: Salam Noureddine Signed-off-by: Dmitry Safonov Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/tcp_ao.h | 11 ++++++++- include/uapi/linux/snmp.h | 1 + include/uapi/linux/tcp.h | 4 +++- net/ipv4/proc.c | 1 + net/ipv4/tcp_ao.c | 58 +++++++++++++++++++++++++++++++++++++++++++++++ net/ipv4/tcp_ipv4.c | 7 ++++++ net/ipv6/tcp_ipv6.c | 7 ++++++ 7 files changed, 87 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h index 4da6e3657913..a9d38b9e8bcb 100644 --- a/include/net/tcp_ao.h +++ b/include/net/tcp_ao.h @@ -24,6 +24,7 @@ struct tcp_ao_counters { atomic64_t pkt_bad; atomic64_t key_not_found; atomic64_t ao_required; + atomic64_t dropped_icmp; }; struct tcp_ao_key { @@ -92,7 +93,8 @@ struct tcp_ao_info { struct tcp_ao_key *rnext_key; struct tcp_ao_counters counters; u32 ao_required :1, - __unused :31; + accept_icmps :1, + __unused :30; __be32 lisn; __be32 risn; /* Sequence Number Extension (SNE) are upper 4 bytes for SEQ, @@ -191,6 +193,7 @@ int tcp_ao_calc_traffic_key(struct tcp_ao_key *mkt, u8 *key, void *ctx, unsigned int len, struct tcp_sigpool *hp); void tcp_ao_destroy_sock(struct sock *sk, bool twsk); void tcp_ao_time_wait(struct tcp_timewait_sock *tcptw, struct tcp_sock *tp); +bool tcp_ao_ignore_icmp(const struct sock *sk, int family, int type, int code); enum skb_drop_reason tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, unsigned short int family, const struct request_sock *req, @@ -274,6 +277,12 @@ static inline void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb, { } +static inline bool tcp_ao_ignore_icmp(const struct sock *sk, int family, + int type, int code) +{ + return false; +} + static inline enum skb_drop_reason tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, unsigned short int family, const struct request_sock *req, const struct tcp_ao_hdr *aoh) diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 3d5ea841bffe..a0819c6a5988 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -301,6 +301,7 @@ enum LINUX_MIB_TCPAOBAD, /* TCPAOBad */ LINUX_MIB_TCPAOKEYNOTFOUND, /* TCPAOKeyNotFound */ LINUX_MIB_TCPAOGOOD, /* TCPAOGood */ + LINUX_MIB_TCPAODROPPEDICMPS, /* TCPAODroppedIcmps */ __LINUX_MIB_MAX }; diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 9c48964849d1..d8b2ea23f12a 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -405,7 +405,8 @@ struct tcp_ao_info_opt { /* setsockopt(TCP_AO_INFO) */ set_rnext :1, /* corresponding ::rnext */ ao_required :1, /* don't accept non-AO connects */ set_counters :1, /* set/clear ::pkt_* counters */ - reserved :28; /* must be 0 */ + accept_icmps :1, /* accept incoming ICMPs */ + reserved :27; /* must be 0 */ __u16 reserved2; /* padding, must be 0 */ __u8 current_key; /* KeyID to set as Current_key */ __u8 rnext; /* KeyID to set as Rnext_key */ @@ -413,6 +414,7 @@ struct tcp_ao_info_opt { /* setsockopt(TCP_AO_INFO) */ __u64 pkt_bad; /* failed verification */ __u64 pkt_key_not_found; /* could not find a key to verify */ __u64 pkt_ao_required; /* segments missing TCP-AO sign */ + __u64 pkt_dropped_icmp; /* ICMPs that were ignored */ } __attribute__((aligned(8))); /* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */ diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index f5b37ebc18c0..5f4654ebff48 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -303,6 +303,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPAOBad", LINUX_MIB_TCPAOBAD), SNMP_MIB_ITEM("TCPAOKeyNotFound", LINUX_MIB_TCPAOKEYNOTFOUND), SNMP_MIB_ITEM("TCPAOGood", LINUX_MIB_TCPAOGOOD), + SNMP_MIB_ITEM("TCPAODroppedIcmps", LINUX_MIB_TCPAODROPPEDICMPS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index f76fcb93499d..223af5c9eaf3 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -15,6 +15,7 @@ #include #include +#include int tcp_ao_calc_traffic_key(struct tcp_ao_key *mkt, u8 *key, void *ctx, unsigned int len, struct tcp_sigpool *hp) @@ -44,6 +45,60 @@ clear_hash: return 1; } +bool tcp_ao_ignore_icmp(const struct sock *sk, int family, int type, int code) +{ + bool ignore_icmp = false; + struct tcp_ao_info *ao; + + /* RFC5925, 7.8: + * >> A TCP-AO implementation MUST default to ignore incoming ICMPv4 + * messages of Type 3 (destination unreachable), Codes 2-4 (protocol + * unreachable, port unreachable, and fragmentation needed -- ’hard + * errors’), and ICMPv6 Type 1 (destination unreachable), Code 1 + * (administratively prohibited) and Code 4 (port unreachable) intended + * for connections in synchronized states (ESTABLISHED, FIN-WAIT-1, FIN- + * WAIT-2, CLOSE-WAIT, CLOSING, LAST-ACK, TIME-WAIT) that match MKTs. + */ + if (family == AF_INET) { + if (type != ICMP_DEST_UNREACH) + return false; + if (code < ICMP_PROT_UNREACH || code > ICMP_FRAG_NEEDED) + return false; + } else { + if (type != ICMPV6_DEST_UNREACH) + return false; + if (code != ICMPV6_ADM_PROHIBITED && code != ICMPV6_PORT_UNREACH) + return false; + } + + rcu_read_lock(); + switch (sk->sk_state) { + case TCP_TIME_WAIT: + ao = rcu_dereference(tcp_twsk(sk)->ao_info); + break; + case TCP_SYN_SENT: + case TCP_SYN_RECV: + case TCP_LISTEN: + case TCP_NEW_SYN_RECV: + /* RFC5925 specifies to ignore ICMPs *only* on connections + * in synchronized states. + */ + rcu_read_unlock(); + return false; + default: + ao = rcu_dereference(tcp_sk(sk)->ao_info); + } + + if (ao && !ao->accept_icmps) { + ignore_icmp = true; + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAODROPPEDICMPS); + atomic64_inc(&ao->counters.dropped_icmp); + } + rcu_read_unlock(); + + return ignore_icmp; +} + /* Optimized version of tcp_ao_do_lookup(): only for sockets for which * it's known that the keys in ao_info are matching peer's * family/address/VRF/etc. @@ -1086,6 +1141,7 @@ int tcp_ao_copy_all_matching(const struct sock *sk, struct sock *newsk, new_ao->lisn = htonl(tcp_rsk(req)->snt_isn); new_ao->risn = htonl(tcp_rsk(req)->rcv_isn); new_ao->ao_required = ao->ao_required; + new_ao->accept_icmps = ao->accept_icmps; if (family == AF_INET) { addr = (union tcp_ao_addr *)&newsk->sk_daddr; @@ -1792,9 +1848,11 @@ static int tcp_ao_info_cmd(struct sock *sk, unsigned short int family, atomic64_set(&ao_info->counters.pkt_bad, cmd.pkt_bad); atomic64_set(&ao_info->counters.key_not_found, cmd.pkt_key_not_found); atomic64_set(&ao_info->counters.ao_required, cmd.pkt_ao_required); + atomic64_set(&ao_info->counters.dropped_icmp, cmd.pkt_dropped_icmp); } ao_info->ao_required = cmd.ao_required; + ao_info->accept_icmps = cmd.accept_icmps; if (new_current) WRITE_ONCE(ao_info->current_key, new_current); if (new_rnext) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index bdec99707028..8f98c58e2689 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -494,6 +494,8 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) return -ENOENT; } if (sk->sk_state == TCP_TIME_WAIT) { + /* To increase the counter of ignored icmps for TCP-AO */ + tcp_ao_ignore_icmp(sk, AF_INET, type, code); inet_twsk_put(inet_twsk(sk)); return 0; } @@ -507,6 +509,11 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) return 0; } + if (tcp_ao_ignore_icmp(sk, AF_INET, type, code)) { + sock_put(sk); + return 0; + } + bh_lock_sock(sk); /* If too many ICMPs get dropped on busy * servers this needs to be solved differently. diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 4dcbc13e9ec8..fa7050579e9a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -396,6 +396,8 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } if (sk->sk_state == TCP_TIME_WAIT) { + /* To increase the counter of ignored icmps for TCP-AO */ + tcp_ao_ignore_icmp(sk, AF_INET6, type, code); inet_twsk_put(inet_twsk(sk)); return 0; } @@ -406,6 +408,11 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return 0; } + if (tcp_ao_ignore_icmp(sk, AF_INET6, type, code)) { + sock_put(sk); + return 0; + } + bh_lock_sock(sk); if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) __NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS); -- cgit From 7753c2f0a857bfa6501e67deee03988dd0bcaae7 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 23 Oct 2023 20:22:09 +0100 Subject: net/tcp: Add option for TCP-AO to (not) hash header Provide setsockopt() key flag that makes TCP-AO exclude hashing TCP header for peers that match the key. This is needed for interraction with middleboxes that may change TCP options, see RFC5925 (9.2). Co-developed-by: Francesco Ruggeri Signed-off-by: Francesco Ruggeri Co-developed-by: Salam Noureddine Signed-off-by: Salam Noureddine Signed-off-by: Dmitry Safonov Acked-by: David Ahern Signed-off-by: David S. Miller --- include/uapi/linux/tcp.h | 5 +++++ net/ipv4/tcp_ao.c | 8 +++++--- 2 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index d8b2ea23f12a..320aab010f9a 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -367,6 +367,11 @@ struct tcp_diag_md5sig { #define TCP_AO_MAXKEYLEN 80 #define TCP_AO_KEYF_IFINDEX (1 << 0) /* L3 ifindex for VRF */ +#define TCP_AO_KEYF_EXCLUDE_OPT (1 << 1) /* "Indicates whether TCP + * options other than TCP-AO + * are included in the MAC + * calculation" + */ struct tcp_ao_add { /* setsockopt(TCP_AO_ADD_KEY) */ struct __kernel_sockaddr_storage addr; /* peer's address for the key */ diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 223af5c9eaf3..10cc6be4d537 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -562,7 +562,8 @@ int tcp_ao_hash_hdr(unsigned short int family, char *ao_hash, WARN_ON_ONCE(1); goto clear_hash; } - if (tcp_ao_hash_header(&hp, th, false, + if (tcp_ao_hash_header(&hp, th, + !!(key->keyflags & TCP_AO_KEYF_EXCLUDE_OPT), ao_hash, hash_offset, tcp_ao_maclen(key))) goto clear_hash; ahash_request_set_crypt(hp.req, NULL, hash_buf, 0); @@ -610,7 +611,8 @@ int tcp_ao_hash_skb(unsigned short int family, goto clear_hash; if (tcp_ao_hash_pseudoheader(family, sk, skb, &hp, skb->len)) goto clear_hash; - if (tcp_ao_hash_header(&hp, th, false, + if (tcp_ao_hash_header(&hp, th, + !!(key->keyflags & TCP_AO_KEYF_EXCLUDE_OPT), ao_hash, hash_offset, tcp_ao_maclen(key))) goto clear_hash; if (tcp_sigpool_hash_skb_data(&hp, skb, th->doff << 2)) @@ -1454,7 +1456,7 @@ static struct tcp_ao_info *setsockopt_ao_info(struct sock *sk) return ERR_PTR(-ESOCKTNOSUPPORT); } -#define TCP_AO_KEYF_ALL (0) +#define TCP_AO_KEYF_ALL (TCP_AO_KEYF_EXCLUDE_OPT) static struct tcp_ao_key *tcp_ao_key_alloc(struct sock *sk, struct tcp_ao_add *cmd) -- cgit From ef84703a911f4ee52ca585e8308b7084093941f4 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 23 Oct 2023 20:22:10 +0100 Subject: net/tcp: Add TCP-AO getsockopt()s Introduce getsockopt(TCP_AO_GET_KEYS) that lets a user get TCP-AO keys and their properties from a socket. The user can provide a filter to match the specific key to be dumped or ::get_all = 1 may be used to dump all keys in one syscall. Add another getsockopt(TCP_AO_INFO) for providing per-socket/per-ao_info stats: packet counters, Current_key/RNext_key and flags like ::ao_required and ::accept_icmps. Co-developed-by: Francesco Ruggeri Signed-off-by: Francesco Ruggeri Co-developed-by: Salam Noureddine Signed-off-by: Salam Noureddine Signed-off-by: Dmitry Safonov Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/tcp_ao.h | 12 ++ include/uapi/linux/tcp.h | 63 +++++++--- net/ipv4/tcp.c | 13 +++ net/ipv4/tcp_ao.c | 295 +++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 369 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h index a9d38b9e8bcb..061c358a3c8a 100644 --- a/include/net/tcp_ao.h +++ b/include/net/tcp_ao.h @@ -194,6 +194,8 @@ int tcp_ao_calc_traffic_key(struct tcp_ao_key *mkt, u8 *key, void *ctx, void tcp_ao_destroy_sock(struct sock *sk, bool twsk); void tcp_ao_time_wait(struct tcp_timewait_sock *tcptw, struct tcp_sock *tp); bool tcp_ao_ignore_icmp(const struct sock *sk, int family, int type, int code); +int tcp_ao_get_mkts(struct sock *sk, sockptr_t optval, sockptr_t optlen); +int tcp_ao_get_sock_info(struct sock *sk, sockptr_t optval, sockptr_t optlen); enum skb_drop_reason tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, unsigned short int family, const struct request_sock *req, @@ -316,6 +318,16 @@ static inline void tcp_ao_time_wait(struct tcp_timewait_sock *tcptw, static inline void tcp_ao_connect_init(struct sock *sk) { } + +static inline int tcp_ao_get_mkts(struct sock *sk, sockptr_t optval, sockptr_t optlen) +{ + return -ENOPROTOOPT; +} + +static inline int tcp_ao_get_sock_info(struct sock *sk, sockptr_t optval, sockptr_t optlen) +{ + return -ENOPROTOOPT; +} #endif #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 320aab010f9a..201b3cbd6020 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -131,7 +131,8 @@ enum { #define TCP_AO_ADD_KEY 38 /* Add/Set MKT */ #define TCP_AO_DEL_KEY 39 /* Delete MKT */ -#define TCP_AO_INFO 40 /* Modify TCP-AO per-socket options */ +#define TCP_AO_INFO 40 /* Set/list TCP-AO per-socket options */ +#define TCP_AO_GET_KEYS 41 /* List MKT(s) */ #define TCP_REPAIR_ON 1 #define TCP_REPAIR_OFF 0 @@ -405,21 +406,55 @@ struct tcp_ao_del { /* setsockopt(TCP_AO_DEL_KEY) */ __u8 keyflags; /* see TCP_AO_KEYF_ */ } __attribute__((aligned(8))); -struct tcp_ao_info_opt { /* setsockopt(TCP_AO_INFO) */ - __u32 set_current :1, /* corresponding ::current_key */ - set_rnext :1, /* corresponding ::rnext */ - ao_required :1, /* don't accept non-AO connects */ - set_counters :1, /* set/clear ::pkt_* counters */ - accept_icmps :1, /* accept incoming ICMPs */ +struct tcp_ao_info_opt { /* setsockopt(TCP_AO_INFO), getsockopt(TCP_AO_INFO) */ + /* Here 'in' is for setsockopt(), 'out' is for getsockopt() */ + __u32 set_current :1, /* in/out: corresponding ::current_key */ + set_rnext :1, /* in/out: corresponding ::rnext */ + ao_required :1, /* in/out: don't accept non-AO connects */ + set_counters :1, /* in: set/clear ::pkt_* counters */ + accept_icmps :1, /* in/out: accept incoming ICMPs */ reserved :27; /* must be 0 */ __u16 reserved2; /* padding, must be 0 */ - __u8 current_key; /* KeyID to set as Current_key */ - __u8 rnext; /* KeyID to set as Rnext_key */ - __u64 pkt_good; /* verified segments */ - __u64 pkt_bad; /* failed verification */ - __u64 pkt_key_not_found; /* could not find a key to verify */ - __u64 pkt_ao_required; /* segments missing TCP-AO sign */ - __u64 pkt_dropped_icmp; /* ICMPs that were ignored */ + __u8 current_key; /* in/out: KeyID of Current_key */ + __u8 rnext; /* in/out: keyid of RNext_key */ + __u64 pkt_good; /* in/out: verified segments */ + __u64 pkt_bad; /* in/out: failed verification */ + __u64 pkt_key_not_found; /* in/out: could not find a key to verify */ + __u64 pkt_ao_required; /* in/out: segments missing TCP-AO sign */ + __u64 pkt_dropped_icmp; /* in/out: ICMPs that were ignored */ +} __attribute__((aligned(8))); + +struct tcp_ao_getsockopt { /* getsockopt(TCP_AO_GET_KEYS) */ + struct __kernel_sockaddr_storage addr; /* in/out: dump keys for peer + * with this address/prefix + */ + char alg_name[64]; /* out: crypto hash algorithm */ + __u8 key[TCP_AO_MAXKEYLEN]; + __u32 nkeys; /* in: size of the userspace buffer + * @optval, measured in @optlen - the + * sizeof(struct tcp_ao_getsockopt) + * out: number of keys that matched + */ + __u16 is_current :1, /* in: match and dump Current_key, + * out: the dumped key is Current_key + */ + + is_rnext :1, /* in: match and dump RNext_key, + * out: the dumped key is RNext_key + */ + get_all :1, /* in: dump all keys */ + reserved :13; /* padding, must be 0 */ + __u8 sndid; /* in/out: dump keys with SendID */ + __u8 rcvid; /* in/out: dump keys with RecvID */ + __u8 prefix; /* in/out: dump keys with address/prefix */ + __u8 maclen; /* out: key's length of authentication + * code (hash) + */ + __u8 keyflags; /* in/out: see TCP_AO_KEYF_ */ + __u8 keylen; /* out: length of ::key */ + __s32 ifindex; /* in/out: L3 dev index for VRF */ + __u64 pkt_good; /* out: verified segments */ + __u64 pkt_bad; /* out: segments that failed verification */ } __attribute__((aligned(8))); /* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1be6467a059a..ce33eee9d0f2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4284,6 +4284,19 @@ zerocopy_rcv_out: return err; } #endif + case TCP_AO_GET_KEYS: + case TCP_AO_INFO: { + int err; + + sockopt_lock_sock(sk); + if (optname == TCP_AO_GET_KEYS) + err = tcp_ao_get_mkts(sk, optval, optlen); + else + err = tcp_ao_get_sock_info(sk, optval, optlen); + sockopt_release_sock(sk); + + return err; + } default: return -ENOPROTOOPT; } diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 10cc6be4d537..cbc1ee0f5b9a 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -1894,3 +1894,298 @@ int tcp_v4_parse_ao(struct sock *sk, int cmd, sockptr_t optval, int optlen) return tcp_parse_ao(sk, cmd, AF_INET, optval, optlen); } +/* tcp_ao_copy_mkts_to_user(ao_info, optval, optlen) + * + * @ao_info: struct tcp_ao_info on the socket that + * socket getsockopt(TCP_AO_GET_KEYS) is executed on + * @optval: pointer to array of tcp_ao_getsockopt structures in user space. + * Must be != NULL. + * @optlen: pointer to size of tcp_ao_getsockopt structure. + * Must be != NULL. + * + * Return value: 0 on success, a negative error number otherwise. + * + * optval points to an array of tcp_ao_getsockopt structures in user space. + * optval[0] is used as both input and output to getsockopt. It determines + * which keys are returned by the kernel. + * optval[0].nkeys is the size of the array in user space. On return it contains + * the number of keys matching the search criteria. + * If tcp_ao_getsockopt::get_all is set, then all keys in the socket are + * returned, otherwise only keys matching + * in optval[0] are returned. + * optlen is also used as both input and output. The user provides the size + * of struct tcp_ao_getsockopt in user space, and the kernel returns the size + * of the structure in kernel space. + * The size of struct tcp_ao_getsockopt may differ between user and kernel. + * There are three cases to consider: + * * If usize == ksize, then keys are copied verbatim. + * * If usize < ksize, then the userspace has passed an old struct to a + * newer kernel. The rest of the trailing bytes in optval[0] + * (ksize - usize) are interpreted as 0 by the kernel. + * * If usize > ksize, then the userspace has passed a new struct to an + * older kernel. The trailing bytes unknown to the kernel (usize - ksize) + * are checked to ensure they are zeroed, otherwise -E2BIG is returned. + * On return the kernel fills in min(usize, ksize) in each entry of the array. + * The layout of the fields in the user and kernel structures is expected to + * be the same (including in the 32bit vs 64bit case). + */ +static int tcp_ao_copy_mkts_to_user(struct tcp_ao_info *ao_info, + sockptr_t optval, sockptr_t optlen) +{ + struct tcp_ao_getsockopt opt_in, opt_out; + struct tcp_ao_key *key, *current_key; + bool do_address_matching = true; + union tcp_ao_addr *addr = NULL; + unsigned int max_keys; /* maximum number of keys to copy to user */ + size_t out_offset = 0; + size_t bytes_to_write; /* number of bytes to write to user level */ + int err, user_len; + u32 matched_keys; /* keys from ao_info matched so far */ + int optlen_out; + __be16 port = 0; + + if (copy_from_sockptr(&user_len, optlen, sizeof(int))) + return -EFAULT; + + if (user_len <= 0) + return -EINVAL; + + memset(&opt_in, 0, sizeof(struct tcp_ao_getsockopt)); + err = copy_struct_from_sockptr(&opt_in, sizeof(opt_in), + optval, user_len); + if (err < 0) + return err; + + if (opt_in.pkt_good || opt_in.pkt_bad) + return -EINVAL; + + if (opt_in.reserved != 0) + return -EINVAL; + + max_keys = opt_in.nkeys; + + if (opt_in.get_all || opt_in.is_current || opt_in.is_rnext) { + if (opt_in.get_all && (opt_in.is_current || opt_in.is_rnext)) + return -EINVAL; + do_address_matching = false; + } + + switch (opt_in.addr.ss_family) { + case AF_INET: { + struct sockaddr_in *sin; + __be32 mask; + + sin = (struct sockaddr_in *)&opt_in.addr; + port = sin->sin_port; + addr = (union tcp_ao_addr *)&sin->sin_addr; + + if (opt_in.prefix > 32) + return -EINVAL; + + if (ntohl(sin->sin_addr.s_addr) == INADDR_ANY && + opt_in.prefix != 0) + return -EINVAL; + + mask = inet_make_mask(opt_in.prefix); + if (sin->sin_addr.s_addr & ~mask) + return -EINVAL; + + break; + } + case AF_INET6: { + struct sockaddr_in6 *sin6; + struct in6_addr *addr6; + + sin6 = (struct sockaddr_in6 *)&opt_in.addr; + addr = (union tcp_ao_addr *)&sin6->sin6_addr; + addr6 = &sin6->sin6_addr; + port = sin6->sin6_port; + + /* We don't have to change family and @addr here if + * ipv6_addr_v4mapped() like in key adding: + * tcp_ao_key_cmp() does it. Do the sanity checks though. + */ + if (opt_in.prefix != 0) { + if (ipv6_addr_v4mapped(addr6)) { + __be32 mask, addr4 = addr6->s6_addr32[3]; + + if (opt_in.prefix > 32 || + ntohl(addr4) == INADDR_ANY) + return -EINVAL; + mask = inet_make_mask(opt_in.prefix); + if (addr4 & ~mask) + return -EINVAL; + } else { + struct in6_addr pfx; + + if (ipv6_addr_any(addr6) || + opt_in.prefix > 128) + return -EINVAL; + + ipv6_addr_prefix(&pfx, addr6, opt_in.prefix); + if (ipv6_addr_cmp(&pfx, addr6)) + return -EINVAL; + } + } else if (!ipv6_addr_any(addr6)) { + return -EINVAL; + } + break; + } + case 0: + if (!do_address_matching) + break; + fallthrough; + default: + return -EAFNOSUPPORT; + } + + if (!do_address_matching) { + /* We could just ignore those, but let's do stricter checks */ + if (addr || port) + return -EINVAL; + if (opt_in.prefix || opt_in.sndid || opt_in.rcvid) + return -EINVAL; + } + + bytes_to_write = min_t(int, user_len, sizeof(struct tcp_ao_getsockopt)); + matched_keys = 0; + /* May change in RX, while we're dumping, pre-fetch it */ + current_key = READ_ONCE(ao_info->current_key); + + hlist_for_each_entry_rcu(key, &ao_info->head, node) { + if (opt_in.get_all) + goto match; + + if (opt_in.is_current || opt_in.is_rnext) { + if (opt_in.is_current && key == current_key) + goto match; + if (opt_in.is_rnext && key == ao_info->rnext_key) + goto match; + continue; + } + + if (tcp_ao_key_cmp(key, addr, opt_in.prefix, + opt_in.addr.ss_family, + opt_in.sndid, opt_in.rcvid) != 0) + continue; +match: + matched_keys++; + if (matched_keys > max_keys) + continue; + + memset(&opt_out, 0, sizeof(struct tcp_ao_getsockopt)); + + if (key->family == AF_INET) { + struct sockaddr_in *sin_out = (struct sockaddr_in *)&opt_out.addr; + + sin_out->sin_family = key->family; + sin_out->sin_port = 0; + memcpy(&sin_out->sin_addr, &key->addr, sizeof(struct in_addr)); + } else { + struct sockaddr_in6 *sin6_out = (struct sockaddr_in6 *)&opt_out.addr; + + sin6_out->sin6_family = key->family; + sin6_out->sin6_port = 0; + memcpy(&sin6_out->sin6_addr, &key->addr, sizeof(struct in6_addr)); + } + opt_out.sndid = key->sndid; + opt_out.rcvid = key->rcvid; + opt_out.prefix = key->prefixlen; + opt_out.keyflags = key->keyflags; + opt_out.is_current = (key == current_key); + opt_out.is_rnext = (key == ao_info->rnext_key); + opt_out.nkeys = 0; + opt_out.maclen = key->maclen; + opt_out.keylen = key->keylen; + opt_out.pkt_good = atomic64_read(&key->pkt_good); + opt_out.pkt_bad = atomic64_read(&key->pkt_bad); + memcpy(&opt_out.key, key->key, key->keylen); + tcp_sigpool_algo(key->tcp_sigpool_id, opt_out.alg_name, 64); + + /* Copy key to user */ + if (copy_to_sockptr_offset(optval, out_offset, + &opt_out, bytes_to_write)) + return -EFAULT; + out_offset += user_len; + } + + optlen_out = (int)sizeof(struct tcp_ao_getsockopt); + if (copy_to_sockptr(optlen, &optlen_out, sizeof(int))) + return -EFAULT; + + out_offset = offsetof(struct tcp_ao_getsockopt, nkeys); + if (copy_to_sockptr_offset(optval, out_offset, + &matched_keys, sizeof(u32))) + return -EFAULT; + + return 0; +} + +int tcp_ao_get_mkts(struct sock *sk, sockptr_t optval, sockptr_t optlen) +{ + struct tcp_ao_info *ao_info; + + ao_info = setsockopt_ao_info(sk); + if (IS_ERR(ao_info)) + return PTR_ERR(ao_info); + if (!ao_info) + return -ENOENT; + + return tcp_ao_copy_mkts_to_user(ao_info, optval, optlen); +} + +int tcp_ao_get_sock_info(struct sock *sk, sockptr_t optval, sockptr_t optlen) +{ + struct tcp_ao_info_opt out, in = {}; + struct tcp_ao_key *current_key; + struct tcp_ao_info *ao; + int err, len; + + if (copy_from_sockptr(&len, optlen, sizeof(int))) + return -EFAULT; + + if (len <= 0) + return -EINVAL; + + /* Copying this "in" only to check ::reserved, ::reserved2, + * that may be needed to extend (struct tcp_ao_info_opt) and + * what getsockopt() provides in future. + */ + err = copy_struct_from_sockptr(&in, sizeof(in), optval, len); + if (err) + return err; + + if (in.reserved != 0 || in.reserved2 != 0) + return -EINVAL; + + ao = setsockopt_ao_info(sk); + if (IS_ERR(ao)) + return PTR_ERR(ao); + if (!ao) + return -ENOENT; + + memset(&out, 0, sizeof(out)); + out.ao_required = ao->ao_required; + out.accept_icmps = ao->accept_icmps; + out.pkt_good = atomic64_read(&ao->counters.pkt_good); + out.pkt_bad = atomic64_read(&ao->counters.pkt_bad); + out.pkt_key_not_found = atomic64_read(&ao->counters.key_not_found); + out.pkt_ao_required = atomic64_read(&ao->counters.ao_required); + out.pkt_dropped_icmp = atomic64_read(&ao->counters.dropped_icmp); + + current_key = READ_ONCE(ao->current_key); + if (current_key) { + out.set_current = 1; + out.current_key = current_key->sndid; + } + if (ao->rnext_key) { + out.set_rnext = 1; + out.rnext = ao->rnext_key->rcvid; + } + + if (copy_to_sockptr(optval, &out, min_t(int, len, sizeof(out)))) + return -EFAULT; + + return 0; +} + -- cgit From d6732b95b6fbbc6d5bb9d2f809e275763640c4a2 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 23 Oct 2023 20:22:11 +0100 Subject: net/tcp: Allow asynchronous delete for TCP-AO keys (MKTs) Delete becomes very, very fast - almost free, but after setsockopt() syscall returns, the key is still alive until next RCU grace period. Which is fine for listen sockets as userspace needs to be aware of setsockopt(TCP_AO) and accept() race and resolve it with verification by getsockopt() after TCP connection was accepted. The benchmark results (on non-loaded box, worse with more RCU work pending): > ok 33 Worst case delete 16384 keys: min=5ms max=10ms mean=6.93904ms stddev=0.263421 > ok 34 Add a new key 16384 keys: min=1ms max=4ms mean=2.17751ms stddev=0.147564 > ok 35 Remove random-search 16384 keys: min=5ms max=10ms mean=6.50243ms stddev=0.254999 > ok 36 Remove async 16384 keys: min=0ms max=0ms mean=0.0296107ms stddev=0.0172078 Co-developed-by: Francesco Ruggeri Signed-off-by: Francesco Ruggeri Co-developed-by: Salam Noureddine Signed-off-by: Salam Noureddine Signed-off-by: Dmitry Safonov Acked-by: David Ahern Signed-off-by: David S. Miller --- include/uapi/linux/tcp.h | 3 ++- net/ipv4/tcp_ao.c | 21 ++++++++++++++++++--- 2 files changed, 20 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 201b3cbd6020..be34d7c5c531 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -396,7 +396,8 @@ struct tcp_ao_del { /* setsockopt(TCP_AO_DEL_KEY) */ __s32 ifindex; /* L3 dev index for VRF */ __u32 set_current :1, /* corresponding ::current_key */ set_rnext :1, /* corresponding ::rnext */ - reserved :30; /* must be 0 */ + del_async :1, /* only valid for listen sockets */ + reserved :29; /* must be 0 */ __u16 reserved2; /* padding, must be 0 */ __u8 prefix; /* peer's address prefix */ __u8 sndid; /* SendID for outgoing segments */ diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index cbc1ee0f5b9a..acbeb635fe29 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -1628,7 +1628,7 @@ err_free_ao: } static int tcp_ao_delete_key(struct sock *sk, struct tcp_ao_info *ao_info, - struct tcp_ao_key *key, + bool del_async, struct tcp_ao_key *key, struct tcp_ao_key *new_current, struct tcp_ao_key *new_rnext) { @@ -1636,11 +1636,24 @@ static int tcp_ao_delete_key(struct sock *sk, struct tcp_ao_info *ao_info, hlist_del_rcu(&key->node); + /* Support for async delete on listening sockets: as they don't + * need current_key/rnext_key maintaining, we don't need to check + * them and we can just free all resources in RCU fashion. + */ + if (del_async) { + atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc); + call_rcu(&key->rcu, tcp_ao_key_free_rcu); + return 0; + } + /* At this moment another CPU could have looked this key up * while it was unlinked from the list. Wait for RCU grace period, * after which the key is off-list and can't be looked up again; * the rx path [just before RCU came] might have used it and set it * as current_key (very unlikely). + * Free the key with next RCU grace period (in case it was + * current_key before tcp_ao_current_rnext() might have + * changed it in forced-delete). */ synchronize_rcu(); if (new_current) @@ -1711,6 +1724,8 @@ static int tcp_ao_del_cmd(struct sock *sk, unsigned short int family, if (!new_rnext) return -ENOENT; } + if (cmd.del_async && sk->sk_state != TCP_LISTEN) + return -EINVAL; if (family == AF_INET) { struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.addr; @@ -1758,8 +1773,8 @@ static int tcp_ao_del_cmd(struct sock *sk, unsigned short int family, if (key == new_current || key == new_rnext) continue; - return tcp_ao_delete_key(sk, ao_info, key, - new_current, new_rnext); + return tcp_ao_delete_key(sk, ao_info, cmd.del_async, key, + new_current, new_rnext); } return -ENOENT; } -- cgit From faadfaba5e018ca0f9595f17115ff48416b7b85e Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 23 Oct 2023 20:22:14 +0100 Subject: net/tcp: Add TCP_AO_REPAIR Add TCP_AO_REPAIR setsockopt(), getsockopt(). They let a user to repair TCP-AO ISNs/SNEs. Also let the user hack around when (tp->repair) is on and add ao_info on a socket in any supported state. As SNEs now can be read/written at any moment, use WRITE_ONCE()/READ_ONCE() to set/read them. Signed-off-by: Dmitry Safonov Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/tcp_ao.h | 14 ++++++++ include/uapi/linux/tcp.h | 8 +++++ net/ipv4/tcp.c | 24 +++++++++---- net/ipv4/tcp_ao.c | 90 +++++++++++++++++++++++++++++++++++++++++++++--- 4 files changed, 125 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h index edd6748b2cfa..a375a171ef3c 100644 --- a/include/net/tcp_ao.h +++ b/include/net/tcp_ao.h @@ -199,6 +199,8 @@ void tcp_ao_time_wait(struct tcp_timewait_sock *tcptw, struct tcp_sock *tp); bool tcp_ao_ignore_icmp(const struct sock *sk, int family, int type, int code); int tcp_ao_get_mkts(struct sock *sk, sockptr_t optval, sockptr_t optlen); int tcp_ao_get_sock_info(struct sock *sk, sockptr_t optval, sockptr_t optlen); +int tcp_ao_get_repair(struct sock *sk, sockptr_t optval, sockptr_t optlen); +int tcp_ao_set_repair(struct sock *sk, sockptr_t optval, unsigned int optlen); enum skb_drop_reason tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, unsigned short int family, const struct request_sock *req, int l3index, @@ -330,6 +332,18 @@ static inline int tcp_ao_get_sock_info(struct sock *sk, sockptr_t optval, sockpt { return -ENOPROTOOPT; } + +static inline int tcp_ao_get_repair(struct sock *sk, + sockptr_t optval, sockptr_t optlen) +{ + return -ENOPROTOOPT; +} + +static inline int tcp_ao_set_repair(struct sock *sk, + sockptr_t optval, unsigned int optlen) +{ + return -ENOPROTOOPT; +} #endif #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index be34d7c5c531..c07e9f90c084 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -133,6 +133,7 @@ enum { #define TCP_AO_DEL_KEY 39 /* Delete MKT */ #define TCP_AO_INFO 40 /* Set/list TCP-AO per-socket options */ #define TCP_AO_GET_KEYS 41 /* List MKT(s) */ +#define TCP_AO_REPAIR 42 /* Get/Set SNEs and ISNs */ #define TCP_REPAIR_ON 1 #define TCP_REPAIR_OFF 0 @@ -458,6 +459,13 @@ struct tcp_ao_getsockopt { /* getsockopt(TCP_AO_GET_KEYS) */ __u64 pkt_bad; /* out: segments that failed verification */ } __attribute__((aligned(8))); +struct tcp_ao_repair { /* {s,g}etsockopt(TCP_AO_REPAIR) */ + __be32 snt_isn; + __be32 rcv_isn; + __u32 snd_sne; + __u32 rcv_sne; +} __attribute__((aligned(8))); + /* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */ #define TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT 0x1 diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index ce33eee9d0f2..53bcc17c91e4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3593,20 +3593,28 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, __tcp_sock_set_quickack(sk, val); break; + case TCP_AO_REPAIR: + err = tcp_ao_set_repair(sk, optval, optlen); + break; #ifdef CONFIG_TCP_AO case TCP_AO_ADD_KEY: case TCP_AO_DEL_KEY: case TCP_AO_INFO: { /* If this is the first TCP-AO setsockopt() on the socket, - * sk_state has to be LISTEN or CLOSE + * sk_state has to be LISTEN or CLOSE. Allow TCP_REPAIR + * in any state. */ - if (((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) || - rcu_dereference_protected(tcp_sk(sk)->ao_info, + if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) + goto ao_parse; + if (rcu_dereference_protected(tcp_sk(sk)->ao_info, lockdep_sock_is_held(sk))) - err = tp->af_specific->ao_parse(sk, optname, optval, - optlen); - else - err = -EISCONN; + goto ao_parse; + if (tp->repair) + goto ao_parse; + err = -EISCONN; + break; +ao_parse: + err = tp->af_specific->ao_parse(sk, optname, optval, optlen); break; } #endif @@ -4284,6 +4292,8 @@ zerocopy_rcv_out: return err; } #endif + case TCP_AO_REPAIR: + return tcp_ao_get_repair(sk, optval, optlen); case TCP_AO_GET_KEYS: case TCP_AO_INFO: { int err; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index b5ac3e73e1da..6a845e906a1d 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -1490,6 +1490,16 @@ static struct tcp_ao_info *setsockopt_ao_info(struct sock *sk) return ERR_PTR(-ESOCKTNOSUPPORT); } +static struct tcp_ao_info *getsockopt_ao_info(struct sock *sk) +{ + if (sk_fullsock(sk)) + return rcu_dereference(tcp_sk(sk)->ao_info); + else if (sk->sk_state == TCP_TIME_WAIT) + return rcu_dereference(tcp_twsk(sk)->ao_info); + + return ERR_PTR(-ESOCKTNOSUPPORT); +} + #define TCP_AO_KEYF_ALL (TCP_AO_KEYF_IFINDEX | TCP_AO_KEYF_EXCLUDE_OPT) #define TCP_AO_GET_KEYF_VALID (TCP_AO_KEYF_IFINDEX) @@ -1671,11 +1681,13 @@ static int tcp_ao_add_cmd(struct sock *sk, unsigned short int family, if (ret < 0) goto err_free_sock; - /* Change this condition if we allow adding keys in states - * like close_wait, syn_sent or fin_wait... - */ - if (sk->sk_state == TCP_ESTABLISHED) + if (!((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) { tcp_ao_cache_traffic_keys(sk, ao_info, key); + if (first) { + ao_info->current_key = key; + ao_info->rnext_key = key; + } + } tcp_ao_link_mkt(ao_info, key); if (first) { @@ -1926,6 +1938,8 @@ static int tcp_ao_info_cmd(struct sock *sk, unsigned short int family, if (IS_ERR(ao_info)) return PTR_ERR(ao_info); if (!ao_info) { + if (!((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) + return -EINVAL; ao_info = tcp_ao_alloc_info(GFP_KERNEL); if (!ao_info) return -ENOMEM; @@ -2308,3 +2322,71 @@ int tcp_ao_get_sock_info(struct sock *sk, sockptr_t optval, sockptr_t optlen) return 0; } +int tcp_ao_set_repair(struct sock *sk, sockptr_t optval, unsigned int optlen) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_ao_repair cmd; + struct tcp_ao_key *key; + struct tcp_ao_info *ao; + int err; + + if (optlen < sizeof(cmd)) + return -EINVAL; + + err = copy_struct_from_sockptr(&cmd, sizeof(cmd), optval, optlen); + if (err) + return err; + + if (!tp->repair) + return -EPERM; + + ao = setsockopt_ao_info(sk); + if (IS_ERR(ao)) + return PTR_ERR(ao); + if (!ao) + return -ENOENT; + + WRITE_ONCE(ao->lisn, cmd.snt_isn); + WRITE_ONCE(ao->risn, cmd.rcv_isn); + WRITE_ONCE(ao->snd_sne, cmd.snd_sne); + WRITE_ONCE(ao->rcv_sne, cmd.rcv_sne); + + hlist_for_each_entry_rcu(key, &ao->head, node) + tcp_ao_cache_traffic_keys(sk, ao, key); + + return 0; +} + +int tcp_ao_get_repair(struct sock *sk, sockptr_t optval, sockptr_t optlen) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_ao_repair opt; + struct tcp_ao_info *ao; + int len; + + if (copy_from_sockptr(&len, optlen, sizeof(int))) + return -EFAULT; + + if (len <= 0) + return -EINVAL; + + if (!tp->repair) + return -EPERM; + + rcu_read_lock(); + ao = getsockopt_ao_info(sk); + if (IS_ERR_OR_NULL(ao)) { + rcu_read_unlock(); + return ao ? PTR_ERR(ao) : -ENOENT; + } + + opt.snt_isn = ao->lisn; + opt.rcv_isn = ao->risn; + opt.snd_sne = READ_ONCE(ao->snd_sne); + opt.rcv_sne = READ_ONCE(ao->rcv_sne); + rcu_read_unlock(); + + if (copy_to_sockptr(optval, &opt, min_t(int, len, sizeof(opt)))) + return -EFAULT; + return 0; +} -- cgit From 83c1bbeb864f2a197603b91b3e0f748cca64543d Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 25 Oct 2023 15:30:14 +0300 Subject: bridge: add MDB get uAPI attributes Add MDB get attributes that correspond to the MDB set attributes used in RTM_NEWMDB messages. Specifically, add 'MDBA_GET_ENTRY' which will hold a 'struct br_mdb_entry' and 'MDBA_GET_ENTRY_ATTRS' which will hold 'MDBE_ATTR_*' attributes that are used as indexes (source IP and source VNI). An example request will look as follows: [ struct nlmsghdr ] [ struct br_port_msg ] [ MDBA_GET_ENTRY ] struct br_mdb_entry [ MDBA_GET_ENTRY_ATTRS ] [ MDBE_ATTR_SOURCE ] struct in_addr / struct in6_addr [ MDBE_ATTR_SRC_VNI ] u32 Signed-off-by: Ido Schimmel Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index f95326fce6bb..2e23f99dc0f1 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -723,6 +723,24 @@ enum { }; #define MDBA_SET_ENTRY_MAX (__MDBA_SET_ENTRY_MAX - 1) +/* [MDBA_GET_ENTRY] = { + * struct br_mdb_entry + * [MDBA_GET_ENTRY_ATTRS] = { + * [MDBE_ATTR_SOURCE] + * struct in_addr / struct in6_addr + * [MDBE_ATTR_SRC_VNI] + * u32 + * } + * } + */ +enum { + MDBA_GET_ENTRY_UNSPEC, + MDBA_GET_ENTRY, + MDBA_GET_ENTRY_ATTRS, + __MDBA_GET_ENTRY_MAX, +}; +#define MDBA_GET_ENTRY_MAX (__MDBA_GET_ENTRY_MAX - 1) + /* [MDBA_SET_ENTRY_ATTRS] = { * [MDBE_ATTR_xxx] * ... -- cgit From 4b057654ebc3e071e2a95ea2edfd15b5682cedba Mon Sep 17 00:00:00 2001 From: Dimitri John Ledkov Date: Sun, 22 Oct 2023 19:22:04 +0100 Subject: crypto: FIPS 202 SHA-3 register in hash info for IMA Register FIPS 202 SHA-3 hashes in hash info for IMA and other users. Sizes 256 and up, as 224 is too weak for any practical purposes. Signed-off-by: Dimitri John Ledkov Signed-off-by: Herbert Xu --- crypto/hash_info.c | 6 ++++++ include/crypto/hash_info.h | 1 + include/uapi/linux/hash_info.h | 3 +++ 3 files changed, 10 insertions(+) (limited to 'include/uapi/linux') diff --git a/crypto/hash_info.c b/crypto/hash_info.c index a49ff96bde77..9a467638c971 100644 --- a/crypto/hash_info.c +++ b/crypto/hash_info.c @@ -29,6 +29,9 @@ const char *const hash_algo_name[HASH_ALGO__LAST] = { [HASH_ALGO_SM3_256] = "sm3", [HASH_ALGO_STREEBOG_256] = "streebog256", [HASH_ALGO_STREEBOG_512] = "streebog512", + [HASH_ALGO_SHA3_256] = "sha3-256", + [HASH_ALGO_SHA3_384] = "sha3-384", + [HASH_ALGO_SHA3_512] = "sha3-512", }; EXPORT_SYMBOL_GPL(hash_algo_name); @@ -53,5 +56,8 @@ const int hash_digest_size[HASH_ALGO__LAST] = { [HASH_ALGO_SM3_256] = SM3256_DIGEST_SIZE, [HASH_ALGO_STREEBOG_256] = STREEBOG256_DIGEST_SIZE, [HASH_ALGO_STREEBOG_512] = STREEBOG512_DIGEST_SIZE, + [HASH_ALGO_SHA3_256] = SHA3_256_DIGEST_SIZE, + [HASH_ALGO_SHA3_384] = SHA3_384_DIGEST_SIZE, + [HASH_ALGO_SHA3_512] = SHA3_512_DIGEST_SIZE, }; EXPORT_SYMBOL_GPL(hash_digest_size); diff --git a/include/crypto/hash_info.h b/include/crypto/hash_info.h index dd4f06785049..d6927739f8b2 100644 --- a/include/crypto/hash_info.h +++ b/include/crypto/hash_info.h @@ -10,6 +10,7 @@ #include #include +#include #include #include diff --git a/include/uapi/linux/hash_info.h b/include/uapi/linux/hash_info.h index 74a8609fcb4d..0af23ec196d8 100644 --- a/include/uapi/linux/hash_info.h +++ b/include/uapi/linux/hash_info.h @@ -35,6 +35,9 @@ enum hash_algo { HASH_ALGO_SM3_256, HASH_ALGO_STREEBOG_256, HASH_ALGO_STREEBOG_512, + HASH_ALGO_SHA3_256, + HASH_ALGO_SHA3_384, + HASH_ALGO_SHA3_512, HASH_ALGO__LAST }; -- cgit From c3a383d8d382e066038ab245c8d2b6d02f4bf8a2 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 26 Oct 2023 22:01:14 +0200 Subject: usb: raw-gadget: report suspend, resume, reset, and disconnect events Update USB_RAW_IOCTL_EVENT_FETCH to also report suspend, resume, reset, and disconnect events. This allows the code that emulates a USB device via Raw Gadget to handle these events. For example, the device can restart enumeration when it gets reset. Also do not print a WARNING when the event queue overflows. With these new events being queued, the queue might overflow if the device emulation code stops fetching events. Also print debug messages when a non-control event is received. Signed-off-by: Andrey Konovalov Link: https://lore.kernel.org/r/d610b629a5f32fb76c24012180743f7f0f1872c0.1698350424.git.andreyknvl@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/legacy/raw_gadget.c | 52 ++++++++++++++++++++++++++++------ include/uapi/linux/usb/raw_gadget.h | 14 +++++++-- 2 files changed, 56 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/usb/gadget/legacy/raw_gadget.c b/drivers/usb/gadget/legacy/raw_gadget.c index daac1f078516..399fca32a8ac 100644 --- a/drivers/usb/gadget/legacy/raw_gadget.c +++ b/drivers/usb/gadget/legacy/raw_gadget.c @@ -65,7 +65,7 @@ static int raw_event_queue_add(struct raw_event_queue *queue, struct usb_raw_event *event; spin_lock_irqsave(&queue->lock, flags); - if (WARN_ON(queue->size >= RAW_EVENT_QUEUE_SIZE)) { + if (queue->size >= RAW_EVENT_QUEUE_SIZE) { spin_unlock_irqrestore(&queue->lock, flags); return -ENOMEM; } @@ -311,9 +311,10 @@ static int gadget_bind(struct usb_gadget *gadget, dev->eps_num = i; spin_unlock_irqrestore(&dev->lock, flags); + dev_dbg(&gadget->dev, "gadget connected\n"); ret = raw_queue_event(dev, USB_RAW_EVENT_CONNECT, 0, NULL); if (ret < 0) { - dev_err(&gadget->dev, "failed to queue event\n"); + dev_err(&gadget->dev, "failed to queue connect event\n"); set_gadget_data(gadget, NULL); return ret; } @@ -358,7 +359,7 @@ static int gadget_setup(struct usb_gadget *gadget, ret = raw_queue_event(dev, USB_RAW_EVENT_CONTROL, sizeof(*ctrl), ctrl); if (ret < 0) - dev_err(&gadget->dev, "failed to queue event\n"); + dev_err(&gadget->dev, "failed to queue control event\n"); goto out; out_unlock: @@ -377,11 +378,46 @@ out: return ret; } -/* These are currently unused but present in case UDC driver requires them. */ -static void gadget_disconnect(struct usb_gadget *gadget) { } -static void gadget_suspend(struct usb_gadget *gadget) { } -static void gadget_resume(struct usb_gadget *gadget) { } -static void gadget_reset(struct usb_gadget *gadget) { } +static void gadget_disconnect(struct usb_gadget *gadget) +{ + struct raw_dev *dev = get_gadget_data(gadget); + int ret; + + dev_dbg(&gadget->dev, "gadget disconnected\n"); + ret = raw_queue_event(dev, USB_RAW_EVENT_DISCONNECT, 0, NULL); + if (ret < 0) + dev_err(&gadget->dev, "failed to queue disconnect event\n"); +} +static void gadget_suspend(struct usb_gadget *gadget) +{ + struct raw_dev *dev = get_gadget_data(gadget); + int ret; + + dev_dbg(&gadget->dev, "gadget suspended\n"); + ret = raw_queue_event(dev, USB_RAW_EVENT_SUSPEND, 0, NULL); + if (ret < 0) + dev_err(&gadget->dev, "failed to queue suspend event\n"); +} +static void gadget_resume(struct usb_gadget *gadget) +{ + struct raw_dev *dev = get_gadget_data(gadget); + int ret; + + dev_dbg(&gadget->dev, "gadget resumed\n"); + ret = raw_queue_event(dev, USB_RAW_EVENT_RESUME, 0, NULL); + if (ret < 0) + dev_err(&gadget->dev, "failed to queue resume event\n"); +} +static void gadget_reset(struct usb_gadget *gadget) +{ + struct raw_dev *dev = get_gadget_data(gadget); + int ret; + + dev_dbg(&gadget->dev, "gadget reset\n"); + ret = raw_queue_event(dev, USB_RAW_EVENT_RESET, 0, NULL); + if (ret < 0) + dev_err(&gadget->dev, "failed to queue reset event\n"); +} /*----------------------------------------------------------------------*/ diff --git a/include/uapi/linux/usb/raw_gadget.h b/include/uapi/linux/usb/raw_gadget.h index c7d2199134d7..f0224a8dc858 100644 --- a/include/uapi/linux/usb/raw_gadget.h +++ b/include/uapi/linux/usb/raw_gadget.h @@ -44,6 +44,16 @@ enum usb_raw_event_type { /* This event is queued when a new control request arrived to ep0. */ USB_RAW_EVENT_CONTROL = 2, + /* + * These events are queued when the gadget driver is suspended, + * resumed, reset, or disconnected. Note that some UDCs (e.g. dwc2) + * report a disconnect event instead of a reset. + */ + USB_RAW_EVENT_SUSPEND = 3, + USB_RAW_EVENT_RESUME = 4, + USB_RAW_EVENT_RESET = 5, + USB_RAW_EVENT_DISCONNECT = 6, + /* The list might grow in the future. */ }; @@ -54,8 +64,8 @@ enum usb_raw_event_type { * actual length of the fetched event data. * @data: A buffer to store the fetched event data. * - * Currently the fetched data buffer is empty for USB_RAW_EVENT_CONNECT, - * and contains struct usb_ctrlrequest for USB_RAW_EVENT_CONTROL. + * The fetched event data buffer contains struct usb_ctrlrequest for + * USB_RAW_EVENT_CONTROL and is empty for other events. */ struct usb_raw_event { __u32 type; -- cgit From 571d91dcadfa3cef499010b4eddb9b58b0da4d24 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Wed, 25 Oct 2023 13:16:19 -0700 Subject: perf: Add branch stack counters Currently, the additional information of a branch entry is stored in a u64 space. With more and more information added, the space is running out. For example, the information of occurrences of events will be added for each branch. Two places were suggested to append the counters. https://lore.kernel.org/lkml/20230802215814.GH231007@hirez.programming.kicks-ass.net/ One place is right after the flags of each branch entry. It changes the existing struct perf_branch_entry. The later ARCH specific implementation has to be really careful to consistently pick the right struct. The other place is right after the entire struct perf_branch_stack. The disadvantage is that the pointer of the extra space has to be recorded. The common interface perf_sample_save_brstack() has to be updated. The latter is much straightforward, and should be easily understood and maintained. It is implemented in the patch. Add a new branch sample type, PERF_SAMPLE_BRANCH_COUNTERS, to indicate the event which is recorded in the branch info. The "u64 counters" may store the occurrences of several events. The information regarding the number of events/counters and the width of each counter should be exposed via sysfs as a reference for the perf tool. Define the branch_counter_nr and branch_counter_width ABI here. The support will be implemented later in the Intel-specific patch. Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20231025201626.3000228-1-kan.liang@linux.intel.com --- .../ABI/testing/sysfs-bus-event_source-devices-caps | 6 ++++++ arch/powerpc/perf/core-book3s.c | 2 +- arch/x86/events/amd/core.c | 2 +- arch/x86/events/core.c | 2 +- arch/x86/events/intel/core.c | 2 +- arch/x86/events/intel/ds.c | 4 ++-- include/linux/perf_event.h | 17 ++++++++++++++++- include/uapi/linux/perf_event.h | 10 ++++++++++ kernel/events/core.c | 8 ++++++++ 9 files changed, 46 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-caps b/Documentation/ABI/testing/sysfs-bus-event_source-devices-caps index 8757dcf41c08..a5f506f7d481 100644 --- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-caps +++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-caps @@ -16,3 +16,9 @@ Description: Example output in powerpc: grep . /sys/bus/event_source/devices/cpu/caps/* /sys/bus/event_source/devices/cpu/caps/pmu_name:POWER9 + + The "branch_counter_nr" in the supported platform exposes the + maximum number of counters which can be shown in the u64 counters + of PERF_SAMPLE_BRANCH_COUNTERS, while the "branch_counter_width" + exposes the width of each counter. Both of them can be used by + the perf tool to parse the logged counters in each branch. diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 8c1f7def596e..3c14596bbfaf 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2313,7 +2313,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, struct cpu_hw_events *cpuhw; cpuhw = this_cpu_ptr(&cpu_hw_events); power_pmu_bhrb_read(event, cpuhw); - perf_sample_save_brstack(&data, event, &cpuhw->bhrb_stack); + perf_sample_save_brstack(&data, event, &cpuhw->bhrb_stack, NULL); } if (event->attr.sample_type & PERF_SAMPLE_DATA_SRC && diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index e24976593a29..4ee6390b45c9 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -940,7 +940,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) continue; if (has_branch_stack(event)) - perf_sample_save_brstack(&data, event, &cpuc->lbr_stack); + perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 40ad1425ffa2..40c9af124128 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1702,7 +1702,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs) perf_sample_data_init(&data, 0, event->hw.last_period); if (has_branch_stack(event)) - perf_sample_save_brstack(&data, event, &cpuc->lbr_stack); + perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index a08f794a0e79..41a164764a84 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3047,7 +3047,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) perf_sample_data_init(&data, 0, event->hw.last_period); if (has_branch_stack(event)) - perf_sample_save_brstack(&data, event, &cpuc->lbr_stack); + perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index bf97ab904d40..cb3f329f8fa4 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1755,7 +1755,7 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, setup_pebs_time(event, data, pebs->tsc); if (has_branch_stack(event)) - perf_sample_save_brstack(data, event, &cpuc->lbr_stack); + perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL); } static void adaptive_pebs_save_regs(struct pt_regs *regs, @@ -1912,7 +1912,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, if (has_branch_stack(event)) { intel_pmu_store_pebs_lbrs(lbr); - perf_sample_save_brstack(data, event, &cpuc->lbr_stack); + perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL); } } diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0367d748fae0..7897ef066027 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1139,6 +1139,10 @@ static inline bool branch_sample_priv(const struct perf_event *event) return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE; } +static inline bool branch_sample_counters(const struct perf_event *event) +{ + return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS; +} struct perf_sample_data { /* @@ -1173,6 +1177,7 @@ struct perf_sample_data { struct perf_callchain_entry *callchain; struct perf_raw_record *raw; struct perf_branch_stack *br_stack; + u64 *br_stack_cntr; union perf_sample_weight weight; union perf_mem_data_src data_src; u64 txn; @@ -1250,7 +1255,8 @@ static inline void perf_sample_save_raw_data(struct perf_sample_data *data, static inline void perf_sample_save_brstack(struct perf_sample_data *data, struct perf_event *event, - struct perf_branch_stack *brs) + struct perf_branch_stack *brs, + u64 *brs_cntr) { int size = sizeof(u64); /* nr */ @@ -1258,7 +1264,16 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data, size += sizeof(u64); size += brs->nr * sizeof(struct perf_branch_entry); + /* + * The extension space for counters is appended after the + * struct perf_branch_stack. It is used to store the occurrences + * of events of each branch. + */ + if (brs_cntr) + size += brs->nr * sizeof(u64); + data->br_stack = brs; + data->br_stack_cntr = brs_cntr; data->dyn_size += size; data->sample_flags |= PERF_SAMPLE_BRANCH_STACK; } diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 39c6a250dd1b..4461f380425b 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -204,6 +204,8 @@ enum perf_branch_sample_type_shift { PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT = 18, /* save privilege mode */ + PERF_SAMPLE_BRANCH_COUNTERS_SHIFT = 19, /* save occurrences of events on a branch */ + PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */ }; @@ -235,6 +237,8 @@ enum perf_branch_sample_type { PERF_SAMPLE_BRANCH_PRIV_SAVE = 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT, + PERF_SAMPLE_BRANCH_COUNTERS = 1U << PERF_SAMPLE_BRANCH_COUNTERS_SHIFT, + PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, }; @@ -982,6 +986,12 @@ enum perf_event_type { * { u64 nr; * { u64 hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX * { u64 from, to, flags } lbr[nr]; + * # + * # The format of the counters is decided by the + * # "branch_counter_nr" and "branch_counter_width", + * # which are defined in the ABI. + * # + * { u64 counters; } cntr[nr] && PERF_SAMPLE_BRANCH_COUNTERS * } && PERF_SAMPLE_BRANCH_STACK * * { u64 abi; # enum perf_sample_regs_abi diff --git a/kernel/events/core.c b/kernel/events/core.c index 3eb26c2c6e65..d27ffd80ed67 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7341,6 +7341,14 @@ void perf_output_sample(struct perf_output_handle *handle, if (branch_sample_hw_index(event)) perf_output_put(handle, data->br_stack->hw_idx); perf_output_copy(handle, data->br_stack->entries, size); + /* + * Add the extension space which is appended + * right after the struct perf_branch_stack. + */ + if (data->br_stack_cntr) { + size = data->br_stack->nr * sizeof(u64); + perf_output_copy(handle, data->br_stack_cntr, size); + } } else { /* * we always store at least the value of nr -- cgit From 33744916196b4ed7a50f6f47af7c3ad46b730ce6 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Wed, 25 Oct 2023 13:16:23 -0700 Subject: perf/x86/intel: Support branch counters logging The branch counters logging (A.K.A LBR event logging) introduces a per-counter indication of precise event occurrences in LBRs. It can provide a means to attribute exposed retirement latency to combinations of events across a block of instructions. It also provides a means of attributing Timed LBR latencies to events. The feature is first introduced on SRF/GRR. It is an enhancement of the ARCH LBR. It adds new fields in the LBR_INFO MSRs to log the occurrences of events on the GP counters. The information is displayed by the order of counters. The design proposed in this patch requires that the events which are logged must be in a group with the event that has LBR. If there are more than one LBR group, the counters logging information only from the current group (overflowed) are stored for the perf tool, otherwise the perf tool cannot know which and when other groups are scheduled especially when multiplexing is triggered. The user can ensure it uses the maximum number of counters that support LBR info (4 by now) by making the group large enough. The HW only logs events by the order of counters. The order may be different from the order of enabling which the perf tool can understand. When parsing the information of each branch entry, convert the counter order to the enabled order, and store the enabled order in the extension space. Unconditionally reset LBRs for an LBR event group when it's deleted. The logged counter information is only valid for the current LBR group. If another LBR group is scheduled later, the information from the stale LBRs would be otherwise wrongly interpreted. Add a sanity check in intel_pmu_hw_config(). Disable the feature if other counter filters (inv, cmask, edge, in_tx) are set or LBR call stack mode is enabled. (For the LBR call stack mode, we cannot simply flush the LBR, since it will break the call stack. Also, there is no obvious usage with the call stack mode for now.) Only applying the PERF_SAMPLE_BRANCH_COUNTERS doesn't require any branch stack setup. Expose the maximum number of supported counters and the width of the counters into the sysfs. The perf tool can use the information to parse the logged counters in each branch. Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20231025201626.3000228-5-kan.liang@linux.intel.com --- arch/x86/events/intel/core.c | 103 ++++++++++++++++++++++++++++++++++--- arch/x86/events/intel/ds.c | 2 +- arch/x86/events/intel/lbr.c | 85 +++++++++++++++++++++++++++++- arch/x86/events/perf_event.h | 12 +++++ arch/x86/events/perf_event_flags.h | 1 + arch/x86/include/asm/msr-index.h | 5 ++ arch/x86/include/asm/perf_event.h | 4 ++ include/uapi/linux/perf_event.h | 3 ++ 8 files changed, 207 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 584b58df7bf6..e068a96aeb54 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2792,6 +2792,7 @@ static void intel_pmu_enable_fixed(struct perf_event *event) static void intel_pmu_enable_event(struct perf_event *event) { + u64 enable_mask = ARCH_PERFMON_EVENTSEL_ENABLE; struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; @@ -2800,8 +2801,10 @@ static void intel_pmu_enable_event(struct perf_event *event) switch (idx) { case 0 ... INTEL_PMC_IDX_FIXED - 1: + if (branch_sample_counters(event)) + enable_mask |= ARCH_PERFMON_EVENTSEL_BR_CNTR; intel_set_masks(event, idx); - __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE); + __x86_pmu_enable_event(hwc, enable_mask); break; case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1: case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END: @@ -3052,7 +3055,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) perf_sample_data_init(&data, 0, event->hw.last_period); if (has_branch_stack(event)) - perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); + intel_pmu_lbr_save_brstack(&data, cpuc, event); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); @@ -3617,6 +3620,13 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, if (cpuc->excl_cntrs) return intel_get_excl_constraints(cpuc, event, idx, c2); + /* Not all counters support the branch counter feature. */ + if (branch_sample_counters(event)) { + c2 = dyn_constraint(cpuc, c2, idx); + c2->idxmsk64 &= x86_pmu.lbr_counters; + c2->weight = hweight64(c2->idxmsk64); + } + return c2; } @@ -3905,6 +3915,58 @@ static int intel_pmu_hw_config(struct perf_event *event) if (needs_branch_stack(event) && is_sampling_event(event)) event->hw.flags |= PERF_X86_EVENT_NEEDS_BRANCH_STACK; + if (branch_sample_counters(event)) { + struct perf_event *leader, *sibling; + int num = 0; + + if (!(x86_pmu.flags & PMU_FL_BR_CNTR) || + (event->attr.config & ~INTEL_ARCH_EVENT_MASK)) + return -EINVAL; + + /* + * The branch counter logging is not supported in the call stack + * mode yet, since we cannot simply flush the LBR during e.g., + * multiplexing. Also, there is no obvious usage with the call + * stack mode. Simply forbids it for now. + * + * If any events in the group enable the branch counter logging + * feature, the group is treated as a branch counter logging + * group, which requires the extra space to store the counters. + */ + leader = event->group_leader; + if (branch_sample_call_stack(leader)) + return -EINVAL; + if (branch_sample_counters(leader)) + num++; + leader->hw.flags |= PERF_X86_EVENT_BRANCH_COUNTERS; + + for_each_sibling_event(sibling, leader) { + if (branch_sample_call_stack(sibling)) + return -EINVAL; + if (branch_sample_counters(sibling)) + num++; + } + + if (num > fls(x86_pmu.lbr_counters)) + return -EINVAL; + /* + * Only applying the PERF_SAMPLE_BRANCH_COUNTERS doesn't + * require any branch stack setup. + * Clear the bit to avoid unnecessary branch stack setup. + */ + if (0 == (event->attr.branch_sample_type & + ~(PERF_SAMPLE_BRANCH_PLM_ALL | + PERF_SAMPLE_BRANCH_COUNTERS))) + event->hw.flags &= ~PERF_X86_EVENT_NEEDS_BRANCH_STACK; + + /* + * Force the leader to be a LBR event. So LBRs can be reset + * with the leader event. See intel_pmu_lbr_del() for details. + */ + if (!intel_pmu_needs_branch_stack(leader)) + return -EINVAL; + } + if (intel_pmu_needs_branch_stack(event)) { ret = intel_pmu_setup_lbr_filter(event); if (ret) @@ -4383,8 +4445,13 @@ cmt_get_event_constraints(struct cpu_hw_events *cpuc, int idx, */ if (event->attr.precise_ip == 3) { /* Force instruction:ppp on PMC0, 1 and Fixed counter 0 */ - if (constraint_match(&fixed0_constraint, event->hw.config)) - return &fixed0_counter0_1_constraint; + if (constraint_match(&fixed0_constraint, event->hw.config)) { + /* The fixed counter 0 doesn't support LBR event logging. */ + if (branch_sample_counters(event)) + return &counter0_1_constraint; + else + return &fixed0_counter0_1_constraint; + } switch (c->idxmsk64 & 0x3ull) { case 0x1: @@ -4563,7 +4630,7 @@ int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu) goto err; } - if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA)) { + if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA | PMU_FL_BR_CNTR)) { size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint); cpuc->constraint_list = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu)); @@ -5535,15 +5602,39 @@ static ssize_t branches_show(struct device *cdev, static DEVICE_ATTR_RO(branches); +static ssize_t branch_counter_nr_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%d\n", fls(x86_pmu.lbr_counters)); +} + +static DEVICE_ATTR_RO(branch_counter_nr); + +static ssize_t branch_counter_width_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%d\n", LBR_INFO_BR_CNTR_BITS); +} + +static DEVICE_ATTR_RO(branch_counter_width); + static struct attribute *lbr_attrs[] = { &dev_attr_branches.attr, + &dev_attr_branch_counter_nr.attr, + &dev_attr_branch_counter_width.attr, NULL }; static umode_t lbr_is_visible(struct kobject *kobj, struct attribute *attr, int i) { - return x86_pmu.lbr_nr ? attr->mode : 0; + /* branches */ + if (i == 0) + return x86_pmu.lbr_nr ? attr->mode : 0; + + return (x86_pmu.flags & PMU_FL_BR_CNTR) ? attr->mode : 0; } static char pmu_name_str[30]; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index cb3f329f8fa4..d49d661ec0a7 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1912,7 +1912,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, if (has_branch_stack(event)) { intel_pmu_store_pebs_lbrs(lbr); - perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL); + intel_pmu_lbr_save_brstack(data, cpuc, event); } } diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index c3b0d15a9841..78cd5084104e 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -676,6 +676,25 @@ void intel_pmu_lbr_del(struct perf_event *event) WARN_ON_ONCE(cpuc->lbr_users < 0); WARN_ON_ONCE(cpuc->lbr_pebs_users < 0); perf_sched_cb_dec(event->pmu); + + /* + * The logged occurrences information is only valid for the + * current LBR group. If another LBR group is scheduled in + * later, the information from the stale LBRs will be wrongly + * interpreted. Reset the LBRs here. + * + * Only clear once for a branch counter group with the leader + * event. Because + * - Cannot simply reset the LBRs with the !cpuc->lbr_users. + * Because it's possible that the last LBR user is not in a + * branch counter group, e.g., a branch_counters group + + * several normal LBR events. + * - The LBR reset can be done with any one of the events in a + * branch counter group, since they are always scheduled together. + * It's easy to force the leader event an LBR event. + */ + if (is_branch_counters_group(event) && event == event->group_leader) + intel_pmu_lbr_reset(); } static inline bool vlbr_exclude_host(void) @@ -866,6 +885,8 @@ static __always_inline u16 get_lbr_cycles(u64 info) return cycles; } +static_assert((64 - PERF_BRANCH_ENTRY_INFO_BITS_MAX) > LBR_INFO_BR_CNTR_NUM * LBR_INFO_BR_CNTR_BITS); + static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc, struct lbr_entry *entries) { @@ -898,11 +919,67 @@ static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc, e->abort = !!(info & LBR_INFO_ABORT); e->cycles = get_lbr_cycles(info); e->type = get_lbr_br_type(info); + + /* + * Leverage the reserved field of cpuc->lbr_entries[i] to + * temporarily store the branch counters information. + * The later code will decide what content can be disclosed + * to the perf tool. Pleae see intel_pmu_lbr_counters_reorder(). + */ + e->reserved = (info >> LBR_INFO_BR_CNTR_OFFSET) & LBR_INFO_BR_CNTR_FULL_MASK; } cpuc->lbr_stack.nr = i; } +/* + * The enabled order may be different from the counter order. + * Update the lbr_counters with the enabled order. + */ +static void intel_pmu_lbr_counters_reorder(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + int i, j, pos = 0, order[X86_PMC_IDX_MAX]; + struct perf_event *leader, *sibling; + u64 src, dst, cnt; + + leader = event->group_leader; + if (branch_sample_counters(leader)) + order[pos++] = leader->hw.idx; + + for_each_sibling_event(sibling, leader) { + if (!branch_sample_counters(sibling)) + continue; + order[pos++] = sibling->hw.idx; + } + + WARN_ON_ONCE(!pos); + + for (i = 0; i < cpuc->lbr_stack.nr; i++) { + src = cpuc->lbr_entries[i].reserved; + dst = 0; + for (j = 0; j < pos; j++) { + cnt = (src >> (order[j] * LBR_INFO_BR_CNTR_BITS)) & LBR_INFO_BR_CNTR_MASK; + dst |= cnt << j * LBR_INFO_BR_CNTR_BITS; + } + cpuc->lbr_counters[i] = dst; + cpuc->lbr_entries[i].reserved = 0; + } +} + +void intel_pmu_lbr_save_brstack(struct perf_sample_data *data, + struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + if (is_branch_counters_group(event)) { + intel_pmu_lbr_counters_reorder(cpuc, event); + perf_sample_save_brstack(data, event, &cpuc->lbr_stack, cpuc->lbr_counters); + return; + } + + perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL); +} + static void intel_pmu_arch_lbr_read(struct cpu_hw_events *cpuc) { intel_pmu_store_lbr(cpuc, NULL); @@ -1173,8 +1250,10 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc) for (i = 0; i < cpuc->lbr_stack.nr; ) { if (!cpuc->lbr_entries[i].from) { j = i; - while (++j < cpuc->lbr_stack.nr) + while (++j < cpuc->lbr_stack.nr) { cpuc->lbr_entries[j-1] = cpuc->lbr_entries[j]; + cpuc->lbr_counters[j-1] = cpuc->lbr_counters[j]; + } cpuc->lbr_stack.nr--; if (!cpuc->lbr_entries[i].from) continue; @@ -1525,8 +1604,12 @@ void __init intel_pmu_arch_lbr_init(void) x86_pmu.lbr_mispred = ecx.split.lbr_mispred; x86_pmu.lbr_timed_lbr = ecx.split.lbr_timed_lbr; x86_pmu.lbr_br_type = ecx.split.lbr_br_type; + x86_pmu.lbr_counters = ecx.split.lbr_counters; x86_pmu.lbr_nr = lbr_nr; + if (!!x86_pmu.lbr_counters) + x86_pmu.flags |= PMU_FL_BR_CNTR; + if (x86_pmu.lbr_mispred) static_branch_enable(&x86_lbr_mispred); if (x86_pmu.lbr_timed_lbr) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 53dd5d495ba6..fb56518356ec 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -110,6 +110,11 @@ static inline bool is_topdown_event(struct perf_event *event) return is_metric_event(event) || is_slots_event(event); } +static inline bool is_branch_counters_group(struct perf_event *event) +{ + return event->group_leader->hw.flags & PERF_X86_EVENT_BRANCH_COUNTERS; +} + struct amd_nb { int nb_id; /* NorthBridge id */ int refcnt; /* reference count */ @@ -283,6 +288,7 @@ struct cpu_hw_events { int lbr_pebs_users; struct perf_branch_stack lbr_stack; struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; + u64 lbr_counters[MAX_LBR_ENTRIES]; /* branch stack extra */ union { struct er_account *lbr_sel; struct er_account *lbr_ctl; @@ -888,6 +894,7 @@ struct x86_pmu { unsigned int lbr_mispred:1; unsigned int lbr_timed_lbr:1; unsigned int lbr_br_type:1; + unsigned int lbr_counters:4; void (*lbr_reset)(void); void (*lbr_read)(struct cpu_hw_events *cpuc); @@ -1012,6 +1019,7 @@ do { \ #define PMU_FL_INSTR_LATENCY 0x80 /* Support Instruction Latency in PEBS Memory Info Record */ #define PMU_FL_MEM_LOADS_AUX 0x100 /* Require an auxiliary event for the complete memory info */ #define PMU_FL_RETIRE_LATENCY 0x200 /* Support Retire Latency in PEBS */ +#define PMU_FL_BR_CNTR 0x400 /* Support branch counter logging */ #define EVENT_VAR(_id) event_attr_##_id #define EVENT_PTR(_id) &event_attr_##_id.attr.attr @@ -1552,6 +1560,10 @@ void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr); void intel_ds_init(void); +void intel_pmu_lbr_save_brstack(struct perf_sample_data *data, + struct cpu_hw_events *cpuc, + struct perf_event *event); + void intel_pmu_lbr_swap_task_ctx(struct perf_event_pmu_context *prev_epc, struct perf_event_pmu_context *next_epc); diff --git a/arch/x86/events/perf_event_flags.h b/arch/x86/events/perf_event_flags.h index a1685981c520..6c977c19f2cd 100644 --- a/arch/x86/events/perf_event_flags.h +++ b/arch/x86/events/perf_event_flags.h @@ -21,3 +21,4 @@ PERF_ARCH(PEBS_STLAT, 0x08000) /* st+stlat data address sampling */ PERF_ARCH(AMD_BRS, 0x10000) /* AMD Branch Sampling */ PERF_ARCH(PEBS_LAT_HYBRID, 0x20000) /* ld and st lat for hybrid */ PERF_ARCH(NEEDS_BRANCH_STACK, 0x40000) /* require branch stack setup */ +PERF_ARCH(BRANCH_COUNTERS, 0x80000) /* logs the counters in the extra space of each branch */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index f8b502867dd1..a5b0a19ccdf2 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -236,6 +236,11 @@ #define LBR_INFO_CYCLES 0xffff #define LBR_INFO_BR_TYPE_OFFSET 56 #define LBR_INFO_BR_TYPE (0xfull << LBR_INFO_BR_TYPE_OFFSET) +#define LBR_INFO_BR_CNTR_OFFSET 32 +#define LBR_INFO_BR_CNTR_NUM 4 +#define LBR_INFO_BR_CNTR_BITS 2 +#define LBR_INFO_BR_CNTR_MASK GENMASK_ULL(LBR_INFO_BR_CNTR_BITS - 1, 0) +#define LBR_INFO_BR_CNTR_FULL_MASK GENMASK_ULL(LBR_INFO_BR_CNTR_NUM * LBR_INFO_BR_CNTR_BITS - 1, 0) #define MSR_ARCH_LBR_CTL 0x000014ce #define ARCH_LBR_CTL_LBREN BIT(0) diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 2618ec7c3d1d..3736b8a46c04 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -31,6 +31,7 @@ #define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22) #define ARCH_PERFMON_EVENTSEL_INV (1ULL << 23) #define ARCH_PERFMON_EVENTSEL_CMASK 0xFF000000ULL +#define ARCH_PERFMON_EVENTSEL_BR_CNTR (1ULL << 35) #define INTEL_FIXED_BITS_MASK 0xFULL #define INTEL_FIXED_BITS_STRIDE 4 @@ -223,6 +224,9 @@ union cpuid28_ecx { unsigned int lbr_timed_lbr:1; /* Branch Type Field Supported */ unsigned int lbr_br_type:1; + unsigned int reserved:13; + /* Branch counters (Event Logging) Supported */ + unsigned int lbr_counters:4; } split; unsigned int full; }; diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 4461f380425b..3a64499b0f5d 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1437,6 +1437,9 @@ struct perf_branch_entry { reserved:31; }; +/* Size of used info bits in struct perf_branch_entry */ +#define PERF_BRANCH_ENTRY_INFO_BITS_MAX 33 + union perf_sample_weight { __u64 full; #if defined(__LITTLE_ENDIAN_BITFIELD) -- cgit From 6479c975b20a7fe6ecacec3a60dc6f838ecee9d6 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Fri, 27 Oct 2023 16:04:54 +0200 Subject: doc/netlink: Update schema to support cmd-cnt-name and cmd-max-name allow specifying cmd-cnt-name and cmd-max-name in netlink specs, in accordance with Documentation/userspace-api/netlink/c-code-gen.rst. Use cmd-cnt-name and attr-cnt-name in the mptcp yaml spec and in the corresponding uAPI headers, to preserve the #defines we had in the past and avoid adding new ones. v2: - squash modification in mptcp.yaml and MPTCP uAPI headers Suggested-by: Jakub Kicinski Signed-off-by: Davide Caratti Link: https://lore.kernel.org/r/12d4ed0116d8883cf4b533b856f3125a34e56749.1698415310.git.dcaratti@redhat.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/genetlink-c.yaml | 6 ++++++ Documentation/netlink/genetlink-legacy.yaml | 6 ++++++ Documentation/netlink/netlink-raw.yaml | 6 ++++++ Documentation/netlink/specs/mptcp.yaml | 2 ++ include/uapi/linux/mptcp.h | 4 ---- include/uapi/linux/mptcp_pm.h | 8 ++++---- 6 files changed, 24 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml index 9d13bbb7ae47..c58f7153fcf8 100644 --- a/Documentation/netlink/genetlink-c.yaml +++ b/Documentation/netlink/genetlink-c.yaml @@ -47,6 +47,12 @@ properties: max-by-define: description: Makes the number of attributes and commands be specified by a define, not an enum value. type: boolean + cmd-max-name: + description: Name of the define for the last operation in the list. + type: string + cmd-cnt-name: + description: The explicit name for constant holding the count of operations (last operation + 1). + type: string # End genetlink-c definitions: diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml index 0daf40402a29..938703088306 100644 --- a/Documentation/netlink/genetlink-legacy.yaml +++ b/Documentation/netlink/genetlink-legacy.yaml @@ -47,6 +47,12 @@ properties: max-by-define: description: Makes the number of attributes and commands be specified by a define, not an enum value. type: boolean + cmd-max-name: + description: Name of the define for the last operation in the list. + type: string + cmd-cnt-name: + description: The explicit name for constant holding the count of operations (last operation + 1). + type: string # End genetlink-c # Start genetlink-legacy kernel-policy: diff --git a/Documentation/netlink/netlink-raw.yaml b/Documentation/netlink/netlink-raw.yaml index 48db31f1d059..775cce8c548a 100644 --- a/Documentation/netlink/netlink-raw.yaml +++ b/Documentation/netlink/netlink-raw.yaml @@ -47,6 +47,12 @@ properties: max-by-define: description: Makes the number of attributes and commands be specified by a define, not an enum value. type: boolean + cmd-max-name: + description: Name of the define for the last operation in the list. + type: string + cmd-cnt-name: + description: The explicit name for constant holding the count of operations (last operation + 1). + type: string # End genetlink-c # Start genetlink-legacy kernel-policy: diff --git a/Documentation/netlink/specs/mptcp.yaml b/Documentation/netlink/specs/mptcp.yaml index ec5c454a87ea..49f90cfb4698 100644 --- a/Documentation/netlink/specs/mptcp.yaml +++ b/Documentation/netlink/specs/mptcp.yaml @@ -8,6 +8,7 @@ c-family-name: mptcp-pm-name c-version-name: mptcp-pm-ver max-by-define: true kernel-policy: per-op +cmd-cnt-name: --mptcp-pm-cmd-after-last definitions: - @@ -167,6 +168,7 @@ attribute-sets: - name: attr name-prefix: mptcp-pm-attr- + attr-cnt-name: --mptcp-attr-after-last attributes: - name: unspec diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 64ecc8a3f9f2..a6451561f3f8 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -28,10 +28,6 @@ #include -/* for backward compatibility */ -#define __MPTCP_PM_CMD_AFTER_LAST __MPTCP_PM_CMD_MAX -#define __MPTCP_ATTR_AFTER_LAST __MPTCP_ATTR_MAX - #define MPTCP_INFO_FLAG_FALLBACK _BITUL(0) #define MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED _BITUL(1) diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h index 0ad598fe940b..b5d11aece408 100644 --- a/include/uapi/linux/mptcp_pm.h +++ b/include/uapi/linux/mptcp_pm.h @@ -100,9 +100,9 @@ enum { MPTCP_PM_ATTR_LOC_ID, MPTCP_PM_ATTR_ADDR_REMOTE, - __MPTCP_PM_ATTR_MAX + __MPTCP_ATTR_AFTER_LAST }; -#define MPTCP_PM_ATTR_MAX (__MPTCP_PM_ATTR_MAX - 1) +#define MPTCP_PM_ATTR_MAX (__MPTCP_ATTR_AFTER_LAST - 1) enum mptcp_event_attr { MPTCP_ATTR_UNSPEC, @@ -143,8 +143,8 @@ enum { MPTCP_PM_CMD_SUBFLOW_CREATE, MPTCP_PM_CMD_SUBFLOW_DESTROY, - __MPTCP_PM_CMD_MAX + __MPTCP_PM_CMD_AFTER_LAST }; -#define MPTCP_PM_CMD_MAX (__MPTCP_PM_CMD_MAX - 1) +#define MPTCP_PM_CMD_MAX (__MPTCP_PM_CMD_AFTER_LAST - 1) #endif /* _UAPI_LINUX_MPTCP_PM_H */ -- cgit From 7db0d6027e69f47431800b510192436563ba415b Mon Sep 17 00:00:00 2001 From: Si-Wei Liu Date: Wed, 18 Oct 2023 20:14:42 +0300 Subject: vhost-vdpa: introduce descriptor group backend feature MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Userspace knows if the device has dedicated descriptor group or not by checking this feature bit. It's only exposed if the vdpa driver backend implements the .get_vq_desc_group() operation callback. Userspace trying to negotiate this feature when it or the dependent _F_IOTLB_ASID feature hasn't been exposed will result in an error. Signed-off-by: Si-Wei Liu Acked-by: Eugenio Pérez Acked-by: Jason Wang Message-Id: <20231018171456.1624030-5-dtatulea@nvidia.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Si-Wei Liu Tested-by: Si-Wei Liu Tested-by: Lei Yang --- drivers/vhost/vdpa.c | 17 +++++++++++++++++ include/uapi/linux/vhost_types.h | 5 +++++ 2 files changed, 22 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 78379ffd2336..2f21798a37ee 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -389,6 +389,14 @@ static bool vhost_vdpa_can_resume(const struct vhost_vdpa *v) return ops->resume; } +static bool vhost_vdpa_has_desc_group(const struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + return ops->get_vq_desc_group; +} + static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep) { struct vdpa_device *vdpa = v->vdpa; @@ -690,6 +698,7 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, if (copy_from_user(&features, featurep, sizeof(features))) return -EFAULT; if (features & ~(VHOST_VDPA_BACKEND_FEATURES | + BIT_ULL(VHOST_BACKEND_F_DESC_ASID) | BIT_ULL(VHOST_BACKEND_F_SUSPEND) | BIT_ULL(VHOST_BACKEND_F_RESUME) | BIT_ULL(VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK))) @@ -700,6 +709,12 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, if ((features & BIT_ULL(VHOST_BACKEND_F_RESUME)) && !vhost_vdpa_can_resume(v)) return -EOPNOTSUPP; + if ((features & BIT_ULL(VHOST_BACKEND_F_DESC_ASID)) && + !(features & BIT_ULL(VHOST_BACKEND_F_IOTLB_ASID))) + return -EINVAL; + if ((features & BIT_ULL(VHOST_BACKEND_F_DESC_ASID)) && + !vhost_vdpa_has_desc_group(v)) + return -EOPNOTSUPP; vhost_set_backend_features(&v->vdev, features); return 0; } @@ -753,6 +768,8 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, features |= BIT_ULL(VHOST_BACKEND_F_SUSPEND); if (vhost_vdpa_can_resume(v)) features |= BIT_ULL(VHOST_BACKEND_F_RESUME); + if (vhost_vdpa_has_desc_group(v)) + features |= BIT_ULL(VHOST_BACKEND_F_DESC_ASID); features |= vhost_vdpa_get_backend_features(v); if (copy_to_user(featurep, &features, sizeof(features))) r = -EFAULT; diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h index 2d827d22cd99..18ad6ae7ab5c 100644 --- a/include/uapi/linux/vhost_types.h +++ b/include/uapi/linux/vhost_types.h @@ -185,5 +185,10 @@ struct vhost_vdpa_iova_range { * DRIVER_OK */ #define VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK 0x6 +/* Device may expose the virtqueue's descriptor area, driver area and + * device area to a different group for ASID binding than where its + * buffers may reside. Requires VHOST_BACKEND_F_IOTLB_ASID. + */ +#define VHOST_BACKEND_F_DESC_ASID 0x7 #endif -- cgit From c8068d9bae0c78e8880451b94668253449b2d71d Mon Sep 17 00:00:00 2001 From: Si-Wei Liu Date: Wed, 18 Oct 2023 20:14:43 +0300 Subject: vhost-vdpa: uAPI to get dedicated descriptor group id MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With _F_DESC_ASID backend feature, the device can now support the VHOST_VDPA_GET_VRING_DESC_GROUP ioctl, and it may expose the descriptor table (including avail and used ring) in a different group than the buffers it contains. This new uAPI will fetch the group ID of the descriptor table. Signed-off-by: Si-Wei Liu Acked-by: Eugenio Pérez Acked-by: Jason Wang Message-Id: <20231018171456.1624030-6-dtatulea@nvidia.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Si-Wei Liu Tested-by: Si-Wei Liu Tested-by: Lei Yang --- drivers/vhost/vdpa.c | 10 ++++++++++ include/uapi/linux/vhost.h | 8 ++++++++ 2 files changed, 18 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 2f21798a37ee..851535f57b95 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -613,6 +613,16 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, else if (copy_to_user(argp, &s, sizeof(s))) return -EFAULT; return 0; + case VHOST_VDPA_GET_VRING_DESC_GROUP: + if (!vhost_vdpa_has_desc_group(v)) + return -EOPNOTSUPP; + s.index = idx; + s.num = ops->get_vq_desc_group(vdpa, idx); + if (s.num >= vdpa->ngroups) + return -EIO; + else if (copy_to_user(argp, &s, sizeof(s))) + return -EFAULT; + return 0; case VHOST_VDPA_SET_GROUP_ASID: if (copy_from_user(&s, argp, sizeof(s))) return -EFAULT; diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index f5c48b61ab62..649560c685f1 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -219,4 +219,12 @@ */ #define VHOST_VDPA_RESUME _IO(VHOST_VIRTIO, 0x7E) +/* Get the group for the descriptor table including driver & device areas + * of a virtqueue: read index, write group in num. + * The virtqueue index is stored in the index field of vhost_vring_state. + * The group ID of the descriptor table for this specific virtqueue + * is returned via num field of vhost_vring_state. + */ +#define VHOST_VDPA_GET_VRING_DESC_GROUP _IOWR(VHOST_VIRTIO, 0x7F, \ + struct vhost_vring_state) #endif -- cgit From 70e16c90ee23233bdd45462e1ebba72ff0c25c3a Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Tue, 10 Oct 2023 11:11:17 +0800 Subject: virtio: add definition of VIRTIO_F_NOTIF_CONFIG_DATA feature bit This patch adds the definition of VIRTIO_F_NOTIF_CONFIG_DATA feature bit in the relevant header file. This feature indicates that the driver uses the data provided by the device as a virtqueue identifier in available buffer notifications. It comes from here: https://github.com/oasis-tcs/virtio-spec/issues/89 Signed-off-by: Xuan Zhuo Message-Id: <20231010031120.81272-2-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- include/uapi/linux/virtio_config.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h index 2c712c654165..8881aea60f6f 100644 --- a/include/uapi/linux/virtio_config.h +++ b/include/uapi/linux/virtio_config.h @@ -105,6 +105,11 @@ */ #define VIRTIO_F_NOTIFICATION_DATA 38 +/* This feature indicates that the driver uses the data provided by the device + * as a virtqueue identifier in available buffer notifications. + */ +#define VIRTIO_F_NOTIF_CONFIG_DATA 39 + /* * This feature indicates that the driver can reset a queue individually. */ -- cgit From 4398776f7a6d532c466f9e41f601c9a291fac5ef Mon Sep 17 00:00:00 2001 From: Si-Wei Liu Date: Sat, 21 Oct 2023 02:25:15 -0700 Subject: vhost-vdpa: introduce IOTLB_PERSIST backend feature bit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Userspace needs this feature flag to distinguish if vhost-vdpa iotlb in the kernel can be trusted to persist IOTLB mapping across vDPA reset. Without it, userspace has no way to tell apart if it's running on an older kernel, which could silently drop all iotlb mapping across vDPA reset, especially with broken parent driver implementation for the .reset driver op. The broken driver may incorrectly drop all mappings of its own as part of .reset, which inadvertently ends up with corrupted mapping state between vhost-vdpa userspace and the kernel. As a workaround, to make the mapping behaviour predictable across reset, userspace has to pro-actively remove all mappings before vDPA reset, and then restore all the mappings afterwards. This workaround is done unconditionally on top of all parent drivers today, due to the parent driver implementation issue and no means to differentiate. This workaround had been utilized in QEMU since day one when the corresponding vhost-vdpa userspace backend came to the world. There are 3 cases that backend may claim this feature bit on for: - parent device that has to work with platform IOMMU - parent device with on-chip IOMMU that has the expected .reset_map support in driver - parent device with vendor specific IOMMU implementation with persistent IOTLB mapping already that has to specifically declare this backend feature The reason why .reset_map is being one of the pre-condition for persistent iotlb is because without it, vhost-vdpa can't switch back iotlb to the initial state later on, especially for the on-chip IOMMU case which starts with identity mapping at device creation. virtio-vdpa requires on-chip IOMMU to perform 1:1 passthrough translation from PA to IOVA as-is to begin with, and .reset_map is the only means to turn back iotlb to the identity mapping mode after vhost-vdpa is gone. The difference in behavior did not matter as QEMU unmaps all the memory unregistering the memory listener at vhost_vdpa_dev_start( started = false), but the backend acknowledging this feature flag allows QEMU to make sure it is safe to skip this unmap & map in the case of vhost stop & start cycle. In that sense, this feature flag is actually a signal for userspace to know that the driver bug has been solved. Not offering it indicates that userspace cannot trust the kernel will retain the maps. Signed-off-by: Si-Wei Liu Acked-by: Eugenio Pérez Message-Id: <1697880319-4937-4-git-send-email-si-wei.liu@oracle.com> Signed-off-by: Michael S. Tsirkin Tested-by: Lei Yang --- drivers/vhost/vdpa.c | 15 +++++++++++++++ include/uapi/linux/vhost_types.h | 2 ++ 2 files changed, 17 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index c6bfe9bdde42..acc7c74ba7d6 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -439,6 +439,15 @@ static u64 vhost_vdpa_get_backend_features(const struct vhost_vdpa *v) return ops->get_backend_features(vdpa); } +static bool vhost_vdpa_has_persistent_map(const struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + return (!ops->set_map && !ops->dma_map) || ops->reset_map || + vhost_vdpa_get_backend_features(v) & BIT_ULL(VHOST_BACKEND_F_IOTLB_PERSIST); +} + static long vhost_vdpa_set_features(struct vhost_vdpa *v, u64 __user *featurep) { struct vdpa_device *vdpa = v->vdpa; @@ -726,6 +735,7 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, return -EFAULT; if (features & ~(VHOST_VDPA_BACKEND_FEATURES | BIT_ULL(VHOST_BACKEND_F_DESC_ASID) | + BIT_ULL(VHOST_BACKEND_F_IOTLB_PERSIST) | BIT_ULL(VHOST_BACKEND_F_SUSPEND) | BIT_ULL(VHOST_BACKEND_F_RESUME) | BIT_ULL(VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK))) @@ -742,6 +752,9 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, if ((features & BIT_ULL(VHOST_BACKEND_F_DESC_ASID)) && !vhost_vdpa_has_desc_group(v)) return -EOPNOTSUPP; + if ((features & BIT_ULL(VHOST_BACKEND_F_IOTLB_PERSIST)) && + !vhost_vdpa_has_persistent_map(v)) + return -EOPNOTSUPP; vhost_set_backend_features(&v->vdev, features); return 0; } @@ -797,6 +810,8 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, features |= BIT_ULL(VHOST_BACKEND_F_RESUME); if (vhost_vdpa_has_desc_group(v)) features |= BIT_ULL(VHOST_BACKEND_F_DESC_ASID); + if (vhost_vdpa_has_persistent_map(v)) + features |= BIT_ULL(VHOST_BACKEND_F_IOTLB_PERSIST); features |= vhost_vdpa_get_backend_features(v); if (copy_to_user(featurep, &features, sizeof(features))) r = -EFAULT; diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h index 18ad6ae7ab5c..d7656908f730 100644 --- a/include/uapi/linux/vhost_types.h +++ b/include/uapi/linux/vhost_types.h @@ -190,5 +190,7 @@ struct vhost_vdpa_iova_range { * buffers may reside. Requires VHOST_BACKEND_F_IOTLB_ASID. */ #define VHOST_BACKEND_F_DESC_ASID 0x7 +/* IOTLB don't flush memory mapping across device reset */ +#define VHOST_BACKEND_F_IOTLB_PERSIST 0x8 #endif -- cgit From 3503895788d402d6a3814085ed582c364ec3e903 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 31 Oct 2023 12:02:06 -0400 Subject: virtio_pci: move structure to a header These are guest/host interfaces, so they belong in the header where e.g. qemu will know to find them. Note: we added a new structure as opposed to extending existing one because someone might be relying on the size of the existing structure staying unchanged. Add a warning to avoid using sizeof. Signed-off-by: Michael S. Tsirkin Reviewed-by: Xuan Zhuo --- drivers/virtio/virtio_pci_modern_dev.c | 7 ++++--- include/linux/virtio_pci_modern.h | 7 ------- include/uapi/linux/virtio_pci.h | 11 +++++++++++ 3 files changed, 15 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c index e2a1fe7bb66c..7de8b1ebabac 100644 --- a/drivers/virtio/virtio_pci_modern_dev.c +++ b/drivers/virtio/virtio_pci_modern_dev.c @@ -294,9 +294,10 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev) err = -EINVAL; mdev->common = vp_modern_map_capability(mdev, common, - sizeof(struct virtio_pci_common_cfg), 4, - 0, sizeof(struct virtio_pci_modern_common_cfg), - &mdev->common_len, NULL); + sizeof(struct virtio_pci_common_cfg), 4, 0, + offsetofend(struct virtio_pci_modern_common_cfg, + queue_reset), + &mdev->common_len, NULL); if (!mdev->common) goto err_map_common; mdev->isr = vp_modern_map_capability(mdev, isr, sizeof(u8), 1, diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h index d0f2797420f7..a09e13a577a9 100644 --- a/include/linux/virtio_pci_modern.h +++ b/include/linux/virtio_pci_modern.h @@ -5,13 +5,6 @@ #include #include -struct virtio_pci_modern_common_cfg { - struct virtio_pci_common_cfg cfg; - - __le16 queue_notify_data; /* read-write */ - __le16 queue_reset; /* read-write */ -}; - /** * struct virtio_pci_modern_device - info for modern PCI virtio * @pci_dev: Ptr to the PCI device struct diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index f703afc7ad31..44f4dd2add18 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -166,6 +166,17 @@ struct virtio_pci_common_cfg { __le32 queue_used_hi; /* read-write */ }; +/* + * Warning: do not use sizeof on this: use offsetofend for + * specific fields you need. + */ +struct virtio_pci_modern_common_cfg { + struct virtio_pci_common_cfg cfg; + + __le16 queue_notify_data; /* read-write */ + __le16 queue_reset; /* read-write */ +}; + /* Fields in VIRTIO_PCI_CAP_PCI_CFG: */ struct virtio_pci_cfg_cap { struct virtio_pci_cap cap; -- cgit From d93f9528573e1d419b69ca5ff4130201d05f6b90 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 2 Nov 2023 11:52:27 -0700 Subject: nfsd: regenerate user space parsers after ynl-gen changes Commit 8cea95b0bd79 ("tools: ynl-gen: handle do ops with no input attrs") added support for some of the previously-skipped ops in nfsd. Regenerate the user space parsers to fill them in. Signed-off-by: Jakub Kicinski Acked-by: Chuck Lever Signed-off-by: David S. Miller --- include/uapi/linux/nfsd_netlink.h | 6 +- tools/net/ynl/generated/nfsd-user.c | 120 ++++++++++++++++++++++++++++++++++-- tools/net/ynl/generated/nfsd-user.h | 44 +++++++++++-- 3 files changed, 156 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nfsd_netlink.h b/include/uapi/linux/nfsd_netlink.h index c8ae72466ee6..3cd044edee5d 100644 --- a/include/uapi/linux/nfsd_netlink.h +++ b/include/uapi/linux/nfsd_netlink.h @@ -3,8 +3,8 @@ /* Documentation/netlink/specs/nfsd.yaml */ /* YNL-GEN uapi header */ -#ifndef _UAPI_LINUX_NFSD_H -#define _UAPI_LINUX_NFSD_H +#ifndef _UAPI_LINUX_NFSD_NETLINK_H +#define _UAPI_LINUX_NFSD_NETLINK_H #define NFSD_FAMILY_NAME "nfsd" #define NFSD_FAMILY_VERSION 1 @@ -36,4 +36,4 @@ enum { NFSD_CMD_MAX = (__NFSD_CMD_MAX - 1) }; -#endif /* _UAPI_LINUX_NFSD_H */ +#endif /* _UAPI_LINUX_NFSD_NETLINK_H */ diff --git a/tools/net/ynl/generated/nfsd-user.c b/tools/net/ynl/generated/nfsd-user.c index fec6828680ce..360b6448c6e9 100644 --- a/tools/net/ynl/generated/nfsd-user.c +++ b/tools/net/ynl/generated/nfsd-user.c @@ -50,9 +50,116 @@ struct ynl_policy_nest nfsd_rpc_status_nest = { /* Common nested types */ /* ============== NFSD_CMD_RPC_STATUS_GET ============== */ /* NFSD_CMD_RPC_STATUS_GET - dump */ -void nfsd_rpc_status_get_list_free(struct nfsd_rpc_status_get_list *rsp) +int nfsd_rpc_status_get_rsp_dump_parse(const struct nlmsghdr *nlh, void *data) { - struct nfsd_rpc_status_get_list *next = rsp; + struct nfsd_rpc_status_get_rsp_dump *dst; + struct ynl_parse_arg *yarg = data; + unsigned int n_compound_ops = 0; + const struct nlattr *attr; + int i; + + dst = yarg->data; + + if (dst->compound_ops) + return ynl_error_parse(yarg, "attribute already present (rpc-status.compound-ops)"); + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == NFSD_A_RPC_STATUS_XID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.xid = 1; + dst->xid = mnl_attr_get_u32(attr); + } else if (type == NFSD_A_RPC_STATUS_FLAGS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.flags = 1; + dst->flags = mnl_attr_get_u32(attr); + } else if (type == NFSD_A_RPC_STATUS_PROG) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.prog = 1; + dst->prog = mnl_attr_get_u32(attr); + } else if (type == NFSD_A_RPC_STATUS_VERSION) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.version = 1; + dst->version = mnl_attr_get_u8(attr); + } else if (type == NFSD_A_RPC_STATUS_PROC) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.proc = 1; + dst->proc = mnl_attr_get_u32(attr); + } else if (type == NFSD_A_RPC_STATUS_SERVICE_TIME) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.service_time = 1; + dst->service_time = mnl_attr_get_u64(attr); + } else if (type == NFSD_A_RPC_STATUS_SADDR4) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.saddr4 = 1; + dst->saddr4 = mnl_attr_get_u32(attr); + } else if (type == NFSD_A_RPC_STATUS_DADDR4) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.daddr4 = 1; + dst->daddr4 = mnl_attr_get_u32(attr); + } else if (type == NFSD_A_RPC_STATUS_SADDR6) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.saddr6_len = len; + dst->saddr6 = malloc(len); + memcpy(dst->saddr6, mnl_attr_get_payload(attr), len); + } else if (type == NFSD_A_RPC_STATUS_DADDR6) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.daddr6_len = len; + dst->daddr6 = malloc(len); + memcpy(dst->daddr6, mnl_attr_get_payload(attr), len); + } else if (type == NFSD_A_RPC_STATUS_SPORT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sport = 1; + dst->sport = mnl_attr_get_u16(attr); + } else if (type == NFSD_A_RPC_STATUS_DPORT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dport = 1; + dst->dport = mnl_attr_get_u16(attr); + } else if (type == NFSD_A_RPC_STATUS_COMPOUND_OPS) { + n_compound_ops++; + } + } + + if (n_compound_ops) { + dst->compound_ops = calloc(n_compound_ops, sizeof(*dst->compound_ops)); + dst->n_compound_ops = n_compound_ops; + i = 0; + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == NFSD_A_RPC_STATUS_COMPOUND_OPS) { + dst->compound_ops[i] = mnl_attr_get_u32(attr); + i++; + } + } + } + + return MNL_CB_OK; +} + +void +nfsd_rpc_status_get_rsp_list_free(struct nfsd_rpc_status_get_rsp_list *rsp) +{ + struct nfsd_rpc_status_get_rsp_list *next = rsp; while ((void *)next != YNL_LIST_END) { rsp = next; @@ -65,15 +172,16 @@ void nfsd_rpc_status_get_list_free(struct nfsd_rpc_status_get_list *rsp) } } -struct nfsd_rpc_status_get_list *nfsd_rpc_status_get_dump(struct ynl_sock *ys) +struct nfsd_rpc_status_get_rsp_list * +nfsd_rpc_status_get_dump(struct ynl_sock *ys) { struct ynl_dump_state yds = {}; struct nlmsghdr *nlh; int err; yds.ys = ys; - yds.alloc_sz = sizeof(struct nfsd_rpc_status_get_list); - yds.cb = nfsd_rpc_status_get_rsp_parse; + yds.alloc_sz = sizeof(struct nfsd_rpc_status_get_rsp_list); + yds.cb = nfsd_rpc_status_get_rsp_dump_parse; yds.rsp_cmd = NFSD_CMD_RPC_STATUS_GET; yds.rsp_policy = &nfsd_rpc_status_nest; @@ -86,7 +194,7 @@ struct nfsd_rpc_status_get_list *nfsd_rpc_status_get_dump(struct ynl_sock *ys) return yds.first; free_list: - nfsd_rpc_status_get_list_free(yds.first); + nfsd_rpc_status_get_rsp_list_free(yds.first); return NULL; } diff --git a/tools/net/ynl/generated/nfsd-user.h b/tools/net/ynl/generated/nfsd-user.h index b6b69501031a..989c6e209ced 100644 --- a/tools/net/ynl/generated/nfsd-user.h +++ b/tools/net/ynl/generated/nfsd-user.h @@ -21,13 +21,47 @@ const char *nfsd_op_str(int op); /* Common nested types */ /* ============== NFSD_CMD_RPC_STATUS_GET ============== */ /* NFSD_CMD_RPC_STATUS_GET - dump */ -struct nfsd_rpc_status_get_list { - struct nfsd_rpc_status_get_list *next; - struct nfsd_rpc_status_get_rsp obj __attribute__ ((aligned (8))); +struct nfsd_rpc_status_get_rsp_dump { + struct { + __u32 xid:1; + __u32 flags:1; + __u32 prog:1; + __u32 version:1; + __u32 proc:1; + __u32 service_time:1; + __u32 saddr4:1; + __u32 daddr4:1; + __u32 saddr6_len; + __u32 daddr6_len; + __u32 sport:1; + __u32 dport:1; + } _present; + + __u32 xid /* big-endian */; + __u32 flags; + __u32 prog; + __u8 version; + __u32 proc; + __s64 service_time; + __u32 saddr4 /* big-endian */; + __u32 daddr4 /* big-endian */; + void *saddr6; + void *daddr6; + __u16 sport /* big-endian */; + __u16 dport /* big-endian */; + unsigned int n_compound_ops; + __u32 *compound_ops; +}; + +struct nfsd_rpc_status_get_rsp_list { + struct nfsd_rpc_status_get_rsp_list *next; + struct nfsd_rpc_status_get_rsp_dump obj __attribute__((aligned(8))); }; -void nfsd_rpc_status_get_list_free(struct nfsd_rpc_status_get_list *rsp); +void +nfsd_rpc_status_get_rsp_list_free(struct nfsd_rpc_status_get_rsp_list *rsp); -struct nfsd_rpc_status_get_list *nfsd_rpc_status_get_dump(struct ynl_sock *ys); +struct nfsd_rpc_status_get_rsp_list * +nfsd_rpc_status_get_dump(struct ynl_sock *ys); #endif /* _LINUX_NFSD_GEN_H */ -- cgit From d3933152442b7f94419e9ea71835d71b620baf0e Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Fri, 3 Nov 2023 11:38:04 -0700 Subject: btrfs: make OWNER_REF_KEY type value smallest among inline refs BTRFS_EXTENT_OWNER_REF_KEY is the type of simple quotas extent owner refs. This special inline ref goes in front of all other inline refs. In general, inline refs have a required sorted order s.t. type never decreases (among other requirements). This was recently reified into a tree-checker and fsck rule, which broke simple quotas. To be fair, though, in a sense, the new owner ref item had also violated that not yet fully enforced requirement. This fix brings the owner ref item into compliance with the requirement that inline ref type never decrease. btrfs/301 exercises this behavior and should pass again with this fix. Fixes: d9a620f77e33 ("btrfs: new inline ref storing owning subvol of data extents") Signed-off-by: Boris Burkov Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/uapi/linux/btrfs_tree.h | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index c25fc9614594..d24e8e121507 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -219,6 +219,22 @@ */ #define BTRFS_METADATA_ITEM_KEY 169 +/* + * Special inline ref key which stores the id of the subvolume which originally + * created the extent. This subvolume owns the extent permanently from the + * perspective of simple quotas. Needed to know which subvolume to free quota + * usage from when the extent is deleted. + * + * Stored as an inline ref rather to avoid wasting space on a separate item on + * top of the existing extent item. However, unlike the other inline refs, + * there is one one owner ref per extent rather than one per extent. + * + * Because of this, it goes at the front of the list of inline refs, and thus + * must have a lower type value than any other inline ref type (to satisfy the + * disk format rule that inline refs have non-decreasing type). + */ +#define BTRFS_EXTENT_OWNER_REF_KEY 172 + #define BTRFS_TREE_BLOCK_REF_KEY 176 #define BTRFS_EXTENT_DATA_REF_KEY 178 @@ -233,14 +249,6 @@ #define BTRFS_SHARED_DATA_REF_KEY 184 -/* - * Special inline ref key which stores the id of the subvolume which originally - * created the extent. This subvolume owns the extent permanently from the - * perspective of simple quotas. Needed to know which subvolume to free quota - * usage from when the extent is deleted. - */ -#define BTRFS_EXTENT_OWNER_REF_KEY 188 - /* * block groups give us hints into the extent allocation trees. Which * blocks are free etc etc -- cgit From 155addf0814a92d08fce26a11b27e3315cdba977 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Fri, 3 Nov 2023 19:49:00 -0700 Subject: bpf: Use named fields for certain bpf uapi structs Martin and Vadim reported a verifier failure with bpf_dynptr usage. The issue is mentioned but Vadim workarounded the issue with source change ([1]). The below describes what is the issue and why there is a verification failure. int BPF_PROG(skb_crypto_setup) { struct bpf_dynptr algo, key; ... bpf_dynptr_from_mem(..., ..., 0, &algo); ... } The bpf program is using vmlinux.h, so we have the following definition in vmlinux.h: struct bpf_dynptr { long: 64; long: 64; }; Note that in uapi header bpf.h, we have struct bpf_dynptr { long: 64; long: 64; } __attribute__((aligned(8))); So we lost alignment information for struct bpf_dynptr by using vmlinux.h. Let us take a look at a simple program below: $ cat align.c typedef unsigned long long __u64; struct bpf_dynptr_no_align { __u64 :64; __u64 :64; }; struct bpf_dynptr_yes_align { __u64 :64; __u64 :64; } __attribute__((aligned(8))); void bar(void *, void *); int foo() { struct bpf_dynptr_no_align a; struct bpf_dynptr_yes_align b; bar(&a, &b); return 0; } $ clang --target=bpf -O2 -S -emit-llvm align.c Look at the generated IR file align.ll: ... %a = alloca %struct.bpf_dynptr_no_align, align 1 %b = alloca %struct.bpf_dynptr_yes_align, align 8 ... The compiler dictates the alignment for struct bpf_dynptr_no_align is 1 and the alignment for struct bpf_dynptr_yes_align is 8. So theoretically compiler could allocate variable %a with alignment 1 although in reallity the compiler may choose a different alignment by considering other local variables. In [1], the verification failure happens because variable 'algo' is allocated on the stack with alignment 4 (fp-28). But the verifer wants its alignment to be 8. To fix the issue, the RFC patch ([1]) tried to add '__attribute__((aligned(8)))' to struct bpf_dynptr plus other similar structs. Andrii suggested that we could directly modify uapi struct with named fields like struct 'bpf_iter_num': struct bpf_iter_num { /* opaque iterator state; having __u64 here allows to preserve correct * alignment requirements in vmlinux.h, generated from BTF */ __u64 __opaque[1]; } __attribute__((aligned(8))); Indeed, adding named fields for those affected structs in this patch can preserve alignment when bpf program references them in vmlinux.h. With this patch, the verification failure in [1] can also be resolved. [1] https://lore.kernel.org/bpf/1b100f73-7625-4c1f-3ae5-50ecf84d3ff0@linux.dev/ [2] https://lore.kernel.org/bpf/20231103055218.2395034-1-yonghong.song@linux.dev/ Cc: Vadim Fedorenko Cc: Martin KaFai Lau Suggested-by: Andrii Nakryiko Signed-off-by: Yonghong Song Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231104024900.1539182-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 23 +++++++---------------- tools/include/uapi/linux/bpf.h | 23 +++++++---------------- 2 files changed, 14 insertions(+), 32 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0f6cdf52b1da..095ca7238ac2 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -7151,40 +7151,31 @@ struct bpf_spin_lock { }; struct bpf_timer { - __u64 :64; - __u64 :64; + __u64 __opaque[2]; } __attribute__((aligned(8))); struct bpf_dynptr { - __u64 :64; - __u64 :64; + __u64 __opaque[2]; } __attribute__((aligned(8))); struct bpf_list_head { - __u64 :64; - __u64 :64; + __u64 __opaque[2]; } __attribute__((aligned(8))); struct bpf_list_node { - __u64 :64; - __u64 :64; - __u64 :64; + __u64 __opaque[3]; } __attribute__((aligned(8))); struct bpf_rb_root { - __u64 :64; - __u64 :64; + __u64 __opaque[2]; } __attribute__((aligned(8))); struct bpf_rb_node { - __u64 :64; - __u64 :64; - __u64 :64; - __u64 :64; + __u64 __opaque[4]; } __attribute__((aligned(8))); struct bpf_refcount { - __u32 :32; + __u32 __opaque[1]; } __attribute__((aligned(4))); struct bpf_sysctl { diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 0f6cdf52b1da..095ca7238ac2 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -7151,40 +7151,31 @@ struct bpf_spin_lock { }; struct bpf_timer { - __u64 :64; - __u64 :64; + __u64 __opaque[2]; } __attribute__((aligned(8))); struct bpf_dynptr { - __u64 :64; - __u64 :64; + __u64 __opaque[2]; } __attribute__((aligned(8))); struct bpf_list_head { - __u64 :64; - __u64 :64; + __u64 __opaque[2]; } __attribute__((aligned(8))); struct bpf_list_node { - __u64 :64; - __u64 :64; - __u64 :64; + __u64 __opaque[3]; } __attribute__((aligned(8))); struct bpf_rb_root { - __u64 :64; - __u64 :64; + __u64 __opaque[2]; } __attribute__((aligned(8))); struct bpf_rb_node { - __u64 :64; - __u64 :64; - __u64 :64; - __u64 :64; + __u64 __opaque[4]; } __attribute__((aligned(8))); struct bpf_refcount { - __u32 :32; + __u32 __opaque[1]; } __attribute__((aligned(4))); struct bpf_sysctl { -- cgit From b8e3a87a627b575896e448021e5c2f8a3bc19931 Mon Sep 17 00:00:00 2001 From: Jordan Rome Date: Wed, 8 Nov 2023 03:23:34 -0800 Subject: bpf: Add crosstask check to __bpf_get_stack Currently get_perf_callchain only supports user stack walking for the current task. Passing the correct *crosstask* param will return 0 frames if the task passed to __bpf_get_stack isn't the current one instead of a single incorrect frame/address. This change passes the correct *crosstask* param but also does a preemptive check in __bpf_get_stack if the task is current and returns -EOPNOTSUPP if it is not. This issue was found using bpf_get_task_stack inside a BPF iterator ("iter/task"), which iterates over all tasks. bpf_get_task_stack works fine for fetching kernel stacks but because get_perf_callchain relies on the caller to know if the requested *task* is the current one (via *crosstask*) it was failing in a confusing way. It might be possible to get user stacks for all tasks utilizing something like access_process_vm but that requires the bpf program calling bpf_get_task_stack to be sleepable and would therefore be a breaking change. Fixes: fa28dcb82a38 ("bpf: Introduce helper bpf_get_task_stack()") Signed-off-by: Jordan Rome Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20231108112334.3433136-1-jordalgo@meta.com --- include/uapi/linux/bpf.h | 3 +++ kernel/bpf/stackmap.c | 11 ++++++++++- tools/include/uapi/linux/bpf.h | 3 +++ 3 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 095ca7238ac2..7cf8bcf9f6a2 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4517,6 +4517,8 @@ union bpf_attr { * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags) * Description * Return a user or a kernel stack in bpf program provided buffer. + * Note: the user stack will only be populated if the *task* is + * the current task; all other tasks will return -EOPNOTSUPP. * To achieve this, the helper needs *task*, which is a valid * pointer to **struct task_struct**. To store the stacktrace, the * bpf program provides *buf* with a nonnegative *size*. @@ -4528,6 +4530,7 @@ union bpf_attr { * * **BPF_F_USER_STACK** * Collect a user space stack instead of a kernel stack. + * The *task* must be the current task. * **BPF_F_USER_BUILD_ID** * Collect buildid+offset instead of ips for user stack, * only valid if **BPF_F_USER_STACK** is also specified. diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index d6b277482085..dff7ba539701 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -388,6 +388,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, { u32 trace_nr, copy_len, elem_size, num_elem, max_depth; bool user_build_id = flags & BPF_F_USER_BUILD_ID; + bool crosstask = task && task != current; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; bool user = flags & BPF_F_USER_STACK; struct perf_callchain_entry *trace; @@ -410,6 +411,14 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, if (task && user && !user_mode(regs)) goto err_fault; + /* get_perf_callchain does not support crosstask user stack walking + * but returns an empty stack instead of NULL. + */ + if (crosstask && user) { + err = -EOPNOTSUPP; + goto clear; + } + num_elem = size / elem_size; max_depth = num_elem + skip; if (sysctl_perf_event_max_stack < max_depth) @@ -421,7 +430,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, trace = get_callchain_entry_for_task(task, max_depth); else trace = get_perf_callchain(regs, 0, kernel, user, max_depth, - false, false); + crosstask, false); if (unlikely(!trace)) goto err_fault; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 095ca7238ac2..7cf8bcf9f6a2 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4517,6 +4517,8 @@ union bpf_attr { * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags) * Description * Return a user or a kernel stack in bpf program provided buffer. + * Note: the user stack will only be populated if the *task* is + * the current task; all other tasks will return -EOPNOTSUPP. * To achieve this, the helper needs *task*, which is a valid * pointer to **struct task_struct**. To store the stacktrace, the * bpf program provides *buf* with a nonnegative *size*. @@ -4528,6 +4530,7 @@ union bpf_attr { * * **BPF_F_USER_STACK** * Collect a user space stack instead of a kernel stack. + * The *task* must be the current task. * **BPF_F_USER_BUILD_ID** * Collect buildid+offset instead of ips for user stack, * only valid if **BPF_F_USER_STACK** is also specified. -- cgit From f3b8788cde61b02f1e6c202f8fac4360e6adbafc Mon Sep 17 00:00:00 2001 From: Casey Schaufler Date: Tue, 12 Sep 2023 13:56:46 -0700 Subject: LSM: Identify modules by more than name Create a struct lsm_id to contain identifying information about Linux Security Modules (LSMs). At inception this contains the name of the module and an identifier associated with the security module. Change the security_add_hooks() interface to use this structure. Change the individual modules to maintain their own struct lsm_id and pass it to security_add_hooks(). The values are for LSM identifiers are defined in a new UAPI header file linux/lsm.h. Each existing LSM has been updated to include it's LSMID in the lsm_id. The LSM ID values are sequential, with the oldest module LSM_ID_CAPABILITY being the lowest value and the existing modules numbered in the order they were included in the main line kernel. This is an arbitrary convention for assigning the values, but none better presents itself. The value 0 is defined as being invalid. The values 1-99 are reserved for any special case uses which may arise in the future. This may include attributes of the LSM infrastructure itself, possibly related to namespacing or network attribute management. A special range is identified for such attributes to help reduce confusion for developers unfamiliar with LSMs. LSM attribute values are defined for the attributes presented by modules that are available today. As with the LSM IDs, The value 0 is defined as being invalid. The values 1-99 are reserved for any special case uses which may arise in the future. Cc: linux-security-module Signed-off-by: Casey Schaufler Reviewed-by: Kees Cook Reviewed-by: Serge Hallyn Reviewed-by: Mickael Salaun Reviewed-by: John Johansen Signed-off-by: Kees Cook Nacked-by: Tetsuo Handa [PM: forward ported beyond v6.6 due merge window changes] Signed-off-by: Paul Moore --- Documentation/userspace-api/index.rst | 1 + MAINTAINERS | 1 + include/linux/lsm_hooks.h | 16 +++++++++-- include/uapi/linux/lsm.h | 54 +++++++++++++++++++++++++++++++++++ security/apparmor/lsm.c | 8 +++++- security/bpf/hooks.c | 9 +++++- security/commoncap.c | 8 +++++- security/landlock/cred.c | 2 +- security/landlock/fs.c | 2 +- security/landlock/net.c | 2 +- security/landlock/ptrace.c | 2 +- security/landlock/setup.c | 6 ++++ security/landlock/setup.h | 1 + security/loadpin/loadpin.c | 9 +++++- security/lockdown/lockdown.c | 8 +++++- security/safesetid/lsm.c | 9 +++++- security/security.c | 12 ++++---- security/selinux/hooks.c | 9 +++++- security/smack/smack_lsm.c | 8 +++++- security/tomoyo/tomoyo.c | 9 +++++- security/yama/yama_lsm.c | 8 +++++- 21 files changed, 162 insertions(+), 22 deletions(-) create mode 100644 include/uapi/linux/lsm.h (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst index 031df47a7c19..8be8b1979194 100644 --- a/Documentation/userspace-api/index.rst +++ b/Documentation/userspace-api/index.rst @@ -33,6 +33,7 @@ place where this information is gathered. sysfs-platform_profile vduse futex2 + lsm .. only:: subproject and html diff --git a/MAINTAINERS b/MAINTAINERS index 97f51d5ec1cf..f1d41fd9159a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -19511,6 +19511,7 @@ L: linux-security-module@vger.kernel.org (suggested Cc:) S: Supported W: http://kernsec.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm.git +F: include/uapi/linux/lsm.h F: security/ X: security/selinux/ diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index dcb5e5b5eb13..7f0adb33caaa 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -42,6 +42,18 @@ struct security_hook_heads { #undef LSM_HOOK } __randomize_layout; +/** + * struct lsm_id - Identify a Linux Security Module. + * @lsm: name of the LSM, must be approved by the LSM maintainers + * @id: LSM ID number from uapi/linux/lsm.h + * + * Contains the information that identifies the LSM. + */ +struct lsm_id { + const char *name; + u64 id; +}; + /* * Security module hook list structure. * For use with generic list macros for common operations. @@ -50,7 +62,7 @@ struct security_hook_list { struct hlist_node list; struct hlist_head *head; union security_list_options hook; - const char *lsm; + const struct lsm_id *lsmid; } __randomize_layout; /* @@ -104,7 +116,7 @@ extern struct security_hook_heads security_hook_heads; extern char *lsm_names; extern void security_add_hooks(struct security_hook_list *hooks, int count, - const char *lsm); + const struct lsm_id *lsmid); #define LSM_FLAG_LEGACY_MAJOR BIT(0) #define LSM_FLAG_EXCLUSIVE BIT(1) diff --git a/include/uapi/linux/lsm.h b/include/uapi/linux/lsm.h new file mode 100644 index 000000000000..f27c9a9cc376 --- /dev/null +++ b/include/uapi/linux/lsm.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Linux Security Modules (LSM) - User space API + * + * Copyright (C) 2022 Casey Schaufler + * Copyright (C) 2022 Intel Corporation + */ + +#ifndef _UAPI_LINUX_LSM_H +#define _UAPI_LINUX_LSM_H + +/* + * ID tokens to identify Linux Security Modules (LSMs) + * + * These token values are used to uniquely identify specific LSMs + * in the kernel as well as in the kernel's LSM userspace API. + * + * A value of zero/0 is considered undefined and should not be used + * outside the kernel. Values 1-99 are reserved for potential + * future use. + */ +#define LSM_ID_UNDEF 0 +#define LSM_ID_CAPABILITY 100 +#define LSM_ID_SELINUX 101 +#define LSM_ID_SMACK 102 +#define LSM_ID_TOMOYO 103 +#define LSM_ID_IMA 104 +#define LSM_ID_APPARMOR 105 +#define LSM_ID_YAMA 106 +#define LSM_ID_LOADPIN 107 +#define LSM_ID_SAFESETID 108 +#define LSM_ID_LOCKDOWN 109 +#define LSM_ID_BPF 110 +#define LSM_ID_LANDLOCK 111 + +/* + * LSM_ATTR_XXX definitions identify different LSM attributes + * which are used in the kernel's LSM userspace API. Support + * for these attributes vary across the different LSMs. None + * are required. + * + * A value of zero/0 is considered undefined and should not be used + * outside the kernel. Values 1-99 are reserved for potential + * future use. + */ +#define LSM_ATTR_UNDEF 0 +#define LSM_ATTR_CURRENT 100 +#define LSM_ATTR_EXEC 101 +#define LSM_ATTR_FSCREATE 102 +#define LSM_ATTR_KEYCREATE 103 +#define LSM_ATTR_PREV 104 +#define LSM_ATTR_SOCKCREATE 105 + +#endif /* _UAPI_LINUX_LSM_H */ diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 4981bdf02993..093da0a9dbd8 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -24,6 +24,7 @@ #include #include #include +#include #include "include/apparmor.h" #include "include/apparmorfs.h" @@ -1385,6 +1386,11 @@ struct lsm_blob_sizes apparmor_blob_sizes __ro_after_init = { .lbs_task = sizeof(struct aa_task_ctx), }; +const struct lsm_id apparmor_lsmid = { + .name = "apparmor", + .id = LSM_ID_APPARMOR, +}; + static struct security_hook_list apparmor_hooks[] __ro_after_init = { LSM_HOOK_INIT(ptrace_access_check, apparmor_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, apparmor_ptrace_traceme), @@ -2202,7 +2208,7 @@ static int __init apparmor_init(void) goto buffers_out; } security_add_hooks(apparmor_hooks, ARRAY_SIZE(apparmor_hooks), - "apparmor"); + &apparmor_lsmid); /* Report that AppArmor successfully initialized */ apparmor_initialized = 1; diff --git a/security/bpf/hooks.c b/security/bpf/hooks.c index cfaf1d0e6a5f..91011e0c361a 100644 --- a/security/bpf/hooks.c +++ b/security/bpf/hooks.c @@ -5,6 +5,7 @@ */ #include #include +#include static struct security_hook_list bpf_lsm_hooks[] __ro_after_init = { #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ @@ -15,9 +16,15 @@ static struct security_hook_list bpf_lsm_hooks[] __ro_after_init = { LSM_HOOK_INIT(task_free, bpf_task_storage_free), }; +const struct lsm_id bpf_lsmid = { + .name = "bpf", + .id = LSM_ID_BPF, +}; + static int __init bpf_lsm_init(void) { - security_add_hooks(bpf_lsm_hooks, ARRAY_SIZE(bpf_lsm_hooks), "bpf"); + security_add_hooks(bpf_lsm_hooks, ARRAY_SIZE(bpf_lsm_hooks), + &bpf_lsmid); pr_info("LSM support for eBPF active\n"); return 0; } diff --git a/security/commoncap.c b/security/commoncap.c index 8e8c630ce204..a64c0c8592bb 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -25,6 +25,7 @@ #include #include #include +#include /* * If a non-root user executes a setuid-root binary in @@ -1440,6 +1441,11 @@ int cap_mmap_file(struct file *file, unsigned long reqprot, #ifdef CONFIG_SECURITY +const struct lsm_id capability_lsmid = { + .name = "capability", + .id = LSM_ID_CAPABILITY, +}; + static struct security_hook_list capability_hooks[] __ro_after_init = { LSM_HOOK_INIT(capable, cap_capable), LSM_HOOK_INIT(settime, cap_settime), @@ -1464,7 +1470,7 @@ static struct security_hook_list capability_hooks[] __ro_after_init = { static int __init capability_init(void) { security_add_hooks(capability_hooks, ARRAY_SIZE(capability_hooks), - "capability"); + &capability_lsmid); return 0; } diff --git a/security/landlock/cred.c b/security/landlock/cred.c index 13dff2a31545..786af18c4a1c 100644 --- a/security/landlock/cred.c +++ b/security/landlock/cred.c @@ -42,5 +42,5 @@ static struct security_hook_list landlock_hooks[] __ro_after_init = { __init void landlock_add_cred_hooks(void) { security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks), - LANDLOCK_NAME); + &landlock_lsmid); } diff --git a/security/landlock/fs.c b/security/landlock/fs.c index bc7c126deea2..490655d09b43 100644 --- a/security/landlock/fs.c +++ b/security/landlock/fs.c @@ -1223,5 +1223,5 @@ static struct security_hook_list landlock_hooks[] __ro_after_init = { __init void landlock_add_fs_hooks(void) { security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks), - LANDLOCK_NAME); + &landlock_lsmid); } diff --git a/security/landlock/net.c b/security/landlock/net.c index aaa92c2b1f08..efa1b644a4af 100644 --- a/security/landlock/net.c +++ b/security/landlock/net.c @@ -196,5 +196,5 @@ static struct security_hook_list landlock_hooks[] __ro_after_init = { __init void landlock_add_net_hooks(void) { security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks), - LANDLOCK_NAME); + &landlock_lsmid); } diff --git a/security/landlock/ptrace.c b/security/landlock/ptrace.c index 8a06d6c492bf..2bfc533d36e4 100644 --- a/security/landlock/ptrace.c +++ b/security/landlock/ptrace.c @@ -116,5 +116,5 @@ static struct security_hook_list landlock_hooks[] __ro_after_init = { __init void landlock_add_ptrace_hooks(void) { security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks), - LANDLOCK_NAME); + &landlock_lsmid); } diff --git a/security/landlock/setup.c b/security/landlock/setup.c index 3e11d303542f..f6dd33143b7f 100644 --- a/security/landlock/setup.c +++ b/security/landlock/setup.c @@ -8,6 +8,7 @@ #include #include +#include #include "common.h" #include "cred.h" @@ -25,6 +26,11 @@ struct lsm_blob_sizes landlock_blob_sizes __ro_after_init = { .lbs_superblock = sizeof(struct landlock_superblock_security), }; +const struct lsm_id landlock_lsmid = { + .name = LANDLOCK_NAME, + .id = LSM_ID_LANDLOCK, +}; + static int __init landlock_init(void) { landlock_add_cred_hooks(); diff --git a/security/landlock/setup.h b/security/landlock/setup.h index 1daffab1ab4b..c4252d46d49d 100644 --- a/security/landlock/setup.h +++ b/security/landlock/setup.h @@ -14,5 +14,6 @@ extern bool landlock_initialized; extern struct lsm_blob_sizes landlock_blob_sizes; +extern const struct lsm_id landlock_lsmid; #endif /* _SECURITY_LANDLOCK_SETUP_H */ diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c index a9d40456a064..d682a851de58 100644 --- a/security/loadpin/loadpin.c +++ b/security/loadpin/loadpin.c @@ -20,6 +20,7 @@ #include #include #include +#include #define VERITY_DIGEST_FILE_HEADER "# LOADPIN_TRUSTED_VERITY_ROOT_DIGESTS" @@ -208,6 +209,11 @@ static int loadpin_load_data(enum kernel_load_data_id id, bool contents) return loadpin_check(NULL, (enum kernel_read_file_id) id); } +const struct lsm_id loadpin_lsmid = { + .name = "loadpin", + .id = LSM_ID_LOADPIN, +}; + static struct security_hook_list loadpin_hooks[] __ro_after_init = { LSM_HOOK_INIT(sb_free_security, loadpin_sb_free_security), LSM_HOOK_INIT(kernel_read_file, loadpin_read_file), @@ -259,7 +265,8 @@ static int __init loadpin_init(void) if (!register_sysctl("kernel/loadpin", loadpin_sysctl_table)) pr_notice("sysctl registration failed!\n"); #endif - security_add_hooks(loadpin_hooks, ARRAY_SIZE(loadpin_hooks), "loadpin"); + security_add_hooks(loadpin_hooks, ARRAY_SIZE(loadpin_hooks), + &loadpin_lsmid); return 0; } diff --git a/security/lockdown/lockdown.c b/security/lockdown/lockdown.c index 68d19632aeb7..cd84d8ea1dfb 100644 --- a/security/lockdown/lockdown.c +++ b/security/lockdown/lockdown.c @@ -13,6 +13,7 @@ #include #include #include +#include static enum lockdown_reason kernel_locked_down; @@ -75,6 +76,11 @@ static struct security_hook_list lockdown_hooks[] __ro_after_init = { LSM_HOOK_INIT(locked_down, lockdown_is_locked_down), }; +const struct lsm_id lockdown_lsmid = { + .name = "lockdown", + .id = LSM_ID_LOCKDOWN, +}; + static int __init lockdown_lsm_init(void) { #if defined(CONFIG_LOCK_DOWN_KERNEL_FORCE_INTEGRITY) @@ -83,7 +89,7 @@ static int __init lockdown_lsm_init(void) lock_kernel_down("Kernel configuration", LOCKDOWN_CONFIDENTIALITY_MAX); #endif security_add_hooks(lockdown_hooks, ARRAY_SIZE(lockdown_hooks), - "lockdown"); + &lockdown_lsmid); return 0; } diff --git a/security/safesetid/lsm.c b/security/safesetid/lsm.c index 5be5894aa0ea..f42d5af5ffb0 100644 --- a/security/safesetid/lsm.c +++ b/security/safesetid/lsm.c @@ -19,6 +19,7 @@ #include #include #include +#include #include "lsm.h" /* Flag indicating whether initialization completed */ @@ -261,6 +262,11 @@ static int safesetid_task_fix_setgroups(struct cred *new, const struct cred *old return 0; } +const struct lsm_id safesetid_lsmid = { + .name = "safesetid", + .id = LSM_ID_SAFESETID, +}; + static struct security_hook_list safesetid_security_hooks[] = { LSM_HOOK_INIT(task_fix_setuid, safesetid_task_fix_setuid), LSM_HOOK_INIT(task_fix_setgid, safesetid_task_fix_setgid), @@ -271,7 +277,8 @@ static struct security_hook_list safesetid_security_hooks[] = { static int __init safesetid_security_init(void) { security_add_hooks(safesetid_security_hooks, - ARRAY_SIZE(safesetid_security_hooks), "safesetid"); + ARRAY_SIZE(safesetid_security_hooks), + &safesetid_lsmid); /* Report that SafeSetID successfully initialized */ safesetid_initialized = 1; diff --git a/security/security.c b/security/security.c index dcb3e7014f9b..08b1bd9457a9 100644 --- a/security/security.c +++ b/security/security.c @@ -513,17 +513,17 @@ static int lsm_append(const char *new, char **result) * security_add_hooks - Add a modules hooks to the hook lists. * @hooks: the hooks to add * @count: the number of hooks to add - * @lsm: the name of the security module + * @lsmid: the identification information for the security module * * Each LSM has to register its hooks with the infrastructure. */ void __init security_add_hooks(struct security_hook_list *hooks, int count, - const char *lsm) + const struct lsm_id *lsmid) { int i; for (i = 0; i < count; i++) { - hooks[i].lsm = lsm; + hooks[i].lsmid = lsmid; hlist_add_tail_rcu(&hooks[i].list, hooks[i].head); } @@ -532,7 +532,7 @@ void __init security_add_hooks(struct security_hook_list *hooks, int count, * and fix this up afterwards. */ if (slab_is_available()) { - if (lsm_append(lsm, &lsm_names) < 0) + if (lsm_append(lsmid->name, &lsm_names) < 0) panic("%s - Cannot get early memory.\n", __func__); } } @@ -3817,7 +3817,7 @@ int security_getprocattr(struct task_struct *p, const char *lsm, struct security_hook_list *hp; hlist_for_each_entry(hp, &security_hook_heads.getprocattr, list) { - if (lsm != NULL && strcmp(lsm, hp->lsm)) + if (lsm != NULL && strcmp(lsm, hp->lsmid->name)) continue; return hp->hook.getprocattr(p, name, value); } @@ -3842,7 +3842,7 @@ int security_setprocattr(const char *lsm, const char *name, void *value, struct security_hook_list *hp; hlist_for_each_entry(hp, &security_hook_heads.setprocattr, list) { - if (lsm != NULL && strcmp(lsm, hp->lsm)) + if (lsm != NULL && strcmp(lsm, hp->lsmid->name)) continue; return hp->hook.setprocattr(name, value, size); } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index feda711c6b7b..f2423dfd19cd 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -92,6 +92,7 @@ #include #include #include +#include #include "avc.h" #include "objsec.h" @@ -6950,6 +6951,11 @@ static int selinux_uring_cmd(struct io_uring_cmd *ioucmd) } #endif /* CONFIG_IO_URING */ +const struct lsm_id selinux_lsmid = { + .name = "selinux", + .id = LSM_ID_SELINUX, +}; + /* * IMPORTANT NOTE: When adding new hooks, please be careful to keep this order: * 1. any hooks that don't belong to (2.) or (3.) below, @@ -7270,7 +7276,8 @@ static __init int selinux_init(void) hashtab_cache_init(); - security_add_hooks(selinux_hooks, ARRAY_SIZE(selinux_hooks), "selinux"); + security_add_hooks(selinux_hooks, ARRAY_SIZE(selinux_hooks), + &selinux_lsmid); if (avc_add_callback(selinux_netcache_avc_callback, AVC_CALLBACK_RESET)) panic("SELinux: Unable to register AVC netcache callback\n"); diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 65130a791f57..f73f9a2834eb 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -43,6 +43,7 @@ #include #include #include +#include #include "smack.h" #define TRANS_TRUE "TRUE" @@ -4933,6 +4934,11 @@ struct lsm_blob_sizes smack_blob_sizes __ro_after_init = { .lbs_xattr_count = SMACK_INODE_INIT_XATTRS, }; +const struct lsm_id smack_lsmid = { + .name = "smack", + .id = LSM_ID_SMACK, +}; + static struct security_hook_list smack_hooks[] __ro_after_init = { LSM_HOOK_INIT(ptrace_access_check, smack_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, smack_ptrace_traceme), @@ -5140,7 +5146,7 @@ static __init int smack_init(void) /* * Register with LSM */ - security_add_hooks(smack_hooks, ARRAY_SIZE(smack_hooks), "smack"); + security_add_hooks(smack_hooks, ARRAY_SIZE(smack_hooks), &smack_lsmid); smack_enabled = 1; pr_info("Smack: Initializing.\n"); diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c index 255f1b470295..722205433105 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/tomoyo.c @@ -6,6 +6,7 @@ */ #include +#include #include "common.h" /** @@ -542,6 +543,11 @@ static void tomoyo_task_free(struct task_struct *task) } } +const struct lsm_id tomoyo_lsmid = { + .name = "tomoyo", + .id = LSM_ID_TOMOYO, +}; + /* * tomoyo_security_ops is a "struct security_operations" which is used for * registering TOMOYO. @@ -595,7 +601,8 @@ static int __init tomoyo_init(void) struct tomoyo_task *s = tomoyo_task(current); /* register ourselves with the security framework */ - security_add_hooks(tomoyo_hooks, ARRAY_SIZE(tomoyo_hooks), "tomoyo"); + security_add_hooks(tomoyo_hooks, ARRAY_SIZE(tomoyo_hooks), + &tomoyo_lsmid); pr_info("TOMOYO Linux initialized\n"); s->domain_info = &tomoyo_kernel_domain; atomic_inc(&tomoyo_kernel_domain.users); diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c index 2503cf153d4a..5cdff292fcae 100644 --- a/security/yama/yama_lsm.c +++ b/security/yama/yama_lsm.c @@ -18,6 +18,7 @@ #include #include #include +#include #define YAMA_SCOPE_DISABLED 0 #define YAMA_SCOPE_RELATIONAL 1 @@ -421,6 +422,11 @@ static int yama_ptrace_traceme(struct task_struct *parent) return rc; } +const struct lsm_id yama_lsmid = { + .name = "yama", + .id = LSM_ID_YAMA, +}; + static struct security_hook_list yama_hooks[] __ro_after_init = { LSM_HOOK_INIT(ptrace_access_check, yama_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, yama_ptrace_traceme), @@ -471,7 +477,7 @@ static inline void yama_init_sysctl(void) { } static int __init yama_init(void) { pr_info("Yama: becoming mindful.\n"); - security_add_hooks(yama_hooks, ARRAY_SIZE(yama_hooks), "yama"); + security_add_hooks(yama_hooks, ARRAY_SIZE(yama_hooks), &yama_lsmid); yama_init_sysctl(); return 0; } -- cgit From a04a1198088a1378d0389c250cc684f649bcc91e Mon Sep 17 00:00:00 2001 From: Casey Schaufler Date: Tue, 12 Sep 2023 13:56:49 -0700 Subject: LSM: syscalls for current process attributes Create a system call lsm_get_self_attr() to provide the security module maintained attributes of the current process. Create a system call lsm_set_self_attr() to set a security module maintained attribute of the current process. Historically these attributes have been exposed to user space via entries in procfs under /proc/self/attr. The attribute value is provided in a lsm_ctx structure. The structure identifies the size of the attribute, and the attribute value. The format of the attribute value is defined by the security module. A flags field is included for LSM specific information. It is currently unused and must be 0. The total size of the data, including the lsm_ctx structure and any padding, is maintained as well. struct lsm_ctx { __u64 id; __u64 flags; __u64 len; __u64 ctx_len; __u8 ctx[]; }; Two new LSM hooks are used to interface with the LSMs. security_getselfattr() collects the lsm_ctx values from the LSMs that support the hook, accounting for space requirements. security_setselfattr() identifies which LSM the attribute is intended for and passes it along. Signed-off-by: Casey Schaufler Reviewed-by: Kees Cook Reviewed-by: Serge Hallyn Reviewed-by: John Johansen Signed-off-by: Paul Moore --- Documentation/userspace-api/lsm.rst | 70 +++++++++++++++++ include/linux/lsm_hook_defs.h | 4 + include/linux/lsm_hooks.h | 1 + include/linux/security.h | 19 +++++ include/linux/syscalls.h | 5 ++ include/uapi/linux/lsm.h | 36 +++++++++ kernel/sys_ni.c | 2 + security/Makefile | 1 + security/lsm_syscalls.c | 57 ++++++++++++++ security/security.c | 152 ++++++++++++++++++++++++++++++++++++ 10 files changed, 347 insertions(+) create mode 100644 Documentation/userspace-api/lsm.rst create mode 100644 security/lsm_syscalls.c (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/lsm.rst b/Documentation/userspace-api/lsm.rst new file mode 100644 index 000000000000..f8499f3e2826 --- /dev/null +++ b/Documentation/userspace-api/lsm.rst @@ -0,0 +1,70 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. Copyright (C) 2022 Casey Schaufler +.. Copyright (C) 2022 Intel Corporation + +===================================== +Linux Security Modules +===================================== + +:Author: Casey Schaufler +:Date: July 2023 + +Linux security modules (LSM) provide a mechanism to implement +additional access controls to the Linux security policies. + +The various security modules may support any of these attributes: + +``LSM_ATTR_CURRENT`` is the current, active security context of the +process. +The proc filesystem provides this value in ``/proc/self/attr/current``. +This is supported by the SELinux, Smack and AppArmor security modules. +Smack also provides this value in ``/proc/self/attr/smack/current``. +AppArmor also provides this value in ``/proc/self/attr/apparmor/current``. + +``LSM_ATTR_EXEC`` is the security context of the process at the time the +current image was executed. +The proc filesystem provides this value in ``/proc/self/attr/exec``. +This is supported by the SELinux and AppArmor security modules. +AppArmor also provides this value in ``/proc/self/attr/apparmor/exec``. + +``LSM_ATTR_FSCREATE`` is the security context of the process used when +creating file system objects. +The proc filesystem provides this value in ``/proc/self/attr/fscreate``. +This is supported by the SELinux security module. + +``LSM_ATTR_KEYCREATE`` is the security context of the process used when +creating key objects. +The proc filesystem provides this value in ``/proc/self/attr/keycreate``. +This is supported by the SELinux security module. + +``LSM_ATTR_PREV`` is the security context of the process at the time the +current security context was set. +The proc filesystem provides this value in ``/proc/self/attr/prev``. +This is supported by the SELinux and AppArmor security modules. +AppArmor also provides this value in ``/proc/self/attr/apparmor/prev``. + +``LSM_ATTR_SOCKCREATE`` is the security context of the process used when +creating socket objects. +The proc filesystem provides this value in ``/proc/self/attr/sockcreate``. +This is supported by the SELinux security module. + +Kernel interface +================ + +Set a security attribute of the current process +----------------------------------------------- + +.. kernel-doc:: security/lsm_syscalls.c + :identifiers: sys_lsm_set_self_attr + +Get the specified security attributes of the current process +------------------------------------------------------------ + +.. kernel-doc:: security/lsm_syscalls.c + :identifiers: sys_lsm_get_self_attr + +Additional documentation +======================== + +* Documentation/security/lsm.rst +* Documentation/security/lsm-development.rst diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index ff217a5ce552..c925a0d26edf 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -262,6 +262,10 @@ LSM_HOOK(int, 0, sem_semop, struct kern_ipc_perm *perm, struct sembuf *sops, LSM_HOOK(int, 0, netlink_send, struct sock *sk, struct sk_buff *skb) LSM_HOOK(void, LSM_RET_VOID, d_instantiate, struct dentry *dentry, struct inode *inode) +LSM_HOOK(int, -EOPNOTSUPP, getselfattr, unsigned int attr, + struct lsm_ctx __user *ctx, size_t *size, u32 flags) +LSM_HOOK(int, -EOPNOTSUPP, setselfattr, unsigned int attr, + struct lsm_ctx *ctx, size_t size, u32 flags) LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, const char *name, char **value) LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 7f0adb33caaa..a2ade0ffe9e7 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -25,6 +25,7 @@ #ifndef __LINUX_LSM_HOOKS_H #define __LINUX_LSM_HOOKS_H +#include #include #include #include diff --git a/include/linux/security.h b/include/linux/security.h index c81bca77f4f2..dd1fe487385d 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -60,6 +60,7 @@ struct fs_parameter; enum fs_value_type; struct watch; struct watch_notification; +struct lsm_ctx; /* Default (no) options for the capable function */ #define CAP_OPT_NONE 0x0 @@ -472,6 +473,10 @@ int security_sem_semctl(struct kern_ipc_perm *sma, int cmd); int security_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops, unsigned nsops, int alter); void security_d_instantiate(struct dentry *dentry, struct inode *inode); +int security_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx, + size_t __user *size, u32 flags); +int security_setselfattr(unsigned int attr, struct lsm_ctx __user *ctx, + size_t size, u32 flags); int security_getprocattr(struct task_struct *p, int lsmid, const char *name, char **value); int security_setprocattr(int lsmid, const char *name, void *value, size_t size); @@ -1338,6 +1343,20 @@ static inline void security_d_instantiate(struct dentry *dentry, struct inode *inode) { } +static inline int security_getselfattr(unsigned int attr, + struct lsm_ctx __user *ctx, + size_t __user *size, u32 flags) +{ + return -EOPNOTSUPP; +} + +static inline int security_setselfattr(unsigned int attr, + struct lsm_ctx __user *ctx, + size_t size, u32 flags) +{ + return -EOPNOTSUPP; +} + static inline int security_getprocattr(struct task_struct *p, int lsmid, const char *name, char **value) { diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index fd9d12de7e92..4e1e56a24f1e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -71,6 +71,7 @@ struct clone_args; struct open_how; struct mount_attr; struct landlock_ruleset_attr; +struct lsm_ctx; enum landlock_rule_type; struct cachestat_range; struct cachestat; @@ -949,6 +950,10 @@ asmlinkage long sys_cachestat(unsigned int fd, struct cachestat_range __user *cstat_range, struct cachestat __user *cstat, unsigned int flags); asmlinkage long sys_map_shadow_stack(unsigned long addr, unsigned long size, unsigned int flags); +asmlinkage long sys_lsm_get_self_attr(unsigned int attr, struct lsm_ctx *ctx, + size_t *size, __u32 flags); +asmlinkage long sys_lsm_set_self_attr(unsigned int attr, struct lsm_ctx *ctx, + size_t size, __u32 flags); /* * Architecture-specific system calls diff --git a/include/uapi/linux/lsm.h b/include/uapi/linux/lsm.h index f27c9a9cc376..eeda59a77c02 100644 --- a/include/uapi/linux/lsm.h +++ b/include/uapi/linux/lsm.h @@ -9,6 +9,36 @@ #ifndef _UAPI_LINUX_LSM_H #define _UAPI_LINUX_LSM_H +#include +#include + +/** + * struct lsm_ctx - LSM context information + * @id: the LSM id number, see LSM_ID_XXX + * @flags: LSM specific flags + * @len: length of the lsm_ctx struct, @ctx and any other data or padding + * @ctx_len: the size of @ctx + * @ctx: the LSM context value + * + * The @len field MUST be equal to the size of the lsm_ctx struct + * plus any additional padding and/or data placed after @ctx. + * + * In all cases @ctx_len MUST be equal to the length of @ctx. + * If @ctx is a string value it should be nul terminated with + * @ctx_len equal to `strlen(@ctx) + 1`. Binary values are + * supported. + * + * The @flags and @ctx fields SHOULD only be interpreted by the + * LSM specified by @id; they MUST be set to zero/0 when not used. + */ +struct lsm_ctx { + __u64 id; + __u64 flags; + __u64 len; + __u64 ctx_len; + __u8 ctx[]; +}; + /* * ID tokens to identify Linux Security Modules (LSMs) * @@ -51,4 +81,10 @@ #define LSM_ATTR_PREV 104 #define LSM_ATTR_SOCKCREATE 105 +/* + * LSM_FLAG_XXX definitions identify special handling instructions + * for the API. + */ +#define LSM_FLAG_SINGLE 0x0001 + #endif /* _UAPI_LINUX_LSM_H */ diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index e1a6e3c675c0..1f61b8452a6e 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -171,6 +171,8 @@ COND_SYSCALL(landlock_add_rule); COND_SYSCALL(landlock_restrict_self); COND_SYSCALL(fadvise64_64); COND_SYSCALL_COMPAT(fadvise64_64); +COND_SYSCALL(lsm_get_self_attr); +COND_SYSCALL(lsm_set_self_attr); /* CONFIG_MMU only */ COND_SYSCALL(swapon); diff --git a/security/Makefile b/security/Makefile index 18121f8f85cd..59f238490665 100644 --- a/security/Makefile +++ b/security/Makefile @@ -7,6 +7,7 @@ obj-$(CONFIG_KEYS) += keys/ # always enable default capabilities obj-y += commoncap.o +obj-$(CONFIG_SECURITY) += lsm_syscalls.o obj-$(CONFIG_MMU) += min_addr.o # Object file lists diff --git a/security/lsm_syscalls.c b/security/lsm_syscalls.c new file mode 100644 index 000000000000..226ae80d9683 --- /dev/null +++ b/security/lsm_syscalls.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * System calls implementing the Linux Security Module API. + * + * Copyright (C) 2022 Casey Schaufler + * Copyright (C) 2022 Intel Corporation + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/** + * sys_lsm_set_self_attr - Set current task's security module attribute + * @attr: which attribute to set + * @ctx: the LSM contexts + * @size: size of @ctx + * @flags: reserved for future use + * + * Sets the calling task's LSM context. On success this function + * returns 0. If the attribute specified cannot be set a negative + * value indicating the reason for the error is returned. + */ +SYSCALL_DEFINE4(lsm_set_self_attr, unsigned int, attr, struct lsm_ctx __user *, + ctx, size_t, size, u32, flags) +{ + return security_setselfattr(attr, ctx, size, flags); +} + +/** + * sys_lsm_get_self_attr - Return current task's security module attributes + * @attr: which attribute to return + * @ctx: the user-space destination for the information, or NULL + * @size: pointer to the size of space available to receive the data + * @flags: special handling options. LSM_FLAG_SINGLE indicates that only + * attributes associated with the LSM identified in the passed @ctx be + * reported. + * + * Returns the calling task's LSM contexts. On success this + * function returns the number of @ctx array elements. This value + * may be zero if there are no LSM contexts assigned. If @size is + * insufficient to contain the return data -E2BIG is returned and + * @size is set to the minimum required size. In all other cases + * a negative value indicating the error is returned. + */ +SYSCALL_DEFINE4(lsm_get_self_attr, unsigned int, attr, struct lsm_ctx __user *, + ctx, size_t __user *, size, u32, flags) +{ + return security_getselfattr(attr, ctx, size, flags); +} diff --git a/security/security.c b/security/security.c index c66f9faefa40..9757d009113f 100644 --- a/security/security.c +++ b/security/security.c @@ -3837,6 +3837,158 @@ void security_d_instantiate(struct dentry *dentry, struct inode *inode) } EXPORT_SYMBOL(security_d_instantiate); +/* + * Please keep this in sync with it's counterpart in security/lsm_syscalls.c + */ + +/** + * security_getselfattr - Read an LSM attribute of the current process. + * @attr: which attribute to return + * @uctx: the user-space destination for the information, or NULL + * @size: pointer to the size of space available to receive the data + * @flags: special handling options. LSM_FLAG_SINGLE indicates that only + * attributes associated with the LSM identified in the passed @ctx be + * reported. + * + * A NULL value for @uctx can be used to get both the number of attributes + * and the size of the data. + * + * Returns the number of attributes found on success, negative value + * on error. @size is reset to the total size of the data. + * If @size is insufficient to contain the data -E2BIG is returned. + */ +int security_getselfattr(unsigned int attr, struct lsm_ctx __user *uctx, + size_t __user *size, u32 flags) +{ + struct security_hook_list *hp; + struct lsm_ctx lctx = { .id = LSM_ID_UNDEF, }; + u8 __user *base = (u8 __user *)uctx; + size_t total = 0; + size_t entrysize; + size_t left; + bool toobig = false; + bool single = false; + int count = 0; + int rc; + + if (attr == LSM_ATTR_UNDEF) + return -EINVAL; + if (size == NULL) + return -EINVAL; + if (get_user(left, size)) + return -EFAULT; + + if (flags) { + /* + * Only flag supported is LSM_FLAG_SINGLE + */ + if (flags != LSM_FLAG_SINGLE) + return -EINVAL; + if (uctx && copy_from_user(&lctx, uctx, sizeof(lctx))) + return -EFAULT; + /* + * If the LSM ID isn't specified it is an error. + */ + if (lctx.id == LSM_ID_UNDEF) + return -EINVAL; + single = true; + } + + /* + * In the usual case gather all the data from the LSMs. + * In the single case only get the data from the LSM specified. + */ + hlist_for_each_entry(hp, &security_hook_heads.getselfattr, list) { + if (single && lctx.id != hp->lsmid->id) + continue; + entrysize = left; + if (base) + uctx = (struct lsm_ctx __user *)(base + total); + rc = hp->hook.getselfattr(attr, uctx, &entrysize, flags); + if (rc == -EOPNOTSUPP) { + rc = 0; + continue; + } + if (rc == -E2BIG) { + toobig = true; + left = 0; + } else if (rc < 0) + return rc; + else + left -= entrysize; + + total += entrysize; + count += rc; + if (single) + break; + } + if (put_user(total, size)) + return -EFAULT; + if (toobig) + return -E2BIG; + if (count == 0) + return LSM_RET_DEFAULT(getselfattr); + return count; +} + +/* + * Please keep this in sync with it's counterpart in security/lsm_syscalls.c + */ + +/** + * security_setselfattr - Set an LSM attribute on the current process. + * @attr: which attribute to set + * @uctx: the user-space source for the information + * @size: the size of the data + * @flags: reserved for future use, must be 0 + * + * Set an LSM attribute for the current process. The LSM, attribute + * and new value are included in @uctx. + * + * Returns 0 on success, -EINVAL if the input is inconsistent, -EFAULT + * if the user buffer is inaccessible, E2BIG if size is too big, or an + * LSM specific failure. + */ +int security_setselfattr(unsigned int attr, struct lsm_ctx __user *uctx, + size_t size, u32 flags) +{ + struct security_hook_list *hp; + struct lsm_ctx *lctx; + int rc = LSM_RET_DEFAULT(setselfattr); + + if (flags) + return -EINVAL; + if (size < sizeof(*lctx)) + return -EINVAL; + if (size > PAGE_SIZE) + return -E2BIG; + + lctx = kmalloc(size, GFP_KERNEL); + if (lctx == NULL) + return -ENOMEM; + + if (copy_from_user(lctx, uctx, size)) { + rc = -EFAULT; + goto free_out; + } + + if (size < lctx->len || size < lctx->ctx_len + sizeof(*lctx) || + lctx->len < lctx->ctx_len + sizeof(*lctx)) { + rc = -EINVAL; + goto free_out; + } + + hlist_for_each_entry(hp, &security_hook_heads.setselfattr, list) + if ((hp->lsmid->id) == lctx->id) { + rc = hp->hook.setselfattr(attr, lctx, size, flags); + break; + } + +free_out: + kfree(lctx); + return rc; +} + /** * security_getprocattr() - Read an attribute for a task * @p: the task -- cgit From edd71f8e266c7ba15eedfec338864e53ddde1c25 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Wed, 18 Oct 2023 17:41:41 -0400 Subject: lsm: drop LSM_ID_IMA When IMA becomes a proper LSM we will reintroduce an appropriate LSM ID, but drop it from the userspace API for now in an effort to put an end to debates around the naming of the LSM ID macro. Reviewed-by: Roberto Sassu Signed-off-by: Paul Moore --- include/uapi/linux/lsm.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/lsm.h b/include/uapi/linux/lsm.h index eeda59a77c02..f0386880a78e 100644 --- a/include/uapi/linux/lsm.h +++ b/include/uapi/linux/lsm.h @@ -54,14 +54,13 @@ struct lsm_ctx { #define LSM_ID_SELINUX 101 #define LSM_ID_SMACK 102 #define LSM_ID_TOMOYO 103 -#define LSM_ID_IMA 104 -#define LSM_ID_APPARMOR 105 -#define LSM_ID_YAMA 106 -#define LSM_ID_LOADPIN 107 -#define LSM_ID_SAFESETID 108 -#define LSM_ID_LOCKDOWN 109 -#define LSM_ID_BPF 110 -#define LSM_ID_LANDLOCK 111 +#define LSM_ID_APPARMOR 104 +#define LSM_ID_YAMA 105 +#define LSM_ID_LOADPIN 106 +#define LSM_ID_SAFESETID 107 +#define LSM_ID_LOCKDOWN 108 +#define LSM_ID_BPF 109 +#define LSM_ID_LANDLOCK 110 /* * LSM_ATTR_XXX definitions identify different LSM attributes -- cgit From bb58b90b1a8f753b582055adaf448214a8e22c31 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 27 Oct 2023 11:21:50 -0700 Subject: KVM: Introduce KVM_SET_USER_MEMORY_REGION2 Introduce a "version 2" of KVM_SET_USER_MEMORY_REGION so that additional information can be supplied without setting userspace up to fail. The padding in the new kvm_userspace_memory_region2 structure will be used to pass a file descriptor in addition to the userspace_addr, i.e. allow userspace to point at a file descriptor and map memory into a guest that is NOT mapped into host userspace. Alternatively, KVM could simply add "struct kvm_userspace_memory_region2" without a new ioctl(), but as Paolo pointed out, adding a new ioctl() makes detection of bad flags a bit more robust, e.g. if the new fd field is guarded only by a flag and not a new ioctl(), then a userspace bug (setting a "bad" flag) would generate out-of-bounds access instead of an -EINVAL error. Cc: Jarkko Sakkinen Reviewed-by: Paolo Bonzini Reviewed-by: Xiaoyao Li Signed-off-by: Sean Christopherson Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Message-Id: <20231027182217.3615211-9-seanjc@google.com> Acked-by: Kai Huang Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 22 ++++++++++++++++ arch/x86/kvm/x86.c | 2 +- include/linux/kvm_host.h | 4 +-- include/uapi/linux/kvm.h | 13 ++++++++++ virt/kvm/kvm_main.c | 57 ++++++++++++++++++++++++++++++++++++------ 5 files changed, 87 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 7025b3751027..9edd9e436bab 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6192,6 +6192,28 @@ to know what fields can be changed for the system register described by ``op0, op1, crn, crm, op2``. KVM rejects ID register values that describe a superset of the features supported by the system. +4.140 KVM_SET_USER_MEMORY_REGION2 +--------------------------------- + +:Capability: KVM_CAP_USER_MEMORY2 +:Architectures: all +:Type: vm ioctl +:Parameters: struct kvm_userspace_memory_region2 (in) +:Returns: 0 on success, -1 on error + +:: + + struct kvm_userspace_memory_region2 { + __u32 slot; + __u32 flags; + __u64 guest_phys_addr; + __u64 memory_size; /* bytes */ + __u64 userspace_addr; /* start of the userspace allocated memory */ + __u64 pad[16]; + }; + +See KVM_SET_USER_MEMORY_REGION. + 5. The kvm_run structure ======================== diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2c924075f6f1..7b389f27dffc 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -12576,7 +12576,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, } for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - struct kvm_userspace_memory_region m; + struct kvm_userspace_memory_region2 m; m.slot = id | (i << 16); m.flags = 0; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5faba69403ac..4e741ff27af3 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1146,9 +1146,9 @@ enum kvm_mr_change { }; int kvm_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem); + const struct kvm_userspace_memory_region2 *mem); int __kvm_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem); + const struct kvm_userspace_memory_region2 *mem); void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen); int kvm_arch_prepare_memory_region(struct kvm *kvm, diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 211b86de35ac..308cc70bd6ab 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -95,6 +95,16 @@ struct kvm_userspace_memory_region { __u64 userspace_addr; /* start of the userspace allocated memory */ }; +/* for KVM_SET_USER_MEMORY_REGION2 */ +struct kvm_userspace_memory_region2 { + __u32 slot; + __u32 flags; + __u64 guest_phys_addr; + __u64 memory_size; + __u64 userspace_addr; + __u64 pad[16]; +}; + /* * The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for * userspace, other bits are reserved for kvm internal use which are defined @@ -1201,6 +1211,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228 #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229 #define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230 +#define KVM_CAP_USER_MEMORY2 231 #ifdef KVM_CAP_IRQ_ROUTING @@ -1483,6 +1494,8 @@ struct kvm_vfio_spapr_tce { struct kvm_userspace_memory_region) #define KVM_SET_TSS_ADDR _IO(KVMIO, 0x47) #define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO, 0x48, __u64) +#define KVM_SET_USER_MEMORY_REGION2 _IOW(KVMIO, 0x49, \ + struct kvm_userspace_memory_region2) /* enable ucontrol for s390 */ struct kvm_s390_ucas_mapping { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index dc81279ea385..756b94ecd511 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1580,7 +1580,15 @@ static void kvm_replace_memslot(struct kvm *kvm, } } -static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem) +/* + * Flags that do not access any of the extra space of struct + * kvm_userspace_memory_region2. KVM_SET_USER_MEMORY_REGION_V1_FLAGS + * only allows these. + */ +#define KVM_SET_USER_MEMORY_REGION_V1_FLAGS \ + (KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY) + +static int check_memory_region_flags(const struct kvm_userspace_memory_region2 *mem) { u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES; @@ -1982,7 +1990,7 @@ static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id, * Must be called holding kvm->slots_lock for write. */ int __kvm_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem) + const struct kvm_userspace_memory_region2 *mem) { struct kvm_memory_slot *old, *new; struct kvm_memslots *slots; @@ -2086,7 +2094,7 @@ int __kvm_set_memory_region(struct kvm *kvm, EXPORT_SYMBOL_GPL(__kvm_set_memory_region); int kvm_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem) + const struct kvm_userspace_memory_region2 *mem) { int r; @@ -2098,7 +2106,7 @@ int kvm_set_memory_region(struct kvm *kvm, EXPORT_SYMBOL_GPL(kvm_set_memory_region); static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem) + struct kvm_userspace_memory_region2 *mem) { if ((u16)mem->slot >= KVM_USER_MEM_SLOTS) return -EINVAL; @@ -4568,6 +4576,7 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) { switch (arg) { case KVM_CAP_USER_MEMORY: + case KVM_CAP_USER_MEMORY2: case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS: case KVM_CAP_INTERNAL_ERROR_DATA: @@ -4823,6 +4832,14 @@ static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm) return fd; } +#define SANITY_CHECK_MEM_REGION_FIELD(field) \ +do { \ + BUILD_BUG_ON(offsetof(struct kvm_userspace_memory_region, field) != \ + offsetof(struct kvm_userspace_memory_region2, field)); \ + BUILD_BUG_ON(sizeof_field(struct kvm_userspace_memory_region, field) != \ + sizeof_field(struct kvm_userspace_memory_region2, field)); \ +} while (0) + static long kvm_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -4845,15 +4862,39 @@ static long kvm_vm_ioctl(struct file *filp, r = kvm_vm_ioctl_enable_cap_generic(kvm, &cap); break; } + case KVM_SET_USER_MEMORY_REGION2: case KVM_SET_USER_MEMORY_REGION: { - struct kvm_userspace_memory_region kvm_userspace_mem; + struct kvm_userspace_memory_region2 mem; + unsigned long size; + + if (ioctl == KVM_SET_USER_MEMORY_REGION) { + /* + * Fields beyond struct kvm_userspace_memory_region shouldn't be + * accessed, but avoid leaking kernel memory in case of a bug. + */ + memset(&mem, 0, sizeof(mem)); + size = sizeof(struct kvm_userspace_memory_region); + } else { + size = sizeof(struct kvm_userspace_memory_region2); + } + + /* Ensure the common parts of the two structs are identical. */ + SANITY_CHECK_MEM_REGION_FIELD(slot); + SANITY_CHECK_MEM_REGION_FIELD(flags); + SANITY_CHECK_MEM_REGION_FIELD(guest_phys_addr); + SANITY_CHECK_MEM_REGION_FIELD(memory_size); + SANITY_CHECK_MEM_REGION_FIELD(userspace_addr); r = -EFAULT; - if (copy_from_user(&kvm_userspace_mem, argp, - sizeof(kvm_userspace_mem))) + if (copy_from_user(&mem, argp, size)) + goto out; + + r = -EINVAL; + if (ioctl == KVM_SET_USER_MEMORY_REGION && + (mem.flags & ~KVM_SET_USER_MEMORY_REGION_V1_FLAGS)) goto out; - r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem); + r = kvm_vm_ioctl_set_memory_region(kvm, &mem); break; } case KVM_GET_DIRTY_LOG: { -- cgit From 16f95f3b95caded251a0440051e44a2fbe9e5f55 Mon Sep 17 00:00:00 2001 From: Chao Peng Date: Fri, 27 Oct 2023 11:21:51 -0700 Subject: KVM: Add KVM_EXIT_MEMORY_FAULT exit to report faults to userspace Add a new KVM exit type to allow userspace to handle memory faults that KVM cannot resolve, but that userspace *may* be able to handle (without terminating the guest). KVM will initially use KVM_EXIT_MEMORY_FAULT to report implicit conversions between private and shared memory. With guest private memory, there will be two kind of memory conversions: - explicit conversion: happens when the guest explicitly calls into KVM to map a range (as private or shared) - implicit conversion: happens when the guest attempts to access a gfn that is configured in the "wrong" state (private vs. shared) On x86 (first architecture to support guest private memory), explicit conversions will be reported via KVM_EXIT_HYPERCALL+KVM_HC_MAP_GPA_RANGE, but reporting KVM_EXIT_HYPERCALL for implicit conversions is undesriable as there is (obviously) no hypercall, and there is no guarantee that the guest actually intends to convert between private and shared, i.e. what KVM thinks is an implicit conversion "request" could actually be the result of a guest code bug. KVM_EXIT_MEMORY_FAULT will be used to report memory faults that appear to be implicit conversions. Note! To allow for future possibilities where KVM reports KVM_EXIT_MEMORY_FAULT and fills run->memory_fault on _any_ unresolved fault, KVM returns "-EFAULT" (-1 with errno == EFAULT from userspace's perspective), not '0'! Due to historical baggage within KVM, exiting to userspace with '0' from deep callstacks, e.g. in emulation paths, is infeasible as doing so would require a near-complete overhaul of KVM, whereas KVM already propagates -errno return codes to userspace even when the -errno originated in a low level helper. Report the gpa+size instead of a single gfn even though the initial usage is expected to always report single pages. It's entirely possible, likely even, that KVM will someday support sub-page granularity faults, e.g. Intel's sub-page protection feature allows for additional protections at 128-byte granularity. Link: https://lore.kernel.org/all/20230908222905.1321305-5-amoorthy@google.com Link: https://lore.kernel.org/all/ZQ3AmLO2SYv3DszH@google.com Cc: Anish Moorthy Cc: David Matlack Suggested-by: Sean Christopherson Co-developed-by: Yu Zhang Signed-off-by: Yu Zhang Signed-off-by: Chao Peng Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson Reviewed-by: Paolo Bonzini Message-Id: <20231027182217.3615211-10-seanjc@google.com> Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Reviewed-by: Xiaoyao Li Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 41 +++++++++++++++++++++++++++++++++++++++++ arch/x86/kvm/x86.c | 1 + include/linux/kvm_host.h | 11 +++++++++++ include/uapi/linux/kvm.h | 8 ++++++++ 4 files changed, 61 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 9edd9e436bab..27d945d5b4e4 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6846,6 +6846,26 @@ array field represents return values. The userspace should update the return values of SBI call before resuming the VCPU. For more details on RISC-V SBI spec refer, https://github.com/riscv/riscv-sbi-doc. +:: + + /* KVM_EXIT_MEMORY_FAULT */ + struct { + __u64 flags; + __u64 gpa; + __u64 size; + } memory_fault; + +KVM_EXIT_MEMORY_FAULT indicates the vCPU has encountered a memory fault that +could not be resolved by KVM. The 'gpa' and 'size' (in bytes) describe the +guest physical address range [gpa, gpa + size) of the fault. The 'flags' field +describes properties of the faulting access that are likely pertinent. +Currently, no flags are defined. + +Note! KVM_EXIT_MEMORY_FAULT is unique among all KVM exit reasons in that it +accompanies a return code of '-1', not '0'! errno will always be set to EFAULT +or EHWPOISON when KVM exits with KVM_EXIT_MEMORY_FAULT, userspace should assume +kvm_run.exit_reason is stale/undefined for all other error numbers. + :: /* KVM_EXIT_NOTIFY */ @@ -7880,6 +7900,27 @@ This capability is aimed to mitigate the threat that malicious VMs can cause CPU stuck (due to event windows don't open up) and make the CPU unavailable to host or other VMs. +7.34 KVM_CAP_MEMORY_FAULT_INFO +------------------------------ + +:Architectures: x86 +:Returns: Informational only, -EINVAL on direct KVM_ENABLE_CAP. + +The presence of this capability indicates that KVM_RUN will fill +kvm_run.memory_fault if KVM cannot resolve a guest page fault VM-Exit, e.g. if +there is a valid memslot but no backing VMA for the corresponding host virtual +address. + +The information in kvm_run.memory_fault is valid if and only if KVM_RUN returns +an error with errno=EFAULT or errno=EHWPOISON *and* kvm_run.exit_reason is set +to KVM_EXIT_MEMORY_FAULT. + +Note: Userspaces which attempt to resolve memory faults so that they can retry +KVM_RUN are encouraged to guard against repeatedly receiving the same +error/annotated fault. + +See KVM_EXIT_MEMORY_FAULT for more information. + 8. Other capabilities. ====================== diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7b389f27dffc..8f9d8939b63b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4625,6 +4625,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ENABLE_CAP: case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES: case KVM_CAP_IRQFD_RESAMPLE: + case KVM_CAP_MEMORY_FAULT_INFO: r = 1; break; case KVM_CAP_EXIT_HYPERCALL: diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4e741ff27af3..96aa930536b1 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2327,4 +2327,15 @@ static inline void kvm_account_pgtable_pages(void *virt, int nr) /* Max number of entries allowed for each kvm dirty ring */ #define KVM_DIRTY_RING_MAX_ENTRIES 65536 +static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, + gpa_t gpa, gpa_t size) +{ + vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT; + vcpu->run->memory_fault.gpa = gpa; + vcpu->run->memory_fault.size = size; + + /* Flags are not (yet) defined or communicated to userspace. */ + vcpu->run->memory_fault.flags = 0; +} + #endif diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 308cc70bd6ab..59010a685007 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -275,6 +275,7 @@ struct kvm_xen_exit { #define KVM_EXIT_RISCV_CSR 36 #define KVM_EXIT_NOTIFY 37 #define KVM_EXIT_LOONGARCH_IOCSR 38 +#define KVM_EXIT_MEMORY_FAULT 39 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -528,6 +529,12 @@ struct kvm_run { #define KVM_NOTIFY_CONTEXT_INVALID (1 << 0) __u32 flags; } notify; + /* KVM_EXIT_MEMORY_FAULT */ + struct { + __u64 flags; + __u64 gpa; + __u64 size; + } memory_fault; /* Fix the size of the union. */ char padding[256]; }; @@ -1212,6 +1219,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229 #define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230 #define KVM_CAP_USER_MEMORY2 231 +#define KVM_CAP_MEMORY_FAULT_INFO 232 #ifdef KVM_CAP_IRQ_ROUTING -- cgit From 5a475554db1e476a14216e742ea2bdb77362d5d5 Mon Sep 17 00:00:00 2001 From: Chao Peng Date: Fri, 27 Oct 2023 11:21:55 -0700 Subject: KVM: Introduce per-page memory attributes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In confidential computing usages, whether a page is private or shared is necessary information for KVM to perform operations like page fault handling, page zapping etc. There are other potential use cases for per-page memory attributes, e.g. to make memory read-only (or no-exec, or exec-only, etc.) without having to modify memslots. Introduce the KVM_SET_MEMORY_ATTRIBUTES ioctl, advertised by KVM_CAP_MEMORY_ATTRIBUTES, to allow userspace to set the per-page memory attributes to a guest memory range. Use an xarray to store the per-page attributes internally, with a naive, not fully optimized implementation, i.e. prioritize correctness over performance for the initial implementation. Use bit 3 for the PRIVATE attribute so that KVM can use bits 0-2 for RWX attributes/protections in the future, e.g. to give userspace fine-grained control over read, write, and execute protections for guest memory. Provide arch hooks for handling attribute changes before and after common code sets the new attributes, e.g. x86 will use the "pre" hook to zap all relevant mappings, and the "post" hook to track whether or not hugepages can be used to map the range. To simplify the implementation wrap the entire sequence with kvm_mmu_invalidate_{begin,end}() even though the operation isn't strictly guaranteed to be an invalidation. For the initial use case, x86 *will* always invalidate memory, and preventing arch code from creating new mappings while the attributes are in flux makes it much easier to reason about the correctness of consuming attributes. It's possible that future usages may not require an invalidation, e.g. if KVM ends up supporting RWX protections and userspace grants _more_ protections, but again opt for simplicity and punt optimizations to if/when they are needed. Suggested-by: Sean Christopherson Link: https://lore.kernel.org/all/Y2WB48kD0J4VGynX@google.com Cc: Fuad Tabba Cc: Xu Yilun Cc: Mickaël Salaün Signed-off-by: Chao Peng Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson Message-Id: <20231027182217.3615211-14-seanjc@google.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 36 +++++++ include/linux/kvm_host.h | 19 ++++ include/uapi/linux/kvm.h | 13 +++ virt/kvm/Kconfig | 4 + virt/kvm/kvm_main.c | 216 +++++++++++++++++++++++++++++++++++++++++ 5 files changed, 288 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 27d945d5b4e4..081ef09d3148 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6214,6 +6214,42 @@ superset of the features supported by the system. See KVM_SET_USER_MEMORY_REGION. +4.141 KVM_SET_MEMORY_ATTRIBUTES +------------------------------- + +:Capability: KVM_CAP_MEMORY_ATTRIBUTES +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_memory_attributes (in) +:Returns: 0 on success, <0 on error + +KVM_SET_MEMORY_ATTRIBUTES allows userspace to set memory attributes for a range +of guest physical memory. + +:: + + struct kvm_memory_attributes { + __u64 address; + __u64 size; + __u64 attributes; + __u64 flags; + }; + + #define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3) + +The address and size must be page aligned. The supported attributes can be +retrieved via ioctl(KVM_CHECK_EXTENSION) on KVM_CAP_MEMORY_ATTRIBUTES. If +executed on a VM, KVM_CAP_MEMORY_ATTRIBUTES precisely returns the attributes +supported by that VM. If executed at system scope, KVM_CAP_MEMORY_ATTRIBUTES +returns all attributes supported by KVM. The only attribute defined at this +time is KVM_MEMORY_ATTRIBUTE_PRIVATE, which marks the associated gfn as being +guest private memory. + +Note, there is no "get" API. Userspace is responsible for explicitly tracking +the state of a gfn/page as needed. + +The "flags" field is reserved for future extensions and must be '0'. + 5. The kvm_run structure ======================== diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 96aa930536b1..68a144cb7dbc 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -256,6 +256,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER union kvm_mmu_notifier_arg { pte_t pte; + unsigned long attributes; }; struct kvm_gfn_range { @@ -806,6 +807,10 @@ struct kvm { #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER struct notifier_block pm_notifier; +#endif +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + /* Protected by slots_locks (for writes) and RCU (for reads) */ + struct xarray mem_attr_array; #endif char stats_id[KVM_STATS_NAME_SIZE]; }; @@ -2338,4 +2343,18 @@ static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, vcpu->run->memory_fault.flags = 0; } +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn) +{ + return xa_to_value(xa_load(&kvm->mem_attr_array, gfn)); +} + +bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, + unsigned long attrs); +bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range); +bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range); +#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ + #endif diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 59010a685007..e8d167e54980 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1220,6 +1220,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230 #define KVM_CAP_USER_MEMORY2 231 #define KVM_CAP_MEMORY_FAULT_INFO 232 +#define KVM_CAP_MEMORY_ATTRIBUTES 233 #ifdef KVM_CAP_IRQ_ROUTING @@ -2288,4 +2289,16 @@ struct kvm_s390_zpci_op { /* flags for kvm_s390_zpci_op->u.reg_aen.flags */ #define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0) +/* Available with KVM_CAP_MEMORY_ATTRIBUTES */ +#define KVM_SET_MEMORY_ATTRIBUTES _IOW(KVMIO, 0xd2, struct kvm_memory_attributes) + +struct kvm_memory_attributes { + __u64 address; + __u64 size; + __u64 attributes; + __u64 flags; +}; + +#define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3) + #endif /* __LINUX_KVM_H */ diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index ecae2914c97e..5bd7fcaf9089 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -96,3 +96,7 @@ config KVM_GENERIC_HARDWARE_ENABLING config KVM_GENERIC_MMU_NOTIFIER select MMU_NOTIFIER bool + +config KVM_GENERIC_MEMORY_ATTRIBUTES + select KVM_GENERIC_MMU_NOTIFIER + bool diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 7f3291dec7a6..f1a575d39b3b 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1211,6 +1211,9 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) spin_lock_init(&kvm->mn_invalidate_lock); rcuwait_init(&kvm->mn_memslots_update_rcuwait); xa_init(&kvm->vcpu_array); +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + xa_init(&kvm->mem_attr_array); +#endif INIT_LIST_HEAD(&kvm->gpc_list); spin_lock_init(&kvm->gpc_lock); @@ -1391,6 +1394,9 @@ static void kvm_destroy_vm(struct kvm *kvm) } cleanup_srcu_struct(&kvm->irq_srcu); cleanup_srcu_struct(&kvm->srcu); +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + xa_destroy(&kvm->mem_attr_array); +#endif kvm_arch_free_vm(kvm); preempt_notifier_dec(); hardware_disable_all(); @@ -2397,6 +2403,200 @@ static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, } #endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +/* + * Returns true if _all_ gfns in the range [@start, @end) have attributes + * matching @attrs. + */ +bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, + unsigned long attrs) +{ + XA_STATE(xas, &kvm->mem_attr_array, start); + unsigned long index; + bool has_attrs; + void *entry; + + rcu_read_lock(); + + if (!attrs) { + has_attrs = !xas_find(&xas, end - 1); + goto out; + } + + has_attrs = true; + for (index = start; index < end; index++) { + do { + entry = xas_next(&xas); + } while (xas_retry(&xas, entry)); + + if (xas.xa_index != index || xa_to_value(entry) != attrs) { + has_attrs = false; + break; + } + } + +out: + rcu_read_unlock(); + return has_attrs; +} + +static u64 kvm_supported_mem_attributes(struct kvm *kvm) +{ + if (!kvm) + return KVM_MEMORY_ATTRIBUTE_PRIVATE; + + return 0; +} + +static __always_inline void kvm_handle_gfn_range(struct kvm *kvm, + struct kvm_mmu_notifier_range *range) +{ + struct kvm_gfn_range gfn_range; + struct kvm_memory_slot *slot; + struct kvm_memslots *slots; + struct kvm_memslot_iter iter; + bool found_memslot = false; + bool ret = false; + int i; + + gfn_range.arg = range->arg; + gfn_range.may_block = range->may_block; + + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + slots = __kvm_memslots(kvm, i); + + kvm_for_each_memslot_in_gfn_range(&iter, slots, range->start, range->end) { + slot = iter.slot; + gfn_range.slot = slot; + + gfn_range.start = max(range->start, slot->base_gfn); + gfn_range.end = min(range->end, slot->base_gfn + slot->npages); + if (gfn_range.start >= gfn_range.end) + continue; + + if (!found_memslot) { + found_memslot = true; + KVM_MMU_LOCK(kvm); + if (!IS_KVM_NULL_FN(range->on_lock)) + range->on_lock(kvm); + } + + ret |= range->handler(kvm, &gfn_range); + } + } + + if (range->flush_on_ret && ret) + kvm_flush_remote_tlbs(kvm); + + if (found_memslot) + KVM_MMU_UNLOCK(kvm); +} + +static bool kvm_pre_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range) +{ + /* + * Unconditionally add the range to the invalidation set, regardless of + * whether or not the arch callback actually needs to zap SPTEs. E.g. + * if KVM supports RWX attributes in the future and the attributes are + * going from R=>RW, zapping isn't strictly necessary. Unconditionally + * adding the range allows KVM to require that MMU invalidations add at + * least one range between begin() and end(), e.g. allows KVM to detect + * bugs where the add() is missed. Relaxing the rule *might* be safe, + * but it's not obvious that allowing new mappings while the attributes + * are in flux is desirable or worth the complexity. + */ + kvm_mmu_invalidate_range_add(kvm, range->start, range->end); + + return kvm_arch_pre_set_memory_attributes(kvm, range); +} + +/* Set @attributes for the gfn range [@start, @end). */ +static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end, + unsigned long attributes) +{ + struct kvm_mmu_notifier_range pre_set_range = { + .start = start, + .end = end, + .handler = kvm_pre_set_memory_attributes, + .on_lock = kvm_mmu_invalidate_begin, + .flush_on_ret = true, + .may_block = true, + }; + struct kvm_mmu_notifier_range post_set_range = { + .start = start, + .end = end, + .arg.attributes = attributes, + .handler = kvm_arch_post_set_memory_attributes, + .on_lock = kvm_mmu_invalidate_end, + .may_block = true, + }; + unsigned long i; + void *entry; + int r = 0; + + entry = attributes ? xa_mk_value(attributes) : NULL; + + mutex_lock(&kvm->slots_lock); + + /* Nothing to do if the entire range as the desired attributes. */ + if (kvm_range_has_memory_attributes(kvm, start, end, attributes)) + goto out_unlock; + + /* + * Reserve memory ahead of time to avoid having to deal with failures + * partway through setting the new attributes. + */ + for (i = start; i < end; i++) { + r = xa_reserve(&kvm->mem_attr_array, i, GFP_KERNEL_ACCOUNT); + if (r) + goto out_unlock; + } + + kvm_handle_gfn_range(kvm, &pre_set_range); + + for (i = start; i < end; i++) { + r = xa_err(xa_store(&kvm->mem_attr_array, i, entry, + GFP_KERNEL_ACCOUNT)); + KVM_BUG_ON(r, kvm); + } + + kvm_handle_gfn_range(kvm, &post_set_range); + +out_unlock: + mutex_unlock(&kvm->slots_lock); + + return r; +} +static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm, + struct kvm_memory_attributes *attrs) +{ + gfn_t start, end; + + /* flags is currently not used. */ + if (attrs->flags) + return -EINVAL; + if (attrs->attributes & ~kvm_supported_mem_attributes(kvm)) + return -EINVAL; + if (attrs->size == 0 || attrs->address + attrs->size < attrs->address) + return -EINVAL; + if (!PAGE_ALIGNED(attrs->address) || !PAGE_ALIGNED(attrs->size)) + return -EINVAL; + + start = attrs->address >> PAGE_SHIFT; + end = (attrs->address + attrs->size) >> PAGE_SHIFT; + + /* + * xarray tracks data using "unsigned long", and as a result so does + * KVM. For simplicity, supports generic attributes only on 64-bit + * architectures. + */ + BUILD_BUG_ON(sizeof(attrs->attributes) != sizeof(unsigned long)); + + return kvm_vm_set_mem_attributes(kvm, start, end, attrs->attributes); +} +#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ + struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) { return __gfn_to_memslot(kvm_memslots(kvm), gfn); @@ -4641,6 +4841,10 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_BINARY_STATS_FD: case KVM_CAP_SYSTEM_EVENT_DATA: return 1; +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + case KVM_CAP_MEMORY_ATTRIBUTES: + return kvm_supported_mem_attributes(kvm); +#endif default: break; } @@ -5034,6 +5238,18 @@ static long kvm_vm_ioctl(struct file *filp, break; } #endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */ +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + case KVM_SET_MEMORY_ATTRIBUTES: { + struct kvm_memory_attributes attrs; + + r = -EFAULT; + if (copy_from_user(&attrs, argp, sizeof(attrs))) + goto out; + + r = kvm_vm_ioctl_set_mem_attributes(kvm, &attrs); + break; + } +#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ case KVM_CREATE_DEVICE: { struct kvm_create_device cd; -- cgit From 07afe1ba288c04280622fa002ed385f1ac0b6fe6 Mon Sep 17 00:00:00 2001 From: Linus Lüssing Date: Thu, 7 Sep 2023 03:09:08 +0200 Subject: batman-adv: mcast: implement multicast packet reception and forwarding MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Implement functionality to receive and forward a new TVLV capable multicast packet type. The new batman-adv multicast packet type allows to contain several originator destination addresses within a TVLV. Routers on the way will potentially split the batman-adv multicast packet and adjust its tracker TVLV contents. Routing decisions are still based on the selected BATMAN IV or BATMAN V routing algorithm. So this new batman-adv multicast packet type retains the same loop-free properties. Also a new OGM multicast TVLV flag is introduced to signal to other nodes that we are capable of handling a batman-adv multicast packet and multicast tracker TVLV. And that all of our hard interfaces have an MTU of at least 1280 bytes (IPv6 minimum MTU), as a simple solution for now to avoid MTU issues while forwarding. Signed-off-by: Linus Lüssing Signed-off-by: Simon Wunderlich --- include/uapi/linux/batadv_packet.h | 45 ++++++- net/batman-adv/Makefile | 1 + net/batman-adv/fragmentation.c | 8 +- net/batman-adv/main.c | 2 + net/batman-adv/multicast.c | 48 +++++++- net/batman-adv/multicast.h | 5 + net/batman-adv/multicast_forw.c | 239 +++++++++++++++++++++++++++++++++++++ net/batman-adv/originator.c | 28 +++++ net/batman-adv/originator.h | 3 + net/batman-adv/routing.c | 70 +++++++++++ net/batman-adv/routing.h | 11 ++ net/batman-adv/soft-interface.c | 12 ++ net/batman-adv/types.h | 64 ++++++++++ 13 files changed, 518 insertions(+), 18 deletions(-) create mode 100644 net/batman-adv/multicast_forw.c (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h index 9204e4494b25..6e25753015df 100644 --- a/include/uapi/linux/batadv_packet.h +++ b/include/uapi/linux/batadv_packet.h @@ -116,6 +116,9 @@ enum batadv_icmp_packettype { * only need routable IPv4 multicast packets we signed up for explicitly * @BATADV_MCAST_WANT_NO_RTR6: we have no IPv6 multicast router and therefore * only need routable IPv6 multicast packets we signed up for explicitly + * @BATADV_MCAST_HAVE_MC_PTYPE_CAPA: we can parse, receive and forward + * batman-adv multicast packets with a multicast tracker TVLV. And all our + * hard interfaces have an MTU of at least 1280 bytes. */ enum batadv_mcast_flags { BATADV_MCAST_WANT_ALL_UNSNOOPABLES = 1UL << 0, @@ -123,6 +126,7 @@ enum batadv_mcast_flags { BATADV_MCAST_WANT_ALL_IPV6 = 1UL << 2, BATADV_MCAST_WANT_NO_RTR4 = 1UL << 3, BATADV_MCAST_WANT_NO_RTR6 = 1UL << 4, + BATADV_MCAST_HAVE_MC_PTYPE_CAPA = 1UL << 5, }; /* tt data subtypes */ @@ -174,14 +178,16 @@ enum batadv_bla_claimframe { * @BATADV_TVLV_TT: translation table tvlv * @BATADV_TVLV_ROAM: roaming advertisement tvlv * @BATADV_TVLV_MCAST: multicast capability tvlv + * @BATADV_TVLV_MCAST_TRACKER: multicast tracker tvlv */ enum batadv_tvlv_type { - BATADV_TVLV_GW = 0x01, - BATADV_TVLV_DAT = 0x02, - BATADV_TVLV_NC = 0x03, - BATADV_TVLV_TT = 0x04, - BATADV_TVLV_ROAM = 0x05, - BATADV_TVLV_MCAST = 0x06, + BATADV_TVLV_GW = 0x01, + BATADV_TVLV_DAT = 0x02, + BATADV_TVLV_NC = 0x03, + BATADV_TVLV_TT = 0x04, + BATADV_TVLV_ROAM = 0x05, + BATADV_TVLV_MCAST = 0x06, + BATADV_TVLV_MCAST_TRACKER = 0x07, }; #pragma pack(2) @@ -487,6 +493,25 @@ struct batadv_bcast_packet { */ }; +/** + * struct batadv_mcast_packet - multicast packet for network payload + * @packet_type: batman-adv packet type, part of the general header + * @version: batman-adv protocol version, part of the general header + * @ttl: time to live for this packet, part of the general header + * @reserved: reserved byte for alignment + * @tvlv_len: length of the appended tvlv buffer (in bytes) + */ +struct batadv_mcast_packet { + __u8 packet_type; + __u8 version; + __u8 ttl; + __u8 reserved; + __be16 tvlv_len; + /* "4 bytes boundary + 2 bytes" long to make the payload after the + * following ethernet header again 4 bytes boundary aligned + */ +}; + /** * struct batadv_coded_packet - network coded packet * @packet_type: batman-adv packet type, part of the general header @@ -628,6 +653,14 @@ struct batadv_tvlv_mcast_data { __u8 reserved[3]; }; +/** + * struct batadv_tvlv_mcast_tracker - payload of a multicast tracker tvlv + * @num_dests: number of subsequent destination originator MAC addresses + */ +struct batadv_tvlv_mcast_tracker { + __be16 num_dests; +}; + #pragma pack() #endif /* _UAPI_LINUX_BATADV_PACKET_H_ */ diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index 3bd0760c76a2..b51d8b071b56 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -20,6 +20,7 @@ batman-adv-y += hash.o batman-adv-$(CONFIG_BATMAN_ADV_DEBUG) += log.o batman-adv-y += main.o batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast.o +batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast_forw.o batman-adv-y += netlink.o batman-adv-$(CONFIG_BATMAN_ADV_NC) += network-coding.o batman-adv-y += originator.o diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index c120c7c6d25f..757c084ac2d1 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -25,7 +25,6 @@ #include "hard-interface.h" #include "originator.h" -#include "routing.h" #include "send.h" /** @@ -351,18 +350,14 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb, struct batadv_orig_node *orig_node_src) { struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); - struct batadv_orig_node *orig_node_dst; struct batadv_neigh_node *neigh_node = NULL; struct batadv_frag_packet *packet; u16 total_size; bool ret = false; packet = (struct batadv_frag_packet *)skb->data; - orig_node_dst = batadv_orig_hash_find(bat_priv, packet->dest); - if (!orig_node_dst) - goto out; - neigh_node = batadv_find_router(bat_priv, orig_node_dst, recv_if); + neigh_node = batadv_orig_to_router(bat_priv, packet->dest, recv_if); if (!neigh_node) goto out; @@ -381,7 +376,6 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb, } out: - batadv_orig_node_put(orig_node_dst); batadv_neigh_node_put(neigh_node); return ret; } diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index e8a449915566..50b2bf2b748c 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -532,6 +532,8 @@ static void batadv_recv_handler_init(void) /* broadcast packet */ batadv_rx_handler[BATADV_BCAST] = batadv_recv_bcast_packet; + /* multicast packet */ + batadv_rx_handler[BATADV_MCAST] = batadv_recv_mcast_packet; /* unicast packets ... */ /* unicast with 4 addresses packet */ diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 315394f12c55..dfc2c645b13f 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -235,6 +235,37 @@ static u8 batadv_mcast_mla_rtr_flags_get(struct batadv_priv *bat_priv, return flags; } +/** + * batadv_mcast_mla_forw_flags_get() - get multicast forwarding flags + * @bat_priv: the bat priv with all the soft interface information + * + * Checks if all active hard interfaces have an MTU larger or equal to 1280 + * bytes (IPv6 minimum MTU). + * + * Return: BATADV_MCAST_HAVE_MC_PTYPE_CAPA if yes, BATADV_NO_FLAGS otherwise. + */ +static u8 batadv_mcast_mla_forw_flags_get(struct batadv_priv *bat_priv) +{ + const struct batadv_hard_iface *hard_iface; + + rcu_read_lock(); + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->if_status != BATADV_IF_ACTIVE) + continue; + + if (hard_iface->soft_iface != bat_priv->soft_iface) + continue; + + if (hard_iface->net_dev->mtu < IPV6_MIN_MTU) { + rcu_read_unlock(); + return BATADV_NO_FLAGS; + } + } + rcu_read_unlock(); + + return BATADV_MCAST_HAVE_MC_PTYPE_CAPA; +} + /** * batadv_mcast_mla_flags_get() - get the new multicast flags * @bat_priv: the bat priv with all the soft interface information @@ -256,6 +287,7 @@ batadv_mcast_mla_flags_get(struct batadv_priv *bat_priv) mla_flags.enabled = 1; mla_flags.tvlv_flags |= batadv_mcast_mla_rtr_flags_get(bat_priv, bridge); + mla_flags.tvlv_flags |= batadv_mcast_mla_forw_flags_get(bat_priv); if (!bridge) return mla_flags; @@ -806,23 +838,25 @@ static void batadv_mcast_flags_log(struct batadv_priv *bat_priv, u8 flags) { bool old_enabled = bat_priv->mcast.mla_flags.enabled; u8 old_flags = bat_priv->mcast.mla_flags.tvlv_flags; - char str_old_flags[] = "[.... . ]"; + char str_old_flags[] = "[.... . .]"; - sprintf(str_old_flags, "[%c%c%c%s%s]", + sprintf(str_old_flags, "[%c%c%c%s%s%c]", (old_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.', (old_flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.', (old_flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.', !(old_flags & BATADV_MCAST_WANT_NO_RTR4) ? "R4" : ". ", - !(old_flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". "); + !(old_flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". ", + !(old_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA) ? 'P' : '.'); batadv_dbg(BATADV_DBG_MCAST, bat_priv, - "Changing multicast flags from '%s' to '[%c%c%c%s%s]'\n", + "Changing multicast flags from '%s' to '[%c%c%c%s%s%c]'\n", old_enabled ? str_old_flags : "", (flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.', (flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.', (flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.', !(flags & BATADV_MCAST_WANT_NO_RTR4) ? "R4" : ". ", - !(flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". "); + !(flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". ", + !(flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA) ? 'P' : '.'); } /** @@ -1820,6 +1854,10 @@ void batadv_mcast_init(struct batadv_priv *bat_priv) batadv_tvlv_handler_register(bat_priv, batadv_mcast_tvlv_ogm_handler, NULL, NULL, BATADV_TVLV_MCAST, 2, BATADV_TVLV_HANDLER_OGM_CIFNOTFND); + batadv_tvlv_handler_register(bat_priv, NULL, NULL, + batadv_mcast_forw_tracker_tvlv_handler, + BATADV_TVLV_MCAST_TRACKER, 1, + BATADV_TVLV_HANDLER_OGM_CIFNOTFND); INIT_DELAYED_WORK(&bat_priv->mcast.work, batadv_mcast_mla_update); batadv_mcast_start_timer(bat_priv); diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index a9770d8d6d36..a5c0f384bb9a 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -52,6 +52,11 @@ void batadv_mcast_free(struct batadv_priv *bat_priv); void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node); +/* multicast_forw.c */ + +int batadv_mcast_forw_tracker_tvlv_handler(struct batadv_priv *bat_priv, + struct sk_buff *skb); + #else static inline enum batadv_forw_mode diff --git a/net/batman-adv/multicast_forw.c b/net/batman-adv/multicast_forw.c new file mode 100644 index 000000000000..d17341dfb832 --- /dev/null +++ b/net/batman-adv/multicast_forw.c @@ -0,0 +1,239 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) B.A.T.M.A.N. contributors: + * + * Linus Lüssing + */ + +#include "multicast.h" +#include "main.h" + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "originator.h" +#include "send.h" + +#define batadv_mcast_forw_tracker_for_each_dest(dest, num_dests) \ + for (; num_dests; num_dests--, (dest) += ETH_ALEN) + +#define batadv_mcast_forw_tracker_for_each_dest2(dest1, dest2, num_dests) \ + for (; num_dests; num_dests--, (dest1) += ETH_ALEN, (dest2) += ETH_ALEN) + +/** + * batadv_mcast_forw_scrub_dests() - scrub destinations in a tracker TVLV + * @bat_priv: the bat priv with all the soft interface information + * @comp_neigh: next hop neighbor to scrub+collect destinations for + * @dest: start MAC entry in original skb's tracker TVLV + * @next_dest: start MAC entry in to be sent skb's tracker TVLV + * @num_dests: number of remaining destination MAC entries to iterate over + * + * This sorts destination entries into either the original batman-adv + * multicast packet or the skb (copy) that is going to be sent to comp_neigh + * next. + * + * In preparation for the next, to be (unicast) transmitted batman-adv multicast + * packet skb to be sent to the given neighbor node, tries to collect all + * originator MAC addresses that have the given neighbor node as their next hop + * in the to be transmitted skb (copy), which next_dest points into. That is we + * zero all destination entries in next_dest which do not have comp_neigh as + * their next hop. And zero all destination entries in the original skb that + * would have comp_neigh as their next hop (to avoid redundant transmissions and + * duplicated payload later). + */ +static void +batadv_mcast_forw_scrub_dests(struct batadv_priv *bat_priv, + struct batadv_neigh_node *comp_neigh, u8 *dest, + u8 *next_dest, u16 num_dests) +{ + struct batadv_neigh_node *next_neigh; + + /* skip first entry, this is what we are comparing with */ + eth_zero_addr(dest); + dest += ETH_ALEN; + next_dest += ETH_ALEN; + num_dests--; + + batadv_mcast_forw_tracker_for_each_dest2(dest, next_dest, num_dests) { + if (is_zero_ether_addr(next_dest)) + continue; + + /* sanity check, we expect unicast destinations */ + if (is_multicast_ether_addr(next_dest)) { + eth_zero_addr(dest); + eth_zero_addr(next_dest); + continue; + } + + next_neigh = batadv_orig_to_router(bat_priv, next_dest, NULL); + if (!next_neigh) { + eth_zero_addr(next_dest); + continue; + } + + if (!batadv_compare_eth(next_neigh->addr, comp_neigh->addr)) { + eth_zero_addr(next_dest); + batadv_neigh_node_put(next_neigh); + continue; + } + + /* found an entry for our next packet to transmit, so remove it + * from the original packet + */ + eth_zero_addr(dest); + batadv_neigh_node_put(next_neigh); + } +} + +/** + * batadv_mcast_forw_packet() - forward a batman-adv multicast packet + * @bat_priv: the bat priv with all the soft interface information + * @skb: the received or locally generated batman-adv multicast packet + * @local_xmit: indicates that the packet was locally generated and not received + * + * Parses the tracker TVLV of a batman-adv multicast packet and forwards the + * packet as indicated in this TVLV. + * + * Caller needs to set the skb network header to the start of the multicast + * tracker TVLV (excluding the generic TVLV header) and the skb transport header + * to the next byte after this multicast tracker TVLV. + * + * Caller needs to free the skb. + * + * Return: NET_RX_SUCCESS or NET_RX_DROP on success or a negative error + * code on failure. NET_RX_SUCCESS if the received packet is supposed to be + * decapsulated and forwarded to the own soft interface, NET_RX_DROP otherwise. + */ +static int batadv_mcast_forw_packet(struct batadv_priv *bat_priv, + struct sk_buff *skb, bool local_xmit) +{ + struct batadv_tvlv_mcast_tracker *mcast_tracker; + struct batadv_neigh_node *neigh_node; + unsigned long offset, num_dests_off; + struct sk_buff *nexthop_skb; + unsigned char *skb_net_hdr; + bool local_recv = false; + unsigned int tvlv_len; + bool xmitted = false; + u8 *dest, *next_dest; + u16 num_dests; + int ret; + + /* (at least) TVLV part needs to be linearized */ + SKB_LINEAR_ASSERT(skb); + + /* check if num_dests is within skb length */ + num_dests_off = offsetof(struct batadv_tvlv_mcast_tracker, num_dests); + if (num_dests_off > skb_network_header_len(skb)) + return -EINVAL; + + skb_net_hdr = skb_network_header(skb); + mcast_tracker = (struct batadv_tvlv_mcast_tracker *)skb_net_hdr; + num_dests = ntohs(mcast_tracker->num_dests); + + dest = (u8 *)mcast_tracker + sizeof(*mcast_tracker); + + /* check if full tracker tvlv is within skb length */ + tvlv_len = sizeof(*mcast_tracker) + ETH_ALEN * num_dests; + if (tvlv_len > skb_network_header_len(skb)) + return -EINVAL; + + /* invalidate checksum: */ + skb->ip_summed = CHECKSUM_NONE; + + batadv_mcast_forw_tracker_for_each_dest(dest, num_dests) { + if (is_zero_ether_addr(dest)) + continue; + + /* only unicast originator addresses supported */ + if (is_multicast_ether_addr(dest)) { + eth_zero_addr(dest); + continue; + } + + if (batadv_is_my_mac(bat_priv, dest)) { + eth_zero_addr(dest); + local_recv = true; + continue; + } + + neigh_node = batadv_orig_to_router(bat_priv, dest, NULL); + if (!neigh_node) { + eth_zero_addr(dest); + continue; + } + + nexthop_skb = skb_copy(skb, GFP_ATOMIC); + if (!nexthop_skb) { + batadv_neigh_node_put(neigh_node); + return -ENOMEM; + } + + offset = dest - skb->data; + next_dest = nexthop_skb->data + offset; + + batadv_mcast_forw_scrub_dests(bat_priv, neigh_node, dest, + next_dest, num_dests); + + batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_TX); + batadv_add_counter(bat_priv, BATADV_CNT_MCAST_TX_BYTES, + nexthop_skb->len + ETH_HLEN); + xmitted = true; + ret = batadv_send_unicast_skb(nexthop_skb, neigh_node); + + batadv_neigh_node_put(neigh_node); + + if (ret < 0) + return ret; + } + + if (xmitted) { + if (local_xmit) { + batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_TX_LOCAL); + batadv_add_counter(bat_priv, + BATADV_CNT_MCAST_TX_LOCAL_BYTES, + skb->len - + skb_transport_offset(skb)); + } else { + batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_FWD); + batadv_add_counter(bat_priv, BATADV_CNT_MCAST_FWD_BYTES, + skb->len + ETH_HLEN); + } + } + + if (local_recv) + return NET_RX_SUCCESS; + else + return NET_RX_DROP; +} + +/** + * batadv_mcast_forw_tracker_tvlv_handler() - handle an mcast tracker tvlv + * @bat_priv: the bat priv with all the soft interface information + * @skb: the received batman-adv multicast packet + * + * Parses the tracker TVLV of an incoming batman-adv multicast packet and + * forwards the packet as indicated in this TVLV. + * + * Caller needs to set the skb network header to the start of the multicast + * tracker TVLV (excluding the generic TVLV header) and the skb transport header + * to the next byte after this multicast tracker TVLV. + * + * Caller needs to free the skb. + * + * Return: NET_RX_SUCCESS or NET_RX_DROP on success or a negative error + * code on failure. NET_RX_SUCCESS if the received packet is supposed to be + * decapsulated and forwarded to the own soft interface, NET_RX_DROP otherwise. + */ +int batadv_mcast_forw_tracker_tvlv_handler(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + return batadv_mcast_forw_packet(bat_priv, skb, false); +} diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 34903df4fe93..71c143d4b6d0 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -311,6 +311,33 @@ batadv_orig_router_get(struct batadv_orig_node *orig_node, return router; } +/** + * batadv_orig_to_router() - get next hop neighbor to an orig address + * @bat_priv: the bat priv with all the soft interface information + * @orig_addr: the originator MAC address to search the best next hop router for + * @if_outgoing: the interface where the payload packet has been received or + * the OGM should be sent to + * + * Return: A neighbor node which is the best router towards the given originator + * address. + */ +struct batadv_neigh_node * +batadv_orig_to_router(struct batadv_priv *bat_priv, u8 *orig_addr, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_neigh_node *neigh_node; + struct batadv_orig_node *orig_node; + + orig_node = batadv_orig_hash_find(bat_priv, orig_addr); + if (!orig_node) + return NULL; + + neigh_node = batadv_find_router(bat_priv, orig_node, if_outgoing); + batadv_orig_node_put(orig_node); + + return neigh_node; +} + /** * batadv_orig_ifinfo_get() - find the ifinfo from an orig_node * @orig_node: the orig node to be queried @@ -942,6 +969,7 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, #ifdef CONFIG_BATMAN_ADV_MCAST orig_node->mcast_flags = BATADV_MCAST_WANT_NO_RTR4; orig_node->mcast_flags |= BATADV_MCAST_WANT_NO_RTR6; + orig_node->mcast_flags |= BATADV_MCAST_HAVE_MC_PTYPE_CAPA; INIT_HLIST_NODE(&orig_node->mcast_want_all_unsnoopables_node); INIT_HLIST_NODE(&orig_node->mcast_want_all_ipv4_node); INIT_HLIST_NODE(&orig_node->mcast_want_all_ipv6_node); diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index ea3d69e4e670..db0c55128170 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -36,6 +36,9 @@ void batadv_neigh_node_release(struct kref *ref); struct batadv_neigh_node * batadv_orig_router_get(struct batadv_orig_node *orig_node, const struct batadv_hard_iface *if_outgoing); +struct batadv_neigh_node * +batadv_orig_to_router(struct batadv_priv *bat_priv, u8 *orig_addr, + struct batadv_hard_iface *if_outgoing); struct batadv_neigh_ifinfo * batadv_neigh_ifinfo_new(struct batadv_neigh_node *neigh, struct batadv_hard_iface *if_outgoing); diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 163cd43c4821..f1061985149f 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1270,3 +1270,73 @@ out: batadv_orig_node_put(orig_node); return ret; } + +#ifdef CONFIG_BATMAN_ADV_MCAST +/** + * batadv_recv_mcast_packet() - process received batman-adv multicast packet + * @skb: the received batman-adv multicast packet + * @recv_if: interface that the skb is received on + * + * Parses the given, received batman-adv multicast packet. Depending on the + * contents of its TVLV forwards it and/or decapsulates it to hand it to the + * soft interface. + * + * Return: NET_RX_DROP if the skb is not consumed, NET_RX_SUCCESS otherwise. + */ +int batadv_recv_mcast_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if) +{ + struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); + struct batadv_mcast_packet *mcast_packet; + int hdr_size = sizeof(*mcast_packet); + unsigned char *tvlv_buff; + int ret = NET_RX_DROP; + u16 tvlv_buff_len; + + if (batadv_check_unicast_packet(bat_priv, skb, hdr_size) < 0) + goto free_skb; + + /* create a copy of the skb, if needed, to modify it. */ + if (skb_cow(skb, ETH_HLEN) < 0) + goto free_skb; + + /* packet needs to be linearized to access the tvlv content */ + if (skb_linearize(skb) < 0) + goto free_skb; + + mcast_packet = (struct batadv_mcast_packet *)skb->data; + if (mcast_packet->ttl-- < 2) + goto free_skb; + + tvlv_buff = (unsigned char *)(skb->data + hdr_size); + tvlv_buff_len = ntohs(mcast_packet->tvlv_len); + + if (tvlv_buff_len > skb->len - hdr_size) + goto free_skb; + + ret = batadv_tvlv_containers_process(bat_priv, BATADV_MCAST, NULL, skb, + tvlv_buff, tvlv_buff_len); + if (ret >= 0) { + batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_RX); + batadv_add_counter(bat_priv, BATADV_CNT_MCAST_RX_BYTES, + skb->len + ETH_HLEN); + } + + hdr_size += tvlv_buff_len; + + if (ret == NET_RX_SUCCESS && (skb->len - hdr_size >= ETH_HLEN)) { + batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_RX_LOCAL); + batadv_add_counter(bat_priv, BATADV_CNT_MCAST_RX_LOCAL_BYTES, + skb->len - hdr_size); + + batadv_interface_rx(bat_priv->soft_iface, skb, hdr_size, NULL); + /* skb was consumed */ + skb = NULL; + } + +free_skb: + kfree_skb(skb); + + return ret; +} +#endif /* CONFIG_BATMAN_ADV_MCAST */ diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index afd15b3879f1..e9849f032a24 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -27,6 +27,17 @@ int batadv_recv_frag_packet(struct sk_buff *skb, struct batadv_hard_iface *iface); int batadv_recv_bcast_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if); +#ifdef CONFIG_BATMAN_ADV_MCAST +int batadv_recv_mcast_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if); +#else +static inline int batadv_recv_mcast_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if) +{ + kfree_skb(skb); + return NET_RX_DROP; +} +#endif int batadv_recv_unicast_tvlv(struct sk_buff *skb, struct batadv_hard_iface *recv_if); int batadv_recv_unhandled_unicast_packet(struct sk_buff *skb, diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 1bf1232a4f75..1b0e2c59aef2 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -925,6 +925,18 @@ static const struct { { "tt_response_rx" }, { "tt_roam_adv_tx" }, { "tt_roam_adv_rx" }, +#ifdef CONFIG_BATMAN_ADV_MCAST + { "mcast_tx" }, + { "mcast_tx_bytes" }, + { "mcast_tx_local" }, + { "mcast_tx_local_bytes" }, + { "mcast_rx" }, + { "mcast_rx_bytes" }, + { "mcast_rx_local" }, + { "mcast_rx_local_bytes" }, + { "mcast_fwd" }, + { "mcast_fwd_bytes" }, +#endif #ifdef CONFIG_BATMAN_ADV_DAT { "dat_get_tx" }, { "dat_get_rx" }, diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 17d5ea1d8e84..850b184e5b04 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -862,6 +862,70 @@ enum batadv_counters { */ BATADV_CNT_TT_ROAM_ADV_RX, +#ifdef CONFIG_BATMAN_ADV_MCAST + /** + * @BATADV_CNT_MCAST_TX: transmitted batman-adv multicast packets + * counter + */ + BATADV_CNT_MCAST_TX, + + /** + * @BATADV_CNT_MCAST_TX_BYTES: transmitted batman-adv multicast packets + * bytes counter + */ + BATADV_CNT_MCAST_TX_BYTES, + + /** + * @BATADV_CNT_MCAST_TX_LOCAL: counter for multicast packets which + * were locally encapsulated and transmitted as batman-adv multicast + * packets + */ + BATADV_CNT_MCAST_TX_LOCAL, + + /** + * @BATADV_CNT_MCAST_TX_LOCAL_BYTES: bytes counter for multicast packets + * which were locally encapsulated and transmitted as batman-adv + * multicast packets + */ + BATADV_CNT_MCAST_TX_LOCAL_BYTES, + + /** + * @BATADV_CNT_MCAST_RX: received batman-adv multicast packet counter + */ + BATADV_CNT_MCAST_RX, + + /** + * @BATADV_CNT_MCAST_RX_BYTES: received batman-adv multicast packet + * bytes counter + */ + BATADV_CNT_MCAST_RX_BYTES, + + /** + * @BATADV_CNT_MCAST_RX_LOCAL: counter for received batman-adv multicast + * packets which were forwarded to the local soft interface + */ + BATADV_CNT_MCAST_RX_LOCAL, + + /** + * @BATADV_CNT_MCAST_RX_LOCAL_BYTES: bytes counter for received + * batman-adv multicast packets which were forwarded to the local soft + * interface + */ + BATADV_CNT_MCAST_RX_LOCAL_BYTES, + + /** + * @BATADV_CNT_MCAST_FWD: counter for received batman-adv multicast + * packets which were forwarded to other, neighboring nodes + */ + BATADV_CNT_MCAST_FWD, + + /** + * @BATADV_CNT_MCAST_FWD_BYTES: bytes counter for received batman-adv + * multicast packets which were forwarded to other, neighboring nodes + */ + BATADV_CNT_MCAST_FWD_BYTES, +#endif + #ifdef CONFIG_BATMAN_ADV_DAT /** * @BATADV_CNT_DAT_GET_TX: transmitted dht GET traffic packet counter -- cgit From a7800aa80ea4d5356b8474c2302812e9d4926fa6 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 13 Nov 2023 05:42:34 -0500 Subject: KVM: Add KVM_CREATE_GUEST_MEMFD ioctl() for guest-specific backing memory MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce an ioctl(), KVM_CREATE_GUEST_MEMFD, to allow creating file-based memory that is tied to a specific KVM virtual machine and whose primary purpose is to serve guest memory. A guest-first memory subsystem allows for optimizations and enhancements that are kludgy or outright infeasible to implement/support in a generic memory subsystem. With guest_memfd, guest protections and mapping sizes are fully decoupled from host userspace mappings. E.g. KVM currently doesn't support mapping memory as writable in the guest without it also being writable in host userspace, as KVM's ABI uses VMA protections to define the allow guest protection. Userspace can fudge this by establishing two mappings, a writable mapping for the guest and readable one for itself, but that’s suboptimal on multiple fronts. Similarly, KVM currently requires the guest mapping size to be a strict subset of the host userspace mapping size, e.g. KVM doesn’t support creating a 1GiB guest mapping unless userspace also has a 1GiB guest mapping. Decoupling the mappings sizes would allow userspace to precisely map only what is needed without impacting guest performance, e.g. to harden against unintentional accesses to guest memory. Decoupling guest and userspace mappings may also allow for a cleaner alternative to high-granularity mappings for HugeTLB, which has reached a bit of an impasse and is unlikely to ever be merged. A guest-first memory subsystem also provides clearer line of sight to things like a dedicated memory pool (for slice-of-hardware VMs) and elimination of "struct page" (for offload setups where userspace _never_ needs to mmap() guest memory). More immediately, being able to map memory into KVM guests without mapping said memory into the host is critical for Confidential VMs (CoCo VMs), the initial use case for guest_memfd. While AMD's SEV and Intel's TDX prevent untrusted software from reading guest private data by encrypting guest memory with a key that isn't usable by the untrusted host, projects such as Protected KVM (pKVM) provide confidentiality and integrity *without* relying on memory encryption. And with SEV-SNP and TDX, accessing guest private memory can be fatal to the host, i.e. KVM must be prevent host userspace from accessing guest memory irrespective of hardware behavior. Attempt #1 to support CoCo VMs was to add a VMA flag to mark memory as being mappable only by KVM (or a similarly enlightened kernel subsystem). That approach was abandoned largely due to it needing to play games with PROT_NONE to prevent userspace from accessing guest memory. Attempt #2 to was to usurp PG_hwpoison to prevent the host from mapping guest private memory into userspace, but that approach failed to meet several requirements for software-based CoCo VMs, e.g. pKVM, as the kernel wouldn't easily be able to enforce a 1:1 page:guest association, let alone a 1:1 pfn:gfn mapping. And using PG_hwpoison does not work for memory that isn't backed by 'struct page', e.g. if devices gain support for exposing encrypted memory regions to guests. Attempt #3 was to extend the memfd() syscall and wrap shmem to provide dedicated file-based guest memory. That approach made it as far as v10 before feedback from Hugh Dickins and Christian Brauner (and others) led to it demise. Hugh's objection was that piggybacking shmem made no sense for KVM's use case as KVM didn't actually *want* the features provided by shmem. I.e. KVM was using memfd() and shmem to avoid having to manage memory directly, not because memfd() and shmem were the optimal solution, e.g. things like read/write/mmap in shmem were dead weight. Christian pointed out flaws with implementing a partial overlay (wrapping only _some_ of shmem), e.g. poking at inode_operations or super_operations would show shmem stuff, but address_space_operations and file_operations would show KVM's overlay. Paraphrashing heavily, Christian suggested KVM stop being lazy and create a proper API. Link: https://lore.kernel.org/all/20201020061859.18385-1-kirill.shutemov@linux.intel.com Link: https://lore.kernel.org/all/20210416154106.23721-1-kirill.shutemov@linux.intel.com Link: https://lore.kernel.org/all/20210824005248.200037-1-seanjc@google.com Link: https://lore.kernel.org/all/20211111141352.26311-1-chao.p.peng@linux.intel.com Link: https://lore.kernel.org/all/20221202061347.1070246-1-chao.p.peng@linux.intel.com Link: https://lore.kernel.org/all/ff5c5b97-acdf-9745-ebe5-c6609dd6322e@google.com Link: https://lore.kernel.org/all/20230418-anfallen-irdisch-6993a61be10b@brauner Link: https://lore.kernel.org/all/ZEM5Zq8oo+xnApW9@google.com Link: https://lore.kernel.org/linux-mm/20230306191944.GA15773@monkey Link: https://lore.kernel.org/linux-mm/ZII1p8ZHlHaQ3dDl@casper.infradead.org Cc: Fuad Tabba Cc: Vishal Annapurve Cc: Ackerley Tng Cc: Jarkko Sakkinen Cc: Maciej Szmigiero Cc: Vlastimil Babka Cc: David Hildenbrand Cc: Quentin Perret Cc: Michael Roth Cc: Wang Cc: Liam Merwick Cc: Isaku Yamahata Co-developed-by: Kirill A. Shutemov Signed-off-by: Kirill A. Shutemov Co-developed-by: Yu Zhang Signed-off-by: Yu Zhang Co-developed-by: Chao Peng Signed-off-by: Chao Peng Co-developed-by: Ackerley Tng Signed-off-by: Ackerley Tng Co-developed-by: Isaku Yamahata Signed-off-by: Isaku Yamahata Co-developed-by: Paolo Bonzini Signed-off-by: Paolo Bonzini Co-developed-by: Michael Roth Signed-off-by: Michael Roth Signed-off-by: Sean Christopherson Message-Id: <20231027182217.3615211-17-seanjc@google.com> Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Reviewed-by: Xiaoyao Li Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 70 +++++- fs/anon_inodes.c | 1 + include/linux/kvm_host.h | 48 ++++ include/uapi/linux/kvm.h | 15 +- virt/kvm/Kconfig | 4 + virt/kvm/Makefile.kvm | 1 + virt/kvm/guest_memfd.c | 538 +++++++++++++++++++++++++++++++++++++++++ virt/kvm/kvm_main.c | 59 ++++- virt/kvm/kvm_mm.h | 26 ++ 9 files changed, 754 insertions(+), 8 deletions(-) create mode 100644 virt/kvm/guest_memfd.c (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 081ef09d3148..1e61faf02b2a 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6201,6 +6201,15 @@ superset of the features supported by the system. :Parameters: struct kvm_userspace_memory_region2 (in) :Returns: 0 on success, -1 on error +KVM_SET_USER_MEMORY_REGION2 is an extension to KVM_SET_USER_MEMORY_REGION that +allows mapping guest_memfd memory into a guest. All fields shared with +KVM_SET_USER_MEMORY_REGION identically. Userspace can set KVM_MEM_GUEST_MEMFD +in flags to have KVM bind the memory region to a given guest_memfd range of +[guest_memfd_offset, guest_memfd_offset + memory_size]. The target guest_memfd +must point at a file created via KVM_CREATE_GUEST_MEMFD on the current VM, and +the target range must not be bound to any other memory region. All standard +bounds checks apply (use common sense). + :: struct kvm_userspace_memory_region2 { @@ -6209,10 +6218,24 @@ superset of the features supported by the system. __u64 guest_phys_addr; __u64 memory_size; /* bytes */ __u64 userspace_addr; /* start of the userspace allocated memory */ - __u64 pad[16]; + __u64 guest_memfd_offset; + __u32 guest_memfd; + __u32 pad1; + __u64 pad2[14]; }; -See KVM_SET_USER_MEMORY_REGION. +A KVM_MEM_GUEST_MEMFD region _must_ have a valid guest_memfd (private memory) and +userspace_addr (shared memory). However, "valid" for userspace_addr simply +means that the address itself must be a legal userspace address. The backing +mapping for userspace_addr is not required to be valid/populated at the time of +KVM_SET_USER_MEMORY_REGION2, e.g. shared memory can be lazily mapped/allocated +on-demand. + +When mapping a gfn into the guest, KVM selects shared vs. private, i.e consumes +userspace_addr vs. guest_memfd, based on the gfn's KVM_MEMORY_ATTRIBUTE_PRIVATE +state. At VM creation time, all memory is shared, i.e. the PRIVATE attribute +is '0' for all gfns. Userspace can control whether memory is shared/private by +toggling KVM_MEMORY_ATTRIBUTE_PRIVATE via KVM_SET_MEMORY_ATTRIBUTES as needed. 4.141 KVM_SET_MEMORY_ATTRIBUTES ------------------------------- @@ -6250,6 +6273,49 @@ the state of a gfn/page as needed. The "flags" field is reserved for future extensions and must be '0'. +4.142 KVM_CREATE_GUEST_MEMFD +---------------------------- + +:Capability: KVM_CAP_GUEST_MEMFD +:Architectures: none +:Type: vm ioctl +:Parameters: struct kvm_create_guest_memfd(in) +:Returns: 0 on success, <0 on error + +KVM_CREATE_GUEST_MEMFD creates an anonymous file and returns a file descriptor +that refers to it. guest_memfd files are roughly analogous to files created +via memfd_create(), e.g. guest_memfd files live in RAM, have volatile storage, +and are automatically released when the last reference is dropped. Unlike +"regular" memfd_create() files, guest_memfd files are bound to their owning +virtual machine (see below), cannot be mapped, read, or written by userspace, +and cannot be resized (guest_memfd files do however support PUNCH_HOLE). + +:: + + struct kvm_create_guest_memfd { + __u64 size; + __u64 flags; + __u64 reserved[6]; + }; + +Conceptually, the inode backing a guest_memfd file represents physical memory, +i.e. is coupled to the virtual machine as a thing, not to a "struct kvm". The +file itself, which is bound to a "struct kvm", is that instance's view of the +underlying memory, e.g. effectively provides the translation of guest addresses +to host memory. This allows for use cases where multiple KVM structures are +used to manage a single virtual machine, e.g. when performing intrahost +migration of a virtual machine. + +KVM currently only supports mapping guest_memfd via KVM_SET_USER_MEMORY_REGION2, +and more specifically via the guest_memfd and guest_memfd_offset fields in +"struct kvm_userspace_memory_region2", where guest_memfd_offset is the offset +into the guest_memfd instance. For a given guest_memfd file, there can be at +most one mapping per page, i.e. binding multiple memory regions to a single +guest_memfd range is not allowed (any number of memory regions can be bound to +a single guest_memfd file, but the bound ranges must not overlap). + +See KVM_SET_USER_MEMORY_REGION2 for additional details. + 5. The kvm_run structure ======================== diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 42b02dc36474..8dd436ee985b 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -183,6 +183,7 @@ struct file *anon_inode_create_getfile(const char *name, return __anon_inode_getfile(name, fops, priv, flags, context_inode, true); } +EXPORT_SYMBOL_GPL(anon_inode_create_getfile); static int __anon_inode_getfd(const char *name, const struct file_operations *fops, diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 68a144cb7dbc..a6de526c0426 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -589,8 +589,20 @@ struct kvm_memory_slot { u32 flags; short id; u16 as_id; + +#ifdef CONFIG_KVM_PRIVATE_MEM + struct { + struct file __rcu *file; + pgoff_t pgoff; + } gmem; +#endif }; +static inline bool kvm_slot_can_be_private(const struct kvm_memory_slot *slot) +{ + return slot && (slot->flags & KVM_MEM_GUEST_MEMFD); +} + static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot) { return slot->flags & KVM_MEM_LOG_DIRTY_PAGES; @@ -685,6 +697,17 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) } #endif +/* + * Arch code must define kvm_arch_has_private_mem if support for private memory + * is enabled. + */ +#if !defined(kvm_arch_has_private_mem) && !IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) +static inline bool kvm_arch_has_private_mem(struct kvm *kvm) +{ + return false; +} +#endif + struct kvm_memslots { u64 generation; atomic_long_t last_used_slot; @@ -1400,6 +1423,7 @@ void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); void kvm_mmu_invalidate_begin(struct kvm *kvm); void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end); void kvm_mmu_invalidate_end(struct kvm *kvm); +bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); @@ -2355,6 +2379,30 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range); + +static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) +{ + return IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) && + kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE; +} +#else +static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) +{ + return false; +} #endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ +#ifdef CONFIG_KVM_PRIVATE_MEM +int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn, kvm_pfn_t *pfn, int *max_order); +#else +static inline int kvm_gmem_get_pfn(struct kvm *kvm, + struct kvm_memory_slot *slot, gfn_t gfn, + kvm_pfn_t *pfn, int *max_order) +{ + KVM_BUG_ON(1, kvm); + return -EIO; +} +#endif /* CONFIG_KVM_PRIVATE_MEM */ + #endif diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index e8d167e54980..2802d10aa88c 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -102,7 +102,10 @@ struct kvm_userspace_memory_region2 { __u64 guest_phys_addr; __u64 memory_size; __u64 userspace_addr; - __u64 pad[16]; + __u64 guest_memfd_offset; + __u32 guest_memfd; + __u32 pad1; + __u64 pad2[14]; }; /* @@ -112,6 +115,7 @@ struct kvm_userspace_memory_region2 { */ #define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0) #define KVM_MEM_READONLY (1UL << 1) +#define KVM_MEM_GUEST_MEMFD (1UL << 2) /* for KVM_IRQ_LINE */ struct kvm_irq_level { @@ -1221,6 +1225,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_USER_MEMORY2 231 #define KVM_CAP_MEMORY_FAULT_INFO 232 #define KVM_CAP_MEMORY_ATTRIBUTES 233 +#define KVM_CAP_GUEST_MEMFD 234 #ifdef KVM_CAP_IRQ_ROUTING @@ -2301,4 +2306,12 @@ struct kvm_memory_attributes { #define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3) +#define KVM_CREATE_GUEST_MEMFD _IOWR(KVMIO, 0xd4, struct kvm_create_guest_memfd) + +struct kvm_create_guest_memfd { + __u64 size; + __u64 flags; + __u64 reserved[6]; +}; + #endif /* __LINUX_KVM_H */ diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 5bd7fcaf9089..08afef022db9 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -100,3 +100,7 @@ config KVM_GENERIC_MMU_NOTIFIER config KVM_GENERIC_MEMORY_ATTRIBUTES select KVM_GENERIC_MMU_NOTIFIER bool + +config KVM_PRIVATE_MEM + select XARRAY_MULTI + bool diff --git a/virt/kvm/Makefile.kvm b/virt/kvm/Makefile.kvm index 2c27d5d0c367..724c89af78af 100644 --- a/virt/kvm/Makefile.kvm +++ b/virt/kvm/Makefile.kvm @@ -12,3 +12,4 @@ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(KVM)/irqchip.o kvm-$(CONFIG_HAVE_KVM_DIRTY_RING) += $(KVM)/dirty_ring.o kvm-$(CONFIG_HAVE_KVM_PFNCACHE) += $(KVM)/pfncache.o +kvm-$(CONFIG_KVM_PRIVATE_MEM) += $(KVM)/guest_memfd.o diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c new file mode 100644 index 000000000000..e65f4170425c --- /dev/null +++ b/virt/kvm/guest_memfd.c @@ -0,0 +1,538 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include + +#include "kvm_mm.h" + +struct kvm_gmem { + struct kvm *kvm; + struct xarray bindings; + struct list_head entry; +}; + +static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index) +{ + struct folio *folio; + + /* TODO: Support huge pages. */ + folio = filemap_grab_folio(inode->i_mapping, index); + if (IS_ERR_OR_NULL(folio)) + return NULL; + + /* + * Use the up-to-date flag to track whether or not the memory has been + * zeroed before being handed off to the guest. There is no backing + * storage for the memory, so the folio will remain up-to-date until + * it's removed. + * + * TODO: Skip clearing pages when trusted firmware will do it when + * assigning memory to the guest. + */ + if (!folio_test_uptodate(folio)) { + unsigned long nr_pages = folio_nr_pages(folio); + unsigned long i; + + for (i = 0; i < nr_pages; i++) + clear_highpage(folio_page(folio, i)); + + folio_mark_uptodate(folio); + } + + /* + * Ignore accessed, referenced, and dirty flags. The memory is + * unevictable and there is no storage to write back to. + */ + return folio; +} + +static void kvm_gmem_invalidate_begin(struct kvm_gmem *gmem, pgoff_t start, + pgoff_t end) +{ + bool flush = false, found_memslot = false; + struct kvm_memory_slot *slot; + struct kvm *kvm = gmem->kvm; + unsigned long index; + + xa_for_each_range(&gmem->bindings, index, slot, start, end - 1) { + pgoff_t pgoff = slot->gmem.pgoff; + + struct kvm_gfn_range gfn_range = { + .start = slot->base_gfn + max(pgoff, start) - pgoff, + .end = slot->base_gfn + min(pgoff + slot->npages, end) - pgoff, + .slot = slot, + .may_block = true, + }; + + if (!found_memslot) { + found_memslot = true; + + KVM_MMU_LOCK(kvm); + kvm_mmu_invalidate_begin(kvm); + } + + flush |= kvm_mmu_unmap_gfn_range(kvm, &gfn_range); + } + + if (flush) + kvm_flush_remote_tlbs(kvm); + + if (found_memslot) + KVM_MMU_UNLOCK(kvm); +} + +static void kvm_gmem_invalidate_end(struct kvm_gmem *gmem, pgoff_t start, + pgoff_t end) +{ + struct kvm *kvm = gmem->kvm; + + if (xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) { + KVM_MMU_LOCK(kvm); + kvm_mmu_invalidate_end(kvm); + KVM_MMU_UNLOCK(kvm); + } +} + +static long kvm_gmem_punch_hole(struct inode *inode, loff_t offset, loff_t len) +{ + struct list_head *gmem_list = &inode->i_mapping->private_list; + pgoff_t start = offset >> PAGE_SHIFT; + pgoff_t end = (offset + len) >> PAGE_SHIFT; + struct kvm_gmem *gmem; + + /* + * Bindings must be stable across invalidation to ensure the start+end + * are balanced. + */ + filemap_invalidate_lock(inode->i_mapping); + + list_for_each_entry(gmem, gmem_list, entry) + kvm_gmem_invalidate_begin(gmem, start, end); + + truncate_inode_pages_range(inode->i_mapping, offset, offset + len - 1); + + list_for_each_entry(gmem, gmem_list, entry) + kvm_gmem_invalidate_end(gmem, start, end); + + filemap_invalidate_unlock(inode->i_mapping); + + return 0; +} + +static long kvm_gmem_allocate(struct inode *inode, loff_t offset, loff_t len) +{ + struct address_space *mapping = inode->i_mapping; + pgoff_t start, index, end; + int r; + + /* Dedicated guest is immutable by default. */ + if (offset + len > i_size_read(inode)) + return -EINVAL; + + filemap_invalidate_lock_shared(mapping); + + start = offset >> PAGE_SHIFT; + end = (offset + len) >> PAGE_SHIFT; + + r = 0; + for (index = start; index < end; ) { + struct folio *folio; + + if (signal_pending(current)) { + r = -EINTR; + break; + } + + folio = kvm_gmem_get_folio(inode, index); + if (!folio) { + r = -ENOMEM; + break; + } + + index = folio_next_index(folio); + + folio_unlock(folio); + folio_put(folio); + + /* 64-bit only, wrapping the index should be impossible. */ + if (WARN_ON_ONCE(!index)) + break; + + cond_resched(); + } + + filemap_invalidate_unlock_shared(mapping); + + return r; +} + +static long kvm_gmem_fallocate(struct file *file, int mode, loff_t offset, + loff_t len) +{ + int ret; + + if (!(mode & FALLOC_FL_KEEP_SIZE)) + return -EOPNOTSUPP; + + if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) + return -EOPNOTSUPP; + + if (!PAGE_ALIGNED(offset) || !PAGE_ALIGNED(len)) + return -EINVAL; + + if (mode & FALLOC_FL_PUNCH_HOLE) + ret = kvm_gmem_punch_hole(file_inode(file), offset, len); + else + ret = kvm_gmem_allocate(file_inode(file), offset, len); + + if (!ret) + file_modified(file); + return ret; +} + +static int kvm_gmem_release(struct inode *inode, struct file *file) +{ + struct kvm_gmem *gmem = file->private_data; + struct kvm_memory_slot *slot; + struct kvm *kvm = gmem->kvm; + unsigned long index; + + /* + * Prevent concurrent attempts to *unbind* a memslot. This is the last + * reference to the file and thus no new bindings can be created, but + * dereferencing the slot for existing bindings needs to be protected + * against memslot updates, specifically so that unbind doesn't race + * and free the memslot (kvm_gmem_get_file() will return NULL). + */ + mutex_lock(&kvm->slots_lock); + + filemap_invalidate_lock(inode->i_mapping); + + xa_for_each(&gmem->bindings, index, slot) + rcu_assign_pointer(slot->gmem.file, NULL); + + synchronize_rcu(); + + /* + * All in-flight operations are gone and new bindings can be created. + * Zap all SPTEs pointed at by this file. Do not free the backing + * memory, as its lifetime is associated with the inode, not the file. + */ + kvm_gmem_invalidate_begin(gmem, 0, -1ul); + kvm_gmem_invalidate_end(gmem, 0, -1ul); + + list_del(&gmem->entry); + + filemap_invalidate_unlock(inode->i_mapping); + + mutex_unlock(&kvm->slots_lock); + + xa_destroy(&gmem->bindings); + kfree(gmem); + + kvm_put_kvm(kvm); + + return 0; +} + +static struct file *kvm_gmem_get_file(struct kvm_memory_slot *slot) +{ + struct file *file; + + rcu_read_lock(); + + file = rcu_dereference(slot->gmem.file); + if (file && !get_file_rcu(file)) + file = NULL; + + rcu_read_unlock(); + + return file; +} + +static struct file_operations kvm_gmem_fops = { + .open = generic_file_open, + .release = kvm_gmem_release, + .fallocate = kvm_gmem_fallocate, +}; + +void kvm_gmem_init(struct module *module) +{ + kvm_gmem_fops.owner = module; +} + +static int kvm_gmem_migrate_folio(struct address_space *mapping, + struct folio *dst, struct folio *src, + enum migrate_mode mode) +{ + WARN_ON_ONCE(1); + return -EINVAL; +} + +static int kvm_gmem_error_page(struct address_space *mapping, struct page *page) +{ + struct list_head *gmem_list = &mapping->private_list; + struct kvm_gmem *gmem; + pgoff_t start, end; + + filemap_invalidate_lock_shared(mapping); + + start = page->index; + end = start + thp_nr_pages(page); + + list_for_each_entry(gmem, gmem_list, entry) + kvm_gmem_invalidate_begin(gmem, start, end); + + /* + * Do not truncate the range, what action is taken in response to the + * error is userspace's decision (assuming the architecture supports + * gracefully handling memory errors). If/when the guest attempts to + * access a poisoned page, kvm_gmem_get_pfn() will return -EHWPOISON, + * at which point KVM can either terminate the VM or propagate the + * error to userspace. + */ + + list_for_each_entry(gmem, gmem_list, entry) + kvm_gmem_invalidate_end(gmem, start, end); + + filemap_invalidate_unlock_shared(mapping); + + return MF_DELAYED; +} + +static const struct address_space_operations kvm_gmem_aops = { + .dirty_folio = noop_dirty_folio, +#ifdef CONFIG_MIGRATION + .migrate_folio = kvm_gmem_migrate_folio, +#endif + .error_remove_page = kvm_gmem_error_page, +}; + +static int kvm_gmem_getattr(struct mnt_idmap *idmap, const struct path *path, + struct kstat *stat, u32 request_mask, + unsigned int query_flags) +{ + struct inode *inode = path->dentry->d_inode; + + generic_fillattr(idmap, request_mask, inode, stat); + return 0; +} + +static int kvm_gmem_setattr(struct mnt_idmap *idmap, struct dentry *dentry, + struct iattr *attr) +{ + return -EINVAL; +} +static const struct inode_operations kvm_gmem_iops = { + .getattr = kvm_gmem_getattr, + .setattr = kvm_gmem_setattr, +}; + +static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags) +{ + const char *anon_name = "[kvm-gmem]"; + struct kvm_gmem *gmem; + struct inode *inode; + struct file *file; + int fd, err; + + fd = get_unused_fd_flags(0); + if (fd < 0) + return fd; + + gmem = kzalloc(sizeof(*gmem), GFP_KERNEL); + if (!gmem) { + err = -ENOMEM; + goto err_fd; + } + + file = anon_inode_create_getfile(anon_name, &kvm_gmem_fops, gmem, + O_RDWR, NULL); + if (IS_ERR(file)) { + err = PTR_ERR(file); + goto err_gmem; + } + + file->f_flags |= O_LARGEFILE; + + inode = file->f_inode; + WARN_ON(file->f_mapping != inode->i_mapping); + + inode->i_private = (void *)(unsigned long)flags; + inode->i_op = &kvm_gmem_iops; + inode->i_mapping->a_ops = &kvm_gmem_aops; + inode->i_mode |= S_IFREG; + inode->i_size = size; + mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); + mapping_set_unmovable(inode->i_mapping); + /* Unmovable mappings are supposed to be marked unevictable as well. */ + WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping)); + + kvm_get_kvm(kvm); + gmem->kvm = kvm; + xa_init(&gmem->bindings); + list_add(&gmem->entry, &inode->i_mapping->private_list); + + fd_install(fd, file); + return fd; + +err_gmem: + kfree(gmem); +err_fd: + put_unused_fd(fd); + return err; +} + +int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args) +{ + loff_t size = args->size; + u64 flags = args->flags; + u64 valid_flags = 0; + + if (flags & ~valid_flags) + return -EINVAL; + + if (size <= 0 || !PAGE_ALIGNED(size)) + return -EINVAL; + + return __kvm_gmem_create(kvm, size, flags); +} + +int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned int fd, loff_t offset) +{ + loff_t size = slot->npages << PAGE_SHIFT; + unsigned long start, end; + struct kvm_gmem *gmem; + struct inode *inode; + struct file *file; + int r = -EINVAL; + + BUILD_BUG_ON(sizeof(gfn_t) != sizeof(slot->gmem.pgoff)); + + file = fget(fd); + if (!file) + return -EBADF; + + if (file->f_op != &kvm_gmem_fops) + goto err; + + gmem = file->private_data; + if (gmem->kvm != kvm) + goto err; + + inode = file_inode(file); + + if (offset < 0 || !PAGE_ALIGNED(offset) || + offset + size > i_size_read(inode)) + goto err; + + filemap_invalidate_lock(inode->i_mapping); + + start = offset >> PAGE_SHIFT; + end = start + slot->npages; + + if (!xa_empty(&gmem->bindings) && + xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) { + filemap_invalidate_unlock(inode->i_mapping); + goto err; + } + + /* + * No synchronize_rcu() needed, any in-flight readers are guaranteed to + * be see either a NULL file or this new file, no need for them to go + * away. + */ + rcu_assign_pointer(slot->gmem.file, file); + slot->gmem.pgoff = start; + + xa_store_range(&gmem->bindings, start, end - 1, slot, GFP_KERNEL); + filemap_invalidate_unlock(inode->i_mapping); + + /* + * Drop the reference to the file, even on success. The file pins KVM, + * not the other way 'round. Active bindings are invalidated if the + * file is closed before memslots are destroyed. + */ + r = 0; +err: + fput(file); + return r; +} + +void kvm_gmem_unbind(struct kvm_memory_slot *slot) +{ + unsigned long start = slot->gmem.pgoff; + unsigned long end = start + slot->npages; + struct kvm_gmem *gmem; + struct file *file; + + /* + * Nothing to do if the underlying file was already closed (or is being + * closed right now), kvm_gmem_release() invalidates all bindings. + */ + file = kvm_gmem_get_file(slot); + if (!file) + return; + + gmem = file->private_data; + + filemap_invalidate_lock(file->f_mapping); + xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL); + rcu_assign_pointer(slot->gmem.file, NULL); + synchronize_rcu(); + filemap_invalidate_unlock(file->f_mapping); + + fput(file); +} + +int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn, kvm_pfn_t *pfn, int *max_order) +{ + pgoff_t index = gfn - slot->base_gfn + slot->gmem.pgoff; + struct kvm_gmem *gmem; + struct folio *folio; + struct page *page; + struct file *file; + int r; + + file = kvm_gmem_get_file(slot); + if (!file) + return -EFAULT; + + gmem = file->private_data; + + if (WARN_ON_ONCE(xa_load(&gmem->bindings, index) != slot)) { + r = -EIO; + goto out_fput; + } + + folio = kvm_gmem_get_folio(file_inode(file), index); + if (!folio) { + r = -ENOMEM; + goto out_fput; + } + + if (folio_test_hwpoison(folio)) { + r = -EHWPOISON; + goto out_unlock; + } + + page = folio_file_page(folio, index); + + *pfn = page_to_pfn(page); + if (max_order) + *max_order = 0; + + r = 0; + +out_unlock: + folio_unlock(folio); +out_fput: + fput(file); + + return r; +} +EXPORT_SYMBOL_GPL(kvm_gmem_get_pfn); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index f1a575d39b3b..8f46d757a2c5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -791,7 +791,7 @@ void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end) } } -static bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) +bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { kvm_mmu_invalidate_range_add(kvm, range->start, range->end); return kvm_unmap_gfn_range(kvm, range); @@ -1027,6 +1027,9 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) /* This does not remove the slot from struct kvm_memslots data structures */ static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { + if (slot->flags & KVM_MEM_GUEST_MEMFD) + kvm_gmem_unbind(slot); + kvm_destroy_dirty_bitmap(slot); kvm_arch_free_memslot(kvm, slot); @@ -1606,10 +1609,18 @@ static void kvm_replace_memslot(struct kvm *kvm, #define KVM_SET_USER_MEMORY_REGION_V1_FLAGS \ (KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY) -static int check_memory_region_flags(const struct kvm_userspace_memory_region2 *mem) +static int check_memory_region_flags(struct kvm *kvm, + const struct kvm_userspace_memory_region2 *mem) { u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES; + if (kvm_arch_has_private_mem(kvm)) + valid_flags |= KVM_MEM_GUEST_MEMFD; + + /* Dirty logging private memory is not currently supported. */ + if (mem->flags & KVM_MEM_GUEST_MEMFD) + valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES; + #ifdef __KVM_HAVE_READONLY_MEM valid_flags |= KVM_MEM_READONLY; #endif @@ -2018,7 +2029,7 @@ int __kvm_set_memory_region(struct kvm *kvm, int as_id, id; int r; - r = check_memory_region_flags(mem); + r = check_memory_region_flags(kvm, mem); if (r) return r; @@ -2037,6 +2048,10 @@ int __kvm_set_memory_region(struct kvm *kvm, !access_ok((void __user *)(unsigned long)mem->userspace_addr, mem->memory_size)) return -EINVAL; + if (mem->flags & KVM_MEM_GUEST_MEMFD && + (mem->guest_memfd_offset & (PAGE_SIZE - 1) || + mem->guest_memfd_offset + mem->memory_size < mem->guest_memfd_offset)) + return -EINVAL; if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM) return -EINVAL; if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) @@ -2075,6 +2090,9 @@ int __kvm_set_memory_region(struct kvm *kvm, if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages) return -EINVAL; } else { /* Modify an existing slot. */ + /* Private memslots are immutable, they can only be deleted. */ + if (mem->flags & KVM_MEM_GUEST_MEMFD) + return -EINVAL; if ((mem->userspace_addr != old->userspace_addr) || (npages != old->npages) || ((mem->flags ^ old->flags) & KVM_MEM_READONLY)) @@ -2103,10 +2121,23 @@ int __kvm_set_memory_region(struct kvm *kvm, new->npages = npages; new->flags = mem->flags; new->userspace_addr = mem->userspace_addr; + if (mem->flags & KVM_MEM_GUEST_MEMFD) { + r = kvm_gmem_bind(kvm, new, mem->guest_memfd, mem->guest_memfd_offset); + if (r) + goto out; + } r = kvm_set_memslot(kvm, old, new, change); if (r) - kfree(new); + goto out_unbind; + + return 0; + +out_unbind: + if (mem->flags & KVM_MEM_GUEST_MEMFD) + kvm_gmem_unbind(new); +out: + kfree(new); return r; } EXPORT_SYMBOL_GPL(__kvm_set_memory_region); @@ -2442,7 +2473,7 @@ out: static u64 kvm_supported_mem_attributes(struct kvm *kvm) { - if (!kvm) + if (!kvm || kvm_arch_has_private_mem(kvm)) return KVM_MEMORY_ATTRIBUTE_PRIVATE; return 0; @@ -4844,6 +4875,10 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES case KVM_CAP_MEMORY_ATTRIBUTES: return kvm_supported_mem_attributes(kvm); +#endif +#ifdef CONFIG_KVM_PRIVATE_MEM + case KVM_CAP_GUEST_MEMFD: + return !kvm || kvm_arch_has_private_mem(kvm); #endif default: break; @@ -5277,6 +5312,18 @@ static long kvm_vm_ioctl(struct file *filp, case KVM_GET_STATS_FD: r = kvm_vm_ioctl_get_stats_fd(kvm); break; +#ifdef CONFIG_KVM_PRIVATE_MEM + case KVM_CREATE_GUEST_MEMFD: { + struct kvm_create_guest_memfd guest_memfd; + + r = -EFAULT; + if (copy_from_user(&guest_memfd, argp, sizeof(guest_memfd))) + goto out; + + r = kvm_gmem_create(kvm, &guest_memfd); + break; + } +#endif default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); } @@ -6409,6 +6456,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) if (WARN_ON_ONCE(r)) goto err_vfio; + kvm_gmem_init(module); + /* * Registration _must_ be the very last thing done, as this exposes * /dev/kvm to userspace, i.e. all infrastructure must be setup! diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h index 180f1a09e6ba..ecefc7ec51af 100644 --- a/virt/kvm/kvm_mm.h +++ b/virt/kvm/kvm_mm.h @@ -37,4 +37,30 @@ static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, } #endif /* HAVE_KVM_PFNCACHE */ +#ifdef CONFIG_KVM_PRIVATE_MEM +void kvm_gmem_init(struct module *module); +int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args); +int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned int fd, loff_t offset); +void kvm_gmem_unbind(struct kvm_memory_slot *slot); +#else +static inline void kvm_gmem_init(struct module *module) +{ + +} + +static inline int kvm_gmem_bind(struct kvm *kvm, + struct kvm_memory_slot *slot, + unsigned int fd, loff_t offset) +{ + WARN_ON_ONCE(1); + return -EIO; +} + +static inline void kvm_gmem_unbind(struct kvm_memory_slot *slot) +{ + WARN_ON_ONCE(1); +} +#endif /* CONFIG_KVM_PRIVATE_MEM */ + #endif /* __KVM_MM_H__ */ -- cgit From 8dd2eee9d526c30fccfe75da7ec5365c6476e510 Mon Sep 17 00:00:00 2001 From: Chao Peng Date: Fri, 27 Oct 2023 11:22:02 -0700 Subject: KVM: x86/mmu: Handle page fault for private memory Add support for resolving page faults on guest private memory for VMs that differentiate between "shared" and "private" memory. For such VMs, KVM_MEM_GUEST_MEMFD memslots can include both fd-based private memory and hva-based shared memory, and KVM needs to map in the "correct" variant, i.e. KVM needs to map the gfn shared/private as appropriate based on the current state of the gfn's KVM_MEMORY_ATTRIBUTE_PRIVATE flag. For AMD's SEV-SNP and Intel's TDX, the guest effectively gets to request shared vs. private via a bit in the guest page tables, i.e. what the guest wants may conflict with the current memory attributes. To support such "implicit" conversion requests, exit to user with KVM_EXIT_MEMORY_FAULT to forward the request to userspace. Add a new flag for memory faults, KVM_MEMORY_EXIT_FLAG_PRIVATE, to communicate whether the guest wants to map memory as shared vs. private. Like KVM_MEMORY_ATTRIBUTE_PRIVATE, use bit 3 for flagging private memory so that KVM can use bits 0-2 for capturing RWX behavior if/when userspace needs such information, e.g. a likely user of KVM_EXIT_MEMORY_FAULT is to exit on missing mappings when handling guest page fault VM-Exits. In that case, userspace will want to know RWX information in order to correctly/precisely resolve the fault. Note, private memory *must* be backed by guest_memfd, i.e. shared mappings always come from the host userspace page tables, and private mappings always come from a guest_memfd instance. Co-developed-by: Yu Zhang Signed-off-by: Yu Zhang Signed-off-by: Chao Peng Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Message-Id: <20231027182217.3615211-21-seanjc@google.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 8 +++- arch/x86/kvm/mmu/mmu.c | 101 ++++++++++++++++++++++++++++++++++++++-- arch/x86/kvm/mmu/mmu_internal.h | 1 + include/linux/kvm_host.h | 8 +++- include/uapi/linux/kvm.h | 1 + 5 files changed, 110 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 1e61faf02b2a..726c87c35d57 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6952,6 +6952,7 @@ spec refer, https://github.com/riscv/riscv-sbi-doc. /* KVM_EXIT_MEMORY_FAULT */ struct { + #define KVM_MEMORY_EXIT_FLAG_PRIVATE (1ULL << 3) __u64 flags; __u64 gpa; __u64 size; @@ -6960,8 +6961,11 @@ spec refer, https://github.com/riscv/riscv-sbi-doc. KVM_EXIT_MEMORY_FAULT indicates the vCPU has encountered a memory fault that could not be resolved by KVM. The 'gpa' and 'size' (in bytes) describe the guest physical address range [gpa, gpa + size) of the fault. The 'flags' field -describes properties of the faulting access that are likely pertinent. -Currently, no flags are defined. +describes properties of the faulting access that are likely pertinent: + + - KVM_MEMORY_EXIT_FLAG_PRIVATE - When set, indicates the memory fault occurred + on a private memory access. When clear, indicates the fault occurred on a + shared access. Note! KVM_EXIT_MEMORY_FAULT is unique among all KVM exit reasons in that it accompanies a return code of '-1', not '0'! errno will always be set to EFAULT diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index f5c6b0643645..754a5aaebee5 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3147,9 +3147,9 @@ out: return level; } -int kvm_mmu_max_mapping_level(struct kvm *kvm, - const struct kvm_memory_slot *slot, gfn_t gfn, - int max_level) +static int __kvm_mmu_max_mapping_level(struct kvm *kvm, + const struct kvm_memory_slot *slot, + gfn_t gfn, int max_level, bool is_private) { struct kvm_lpage_info *linfo; int host_level; @@ -3161,6 +3161,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, break; } + if (is_private) + return max_level; + if (max_level == PG_LEVEL_4K) return PG_LEVEL_4K; @@ -3168,6 +3171,16 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, return min(host_level, max_level); } +int kvm_mmu_max_mapping_level(struct kvm *kvm, + const struct kvm_memory_slot *slot, gfn_t gfn, + int max_level) +{ + bool is_private = kvm_slot_can_be_private(slot) && + kvm_mem_is_private(kvm, gfn); + + return __kvm_mmu_max_mapping_level(kvm, slot, gfn, max_level, is_private); +} + void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_memory_slot *slot = fault->slot; @@ -3188,8 +3201,9 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault * Enforce the iTLB multihit workaround after capturing the requested * level, which will be used to do precise, accurate accounting. */ - fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot, - fault->gfn, fault->max_level); + fault->req_level = __kvm_mmu_max_mapping_level(vcpu->kvm, slot, + fault->gfn, fault->max_level, + fault->is_private); if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed) return; @@ -4269,6 +4283,55 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL); } +static inline u8 kvm_max_level_for_order(int order) +{ + BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G); + + KVM_MMU_WARN_ON(order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G) && + order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M) && + order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K)); + + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G)) + return PG_LEVEL_1G; + + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M)) + return PG_LEVEL_2M; + + return PG_LEVEL_4K; +} + +static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT, + PAGE_SIZE, fault->write, fault->exec, + fault->is_private); +} + +static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + int max_order, r; + + if (!kvm_slot_can_be_private(fault->slot)) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + + r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn, + &max_order); + if (r) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return r; + } + + fault->max_level = min(kvm_max_level_for_order(max_order), + fault->max_level); + fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY); + + return RET_PF_CONTINUE; +} + static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_memory_slot *slot = fault->slot; @@ -4301,6 +4364,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault return RET_PF_EMULATE; } + if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + + if (fault->is_private) + return kvm_faultin_pfn_private(vcpu, fault); + async = false; fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async, fault->write, &fault->map_writable, @@ -7188,6 +7259,26 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm) } #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range) +{ + /* + * Zap SPTEs even if the slot can't be mapped PRIVATE. KVM x86 only + * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM + * can simply ignore such slots. But if userspace is making memory + * PRIVATE, then KVM must prevent the guest from accessing the memory + * as shared. And if userspace is making memory SHARED and this point + * is reached, then at least one page within the range was previously + * PRIVATE, i.e. the slot's possible hugepage ranges are changing. + * Zapping SPTEs in this case ensures KVM will reassess whether or not + * a hugepage can be used for affected ranges. + */ + if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) + return false; + + return kvm_unmap_gfn_range(kvm, range); +} + static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn, int level) { diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index decc1f153669..86c7cb692786 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -201,6 +201,7 @@ struct kvm_page_fault { /* Derived from mmu and global state. */ const bool is_tdp; + const bool is_private; const bool nx_huge_page_workaround_enabled; /* diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a6de526c0426..67dfd4d79529 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2357,14 +2357,18 @@ static inline void kvm_account_pgtable_pages(void *virt, int nr) #define KVM_DIRTY_RING_MAX_ENTRIES 65536 static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, - gpa_t gpa, gpa_t size) + gpa_t gpa, gpa_t size, + bool is_write, bool is_exec, + bool is_private) { vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT; vcpu->run->memory_fault.gpa = gpa; vcpu->run->memory_fault.size = size; - /* Flags are not (yet) defined or communicated to userspace. */ + /* RWX flags are not (yet) defined or communicated to userspace. */ vcpu->run->memory_fault.flags = 0; + if (is_private) + vcpu->run->memory_fault.flags |= KVM_MEMORY_EXIT_FLAG_PRIVATE; } #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 2802d10aa88c..8eb10f560c69 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -535,6 +535,7 @@ struct kvm_run { } notify; /* KVM_EXIT_MEMORY_FAULT */ struct { +#define KVM_MEMORY_EXIT_FLAG_PRIVATE (1ULL << 3) __u64 flags; __u64 gpa; __u64 size; -- cgit From 89ea60c2c7b5838bf192c50062d5720cd6ab8662 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 27 Oct 2023 11:22:05 -0700 Subject: KVM: x86: Add support for "protected VMs" that can utilize private memory Add a new x86 VM type, KVM_X86_SW_PROTECTED_VM, to serve as a development and testing vehicle for Confidential (CoCo) VMs, and potentially to even become a "real" product in the distant future, e.g. a la pKVM. The private memory support in KVM x86 is aimed at AMD's SEV-SNP and Intel's TDX, but those technologies are extremely complex (understatement), difficult to debug, don't support running as nested guests, and require hardware that's isn't universally accessible. I.e. relying SEV-SNP or TDX for maintaining guest private memory isn't a realistic option. At the very least, KVM_X86_SW_PROTECTED_VM will enable a variety of selftests for guest_memfd and private memory support without requiring unique hardware. Signed-off-by: Sean Christopherson Reviewed-by: Paolo Bonzini Message-Id: <20231027182217.3615211-24-seanjc@google.com> Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 32 ++++++++++++++++++++++++++++++++ arch/x86/include/asm/kvm_host.h | 15 +++++++++------ arch/x86/include/uapi/asm/kvm.h | 3 +++ arch/x86/kvm/Kconfig | 12 ++++++++++++ arch/x86/kvm/mmu/mmu_internal.h | 1 + arch/x86/kvm/x86.c | 16 +++++++++++++++- include/uapi/linux/kvm.h | 1 + virt/kvm/Kconfig | 5 +++++ 8 files changed, 78 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 726c87c35d57..926241e23aeb 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -147,10 +147,29 @@ described as 'basic' will be available. The new VM has no virtual cpus and no memory. You probably want to use 0 as machine type. +X86: +^^^^ + +Supported X86 VM types can be queried via KVM_CAP_VM_TYPES. + +S390: +^^^^^ + In order to create user controlled virtual machines on S390, check KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL as privileged user (CAP_SYS_ADMIN). +MIPS: +^^^^^ + +To use hardware assisted virtualization on MIPS (VZ ASE) rather than +the default trap & emulate implementation (which changes the virtual +memory layout to fit in user mode), check KVM_CAP_MIPS_VZ and use the +flag KVM_VM_MIPS_VZ. + +ARM64: +^^^^^^ + On arm64, the physical address size for a VM (IPA Size limit) is limited to 40bits by default. The limit can be configured if the host supports the extension KVM_CAP_ARM_VM_IPA_SIZE. When supported, use @@ -8765,6 +8784,19 @@ block sizes is exposed in KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES as a 64-bit bitmap (each bit describing a block size). The default value is 0, to disable the eager page splitting. +8.41 KVM_CAP_VM_TYPES +--------------------- + +:Capability: KVM_CAP_MEMORY_ATTRIBUTES +:Architectures: x86 +:Type: system ioctl + +This capability returns a bitmap of support VM types. The 1-setting of bit @n +means the VM type with value @n is supported. Possible values of @n are:: + + #define KVM_X86_DEFAULT_VM 0 + #define KVM_X86_SW_PROTECTED_VM 1 + 9. Known KVM API problems ========================= diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 75ab0da06e64..a565a2e70f30 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1255,6 +1255,7 @@ enum kvm_apicv_inhibit { }; struct kvm_arch { + unsigned long vm_type; unsigned long n_used_mmu_pages; unsigned long n_requested_mmu_pages; unsigned long n_max_mmu_pages; @@ -2089,6 +2090,12 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd); void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, int tdp_max_root_level, int tdp_huge_page_level); +#ifdef CONFIG_KVM_PRIVATE_MEM +#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.vm_type != KVM_X86_DEFAULT_VM) +#else +#define kvm_arch_has_private_mem(kvm) false +#endif + static inline u16 kvm_read_ldt(void) { u16 ldt; @@ -2137,14 +2144,10 @@ enum { #define HF_SMM_INSIDE_NMI_MASK (1 << 2) # define KVM_MAX_NR_ADDRESS_SPACES 2 +/* SMM is currently unsupported for guests with private memory. */ +# define kvm_arch_nr_memslot_as_ids(kvm) (kvm_arch_has_private_mem(kvm) ? 1 : 2) # define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0) # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm) - -static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm) -{ - return KVM_MAX_NR_ADDRESS_SPACES; -} - #else # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0) #endif diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 1a6a1f987949..a448d0964fc0 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -562,4 +562,7 @@ struct kvm_pmu_event_filter { /* x86-specific KVM_EXIT_HYPERCALL flags. */ #define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) +#define KVM_X86_DEFAULT_VM 0 +#define KVM_X86_SW_PROTECTED_VM 1 + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index e61383674c75..c1716e83d176 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -77,6 +77,18 @@ config KVM_WERROR If in doubt, say "N". +config KVM_SW_PROTECTED_VM + bool "Enable support for KVM software-protected VMs" + depends on EXPERT + depends on X86_64 + select KVM_GENERIC_PRIVATE_MEM + help + Enable support for KVM software-protected VMs. Currently "protected" + means the VM can be backed with memory provided by + KVM_CREATE_GUEST_MEMFD. + + If unsure, say "N". + config KVM_INTEL tristate "KVM for Intel (and compatible) processors support" depends on KVM && IA32_FEAT_CTL diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 86c7cb692786..b66a7d47e0e4 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -297,6 +297,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, .max_level = KVM_MAX_HUGEPAGE_LEVEL, .req_level = PG_LEVEL_4K, .goal_level = PG_LEVEL_4K, + .is_private = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT), }; int r; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f521c97f5c64..6d0772b47041 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4548,6 +4548,13 @@ static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu, return 0; } +static bool kvm_is_vm_type_supported(unsigned long type) +{ + return type == KVM_X86_DEFAULT_VM || + (type == KVM_X86_SW_PROTECTED_VM && + IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_enabled); +} + int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) { int r = 0; @@ -4739,6 +4746,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_X86_NOTIFY_VMEXIT: r = kvm_caps.has_notify_vmexit; break; + case KVM_CAP_VM_TYPES: + r = BIT(KVM_X86_DEFAULT_VM); + if (kvm_is_vm_type_supported(KVM_X86_SW_PROTECTED_VM)) + r |= BIT(KVM_X86_SW_PROTECTED_VM); + break; default: break; } @@ -12436,9 +12448,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) int ret; unsigned long flags; - if (type) + if (!kvm_is_vm_type_supported(type)) return -EINVAL; + kvm->arch.vm_type = type; + ret = kvm_page_track_init(kvm); if (ret) goto out; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 8eb10f560c69..e9cb2df67a1d 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1227,6 +1227,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_MEMORY_FAULT_INFO 232 #define KVM_CAP_MEMORY_ATTRIBUTES 233 #define KVM_CAP_GUEST_MEMFD 234 +#define KVM_CAP_VM_TYPES 235 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 08afef022db9..2c964586aa14 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -104,3 +104,8 @@ config KVM_GENERIC_MEMORY_ATTRIBUTES config KVM_PRIVATE_MEM select XARRAY_MULTI bool + +config KVM_GENERIC_PRIVATE_MEM + select KVM_GENERIC_MEMORY_ATTRIBUTES + select KVM_PRIVATE_MEM + bool -- cgit From 5f99f312bd3bedb3b266b0d26376a8c500cdc97f Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Sat, 11 Nov 2023 17:06:00 -0800 Subject: bpf: add register bounds sanity checks and sanitization Add simple sanity checks that validate well-formed ranges (min <= max) across u64, s64, u32, and s32 ranges. Also for cases when the value is constant (either 64-bit or 32-bit), we validate that ranges and tnums are in agreement. These bounds checks are performed at the end of BPF_ALU/BPF_ALU64 operations, on conditional jumps, and for LDX instructions (where subreg zero/sign extension is probably the most important to check). This covers most of the interesting cases. Also, we validate the sanity of the return register when manually adjusting it for some special helpers. By default, sanity violation will trigger a warning in verifier log and resetting register bounds to "unbounded" ones. But to aid development and debugging, BPF_F_TEST_SANITY_STRICT flag is added, which will trigger hard failure of verification with -EFAULT on register bounds violations. This allows selftests to catch such issues. veristat will also gain a CLI option to enable this behavior. Acked-by: Eduard Zingerman Signed-off-by: Andrii Nakryiko Acked-by: Shung-Hsi Yu Link: https://lore.kernel.org/r/20231112010609.848406-5-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 1 + include/uapi/linux/bpf.h | 3 ++ kernel/bpf/syscall.c | 3 +- kernel/bpf/verifier.c | 117 ++++++++++++++++++++++++++++++++--------- tools/include/uapi/linux/bpf.h | 3 ++ 5 files changed, 101 insertions(+), 26 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 24213a99cc79..402b6bc44a1b 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -602,6 +602,7 @@ struct bpf_verifier_env { int stack_size; /* number of states to be processed */ bool strict_alignment; /* perform strict pointer alignment checks */ bool test_state_freq; /* test verifier with different pruning frequency */ + bool test_sanity_strict; /* fail verification on sanity violations */ struct bpf_verifier_state *cur_state; /* current verifier state */ struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ struct bpf_verifier_state_list *free_list; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7cf8bcf9f6a2..8a5855fcee69 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1200,6 +1200,9 @@ enum bpf_perf_event_type { */ #define BPF_F_XDP_DEV_BOUND_ONLY (1U << 6) +/* The verifier internal test flag. Behavior is undefined */ +#define BPF_F_TEST_SANITY_STRICT (1U << 7) + /* link_create.kprobe_multi.flags used in LINK_CREATE command for * BPF_TRACE_KPROBE_MULTI attach type to create return probe. */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0ed286b8a0f0..f266e03ba342 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2573,7 +2573,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) BPF_F_SLEEPABLE | BPF_F_TEST_RND_HI32 | BPF_F_XDP_HAS_FRAGS | - BPF_F_XDP_DEV_BOUND_ONLY)) + BPF_F_XDP_DEV_BOUND_ONLY | + BPF_F_TEST_SANITY_STRICT)) return -EINVAL; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 65570eedfe88..e7edacf86e0f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2615,6 +2615,56 @@ static void reg_bounds_sync(struct bpf_reg_state *reg) __update_reg_bounds(reg); } +static int reg_bounds_sanity_check(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, const char *ctx) +{ + const char *msg; + + if (reg->umin_value > reg->umax_value || + reg->smin_value > reg->smax_value || + reg->u32_min_value > reg->u32_max_value || + reg->s32_min_value > reg->s32_max_value) { + msg = "range bounds violation"; + goto out; + } + + if (tnum_is_const(reg->var_off)) { + u64 uval = reg->var_off.value; + s64 sval = (s64)uval; + + if (reg->umin_value != uval || reg->umax_value != uval || + reg->smin_value != sval || reg->smax_value != sval) { + msg = "const tnum out of sync with range bounds"; + goto out; + } + } + + if (tnum_subreg_is_const(reg->var_off)) { + u32 uval32 = tnum_subreg(reg->var_off).value; + s32 sval32 = (s32)uval32; + + if (reg->u32_min_value != uval32 || reg->u32_max_value != uval32 || + reg->s32_min_value != sval32 || reg->s32_max_value != sval32) { + msg = "const subreg tnum out of sync with range bounds"; + goto out; + } + } + + return 0; +out: + verbose(env, "REG SANITY VIOLATION (%s): %s u64=[%#llx, %#llx] " + "s64=[%#llx, %#llx] u32=[%#x, %#x] s32=[%#x, %#x] var_off=(%#llx, %#llx)\n", + ctx, msg, reg->umin_value, reg->umax_value, + reg->smin_value, reg->smax_value, + reg->u32_min_value, reg->u32_max_value, + reg->s32_min_value, reg->s32_max_value, + reg->var_off.value, reg->var_off.mask); + if (env->test_sanity_strict) + return -EFAULT; + __mark_reg_unbounded(reg); + return 0; +} + static bool __reg32_bound_s64(s32 a) { return a >= 0 && a <= S32_MAX; @@ -9982,14 +10032,15 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) return 0; } -static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type, - int func_id, - struct bpf_call_arg_meta *meta) +static int do_refine_retval_range(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, int ret_type, + int func_id, + struct bpf_call_arg_meta *meta) { struct bpf_reg_state *ret_reg = ®s[BPF_REG_0]; if (ret_type != RET_INTEGER) - return; + return 0; switch (func_id) { case BPF_FUNC_get_stack: @@ -10015,6 +10066,8 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type, reg_bounds_sync(ret_reg); break; } + + return reg_bounds_sanity_check(env, ret_reg, "retval"); } static int @@ -10666,7 +10719,9 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs[BPF_REG_0].ref_obj_id = id; } - do_refine_retval_range(regs, fn->ret_type, func_id, &meta); + err = do_refine_retval_range(env, regs, fn->ret_type, func_id, &meta); + if (err) + return err; err = check_map_func_compatibility(env, meta.map_ptr, func_id); if (err) @@ -14166,13 +14221,12 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) /* check dest operand */ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); + err = err ?: adjust_reg_min_max_vals(env, insn); if (err) return err; - - return adjust_reg_min_max_vals(env, insn); } - return 0; + return reg_bounds_sanity_check(env, ®s[insn->dst_reg], "alu"); } static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, @@ -14653,18 +14707,21 @@ again: * Technically we can do similar adjustments for pointers to the same object, * but we don't support that right now. */ -static void reg_set_min_max(struct bpf_reg_state *true_reg1, - struct bpf_reg_state *true_reg2, - struct bpf_reg_state *false_reg1, - struct bpf_reg_state *false_reg2, - u8 opcode, bool is_jmp32) +static int reg_set_min_max(struct bpf_verifier_env *env, + struct bpf_reg_state *true_reg1, + struct bpf_reg_state *true_reg2, + struct bpf_reg_state *false_reg1, + struct bpf_reg_state *false_reg2, + u8 opcode, bool is_jmp32) { + int err; + /* If either register is a pointer, we can't learn anything about its * variable offset from the compare (unless they were a pointer into * the same object, but we don't bother with that). */ if (false_reg1->type != SCALAR_VALUE || false_reg2->type != SCALAR_VALUE) - return; + return 0; /* fallthrough (FALSE) branch */ regs_refine_cond_op(false_reg1, false_reg2, rev_opcode(opcode), is_jmp32); @@ -14675,6 +14732,12 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg1, regs_refine_cond_op(true_reg1, true_reg2, opcode, is_jmp32); reg_bounds_sync(true_reg1); reg_bounds_sync(true_reg2); + + err = reg_bounds_sanity_check(env, true_reg1, "true_reg1"); + err = err ?: reg_bounds_sanity_check(env, true_reg2, "true_reg2"); + err = err ?: reg_bounds_sanity_check(env, false_reg1, "false_reg1"); + err = err ?: reg_bounds_sanity_check(env, false_reg2, "false_reg2"); + return err; } static void mark_ptr_or_null_reg(struct bpf_func_state *state, @@ -14968,15 +15031,20 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, other_branch_regs = other_branch->frame[other_branch->curframe]->regs; if (BPF_SRC(insn->code) == BPF_X) { - reg_set_min_max(&other_branch_regs[insn->dst_reg], - &other_branch_regs[insn->src_reg], - dst_reg, src_reg, opcode, is_jmp32); + err = reg_set_min_max(env, + &other_branch_regs[insn->dst_reg], + &other_branch_regs[insn->src_reg], + dst_reg, src_reg, opcode, is_jmp32); } else /* BPF_SRC(insn->code) == BPF_K */ { - reg_set_min_max(&other_branch_regs[insn->dst_reg], - src_reg /* fake one */, - dst_reg, src_reg /* same fake one */, - opcode, is_jmp32); + err = reg_set_min_max(env, + &other_branch_regs[insn->dst_reg], + src_reg /* fake one */, + dst_reg, src_reg /* same fake one */, + opcode, is_jmp32); } + if (err) + return err; + if (BPF_SRC(insn->code) == BPF_X && src_reg->type == SCALAR_VALUE && src_reg->id && !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) { @@ -17479,10 +17547,8 @@ static int do_check(struct bpf_verifier_env *env) insn->off, BPF_SIZE(insn->code), BPF_READ, insn->dst_reg, false, BPF_MODE(insn->code) == BPF_MEMSX); - if (err) - return err; - - err = save_aux_ptr_type(env, src_reg_type, true); + err = err ?: save_aux_ptr_type(env, src_reg_type, true); + err = err ?: reg_bounds_sanity_check(env, ®s[insn->dst_reg], "ldx"); if (err) return err; } else if (class == BPF_STX) { @@ -20769,6 +20835,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; + env->test_sanity_strict = attr->prog_flags & BPF_F_TEST_SANITY_STRICT; env->explored_states = kvcalloc(state_htab_size(env), sizeof(struct bpf_verifier_state_list *), diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7cf8bcf9f6a2..8a5855fcee69 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1200,6 +1200,9 @@ enum bpf_perf_event_type { */ #define BPF_F_XDP_DEV_BOUND_ONLY (1U << 6) +/* The verifier internal test flag. Behavior is undefined */ +#define BPF_F_TEST_SANITY_STRICT (1U << 7) + /* link_create.kprobe_multi.flags used in LINK_CREATE command for * BPF_TRACE_KPROBE_MULTI attach type to create return probe. */ -- cgit From 5d33213fac5929a2e7766c88d78779fd443b0fe8 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 3 Nov 2023 10:39:24 +0300 Subject: media: v4l2-subdev: Fix a 64bit bug The problem is this line here from subdev_do_ioctl(). client_cap->capabilities &= ~V4L2_SUBDEV_CLIENT_CAP_STREAMS; The "client_cap->capabilities" variable is a u64. The AND operation is supposed to clear out the V4L2_SUBDEV_CLIENT_CAP_STREAMS flag. But because it's a 32 bit variable it accidentally clears out the high 32 bits as well. Currently we only use the first bit and none of the upper bits so this doesn't affect runtime behavior. Fixes: f57fa2959244 ("media: v4l2-subdev: Add new ioctl for client capabilities") Signed-off-by: Dan Carpenter Reviewed-by: Tomi Valkeinen Signed-off-by: Hans Verkuil --- include/uapi/linux/v4l2-subdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h index 4a195b68f28f..b383c2fe0cf3 100644 --- a/include/uapi/linux/v4l2-subdev.h +++ b/include/uapi/linux/v4l2-subdev.h @@ -239,7 +239,7 @@ struct v4l2_subdev_routing { * set (which is the default), the 'stream' fields will be forced to 0 by the * kernel. */ - #define V4L2_SUBDEV_CLIENT_CAP_STREAMS (1U << 0) + #define V4L2_SUBDEV_CLIENT_CAP_STREAMS (1ULL << 0) /** * struct v4l2_subdev_client_capability - Capabilities of the client accessing -- cgit From c6e9dba3be5ef3b701b29b143609561915e5d0e9 Mon Sep 17 00:00:00 2001 From: Alce Lafranque Date: Tue, 14 Nov 2023 11:36:57 -0600 Subject: vxlan: add support for flowlabel inherit By default, VXLAN encapsulation over IPv6 sets the flow label to 0, with an option for a fixed value. This commits add the ability to inherit the flow label from the inner packet, like for other tunnel implementations. This enables devices using only L3 headers for ECMP to correctly balance VXLAN-encapsulated IPv6 packets. ``` $ ./ip/ip link add dummy1 type dummy $ ./ip/ip addr add 2001:db8::2/64 dev dummy1 $ ./ip/ip link set up dev dummy1 $ ./ip/ip link add vxlan1 type vxlan id 100 flowlabel inherit remote 2001:db8::1 local 2001:db8::2 $ ./ip/ip link set up dev vxlan1 $ ./ip/ip addr add 2001:db8:1::2/64 dev vxlan1 $ ./ip/ip link set arp off dev vxlan1 $ ping -q 2001:db8:1::1 & $ tshark -d udp.port==8472,vxlan -Vpni dummy1 -c1 [...] Internet Protocol Version 6, Src: 2001:db8::2, Dst: 2001:db8::1 0110 .... = Version: 6 .... 0000 0000 .... .... .... .... .... = Traffic Class: 0x00 (DSCP: CS0, ECN: Not-ECT) .... 0000 00.. .... .... .... .... .... = Differentiated Services Codepoint: Default (0) .... .... ..00 .... .... .... .... .... = Explicit Congestion Notification: Not ECN-Capable Transport (0) .... 1011 0001 1010 1111 1011 = Flow Label: 0xb1afb [...] Virtual eXtensible Local Area Network Flags: 0x0800, VXLAN Network ID (VNI) Group Policy ID: 0 VXLAN Network Identifier (VNI): 100 [...] Internet Protocol Version 6, Src: 2001:db8:1::2, Dst: 2001:db8:1::1 0110 .... = Version: 6 .... 0000 0000 .... .... .... .... .... = Traffic Class: 0x00 (DSCP: CS0, ECN: Not-ECT) .... 0000 00.. .... .... .... .... .... = Differentiated Services Codepoint: Default (0) .... .... ..00 .... .... .... .... .... = Explicit Congestion Notification: Not ECN-Capable Transport (0) .... 1011 0001 1010 1111 1011 = Flow Label: 0xb1afb ``` Signed-off-by: Alce Lafranque Co-developed-by: Vincent Bernat Signed-off-by: Vincent Bernat Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/vxlan/vxlan_core.c | 23 ++++++++++++++++++++++- include/net/ip_tunnels.h | 11 +++++++++++ include/net/vxlan.h | 33 +++++++++++++++++---------------- include/uapi/linux/if_link.h | 8 ++++++++ 4 files changed, 58 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 412c3c0b6990..764ea02ff911 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -2379,7 +2379,17 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, else udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX); #if IS_ENABLED(CONFIG_IPV6) - key.label = vxlan->cfg.label; + switch (vxlan->cfg.label_policy) { + case VXLAN_LABEL_FIXED: + key.label = vxlan->cfg.label; + break; + case VXLAN_LABEL_INHERIT: + key.label = ip_tunnel_get_flowlabel(old_iph, skb); + break; + default: + DEBUG_NET_WARN_ON_ONCE(1); + goto drop; + } #endif } else { if (!info) { @@ -3366,6 +3376,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_DF] = { .type = NLA_U8 }, [IFLA_VXLAN_VNIFILTER] = { .type = NLA_U8 }, [IFLA_VXLAN_LOCALBYPASS] = NLA_POLICY_MAX(NLA_U8, 1), + [IFLA_VXLAN_LABEL_POLICY] = NLA_POLICY_MAX(NLA_U32, VXLAN_LABEL_MAX), }; static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[], @@ -3740,6 +3751,12 @@ static int vxlan_config_validate(struct net *src_net, struct vxlan_config *conf, return -EINVAL; } + if (conf->label_policy && !use_ipv6) { + NL_SET_ERR_MSG(extack, + "Label policy only applies to IPv6 VXLAN devices"); + return -EINVAL; + } + if (conf->remote_ifindex) { struct net_device *lowerdev; @@ -4082,6 +4099,8 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], if (data[IFLA_VXLAN_LABEL]) conf->label = nla_get_be32(data[IFLA_VXLAN_LABEL]) & IPV6_FLOWLABEL_MASK; + if (data[IFLA_VXLAN_LABEL_POLICY]) + conf->label_policy = nla_get_u32(data[IFLA_VXLAN_LABEL_POLICY]); if (data[IFLA_VXLAN_LEARNING]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LEARNING, @@ -4398,6 +4417,7 @@ static size_t vxlan_get_size(const struct net_device *dev) nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TOS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_DF */ nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */ + nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LABEL_POLICY */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_PROXY */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_RSC */ @@ -4471,6 +4491,7 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) || nla_put_u8(skb, IFLA_VXLAN_DF, vxlan->cfg.df) || nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) || + nla_put_u32(skb, IFLA_VXLAN_LABEL_POLICY, vxlan->cfg.label_policy) || nla_put_u8(skb, IFLA_VXLAN_LEARNING, !!(vxlan->cfg.flags & VXLAN_F_LEARN)) || nla_put_u8(skb, IFLA_VXLAN_PROXY, diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index f346b4efbc30..2d746f4c9a0a 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -416,6 +416,17 @@ static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph, return 0; } +static inline __be32 ip_tunnel_get_flowlabel(const struct iphdr *iph, + const struct sk_buff *skb) +{ + __be16 payload_protocol = skb_protocol(skb, true); + + if (payload_protocol == htons(ETH_P_IPV6)) + return ip6_flowlabel((const struct ipv6hdr *)iph); + else + return 0; +} + static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph, const struct sk_buff *skb) { diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 6a9f8a5f387c..33ba6fc151cf 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -210,22 +210,23 @@ struct vxlan_rdst { }; struct vxlan_config { - union vxlan_addr remote_ip; - union vxlan_addr saddr; - __be32 vni; - int remote_ifindex; - int mtu; - __be16 dst_port; - u16 port_min; - u16 port_max; - u8 tos; - u8 ttl; - __be32 label; - u32 flags; - unsigned long age_interval; - unsigned int addrmax; - bool no_share; - enum ifla_vxlan_df df; + union vxlan_addr remote_ip; + union vxlan_addr saddr; + __be32 vni; + int remote_ifindex; + int mtu; + __be16 dst_port; + u16 port_min; + u16 port_max; + u8 tos; + u8 ttl; + __be32 label; + enum ifla_vxlan_label_policy label_policy; + u32 flags; + unsigned long age_interval; + unsigned int addrmax; + bool no_share; + enum ifla_vxlan_df df; }; enum { diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 29ff80da2775..8181ef23a7a2 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -856,6 +856,7 @@ enum { IFLA_VXLAN_DF, IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */ IFLA_VXLAN_LOCALBYPASS, + IFLA_VXLAN_LABEL_POLICY, /* IPv6 flow label policy; ifla_vxlan_label_policy */ __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) @@ -873,6 +874,13 @@ enum ifla_vxlan_df { VXLAN_DF_MAX = __VXLAN_DF_END - 1, }; +enum ifla_vxlan_label_policy { + VXLAN_LABEL_FIXED = 0, + VXLAN_LABEL_INHERIT = 1, + __VXLAN_LABEL_END, + VXLAN_LABEL_MAX = __VXLAN_LABEL_END - 1, +}; + /* GENEVE section */ enum { IFLA_GENEVE_UNSPEC, -- cgit From ff8867af01daa7ea770bebf5f91199b7434b74e5 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 17 Nov 2023 09:14:04 -0800 Subject: bpf: rename BPF_F_TEST_SANITY_STRICT to BPF_F_TEST_REG_INVARIANTS Rename verifier internal flag BPF_F_TEST_SANITY_STRICT to more neutral BPF_F_TEST_REG_INVARIANTS. This is a follow up to [0]. A few selftests and veristat need to be adjusted in the same patch as well. [0] https://patchwork.kernel.org/project/netdevbpf/patch/20231112010609.848406-5-andrii@kernel.org/ Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231117171404.225508-1-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 2 +- include/uapi/linux/bpf.h | 2 +- kernel/bpf/syscall.c | 2 +- kernel/bpf/verifier.c | 6 +++--- tools/include/uapi/linux/bpf.h | 2 +- tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c | 2 +- tools/testing/selftests/bpf/prog_tests/reg_bounds.c | 2 +- tools/testing/selftests/bpf/progs/verifier_bounds.c | 4 ++-- tools/testing/selftests/bpf/test_loader.c | 6 +++--- tools/testing/selftests/bpf/test_sock_addr.c | 3 +-- tools/testing/selftests/bpf/test_verifier.c | 2 +- tools/testing/selftests/bpf/testing_helpers.c | 4 ++-- tools/testing/selftests/bpf/veristat.c | 12 ++++++------ 13 files changed, 24 insertions(+), 25 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 402b6bc44a1b..52a4012b8255 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -602,7 +602,7 @@ struct bpf_verifier_env { int stack_size; /* number of states to be processed */ bool strict_alignment; /* perform strict pointer alignment checks */ bool test_state_freq; /* test verifier with different pruning frequency */ - bool test_sanity_strict; /* fail verification on sanity violations */ + bool test_reg_invariants; /* fail verification on register invariants violations */ struct bpf_verifier_state *cur_state; /* current verifier state */ struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ struct bpf_verifier_state_list *free_list; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 8a5855fcee69..7a5498242eaa 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1201,7 +1201,7 @@ enum bpf_perf_event_type { #define BPF_F_XDP_DEV_BOUND_ONLY (1U << 6) /* The verifier internal test flag. Behavior is undefined */ -#define BPF_F_TEST_SANITY_STRICT (1U << 7) +#define BPF_F_TEST_REG_INVARIANTS (1U << 7) /* link_create.kprobe_multi.flags used in LINK_CREATE command for * BPF_TRACE_KPROBE_MULTI attach type to create return probe. diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f266e03ba342..5e43ddd1b83f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2574,7 +2574,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) BPF_F_TEST_RND_HI32 | BPF_F_XDP_HAS_FRAGS | BPF_F_XDP_DEV_BOUND_ONLY | - BPF_F_TEST_SANITY_STRICT)) + BPF_F_TEST_REG_INVARIANTS)) return -EINVAL; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 59505881e7a7..7c3461b89513 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2608,14 +2608,14 @@ static int reg_bounds_sanity_check(struct bpf_verifier_env *env, return 0; out: - verbose(env, "REG SANITY VIOLATION (%s): %s u64=[%#llx, %#llx] " + verbose(env, "REG INVARIANTS VIOLATION (%s): %s u64=[%#llx, %#llx] " "s64=[%#llx, %#llx] u32=[%#x, %#x] s32=[%#x, %#x] var_off=(%#llx, %#llx)\n", ctx, msg, reg->umin_value, reg->umax_value, reg->smin_value, reg->smax_value, reg->u32_min_value, reg->u32_max_value, reg->s32_min_value, reg->s32_max_value, reg->var_off.value, reg->var_off.mask); - if (env->test_sanity_strict) + if (env->test_reg_invariants) return -EFAULT; __mark_reg_unbounded(reg); return 0; @@ -20791,7 +20791,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; - env->test_sanity_strict = attr->prog_flags & BPF_F_TEST_SANITY_STRICT; + env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS; env->explored_states = kvcalloc(state_htab_size(env), sizeof(struct bpf_verifier_state_list *), diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 8a5855fcee69..7a5498242eaa 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1201,7 +1201,7 @@ enum bpf_perf_event_type { #define BPF_F_XDP_DEV_BOUND_ONLY (1U << 6) /* The verifier internal test flag. Behavior is undefined */ -#define BPF_F_TEST_SANITY_STRICT (1U << 7) +#define BPF_F_TEST_REG_INVARIANTS (1U << 7) /* link_create.kprobe_multi.flags used in LINK_CREATE command for * BPF_TRACE_KPROBE_MULTI attach type to create return probe. diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c index 3f2d70831873..e770912fc1d2 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c @@ -35,7 +35,7 @@ static int check_load(const char *file, enum bpf_prog_type type) } bpf_program__set_type(prog, type); - bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32 | BPF_F_TEST_SANITY_STRICT); + bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS); bpf_program__set_log_level(prog, 4 | extra_prog_load_log_flags); err = bpf_object__load(obj); diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c index fe0cb906644b..7a8b0bf0a7f8 100644 --- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c +++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c @@ -838,7 +838,7 @@ static int load_range_cmp_prog(struct range x, struct range y, enum op op, .log_level = 2, .log_buf = log_buf, .log_size = log_sz, - .prog_flags = BPF_F_TEST_SANITY_STRICT, + .prog_flags = BPF_F_TEST_REG_INVARIANTS, ); /* ; skip exit block below diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c index 0c1460936373..ec430b71730b 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bounds.c +++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c @@ -965,7 +965,7 @@ l0_%=: r0 = 0; \ SEC("xdp") __description("bound check with JMP_JSLT for crossing 64-bit signed boundary") __success __retval(0) -__flag(!BPF_F_TEST_SANITY_STRICT) /* known sanity violation */ +__flag(!BPF_F_TEST_REG_INVARIANTS) /* known invariants violation */ __naked void crossing_64_bit_signed_boundary_2(void) { asm volatile (" \ @@ -1047,7 +1047,7 @@ l0_%=: r0 = 0; \ SEC("xdp") __description("bound check with JMP32_JSLT for crossing 32-bit signed boundary") __success __retval(0) -__flag(!BPF_F_TEST_SANITY_STRICT) /* known sanity violation */ +__flag(!BPF_F_TEST_REG_INVARIANTS) /* known invariants violation */ __naked void crossing_32_bit_signed_boundary_2(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c index 57e27b1a73a6..a350ecdfba4a 100644 --- a/tools/testing/selftests/bpf/test_loader.c +++ b/tools/testing/selftests/bpf/test_loader.c @@ -179,7 +179,7 @@ static int parse_test_spec(struct test_loader *tester, memset(spec, 0, sizeof(*spec)); spec->prog_name = bpf_program__name(prog); - spec->prog_flags = BPF_F_TEST_SANITY_STRICT; /* by default be strict */ + spec->prog_flags = BPF_F_TEST_REG_INVARIANTS; /* by default be strict */ btf = bpf_object__btf(obj); if (!btf) { @@ -280,8 +280,8 @@ static int parse_test_spec(struct test_loader *tester, update_flags(&spec->prog_flags, BPF_F_SLEEPABLE, clear); } else if (strcmp(val, "BPF_F_XDP_HAS_FRAGS") == 0) { update_flags(&spec->prog_flags, BPF_F_XDP_HAS_FRAGS, clear); - } else if (strcmp(val, "BPF_F_TEST_SANITY_STRICT") == 0) { - update_flags(&spec->prog_flags, BPF_F_TEST_SANITY_STRICT, clear); + } else if (strcmp(val, "BPF_F_TEST_REG_INVARIANTS") == 0) { + update_flags(&spec->prog_flags, BPF_F_TEST_REG_INVARIANTS, clear); } else /* assume numeric value */ { err = parse_int(val, &flags, "test prog flags"); if (err) diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index 878c077e0fa7..b0068a9d2cfe 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -679,8 +679,7 @@ static int load_path(const struct sock_addr_test *test, const char *path) bpf_program__set_type(prog, BPF_PROG_TYPE_CGROUP_SOCK_ADDR); bpf_program__set_expected_attach_type(prog, test->expected_attach_type); - bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32); - bpf_program__set_flags(prog, BPF_F_TEST_SANITY_STRICT); + bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS); err = bpf_object__load(obj); if (err) { diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 4992022f3137..f36e41435be7 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -1588,7 +1588,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, if (fixup_skips != skips) return; - pflags = BPF_F_TEST_RND_HI32 | BPF_F_TEST_SANITY_STRICT; + pflags = BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS; if (test->flags & F_LOAD_WITH_STRICT_ALIGNMENT) pflags |= BPF_F_STRICT_ALIGNMENT; if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c index 9786a94a666c..d2458c1b1671 100644 --- a/tools/testing/selftests/bpf/testing_helpers.c +++ b/tools/testing/selftests/bpf/testing_helpers.c @@ -276,7 +276,7 @@ int bpf_prog_test_load(const char *file, enum bpf_prog_type type, if (type != BPF_PROG_TYPE_UNSPEC && bpf_program__type(prog) != type) bpf_program__set_type(prog, type); - flags = bpf_program__flags(prog) | BPF_F_TEST_RND_HI32 | BPF_F_TEST_SANITY_STRICT; + flags = bpf_program__flags(prog) | BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS; bpf_program__set_flags(prog, flags); err = bpf_object__load(obj); @@ -299,7 +299,7 @@ int bpf_test_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, { LIBBPF_OPTS(bpf_prog_load_opts, opts, .kern_version = kern_version, - .prog_flags = BPF_F_TEST_RND_HI32 | BPF_F_TEST_SANITY_STRICT, + .prog_flags = BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS, .log_level = extra_prog_load_log_flags, .log_buf = log_buf, .log_size = log_buf_sz, diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c index 609fd9753af0..1d418d66e375 100644 --- a/tools/testing/selftests/bpf/veristat.c +++ b/tools/testing/selftests/bpf/veristat.c @@ -145,7 +145,7 @@ static struct env { bool debug; bool quiet; bool force_checkpoints; - bool strict_range_sanity; + bool force_reg_invariants; enum resfmt out_fmt; bool show_version; bool comparison_mode; @@ -225,8 +225,8 @@ static const struct argp_option opts[] = { { "filter", 'f', "FILTER", 0, "Filter expressions (or @filename for file with expressions)." }, { "test-states", 't', NULL, 0, "Force frequent BPF verifier state checkpointing (set BPF_F_TEST_STATE_FREQ program flag)" }, - { "test-sanity", 'r', NULL, 0, - "Force strict BPF verifier register sanity behavior (BPF_F_TEST_SANITY_STRICT program flag)" }, + { "test-reg-invariants", 'r', NULL, 0, + "Force BPF verifier failure on register invariant violation (BPF_F_TEST_REG_INVARIANTS program flag)" }, {}, }; @@ -299,7 +299,7 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) env.force_checkpoints = true; break; case 'r': - env.strict_range_sanity = true; + env.force_reg_invariants = true; break; case 'n': errno = 0; @@ -1028,8 +1028,8 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf if (env.force_checkpoints) bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_STATE_FREQ); - if (env.strict_range_sanity) - bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_SANITY_STRICT); + if (env.force_reg_invariants) + bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_REG_INVARIANTS); err = bpf_object__load(obj); env.progs_processed++; -- cgit From 8a924db2d7b5eb69ba08b1a0af46e9f1359a9bdf Mon Sep 17 00:00:00 2001 From: Stefan Berger Date: Mon, 2 Oct 2023 08:57:33 -0400 Subject: fs: Pass AT_GETATTR_NOSEC flag to getattr interface function When vfs_getattr_nosec() calls a filesystem's getattr interface function then the 'nosec' should propagate into this function so that vfs_getattr_nosec() can again be called from the filesystem's gettattr rather than vfs_getattr(). The latter would add unnecessary security checks that the initial vfs_getattr_nosec() call wanted to avoid. Therefore, introduce the getattr flag GETATTR_NOSEC and allow to pass with the new getattr_flags parameter to the getattr interface function. In overlayfs and ecryptfs use this flag to determine which one of the two functions to call. In a recent code change introduced to IMA vfs_getattr_nosec() ended up calling vfs_getattr() in overlayfs, which in turn called security_inode_getattr() on an exiting process that did not have current->fs set anymore, which then caused a kernel NULL pointer dereference. With this change the call to security_inode_getattr() can be avoided, thus avoiding the NULL pointer dereference. Reported-by: Fixes: db1d1e8b9867 ("IMA: use vfs_getattr_nosec to get the i_version") Cc: Alexander Viro Cc: Cc: Miklos Szeredi Cc: Amir Goldstein Cc: Tyler Hicks Cc: Mimi Zohar Suggested-by: Christian Brauner Co-developed-by: Amir Goldstein Signed-off-by: Stefan Berger Link: https://lore.kernel.org/r/20231002125733.1251467-1-stefanb@linux.vnet.ibm.com Reviewed-by: Amir Goldstein Signed-off-by: Christian Brauner --- fs/ecryptfs/inode.c | 12 ++++++++++-- fs/overlayfs/inode.c | 10 +++++----- fs/overlayfs/overlayfs.h | 8 ++++++++ fs/stat.c | 6 +++++- include/uapi/linux/fcntl.h | 3 +++ 5 files changed, 31 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index a25dd3d20008..b0e8774c435a 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -998,6 +998,14 @@ static int ecryptfs_getattr_link(struct mnt_idmap *idmap, return rc; } +static int ecryptfs_do_getattr(const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int flags) +{ + if (flags & AT_GETATTR_NOSEC) + return vfs_getattr_nosec(path, stat, request_mask, flags); + return vfs_getattr(path, stat, request_mask, flags); +} + static int ecryptfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) @@ -1006,8 +1014,8 @@ static int ecryptfs_getattr(struct mnt_idmap *idmap, struct kstat lower_stat; int rc; - rc = vfs_getattr(ecryptfs_dentry_to_lower_path(dentry), &lower_stat, - request_mask, flags); + rc = ecryptfs_do_getattr(ecryptfs_dentry_to_lower_path(dentry), + &lower_stat, request_mask, flags); if (!rc) { fsstack_copy_attr_all(d_inode(dentry), ecryptfs_inode_to_lower(d_inode(dentry))); diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 345b8f161ca4..c63b31a460be 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -171,7 +171,7 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path, type = ovl_path_real(dentry, &realpath); old_cred = ovl_override_creds(dentry->d_sb); - err = vfs_getattr(&realpath, stat, request_mask, flags); + err = ovl_do_getattr(&realpath, stat, request_mask, flags); if (err) goto out; @@ -196,8 +196,8 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path, (!is_dir ? STATX_NLINK : 0); ovl_path_lower(dentry, &realpath); - err = vfs_getattr(&realpath, &lowerstat, - lowermask, flags); + err = ovl_do_getattr(&realpath, &lowerstat, lowermask, + flags); if (err) goto out; @@ -249,8 +249,8 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path, ovl_path_lowerdata(dentry, &realpath); if (realpath.dentry) { - err = vfs_getattr(&realpath, &lowerdatastat, - lowermask, flags); + err = ovl_do_getattr(&realpath, &lowerdatastat, + lowermask, flags); if (err) goto out; } else { diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index ca88b2636a57..05c3dd597fa8 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -408,6 +408,14 @@ static inline bool ovl_open_flags_need_copy_up(int flags) return ((OPEN_FMODE(flags) & FMODE_WRITE) || (flags & O_TRUNC)); } +static inline int ovl_do_getattr(const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int flags) +{ + if (flags & AT_GETATTR_NOSEC) + return vfs_getattr_nosec(path, stat, request_mask, flags); + return vfs_getattr(path, stat, request_mask, flags); +} + /* util.c */ int ovl_get_write_access(struct dentry *dentry); void ovl_put_write_access(struct dentry *dentry); diff --git a/fs/stat.c b/fs/stat.c index 24bb0209e459..f721d26ec3f7 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -133,7 +133,8 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat, idmap = mnt_idmap(path->mnt); if (inode->i_op->getattr) return inode->i_op->getattr(idmap, path, stat, - request_mask, query_flags); + request_mask, + query_flags | AT_GETATTR_NOSEC); generic_fillattr(idmap, request_mask, inode, stat); return 0; @@ -166,6 +167,9 @@ int vfs_getattr(const struct path *path, struct kstat *stat, { int retval; + if (WARN_ON_ONCE(query_flags & AT_GETATTR_NOSEC)) + return -EPERM; + retval = security_inode_getattr(path); if (retval) return retval; diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index 6c80f96049bd..282e90aeb163 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -116,5 +116,8 @@ #define AT_HANDLE_FID AT_REMOVEDIR /* file handle is needed to compare object identity and may not be usable to open_by_handle_at(2) */ +#if defined(__KERNEL__) +#define AT_GETATTR_NOSEC 0x80000000 +#endif #endif /* _UAPI_LINUX_FCNTL_H */ -- cgit From 98d2b43081972abeb5bb5a087bc3e3197531c46e Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 25 Oct 2023 16:01:59 +0200 Subject: add unique mount ID If a mount is released then its mnt_id can immediately be reused. This is bad news for user interfaces that want to uniquely identify a mount. Implementing a unique mount ID is trivial (use a 64bit counter). Unfortunately userspace assumes 32bit size and would overflow after the counter reaches 2^32. Introduce a new 64bit ID alongside the old one. Initialize the counter to 2^32, this guarantees that the old and new IDs are never mixed up. Signed-off-by: Miklos Szeredi Link: https://lore.kernel.org/r/20231025140205.3586473-2-mszeredi@redhat.com Reviewed-by: Ian Kent Signed-off-by: Christian Brauner --- fs/mount.h | 3 ++- fs/namespace.c | 4 ++++ fs/stat.c | 9 +++++++-- include/uapi/linux/stat.h | 1 + 4 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/mount.h b/fs/mount.h index 130c07c2f8d2..a14f762b3f29 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -72,7 +72,8 @@ struct mount { struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks; __u32 mnt_fsnotify_mask; #endif - int mnt_id; /* mount identifier */ + int mnt_id; /* mount identifier, reused */ + u64 mnt_id_unique; /* mount ID unique until reboot */ int mnt_group_id; /* peer group identifier */ int mnt_expiry_mark; /* true if marked for expiry */ struct hlist_head mnt_pins; diff --git a/fs/namespace.c b/fs/namespace.c index fbf0e596fcd3..0bcba81402b5 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -68,6 +68,9 @@ static u64 event; static DEFINE_IDA(mnt_id_ida); static DEFINE_IDA(mnt_group_ida); +/* Don't allow confusion with old 32bit mount ID */ +static atomic64_t mnt_id_ctr = ATOMIC64_INIT(1ULL << 32); + static struct hlist_head *mount_hashtable __ro_after_init; static struct hlist_head *mountpoint_hashtable __ro_after_init; static struct kmem_cache *mnt_cache __ro_after_init; @@ -131,6 +134,7 @@ static int mnt_alloc_id(struct mount *mnt) if (res < 0) return res; mnt->mnt_id = res; + mnt->mnt_id_unique = atomic64_inc_return(&mnt_id_ctr); return 0; } diff --git a/fs/stat.c b/fs/stat.c index 24bb0209e459..e44f0625c24f 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -243,8 +243,13 @@ retry: error = vfs_getattr(&path, stat, request_mask, flags); - stat->mnt_id = real_mount(path.mnt)->mnt_id; - stat->result_mask |= STATX_MNT_ID; + if (request_mask & STATX_MNT_ID_UNIQUE) { + stat->mnt_id = real_mount(path.mnt)->mnt_id_unique; + stat->result_mask |= STATX_MNT_ID_UNIQUE; + } else { + stat->mnt_id = real_mount(path.mnt)->mnt_id; + stat->result_mask |= STATX_MNT_ID; + } if (path.mnt->mnt_root == path.dentry) stat->attributes |= STATX_ATTR_MOUNT_ROOT; diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 7cab2c65d3d7..2f2ee82d5517 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -154,6 +154,7 @@ struct statx { #define STATX_BTIME 0x00000800U /* Want/got stx_btime */ #define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */ #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ +#define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ -- cgit From acec05fb78abb74fdab2195bfca9a6d38a732643 Mon Sep 17 00:00:00 2001 From: Kory Maincent Date: Tue, 14 Nov 2023 12:28:35 +0100 Subject: net_tstamp: Add TIMESTAMPING SOFTWARE and HARDWARE mask Timestamping software or hardware flags are often used as a group, therefore adding these masks will easier future use. I did not use SOF_TIMESTAMPING_SYS_HARDWARE flag as it is deprecated and not use at all. Signed-off-by: Kory Maincent Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/uapi/linux/net_tstamp.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index a2c66b3d7f0f..df8091998c8d 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -48,6 +48,14 @@ enum { SOF_TIMESTAMPING_TX_SCHED | \ SOF_TIMESTAMPING_TX_ACK) +#define SOF_TIMESTAMPING_SOFTWARE_MASK (SOF_TIMESTAMPING_RX_SOFTWARE | \ + SOF_TIMESTAMPING_TX_SOFTWARE | \ + SOF_TIMESTAMPING_SOFTWARE) + +#define SOF_TIMESTAMPING_HARDWARE_MASK (SOF_TIMESTAMPING_RX_HARDWARE | \ + SOF_TIMESTAMPING_TX_HARDWARE | \ + SOF_TIMESTAMPING_RAW_HARDWARE) + /** * struct so_timestamping - SO_TIMESTAMPING parameter * -- cgit From 11d55be06df0aedf19b05ab61c2d26b31a3c7e64 Mon Sep 17 00:00:00 2001 From: Kory Maincent Date: Tue, 14 Nov 2023 12:28:36 +0100 Subject: net: ethtool: Add a command to expose current time stamping layer Time stamping on network packets may happen either in the MAC or in the PHY, but not both. In preparation for making the choice selectable, expose both the current layers via ethtool. In accordance with the kernel implementation as it stands, the current layer will always read as "phy" when a PHY time stamping device is present. Future patches will allow changing the current layer administratively. Signed-off-by: Kory Maincent Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 23 ++++++++ include/uapi/linux/ethtool_netlink.h | 14 +++++ include/uapi/linux/net_tstamp.h | 10 ++++ net/ethtool/Makefile | 2 +- net/ethtool/common.h | 1 + net/ethtool/netlink.c | 10 ++++ net/ethtool/netlink.h | 2 + net/ethtool/ts.c | 88 ++++++++++++++++++++++++++++ 8 files changed, 149 insertions(+), 1 deletion(-) create mode 100644 net/ethtool/ts.c (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 2540c70952ff..644b3b764044 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -225,6 +225,7 @@ Userspace to kernel: ``ETHTOOL_MSG_RSS_GET`` get RSS settings ``ETHTOOL_MSG_MM_GET`` get MAC merge layer state ``ETHTOOL_MSG_MM_SET`` set MAC merge layer parameters + ``ETHTOOL_MSG_TS_GET`` get current timestamping ===================================== ================================= Kernel to userspace: @@ -268,6 +269,7 @@ Kernel to userspace: ``ETHTOOL_MSG_PSE_GET_REPLY`` PSE parameters ``ETHTOOL_MSG_RSS_GET_REPLY`` RSS settings ``ETHTOOL_MSG_MM_GET_REPLY`` MAC merge layer status + ``ETHTOOL_MSG_TS_GET_REPLY`` current timestamping ======================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -1994,6 +1996,26 @@ The attributes are propagated to the driver through the following structure: .. kernel-doc:: include/linux/ethtool.h :identifiers: ethtool_mm_cfg +TS_GET +====== + +Gets current timestamping. + +Request contents: + + ================================= ====== ==================== + ``ETHTOOL_A_TS_HEADER`` nested request header + ================================= ====== ==================== + +Kernel response contents: + + ======================= ====== ============================== + ``ETHTOOL_A_TS_HEADER`` nested reply header + ``ETHTOOL_A_TS_LAYER`` u32 current timestamping + ======================= ====== ============================== + +This command get the current timestamp layer. + Request translation =================== @@ -2100,4 +2122,5 @@ are netlink only. n/a ``ETHTOOL_MSG_PLCA_GET_STATUS`` n/a ``ETHTOOL_MSG_MM_GET`` n/a ``ETHTOOL_MSG_MM_SET`` + n/a ``ETHTOOL_MSG_TS_GET`` =================================== ===================================== diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 73e2c10dc2cc..cb51136328cf 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -57,6 +57,7 @@ enum { ETHTOOL_MSG_PLCA_GET_STATUS, ETHTOOL_MSG_MM_GET, ETHTOOL_MSG_MM_SET, + ETHTOOL_MSG_TS_GET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -109,6 +110,7 @@ enum { ETHTOOL_MSG_PLCA_NTF, ETHTOOL_MSG_MM_GET_REPLY, ETHTOOL_MSG_MM_NTF, + ETHTOOL_MSG_TS_GET_REPLY, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -975,6 +977,18 @@ enum { ETHTOOL_A_MM_MAX = (__ETHTOOL_A_MM_CNT - 1) }; +/* TS LAYER */ + +enum { + ETHTOOL_A_TS_UNSPEC, + ETHTOOL_A_TS_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_TS_LAYER, /* u32 */ + + /* add new constants above here */ + __ETHTOOL_A_TS_CNT, + ETHTOOL_A_TS_MAX = (__ETHTOOL_A_TS_CNT - 1) +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index df8091998c8d..4551fb3d7720 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -13,6 +13,16 @@ #include #include /* for SO_TIMESTAMPING */ +/* Layer of the TIMESTAMPING provider */ +enum timestamping_layer { + NO_TIMESTAMPING, + SOFTWARE_TIMESTAMPING, + MAC_TIMESTAMPING, + PHY_TIMESTAMPING, + + __TIMESTAMPING_COUNT, +}; + /* SO_TIMESTAMPING flags */ enum { SOF_TIMESTAMPING_TX_HARDWARE = (1<<0), diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 504f954a1b28..4ea64c080639 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -8,4 +8,4 @@ ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ tunnels.o fec.o eeprom.o stats.o phc_vclocks.o mm.o \ - module.o pse-pd.o plca.o mm.o + module.o pse-pd.o plca.o mm.o ts.o diff --git a/net/ethtool/common.h b/net/ethtool/common.h index 28b8aaaf9bcb..a264b635f7d3 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -35,6 +35,7 @@ extern const char wol_mode_names[][ETH_GSTRING_LEN]; extern const char sof_timestamping_names[][ETH_GSTRING_LEN]; extern const char ts_tx_type_names[][ETH_GSTRING_LEN]; extern const char ts_rx_filter_names[][ETH_GSTRING_LEN]; +extern const char ts_layer_names[][ETH_GSTRING_LEN]; extern const char udp_tunnel_type_names[][ETH_GSTRING_LEN]; int __ethtool_get_link(struct net_device *dev); diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 3bbd5afb7b31..561c0931d055 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -306,6 +306,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_PLCA_GET_STATUS] = ðnl_plca_status_request_ops, [ETHTOOL_MSG_MM_GET] = ðnl_mm_request_ops, [ETHTOOL_MSG_MM_SET] = ðnl_mm_request_ops, + [ETHTOOL_MSG_TS_GET] = ðnl_ts_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -1128,6 +1129,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_mm_set_policy, .maxattr = ARRAY_SIZE(ethnl_mm_set_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_TS_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + .policy = ethnl_ts_get_policy, + .maxattr = ARRAY_SIZE(ethnl_ts_get_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 9a333a8d04c1..1e6085198acc 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -395,6 +395,7 @@ extern const struct ethnl_request_ops ethnl_rss_request_ops; extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops; extern const struct ethnl_request_ops ethnl_plca_status_request_ops; extern const struct ethnl_request_ops ethnl_mm_request_ops; +extern const struct ethnl_request_ops ethnl_ts_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; @@ -441,6 +442,7 @@ extern const struct nla_policy ethnl_plca_set_cfg_policy[ETHTOOL_A_PLCA_MAX + 1] extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADER + 1]; extern const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1]; extern const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1]; +extern const struct nla_policy ethnl_ts_get_policy[ETHTOOL_A_TS_HEADER + 1]; int ethnl_set_features(struct sk_buff *skb, struct genl_info *info); int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info); diff --git a/net/ethtool/ts.c b/net/ethtool/ts.c new file mode 100644 index 000000000000..066cb06f4d0b --- /dev/null +++ b/net/ethtool/ts.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include + +#include "netlink.h" +#include "common.h" +#include "bitset.h" + +struct ts_req_info { + struct ethnl_req_info base; +}; + +struct ts_reply_data { + struct ethnl_reply_data base; + enum timestamping_layer ts_layer; +}; + +#define TS_REPDATA(__reply_base) \ + container_of(__reply_base, struct ts_reply_data, base) + +/* TS_GET */ +const struct nla_policy ethnl_ts_get_policy[] = { + [ETHTOOL_A_TS_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), +}; + +static int ts_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + const struct genl_info *info) +{ + struct ts_reply_data *data = TS_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + const struct ethtool_ops *ops = dev->ethtool_ops; + int ret; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + + if (phy_has_tsinfo(dev->phydev)) { + data->ts_layer = PHY_TIMESTAMPING; + } else if (ops->get_ts_info) { + struct ethtool_ts_info ts_info = {0}; + + ops->get_ts_info(dev, &ts_info); + if (ts_info.so_timestamping & + SOF_TIMESTAMPING_HARDWARE_MASK) + data->ts_layer = MAC_TIMESTAMPING; + + if (ts_info.so_timestamping & + SOF_TIMESTAMPING_SOFTWARE_MASK) + data->ts_layer = SOFTWARE_TIMESTAMPING; + } else { + data->ts_layer = NO_TIMESTAMPING; + } + + ethnl_ops_complete(dev); + + return ret; +} + +static int ts_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + return nla_total_size(sizeof(u32)); +} + +static int ts_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + struct ts_reply_data *data = TS_REPDATA(reply_base); + + return nla_put_u32(skb, ETHTOOL_A_TS_LAYER, data->ts_layer); +} + +const struct ethnl_request_ops ethnl_ts_request_ops = { + .request_cmd = ETHTOOL_MSG_TS_GET, + .reply_cmd = ETHTOOL_MSG_TS_GET_REPLY, + .hdr_attr = ETHTOOL_A_TS_HEADER, + .req_info_size = sizeof(struct ts_req_info), + .reply_data_size = sizeof(struct ts_reply_data), + + .prepare_data = ts_prepare_data, + .reply_size = ts_reply_size, + .fill_reply = ts_fill_reply, +}; -- cgit From d905f9c753295ee5a30af265f4b724f10050e7d3 Mon Sep 17 00:00:00 2001 From: Kory Maincent Date: Tue, 14 Nov 2023 12:28:38 +0100 Subject: net: ethtool: Add a command to list available time stamping layers Introduce a new netlink message that lists all available time stamping layers on a given interface. Signed-off-by: Kory Maincent Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 23 +++++++++ include/uapi/linux/ethtool_netlink.h | 14 ++++++ net/ethtool/netlink.c | 10 ++++ net/ethtool/netlink.h | 1 + net/ethtool/ts.c | 73 ++++++++++++++++++++++++++++ 5 files changed, 121 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 644b3b764044..b8d00676ed82 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -226,6 +226,7 @@ Userspace to kernel: ``ETHTOOL_MSG_MM_GET`` get MAC merge layer state ``ETHTOOL_MSG_MM_SET`` set MAC merge layer parameters ``ETHTOOL_MSG_TS_GET`` get current timestamping + ``ETHTOOL_MSG_TS_LIST_GET`` list available timestampings ===================================== ================================= Kernel to userspace: @@ -270,6 +271,7 @@ Kernel to userspace: ``ETHTOOL_MSG_RSS_GET_REPLY`` RSS settings ``ETHTOOL_MSG_MM_GET_REPLY`` MAC merge layer status ``ETHTOOL_MSG_TS_GET_REPLY`` current timestamping + ``ETHTOOL_MSG_TS_LIST_GET_REPLY`` available timestampings ======================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -2016,6 +2018,26 @@ Kernel response contents: This command get the current timestamp layer. +TS_LIST_GET +=========== + +Get the list of available timestampings. + +Request contents: + + ================================= ====== ==================== + ``ETHTOOL_A_TS_HEADER`` nested request header + ================================= ====== ==================== + +Kernel response contents: + + =========================== ====== ============================== + ``ETHTOOL_A_TS_HEADER`` nested reply header + ``ETHTOOL_A_TS_LIST_LAYER`` binary available timestampings + =========================== ====== ============================== + +This command lists all the possible timestamp layer available. + Request translation =================== @@ -2123,4 +2145,5 @@ are netlink only. n/a ``ETHTOOL_MSG_MM_GET`` n/a ``ETHTOOL_MSG_MM_SET`` n/a ``ETHTOOL_MSG_TS_GET`` + n/a ``ETHTOOL_MSG_TS_LIST_GET`` =================================== ===================================== diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index cb51136328cf..62b885d44d06 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -58,6 +58,7 @@ enum { ETHTOOL_MSG_MM_GET, ETHTOOL_MSG_MM_SET, ETHTOOL_MSG_TS_GET, + ETHTOOL_MSG_TS_LIST_GET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -111,6 +112,7 @@ enum { ETHTOOL_MSG_MM_GET_REPLY, ETHTOOL_MSG_MM_NTF, ETHTOOL_MSG_TS_GET_REPLY, + ETHTOOL_MSG_TS_LIST_GET_REPLY, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -989,6 +991,18 @@ enum { ETHTOOL_A_TS_MAX = (__ETHTOOL_A_TS_CNT - 1) }; +/* TS LIST LAYER */ + +enum { + ETHTOOL_A_TS_LIST_UNSPEC, + ETHTOOL_A_TS_LIST_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_TS_LIST_LAYER, /* array, u32 */ + + /* add new constants above here */ + __ETHTOOL_A_TS_LIST_CNT, + ETHTOOL_A_TS_LIST_MAX = (__ETHTOOL_A_TS_LIST_CNT - 1) +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 561c0931d055..842c9db1531f 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -307,6 +307,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_MM_GET] = ðnl_mm_request_ops, [ETHTOOL_MSG_MM_SET] = ðnl_mm_request_ops, [ETHTOOL_MSG_TS_GET] = ðnl_ts_request_ops, + [ETHTOOL_MSG_TS_LIST_GET] = ðnl_ts_list_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -1138,6 +1139,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_ts_get_policy, .maxattr = ARRAY_SIZE(ethnl_ts_get_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_TS_LIST_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + .policy = ethnl_ts_get_policy, + .maxattr = ARRAY_SIZE(ethnl_ts_get_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 1e6085198acc..ea8c312db3af 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -396,6 +396,7 @@ extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops; extern const struct ethnl_request_ops ethnl_plca_status_request_ops; extern const struct ethnl_request_ops ethnl_mm_request_ops; extern const struct ethnl_request_ops ethnl_ts_request_ops; +extern const struct ethnl_request_ops ethnl_ts_list_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; diff --git a/net/ethtool/ts.c b/net/ethtool/ts.c index 066cb06f4d0b..f2dd65a2e69c 100644 --- a/net/ethtool/ts.c +++ b/net/ethtool/ts.c @@ -86,3 +86,76 @@ const struct ethnl_request_ops ethnl_ts_request_ops = { .reply_size = ts_reply_size, .fill_reply = ts_fill_reply, }; + +/* TS_LIST_GET */ +struct ts_list_reply_data { + struct ethnl_reply_data base; + enum timestamping_layer ts_layer[__TIMESTAMPING_COUNT]; + u8 num_ts; +}; + +#define TS_LIST_REPDATA(__reply_base) \ + container_of(__reply_base, struct ts_list_reply_data, base) + +static int ts_list_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + const struct genl_info *info) +{ + struct ts_list_reply_data *data = TS_LIST_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + const struct ethtool_ops *ops = dev->ethtool_ops; + int ret, i = 0; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + + if (phy_has_tsinfo(dev->phydev)) + data->ts_layer[i++] = PHY_TIMESTAMPING; + if (ops->get_ts_info) { + struct ethtool_ts_info ts_info = {0}; + + ops->get_ts_info(dev, &ts_info); + if (ts_info.so_timestamping & + SOF_TIMESTAMPING_HARDWARE_MASK) + data->ts_layer[i++] = MAC_TIMESTAMPING; + + if (ts_info.so_timestamping & + SOF_TIMESTAMPING_SOFTWARE_MASK) + data->ts_layer[i++] = SOFTWARE_TIMESTAMPING; + } + + data->num_ts = i; + ethnl_ops_complete(dev); + + return ret; +} + +static int ts_list_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + struct ts_list_reply_data *data = TS_LIST_REPDATA(reply_base); + + return nla_total_size(sizeof(u32)) * data->num_ts; +} + +static int ts_list_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + struct ts_list_reply_data *data = TS_LIST_REPDATA(reply_base); + + return nla_put(skb, ETHTOOL_A_TS_LIST_LAYER, sizeof(u32) * data->num_ts, data->ts_layer); +} + +const struct ethnl_request_ops ethnl_ts_list_request_ops = { + .request_cmd = ETHTOOL_MSG_TS_LIST_GET, + .reply_cmd = ETHTOOL_MSG_TS_LIST_GET_REPLY, + .hdr_attr = ETHTOOL_A_TS_HEADER, + .req_info_size = sizeof(struct ts_req_info), + .reply_data_size = sizeof(struct ts_list_reply_data), + + .prepare_data = ts_list_prepare_data, + .reply_size = ts_list_reply_size, + .fill_reply = ts_list_fill_reply, +}; -- cgit From 152c75e1d00200edc4da1beb67dd099a462ea86b Mon Sep 17 00:00:00 2001 From: Kory Maincent Date: Tue, 14 Nov 2023 12:28:43 +0100 Subject: net: ethtool: ts: Let the active time stamping layer be selectable Now that the current timestamp is saved in a variable lets add the ETHTOOL_MSG_TS_SET ethtool netlink socket to make it selectable. Signed-off-by: Kory Maincent Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 17 +++++ include/uapi/linux/ethtool_netlink.h | 1 + net/ethtool/netlink.c | 8 +++ net/ethtool/netlink.h | 1 + net/ethtool/ts.c | 99 ++++++++++++++++++++++++++++ 5 files changed, 126 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index b8d00676ed82..530c1775e5f4 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -227,6 +227,7 @@ Userspace to kernel: ``ETHTOOL_MSG_MM_SET`` set MAC merge layer parameters ``ETHTOOL_MSG_TS_GET`` get current timestamping ``ETHTOOL_MSG_TS_LIST_GET`` list available timestampings + ``ETHTOOL_MSG_TS_SET`` set current timestamping ===================================== ================================= Kernel to userspace: @@ -2038,6 +2039,21 @@ Kernel response contents: This command lists all the possible timestamp layer available. +TS_SET +====== + +Modify the selected timestamping. + +Request contents: + + ======================= ====== =================== + ``ETHTOOL_A_TS_HEADER`` nested reply header + ``ETHTOOL_A_TS_LAYER`` u32 timestamping + ======================= ====== =================== + +This command set the timestamping with one that should be listed by the +TSLIST_GET command. + Request translation =================== @@ -2146,4 +2162,5 @@ are netlink only. n/a ``ETHTOOL_MSG_MM_SET`` n/a ``ETHTOOL_MSG_TS_GET`` n/a ``ETHTOOL_MSG_TS_LIST_GET`` + n/a ``ETHTOOL_MSG_TS_SET`` =================================== ===================================== diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 62b885d44d06..df6c4fcc62c1 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -59,6 +59,7 @@ enum { ETHTOOL_MSG_MM_SET, ETHTOOL_MSG_TS_GET, ETHTOOL_MSG_TS_LIST_GET, + ETHTOOL_MSG_TS_SET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 842c9db1531f..8322bf71f80d 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -308,6 +308,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_MM_SET] = ðnl_mm_request_ops, [ETHTOOL_MSG_TS_GET] = ðnl_ts_request_ops, [ETHTOOL_MSG_TS_LIST_GET] = ðnl_ts_list_request_ops, + [ETHTOOL_MSG_TS_SET] = ðnl_ts_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -1148,6 +1149,13 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_ts_get_policy, .maxattr = ARRAY_SIZE(ethnl_ts_get_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_TS_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_default_set_doit, + .policy = ethnl_ts_set_policy, + .maxattr = ARRAY_SIZE(ethnl_ts_set_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index ea8c312db3af..8fedf234b824 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -444,6 +444,7 @@ extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADE extern const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1]; extern const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1]; extern const struct nla_policy ethnl_ts_get_policy[ETHTOOL_A_TS_HEADER + 1]; +extern const struct nla_policy ethnl_ts_set_policy[ETHTOOL_A_TS_MAX + 1]; int ethnl_set_features(struct sk_buff *skb, struct genl_info *info); int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info); diff --git a/net/ethtool/ts.c b/net/ethtool/ts.c index bd219512b8de..357265e74e08 100644 --- a/net/ethtool/ts.c +++ b/net/ethtool/ts.c @@ -59,6 +59,102 @@ static int ts_fill_reply(struct sk_buff *skb, return nla_put_u32(skb, ETHTOOL_A_TS_LAYER, data->ts_layer); } +/* TS_SET */ +const struct nla_policy ethnl_ts_set_policy[] = { + [ETHTOOL_A_TS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_TS_LAYER] = NLA_POLICY_RANGE(NLA_U32, 0, + __TIMESTAMPING_COUNT - 1) +}; + +static int ethnl_set_ts_validate(struct ethnl_req_info *req_info, + struct genl_info *info) +{ + struct nlattr **tb = info->attrs; + const struct net_device_ops *ops = req_info->dev->netdev_ops; + + if (!ops->ndo_hwtstamp_set) + return -EOPNOTSUPP; + + if (!tb[ETHTOOL_A_TS_LAYER]) + return 0; + + return 1; +} + +static int ethnl_set_ts(struct ethnl_req_info *req_info, struct genl_info *info) +{ + struct net_device *dev = req_info->dev; + const struct ethtool_ops *ops = dev->ethtool_ops; + struct kernel_hwtstamp_config config = {0}; + struct nlattr **tb = info->attrs; + enum timestamping_layer ts_layer; + bool mod = false; + int ret; + + ts_layer = dev->ts_layer; + ethnl_update_u32(&ts_layer, tb[ETHTOOL_A_TS_LAYER], &mod); + + if (!mod) + return 0; + + if (ts_layer == SOFTWARE_TIMESTAMPING) { + struct ethtool_ts_info ts_info = {0}; + + if (!ops->get_ts_info) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_TS_LAYER], + "this net device cannot support timestamping"); + return -EINVAL; + } + + ops->get_ts_info(dev, &ts_info); + if ((ts_info.so_timestamping & + SOF_TIMESTAMPING_SOFTWARE_MASK) != + SOF_TIMESTAMPING_SOFTWARE_MASK) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_TS_LAYER], + "this net device cannot support software timestamping"); + return -EINVAL; + } + } else if (ts_layer == MAC_TIMESTAMPING) { + struct ethtool_ts_info ts_info = {0}; + + if (!ops->get_ts_info) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_TS_LAYER], + "this net device cannot support timestamping"); + return -EINVAL; + } + + ops->get_ts_info(dev, &ts_info); + if ((ts_info.so_timestamping & + SOF_TIMESTAMPING_HARDWARE_MASK) != + SOF_TIMESTAMPING_HARDWARE_MASK) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_TS_LAYER], + "this net device cannot support hardware timestamping"); + return -EINVAL; + } + } else if (ts_layer == PHY_TIMESTAMPING && !phy_has_tsinfo(dev->phydev)) { + NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_TS_LAYER], + "this phy device cannot support timestamping"); + return -EINVAL; + } + + /* Disable time stamping in the current layer. */ + if (netif_device_present(dev) && + (dev->ts_layer == PHY_TIMESTAMPING || + dev->ts_layer == MAC_TIMESTAMPING)) { + ret = dev_set_hwtstamp_phylib(dev, &config, info->extack); + if (ret < 0) + return ret; + } + + dev->ts_layer = ts_layer; + + return 1; +} + const struct ethnl_request_ops ethnl_ts_request_ops = { .request_cmd = ETHTOOL_MSG_TS_GET, .reply_cmd = ETHTOOL_MSG_TS_GET_REPLY, @@ -69,6 +165,9 @@ const struct ethnl_request_ops ethnl_ts_request_ops = { .prepare_data = ts_prepare_data, .reply_size = ts_reply_size, .fill_reply = ts_fill_reply, + + .set_validate = ethnl_set_ts_validate, + .set = ethnl_set_ts, }; /* TS_LIST_GET */ -- cgit From 289354f21b2c3fac93e956efd45f256a88a4d997 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sat, 18 Nov 2023 18:38:05 -0800 Subject: net: partial revert of the "Make timestamping selectable: series Revert following commits: commit acec05fb78ab ("net_tstamp: Add TIMESTAMPING SOFTWARE and HARDWARE mask") commit 11d55be06df0 ("net: ethtool: Add a command to expose current time stamping layer") commit bb8645b00ced ("netlink: specs: Introduce new netlink command to get current timestamp") commit d905f9c75329 ("net: ethtool: Add a command to list available time stamping layers") commit aed5004ee7a0 ("netlink: specs: Introduce new netlink command to list available time stamping layers") commit 51bdf3165f01 ("net: Replace hwtstamp_source by timestamping layer") commit 0f7f463d4821 ("net: Change the API of PHY default timestamp to MAC") commit 091fab122869 ("net: ethtool: ts: Update GET_TS to reply the current selected timestamp") commit 152c75e1d002 ("net: ethtool: ts: Let the active time stamping layer be selectable") commit ee60ea6be0d3 ("netlink: specs: Introduce time stamping set command") They need more time for reviews. Link: https://lore.kernel.org/all/20231118183529.6e67100c@kernel.org/ Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/ethtool.yaml | 57 ----- Documentation/networking/ethtool-netlink.rst | 63 ------ .../net/ethernet/microchip/lan966x/lan966x_main.c | 6 +- drivers/net/phy/bcm-phy-ptp.c | 3 - drivers/net/phy/dp83640.c | 3 - drivers/net/phy/micrel.c | 6 - drivers/net/phy/mscc/mscc_ptp.c | 2 - drivers/net/phy/nxp-c45-tja11xx.c | 3 - drivers/net/phy/phy_device.c | 37 ---- include/linux/net_tstamp.h | 11 +- include/linux/netdevice.h | 5 - include/linux/phy.h | 4 - include/uapi/linux/ethtool_netlink.h | 29 --- include/uapi/linux/net_tstamp.h | 18 -- net/core/dev.c | 3 - net/core/dev_ioctl.c | 36 ++- net/core/timestamping.c | 10 - net/ethtool/Makefile | 2 +- net/ethtool/common.c | 19 +- net/ethtool/common.h | 1 - net/ethtool/netlink.c | 28 --- net/ethtool/netlink.h | 4 - net/ethtool/ts.c | 244 --------------------- 23 files changed, 28 insertions(+), 566 deletions(-) delete mode 100644 net/ethtool/ts.c (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 06d9120543d3..5c7a65b009b4 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -939,26 +939,6 @@ attribute-sets: - name: burst-tmr type: u32 - - - name: ts - attributes: - - - name: header - type: nest - nested-attributes: header - - - name: ts-layer - type: u32 - - - name: ts-list - attributes: - - - name: header - type: nest - nested-attributes: header - - - name: ts-list-layer - type: binary operations: enum-model: directional @@ -1709,40 +1689,3 @@ operations: name: mm-ntf doc: Notification for change in MAC Merge configuration. notify: mm-get - - - name: ts-get - doc: Get current timestamp - - attribute-set: ts - - do: - request: - attributes: - - header - reply: - attributes: &ts - - header - - ts-layer - - - name: ts-list-get - doc: Get list of timestamp devices available on an interface - - attribute-set: ts-list - - do: - request: - attributes: - - header - reply: - attributes: - - header - - ts-list-layer - - - name: ts-set - doc: Set the timestamp device - - attribute-set: ts - - do: - request: - attributes: *ts diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 530c1775e5f4..2540c70952ff 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -225,9 +225,6 @@ Userspace to kernel: ``ETHTOOL_MSG_RSS_GET`` get RSS settings ``ETHTOOL_MSG_MM_GET`` get MAC merge layer state ``ETHTOOL_MSG_MM_SET`` set MAC merge layer parameters - ``ETHTOOL_MSG_TS_GET`` get current timestamping - ``ETHTOOL_MSG_TS_LIST_GET`` list available timestampings - ``ETHTOOL_MSG_TS_SET`` set current timestamping ===================================== ================================= Kernel to userspace: @@ -271,8 +268,6 @@ Kernel to userspace: ``ETHTOOL_MSG_PSE_GET_REPLY`` PSE parameters ``ETHTOOL_MSG_RSS_GET_REPLY`` RSS settings ``ETHTOOL_MSG_MM_GET_REPLY`` MAC merge layer status - ``ETHTOOL_MSG_TS_GET_REPLY`` current timestamping - ``ETHTOOL_MSG_TS_LIST_GET_REPLY`` available timestampings ======================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -1999,61 +1994,6 @@ The attributes are propagated to the driver through the following structure: .. kernel-doc:: include/linux/ethtool.h :identifiers: ethtool_mm_cfg -TS_GET -====== - -Gets current timestamping. - -Request contents: - - ================================= ====== ==================== - ``ETHTOOL_A_TS_HEADER`` nested request header - ================================= ====== ==================== - -Kernel response contents: - - ======================= ====== ============================== - ``ETHTOOL_A_TS_HEADER`` nested reply header - ``ETHTOOL_A_TS_LAYER`` u32 current timestamping - ======================= ====== ============================== - -This command get the current timestamp layer. - -TS_LIST_GET -=========== - -Get the list of available timestampings. - -Request contents: - - ================================= ====== ==================== - ``ETHTOOL_A_TS_HEADER`` nested request header - ================================= ====== ==================== - -Kernel response contents: - - =========================== ====== ============================== - ``ETHTOOL_A_TS_HEADER`` nested reply header - ``ETHTOOL_A_TS_LIST_LAYER`` binary available timestampings - =========================== ====== ============================== - -This command lists all the possible timestamp layer available. - -TS_SET -====== - -Modify the selected timestamping. - -Request contents: - - ======================= ====== =================== - ``ETHTOOL_A_TS_HEADER`` nested reply header - ``ETHTOOL_A_TS_LAYER`` u32 timestamping - ======================= ====== =================== - -This command set the timestamping with one that should be listed by the -TSLIST_GET command. - Request translation =================== @@ -2160,7 +2100,4 @@ are netlink only. n/a ``ETHTOOL_MSG_PLCA_GET_STATUS`` n/a ``ETHTOOL_MSG_MM_GET`` n/a ``ETHTOOL_MSG_MM_SET`` - n/a ``ETHTOOL_MSG_TS_GET`` - n/a ``ETHTOOL_MSG_TS_LIST_GET`` - n/a ``ETHTOOL_MSG_TS_SET`` =================================== ===================================== diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index fbe56b1bb386..2635ef8958c8 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -470,15 +470,15 @@ static int lan966x_port_hwtstamp_set(struct net_device *dev, struct lan966x_port *port = netdev_priv(dev); int err; - if (cfg->source != MAC_TIMESTAMPING && - cfg->source != PHY_TIMESTAMPING) + if (cfg->source != HWTSTAMP_SOURCE_NETDEV && + cfg->source != HWTSTAMP_SOURCE_PHYLIB) return -EOPNOTSUPP; err = lan966x_ptp_setup_traps(port, cfg); if (err) return err; - if (cfg->source == MAC_TIMESTAMPING) { + if (cfg->source == HWTSTAMP_SOURCE_NETDEV) { if (!port->lan966x->ptp) return -EOPNOTSUPP; diff --git a/drivers/net/phy/bcm-phy-ptp.c b/drivers/net/phy/bcm-phy-ptp.c index d3e825c951ee..617d384d4551 100644 --- a/drivers/net/phy/bcm-phy-ptp.c +++ b/drivers/net/phy/bcm-phy-ptp.c @@ -931,9 +931,6 @@ struct bcm_ptp_private *bcm_ptp_probe(struct phy_device *phydev) return ERR_CAST(clock); priv->ptp_clock = clock; - /* Timestamp selected by default to keep legacy API */ - phydev->default_timestamp = true; - priv->phydev = phydev; bcm_ptp_init(priv); diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 64fd1a109c0f..5c42c47dc564 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -1450,9 +1450,6 @@ static int dp83640_probe(struct phy_device *phydev) phydev->mii_ts = &dp83640->mii_ts; phydev->priv = dp83640; - /* Timestamp selected by default to keep legacy API */ - phydev->default_timestamp = true; - spin_lock_init(&dp83640->rx_lock); skb_queue_head_init(&dp83640->rx_queue); skb_queue_head_init(&dp83640->tx_queue); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 2b8dd0131926..bd4cd082662f 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -3158,9 +3158,6 @@ static void lan8814_ptp_init(struct phy_device *phydev) ptp_priv->mii_ts.ts_info = lan8814_ts_info; phydev->mii_ts = &ptp_priv->mii_ts; - - /* Timestamp selected by default to keep legacy API */ - phydev->default_timestamp = true; } static int lan8814_ptp_probe_once(struct phy_device *phydev) @@ -4589,9 +4586,6 @@ static int lan8841_probe(struct phy_device *phydev) phydev->mii_ts = &ptp_priv->mii_ts; - /* Timestamp selected by default to keep legacy API */ - phydev->default_timestamp = true; - return 0; } diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c index fd174eb06d4a..eb0b032cb613 100644 --- a/drivers/net/phy/mscc/mscc_ptp.c +++ b/drivers/net/phy/mscc/mscc_ptp.c @@ -1570,8 +1570,6 @@ int vsc8584_ptp_probe(struct phy_device *phydev) return PTR_ERR(vsc8531->load_save); } - /* Timestamp selected by default to keep legacy API */ - phydev->default_timestamp = true; vsc8531->ptp->phydev = phydev; return 0; diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c index 0515c7b979db..780ad353cf55 100644 --- a/drivers/net/phy/nxp-c45-tja11xx.c +++ b/drivers/net/phy/nxp-c45-tja11xx.c @@ -1658,9 +1658,6 @@ static int nxp_c45_probe(struct phy_device *phydev) priv->mii_ts.ts_info = nxp_c45_ts_info; phydev->mii_ts = &priv->mii_ts; ret = nxp_c45_init_ptp_clock(priv); - - /* Timestamp selected by default to keep legacy API */ - phydev->default_timestamp = true; } else { phydev_dbg(phydev, "PTP support not enabled even if the phy supports it"); } diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 8c4794631daa..2ce74593d6e4 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1411,26 +1411,6 @@ int phy_sfp_probe(struct phy_device *phydev, } EXPORT_SYMBOL(phy_sfp_probe); -/** - * phy_set_timestamp - set the default selected timestamping device - * @dev: Pointer to net_device - * @phydev: Pointer to phy_device - * - * This is used to set default timestamping device taking into account - * the new API choice, which is selecting the timestamping from MAC by - * default if the phydev does not have default_timestamp flag enabled. - */ -static void phy_set_timestamp(struct net_device *dev, struct phy_device *phydev) -{ - const struct ethtool_ops *ops = dev->ethtool_ops; - - if (!phy_has_tsinfo(phydev)) - return; - - if (!ops->get_ts_info || phydev->default_timestamp) - dev->ts_layer = PHY_TIMESTAMPING; -} - /** * phy_attach_direct - attach a network device to a given PHY device pointer * @dev: network device to attach @@ -1504,7 +1484,6 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, phydev->phy_link_change = phy_link_change; if (dev) { - phy_set_timestamp(dev, phydev); phydev->attached_dev = dev; dev->phydev = phydev; @@ -1833,22 +1812,6 @@ void phy_detach(struct phy_device *phydev) phy_suspend(phydev); if (dev) { - const struct ethtool_ops *ops = dev->ethtool_ops; - struct ethtool_ts_info ts_info = {0}; - - if (ops->get_ts_info) { - ops->get_ts_info(dev, &ts_info); - if ((ts_info.so_timestamping & - SOF_TIMESTAMPING_HARDWARE_MASK) == - SOF_TIMESTAMPING_HARDWARE_MASK) - dev->ts_layer = MAC_TIMESTAMPING; - else if ((ts_info.so_timestamping & - SOF_TIMESTAMPING_SOFTWARE_MASK) == - SOF_TIMESTAMPING_SOFTWARE_MASK) - dev->ts_layer = SOFTWARE_TIMESTAMPING; - } else { - dev->ts_layer = NO_TIMESTAMPING; - } phydev->attached_dev->phydev = NULL; phydev->attached_dev = NULL; } diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h index bb289c2ad376..eb01c37e71e0 100644 --- a/include/linux/net_tstamp.h +++ b/include/linux/net_tstamp.h @@ -5,6 +5,11 @@ #include +enum hwtstamp_source { + HWTSTAMP_SOURCE_NETDEV, + HWTSTAMP_SOURCE_PHYLIB, +}; + /** * struct kernel_hwtstamp_config - Kernel copy of struct hwtstamp_config * @@ -15,8 +20,8 @@ * a legacy implementation of a lower driver * @copied_to_user: request was passed to a legacy implementation which already * copied the ioctl request back to user space - * @source: indication whether timestamps should come from software, the netdev - * or from an attached phylib PHY + * @source: indication whether timestamps should come from the netdev or from + * an attached phylib PHY * * Prefer using this structure for in-kernel processing of hardware * timestamping configuration, over the inextensible struct hwtstamp_config @@ -28,7 +33,7 @@ struct kernel_hwtstamp_config { int rx_filter; struct ifreq *ifr; bool copied_to_user; - enum timestamping_layer source; + enum hwtstamp_source source; }; static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kernel_cfg, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f020d2790c12..2d840d7056f2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -47,7 +47,6 @@ #include #include #include -#include #include #include #include @@ -2075,8 +2074,6 @@ enum netdev_ml_priv_type { * * @dpll_pin: Pointer to the SyncE source pin of a DPLL subsystem, * where the clock is recovered. - * @ts_layer: Tracks which network device - * performs packet time stamping. * * FIXME: cleanup struct net_device such that network protocol info * moves out. @@ -2438,8 +2435,6 @@ struct net_device { #if IS_ENABLED(CONFIG_DPLL) struct dpll_pin *dpll_pin; #endif - - enum timestamping_layer ts_layer; }; #define to_net_dev(d) container_of(d, struct net_device, dev) diff --git a/include/linux/phy.h b/include/linux/phy.h index 317def2a7843..e5f1f41e399c 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -604,8 +604,6 @@ struct macsec_ops; * handling shall be postponed until PHY has resumed * @irq_rerun: Flag indicating interrupts occurred while PHY was suspended, * requiring a rerun of the interrupt handler after resume - * @default_timestamp: Flag indicating whether we are using the phy - * timestamp as the default one * @interface: enum phy_interface_t value * @skb: Netlink message for cable diagnostics * @nest: Netlink nest used for cable diagnostics @@ -669,8 +667,6 @@ struct phy_device { unsigned irq_suspended:1; unsigned irq_rerun:1; - unsigned default_timestamp:1; - int rate_matching; enum phy_state state; diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index df6c4fcc62c1..73e2c10dc2cc 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -57,9 +57,6 @@ enum { ETHTOOL_MSG_PLCA_GET_STATUS, ETHTOOL_MSG_MM_GET, ETHTOOL_MSG_MM_SET, - ETHTOOL_MSG_TS_GET, - ETHTOOL_MSG_TS_LIST_GET, - ETHTOOL_MSG_TS_SET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -112,8 +109,6 @@ enum { ETHTOOL_MSG_PLCA_NTF, ETHTOOL_MSG_MM_GET_REPLY, ETHTOOL_MSG_MM_NTF, - ETHTOOL_MSG_TS_GET_REPLY, - ETHTOOL_MSG_TS_LIST_GET_REPLY, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -980,30 +975,6 @@ enum { ETHTOOL_A_MM_MAX = (__ETHTOOL_A_MM_CNT - 1) }; -/* TS LAYER */ - -enum { - ETHTOOL_A_TS_UNSPEC, - ETHTOOL_A_TS_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_TS_LAYER, /* u32 */ - - /* add new constants above here */ - __ETHTOOL_A_TS_CNT, - ETHTOOL_A_TS_MAX = (__ETHTOOL_A_TS_CNT - 1) -}; - -/* TS LIST LAYER */ - -enum { - ETHTOOL_A_TS_LIST_UNSPEC, - ETHTOOL_A_TS_LIST_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_TS_LIST_LAYER, /* array, u32 */ - - /* add new constants above here */ - __ETHTOOL_A_TS_LIST_CNT, - ETHTOOL_A_TS_LIST_MAX = (__ETHTOOL_A_TS_LIST_CNT - 1) -}; - /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index 4551fb3d7720..a2c66b3d7f0f 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -13,16 +13,6 @@ #include #include /* for SO_TIMESTAMPING */ -/* Layer of the TIMESTAMPING provider */ -enum timestamping_layer { - NO_TIMESTAMPING, - SOFTWARE_TIMESTAMPING, - MAC_TIMESTAMPING, - PHY_TIMESTAMPING, - - __TIMESTAMPING_COUNT, -}; - /* SO_TIMESTAMPING flags */ enum { SOF_TIMESTAMPING_TX_HARDWARE = (1<<0), @@ -58,14 +48,6 @@ enum { SOF_TIMESTAMPING_TX_SCHED | \ SOF_TIMESTAMPING_TX_ACK) -#define SOF_TIMESTAMPING_SOFTWARE_MASK (SOF_TIMESTAMPING_RX_SOFTWARE | \ - SOF_TIMESTAMPING_TX_SOFTWARE | \ - SOF_TIMESTAMPING_SOFTWARE) - -#define SOF_TIMESTAMPING_HARDWARE_MASK (SOF_TIMESTAMPING_RX_HARDWARE | \ - SOF_TIMESTAMPING_TX_HARDWARE | \ - SOF_TIMESTAMPING_RAW_HARDWARE) - /** * struct so_timestamping - SO_TIMESTAMPING parameter * diff --git a/net/core/dev.c b/net/core/dev.c index 05ce00632892..af53f6d838ce 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10212,9 +10212,6 @@ int register_netdevice(struct net_device *dev) dev->rtnl_link_state == RTNL_LINK_INITIALIZED) rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL); - if (dev->ethtool_ops->get_ts_info) - dev->ts_layer = MAC_TIMESTAMPING; - out: return ret; diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index bc8be9749376..9a66cf5015f2 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -259,7 +259,9 @@ static int dev_eth_ioctl(struct net_device *dev, * @dev: Network device * @cfg: Timestamping configuration structure * - * Helper for calling the selected hardware provider timestamping. + * Helper for enforcing a common policy that phylib timestamping, if available, + * should take precedence in front of hardware timestamping provided by the + * netdev. * * Note: phy_mii_ioctl() only handles SIOCSHWTSTAMP (not SIOCGHWTSTAMP), and * there only exists a phydev->mii_ts->hwtstamp() method. So this will return @@ -269,14 +271,10 @@ static int dev_eth_ioctl(struct net_device *dev, static int dev_get_hwtstamp_phylib(struct net_device *dev, struct kernel_hwtstamp_config *cfg) { - enum timestamping_layer ts_layer = dev->ts_layer; - - if (ts_layer == PHY_TIMESTAMPING) + if (phy_has_hwtstamp(dev->phydev)) return phy_hwtstamp_get(dev->phydev, cfg); - else if (ts_layer == MAC_TIMESTAMPING) - return dev->netdev_ops->ndo_hwtstamp_get(dev, cfg); - return -EOPNOTSUPP; + return dev->netdev_ops->ndo_hwtstamp_get(dev, cfg); } static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr) @@ -317,8 +315,9 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr) * @cfg: Timestamping configuration structure * @extack: Netlink extended ack message structure, for error reporting * - * Helper for calling the selected hardware provider timestamping. - * If the netdev driver needs to perform specific actions even for PHY + * Helper for enforcing a common policy that phylib timestamping, if available, + * should take precedence in front of hardware timestamping provided by the + * netdev. If the netdev driver needs to perform specific actions even for PHY * timestamping to work properly (a switch port must trap the timestamped * frames and not forward them), it must set IFF_SEE_ALL_HWTSTAMP_REQUESTS in * dev->priv_flags. @@ -328,26 +327,20 @@ int dev_set_hwtstamp_phylib(struct net_device *dev, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; - enum timestamping_layer ts_layer = dev->ts_layer; + bool phy_ts = phy_has_hwtstamp(dev->phydev); struct kernel_hwtstamp_config old_cfg = {}; bool changed = false; int err; - cfg->source = ts_layer; - - if (ts_layer != PHY_TIMESTAMPING && - ts_layer != MAC_TIMESTAMPING) - return -EOPNOTSUPP; + cfg->source = phy_ts ? HWTSTAMP_SOURCE_PHYLIB : HWTSTAMP_SOURCE_NETDEV; - if (ts_layer == PHY_TIMESTAMPING && - dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS) { + if (phy_ts && (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) { err = ops->ndo_hwtstamp_get(dev, &old_cfg); if (err) return err; } - if (ts_layer == MAC_TIMESTAMPING || - dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS) { + if (!phy_ts || (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) { err = ops->ndo_hwtstamp_set(dev, cfg, extack); if (err) { if (extack->_msg) @@ -356,11 +349,10 @@ int dev_set_hwtstamp_phylib(struct net_device *dev, } } - if (ts_layer == PHY_TIMESTAMPING && - dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS) + if (phy_ts && (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) changed = kernel_hwtstamp_config_changed(&old_cfg, cfg); - if (ts_layer == PHY_TIMESTAMPING) { + if (phy_ts) { err = phy_hwtstamp_set(dev->phydev, cfg, extack); if (err) { if (changed) diff --git a/net/core/timestamping.c b/net/core/timestamping.c index 5cf51a523fb3..04840697fe79 100644 --- a/net/core/timestamping.c +++ b/net/core/timestamping.c @@ -21,7 +21,6 @@ static unsigned int classify(const struct sk_buff *skb) void skb_clone_tx_timestamp(struct sk_buff *skb) { - enum timestamping_layer ts_layer; struct mii_timestamper *mii_ts; struct sk_buff *clone; unsigned int type; @@ -29,10 +28,6 @@ void skb_clone_tx_timestamp(struct sk_buff *skb) if (!skb->sk) return; - ts_layer = skb->dev->ts_layer; - if (ts_layer != PHY_TIMESTAMPING) - return; - type = classify(skb); if (type == PTP_CLASS_NONE) return; @@ -49,17 +44,12 @@ EXPORT_SYMBOL_GPL(skb_clone_tx_timestamp); bool skb_defer_rx_timestamp(struct sk_buff *skb) { - enum timestamping_layer ts_layer; struct mii_timestamper *mii_ts; unsigned int type; if (!skb->dev || !skb->dev->phydev || !skb->dev->phydev->mii_ts) return false; - ts_layer = skb->dev->ts_layer; - if (ts_layer != PHY_TIMESTAMPING) - return false; - if (skb_headroom(skb) < ETH_HLEN) return false; diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 4ea64c080639..504f954a1b28 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -8,4 +8,4 @@ ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ tunnels.o fec.o eeprom.o stats.o phc_vclocks.o mm.o \ - module.o pse-pd.o plca.o mm.o ts.o + module.o pse-pd.o plca.o mm.o diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 9f6e3b2c74e2..11d8797f63f6 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -633,28 +633,13 @@ int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) { const struct ethtool_ops *ops = dev->ethtool_ops; struct phy_device *phydev = dev->phydev; - enum timestamping_layer ts_layer; - int ret; memset(info, 0, sizeof(*info)); info->cmd = ETHTOOL_GET_TS_INFO; - ts_layer = dev->ts_layer; - if (ts_layer == SOFTWARE_TIMESTAMPING) { - ret = ops->get_ts_info(dev, info); - if (ret) - return ret; - info->so_timestamping &= ~SOF_TIMESTAMPING_HARDWARE_MASK; - info->phc_index = -1; - info->rx_filters = 0; - info->tx_types = 0; - return 0; - } - - if (ts_layer == PHY_TIMESTAMPING) + if (phy_has_tsinfo(phydev)) return phy_ts_info(phydev, info); - - if (ts_layer == MAC_TIMESTAMPING) + if (ops->get_ts_info) return ops->get_ts_info(dev, info); info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE | diff --git a/net/ethtool/common.h b/net/ethtool/common.h index a264b635f7d3..28b8aaaf9bcb 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -35,7 +35,6 @@ extern const char wol_mode_names[][ETH_GSTRING_LEN]; extern const char sof_timestamping_names[][ETH_GSTRING_LEN]; extern const char ts_tx_type_names[][ETH_GSTRING_LEN]; extern const char ts_rx_filter_names[][ETH_GSTRING_LEN]; -extern const char ts_layer_names[][ETH_GSTRING_LEN]; extern const char udp_tunnel_type_names[][ETH_GSTRING_LEN]; int __ethtool_get_link(struct net_device *dev); diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 8322bf71f80d..3bbd5afb7b31 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -306,9 +306,6 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_PLCA_GET_STATUS] = ðnl_plca_status_request_ops, [ETHTOOL_MSG_MM_GET] = ðnl_mm_request_ops, [ETHTOOL_MSG_MM_SET] = ðnl_mm_request_ops, - [ETHTOOL_MSG_TS_GET] = ðnl_ts_request_ops, - [ETHTOOL_MSG_TS_LIST_GET] = ðnl_ts_list_request_ops, - [ETHTOOL_MSG_TS_SET] = ðnl_ts_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -1131,31 +1128,6 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_mm_set_policy, .maxattr = ARRAY_SIZE(ethnl_mm_set_policy) - 1, }, - { - .cmd = ETHTOOL_MSG_TS_GET, - .doit = ethnl_default_doit, - .start = ethnl_default_start, - .dumpit = ethnl_default_dumpit, - .done = ethnl_default_done, - .policy = ethnl_ts_get_policy, - .maxattr = ARRAY_SIZE(ethnl_ts_get_policy) - 1, - }, - { - .cmd = ETHTOOL_MSG_TS_LIST_GET, - .doit = ethnl_default_doit, - .start = ethnl_default_start, - .dumpit = ethnl_default_dumpit, - .done = ethnl_default_done, - .policy = ethnl_ts_get_policy, - .maxattr = ARRAY_SIZE(ethnl_ts_get_policy) - 1, - }, - { - .cmd = ETHTOOL_MSG_TS_SET, - .flags = GENL_UNS_ADMIN_PERM, - .doit = ethnl_default_set_doit, - .policy = ethnl_ts_set_policy, - .maxattr = ARRAY_SIZE(ethnl_ts_set_policy) - 1, - }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 8fedf234b824..9a333a8d04c1 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -395,8 +395,6 @@ extern const struct ethnl_request_ops ethnl_rss_request_ops; extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops; extern const struct ethnl_request_ops ethnl_plca_status_request_ops; extern const struct ethnl_request_ops ethnl_mm_request_ops; -extern const struct ethnl_request_ops ethnl_ts_request_ops; -extern const struct ethnl_request_ops ethnl_ts_list_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; @@ -443,8 +441,6 @@ extern const struct nla_policy ethnl_plca_set_cfg_policy[ETHTOOL_A_PLCA_MAX + 1] extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADER + 1]; extern const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1]; extern const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1]; -extern const struct nla_policy ethnl_ts_get_policy[ETHTOOL_A_TS_HEADER + 1]; -extern const struct nla_policy ethnl_ts_set_policy[ETHTOOL_A_TS_MAX + 1]; int ethnl_set_features(struct sk_buff *skb, struct genl_info *info); int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info); diff --git a/net/ethtool/ts.c b/net/ethtool/ts.c deleted file mode 100644 index 357265e74e08..000000000000 --- a/net/ethtool/ts.c +++ /dev/null @@ -1,244 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only - -#include -#include - -#include "netlink.h" -#include "common.h" -#include "bitset.h" - -struct ts_req_info { - struct ethnl_req_info base; -}; - -struct ts_reply_data { - struct ethnl_reply_data base; - enum timestamping_layer ts_layer; -}; - -#define TS_REPDATA(__reply_base) \ - container_of(__reply_base, struct ts_reply_data, base) - -/* TS_GET */ -const struct nla_policy ethnl_ts_get_policy[] = { - [ETHTOOL_A_TS_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), -}; - -static int ts_prepare_data(const struct ethnl_req_info *req_base, - struct ethnl_reply_data *reply_base, - const struct genl_info *info) -{ - struct ts_reply_data *data = TS_REPDATA(reply_base); - struct net_device *dev = reply_base->dev; - int ret; - - ret = ethnl_ops_begin(dev); - if (ret < 0) - return ret; - - data->ts_layer = dev->ts_layer; - - ethnl_ops_complete(dev); - - return ret; -} - -static int ts_reply_size(const struct ethnl_req_info *req_base, - const struct ethnl_reply_data *reply_base) -{ - return nla_total_size(sizeof(u32)); -} - -static int ts_fill_reply(struct sk_buff *skb, - const struct ethnl_req_info *req_base, - const struct ethnl_reply_data *reply_base) -{ - struct ts_reply_data *data = TS_REPDATA(reply_base); - - return nla_put_u32(skb, ETHTOOL_A_TS_LAYER, data->ts_layer); -} - -/* TS_SET */ -const struct nla_policy ethnl_ts_set_policy[] = { - [ETHTOOL_A_TS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), - [ETHTOOL_A_TS_LAYER] = NLA_POLICY_RANGE(NLA_U32, 0, - __TIMESTAMPING_COUNT - 1) -}; - -static int ethnl_set_ts_validate(struct ethnl_req_info *req_info, - struct genl_info *info) -{ - struct nlattr **tb = info->attrs; - const struct net_device_ops *ops = req_info->dev->netdev_ops; - - if (!ops->ndo_hwtstamp_set) - return -EOPNOTSUPP; - - if (!tb[ETHTOOL_A_TS_LAYER]) - return 0; - - return 1; -} - -static int ethnl_set_ts(struct ethnl_req_info *req_info, struct genl_info *info) -{ - struct net_device *dev = req_info->dev; - const struct ethtool_ops *ops = dev->ethtool_ops; - struct kernel_hwtstamp_config config = {0}; - struct nlattr **tb = info->attrs; - enum timestamping_layer ts_layer; - bool mod = false; - int ret; - - ts_layer = dev->ts_layer; - ethnl_update_u32(&ts_layer, tb[ETHTOOL_A_TS_LAYER], &mod); - - if (!mod) - return 0; - - if (ts_layer == SOFTWARE_TIMESTAMPING) { - struct ethtool_ts_info ts_info = {0}; - - if (!ops->get_ts_info) { - NL_SET_ERR_MSG_ATTR(info->extack, - tb[ETHTOOL_A_TS_LAYER], - "this net device cannot support timestamping"); - return -EINVAL; - } - - ops->get_ts_info(dev, &ts_info); - if ((ts_info.so_timestamping & - SOF_TIMESTAMPING_SOFTWARE_MASK) != - SOF_TIMESTAMPING_SOFTWARE_MASK) { - NL_SET_ERR_MSG_ATTR(info->extack, - tb[ETHTOOL_A_TS_LAYER], - "this net device cannot support software timestamping"); - return -EINVAL; - } - } else if (ts_layer == MAC_TIMESTAMPING) { - struct ethtool_ts_info ts_info = {0}; - - if (!ops->get_ts_info) { - NL_SET_ERR_MSG_ATTR(info->extack, - tb[ETHTOOL_A_TS_LAYER], - "this net device cannot support timestamping"); - return -EINVAL; - } - - ops->get_ts_info(dev, &ts_info); - if ((ts_info.so_timestamping & - SOF_TIMESTAMPING_HARDWARE_MASK) != - SOF_TIMESTAMPING_HARDWARE_MASK) { - NL_SET_ERR_MSG_ATTR(info->extack, - tb[ETHTOOL_A_TS_LAYER], - "this net device cannot support hardware timestamping"); - return -EINVAL; - } - } else if (ts_layer == PHY_TIMESTAMPING && !phy_has_tsinfo(dev->phydev)) { - NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_TS_LAYER], - "this phy device cannot support timestamping"); - return -EINVAL; - } - - /* Disable time stamping in the current layer. */ - if (netif_device_present(dev) && - (dev->ts_layer == PHY_TIMESTAMPING || - dev->ts_layer == MAC_TIMESTAMPING)) { - ret = dev_set_hwtstamp_phylib(dev, &config, info->extack); - if (ret < 0) - return ret; - } - - dev->ts_layer = ts_layer; - - return 1; -} - -const struct ethnl_request_ops ethnl_ts_request_ops = { - .request_cmd = ETHTOOL_MSG_TS_GET, - .reply_cmd = ETHTOOL_MSG_TS_GET_REPLY, - .hdr_attr = ETHTOOL_A_TS_HEADER, - .req_info_size = sizeof(struct ts_req_info), - .reply_data_size = sizeof(struct ts_reply_data), - - .prepare_data = ts_prepare_data, - .reply_size = ts_reply_size, - .fill_reply = ts_fill_reply, - - .set_validate = ethnl_set_ts_validate, - .set = ethnl_set_ts, -}; - -/* TS_LIST_GET */ -struct ts_list_reply_data { - struct ethnl_reply_data base; - enum timestamping_layer ts_layer[__TIMESTAMPING_COUNT]; - u8 num_ts; -}; - -#define TS_LIST_REPDATA(__reply_base) \ - container_of(__reply_base, struct ts_list_reply_data, base) - -static int ts_list_prepare_data(const struct ethnl_req_info *req_base, - struct ethnl_reply_data *reply_base, - const struct genl_info *info) -{ - struct ts_list_reply_data *data = TS_LIST_REPDATA(reply_base); - struct net_device *dev = reply_base->dev; - const struct ethtool_ops *ops = dev->ethtool_ops; - int ret, i = 0; - - ret = ethnl_ops_begin(dev); - if (ret < 0) - return ret; - - if (phy_has_tsinfo(dev->phydev)) - data->ts_layer[i++] = PHY_TIMESTAMPING; - if (ops->get_ts_info) { - struct ethtool_ts_info ts_info = {0}; - - ops->get_ts_info(dev, &ts_info); - if (ts_info.so_timestamping & - SOF_TIMESTAMPING_HARDWARE_MASK) - data->ts_layer[i++] = MAC_TIMESTAMPING; - - if (ts_info.so_timestamping & - SOF_TIMESTAMPING_SOFTWARE_MASK) - data->ts_layer[i++] = SOFTWARE_TIMESTAMPING; - } - - data->num_ts = i; - ethnl_ops_complete(dev); - - return ret; -} - -static int ts_list_reply_size(const struct ethnl_req_info *req_base, - const struct ethnl_reply_data *reply_base) -{ - struct ts_list_reply_data *data = TS_LIST_REPDATA(reply_base); - - return nla_total_size(sizeof(u32)) * data->num_ts; -} - -static int ts_list_fill_reply(struct sk_buff *skb, - const struct ethnl_req_info *req_base, - const struct ethnl_reply_data *reply_base) -{ - struct ts_list_reply_data *data = TS_LIST_REPDATA(reply_base); - - return nla_put(skb, ETHTOOL_A_TS_LIST_LAYER, sizeof(u32) * data->num_ts, data->ts_layer); -} - -const struct ethnl_request_ops ethnl_ts_list_request_ops = { - .request_cmd = ETHTOOL_MSG_TS_LIST_GET, - .reply_cmd = ETHTOOL_MSG_TS_LIST_GET_REPLY, - .hdr_attr = ETHTOOL_A_TS_HEADER, - .req_info_size = sizeof(struct ts_req_info), - .reply_data_size = sizeof(struct ts_list_reply_data), - - .prepare_data = ts_list_prepare_data, - .reply_size = ts_list_reply_size, - .fill_reply = ts_list_fill_reply, -}; -- cgit From d055a76c006540defd4eb80dcdea217cee0a141a Mon Sep 17 00:00:00 2001 From: Benjamin Gaignard Date: Thu, 9 Nov 2023 17:35:00 +0100 Subject: media: core: Report the maximum possible number of buffers for the queue Use one of the struct v4l2_create_buffers reserved bytes to report the maximum possible number of buffers for the queue. V4l2 framework set V4L2_BUF_CAP_SUPPORTS_MAX_NUM_BUFFERS flags in queue capabilities so userland can know when the field is valid. Does the same change in v4l2_create_buffers32 structure. Signed-off-by: Benjamin Gaignard Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst | 8 ++++++-- Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst | 1 + drivers/media/common/videobuf2/videobuf2-v4l2.c | 2 ++ drivers/media/v4l2-core/v4l2-compat-ioctl32.c | 10 +++++++++- drivers/media/v4l2-core/v4l2-ioctl.c | 4 ++-- include/uapi/linux/videodev2.h | 7 ++++++- 6 files changed, 26 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst b/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst index a048a9f6b7b6..49232c9006c2 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst @@ -116,9 +116,13 @@ than the number requested. - ``flags`` - Specifies additional buffer management attributes. See :ref:`memory-flags`. - * - __u32 - - ``reserved``\ [6] + - ``max_num_buffers`` + - If the V4L2_BUF_CAP_SUPPORTS_MAX_NUM_BUFFERS capability flag is set + this field indicates the maximum possible number of buffers + for this queue. + * - __u32 + - ``reserved``\ [5] - A place holder for future extensions. Drivers and applications must set the array to zero. diff --git a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst index 099fa6695167..0b3a41a45d05 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst @@ -120,6 +120,7 @@ aborting or finishing any DMA in progress, an implicit .. _V4L2-BUF-CAP-SUPPORTS-ORPHANED-BUFS: .. _V4L2-BUF-CAP-SUPPORTS-M2M-HOLD-CAPTURE-BUF: .. _V4L2-BUF-CAP-SUPPORTS-MMAP-CACHE-HINTS: +.. _V4L2-BUF-CAP-SUPPORTS-MAX-NUM-BUFFERS: .. raw:: latex diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c index 3d71c205406d..440c3b1c18ec 100644 --- a/drivers/media/common/videobuf2/videobuf2-v4l2.c +++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c @@ -756,6 +756,8 @@ int vb2_create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create) fill_buf_caps(q, &create->capabilities); validate_memory_flags(q, create->memory, &create->flags); create->index = vb2_get_num_buffers(q); + create->max_num_buffers = q->max_num_buffers; + create->capabilities |= V4L2_BUF_CAP_SUPPORTS_MAX_NUM_BUFFERS; if (create->count == 0) return ret != -EBUSY ? ret : 0; diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c index f3bed37859a2..8c07400bd280 100644 --- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c +++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c @@ -116,6 +116,9 @@ struct v4l2_format32 { * @flags: additional buffer management attributes (ignored unless the * queue has V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS capability and * configured for MMAP streaming I/O). + * @max_num_buffers: if V4L2_BUF_CAP_SUPPORTS_MAX_NUM_BUFFERS capability flag is set + * this field indicate the maximum possible number of buffers + * for this queue. * @reserved: future extensions */ struct v4l2_create_buffers32 { @@ -125,7 +128,8 @@ struct v4l2_create_buffers32 { struct v4l2_format32 format; __u32 capabilities; __u32 flags; - __u32 reserved[6]; + __u32 max_num_buffers; + __u32 reserved[5]; }; static int get_v4l2_format32(struct v4l2_format *p64, @@ -175,6 +179,9 @@ static int get_v4l2_create32(struct v4l2_create_buffers *p64, return -EFAULT; if (copy_from_user(&p64->flags, &p32->flags, sizeof(p32->flags))) return -EFAULT; + if (copy_from_user(&p64->max_num_buffers, &p32->max_num_buffers, + sizeof(p32->max_num_buffers))) + return -EFAULT; return get_v4l2_format32(&p64->format, &p32->format); } @@ -221,6 +228,7 @@ static int put_v4l2_create32(struct v4l2_create_buffers *p64, offsetof(struct v4l2_create_buffers32, format)) || put_user(p64->capabilities, &p32->capabilities) || put_user(p64->flags, &p32->flags) || + put_user(p64->max_num_buffers, &p32->max_num_buffers) || copy_to_user(p32->reserved, p64->reserved, sizeof(p64->reserved))) return -EFAULT; return put_v4l2_format32(&p64->format, &p32->format); diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 9b1de54ce379..4d90424cbfc4 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -483,9 +483,9 @@ static void v4l_print_create_buffers(const void *arg, bool write_only) { const struct v4l2_create_buffers *p = arg; - pr_cont("index=%d, count=%d, memory=%s, capabilities=0x%08x, ", + pr_cont("index=%d, count=%d, memory=%s, capabilities=0x%08x, max num buffers=%u", p->index, p->count, prt_names(p->memory, v4l2_memory_names), - p->capabilities); + p->capabilities, p->max_num_buffers); v4l_print_format(&p->format, write_only); } diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index c3d4e490ce7c..13ddb5abf584 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1035,6 +1035,7 @@ struct v4l2_requestbuffers { #define V4L2_BUF_CAP_SUPPORTS_ORPHANED_BUFS (1 << 4) #define V4L2_BUF_CAP_SUPPORTS_M2M_HOLD_CAPTURE_BUF (1 << 5) #define V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS (1 << 6) +#define V4L2_BUF_CAP_SUPPORTS_MAX_NUM_BUFFERS (1 << 7) /** * struct v4l2_plane - plane info for multi-planar buffers @@ -2605,6 +2606,9 @@ struct v4l2_dbg_chip_info { * @flags: additional buffer management attributes (ignored unless the * queue has V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS capability * and configured for MMAP streaming I/O). + * @max_num_buffers: if V4L2_BUF_CAP_SUPPORTS_MAX_NUM_BUFFERS capability flag is set + * this field indicate the maximum possible number of buffers + * for this queue. * @reserved: future extensions */ struct v4l2_create_buffers { @@ -2614,7 +2618,8 @@ struct v4l2_create_buffers { struct v4l2_format format; __u32 capabilities; __u32 flags; - __u32 reserved[6]; + __u32 max_num_buffers; + __u32 reserved[5]; }; /* -- cgit From 70be8a84017a4454429abc40dec40a1f845c7827 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 14 Nov 2023 11:39:44 +0100 Subject: media: videodev2.h: add missing __user to p_h264_pps The p_h264_pps pointer in struct v4l2_ext_control was missing the __user annotation. Add this. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 13ddb5abf584..c3fc710ef9a7 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1817,7 +1817,7 @@ struct v4l2_ext_control { __s64 __user *p_s64; struct v4l2_area __user *p_area; struct v4l2_ctrl_h264_sps __user *p_h264_sps; - struct v4l2_ctrl_h264_pps *p_h264_pps; + struct v4l2_ctrl_h264_pps __user *p_h264_pps; struct v4l2_ctrl_h264_scaling_matrix __user *p_h264_scaling_matrix; struct v4l2_ctrl_h264_pred_weights __user *p_h264_pred_weights; struct v4l2_ctrl_h264_slice_params __user *p_h264_slice_params; -- cgit From 26846dda3eca07cbb8dd481421ae52b31ef232d5 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 14 Nov 2023 11:50:36 +0100 Subject: media: videodev.h: add missing p_hdr10_* pointers The HDR10 standard compound controls were missing the corresponding pointers in videodev2.h. Add these and document them. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst | 8 ++++++++ include/uapi/linux/videodev2.h | 2 ++ 2 files changed, 10 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst b/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst index f9f73530a6be..4d56c0528ad7 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst @@ -295,6 +295,14 @@ still cause this situation. - ``p_av1_film_grain`` - A pointer to a struct :c:type:`v4l2_ctrl_av1_film_grain`. Valid if this control is of type ``V4L2_CTRL_TYPE_AV1_FILM_GRAIN``. + * - struct :c:type:`v4l2_ctrl_hdr10_cll_info` * + - ``p_hdr10_cll_info`` + - A pointer to a struct :c:type:`v4l2_ctrl_hdr10_cll_info`. Valid if this control is + of type ``V4L2_CTRL_TYPE_HDR10_CLL_INFO``. + * - struct :c:type:`v4l2_ctrl_hdr10_mastering_display` * + - ``p_hdr10_mastering_display`` + - A pointer to a struct :c:type:`v4l2_ctrl_hdr10_mastering_display`. Valid if this control is + of type ``V4L2_CTRL_TYPE_HDR10_MASTERING_DISPLAY``. * - void * - ``ptr`` - A pointer to a compound type which can be an N-dimensional array diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index c3fc710ef9a7..68e7ac178cc2 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1838,6 +1838,8 @@ struct v4l2_ext_control { struct v4l2_ctrl_av1_tile_group_entry __user *p_av1_tile_group_entry; struct v4l2_ctrl_av1_frame __user *p_av1_frame; struct v4l2_ctrl_av1_film_grain __user *p_av1_film_grain; + struct v4l2_ctrl_hdr10_cll_info __user *p_hdr10_cll_info; + struct v4l2_ctrl_hdr10_mastering_display __user *p_hdr10_mastering_display; void __user *ptr; }; } __attribute__ ((packed)); -- cgit From 6285ee30caa1a0fbd9537496578085c143127eee Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Mon, 13 Nov 2023 11:35:00 +0200 Subject: wifi: cfg80211: Extend support for scanning while MLO connected To extend the support of TSF accounting in scan results for MLO connections, allow to indicate in the scan request the link ID corresponding to the BSS whose TSF should be used for the TSF accounting. Signed-off-by: Ilan Peer Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20231113112844.d4490bcdefb1.I8fcd158b810adddef4963727e9153096416b30ce@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 3 +++ include/uapi/linux/nl80211.h | 8 +++++--- net/wireless/nl80211.c | 1 + 3 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index b137a33a1b68..d36ad4cedf3b 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2608,6 +2608,8 @@ struct cfg80211_scan_6ghz_params { * @n_6ghz_params: number of 6 GHz params * @scan_6ghz_params: 6 GHz params * @bssid: BSSID to scan for (most commonly, the wildcard BSSID) + * @tsf_report_link_id: for MLO, indicates the link ID of the BSS that should be + * used for TSF reporting. Can be set to -1 to indicate no preference. */ struct cfg80211_scan_request { struct cfg80211_ssid *ssids; @@ -2636,6 +2638,7 @@ struct cfg80211_scan_request { bool scan_6ghz; u32 n_6ghz_params; struct cfg80211_scan_6ghz_params *scan_6ghz_params; + s8 tsf_report_link_id; /* keep last */ struct ieee80211_channel *channels[] __counted_by(n_channels); diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index dced2c49daec..03e44823355e 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -6241,9 +6241,11 @@ enum nl80211_feature_flags { * the BSS that the interface that requested the scan is connected to * (if available). * @NL80211_EXT_FEATURE_BSS_PARENT_TSF: Per BSS, this driver reports the - * time the last beacon/probe was received. The time is the TSF of the - * BSS that the interface that requested the scan is connected to - * (if available). + * time the last beacon/probe was received. For a non MLO connection, the + * time is the TSF of the BSS that the interface that requested the scan is + * connected to (if available). For an MLO connection, the time is the TSF + * of the BSS corresponding with link ID specified in the scan request (if + * specified). * @NL80211_EXT_FEATURE_SET_SCAN_DWELL: This driver supports configuration of * channel dwell time. * @NL80211_EXT_FEATURE_BEACON_RATE_LEGACY: Driver supports beacon rate diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 569234bc2be6..12b7bd92bb86 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -9337,6 +9337,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) else eth_broadcast_addr(request->bssid); + request->tsf_report_link_id = nl80211_link_id_or_invalid(info->attrs); request->wdev = wdev; request->wiphy = &rdev->wiphy; request->scan_start = jiffies; -- cgit From 0cc3f50f42d262d6175ee2834aeb56e98934cfcc Mon Sep 17 00:00:00 2001 From: Vinayak Yadawad Date: Thu, 9 Nov 2023 12:03:44 +0530 Subject: wifi: nl80211: Documentation update for NL80211_CMD_PORT_AUTHORIZED event Drivers supporting 4-way handshake offload for AP/P2p-GO and STA/P2P-client should use this event to indicate that port has been authorized and open for regular data traffic, sending this event on completion of successful 4-way handshake. Signed-off-by: Vinayak Yadawad Link: https://lore.kernel.org/r/f746b59f41436e9df29c24688035fbc6eb91ab06.1699510229.git.vinayak.yadawad@broadcom.com [rewrite it all to not use the term 'GC' that we don't use in place of P2P-client] Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 03e44823355e..0cd1da2c2902 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1135,11 +1135,15 @@ * @NL80211_CMD_DEL_PMK: For offloaded 4-Way handshake, delete the previously * configured PMK for the authenticator address identified by * %NL80211_ATTR_MAC. - * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates an 802.1X FT roam was - * completed successfully. Drivers that support 4 way handshake offload - * should send this event after indicating 802.1X FT assocation with - * %NL80211_CMD_ROAM. If the 4 way handshake failed %NL80211_CMD_DISCONNECT - * should be indicated instead. + * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates port is authorized and + * open for regular data traffic. For STA/P2P-client, this event is sent + * with AP MAC address and for AP/P2P-GO, the event carries the STA/P2P- + * client MAC address. + * Drivers that support 4 way handshake offload should send this event for + * STA/P2P-client after successful 4-way HS or after 802.1X FT following + * NL80211_CMD_CONNECT or NL80211_CMD_ROAM. Drivers using AP/P2P-GO 4-way + * handshake offload should send this event on successful completion of + * 4-way handshake with the peer (STA/P2P-client). * @NL80211_CMD_CONTROL_PORT_FRAME: Control Port (e.g. PAE) frame TX request * and RX notification. This command is used both as a request to transmit * a control port frame and as a notification that a control port frame -- cgit From 4e86f32a13af1970d21be94f659cae56bbe487ee Mon Sep 17 00:00:00 2001 From: Dmitry Antipov Date: Mon, 20 Nov 2023 14:05:08 +0300 Subject: uapi: propagate __struct_group() attributes to the container union Recently the kernel test robot has reported an ARM-specific BUILD_BUG_ON() in an old and unmaintained wil6210 wireless driver. The problem comes from the structure packing rules of old ARM ABI ('-mabi=apcs-gnu'). For example, the following structure is packed to 18 bytes instead of 16: struct poorly_packed { unsigned int a; unsigned int b; unsigned short c; union { struct { unsigned short d; unsigned int e; } __attribute__((packed)); struct { unsigned short d; unsigned int e; } __attribute__((packed)) inner; }; } __attribute__((packed)); To fit it into 16 bytes, it's required to add packed attribute to the container union as well: struct poorly_packed { unsigned int a; unsigned int b; unsigned short c; union { struct { unsigned short d; unsigned int e; } __attribute__((packed)); struct { unsigned short d; unsigned int e; } __attribute__((packed)) inner; } __attribute__((packed)); } __attribute__((packed)); Thanks to Andrew Pinski of GCC team for sorting the things out at https://gcc.gnu.org/pipermail/gcc/2023-November/242888.html. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202311150821.cI4yciFE-lkp@intel.com Signed-off-by: Dmitry Antipov Link: https://lore.kernel.org/r/20231120110607.98956-1-dmantipov@yandex.ru Fixes: 50d7bd38c3aa ("stddef: Introduce struct_group() helper macro") Signed-off-by: Kees Cook --- include/uapi/linux/stddef.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 5c6c4269f7ef..2ec6f35cda32 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -27,7 +27,7 @@ union { \ struct { MEMBERS } ATTRS; \ struct TAG { MEMBERS } ATTRS NAME; \ - } + } ATTRS #ifdef __cplusplus /* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */ -- cgit From 950ab53b77ab829defeb22bc98d40a5e926ae018 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 26 Nov 2023 15:07:34 -0800 Subject: net: page_pool: implement GET in the netlink API Expose the very basic page pool information via netlink. Example using ynl-py for a system with 9 queues: $ ./cli.py --no-schema --spec netlink/specs/netdev.yaml \ --dump page-pool-get [{'id': 19, 'ifindex': 2, 'napi-id': 147}, {'id': 18, 'ifindex': 2, 'napi-id': 146}, {'id': 17, 'ifindex': 2, 'napi-id': 145}, {'id': 16, 'ifindex': 2, 'napi-id': 144}, {'id': 15, 'ifindex': 2, 'napi-id': 143}, {'id': 14, 'ifindex': 2, 'napi-id': 142}, {'id': 13, 'ifindex': 2, 'napi-id': 141}, {'id': 12, 'ifindex': 2, 'napi-id': 140}, {'id': 11, 'ifindex': 2, 'napi-id': 139}, {'id': 10, 'ifindex': 2, 'napi-id': 138}] Reviewed-by: Eric Dumazet Acked-by: Jesper Dangaard Brouer Signed-off-by: Jakub Kicinski Signed-off-by: Paolo Abeni --- include/uapi/linux/netdev.h | 10 ++++ net/core/netdev-genl-gen.c | 27 ++++++++++ net/core/netdev-genl-gen.h | 3 ++ net/core/page_pool_user.c | 127 ++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 167 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 2943a151d4f1..176665bcf0da 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -64,11 +64,21 @@ enum { NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1) }; +enum { + NETDEV_A_PAGE_POOL_ID = 1, + NETDEV_A_PAGE_POOL_IFINDEX, + NETDEV_A_PAGE_POOL_NAPI_ID, + + __NETDEV_A_PAGE_POOL_MAX, + NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1) +}; + enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, NETDEV_CMD_DEV_DEL_NTF, NETDEV_CMD_DEV_CHANGE_NTF, + NETDEV_CMD_PAGE_POOL_GET, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index ea9231378aa6..bfde13981c77 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -10,11 +10,24 @@ #include +/* Integer value ranges */ +static const struct netlink_range_validation netdev_a_page_pool_id_range = { + .min = 1ULL, + .max = 4294967295ULL, +}; + /* NETDEV_CMD_DEV_GET - do */ static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = { [NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), }; +/* NETDEV_CMD_PAGE_POOL_GET - do */ +#ifdef CONFIG_PAGE_POOL +static const struct nla_policy netdev_page_pool_get_nl_policy[NETDEV_A_PAGE_POOL_ID + 1] = { + [NETDEV_A_PAGE_POOL_ID] = NLA_POLICY_FULL_RANGE(NLA_UINT, &netdev_a_page_pool_id_range), +}; +#endif /* CONFIG_PAGE_POOL */ + /* Ops table for netdev */ static const struct genl_split_ops netdev_nl_ops[] = { { @@ -29,6 +42,20 @@ static const struct genl_split_ops netdev_nl_ops[] = { .dumpit = netdev_nl_dev_get_dumpit, .flags = GENL_CMD_CAP_DUMP, }, +#ifdef CONFIG_PAGE_POOL + { + .cmd = NETDEV_CMD_PAGE_POOL_GET, + .doit = netdev_nl_page_pool_get_doit, + .policy = netdev_page_pool_get_nl_policy, + .maxattr = NETDEV_A_PAGE_POOL_ID, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = NETDEV_CMD_PAGE_POOL_GET, + .dumpit = netdev_nl_page_pool_get_dumpit, + .flags = GENL_CMD_CAP_DUMP, + }, +#endif /* CONFIG_PAGE_POOL */ }; static const struct genl_multicast_group netdev_nl_mcgrps[] = { diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index 7b370c073e7d..a011d12abff4 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -13,6 +13,9 @@ int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info); +int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); enum { NETDEV_NLGRP_MGMT, diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index 2888aa8dd3e4..7eb37c31fce9 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -5,8 +5,10 @@ #include #include #include +#include #include "page_pool_priv.h" +#include "netdev-genl-gen.h" static DEFINE_XARRAY_FLAGS(page_pools, XA_FLAGS_ALLOC1); /* Protects: page_pools, netdevice->page_pools, pool->slow.netdev, pool->user. @@ -26,6 +28,131 @@ static DEFINE_MUTEX(page_pools_lock); * - user.list: unhashed, netdev: unknown */ +typedef int (*pp_nl_fill_cb)(struct sk_buff *rsp, const struct page_pool *pool, + const struct genl_info *info); + +static int +netdev_nl_page_pool_get_do(struct genl_info *info, u32 id, pp_nl_fill_cb fill) +{ + struct page_pool *pool; + struct sk_buff *rsp; + int err; + + mutex_lock(&page_pools_lock); + pool = xa_load(&page_pools, id); + if (!pool || hlist_unhashed(&pool->user.list) || + !net_eq(dev_net(pool->slow.netdev), genl_info_net(info))) { + err = -ENOENT; + goto err_unlock; + } + + rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!rsp) { + err = -ENOMEM; + goto err_unlock; + } + + err = fill(rsp, pool, info); + if (err) + goto err_free_msg; + + mutex_unlock(&page_pools_lock); + + return genlmsg_reply(rsp, info); + +err_free_msg: + nlmsg_free(rsp); +err_unlock: + mutex_unlock(&page_pools_lock); + return err; +} + +struct page_pool_dump_cb { + unsigned long ifindex; + u32 pp_id; +}; + +static int +netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb, + pp_nl_fill_cb fill) +{ + struct page_pool_dump_cb *state = (void *)cb->ctx; + const struct genl_info *info = genl_info_dump(cb); + struct net *net = sock_net(skb->sk); + struct net_device *netdev; + struct page_pool *pool; + int err = 0; + + rtnl_lock(); + mutex_lock(&page_pools_lock); + for_each_netdev_dump(net, netdev, state->ifindex) { + hlist_for_each_entry(pool, &netdev->page_pools, user.list) { + if (state->pp_id && state->pp_id < pool->user.id) + continue; + + state->pp_id = pool->user.id; + err = fill(skb, pool, info); + if (err) + break; + } + + state->pp_id = 0; + } + mutex_unlock(&page_pools_lock); + rtnl_unlock(); + + if (skb->len && err == -EMSGSIZE) + return skb->len; + return err; +} + +static int +page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, + const struct genl_info *info) +{ + void *hdr; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_ID, pool->user.id)) + goto err_cancel; + + if (pool->slow.netdev->ifindex != LOOPBACK_IFINDEX && + nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX, + pool->slow.netdev->ifindex)) + goto err_cancel; + if (pool->user.napi_id && + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, pool->user.napi_id)) + goto err_cancel; + + genlmsg_end(rsp, hdr); + + return 0; +err_cancel: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +} + +int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + u32 id; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_PAGE_POOL_ID)) + return -EINVAL; + + id = nla_get_uint(info->attrs[NETDEV_A_PAGE_POOL_ID]); + + return netdev_nl_page_pool_get_do(info, id, page_pool_nl_fill); +} + +int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return netdev_nl_page_pool_get_dump(skb, cb, page_pool_nl_fill); +} + int page_pool_list(struct page_pool *pool) { static u32 id_alloc_next; -- cgit From d2ef6aa077bdd0b3495dba5dcae6d3f19579b20b Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 26 Nov 2023 15:07:35 -0800 Subject: net: page_pool: add netlink notifications for state changes Generate netlink notifications about page pool state changes. Reviewed-by: Eric Dumazet Acked-by: Jesper Dangaard Brouer Signed-off-by: Jakub Kicinski Signed-off-by: Paolo Abeni --- Documentation/netlink/specs/netdev.yaml | 20 ++++++++++++++++++ include/uapi/linux/netdev.h | 4 ++++ net/core/netdev-genl-gen.c | 1 + net/core/netdev-genl-gen.h | 1 + net/core/page_pool_user.c | 36 +++++++++++++++++++++++++++++++++ 5 files changed, 62 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 84ca3c2ab872..82fbe81f7a49 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -166,8 +166,28 @@ operations: dump: reply: *pp-reply config-cond: page-pool + - + name: page-pool-add-ntf + doc: Notification about page pool appearing. + notify: page-pool-get + mcgrp: page-pool + config-cond: page-pool + - + name: page-pool-del-ntf + doc: Notification about page pool disappearing. + notify: page-pool-get + mcgrp: page-pool + config-cond: page-pool + - + name: page-pool-change-ntf + doc: Notification about page pool configuration being changed. + notify: page-pool-get + mcgrp: page-pool + config-cond: page-pool mcast-groups: list: - name: mgmt + - + name: page-pool diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 176665bcf0da..beb158872226 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -79,11 +79,15 @@ enum { NETDEV_CMD_DEV_DEL_NTF, NETDEV_CMD_DEV_CHANGE_NTF, NETDEV_CMD_PAGE_POOL_GET, + NETDEV_CMD_PAGE_POOL_ADD_NTF, + NETDEV_CMD_PAGE_POOL_DEL_NTF, + NETDEV_CMD_PAGE_POOL_CHANGE_NTF, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) }; #define NETDEV_MCGRP_MGMT "mgmt" +#define NETDEV_MCGRP_PAGE_POOL "page-pool" #endif /* _UAPI_LINUX_NETDEV_H */ diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index bfde13981c77..47fb5e1b6369 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -60,6 +60,7 @@ static const struct genl_split_ops netdev_nl_ops[] = { static const struct genl_multicast_group netdev_nl_mcgrps[] = { [NETDEV_NLGRP_MGMT] = { "mgmt", }, + [NETDEV_NLGRP_PAGE_POOL] = { "page-pool", }, }; struct genl_family netdev_nl_family __ro_after_init = { diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index a011d12abff4..738097847100 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -19,6 +19,7 @@ int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb, enum { NETDEV_NLGRP_MGMT, + NETDEV_NLGRP_PAGE_POOL, }; extern struct genl_family netdev_nl_family; diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index 7eb37c31fce9..1577fef880c9 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -135,6 +135,37 @@ err_cancel: return -EMSGSIZE; } +static void netdev_nl_page_pool_event(const struct page_pool *pool, u32 cmd) +{ + struct genl_info info; + struct sk_buff *ntf; + struct net *net; + + lockdep_assert_held(&page_pools_lock); + + /* 'invisible' page pools don't matter */ + if (hlist_unhashed(&pool->user.list)) + return; + net = dev_net(pool->slow.netdev); + + if (!genl_has_listeners(&netdev_nl_family, net, NETDEV_NLGRP_PAGE_POOL)) + return; + + genl_info_init_ntf(&info, &netdev_nl_family, cmd); + + ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!ntf) + return; + + if (page_pool_nl_fill(ntf, pool, &info)) { + nlmsg_free(ntf); + return; + } + + genlmsg_multicast_netns(&netdev_nl_family, net, ntf, + 0, NETDEV_NLGRP_PAGE_POOL, GFP_KERNEL); +} + int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info) { u32 id; @@ -168,6 +199,8 @@ int page_pool_list(struct page_pool *pool) hlist_add_head(&pool->user.list, &pool->slow.netdev->page_pools); pool->user.napi_id = pool->p.napi ? pool->p.napi->napi_id : 0; + + netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_ADD_NTF); } mutex_unlock(&page_pools_lock); @@ -181,6 +214,7 @@ err_unlock: void page_pool_unlist(struct page_pool *pool) { mutex_lock(&page_pools_lock); + netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_DEL_NTF); xa_erase(&page_pools, pool->user.id); hlist_del(&pool->user.list); mutex_unlock(&page_pools_lock); @@ -210,6 +244,8 @@ static void page_pool_unreg_netdev(struct net_device *netdev) last = NULL; hlist_for_each_entry(pool, &netdev->page_pools, user.list) { pool->slow.netdev = lo; + netdev_nl_page_pool_event(pool, + NETDEV_CMD_PAGE_POOL_CHANGE_NTF); last = pool; } if (last) -- cgit From 7aee8429eedd0970d8add2fb5b856bfc5f5f1fc1 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 26 Nov 2023 15:07:36 -0800 Subject: net: page_pool: report amount of memory held by page pools Advanced deployments need the ability to check memory use of various system components. It makes it possible to make informed decisions about memory allocation and to find regressions and leaks. Report memory use of page pools. Report both number of references and bytes held. Acked-by: Jesper Dangaard Brouer Signed-off-by: Jakub Kicinski Signed-off-by: Paolo Abeni --- Documentation/netlink/specs/netdev.yaml | 15 +++++++++++++++ include/uapi/linux/netdev.h | 2 ++ net/core/page_pool.c | 13 +++++++++---- net/core/page_pool_priv.h | 2 ++ net/core/page_pool_user.c | 8 ++++++++ 5 files changed, 36 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 82fbe81f7a49..b76623ff2932 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -114,6 +114,19 @@ attribute-sets: checks: min: 1 max: u32-max + - + name: inflight + type: uint + doc: | + Number of outstanding references to this page pool (allocated + but yet to be freed pages). Allocated pages may be held in + socket receive queues, driver receive ring, page pool recycling + ring, the page pool cache, etc. + - + name: inflight-mem + type: uint + doc: | + Amount of memory held by inflight pages. operations: list: @@ -163,6 +176,8 @@ operations: - id - ifindex - napi-id + - inflight + - inflight-mem dump: reply: *pp-reply config-cond: page-pool diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index beb158872226..26ae5bdd3187 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -68,6 +68,8 @@ enum { NETDEV_A_PAGE_POOL_ID = 1, NETDEV_A_PAGE_POOL_IFINDEX, NETDEV_A_PAGE_POOL_NAPI_ID, + NETDEV_A_PAGE_POOL_INFLIGHT, + NETDEV_A_PAGE_POOL_INFLIGHT_MEM, __NETDEV_A_PAGE_POOL_MAX, NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index a8d96ea38d18..566390759294 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -529,7 +529,7 @@ EXPORT_SYMBOL(page_pool_alloc_pages); */ #define _distance(a, b) (s32)((a) - (b)) -static s32 page_pool_inflight(struct page_pool *pool) +s32 page_pool_inflight(const struct page_pool *pool, bool strict) { u32 release_cnt = atomic_read(&pool->pages_state_release_cnt); u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt); @@ -537,8 +537,13 @@ static s32 page_pool_inflight(struct page_pool *pool) inflight = _distance(hold_cnt, release_cnt); - trace_page_pool_release(pool, inflight, hold_cnt, release_cnt); - WARN(inflight < 0, "Negative(%d) inflight packet-pages", inflight); + if (strict) { + trace_page_pool_release(pool, inflight, hold_cnt, release_cnt); + WARN(inflight < 0, "Negative(%d) inflight packet-pages", + inflight); + } else { + inflight = max(0, inflight); + } return inflight; } @@ -881,7 +886,7 @@ static int page_pool_release(struct page_pool *pool) int inflight; page_pool_scrub(pool); - inflight = page_pool_inflight(pool); + inflight = page_pool_inflight(pool, true); if (!inflight) __page_pool_destroy(pool); diff --git a/net/core/page_pool_priv.h b/net/core/page_pool_priv.h index c17ea092b4ab..72fb21ea1ddc 100644 --- a/net/core/page_pool_priv.h +++ b/net/core/page_pool_priv.h @@ -3,6 +3,8 @@ #ifndef __PAGE_POOL_PRIV_H #define __PAGE_POOL_PRIV_H +s32 page_pool_inflight(const struct page_pool *pool, bool strict); + int page_pool_list(struct page_pool *pool); void page_pool_unlist(struct page_pool *pool); diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index 1577fef880c9..2db71e718485 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -110,6 +110,7 @@ static int page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, const struct genl_info *info) { + size_t inflight, refsz; void *hdr; hdr = genlmsg_iput(rsp, info); @@ -127,6 +128,13 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, pool->user.napi_id)) goto err_cancel; + inflight = page_pool_inflight(pool, false); + refsz = PAGE_SIZE << pool->p.order; + if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT, inflight) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT_MEM, + inflight * refsz)) + goto err_cancel; + genlmsg_end(rsp, hdr); return 0; -- cgit From 69cb4952b6f6a226c1c0a7ca400398aaa8f75cf2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 26 Nov 2023 15:07:37 -0800 Subject: net: page_pool: report when page pool was destroyed Report when page pool was destroyed. Together with the inflight / memory use reporting this can serve as a replacement for the warning about leaked page pools we currently print to dmesg. Example output for a fake leaked page pool using some hacks in netdevsim (one "live" pool, and one "leaked" on the same dev): $ ./cli.py --no-schema --spec netlink/specs/netdev.yaml \ --dump page-pool-get [{'id': 2, 'ifindex': 3}, {'id': 1, 'ifindex': 3, 'destroyed': 133, 'inflight': 1}] Tested-by: Dragos Tatulea Reviewed-by: Eric Dumazet Acked-by: Jesper Dangaard Brouer Signed-off-by: Jakub Kicinski Signed-off-by: Paolo Abeni --- Documentation/netlink/specs/netdev.yaml | 13 +++++++++++++ include/net/page_pool/types.h | 1 + include/uapi/linux/netdev.h | 1 + net/core/page_pool.c | 1 + net/core/page_pool_priv.h | 1 + net/core/page_pool_user.c | 12 ++++++++++++ 6 files changed, 29 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index b76623ff2932..b5f715cf9e06 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -127,6 +127,18 @@ attribute-sets: type: uint doc: | Amount of memory held by inflight pages. + - + name: detach-time + type: uint + doc: | + Seconds in CLOCK_BOOTTIME of when Page Pool was detached by + the driver. Once detached Page Pool can no longer be used to + allocate memory. + Page Pools wait for all the memory allocated from them to be freed + before truly disappearing. "Detached" Page Pools cannot be + "re-attached", they are just waiting to disappear. + Attribute is absent if Page Pool has not been detached, and + can still be used to allocate new memory. operations: list: @@ -178,6 +190,7 @@ operations: - napi-id - inflight - inflight-mem + - detach-time dump: reply: *pp-reply config-cond: page-pool diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 7e47d7bb2c1e..ac286ea8ce2d 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -193,6 +193,7 @@ struct page_pool { /* User-facing fields, protected by page_pools_lock */ struct { struct hlist_node list; + u64 detach_time; u32 napi_id; u32 id; } user; diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 26ae5bdd3187..756410274120 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -70,6 +70,7 @@ enum { NETDEV_A_PAGE_POOL_NAPI_ID, NETDEV_A_PAGE_POOL_INFLIGHT, NETDEV_A_PAGE_POOL_INFLIGHT_MEM, + NETDEV_A_PAGE_POOL_DETACH_TIME, __NETDEV_A_PAGE_POOL_MAX, NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 566390759294..a821fb5fe054 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -953,6 +953,7 @@ void page_pool_destroy(struct page_pool *pool) if (!page_pool_release(pool)) return; + page_pool_detached(pool); pool->defer_start = jiffies; pool->defer_warn = jiffies + DEFER_WARN_INTERVAL; diff --git a/net/core/page_pool_priv.h b/net/core/page_pool_priv.h index 72fb21ea1ddc..90665d40f1eb 100644 --- a/net/core/page_pool_priv.h +++ b/net/core/page_pool_priv.h @@ -6,6 +6,7 @@ s32 page_pool_inflight(const struct page_pool *pool, bool strict); int page_pool_list(struct page_pool *pool); +void page_pool_detached(struct page_pool *pool); void page_pool_unlist(struct page_pool *pool); #endif diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index 2db71e718485..bd5ca94f683f 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -134,6 +134,10 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT_MEM, inflight * refsz)) goto err_cancel; + if (pool->user.detach_time && + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_DETACH_TIME, + pool->user.detach_time)) + goto err_cancel; genlmsg_end(rsp, hdr); @@ -219,6 +223,14 @@ err_unlock: return err; } +void page_pool_detached(struct page_pool *pool) +{ + mutex_lock(&page_pools_lock); + pool->user.detach_time = ktime_get_boottime_seconds(); + netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_CHANGE_NTF); + mutex_unlock(&page_pools_lock); +} + void page_pool_unlist(struct page_pool *pool) { mutex_lock(&page_pools_lock); -- cgit From d49010adae737638447369a4eff8f1aab736b076 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 26 Nov 2023 15:07:38 -0800 Subject: net: page_pool: expose page pool stats via netlink Dump the stats into netlink. More clever approaches like dumping the stats per-CPU for each CPU individually to see where the packets get consumed can be implemented in the future. A trimmed example from a real (but recently booted system): $ ./cli.py --no-schema --spec netlink/specs/netdev.yaml \ --dump page-pool-stats-get [{'info': {'id': 19, 'ifindex': 2}, 'alloc-empty': 48, 'alloc-fast': 3024, 'alloc-refill': 0, 'alloc-slow': 48, 'alloc-slow-high-order': 0, 'alloc-waive': 0, 'recycle-cache-full': 0, 'recycle-cached': 0, 'recycle-released-refcnt': 0, 'recycle-ring': 0, 'recycle-ring-full': 0}, {'info': {'id': 18, 'ifindex': 2}, 'alloc-empty': 66, 'alloc-fast': 11811, 'alloc-refill': 35, 'alloc-slow': 66, 'alloc-slow-high-order': 0, 'alloc-waive': 0, 'recycle-cache-full': 1145, 'recycle-cached': 6541, 'recycle-released-refcnt': 0, 'recycle-ring': 1275, 'recycle-ring-full': 0}, {'info': {'id': 17, 'ifindex': 2}, 'alloc-empty': 73, 'alloc-fast': 62099, 'alloc-refill': 413, ... Acked-by: Jesper Dangaard Brouer Signed-off-by: Jakub Kicinski Signed-off-by: Paolo Abeni --- Documentation/netlink/specs/netdev.yaml | 78 ++++++++++++++++++++++++ Documentation/networking/page_pool.rst | 10 +++- include/net/page_pool/helpers.h | 8 +-- include/uapi/linux/netdev.h | 19 ++++++ net/core/netdev-genl-gen.c | 32 ++++++++++ net/core/netdev-genl-gen.h | 7 +++ net/core/page_pool.c | 2 +- net/core/page_pool_user.c | 103 ++++++++++++++++++++++++++++++++ 8 files changed, 250 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index b5f715cf9e06..20f75b7d3240 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -139,6 +139,59 @@ attribute-sets: "re-attached", they are just waiting to disappear. Attribute is absent if Page Pool has not been detached, and can still be used to allocate new memory. + - + name: page-pool-info + subset-of: page-pool + attributes: + - + name: id + - + name: ifindex + - + name: page-pool-stats + doc: | + Page pool statistics, see docs for struct page_pool_stats + for information about individual statistics. + attributes: + - + name: info + doc: Page pool identifying information. + type: nest + nested-attributes: page-pool-info + - + name: alloc-fast + type: uint + value: 8 # reserve some attr ids in case we need more metadata later + - + name: alloc-slow + type: uint + - + name: alloc-slow-high-order + type: uint + - + name: alloc-empty + type: uint + - + name: alloc-refill + type: uint + - + name: alloc-waive + type: uint + - + name: recycle-cached + type: uint + - + name: recycle-cache-full + type: uint + - + name: recycle-ring + type: uint + - + name: recycle-ring-full + type: uint + - + name: recycle-released-refcnt + type: uint operations: list: @@ -212,6 +265,31 @@ operations: notify: page-pool-get mcgrp: page-pool config-cond: page-pool + - + name: page-pool-stats-get + doc: Get page pool statistics. + attribute-set: page-pool-stats + do: + request: + attributes: + - info + reply: &pp-stats-reply + attributes: + - info + - alloc-fast + - alloc-slow + - alloc-slow-high-order + - alloc-empty + - alloc-refill + - alloc-waive + - recycle-cached + - recycle-cache-full + - recycle-ring + - recycle-ring-full + - recycle-released-refcnt + dump: + reply: *pp-stats-reply + config-cond: page-pool-stats mcast-groups: list: diff --git a/Documentation/networking/page_pool.rst b/Documentation/networking/page_pool.rst index 60993cb56b32..9d958128a57c 100644 --- a/Documentation/networking/page_pool.rst +++ b/Documentation/networking/page_pool.rst @@ -41,6 +41,11 @@ Architecture overview | Fast cache | | ptr-ring cache | +-----------------+ +------------------+ +Monitoring +========== +Information about page pools on the system can be accessed via the netdev +genetlink family (see Documentation/netlink/specs/netdev.yaml). + API interface ============= The number of pools created **must** match the number of hardware queues @@ -107,8 +112,9 @@ page_pool_get_stats() and structures described below are available. It takes a pointer to a ``struct page_pool`` and a pointer to a struct page_pool_stats allocated by the caller. -The API will fill in the provided struct page_pool_stats with -statistics about the page_pool. +Older drivers expose page pool statistics via ethtool or debugfs. +The same statistics are accessible via the netlink netdev family +in a driver-independent fashion. .. kernel-doc:: include/net/page_pool/types.h :identifiers: struct page_pool_recycle_stats diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 4ebd544ae977..7dc65774cde5 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -55,16 +55,12 @@ #include #ifdef CONFIG_PAGE_POOL_STATS +/* Deprecated driver-facing API, use netlink instead */ int page_pool_ethtool_stats_get_count(void); u8 *page_pool_ethtool_stats_get_strings(u8 *data); u64 *page_pool_ethtool_stats_get(u64 *data, void *stats); -/* - * Drivers that wish to harvest page pool stats and report them to users - * (perhaps via ethtool, debugfs, or another mechanism) can allocate a - * struct page_pool_stats call page_pool_get_stats to get stats for the specified pool. - */ -bool page_pool_get_stats(struct page_pool *pool, +bool page_pool_get_stats(const struct page_pool *pool, struct page_pool_stats *stats); #else static inline int page_pool_ethtool_stats_get_count(void) diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 756410274120..2b37233e00c0 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -76,6 +76,24 @@ enum { NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1) }; +enum { + NETDEV_A_PAGE_POOL_STATS_INFO = 1, + NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST = 8, + NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW, + NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER, + NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY, + NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL, + NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE, + NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED, + NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL, + NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING, + NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL, + NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT, + + __NETDEV_A_PAGE_POOL_STATS_MAX, + NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1) +}; + enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, @@ -85,6 +103,7 @@ enum { NETDEV_CMD_PAGE_POOL_ADD_NTF, NETDEV_CMD_PAGE_POOL_DEL_NTF, NETDEV_CMD_PAGE_POOL_CHANGE_NTF, + NETDEV_CMD_PAGE_POOL_STATS_GET, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index 47fb5e1b6369..dccd8c3a141e 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -16,6 +16,17 @@ static const struct netlink_range_validation netdev_a_page_pool_id_range = { .max = 4294967295ULL, }; +static const struct netlink_range_validation netdev_a_page_pool_ifindex_range = { + .min = 1ULL, + .max = 2147483647ULL, +}; + +/* Common nested types */ +const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1] = { + [NETDEV_A_PAGE_POOL_ID] = NLA_POLICY_FULL_RANGE(NLA_UINT, &netdev_a_page_pool_id_range), + [NETDEV_A_PAGE_POOL_IFINDEX] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_page_pool_ifindex_range), +}; + /* NETDEV_CMD_DEV_GET - do */ static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = { [NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), @@ -28,6 +39,13 @@ static const struct nla_policy netdev_page_pool_get_nl_policy[NETDEV_A_PAGE_POOL }; #endif /* CONFIG_PAGE_POOL */ +/* NETDEV_CMD_PAGE_POOL_STATS_GET - do */ +#ifdef CONFIG_PAGE_POOL_STATS +static const struct nla_policy netdev_page_pool_stats_get_nl_policy[NETDEV_A_PAGE_POOL_STATS_INFO + 1] = { + [NETDEV_A_PAGE_POOL_STATS_INFO] = NLA_POLICY_NESTED(netdev_page_pool_info_nl_policy), +}; +#endif /* CONFIG_PAGE_POOL_STATS */ + /* Ops table for netdev */ static const struct genl_split_ops netdev_nl_ops[] = { { @@ -56,6 +74,20 @@ static const struct genl_split_ops netdev_nl_ops[] = { .flags = GENL_CMD_CAP_DUMP, }, #endif /* CONFIG_PAGE_POOL */ +#ifdef CONFIG_PAGE_POOL_STATS + { + .cmd = NETDEV_CMD_PAGE_POOL_STATS_GET, + .doit = netdev_nl_page_pool_stats_get_doit, + .policy = netdev_page_pool_stats_get_nl_policy, + .maxattr = NETDEV_A_PAGE_POOL_STATS_INFO, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = NETDEV_CMD_PAGE_POOL_STATS_GET, + .dumpit = netdev_nl_page_pool_stats_get_dumpit, + .flags = GENL_CMD_CAP_DUMP, + }, +#endif /* CONFIG_PAGE_POOL_STATS */ }; static const struct genl_multicast_group netdev_nl_mcgrps[] = { diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index 738097847100..649e4b46eccf 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -11,11 +11,18 @@ #include +/* Common nested types */ +extern const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1]; + int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int netdev_nl_page_pool_stats_get_doit(struct sk_buff *skb, + struct genl_info *info); +int netdev_nl_page_pool_stats_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); enum { NETDEV_NLGRP_MGMT, diff --git a/net/core/page_pool.c b/net/core/page_pool.c index a821fb5fe054..3d0938a60646 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -71,7 +71,7 @@ static const char pp_stats[][ETH_GSTRING_LEN] = { * is passed to this API which is filled in. The caller can then report * those stats to the user (perhaps via ethtool, debugfs, etc.). */ -bool page_pool_get_stats(struct page_pool *pool, +bool page_pool_get_stats(const struct page_pool *pool, struct page_pool_stats *stats) { int cpu = 0; diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index bd5ca94f683f..1426434a7e15 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include "page_pool_priv.h" @@ -106,6 +107,108 @@ netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb, return err; } +static int +page_pool_nl_stats_fill(struct sk_buff *rsp, const struct page_pool *pool, + const struct genl_info *info) +{ +#ifdef CONFIG_PAGE_POOL_STATS + struct page_pool_stats stats = {}; + struct nlattr *nest; + void *hdr; + + if (!page_pool_get_stats(pool, &stats)) + return 0; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + + nest = nla_nest_start(rsp, NETDEV_A_PAGE_POOL_STATS_INFO); + + if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_ID, pool->user.id) || + (pool->slow.netdev->ifindex != LOOPBACK_IFINDEX && + nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX, + pool->slow.netdev->ifindex))) + goto err_cancel_nest; + + nla_nest_end(rsp, nest); + + if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST, + stats.alloc_stats.fast) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW, + stats.alloc_stats.slow) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER, + stats.alloc_stats.slow_high_order) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY, + stats.alloc_stats.empty) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL, + stats.alloc_stats.refill) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE, + stats.alloc_stats.waive) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED, + stats.recycle_stats.cached) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL, + stats.recycle_stats.cache_full) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING, + stats.recycle_stats.ring) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL, + stats.recycle_stats.ring_full) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT, + stats.recycle_stats.released_refcnt)) + goto err_cancel_msg; + + genlmsg_end(rsp, hdr); + + return 0; +err_cancel_nest: + nla_nest_cancel(rsp, nest); +err_cancel_msg: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +#else + GENL_SET_ERR_MSG(info, "kernel built without CONFIG_PAGE_POOL_STATS"); + return -EOPNOTSUPP; +#endif +} + +int netdev_nl_page_pool_stats_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct nlattr *tb[ARRAY_SIZE(netdev_page_pool_info_nl_policy)]; + struct nlattr *nest; + int err; + u32 id; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_PAGE_POOL_STATS_INFO)) + return -EINVAL; + + nest = info->attrs[NETDEV_A_PAGE_POOL_STATS_INFO]; + err = nla_parse_nested(tb, ARRAY_SIZE(tb) - 1, nest, + netdev_page_pool_info_nl_policy, + info->extack); + if (err) + return err; + + if (NL_REQ_ATTR_CHECK(info->extack, nest, tb, NETDEV_A_PAGE_POOL_ID)) + return -EINVAL; + if (tb[NETDEV_A_PAGE_POOL_IFINDEX]) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[NETDEV_A_PAGE_POOL_IFINDEX], + "selecting by ifindex not supported"); + return -EINVAL; + } + + id = nla_get_uint(tb[NETDEV_A_PAGE_POOL_ID]); + + return netdev_nl_page_pool_get_do(info, id, page_pool_nl_stats_fill); +} + +int netdev_nl_page_pool_stats_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return netdev_nl_page_pool_get_dump(skb, cb, page_pool_nl_stats_fill); +} + static int page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, const struct genl_info *info) -- cgit From b9873755a6c8ccfce79094c4dce9efa3ecb1a749 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Wed, 11 Oct 2023 21:35:22 +0000 Subject: misc: Add Nitro Secure Module driver When running Linux inside a Nitro Enclave, the hypervisor provides a special virtio device called "Nitro Security Module" (NSM). This device has 3 main functions: 1) Provide attestation reports 2) Modify PCR state 3) Provide entropy This patch adds a driver for NSM that exposes a /dev/nsm device node which user space can issue an ioctl on this device with raw NSM CBOR formatted commands to request attestation documents, influence PCR states, read entropy and enumerate status of the device. In addition, the driver implements a hwrng backend. Originally-by: Petre Eftime Signed-off-by: Alexander Graf Reviewed-by: Arnd Bergmann Link: https://lore.kernel.org/r/20231011213522.51781-1-graf@amazon.com Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 9 + drivers/misc/Kconfig | 13 ++ drivers/misc/Makefile | 1 + drivers/misc/nsm.c | 506 +++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/nsm.h | 31 +++ 5 files changed, 560 insertions(+) create mode 100644 drivers/misc/nsm.c create mode 100644 include/uapi/linux/nsm.h (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 012df8ccf34e..b9bbbd82742a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15291,6 +15291,15 @@ F: include/linux/nitro_enclaves.h F: include/uapi/linux/nitro_enclaves.h F: samples/nitro_enclaves/ +NITRO SECURE MODULE (NSM) +M: Alexander Graf +L: linux-kernel@vger.kernel.org +L: The AWS Nitro Enclaves Team +S: Supported +W: https://aws.amazon.com/ec2/nitro/nitro-enclaves/ +F: drivers/misc/nsm.c +F: include/uapi/linux/nsm.h + NOHZ, DYNTICKS SUPPORT M: Frederic Weisbecker M: Thomas Gleixner diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index f37c4b8380ae..8932b6cf9595 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -562,6 +562,19 @@ config TPS6594_PFSM This driver can also be built as a module. If so, the module will be called tps6594-pfsm. +config NSM + tristate "Nitro (Enclaves) Security Module support" + depends on VIRTIO + select HW_RANDOM + select CBOR + help + This driver provides support for the Nitro Security Module + in AWS EC2 Nitro based Enclaves. The driver exposes a /dev/nsm + device user space can use to communicate with the hypervisor. + + To compile this driver as a module, choose M here. + The module will be called nsm. + source "drivers/misc/c2port/Kconfig" source "drivers/misc/eeprom/Kconfig" source "drivers/misc/cb710/Kconfig" diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index f2a4d1ff65d4..ea6ea5bbbc9c 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -67,3 +67,4 @@ obj-$(CONFIG_TMR_MANAGER) += xilinx_tmr_manager.o obj-$(CONFIG_TMR_INJECT) += xilinx_tmr_inject.o obj-$(CONFIG_TPS6594_ESM) += tps6594-esm.o obj-$(CONFIG_TPS6594_PFSM) += tps6594-pfsm.o +obj-$(CONFIG_NSM) += nsm.o diff --git a/drivers/misc/nsm.c b/drivers/misc/nsm.c new file mode 100644 index 000000000000..0eaa3b4484bd --- /dev/null +++ b/drivers/misc/nsm.c @@ -0,0 +1,506 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Amazon Nitro Secure Module driver. + * + * Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved. + * + * The Nitro Secure Module implements commands via CBOR over virtio. + * This driver exposes a raw message ioctls on /dev/nsm that user + * space can use to issue these commands. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* Timeout for NSM virtqueue respose in milliseconds. */ +#define NSM_DEFAULT_TIMEOUT_MSECS (120000) /* 2 minutes */ + +/* Maximum length input data */ +struct nsm_data_req { + u32 len; + u8 data[NSM_REQUEST_MAX_SIZE]; +}; + +/* Maximum length output data */ +struct nsm_data_resp { + u32 len; + u8 data[NSM_RESPONSE_MAX_SIZE]; +}; + +/* Full NSM request/response message */ +struct nsm_msg { + struct nsm_data_req req; + struct nsm_data_resp resp; +}; + +struct nsm { + struct virtio_device *vdev; + struct virtqueue *vq; + struct mutex lock; + struct completion cmd_done; + struct miscdevice misc; + struct hwrng hwrng; + struct work_struct misc_init; + struct nsm_msg msg; +}; + +/* NSM device ID */ +static const struct virtio_device_id id_table[] = { + { VIRTIO_ID_NITRO_SEC_MOD, VIRTIO_DEV_ANY_ID }, + { 0 }, +}; + +static struct nsm *file_to_nsm(struct file *file) +{ + return container_of(file->private_data, struct nsm, misc); +} + +static struct nsm *hwrng_to_nsm(struct hwrng *rng) +{ + return container_of(rng, struct nsm, hwrng); +} + +#define CBOR_TYPE_MASK 0xE0 +#define CBOR_TYPE_MAP 0xA0 +#define CBOR_TYPE_TEXT 0x60 +#define CBOR_TYPE_ARRAY 0x40 +#define CBOR_HEADER_SIZE_SHORT 1 + +#define CBOR_SHORT_SIZE_MAX_VALUE 23 +#define CBOR_LONG_SIZE_U8 24 +#define CBOR_LONG_SIZE_U16 25 +#define CBOR_LONG_SIZE_U32 26 +#define CBOR_LONG_SIZE_U64 27 + +static bool cbor_object_is_array(const u8 *cbor_object, size_t cbor_object_size) +{ + if (cbor_object_size == 0 || cbor_object == NULL) + return false; + + return (cbor_object[0] & CBOR_TYPE_MASK) == CBOR_TYPE_ARRAY; +} + +static int cbor_object_get_array(u8 *cbor_object, size_t cbor_object_size, u8 **cbor_array) +{ + u8 cbor_short_size; + void *array_len_p; + u64 array_len; + u64 array_offset; + + if (!cbor_object_is_array(cbor_object, cbor_object_size)) + return -EFAULT; + + cbor_short_size = (cbor_object[0] & 0x1F); + + /* Decoding byte array length */ + array_offset = CBOR_HEADER_SIZE_SHORT; + if (cbor_short_size >= CBOR_LONG_SIZE_U8) + array_offset += BIT(cbor_short_size - CBOR_LONG_SIZE_U8); + + if (cbor_object_size < array_offset) + return -EFAULT; + + array_len_p = &cbor_object[1]; + + switch (cbor_short_size) { + case CBOR_SHORT_SIZE_MAX_VALUE: /* short encoding */ + array_len = cbor_short_size; + break; + case CBOR_LONG_SIZE_U8: + array_len = *(u8 *)array_len_p; + break; + case CBOR_LONG_SIZE_U16: + array_len = be16_to_cpup((__be16 *)array_len_p); + break; + case CBOR_LONG_SIZE_U32: + array_len = be32_to_cpup((__be32 *)array_len_p); + break; + case CBOR_LONG_SIZE_U64: + array_len = be64_to_cpup((__be64 *)array_len_p); + break; + } + + if (cbor_object_size < array_offset) + return -EFAULT; + + if (cbor_object_size - array_offset < array_len) + return -EFAULT; + + if (array_len > INT_MAX) + return -EFAULT; + + *cbor_array = cbor_object + array_offset; + return array_len; +} + +/* Copy the request of a raw message to kernel space */ +static int fill_req_raw(struct nsm *nsm, struct nsm_data_req *req, + struct nsm_raw *raw) +{ + /* Verify the user input size. */ + if (raw->request.len > sizeof(req->data)) + return -EMSGSIZE; + + /* Copy the request payload */ + if (copy_from_user(req->data, u64_to_user_ptr(raw->request.addr), + raw->request.len)) + return -EFAULT; + + req->len = raw->request.len; + + return 0; +} + +/* Copy the response of a raw message back to user-space */ +static int parse_resp_raw(struct nsm *nsm, struct nsm_data_resp *resp, + struct nsm_raw *raw) +{ + /* Truncate any message that does not fit. */ + raw->response.len = min_t(u64, raw->response.len, resp->len); + + /* Copy the response content to user space */ + if (copy_to_user(u64_to_user_ptr(raw->response.addr), + resp->data, raw->response.len)) + return -EFAULT; + + return 0; +} + +/* Virtqueue interrupt handler */ +static void nsm_vq_callback(struct virtqueue *vq) +{ + struct nsm *nsm = vq->vdev->priv; + + complete(&nsm->cmd_done); +} + +/* Forward a message to the NSM device and wait for the response from it */ +static int nsm_sendrecv_msg_locked(struct nsm *nsm) +{ + struct device *dev = &nsm->vdev->dev; + struct scatterlist sg_in, sg_out; + struct nsm_msg *msg = &nsm->msg; + struct virtqueue *vq = nsm->vq; + unsigned int len; + void *queue_buf; + bool kicked; + int rc; + + /* Initialize scatter-gather lists with request and response buffers. */ + sg_init_one(&sg_out, msg->req.data, msg->req.len); + sg_init_one(&sg_in, msg->resp.data, sizeof(msg->resp.data)); + + init_completion(&nsm->cmd_done); + /* Add the request buffer (read by the device). */ + rc = virtqueue_add_outbuf(vq, &sg_out, 1, msg->req.data, GFP_KERNEL); + if (rc) + return rc; + + /* Add the response buffer (written by the device). */ + rc = virtqueue_add_inbuf(vq, &sg_in, 1, msg->resp.data, GFP_KERNEL); + if (rc) + goto cleanup; + + kicked = virtqueue_kick(vq); + if (!kicked) { + /* Cannot kick the virtqueue. */ + rc = -EIO; + goto cleanup; + } + + /* If the kick succeeded, wait for the device's response. */ + if (!wait_for_completion_io_timeout(&nsm->cmd_done, + msecs_to_jiffies(NSM_DEFAULT_TIMEOUT_MSECS))) { + rc = -ETIMEDOUT; + goto cleanup; + } + + queue_buf = virtqueue_get_buf(vq, &len); + if (!queue_buf || (queue_buf != msg->req.data)) { + dev_err(dev, "wrong request buffer."); + rc = -ENODATA; + goto cleanup; + } + + queue_buf = virtqueue_get_buf(vq, &len); + if (!queue_buf || (queue_buf != msg->resp.data)) { + dev_err(dev, "wrong response buffer."); + rc = -ENODATA; + goto cleanup; + } + + msg->resp.len = len; + + rc = 0; + +cleanup: + if (rc) { + /* Clean the virtqueue. */ + while (virtqueue_get_buf(vq, &len) != NULL) + ; + } + + return rc; +} + +static int fill_req_get_random(struct nsm *nsm, struct nsm_data_req *req) +{ + /* + * 69 # text(9) + * 47657452616E646F6D # "GetRandom" + */ + const u8 request[] = { CBOR_TYPE_TEXT + strlen("GetRandom"), + 'G', 'e', 't', 'R', 'a', 'n', 'd', 'o', 'm' }; + + memcpy(req->data, request, sizeof(request)); + req->len = sizeof(request); + + return 0; +} + +static int parse_resp_get_random(struct nsm *nsm, struct nsm_data_resp *resp, + void *out, size_t max) +{ + /* + * A1 # map(1) + * 69 # text(9) - Name of field + * 47657452616E646F6D # "GetRandom" + * A1 # map(1) - The field itself + * 66 # text(6) + * 72616E646F6D # "random" + * # The rest of the response is random data + */ + const u8 response[] = { CBOR_TYPE_MAP + 1, + CBOR_TYPE_TEXT + strlen("GetRandom"), + 'G', 'e', 't', 'R', 'a', 'n', 'd', 'o', 'm', + CBOR_TYPE_MAP + 1, + CBOR_TYPE_TEXT + strlen("random"), + 'r', 'a', 'n', 'd', 'o', 'm' }; + struct device *dev = &nsm->vdev->dev; + u8 *rand_data = NULL; + u8 *resp_ptr = resp->data; + u64 resp_len = resp->len; + int rc; + + if ((resp->len < sizeof(response) + 1) || + (memcmp(resp_ptr, response, sizeof(response)) != 0)) { + dev_err(dev, "Invalid response for GetRandom"); + return -EFAULT; + } + + resp_ptr += sizeof(response); + resp_len -= sizeof(response); + + rc = cbor_object_get_array(resp_ptr, resp_len, &rand_data); + if (rc < 0) { + dev_err(dev, "GetRandom: Invalid CBOR encoding\n"); + return rc; + } + + rc = min_t(size_t, rc, max); + memcpy(out, rand_data, rc); + + return rc; +} + +/* + * HwRNG implementation + */ +static int nsm_rng_read(struct hwrng *rng, void *data, size_t max, bool wait) +{ + struct nsm *nsm = hwrng_to_nsm(rng); + struct device *dev = &nsm->vdev->dev; + int rc = 0; + + /* NSM always needs to wait for a response */ + if (!wait) + return 0; + + mutex_lock(&nsm->lock); + + rc = fill_req_get_random(nsm, &nsm->msg.req); + if (rc != 0) + goto out; + + rc = nsm_sendrecv_msg_locked(nsm); + if (rc != 0) + goto out; + + rc = parse_resp_get_random(nsm, &nsm->msg.resp, data, max); + if (rc < 0) + goto out; + + dev_dbg(dev, "RNG: returning rand bytes = %d", rc); +out: + mutex_unlock(&nsm->lock); + return rc; +} + +static long nsm_dev_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + void __user *argp = u64_to_user_ptr((u64)arg); + struct nsm *nsm = file_to_nsm(file); + struct nsm_raw raw; + int r = 0; + + if (cmd != NSM_IOCTL_RAW) + return -EINVAL; + + if (_IOC_SIZE(cmd) != sizeof(raw)) + return -EINVAL; + + /* Copy user argument struct to kernel argument struct */ + r = -EFAULT; + if (copy_from_user(&raw, argp, _IOC_SIZE(cmd))) + goto out; + + mutex_lock(&nsm->lock); + + /* Convert kernel argument struct to device request */ + r = fill_req_raw(nsm, &nsm->msg.req, &raw); + if (r) + goto out; + + /* Send message to NSM and read reply */ + r = nsm_sendrecv_msg_locked(nsm); + if (r) + goto out; + + /* Parse device response into kernel argument struct */ + r = parse_resp_raw(nsm, &nsm->msg.resp, &raw); + if (r) + goto out; + + /* Copy kernel argument struct back to user argument struct */ + r = -EFAULT; + if (copy_to_user(argp, &raw, sizeof(raw))) + goto out; + + r = 0; + +out: + mutex_unlock(&nsm->lock); + return r; +} + +static int nsm_device_init_vq(struct virtio_device *vdev) +{ + struct virtqueue *vq = virtio_find_single_vq(vdev, + nsm_vq_callback, "nsm.vq.0"); + struct nsm *nsm = vdev->priv; + + if (IS_ERR(vq)) + return PTR_ERR(vq); + + nsm->vq = vq; + + return 0; +} + +static const struct file_operations nsm_dev_fops = { + .unlocked_ioctl = nsm_dev_ioctl, + .compat_ioctl = compat_ptr_ioctl, +}; + +/* Handler for probing the NSM device */ +static int nsm_device_probe(struct virtio_device *vdev) +{ + struct device *dev = &vdev->dev; + struct nsm *nsm; + int rc; + + nsm = devm_kzalloc(&vdev->dev, sizeof(*nsm), GFP_KERNEL); + if (!nsm) + return -ENOMEM; + + vdev->priv = nsm; + nsm->vdev = vdev; + + rc = nsm_device_init_vq(vdev); + if (rc) { + dev_err(dev, "queue failed to initialize: %d.\n", rc); + goto err_init_vq; + } + + mutex_init(&nsm->lock); + + /* Register as hwrng provider */ + nsm->hwrng = (struct hwrng) { + .read = nsm_rng_read, + .name = "nsm-hwrng", + .quality = 1000, + }; + + rc = hwrng_register(&nsm->hwrng); + if (rc) { + dev_err(dev, "RNG initialization error: %d.\n", rc); + goto err_hwrng; + } + + /* Register /dev/nsm device node */ + nsm->misc = (struct miscdevice) { + .minor = MISC_DYNAMIC_MINOR, + .name = "nsm", + .fops = &nsm_dev_fops, + .mode = 0666, + }; + + rc = misc_register(&nsm->misc); + if (rc) { + dev_err(dev, "misc device registration error: %d.\n", rc); + goto err_misc; + } + + return 0; + +err_misc: + hwrng_unregister(&nsm->hwrng); +err_hwrng: + vdev->config->del_vqs(vdev); +err_init_vq: + return rc; +} + +/* Handler for removing the NSM device */ +static void nsm_device_remove(struct virtio_device *vdev) +{ + struct nsm *nsm = vdev->priv; + + hwrng_unregister(&nsm->hwrng); + + vdev->config->del_vqs(vdev); + misc_deregister(&nsm->misc); +} + +/* NSM device configuration structure */ +static struct virtio_driver virtio_nsm_driver = { + .feature_table = 0, + .feature_table_size = 0, + .feature_table_legacy = 0, + .feature_table_size_legacy = 0, + .driver.name = KBUILD_MODNAME, + .driver.owner = THIS_MODULE, + .id_table = id_table, + .probe = nsm_device_probe, + .remove = nsm_device_remove, +}; + +module_virtio_driver(virtio_nsm_driver); +MODULE_DEVICE_TABLE(virtio, id_table); +MODULE_DESCRIPTION("Virtio NSM driver"); +MODULE_LICENSE("GPL"); diff --git a/include/uapi/linux/nsm.h b/include/uapi/linux/nsm.h new file mode 100644 index 000000000000..e529f232f6c0 --- /dev/null +++ b/include/uapi/linux/nsm.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved. + */ + +#ifndef __UAPI_LINUX_NSM_H +#define __UAPI_LINUX_NSM_H + +#include +#include + +#define NSM_MAGIC 0x0A + +#define NSM_REQUEST_MAX_SIZE 0x1000 +#define NSM_RESPONSE_MAX_SIZE 0x3000 + +struct nsm_iovec { + __u64 addr; /* Virtual address of target buffer */ + __u64 len; /* Length of target buffer */ +}; + +/* Raw NSM message. Only available with CAP_SYS_ADMIN. */ +struct nsm_raw { + /* Request from user */ + struct nsm_iovec request; + /* Response to user */ + struct nsm_iovec response; +}; +#define NSM_IOCTL_RAW _IOWR(NSM_MAGIC, 0x0, struct nsm_raw) + +#endif /* __UAPI_LINUX_NSM_H */ -- cgit From e56fdbfb06e26a7066b070967badef4148528df2 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sat, 25 Nov 2023 20:31:27 +0100 Subject: bpf: Add link_info support for uprobe multi link Adding support to get uprobe_link details through bpf_link_info interface. Adding new struct uprobe_multi to struct bpf_link_info to carry the uprobe_multi link details. The uprobe_multi.count is passed from user space to denote size of array fields (offsets/ref_ctr_offsets/cookies). The actual array size is stored back to uprobe_multi.count (allowing user to find out the actual array size) and array fields are populated up to the user passed size. All the non-array fields (path/count/flags/pid) are always set. Signed-off-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20231125193130.834322-4-jolsa@kernel.org --- include/uapi/linux/bpf.h | 10 ++++++ kernel/trace/bpf_trace.c | 72 ++++++++++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 10 ++++++ 3 files changed, 92 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7a5498242eaa..e88746ba7d21 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6562,6 +6562,16 @@ struct bpf_link_info { __u32 flags; __u64 missed; } kprobe_multi; + struct { + __aligned_u64 path; + __aligned_u64 offsets; + __aligned_u64 ref_ctr_offsets; + __aligned_u64 cookies; + __u32 path_size; /* in/out: real path size on success, including zero byte */ + __u32 count; /* in/out: uprobe_multi offsets/ref_ctr_offsets/cookies count */ + __u32 flags; + __u32 pid; + } uprobe_multi; struct { __u32 type; /* enum bpf_perf_event_type */ __u32 :32; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index ad0323f27288..c284a4ad0315 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3042,6 +3042,7 @@ struct bpf_uprobe_multi_link { struct path path; struct bpf_link link; u32 cnt; + u32 flags; struct bpf_uprobe *uprobes; struct task_struct *task; }; @@ -3083,9 +3084,79 @@ static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link) kfree(umulti_link); } +static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + u64 __user *uref_ctr_offsets = u64_to_user_ptr(info->uprobe_multi.ref_ctr_offsets); + u64 __user *ucookies = u64_to_user_ptr(info->uprobe_multi.cookies); + u64 __user *uoffsets = u64_to_user_ptr(info->uprobe_multi.offsets); + u64 __user *upath = u64_to_user_ptr(info->uprobe_multi.path); + u32 upath_size = info->uprobe_multi.path_size; + struct bpf_uprobe_multi_link *umulti_link; + u32 ucount = info->uprobe_multi.count; + int err = 0, i; + long left; + + if (!upath ^ !upath_size) + return -EINVAL; + + if ((uoffsets || uref_ctr_offsets || ucookies) && !ucount) + return -EINVAL; + + umulti_link = container_of(link, struct bpf_uprobe_multi_link, link); + info->uprobe_multi.count = umulti_link->cnt; + info->uprobe_multi.flags = umulti_link->flags; + info->uprobe_multi.pid = umulti_link->task ? + task_pid_nr_ns(umulti_link->task, task_active_pid_ns(current)) : 0; + + if (upath) { + char *p, *buf; + + upath_size = min_t(u32, upath_size, PATH_MAX); + + buf = kmalloc(upath_size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + p = d_path(&umulti_link->path, buf, upath_size); + if (IS_ERR(p)) { + kfree(buf); + return PTR_ERR(p); + } + upath_size = buf + upath_size - p; + left = copy_to_user(upath, p, upath_size); + kfree(buf); + if (left) + return -EFAULT; + info->uprobe_multi.path_size = upath_size; + } + + if (!uoffsets && !ucookies && !uref_ctr_offsets) + return 0; + + if (ucount < umulti_link->cnt) + err = -ENOSPC; + else + ucount = umulti_link->cnt; + + for (i = 0; i < ucount; i++) { + if (uoffsets && + put_user(umulti_link->uprobes[i].offset, uoffsets + i)) + return -EFAULT; + if (uref_ctr_offsets && + put_user(umulti_link->uprobes[i].ref_ctr_offset, uref_ctr_offsets + i)) + return -EFAULT; + if (ucookies && + put_user(umulti_link->uprobes[i].cookie, ucookies + i)) + return -EFAULT; + } + + return err; +} + static const struct bpf_link_ops bpf_uprobe_multi_link_lops = { .release = bpf_uprobe_multi_link_release, .dealloc = bpf_uprobe_multi_link_dealloc, + .fill_link_info = bpf_uprobe_multi_link_fill_link_info, }; static int uprobe_prog_run(struct bpf_uprobe *uprobe, @@ -3274,6 +3345,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr link->uprobes = uprobes; link->path = path; link->task = task; + link->flags = flags; bpf_link_init(&link->link, BPF_LINK_TYPE_UPROBE_MULTI, &bpf_uprobe_multi_link_lops, prog); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7a5498242eaa..e88746ba7d21 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6562,6 +6562,16 @@ struct bpf_link_info { __u32 flags; __u64 missed; } kprobe_multi; + struct { + __aligned_u64 path; + __aligned_u64 offsets; + __aligned_u64 ref_ctr_offsets; + __aligned_u64 cookies; + __u32 path_size; /* in/out: real path size on success, including zero byte */ + __u32 count; /* in/out: uprobe_multi offsets/ref_ctr_offsets/cookies count */ + __u32 flags; + __u32 pid; + } uprobe_multi; struct { __u32 type; /* enum bpf_perf_event_type */ __u32 :32; -- cgit From 341ac980eab90ac1f6c22ee9f9da83ed9604d899 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 27 Nov 2023 11:03:07 -0800 Subject: xsk: Support tx_metadata_len For zerocopy mode, tx_desc->addr can point to an arbitrary offset and carry some TX metadata in the headroom. For copy mode, there is no way currently to populate skb metadata. Introduce new tx_metadata_len umem config option that indicates how many bytes to treat as metadata. Metadata bytes come prior to tx_desc address (same as in RX case). The size of the metadata has mostly the same constraints as XDP: - less than 256 bytes - 8-byte aligned (compared to 4-byte alignment on xdp, due to 8-byte timestamp in the completion) - non-zero This data is not interpreted in any way right now. Reviewed-by: Song Yoong Siang Signed-off-by: Stanislav Fomichev Reviewed-by: Jakub Kicinski Link: https://lore.kernel.org/r/20231127190319.1190813-2-sdf@google.com Signed-off-by: Alexei Starovoitov --- include/net/xdp_sock.h | 1 + include/net/xsk_buff_pool.h | 1 + include/uapi/linux/if_xdp.h | 1 + net/xdp/xdp_umem.c | 4 ++++ net/xdp/xsk.c | 12 +++++++++++- net/xdp/xsk_buff_pool.c | 1 + net/xdp/xsk_queue.h | 17 ++++++++++------- tools/include/uapi/linux/if_xdp.h | 1 + 8 files changed, 30 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index f83128007fb0..bcf765124f72 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -30,6 +30,7 @@ struct xdp_umem { struct user_struct *user; refcount_t users; u8 flags; + u8 tx_metadata_len; bool zc; struct page **pgs; int id; diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index b0bdff26fc88..1985ffaf9b0c 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -77,6 +77,7 @@ struct xsk_buff_pool { u32 chunk_size; u32 chunk_shift; u32 frame_len; + u8 tx_metadata_len; /* inherited from umem */ u8 cached_need_wakeup; bool uses_need_wakeup; bool dma_need_sync; diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h index 8d48863472b9..2ecf79282c26 100644 --- a/include/uapi/linux/if_xdp.h +++ b/include/uapi/linux/if_xdp.h @@ -76,6 +76,7 @@ struct xdp_umem_reg { __u32 chunk_size; __u32 headroom; __u32 flags; + __u32 tx_metadata_len; }; struct xdp_statistics { diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 06cead2b8e34..946a687fb8e8 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -199,6 +199,9 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (headroom >= chunk_size - XDP_PACKET_HEADROOM) return -EINVAL; + if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8) + return -EINVAL; + umem->size = size; umem->headroom = headroom; umem->chunk_size = chunk_size; @@ -207,6 +210,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->pgs = NULL; umem->user = NULL; umem->flags = mr->flags; + umem->tx_metadata_len = mr->tx_metadata_len; INIT_LIST_HEAD(&umem->xsk_dma_list); refcount_set(&umem->users, 1); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index ae9f8cb611f6..c904356e2800 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -1283,6 +1283,14 @@ struct xdp_umem_reg_v1 { __u32 headroom; }; +struct xdp_umem_reg_v2 { + __u64 addr; /* Start of packet data area */ + __u64 len; /* Length of packet data area */ + __u32 chunk_size; + __u32 headroom; + __u32 flags; +}; + static int xsk_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { @@ -1326,8 +1334,10 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, if (optlen < sizeof(struct xdp_umem_reg_v1)) return -EINVAL; - else if (optlen < sizeof(mr)) + else if (optlen < sizeof(struct xdp_umem_reg_v2)) mr_size = sizeof(struct xdp_umem_reg_v1); + else if (optlen < sizeof(mr)) + mr_size = sizeof(struct xdp_umem_reg_v2); if (copy_from_sockptr(&mr, optval, mr_size)) return -EFAULT; diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 49cb9f9a09be..386eddcdf837 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -85,6 +85,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, XDP_PACKET_HEADROOM; pool->umem = umem; pool->addrs = umem->addrs; + pool->tx_metadata_len = umem->tx_metadata_len; INIT_LIST_HEAD(&pool->free_list); INIT_LIST_HEAD(&pool->xskb_list); INIT_LIST_HEAD(&pool->xsk_tx_list); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 13354a1e4280..c74a1372bcb9 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -143,15 +143,17 @@ static inline bool xp_unused_options_set(u32 options) static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { - u64 offset = desc->addr & (pool->chunk_size - 1); + u64 addr = desc->addr - pool->tx_metadata_len; + u64 len = desc->len + pool->tx_metadata_len; + u64 offset = addr & (pool->chunk_size - 1); if (!desc->len) return false; - if (offset + desc->len > pool->chunk_size) + if (offset + len > pool->chunk_size) return false; - if (desc->addr >= pool->addrs_cnt) + if (addr >= pool->addrs_cnt) return false; if (xp_unused_options_set(desc->options)) @@ -162,16 +164,17 @@ static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool, static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { - u64 addr = xp_unaligned_add_offset_to_addr(desc->addr); + u64 addr = xp_unaligned_add_offset_to_addr(desc->addr) - pool->tx_metadata_len; + u64 len = desc->len + pool->tx_metadata_len; if (!desc->len) return false; - if (desc->len > pool->chunk_size) + if (len > pool->chunk_size) return false; - if (addr >= pool->addrs_cnt || addr + desc->len > pool->addrs_cnt || - xp_desc_crosses_non_contig_pg(pool, addr, desc->len)) + if (addr >= pool->addrs_cnt || addr + len > pool->addrs_cnt || + xp_desc_crosses_non_contig_pg(pool, addr, len)) return false; if (xp_unused_options_set(desc->options)) diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h index 73a47da885dc..34411a2e5b6c 100644 --- a/tools/include/uapi/linux/if_xdp.h +++ b/tools/include/uapi/linux/if_xdp.h @@ -76,6 +76,7 @@ struct xdp_umem_reg { __u32 chunk_size; __u32 headroom; __u32 flags; + __u32 tx_metadata_len; }; struct xdp_statistics { -- cgit From 48eb03dd26304c24f03bdbb9382e89c8564e71df Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 27 Nov 2023 11:03:08 -0800 Subject: xsk: Add TX timestamp and TX checksum offload support This change actually defines the (initial) metadata layout that should be used by AF_XDP userspace (xsk_tx_metadata). The first field is flags which requests appropriate offloads, followed by the offload-specific fields. The supported per-device offloads are exported via netlink (new xsk-flags). The offloads themselves are still implemented in a bit of a framework-y fashion that's left from my initial kfunc attempt. I'm introducing new xsk_tx_metadata_ops which drivers are supposed to implement. The drivers are also supposed to call xsk_tx_metadata_request/xsk_tx_metadata_complete in the right places. Since xsk_tx_metadata_{request,_complete} are static inline, we don't incur any extra overhead doing indirect calls. The benefit of this scheme is as follows: - keeps all metadata layout parsing away from driver code - makes it easy to grep and see which drivers implement what - don't need any extra flags to maintain to keep track of what offloads are implemented; if the callback is implemented - the offload is supported (used by netlink reporting code) Two offloads are defined right now: 1. XDP_TXMD_FLAGS_CHECKSUM: skb-style csum_start+csum_offset 2. XDP_TXMD_FLAGS_TIMESTAMP: writes TX timestamp back into metadata area upon completion (tx_timestamp field) XDP_TXMD_FLAGS_TIMESTAMP is also implemented for XDP_COPY mode: it writes SW timestamp from the skb destructor (note I'm reusing hwtstamps to pass metadata pointer). The struct is forward-compatible and can be extended in the future by appending more fields. Reviewed-by: Song Yoong Siang Signed-off-by: Stanislav Fomichev Acked-by: Jakub Kicinski Link: https://lore.kernel.org/r/20231127190319.1190813-3-sdf@google.com Signed-off-by: Alexei Starovoitov --- Documentation/netlink/specs/netdev.yaml | 19 +++++- include/linux/netdevice.h | 2 + include/linux/skbuff.h | 14 +++- include/net/xdp_sock.h | 110 ++++++++++++++++++++++++++++++++ include/net/xdp_sock_drv.h | 13 ++++ include/net/xsk_buff_pool.h | 6 ++ include/uapi/linux/if_xdp.h | 38 +++++++++++ include/uapi/linux/netdev.h | 16 +++++ net/core/netdev-genl.c | 13 +++- net/xdp/xsk.c | 34 ++++++++++ net/xdp/xsk_queue.h | 2 +- tools/include/uapi/linux/if_xdp.h | 52 +++++++++++++-- tools/include/uapi/linux/netdev.h | 16 +++++ tools/net/ynl/generated/netdev-user.c | 19 ++++++ tools/net/ynl/generated/netdev-user.h | 3 + 15 files changed, 348 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 14511b13f305..00439bcbd2e3 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -45,7 +45,6 @@ definitions: - type: flags name: xdp-rx-metadata - render-max: true entries: - name: timestamp @@ -55,6 +54,18 @@ definitions: name: hash doc: Device is capable of exposing receive packet hash via bpf_xdp_metadata_rx_hash(). + - + type: flags + name: xsk-flags + entries: + - + name: tx-timestamp + doc: + HW timestamping egress packets is supported by the driver. + - + name: tx-checksum + doc: + L3 checksum HW offload is supported by the driver. attribute-sets: - @@ -86,6 +97,11 @@ attribute-sets: See Documentation/networking/xdp-rx-metadata.rst for more details. type: u64 enum: xdp-rx-metadata + - + name: xsk-features + doc: Bitmask of enabled AF_XDP features. + type: u64 + enum: xsk-flags operations: list: @@ -103,6 +119,7 @@ operations: - xdp-features - xdp-zc-max-segs - xdp-rx-metadata-features + - xsk-features dump: reply: *dev-all - diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e87caa81f70c..08da8b28c816 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1865,6 +1865,7 @@ enum netdev_stat_type { * @netdev_ops: Includes several pointers to callbacks, * if one wants to override the ndo_*() functions * @xdp_metadata_ops: Includes pointers to XDP metadata callbacks. + * @xsk_tx_metadata_ops: Includes pointers to AF_XDP TX metadata callbacks. * @ethtool_ops: Management operations * @l3mdev_ops: Layer 3 master device operations * @ndisc_ops: Includes callbacks for different IPv6 neighbour @@ -2128,6 +2129,7 @@ struct net_device { unsigned long long priv_flags; const struct net_device_ops *netdev_ops; const struct xdp_metadata_ops *xdp_metadata_ops; + const struct xsk_tx_metadata_ops *xsk_tx_metadata_ops; int ifindex; unsigned short gflags; unsigned short hard_header_len; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 27998f73183e..b370eb8d70f7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -566,6 +566,15 @@ struct ubuf_info_msgzc { int mm_account_pinned_pages(struct mmpin *mmp, size_t size); void mm_unaccount_pinned_pages(struct mmpin *mmp); +/* Preserve some data across TX submission and completion. + * + * Note, this state is stored in the driver. Extending the layout + * might need some special care. + */ +struct xsk_tx_metadata_compl { + __u64 *tx_timestamp; +}; + /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ @@ -578,7 +587,10 @@ struct skb_shared_info { /* Warning: this field is not always filled in (UFO)! */ unsigned short gso_segs; struct sk_buff *frag_list; - struct skb_shared_hwtstamps hwtstamps; + union { + struct skb_shared_hwtstamps hwtstamps; + struct xsk_tx_metadata_compl xsk_meta; + }; unsigned int gso_type; u32 tskey; diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index bcf765124f72..3cb4dc9bd70e 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -93,12 +93,105 @@ struct xdp_sock { struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */ }; +/* + * AF_XDP TX metadata hooks for network devices. + * The following hooks can be defined; unless noted otherwise, they are + * optional and can be filled with a null pointer. + * + * void (*tmo_request_timestamp)(void *priv) + * Called when AF_XDP frame requested egress timestamp. + * + * u64 (*tmo_fill_timestamp)(void *priv) + * Called when AF_XDP frame, that had requested egress timestamp, + * received a completion. The hook needs to return the actual HW timestamp. + * + * void (*tmo_request_checksum)(u16 csum_start, u16 csum_offset, void *priv) + * Called when AF_XDP frame requested HW checksum offload. csum_start + * indicates position where checksumming should start. + * csum_offset indicates position where checksum should be stored. + * + */ +struct xsk_tx_metadata_ops { + void (*tmo_request_timestamp)(void *priv); + u64 (*tmo_fill_timestamp)(void *priv); + void (*tmo_request_checksum)(u16 csum_start, u16 csum_offset, void *priv); +}; + #ifdef CONFIG_XDP_SOCKETS int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp); void __xsk_map_flush(void); +/** + * xsk_tx_metadata_to_compl - Save enough relevant metadata information + * to perform tx completion in the future. + * @meta: pointer to AF_XDP metadata area + * @compl: pointer to output struct xsk_tx_metadata_to_compl + * + * This function should be called by the networking device when + * it prepares AF_XDP egress packet. The value of @compl should be stored + * and passed to xsk_tx_metadata_complete upon TX completion. + */ +static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta, + struct xsk_tx_metadata_compl *compl) +{ + if (!meta) + return; + + if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP) + compl->tx_timestamp = &meta->completion.tx_timestamp; + else + compl->tx_timestamp = NULL; +} + +/** + * xsk_tx_metadata_request - Evaluate AF_XDP TX metadata at submission + * and call appropriate xsk_tx_metadata_ops operation. + * @meta: pointer to AF_XDP metadata area + * @ops: pointer to struct xsk_tx_metadata_ops + * @priv: pointer to driver-private aread + * + * This function should be called by the networking device when + * it prepares AF_XDP egress packet. + */ +static inline void xsk_tx_metadata_request(const struct xsk_tx_metadata *meta, + const struct xsk_tx_metadata_ops *ops, + void *priv) +{ + if (!meta) + return; + + if (ops->tmo_request_timestamp) + if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP) + ops->tmo_request_timestamp(priv); + + if (ops->tmo_request_checksum) + if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) + ops->tmo_request_checksum(meta->request.csum_start, + meta->request.csum_offset, priv); +} + +/** + * xsk_tx_metadata_complete - Evaluate AF_XDP TX metadata at completion + * and call appropriate xsk_tx_metadata_ops operation. + * @compl: pointer to completion metadata produced from xsk_tx_metadata_to_compl + * @ops: pointer to struct xsk_tx_metadata_ops + * @priv: pointer to driver-private aread + * + * This function should be called by the networking device upon + * AF_XDP egress completion. + */ +static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl, + const struct xsk_tx_metadata_ops *ops, + void *priv) +{ + if (!compl) + return; + + *compl->tx_timestamp = ops->tmo_fill_timestamp(priv); +} + #else static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) @@ -115,6 +208,23 @@ static inline void __xsk_map_flush(void) { } +static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta, + struct xsk_tx_metadata_compl *compl) +{ +} + +static inline void xsk_tx_metadata_request(struct xsk_tx_metadata *meta, + const struct xsk_tx_metadata_ops *ops, + void *priv) +{ +} + +static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl, + const struct xsk_tx_metadata_ops *ops, + void *priv) +{ +} + #endif /* CONFIG_XDP_SOCKETS */ #if defined(CONFIG_XDP_SOCKETS) && defined(CONFIG_DEBUG_NET) diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 1f6fc8c7a84c..e2558ac3e195 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -165,6 +165,14 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) return xp_raw_get_data(pool, addr); } +static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr) +{ + if (!pool->tx_metadata_len) + return NULL; + + return xp_raw_get_data(pool, addr) - pool->tx_metadata_len; +} + static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); @@ -324,6 +332,11 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) return NULL; } +static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr) +{ + return NULL; +} + static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) { } diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 1985ffaf9b0c..97f5cc10d79e 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -33,6 +33,7 @@ struct xdp_buff_xsk { }; #define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb)) +#define XSK_TX_COMPL_FITS(t) BUILD_BUG_ON(sizeof(struct xsk_tx_metadata_compl) > sizeof(t)) struct xsk_dma_map { dma_addr_t *dma_pages; @@ -234,4 +235,9 @@ static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb) return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT); } +static inline bool xp_tx_metadata_enabled(const struct xsk_buff_pool *pool) +{ + return pool->tx_metadata_len > 0; +} + #endif /* XSK_BUFF_POOL_H_ */ diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h index 2ecf79282c26..95de66d5a26c 100644 --- a/include/uapi/linux/if_xdp.h +++ b/include/uapi/linux/if_xdp.h @@ -106,6 +106,41 @@ struct xdp_options { #define XSK_UNALIGNED_BUF_ADDR_MASK \ ((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1) +/* Request transmit timestamp. Upon completion, put it into tx_timestamp + * field of struct xsk_tx_metadata. + */ +#define XDP_TXMD_FLAGS_TIMESTAMP (1 << 0) + +/* Request transmit checksum offload. Checksum start position and offset + * are communicated via csum_start and csum_offset fields of struct + * xsk_tx_metadata. + */ +#define XDP_TXMD_FLAGS_CHECKSUM (1 << 1) + +/* AF_XDP offloads request. 'request' union member is consumed by the driver + * when the packet is being transmitted. 'completion' union member is + * filled by the driver when the transmit completion arrives. + */ +struct xsk_tx_metadata { + __u64 flags; + + union { + struct { + /* XDP_TXMD_FLAGS_CHECKSUM */ + + /* Offset from desc->addr where checksumming should start. */ + __u16 csum_start; + /* Offset from csum_start where checksum should be stored. */ + __u16 csum_offset; + } request; + + struct { + /* XDP_TXMD_FLAGS_TIMESTAMP */ + __u64 tx_timestamp; + } completion; + }; +}; + /* Rx/Tx descriptor */ struct xdp_desc { __u64 addr; @@ -122,4 +157,7 @@ struct xdp_desc { */ #define XDP_PKT_CONTD (1 << 0) +/* TX packet carries valid metadata. */ +#define XDP_TX_METADATA (1 << 1) + #endif /* _LINUX_IF_XDP_H */ diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 2943a151d4f1..48d5477a668c 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -53,12 +53,28 @@ enum netdev_xdp_rx_metadata { NETDEV_XDP_RX_METADATA_MASK = 3, }; +/** + * enum netdev_xsk_flags + * @NETDEV_XSK_FLAGS_TX_TIMESTAMP: HW timestamping egress packets is supported + * by the driver. + * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the + * driver. + */ +enum netdev_xsk_flags { + NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1, + NETDEV_XSK_FLAGS_TX_CHECKSUM = 2, + + /* private: */ + NETDEV_XSK_FLAGS_MASK = 3, +}; + enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, NETDEV_A_DEV_XDP_FEATURES, NETDEV_A_DEV_XDP_ZC_MAX_SEGS, NETDEV_A_DEV_XDP_RX_METADATA_FEATURES, + NETDEV_A_DEV_XSK_FEATURES, __NETDEV_A_DEV_MAX, NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1) diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index fe61f85bcf33..10f2124e9e23 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -6,6 +6,7 @@ #include #include #include +#include #include "netdev-genl-gen.h" @@ -13,6 +14,7 @@ static int netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp, const struct genl_info *info) { + u64 xsk_features = 0; u64 xdp_rx_meta = 0; void *hdr; @@ -26,11 +28,20 @@ netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp, XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC + if (netdev->xsk_tx_metadata_ops) { + if (netdev->xsk_tx_metadata_ops->tmo_fill_timestamp) + xsk_features |= NETDEV_XSK_FLAGS_TX_TIMESTAMP; + if (netdev->xsk_tx_metadata_ops->tmo_request_checksum) + xsk_features |= NETDEV_XSK_FLAGS_TX_CHECKSUM; + } + if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) || nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_FEATURES, netdev->xdp_features, NETDEV_A_DEV_PAD) || nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_RX_METADATA_FEATURES, - xdp_rx_meta, NETDEV_A_DEV_PAD)) { + xdp_rx_meta, NETDEV_A_DEV_PAD) || + nla_put_u64_64bit(rsp, NETDEV_A_DEV_XSK_FEATURES, + xsk_features, NETDEV_A_DEV_PAD)) { genlmsg_cancel(rsp, hdr); return -EINVAL; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index c904356e2800..e83ade32f1fd 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -571,6 +571,13 @@ static u32 xsk_get_num_desc(struct sk_buff *skb) static void xsk_destruct_skb(struct sk_buff *skb) { + struct xsk_tx_metadata_compl *compl = &skb_shinfo(skb)->xsk_meta; + + if (compl->tx_timestamp) { + /* sw completion timestamp, not a real one */ + *compl->tx_timestamp = ktime_get_tai_fast_ns(); + } + xsk_cq_submit_locked(xdp_sk(skb->sk), xsk_get_num_desc(skb)); sock_wfree(skb); } @@ -655,8 +662,10 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs, static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, struct xdp_desc *desc) { + struct xsk_tx_metadata *meta = NULL; struct net_device *dev = xs->dev; struct sk_buff *skb = xs->skb; + bool first_frag = false; int err; if (dev->priv_flags & IFF_TX_SKB_NO_LINEAR) { @@ -687,6 +696,8 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, kfree_skb(skb); goto free_err; } + + first_frag = true; } else { int nr_frags = skb_shinfo(skb)->nr_frags; struct page *page; @@ -709,12 +720,35 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, skb_add_rx_frag(skb, nr_frags, page, 0, len, 0); } + + if (first_frag && desc->options & XDP_TX_METADATA) { + if (unlikely(xs->pool->tx_metadata_len == 0)) { + err = -EINVAL; + goto free_err; + } + + meta = buffer - xs->pool->tx_metadata_len; + + if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) { + if (unlikely(meta->request.csum_start + + meta->request.csum_offset + + sizeof(__sum16) > len)) { + err = -EINVAL; + goto free_err; + } + + skb->csum_start = hr + meta->request.csum_start; + skb->csum_offset = meta->request.csum_offset; + skb->ip_summed = CHECKSUM_PARTIAL; + } + } } skb->dev = dev; skb->priority = READ_ONCE(xs->sk.sk_priority); skb->mark = READ_ONCE(xs->sk.sk_mark); skb->destructor = xsk_destruct_skb; + xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta); xsk_set_destructor_arg(skb); return skb; diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index c74a1372bcb9..6f2d1621c992 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -137,7 +137,7 @@ static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr) static inline bool xp_unused_options_set(u32 options) { - return options & ~XDP_PKT_CONTD; + return options & ~(XDP_PKT_CONTD | XDP_TX_METADATA); } static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool, diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h index 34411a2e5b6c..d0882edc1642 100644 --- a/tools/include/uapi/linux/if_xdp.h +++ b/tools/include/uapi/linux/if_xdp.h @@ -26,11 +26,11 @@ */ #define XDP_USE_NEED_WAKEUP (1 << 3) /* By setting this option, userspace application indicates that it can - * handle multiple descriptors per packet thus enabling xsk core to split + * handle multiple descriptors per packet thus enabling AF_XDP to split * multi-buffer XDP frames into multiple Rx descriptors. Without this set - * such frames will be dropped by xsk. + * such frames will be dropped. */ -#define XDP_USE_SG (1 << 4) +#define XDP_USE_SG (1 << 4) /* Flags for xsk_umem_config flags */ #define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0) @@ -106,6 +106,41 @@ struct xdp_options { #define XSK_UNALIGNED_BUF_ADDR_MASK \ ((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1) +/* Request transmit timestamp. Upon completion, put it into tx_timestamp + * field of union xsk_tx_metadata. + */ +#define XDP_TXMD_FLAGS_TIMESTAMP (1 << 0) + +/* Request transmit checksum offload. Checksum start position and offset + * are communicated via csum_start and csum_offset fields of union + * xsk_tx_metadata. + */ +#define XDP_TXMD_FLAGS_CHECKSUM (1 << 1) + +/* AF_XDP offloads request. 'request' union member is consumed by the driver + * when the packet is being transmitted. 'completion' union member is + * filled by the driver when the transmit completion arrives. + */ +struct xsk_tx_metadata { + __u64 flags; + + union { + struct { + /* XDP_TXMD_FLAGS_CHECKSUM */ + + /* Offset from desc->addr where checksumming should start. */ + __u16 csum_start; + /* Offset from csum_start where checksum should be stored. */ + __u16 csum_offset; + } request; + + struct { + /* XDP_TXMD_FLAGS_TIMESTAMP */ + __u64 tx_timestamp; + } completion; + }; +}; + /* Rx/Tx descriptor */ struct xdp_desc { __u64 addr; @@ -113,9 +148,16 @@ struct xdp_desc { __u32 options; }; -/* Flag indicating packet constitutes of multiple buffers*/ +/* UMEM descriptor is __u64 */ + +/* Flag indicating that the packet continues with the buffer pointed out by the + * next frame in the ring. The end of the packet is signalled by setting this + * bit to zero. For single buffer packets, every descriptor has 'options' set + * to 0 and this maintains backward compatibility. + */ #define XDP_PKT_CONTD (1 << 0) -/* UMEM descriptor is __u64 */ +/* TX packet carries valid metadata. */ +#define XDP_TX_METADATA (1 << 1) #endif /* _LINUX_IF_XDP_H */ diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 2943a151d4f1..48d5477a668c 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -53,12 +53,28 @@ enum netdev_xdp_rx_metadata { NETDEV_XDP_RX_METADATA_MASK = 3, }; +/** + * enum netdev_xsk_flags + * @NETDEV_XSK_FLAGS_TX_TIMESTAMP: HW timestamping egress packets is supported + * by the driver. + * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the + * driver. + */ +enum netdev_xsk_flags { + NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1, + NETDEV_XSK_FLAGS_TX_CHECKSUM = 2, + + /* private: */ + NETDEV_XSK_FLAGS_MASK = 3, +}; + enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, NETDEV_A_DEV_XDP_FEATURES, NETDEV_A_DEV_XDP_ZC_MAX_SEGS, NETDEV_A_DEV_XDP_RX_METADATA_FEATURES, + NETDEV_A_DEV_XSK_FEATURES, __NETDEV_A_DEV_MAX, NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1) diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c index b5ffe8cd1144..6283d87dad37 100644 --- a/tools/net/ynl/generated/netdev-user.c +++ b/tools/net/ynl/generated/netdev-user.c @@ -58,6 +58,19 @@ const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value) return netdev_xdp_rx_metadata_strmap[value]; } +static const char * const netdev_xsk_flags_strmap[] = { + [0] = "tx-timestamp", + [1] = "tx-checksum", +}; + +const char *netdev_xsk_flags_str(enum netdev_xsk_flags value) +{ + value = ffs(value) - 1; + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(netdev_xsk_flags_strmap)) + return NULL; + return netdev_xsk_flags_strmap[value]; +} + /* Policies */ struct ynl_policy_attr netdev_dev_policy[NETDEV_A_DEV_MAX + 1] = { [NETDEV_A_DEV_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, }, @@ -65,6 +78,7 @@ struct ynl_policy_attr netdev_dev_policy[NETDEV_A_DEV_MAX + 1] = { [NETDEV_A_DEV_XDP_FEATURES] = { .name = "xdp-features", .type = YNL_PT_U64, }, [NETDEV_A_DEV_XDP_ZC_MAX_SEGS] = { .name = "xdp-zc-max-segs", .type = YNL_PT_U32, }, [NETDEV_A_DEV_XDP_RX_METADATA_FEATURES] = { .name = "xdp-rx-metadata-features", .type = YNL_PT_U64, }, + [NETDEV_A_DEV_XSK_FEATURES] = { .name = "xsk-features", .type = YNL_PT_U64, }, }; struct ynl_policy_nest netdev_dev_nest = { @@ -116,6 +130,11 @@ int netdev_dev_get_rsp_parse(const struct nlmsghdr *nlh, void *data) return MNL_CB_ERROR; dst->_present.xdp_rx_metadata_features = 1; dst->xdp_rx_metadata_features = mnl_attr_get_u64(attr); + } else if (type == NETDEV_A_DEV_XSK_FEATURES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.xsk_features = 1; + dst->xsk_features = mnl_attr_get_u64(attr); } } diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h index 4fafac879df3..39af1908444b 100644 --- a/tools/net/ynl/generated/netdev-user.h +++ b/tools/net/ynl/generated/netdev-user.h @@ -19,6 +19,7 @@ extern const struct ynl_family ynl_netdev_family; const char *netdev_op_str(int op); const char *netdev_xdp_act_str(enum netdev_xdp_act value); const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value); +const char *netdev_xsk_flags_str(enum netdev_xsk_flags value); /* Common nested types */ /* ============== NETDEV_CMD_DEV_GET ============== */ @@ -50,12 +51,14 @@ struct netdev_dev_get_rsp { __u32 xdp_features:1; __u32 xdp_zc_max_segs:1; __u32 xdp_rx_metadata_features:1; + __u32 xsk_features:1; } _present; __u32 ifindex; __u64 xdp_features; __u32 xdp_zc_max_segs; __u64 xdp_rx_metadata_features; + __u64 xsk_features; }; void netdev_dev_get_rsp_free(struct netdev_dev_get_rsp *rsp); -- cgit From 11614723af26e7c32fcb704d8f30fdf60c1122dc Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 27 Nov 2023 11:03:14 -0800 Subject: xsk: Add option to calculate TX checksum in SW For XDP_COPY mode, add a UMEM option XDP_UMEM_TX_SW_CSUM to call skb_checksum_help in transmit path. Might be useful to debugging issues with real hardware. I also use this mode in the selftests. Signed-off-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20231127190319.1190813-9-sdf@google.com Signed-off-by: Alexei Starovoitov --- Documentation/networking/xsk-tx-metadata.rst | 9 +++++++++ include/net/xsk_buff_pool.h | 1 + include/uapi/linux/if_xdp.h | 8 +++++++- net/xdp/xdp_umem.c | 7 ++++++- net/xdp/xsk.c | 6 ++++++ net/xdp/xsk_buff_pool.c | 1 + tools/include/uapi/linux/if_xdp.h | 8 +++++++- 7 files changed, 37 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/xsk-tx-metadata.rst b/Documentation/networking/xsk-tx-metadata.rst index 4f376560b23f..97ecfa480d00 100644 --- a/Documentation/networking/xsk-tx-metadata.rst +++ b/Documentation/networking/xsk-tx-metadata.rst @@ -50,6 +50,15 @@ packet's ``struct xdp_desc`` descriptor should set ``XDP_TX_METADATA`` bit in the ``options`` field. Also note that in a multi-buffer packet only the first chunk should carry the metadata. +Software TX Checksum +==================== + +For development and testing purposes its possible to pass +``XDP_UMEM_TX_SW_CSUM`` flag to ``XDP_UMEM_REG`` UMEM registration call. +In this case, when running in ``XDK_COPY`` mode, the TX checksum +is calculated on the CPU. Do not enable this option in production because +it will negatively affect performance. + Querying Device Capabilities ============================ diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 97f5cc10d79e..8d48d37ab7c0 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -83,6 +83,7 @@ struct xsk_buff_pool { bool uses_need_wakeup; bool dma_need_sync; bool unaligned; + bool tx_sw_csum; void *addrs; /* Mutual exclusion of the completion ring in the SKB mode. Two cases to protect: * NAPI TX thread and sendmsg error paths in the SKB destructor callback and when diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h index 95de66d5a26c..d31698410410 100644 --- a/include/uapi/linux/if_xdp.h +++ b/include/uapi/linux/if_xdp.h @@ -33,7 +33,13 @@ #define XDP_USE_SG (1 << 4) /* Flags for xsk_umem_config flags */ -#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0) +#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0) + +/* Force checksum calculation in software. Can be used for testing or + * working around potential HW issues. This option causes performance + * degradation and only works in XDP_COPY mode. + */ +#define XDP_UMEM_TX_SW_CSUM (1 << 1) struct sockaddr_xdp { __u16 sxdp_family; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 946a687fb8e8..caa340134b0e 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -148,6 +148,11 @@ static int xdp_umem_account_pages(struct xdp_umem *umem) return 0; } +#define XDP_UMEM_FLAGS_VALID ( \ + XDP_UMEM_UNALIGNED_CHUNK_FLAG | \ + XDP_UMEM_TX_SW_CSUM | \ + 0) + static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) { bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG; @@ -167,7 +172,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) return -EINVAL; } - if (mr->flags & ~XDP_UMEM_UNALIGNED_CHUNK_FLAG) + if (mr->flags & ~XDP_UMEM_FLAGS_VALID) return -EINVAL; if (!unaligned_chunks && !is_power_of_2(chunk_size)) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index d66ba9d6154f..281d49b4fca4 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -744,6 +744,12 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, skb->csum_start = hr + meta->request.csum_start; skb->csum_offset = meta->request.csum_offset; skb->ip_summed = CHECKSUM_PARTIAL; + + if (unlikely(xs->pool->tx_sw_csum)) { + err = skb_checksum_help(skb); + if (err) + goto free_err; + } } } } diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 386eddcdf837..4f6f538a5462 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -86,6 +86,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, pool->umem = umem; pool->addrs = umem->addrs; pool->tx_metadata_len = umem->tx_metadata_len; + pool->tx_sw_csum = umem->flags & XDP_UMEM_TX_SW_CSUM; INIT_LIST_HEAD(&pool->free_list); INIT_LIST_HEAD(&pool->xskb_list); INIT_LIST_HEAD(&pool->xsk_tx_list); diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h index d0882edc1642..638c606dfa74 100644 --- a/tools/include/uapi/linux/if_xdp.h +++ b/tools/include/uapi/linux/if_xdp.h @@ -33,7 +33,13 @@ #define XDP_USE_SG (1 << 4) /* Flags for xsk_umem_config flags */ -#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0) +#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0) + +/* Force checksum calculation in software. Can be used for testing or + * working around potential HW issues. This option causes performance + * degradation and only works in XDP_COPY mode. + */ +#define XDP_UMEM_TX_SW_CSUM (1 << 1) struct sockaddr_xdp { __u16 sxdp_family; -- cgit From 6ebf6f90ab4ac09a76172a6d387e8819d3259595 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Tue, 28 Nov 2023 15:18:45 -0800 Subject: mptcp: add mptcpi_subflows_total counter If the initial subflow has been removed, we cannot know without checking other counters, e.g. ss -ti | grep -c tcp-ulp-mptcp or getsockopt(SOL_MPTCP, MPTCP_FULL_INFO, ...) (or others except MPTCP_INFO of course) and then check mptcp_subflow_data->num_subflows to get the total amount of subflows. This patch adds a new counter mptcpi_subflows_total in mptcpi_flags to store the total amount of subflows, including the initial one. A new helper __mptcp_has_initial_subflow() is added to check whether the initial subflow has been removed or not. With this helper, we can then compute the total amount of subflows from mptcp_info by doing something like: mptcpi_subflows_total = mptcpi_subflows + __mptcp_has_initial_subflow(msk). Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/428 Reviewed-by: Matthieu Baerts Signed-off-by: Geliang Tang Signed-off-by: Mat Martineau Link: https://lore.kernel.org/r/20231128-send-net-next-2023107-v4-1-8d6b94150f6b@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 1 + net/mptcp/protocol.h | 9 +++++++++ net/mptcp/sockopt.c | 2 ++ 3 files changed, 12 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index a6451561f3f8..74cfe496891e 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -57,6 +57,7 @@ struct mptcp_info { __u64 mptcpi_bytes_sent; __u64 mptcpi_bytes_received; __u64 mptcpi_bytes_acked; + __u8 mptcpi_subflows_total; }; /* MPTCP Reset reason codes, rfc8684 */ diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index fe6f2d399ee8..458a2d7bb0dd 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -1072,6 +1072,15 @@ static inline void __mptcp_do_fallback(struct mptcp_sock *msk) set_bit(MPTCP_FALLBACK_DONE, &msk->flags); } +static inline bool __mptcp_has_initial_subflow(const struct mptcp_sock *msk) +{ + struct sock *ssk = READ_ONCE(msk->first); + + return ssk && ((1 << inet_sk_state_load(ssk)) & + (TCPF_ESTABLISHED | TCPF_SYN_SENT | + TCPF_SYN_RECV | TCPF_LISTEN)); +} + static inline void mptcp_do_fallback(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 353680733700..cabe856b2a45 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -938,6 +938,8 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) info->mptcpi_bytes_sent = msk->bytes_sent; info->mptcpi_bytes_received = msk->bytes_received; info->mptcpi_bytes_retrans = msk->bytes_retrans; + info->mptcpi_subflows_total = info->mptcpi_subflows + + __mptcp_has_initial_subflow(msk); unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(mptcp_diag_fill_info); -- cgit From 63ee44540205d993854f143a5ab1d7d9e63ffcf1 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Wed, 23 Aug 2023 14:54:55 -0700 Subject: dma-buf/sync_file: Add SET_DEADLINE ioctl The initial purpose is for igt tests, but this would also be useful for compositors that wait until close to vblank deadline to make decisions about which frame to show. The igt tests can be found at: https://gitlab.freedesktop.org/robclark/igt-gpu-tools/-/commits/fence-deadline v2: Clarify the timebase, add link to igt tests v3: Use u64 value in ns to express deadline. v4: More doc Signed-off-by: Rob Clark Acked-by: Pekka Paalanen Signed-off-by: Dmitry Baryshkov Link: https://patchwork.freedesktop.org/patch/msgid/20230823215458.203366-3-robdclark@gmail.com --- drivers/dma-buf/dma-fence.c | 3 ++- drivers/dma-buf/sync_file.c | 19 +++++++++++++++++++ include/uapi/linux/sync_file.h | 22 ++++++++++++++++++++++ 3 files changed, 43 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 8aa8f8cb7071..e0fd99e61a2d 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -934,7 +934,8 @@ EXPORT_SYMBOL(dma_fence_wait_any_timeout); * the GPU's devfreq to reduce frequency, when in fact the opposite is what is * needed. * - * To this end, deadline hint(s) can be set on a &dma_fence via &dma_fence_set_deadline. + * To this end, deadline hint(s) can be set on a &dma_fence via &dma_fence_set_deadline + * (or indirectly via userspace facing ioctls like &sync_set_deadline). * The deadline hint provides a way for the waiting driver, or userspace, to * convey an appropriate sense of urgency to the signaling driver. * diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index 2e9a316c596a..d9b1c1b2a72b 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -347,6 +347,22 @@ out: return ret; } +static int sync_file_ioctl_set_deadline(struct sync_file *sync_file, + unsigned long arg) +{ + struct sync_set_deadline ts; + + if (copy_from_user(&ts, (void __user *)arg, sizeof(ts))) + return -EFAULT; + + if (ts.pad) + return -EINVAL; + + dma_fence_set_deadline(sync_file->fence, ns_to_ktime(ts.deadline_ns)); + + return 0; +} + static long sync_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -359,6 +375,9 @@ static long sync_file_ioctl(struct file *file, unsigned int cmd, case SYNC_IOC_FILE_INFO: return sync_file_ioctl_fence_info(sync_file, arg); + case SYNC_IOC_SET_DEADLINE: + return sync_file_ioctl_set_deadline(sync_file, arg); + default: return -ENOTTY; } diff --git a/include/uapi/linux/sync_file.h b/include/uapi/linux/sync_file.h index ff0a931833e2..ff1f38889dcf 100644 --- a/include/uapi/linux/sync_file.h +++ b/include/uapi/linux/sync_file.h @@ -76,6 +76,27 @@ struct sync_file_info { __u64 sync_fence_info; }; +/** + * struct sync_set_deadline - SYNC_IOC_SET_DEADLINE - set a deadline hint on a fence + * @deadline_ns: absolute time of the deadline + * @pad: must be zero + * + * Allows userspace to set a deadline on a fence, see &dma_fence_set_deadline + * + * The timebase for the deadline is CLOCK_MONOTONIC (same as vblank). For + * example + * + * clock_gettime(CLOCK_MONOTONIC, &t); + * deadline_ns = (t.tv_sec * 1000000000L) + t.tv_nsec + ns_until_deadline + */ +struct sync_set_deadline { + __u64 deadline_ns; + /* Not strictly needed for alignment but gives some possibility + * for future extension: + */ + __u64 pad; +}; + #define SYNC_IOC_MAGIC '>' /* @@ -87,5 +108,6 @@ struct sync_file_info { #define SYNC_IOC_MERGE _IOWR(SYNC_IOC_MAGIC, 3, struct sync_merge_data) #define SYNC_IOC_FILE_INFO _IOWR(SYNC_IOC_MAGIC, 4, struct sync_file_info) +#define SYNC_IOC_SET_DEADLINE _IOW(SYNC_IOC_MAGIC, 5, struct sync_set_deadline) #endif /* _UAPI_LINUX_SYNC_H */ -- cgit From c55e0a55b165202f18cbc4a20650d2e1becd5507 Mon Sep 17 00:00:00 2001 From: Tyler Fanelli Date: Tue, 19 Sep 2023 22:40:00 -0400 Subject: fuse: Rename DIRECT_IO_RELAX to DIRECT_IO_ALLOW_MMAP Although DIRECT_IO_RELAX's initial usage is to allow shared mmap, its description indicates a purpose of reducing memory footprint. This may imply that it could be further used to relax other DIRECT_IO operations in the future. Replace it with a flag DIRECT_IO_ALLOW_MMAP which does only one thing, allow shared mmap of DIRECT_IO files while still bypassing the cache on regular reads and writes. [Miklos] Also Keep DIRECT_IO_RELAX definition for backward compatibility. Signed-off-by: Tyler Fanelli Fixes: e78662e818f9 ("fuse: add a new fuse init flag to relax restrictions in no cache mode") Cc: # v6.6 Signed-off-by: Miklos Szeredi --- fs/fuse/file.c | 6 +++--- fs/fuse/fuse_i.h | 4 ++-- fs/fuse/inode.c | 6 +++--- include/uapi/linux/fuse.h | 10 ++++++---- 4 files changed, 14 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 1cdb6327511e..89e870d1a526 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1448,7 +1448,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, if (!ia) return -ENOMEM; - if (fopen_direct_io && fc->direct_io_relax) { + if (fopen_direct_io && fc->direct_io_allow_mmap) { res = filemap_write_and_wait_range(mapping, pos, pos + count - 1); if (res) { fuse_io_free(ia); @@ -2466,9 +2466,9 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) if (ff->open_flags & FOPEN_DIRECT_IO) { /* Can't provide the coherency needed for MAP_SHARED - * if FUSE_DIRECT_IO_RELAX isn't set. + * if FUSE_DIRECT_IO_ALLOW_MMAP isn't set. */ - if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_relax) + if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_allow_mmap) return -ENODEV; invalidate_inode_pages2(file->f_mapping); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 6e6e721f421b..69bcffaf4832 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -797,8 +797,8 @@ struct fuse_conn { /* Is tmpfile not implemented by fs? */ unsigned int no_tmpfile:1; - /* relax restrictions in FOPEN_DIRECT_IO mode */ - unsigned int direct_io_relax:1; + /* Relax restrictions to allow shared mmap in FOPEN_DIRECT_IO mode */ + unsigned int direct_io_allow_mmap:1; /* Is statx not implemented by fs? */ unsigned int no_statx:1; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 74d4f09d5827..88090c6026a7 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1230,8 +1230,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, fc->init_security = 1; if (flags & FUSE_CREATE_SUPP_GROUP) fc->create_supp_group = 1; - if (flags & FUSE_DIRECT_IO_RELAX) - fc->direct_io_relax = 1; + if (flags & FUSE_DIRECT_IO_ALLOW_MMAP) + fc->direct_io_allow_mmap = 1; } else { ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; @@ -1278,7 +1278,7 @@ void fuse_send_init(struct fuse_mount *fm) FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA | FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT | FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP | - FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_RELAX; + FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP; #ifdef CONFIG_FUSE_DAX if (fm->fc->dax) flags |= FUSE_MAP_ALIGNMENT; diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index db92a7202b34..e7418d15fe39 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -209,7 +209,7 @@ * - add FUSE_HAS_EXPIRE_ONLY * * 7.39 - * - add FUSE_DIRECT_IO_RELAX + * - add FUSE_DIRECT_IO_ALLOW_MMAP * - add FUSE_STATX and related structures */ @@ -409,8 +409,7 @@ struct fuse_file_lock { * FUSE_CREATE_SUPP_GROUP: add supplementary group info to create, mkdir, * symlink and mknod (single group that matches parent) * FUSE_HAS_EXPIRE_ONLY: kernel supports expiry-only entry invalidation - * FUSE_DIRECT_IO_RELAX: relax restrictions in FOPEN_DIRECT_IO mode, for now - * allow shared mmap + * FUSE_DIRECT_IO_ALLOW_MMAP: allow shared mmap in FOPEN_DIRECT_IO mode. */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -449,7 +448,10 @@ struct fuse_file_lock { #define FUSE_HAS_INODE_DAX (1ULL << 33) #define FUSE_CREATE_SUPP_GROUP (1ULL << 34) #define FUSE_HAS_EXPIRE_ONLY (1ULL << 35) -#define FUSE_DIRECT_IO_RELAX (1ULL << 36) +#define FUSE_DIRECT_IO_ALLOW_MMAP (1ULL << 36) + +/* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */ +#define FUSE_DIRECT_IO_RELAX FUSE_DIRECT_IO_ALLOW_MMAP /** * CUSE INIT request/reply flags -- cgit From 0d9e32a8075a6cccbab294f98ccf7d33821d9b1c Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Fri, 24 Nov 2023 16:26:24 +0200 Subject: media: uapi: Add controls for the THP7312 ISP The THP7312 is an external ISP from THine. As such, it implements a large number of parameters to control all aspects of the image processing. Many of those controls are already standard in V4L2, but some are fairly device-specific. Reserve a range of 32 controls for the device. The driver will implement 4 device-specific controls to start with, define and document them. 28 additional device-specific controls should be enough for future development. Co-developed-by: Paul Elder Signed-off-by: Paul Elder Signed-off-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- .../userspace-api/media/drivers/index.rst | 1 + .../userspace-api/media/drivers/thp7312.rst | 39 ++++++++++++++++++++++ MAINTAINERS | 2 ++ include/uapi/linux/thp7312.h | 19 +++++++++++ include/uapi/linux/v4l2-controls.h | 6 ++++ 5 files changed, 67 insertions(+) create mode 100644 Documentation/userspace-api/media/drivers/thp7312.rst create mode 100644 include/uapi/linux/thp7312.h (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/drivers/index.rst b/Documentation/userspace-api/media/drivers/index.rst index 1726f8ec86fa..6b62c818899f 100644 --- a/Documentation/userspace-api/media/drivers/index.rst +++ b/Documentation/userspace-api/media/drivers/index.rst @@ -41,4 +41,5 @@ For more details see the file COPYING in the source distribution of Linux. npcm-video omap3isp-uapi st-vgxy61 + thp7312 uvcvideo diff --git a/Documentation/userspace-api/media/drivers/thp7312.rst b/Documentation/userspace-api/media/drivers/thp7312.rst new file mode 100644 index 000000000000..7c777e6fb7d2 --- /dev/null +++ b/Documentation/userspace-api/media/drivers/thp7312.rst @@ -0,0 +1,39 @@ +.. SPDX-License-Identifier: GPL-2.0-only + +THine THP7312 ISP driver +======================== + +The THP7312 driver implements the following driver-specific controls: + +``V4L2_CID_THP7312_LOW_LIGHT_COMPENSATION`` + Enable/Disable auto-adjustment, based on lighting conditions, of the frame + rate when auto-exposure is enabled. + +``V4L2_CID_THP7312_AUTO_FOCUS_METHOD`` + Set method of auto-focus. Only takes effect when auto-focus is enabled. + + .. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 4 + + * - ``0`` + - Contrast-based auto-focus + * - ``1`` + - PDAF + * - ``2`` + - Hybrid of contrast-based and PDAF + + Supported values for the control depend on the camera sensor module + connected to the THP7312. If the module doesn't have a focus lens actuator, + this control will not be exposed by the THP7312 driver. If the module has a + controllable focus lens but the sensor doesn't support PDAF, only the + contrast-based auto-focus value will be valid. Otherwise all values for the + controls will be supported. + +``V4L2_CID_THP7312_NOISE_REDUCTION_AUTO`` + Enable/Disable auto noise reduction. + +``V4L2_CID_THP7312_NOISE_REDUCTION_ABSOLUTE`` + Set the noise reduction strength, where 0 is the weakest and 10 is the + strongest. diff --git a/MAINTAINERS b/MAINTAINERS index 6d20dc6f617c..c4468f6a4cb2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -21670,6 +21670,8 @@ L: linux-media@vger.kernel.org S: Maintained T: git git://linuxtv.org/media_tree.git F: Documentation/devicetree/bindings/media/i2c/thine,thp7312.yaml +F: Documentation/userspace-api/media/drivers/thp7312.rst +F: include/uapi/linux/thp7312.h THUNDERBOLT DMA TRAFFIC TEST DRIVER M: Isaac Hazan diff --git a/include/uapi/linux/thp7312.h b/include/uapi/linux/thp7312.h new file mode 100644 index 000000000000..2b629e05daf9 --- /dev/null +++ b/include/uapi/linux/thp7312.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * THine THP7312 user space header file. + * + * Copyright (C) 2021 THine Electronics, Inc. + * Copyright (C) 2023 Ideas on Board Oy + */ + +#ifndef __UAPI_THP7312_H_ +#define __UAPI_THP7312_H_ + +#include + +#define V4L2_CID_THP7312_LOW_LIGHT_COMPENSATION (V4L2_CID_USER_THP7312_BASE + 0x01) +#define V4L2_CID_THP7312_AUTO_FOCUS_METHOD (V4L2_CID_USER_THP7312_BASE + 0x02) +#define V4L2_CID_THP7312_NOISE_REDUCTION_AUTO (V4L2_CID_USER_THP7312_BASE + 0x03) +#define V4L2_CID_THP7312_NOISE_REDUCTION_ABSOLUTE (V4L2_CID_USER_THP7312_BASE + 0x04) + +#endif /* __UAPI_THP7312_H_ */ diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 68db66d4aae8..99c3f5e99da7 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -209,6 +209,12 @@ enum v4l2_colorfx { */ #define V4L2_CID_USER_NPCM_BASE (V4L2_CID_USER_BASE + 0x11b0) +/* + * The base for THine THP7312 driver controls. + * We reserve 32 controls for this driver. + */ +#define V4L2_CID_USER_THP7312_BASE (V4L2_CID_USER_BASE + 0x11c0) + /* MPEG-class control IDs */ /* The MPEG controls are applicable to all codec controls * and the 'MPEG' part of the define is historical */ -- cgit From 2112f3a28e8d9d1e2faaa32d124b450bde055b72 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Mon, 23 Oct 2023 21:19:22 +0300 Subject: media: v4l2-subdev: Fix indentation in v4l2-subdev.h Fix a simple indentation issue in the v4l2-subdev.h header. Fixes: f57fa2959244 ("media: v4l2-subdev: Add new ioctl for client capabilities") Signed-off-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- include/uapi/linux/v4l2-subdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h index b383c2fe0cf3..f0fbb4a7c150 100644 --- a/include/uapi/linux/v4l2-subdev.h +++ b/include/uapi/linux/v4l2-subdev.h @@ -239,7 +239,7 @@ struct v4l2_subdev_routing { * set (which is the default), the 'stream' fields will be forced to 0 by the * kernel. */ - #define V4L2_SUBDEV_CLIENT_CAP_STREAMS (1ULL << 0) +#define V4L2_SUBDEV_CLIENT_CAP_STREAMS (1ULL << 0) /** * struct v4l2_subdev_client_capability - Capabilities of the client accessing -- cgit From b89710bd215e650f0aaf8ffe7104413d46d44392 Mon Sep 17 00:00:00 2001 From: Javier Carrasco Date: Mon, 27 Nov 2023 18:34:28 +0100 Subject: iio: add modifiers for A and B ultraviolet light Currently there are only two modifiers for ultraviolet light: a generic one for any ultraviolet light (IIO_MOD_LIGHT_UV) and one for deep ultraviolet (IIO_MOD_LIGHT_DUV), which is also referred as ultraviolet C (UV-C) band and covers short-wave ultraviolet. There are still no modifiers for the long-wave and medium-wave ultraviolet bands. These two bands are the main components used to obtain the UV index on the Earth's surface. Add modifiers for the ultraviolet A (UV-A) and ultraviolet B (UV-B) bands. Signed-off-by: Javier Carrasco Link: https://lore.kernel.org/r/20231110-veml6075-v3-1-6ee46775b422@gmail.com Signed-off-by: Jonathan Cameron --- Documentation/ABI/testing/sysfs-bus-iio | 7 +++++-- drivers/iio/industrialio-core.c | 2 ++ include/uapi/linux/iio/types.h | 2 ++ tools/iio/iio_event_monitor.c | 2 ++ 4 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index 0eadc08c3a13..0d3ec5fc45f2 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -1574,6 +1574,8 @@ What: /sys/.../iio:deviceX/in_intensityY_raw What: /sys/.../iio:deviceX/in_intensityY_ir_raw What: /sys/.../iio:deviceX/in_intensityY_both_raw What: /sys/.../iio:deviceX/in_intensityY_uv_raw +What: /sys/.../iio:deviceX/in_intensityY_uva_raw +What: /sys/.../iio:deviceX/in_intensityY_uvb_raw What: /sys/.../iio:deviceX/in_intensityY_duv_raw KernelVersion: 3.4 Contact: linux-iio@vger.kernel.org @@ -1582,8 +1584,9 @@ Description: that measurements contain visible and infrared light components or just infrared light, respectively. Modifier uv indicates that measurements contain ultraviolet light - components. Modifier duv indicates that measurements - contain deep ultraviolet light components. + components. Modifiers uva, uvb and duv indicate that + measurements contain A, B or deep (C) ultraviolet light + components respectively. What: /sys/.../iio:deviceX/in_uvindex_input KernelVersion: 4.6 diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 34e1f8d0071c..f6a123d397db 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -117,6 +117,8 @@ static const char * const iio_modifier_names[] = { [IIO_MOD_LIGHT_GREEN] = "green", [IIO_MOD_LIGHT_BLUE] = "blue", [IIO_MOD_LIGHT_UV] = "uv", + [IIO_MOD_LIGHT_UVA] = "uva", + [IIO_MOD_LIGHT_UVB] = "uvb", [IIO_MOD_LIGHT_DUV] = "duv", [IIO_MOD_QUATERNION] = "quaternion", [IIO_MOD_TEMP_AMBIENT] = "ambient", diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index 9c2ffdcd6623..5060963707b1 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -91,6 +91,8 @@ enum iio_modifier { IIO_MOD_CO2, IIO_MOD_VOC, IIO_MOD_LIGHT_UV, + IIO_MOD_LIGHT_UVA, + IIO_MOD_LIGHT_UVB, IIO_MOD_LIGHT_DUV, IIO_MOD_PM1, IIO_MOD_PM2P5, diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c index 2eaaa7123b04..8073c9e4fe46 100644 --- a/tools/iio/iio_event_monitor.c +++ b/tools/iio/iio_event_monitor.c @@ -105,6 +105,8 @@ static const char * const iio_modifier_names[] = { [IIO_MOD_LIGHT_GREEN] = "green", [IIO_MOD_LIGHT_BLUE] = "blue", [IIO_MOD_LIGHT_UV] = "uv", + [IIO_MOD_LIGHT_UVA] = "uva", + [IIO_MOD_LIGHT_UVB] = "uvb", [IIO_MOD_LIGHT_DUV] = "duv", [IIO_MOD_QUATERNION] = "quaternion", [IIO_MOD_TEMP_AMBIENT] = "ambient", -- cgit From 2202844e4468c7539dba0c0b06577c93735af952 Mon Sep 17 00:00:00 2001 From: Longfang Liu Date: Mon, 6 Nov 2023 15:22:23 +0800 Subject: vfio/migration: Add debugfs to live migration driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are multiple devices, software and operational steps involved in the process of live migration. An error occurred on any node may cause the live migration operation to fail. This complex process makes it very difficult to locate and analyze the cause when the function fails. In order to quickly locate the cause of the problem when the live migration fails, I added a set of debugfs to the vfio live migration driver. +-------------------------------------------+ | | | | | QEMU | | | | | +---+----------------------------+----------+ | ^ | ^ | | | | | | | | v | v | +---------+--+ +---------+--+ |src vfio_dev| |dst vfio_dev| +--+---------+ +--+---------+ | ^ | ^ | | | | v | | | +-----------+----+ +-----------+----+ |src dev debugfs | |dst dev debugfs | +----------------+ +----------------+ The entire debugfs directory will be based on the definition of the CONFIG_DEBUG_FS macro. If this macro is not enabled, the interfaces in vfio.h will be empty definitions, and the creation and initialization of the debugfs directory will not be executed. vfio | +--- | +---migration | +--state | +--- +---migration +--state debugfs will create a public root directory "vfio" file. then create a dev_name() file for each live migration device. First, create a unified state acquisition file of "migration" in this device directory. Then, create a public live migration state lookup file "state". Signed-off-by: Longfang Liu Reviewed-by: Cédric Le Goater Link: https://lore.kernel.org/r/20231106072225.28577-2-liulongfang@huawei.com Signed-off-by: Alex Williamson --- drivers/vfio/Kconfig | 10 ++++++ drivers/vfio/Makefile | 1 + drivers/vfio/debugfs.c | 92 +++++++++++++++++++++++++++++++++++++++++++++++ drivers/vfio/vfio.h | 14 ++++++++ drivers/vfio/vfio_main.c | 4 +++ include/linux/vfio.h | 7 ++++ include/uapi/linux/vfio.h | 1 + 7 files changed, 129 insertions(+) create mode 100644 drivers/vfio/debugfs.c (limited to 'include/uapi/linux') diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig index 6bda6dbb4878..ceae52fd7586 100644 --- a/drivers/vfio/Kconfig +++ b/drivers/vfio/Kconfig @@ -80,6 +80,16 @@ config VFIO_VIRQFD select EVENTFD default n +config VFIO_DEBUGFS + bool "Export VFIO internals in DebugFS" + depends on DEBUG_FS + help + Allows exposure of VFIO device internals. This option enables + the use of debugfs by VFIO drivers as required. The device can + cause the VFIO code create a top-level debug/vfio directory + during initialization, and then populate a subdirectory with + entries as required. + source "drivers/vfio/pci/Kconfig" source "drivers/vfio/platform/Kconfig" source "drivers/vfio/mdev/Kconfig" diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile index 68c05705200f..b2fc9fb499d8 100644 --- a/drivers/vfio/Makefile +++ b/drivers/vfio/Makefile @@ -7,6 +7,7 @@ vfio-$(CONFIG_VFIO_GROUP) += group.o vfio-$(CONFIG_IOMMUFD) += iommufd.o vfio-$(CONFIG_VFIO_CONTAINER) += container.o vfio-$(CONFIG_VFIO_VIRQFD) += virqfd.o +vfio-$(CONFIG_VFIO_DEBUGFS) += debugfs.o obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o diff --git a/drivers/vfio/debugfs.c b/drivers/vfio/debugfs.c new file mode 100644 index 000000000000..298bd866f157 --- /dev/null +++ b/drivers/vfio/debugfs.c @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2023, HiSilicon Ltd. + */ + +#include +#include +#include +#include +#include "vfio.h" + +static struct dentry *vfio_debugfs_root; + +static int vfio_device_state_read(struct seq_file *seq, void *data) +{ + struct device *vf_dev = seq->private; + struct vfio_device *vdev = container_of(vf_dev, + struct vfio_device, device); + enum vfio_device_mig_state state; + int ret; + + BUILD_BUG_ON(VFIO_DEVICE_STATE_NR != + VFIO_DEVICE_STATE_PRE_COPY_P2P + 1); + + ret = vdev->mig_ops->migration_get_state(vdev, &state); + if (ret) + return -EINVAL; + + switch (state) { + case VFIO_DEVICE_STATE_ERROR: + seq_puts(seq, "ERROR\n"); + break; + case VFIO_DEVICE_STATE_STOP: + seq_puts(seq, "STOP\n"); + break; + case VFIO_DEVICE_STATE_RUNNING: + seq_puts(seq, "RUNNING\n"); + break; + case VFIO_DEVICE_STATE_STOP_COPY: + seq_puts(seq, "STOP_COPY\n"); + break; + case VFIO_DEVICE_STATE_RESUMING: + seq_puts(seq, "RESUMING\n"); + break; + case VFIO_DEVICE_STATE_RUNNING_P2P: + seq_puts(seq, "RUNNING_P2P\n"); + break; + case VFIO_DEVICE_STATE_PRE_COPY: + seq_puts(seq, "PRE_COPY\n"); + break; + case VFIO_DEVICE_STATE_PRE_COPY_P2P: + seq_puts(seq, "PRE_COPY_P2P\n"); + break; + default: + seq_puts(seq, "Invalid\n"); + } + + return 0; +} + +void vfio_device_debugfs_init(struct vfio_device *vdev) +{ + struct device *dev = &vdev->device; + + vdev->debug_root = debugfs_create_dir(dev_name(vdev->dev), + vfio_debugfs_root); + + if (vdev->mig_ops) { + struct dentry *vfio_dev_migration = NULL; + + vfio_dev_migration = debugfs_create_dir("migration", + vdev->debug_root); + debugfs_create_devm_seqfile(dev, "state", vfio_dev_migration, + vfio_device_state_read); + } +} + +void vfio_device_debugfs_exit(struct vfio_device *vdev) +{ + debugfs_remove_recursive(vdev->debug_root); +} + +void vfio_debugfs_create_root(void) +{ + vfio_debugfs_root = debugfs_create_dir("vfio", NULL); +} + +void vfio_debugfs_remove_root(void) +{ + debugfs_remove_recursive(vfio_debugfs_root); + vfio_debugfs_root = NULL; +} diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h index 307e3f29b527..bde84ad344e5 100644 --- a/drivers/vfio/vfio.h +++ b/drivers/vfio/vfio.h @@ -448,4 +448,18 @@ static inline void vfio_device_put_kvm(struct vfio_device *device) } #endif +#ifdef CONFIG_VFIO_DEBUGFS +void vfio_debugfs_create_root(void); +void vfio_debugfs_remove_root(void); + +void vfio_device_debugfs_init(struct vfio_device *vdev); +void vfio_device_debugfs_exit(struct vfio_device *vdev); +#else +static inline void vfio_debugfs_create_root(void) { } +static inline void vfio_debugfs_remove_root(void) { } + +static inline void vfio_device_debugfs_init(struct vfio_device *vdev) { } +static inline void vfio_device_debugfs_exit(struct vfio_device *vdev) { } +#endif /* CONFIG_VFIO_DEBUGFS */ + #endif diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index 8d4995ada74a..1cc93aac99a2 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -311,6 +311,7 @@ static int __vfio_register_dev(struct vfio_device *device, refcount_set(&device->refcount, 1); vfio_device_group_register(device); + vfio_device_debugfs_init(device); return 0; err_out: @@ -378,6 +379,7 @@ void vfio_unregister_group_dev(struct vfio_device *device) } } + vfio_device_debugfs_exit(device); /* Balances vfio_device_set_group in register path */ vfio_device_remove_group(device); } @@ -1676,6 +1678,7 @@ static int __init vfio_init(void) if (ret) goto err_alloc_dev_chrdev; + vfio_debugfs_create_root(); pr_info(DRIVER_DESC " version: " DRIVER_VERSION "\n"); return 0; @@ -1691,6 +1694,7 @@ err_virqfd: static void __exit vfio_cleanup(void) { + vfio_debugfs_remove_root(); ida_destroy(&vfio.device_ida); vfio_cdev_cleanup(); class_destroy(vfio.device_class); diff --git a/include/linux/vfio.h b/include/linux/vfio.h index a65b2513f8cd..89b265bc6ec3 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -69,6 +69,13 @@ struct vfio_device { u8 iommufd_attached:1; #endif u8 cdev_opened:1; +#ifdef CONFIG_DEBUG_FS + /* + * debug_root is a static property of the vfio_device + * which must be set prior to registering the vfio_device. + */ + struct dentry *debug_root; +#endif }; /** diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 7f5fb010226d..2b68e6cdf190 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1219,6 +1219,7 @@ enum vfio_device_mig_state { VFIO_DEVICE_STATE_RUNNING_P2P = 5, VFIO_DEVICE_STATE_PRE_COPY = 6, VFIO_DEVICE_STATE_PRE_COPY_P2P = 7, + VFIO_DEVICE_STATE_NR, }; /** -- cgit From 91051f003948432f83b5d2766eeb83b2b4993649 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 1 Dec 2023 15:49:52 +0100 Subject: tcp: Dump bound-only sockets in inet_diag. Walk the hashinfo->bhash2 table so that inet_diag can dump TCP sockets that are bound but haven't yet called connect() or listen(). The code is inspired by the ->lhash2 loop. However there's no manual test of the source port, since this kind of filtering is already handled by inet_diag_bc_sk(). Also, a maximum of 16 sockets are dumped at a time, to avoid running with bh disabled for too long. There's no TCP state for bound but otherwise inactive sockets. Such sockets normally map to TCP_CLOSE. However, "ss -l", which is supposed to only dump listening sockets, actually requests the kernel to dump sockets in either the TCP_LISTEN or TCP_CLOSE states. To avoid dumping bound-only sockets with "ss -l", we therefore need to define a new pseudo-state (TCP_BOUND_INACTIVE) that user space will be able to set explicitly. With an IPv4, an IPv6 and an IPv6-only socket, bound respectively to 40000, 64000, 60000, an updated version of iproute2 could work as follow: $ ss -t state bound-inactive Recv-Q Send-Q Local Address:Port Peer Address:Port Process 0 0 0.0.0.0:40000 0.0.0.0:* 0 0 [::]:60000 [::]:* 0 0 *:64000 *:* Reviewed-by: Eric Dumazet Signed-off-by: Guillaume Nault Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/b3a84ae61e19c06806eea9c602b3b66e8f0cfc81.1701362867.git.gnault@redhat.com Signed-off-by: Jakub Kicinski --- include/net/tcp_states.h | 2 ++ include/uapi/linux/bpf.h | 1 + net/ipv4/inet_diag.c | 86 +++++++++++++++++++++++++++++++++++++++++++++++- net/ipv4/tcp.c | 1 + 4 files changed, 89 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/net/tcp_states.h b/include/net/tcp_states.h index cc00118acca1..d60e8148ff4c 100644 --- a/include/net/tcp_states.h +++ b/include/net/tcp_states.h @@ -22,6 +22,7 @@ enum { TCP_LISTEN, TCP_CLOSING, /* Now a valid state */ TCP_NEW_SYN_RECV, + TCP_BOUND_INACTIVE, /* Pseudo-state for inet_diag */ TCP_MAX_STATES /* Leave at the end! */ }; @@ -43,6 +44,7 @@ enum { TCPF_LISTEN = (1 << TCP_LISTEN), TCPF_CLOSING = (1 << TCP_CLOSING), TCPF_NEW_SYN_RECV = (1 << TCP_NEW_SYN_RECV), + TCPF_BOUND_INACTIVE = (1 << TCP_BOUND_INACTIVE), }; #endif /* _LINUX_TCP_STATES_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e88746ba7d21..b1e8c5bdfc82 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6902,6 +6902,7 @@ enum { BPF_TCP_LISTEN, BPF_TCP_CLOSING, /* Now a valid state */ BPF_TCP_NEW_SYN_RECV, + BPF_TCP_BOUND_INACTIVE, BPF_TCP_MAX_STATES /* Leave at the end! */ }; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 7d0e7aaa71e0..46b13962ad02 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -1077,10 +1077,94 @@ skip_listen_ht: s_i = num = s_num = 0; } +/* Process a maximum of SKARR_SZ sockets at a time when walking hash buckets + * with bh disabled. + */ +#define SKARR_SZ 16 + + /* Dump bound but inactive (not listening, connecting, etc.) sockets */ + if (cb->args[0] == 1) { + if (!(idiag_states & TCPF_BOUND_INACTIVE)) + goto skip_bind_ht; + + for (i = s_i; i < hashinfo->bhash_size; i++) { + struct inet_bind_hashbucket *ibb; + struct inet_bind2_bucket *tb2; + struct sock *sk_arr[SKARR_SZ]; + int num_arr[SKARR_SZ]; + int idx, accum, res; + +resume_bind_walk: + num = 0; + accum = 0; + ibb = &hashinfo->bhash2[i]; + + spin_lock_bh(&ibb->lock); + inet_bind_bucket_for_each(tb2, &ibb->chain) { + if (!net_eq(ib2_net(tb2), net)) + continue; + + sk_for_each_bound_bhash2(sk, &tb2->owners) { + struct inet_sock *inet = inet_sk(sk); + + if (num < s_num) + goto next_bind; + + if (sk->sk_state != TCP_CLOSE || + !inet->inet_num) + goto next_bind; + + if (r->sdiag_family != AF_UNSPEC && + r->sdiag_family != sk->sk_family) + goto next_bind; + + if (!inet_diag_bc_sk(bc, sk)) + goto next_bind; + + sock_hold(sk); + num_arr[accum] = num; + sk_arr[accum] = sk; + if (++accum == SKARR_SZ) + goto pause_bind_walk; +next_bind: + num++; + } + } +pause_bind_walk: + spin_unlock_bh(&ibb->lock); + + res = 0; + for (idx = 0; idx < accum; idx++) { + if (res >= 0) { + res = inet_sk_diag_fill(sk_arr[idx], + NULL, skb, cb, + r, NLM_F_MULTI, + net_admin); + if (res < 0) + num = num_arr[idx]; + } + sock_put(sk_arr[idx]); + } + if (res < 0) + goto done; + + cond_resched(); + + if (accum == SKARR_SZ) { + s_num = num + 1; + goto resume_bind_walk; + } + + s_num = 0; + } +skip_bind_ht: + cb->args[0] = 2; + s_i = num = s_num = 0; + } + if (!(idiag_states & ~TCPF_LISTEN)) goto out; -#define SKARR_SZ 16 for (i = s_i; i <= hashinfo->ehash_mask; i++) { struct inet_ehash_bucket *head = &hashinfo->ehash[i]; spinlock_t *lock = inet_ehash_lockp(hashinfo, i); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 53bcc17c91e4..a100df07d34a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2605,6 +2605,7 @@ void tcp_set_state(struct sock *sk, int state) BUILD_BUG_ON((int)BPF_TCP_LISTEN != (int)TCP_LISTEN); BUILD_BUG_ON((int)BPF_TCP_CLOSING != (int)TCP_CLOSING); BUILD_BUG_ON((int)BPF_TCP_NEW_SYN_RECV != (int)TCP_NEW_SYN_RECV); + BUILD_BUG_ON((int)BPF_TCP_BOUND_INACTIVE != (int)TCP_BOUND_INACTIVE); BUILD_BUG_ON((int)BPF_TCP_MAX_STATES != (int)TCP_MAX_STATES); /* bpf uapi header bpf.h defines an anonymous enum with values -- cgit From bc877956272f0521fef107838555817112a450dc Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Fri, 1 Dec 2023 15:28:29 -0800 Subject: netdev-genl: spec: Extend netdev netlink spec in YAML for queue Add support in netlink spec(netdev.yaml) for queue information. Add code generated from the spec. Note: The "queue-type" attribute takes values 0 and 1 for rx and tx queue type respectively. Signed-off-by: Amritha Nambiar Reviewed-by: Sridhar Samudrala Link: https://lore.kernel.org/r/170147330963.5260.2576294626647300472.stgit@anambiarhost.jf.intel.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/netdev.yaml | 52 +++++++++++ include/uapi/linux/netdev.h | 16 ++++ net/core/netdev-genl-gen.c | 26 ++++++ net/core/netdev-genl-gen.h | 3 + net/core/netdev-genl.c | 10 +++ tools/include/uapi/linux/netdev.h | 16 ++++ tools/net/ynl/generated/netdev-user.c | 153 ++++++++++++++++++++++++++++++++ tools/net/ynl/generated/netdev-user.h | 99 +++++++++++++++++++++ 8 files changed, 375 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index eef6358ec587..719e6aafbfdb 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -66,6 +66,10 @@ definitions: name: tx-checksum doc: L3 checksum HW offload is supported by the driver. + - + name: queue-type + type: enum + entries: [ rx, tx ] attribute-sets: - @@ -209,6 +213,31 @@ attribute-sets: name: recycle-released-refcnt type: uint + - + name: queue + attributes: + - + name: id + doc: Queue index; most queue types are indexed like a C array, with + indexes starting at 0 and ending at queue count - 1. Queue indexes + are scoped to an interface and queue type. + type: u32 + - + name: ifindex + doc: ifindex of the netdevice to which the queue belongs. + type: u32 + checks: + min: 1 + - + name: type + doc: Queue type as rx, tx. Each queue type defines a separate ID space. + type: u32 + enum: queue-type + - + name: napi-id + doc: ID of the NAPI instance which services this queue. + type: u32 + operations: list: - @@ -307,6 +336,29 @@ operations: dump: reply: *pp-stats-reply config-cond: page-pool-stats + - + name: queue-get + doc: Get queue information from the kernel. + Only configured queues will be reported (as opposed to all available + hardware queues). + attribute-set: queue + do: + request: + attributes: + - ifindex + - type + - id + reply: &queue-get-op + attributes: + - id + - type + - napi-id + - ifindex + dump: + request: + attributes: + - ifindex + reply: *queue-get-op mcast-groups: list: diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 6244c0164976..f857960a7f06 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -62,6 +62,11 @@ enum netdev_xsk_flags { NETDEV_XSK_FLAGS_TX_CHECKSUM = 2, }; +enum netdev_queue_type { + NETDEV_QUEUE_TYPE_RX, + NETDEV_QUEUE_TYPE_TX, +}; + enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, @@ -104,6 +109,16 @@ enum { NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1) }; +enum { + NETDEV_A_QUEUE_ID = 1, + NETDEV_A_QUEUE_IFINDEX, + NETDEV_A_QUEUE_TYPE, + NETDEV_A_QUEUE_NAPI_ID, + + __NETDEV_A_QUEUE_MAX, + NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) +}; + enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, @@ -114,6 +129,7 @@ enum { NETDEV_CMD_PAGE_POOL_DEL_NTF, NETDEV_CMD_PAGE_POOL_CHANGE_NTF, NETDEV_CMD_PAGE_POOL_STATS_GET, + NETDEV_CMD_QUEUE_GET, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index dccd8c3a141e..b1dcf88c82cf 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -46,6 +46,18 @@ static const struct nla_policy netdev_page_pool_stats_get_nl_policy[NETDEV_A_PAG }; #endif /* CONFIG_PAGE_POOL_STATS */ +/* NETDEV_CMD_QUEUE_GET - do */ +static const struct nla_policy netdev_queue_get_do_nl_policy[NETDEV_A_QUEUE_TYPE + 1] = { + [NETDEV_A_QUEUE_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), + [NETDEV_A_QUEUE_TYPE] = NLA_POLICY_MAX(NLA_U32, 1), + [NETDEV_A_QUEUE_ID] = { .type = NLA_U32, }, +}; + +/* NETDEV_CMD_QUEUE_GET - dump */ +static const struct nla_policy netdev_queue_get_dump_nl_policy[NETDEV_A_QUEUE_IFINDEX + 1] = { + [NETDEV_A_QUEUE_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), +}; + /* Ops table for netdev */ static const struct genl_split_ops netdev_nl_ops[] = { { @@ -88,6 +100,20 @@ static const struct genl_split_ops netdev_nl_ops[] = { .flags = GENL_CMD_CAP_DUMP, }, #endif /* CONFIG_PAGE_POOL_STATS */ + { + .cmd = NETDEV_CMD_QUEUE_GET, + .doit = netdev_nl_queue_get_doit, + .policy = netdev_queue_get_do_nl_policy, + .maxattr = NETDEV_A_QUEUE_TYPE, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = NETDEV_CMD_QUEUE_GET, + .dumpit = netdev_nl_queue_get_dumpit, + .policy = netdev_queue_get_dump_nl_policy, + .maxattr = NETDEV_A_QUEUE_IFINDEX, + .flags = GENL_CMD_CAP_DUMP, + }, }; static const struct genl_multicast_group netdev_nl_mcgrps[] = { diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index 649e4b46eccf..086623c1797a 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -23,6 +23,9 @@ int netdev_nl_page_pool_stats_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_page_pool_stats_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info); +int netdev_nl_queue_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); enum { NETDEV_NLGRP_MGMT, diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 10f2124e9e23..35e2d692f651 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -140,6 +140,16 @@ int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } +int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + return -EOPNOTSUPP; +} + +int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + return -EOPNOTSUPP; +} + static int netdev_genl_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 6244c0164976..f857960a7f06 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -62,6 +62,11 @@ enum netdev_xsk_flags { NETDEV_XSK_FLAGS_TX_CHECKSUM = 2, }; +enum netdev_queue_type { + NETDEV_QUEUE_TYPE_RX, + NETDEV_QUEUE_TYPE_TX, +}; + enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, @@ -104,6 +109,16 @@ enum { NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1) }; +enum { + NETDEV_A_QUEUE_ID = 1, + NETDEV_A_QUEUE_IFINDEX, + NETDEV_A_QUEUE_TYPE, + NETDEV_A_QUEUE_NAPI_ID, + + __NETDEV_A_QUEUE_MAX, + NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) +}; + enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, @@ -114,6 +129,7 @@ enum { NETDEV_CMD_PAGE_POOL_DEL_NTF, NETDEV_CMD_PAGE_POOL_CHANGE_NTF, NETDEV_CMD_PAGE_POOL_STATS_GET, + NETDEV_CMD_QUEUE_GET, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c index 3b9dee94d4ce..fbf7e24ade91 100644 --- a/tools/net/ynl/generated/netdev-user.c +++ b/tools/net/ynl/generated/netdev-user.c @@ -23,6 +23,7 @@ static const char * const netdev_op_strmap[] = { [NETDEV_CMD_PAGE_POOL_DEL_NTF] = "page-pool-del-ntf", [NETDEV_CMD_PAGE_POOL_CHANGE_NTF] = "page-pool-change-ntf", [NETDEV_CMD_PAGE_POOL_STATS_GET] = "page-pool-stats-get", + [NETDEV_CMD_QUEUE_GET] = "queue-get", }; const char *netdev_op_str(int op) @@ -76,6 +77,18 @@ const char *netdev_xsk_flags_str(enum netdev_xsk_flags value) return netdev_xsk_flags_strmap[value]; } +static const char * const netdev_queue_type_strmap[] = { + [0] = "rx", + [1] = "tx", +}; + +const char *netdev_queue_type_str(enum netdev_queue_type value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(netdev_queue_type_strmap)) + return NULL; + return netdev_queue_type_strmap[value]; +} + /* Policies */ struct ynl_policy_attr netdev_page_pool_info_policy[NETDEV_A_PAGE_POOL_MAX + 1] = { [NETDEV_A_PAGE_POOL_ID] = { .name = "id", .type = YNL_PT_UINT, }, @@ -135,6 +148,18 @@ struct ynl_policy_nest netdev_page_pool_stats_nest = { .table = netdev_page_pool_stats_policy, }; +struct ynl_policy_attr netdev_queue_policy[NETDEV_A_QUEUE_MAX + 1] = { + [NETDEV_A_QUEUE_ID] = { .name = "id", .type = YNL_PT_U32, }, + [NETDEV_A_QUEUE_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, }, + [NETDEV_A_QUEUE_TYPE] = { .name = "type", .type = YNL_PT_U32, }, + [NETDEV_A_QUEUE_NAPI_ID] = { .name = "napi-id", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest netdev_queue_nest = { + .max_attr = NETDEV_A_QUEUE_MAX, + .table = netdev_queue_policy, +}; + /* Common nested types */ void netdev_page_pool_info_free(struct netdev_page_pool_info *obj) { @@ -617,6 +642,134 @@ free_list: return NULL; } +/* ============== NETDEV_CMD_QUEUE_GET ============== */ +/* NETDEV_CMD_QUEUE_GET - do */ +void netdev_queue_get_req_free(struct netdev_queue_get_req *req) +{ + free(req); +} + +void netdev_queue_get_rsp_free(struct netdev_queue_get_rsp *rsp) +{ + free(rsp); +} + +int netdev_queue_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct netdev_queue_get_rsp *dst; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == NETDEV_A_QUEUE_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.id = 1; + dst->id = mnl_attr_get_u32(attr); + } else if (type == NETDEV_A_QUEUE_TYPE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.type = 1; + dst->type = mnl_attr_get_u32(attr); + } else if (type == NETDEV_A_QUEUE_NAPI_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.napi_id = 1; + dst->napi_id = mnl_attr_get_u32(attr); + } else if (type == NETDEV_A_QUEUE_IFINDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.ifindex = 1; + dst->ifindex = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct netdev_queue_get_rsp * +netdev_queue_get(struct ynl_sock *ys, struct netdev_queue_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct netdev_queue_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, NETDEV_CMD_QUEUE_GET, 1); + ys->req_policy = &netdev_queue_nest; + yrs.yarg.rsp_policy = &netdev_queue_nest; + + if (req->_present.ifindex) + mnl_attr_put_u32(nlh, NETDEV_A_QUEUE_IFINDEX, req->ifindex); + if (req->_present.type) + mnl_attr_put_u32(nlh, NETDEV_A_QUEUE_TYPE, req->type); + if (req->_present.id) + mnl_attr_put_u32(nlh, NETDEV_A_QUEUE_ID, req->id); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = netdev_queue_get_rsp_parse; + yrs.rsp_cmd = NETDEV_CMD_QUEUE_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + netdev_queue_get_rsp_free(rsp); + return NULL; +} + +/* NETDEV_CMD_QUEUE_GET - dump */ +void netdev_queue_get_list_free(struct netdev_queue_get_list *rsp) +{ + struct netdev_queue_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp); + } +} + +struct netdev_queue_get_list * +netdev_queue_get_dump(struct ynl_sock *ys, + struct netdev_queue_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct netdev_queue_get_list); + yds.cb = netdev_queue_get_rsp_parse; + yds.rsp_cmd = NETDEV_CMD_QUEUE_GET; + yds.rsp_policy = &netdev_queue_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, NETDEV_CMD_QUEUE_GET, 1); + ys->req_policy = &netdev_queue_nest; + + if (req->_present.ifindex) + mnl_attr_put_u32(nlh, NETDEV_A_QUEUE_IFINDEX, req->ifindex); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + netdev_queue_get_list_free(yds.first); + return NULL; +} + static const struct ynl_ntf_info netdev_ntf_info[] = { [NETDEV_CMD_DEV_ADD_NTF] = { .alloc_sz = sizeof(struct netdev_dev_get_ntf), diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h index cc3d80d1cf8c..d7daf6df3df0 100644 --- a/tools/net/ynl/generated/netdev-user.h +++ b/tools/net/ynl/generated/netdev-user.h @@ -20,6 +20,7 @@ const char *netdev_op_str(int op); const char *netdev_xdp_act_str(enum netdev_xdp_act value); const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value); const char *netdev_xsk_flags_str(enum netdev_xsk_flags value); +const char *netdev_queue_type_str(enum netdev_queue_type value); /* Common nested types */ struct netdev_page_pool_info { @@ -261,4 +262,102 @@ netdev_page_pool_stats_get_list_free(struct netdev_page_pool_stats_get_list *rsp struct netdev_page_pool_stats_get_list * netdev_page_pool_stats_get_dump(struct ynl_sock *ys); +/* ============== NETDEV_CMD_QUEUE_GET ============== */ +/* NETDEV_CMD_QUEUE_GET - do */ +struct netdev_queue_get_req { + struct { + __u32 ifindex:1; + __u32 type:1; + __u32 id:1; + } _present; + + __u32 ifindex; + enum netdev_queue_type type; + __u32 id; +}; + +static inline struct netdev_queue_get_req *netdev_queue_get_req_alloc(void) +{ + return calloc(1, sizeof(struct netdev_queue_get_req)); +} +void netdev_queue_get_req_free(struct netdev_queue_get_req *req); + +static inline void +netdev_queue_get_req_set_ifindex(struct netdev_queue_get_req *req, + __u32 ifindex) +{ + req->_present.ifindex = 1; + req->ifindex = ifindex; +} +static inline void +netdev_queue_get_req_set_type(struct netdev_queue_get_req *req, + enum netdev_queue_type type) +{ + req->_present.type = 1; + req->type = type; +} +static inline void +netdev_queue_get_req_set_id(struct netdev_queue_get_req *req, __u32 id) +{ + req->_present.id = 1; + req->id = id; +} + +struct netdev_queue_get_rsp { + struct { + __u32 id:1; + __u32 type:1; + __u32 napi_id:1; + __u32 ifindex:1; + } _present; + + __u32 id; + enum netdev_queue_type type; + __u32 napi_id; + __u32 ifindex; +}; + +void netdev_queue_get_rsp_free(struct netdev_queue_get_rsp *rsp); + +/* + * Get queue information from the kernel. Only configured queues will be reported (as opposed to all available hardware queues). + */ +struct netdev_queue_get_rsp * +netdev_queue_get(struct ynl_sock *ys, struct netdev_queue_get_req *req); + +/* NETDEV_CMD_QUEUE_GET - dump */ +struct netdev_queue_get_req_dump { + struct { + __u32 ifindex:1; + } _present; + + __u32 ifindex; +}; + +static inline struct netdev_queue_get_req_dump * +netdev_queue_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct netdev_queue_get_req_dump)); +} +void netdev_queue_get_req_dump_free(struct netdev_queue_get_req_dump *req); + +static inline void +netdev_queue_get_req_dump_set_ifindex(struct netdev_queue_get_req_dump *req, + __u32 ifindex) +{ + req->_present.ifindex = 1; + req->ifindex = ifindex; +} + +struct netdev_queue_get_list { + struct netdev_queue_get_list *next; + struct netdev_queue_get_rsp obj __attribute__((aligned(8))); +}; + +void netdev_queue_get_list_free(struct netdev_queue_get_list *rsp); + +struct netdev_queue_get_list * +netdev_queue_get_dump(struct ynl_sock *ys, + struct netdev_queue_get_req_dump *req); + #endif /* _LINUX_NETDEV_GEN_H */ -- cgit From ff9991499fb53575c45eb92cd064bcd7141bb572 Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Fri, 1 Dec 2023 15:28:51 -0800 Subject: netdev-genl: spec: Extend netdev netlink spec in YAML for NAPI Add support in netlink spec(netdev.yaml) for napi related information. Add code generated from the spec. Signed-off-by: Amritha Nambiar Reviewed-by: Sridhar Samudrala Link: https://lore.kernel.org/r/170147333119.5260.7050639053080529108.stgit@anambiarhost.jf.intel.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/netdev.yaml | 30 ++++++++ include/uapi/linux/netdev.h | 9 +++ net/core/netdev-genl-gen.c | 24 +++++++ net/core/netdev-genl-gen.h | 2 + net/core/netdev-genl.c | 10 +++ tools/include/uapi/linux/netdev.h | 9 +++ tools/net/ynl/generated/netdev-user.c | 124 ++++++++++++++++++++++++++++++++ tools/net/ynl/generated/netdev-user.h | 75 +++++++++++++++++++ 8 files changed, 283 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 719e6aafbfdb..76d6b2e15b67 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -213,6 +213,19 @@ attribute-sets: name: recycle-released-refcnt type: uint + - + name: napi + attributes: + - + name: ifindex + doc: ifindex of the netdevice to which NAPI instance belongs. + type: u32 + checks: + min: 1 + - + name: id + doc: ID of the NAPI instance. + type: u32 - name: queue attributes: @@ -359,6 +372,23 @@ operations: attributes: - ifindex reply: *queue-get-op + - + name: napi-get + doc: Get information about NAPI instances configured on the system. + attribute-set: napi + do: + request: + attributes: + - id + reply: &napi-get-op + attributes: + - id + - ifindex + dump: + request: + attributes: + - ifindex + reply: *napi-get-op mcast-groups: list: diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index f857960a7f06..e7bdbcb01f22 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -109,6 +109,14 @@ enum { NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1) }; +enum { + NETDEV_A_NAPI_IFINDEX = 1, + NETDEV_A_NAPI_ID, + + __NETDEV_A_NAPI_MAX, + NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1) +}; + enum { NETDEV_A_QUEUE_ID = 1, NETDEV_A_QUEUE_IFINDEX, @@ -130,6 +138,7 @@ enum { NETDEV_CMD_PAGE_POOL_CHANGE_NTF, NETDEV_CMD_PAGE_POOL_STATS_GET, NETDEV_CMD_QUEUE_GET, + NETDEV_CMD_NAPI_GET, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index b1dcf88c82cf..be7f2ebd61b2 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -58,6 +58,16 @@ static const struct nla_policy netdev_queue_get_dump_nl_policy[NETDEV_A_QUEUE_IF [NETDEV_A_QUEUE_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), }; +/* NETDEV_CMD_NAPI_GET - do */ +static const struct nla_policy netdev_napi_get_do_nl_policy[NETDEV_A_NAPI_ID + 1] = { + [NETDEV_A_NAPI_ID] = { .type = NLA_U32, }, +}; + +/* NETDEV_CMD_NAPI_GET - dump */ +static const struct nla_policy netdev_napi_get_dump_nl_policy[NETDEV_A_NAPI_IFINDEX + 1] = { + [NETDEV_A_NAPI_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), +}; + /* Ops table for netdev */ static const struct genl_split_ops netdev_nl_ops[] = { { @@ -114,6 +124,20 @@ static const struct genl_split_ops netdev_nl_ops[] = { .maxattr = NETDEV_A_QUEUE_IFINDEX, .flags = GENL_CMD_CAP_DUMP, }, + { + .cmd = NETDEV_CMD_NAPI_GET, + .doit = netdev_nl_napi_get_doit, + .policy = netdev_napi_get_do_nl_policy, + .maxattr = NETDEV_A_NAPI_ID, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = NETDEV_CMD_NAPI_GET, + .dumpit = netdev_nl_napi_get_dumpit, + .policy = netdev_napi_get_dump_nl_policy, + .maxattr = NETDEV_A_NAPI_IFINDEX, + .flags = GENL_CMD_CAP_DUMP, + }, }; static const struct genl_multicast_group netdev_nl_mcgrps[] = { diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index 086623c1797a..a47f2bcbe4fa 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -26,6 +26,8 @@ int netdev_nl_page_pool_stats_get_dumpit(struct sk_buff *skb, int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info); +int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); enum { NETDEV_NLGRP_MGMT, diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 3bc1661e6ebf..4c8ea6a4f015 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -155,6 +155,16 @@ int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } +int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + return -EOPNOTSUPP; +} + +int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + return -EOPNOTSUPP; +} + static int netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx, u32 q_type, const struct genl_info *info) diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index f857960a7f06..e7bdbcb01f22 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -109,6 +109,14 @@ enum { NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1) }; +enum { + NETDEV_A_NAPI_IFINDEX = 1, + NETDEV_A_NAPI_ID, + + __NETDEV_A_NAPI_MAX, + NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1) +}; + enum { NETDEV_A_QUEUE_ID = 1, NETDEV_A_QUEUE_IFINDEX, @@ -130,6 +138,7 @@ enum { NETDEV_CMD_PAGE_POOL_CHANGE_NTF, NETDEV_CMD_PAGE_POOL_STATS_GET, NETDEV_CMD_QUEUE_GET, + NETDEV_CMD_NAPI_GET, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c index fbf7e24ade91..906b61554698 100644 --- a/tools/net/ynl/generated/netdev-user.c +++ b/tools/net/ynl/generated/netdev-user.c @@ -24,6 +24,7 @@ static const char * const netdev_op_strmap[] = { [NETDEV_CMD_PAGE_POOL_CHANGE_NTF] = "page-pool-change-ntf", [NETDEV_CMD_PAGE_POOL_STATS_GET] = "page-pool-stats-get", [NETDEV_CMD_QUEUE_GET] = "queue-get", + [NETDEV_CMD_NAPI_GET] = "napi-get", }; const char *netdev_op_str(int op) @@ -160,6 +161,16 @@ struct ynl_policy_nest netdev_queue_nest = { .table = netdev_queue_policy, }; +struct ynl_policy_attr netdev_napi_policy[NETDEV_A_NAPI_MAX + 1] = { + [NETDEV_A_NAPI_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, }, + [NETDEV_A_NAPI_ID] = { .name = "id", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest netdev_napi_nest = { + .max_attr = NETDEV_A_NAPI_MAX, + .table = netdev_napi_policy, +}; + /* Common nested types */ void netdev_page_pool_info_free(struct netdev_page_pool_info *obj) { @@ -770,6 +781,119 @@ free_list: return NULL; } +/* ============== NETDEV_CMD_NAPI_GET ============== */ +/* NETDEV_CMD_NAPI_GET - do */ +void netdev_napi_get_req_free(struct netdev_napi_get_req *req) +{ + free(req); +} + +void netdev_napi_get_rsp_free(struct netdev_napi_get_rsp *rsp) +{ + free(rsp); +} + +int netdev_napi_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct netdev_napi_get_rsp *dst; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == NETDEV_A_NAPI_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.id = 1; + dst->id = mnl_attr_get_u32(attr); + } else if (type == NETDEV_A_NAPI_IFINDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.ifindex = 1; + dst->ifindex = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct netdev_napi_get_rsp * +netdev_napi_get(struct ynl_sock *ys, struct netdev_napi_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct netdev_napi_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, NETDEV_CMD_NAPI_GET, 1); + ys->req_policy = &netdev_napi_nest; + yrs.yarg.rsp_policy = &netdev_napi_nest; + + if (req->_present.id) + mnl_attr_put_u32(nlh, NETDEV_A_NAPI_ID, req->id); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = netdev_napi_get_rsp_parse; + yrs.rsp_cmd = NETDEV_CMD_NAPI_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + netdev_napi_get_rsp_free(rsp); + return NULL; +} + +/* NETDEV_CMD_NAPI_GET - dump */ +void netdev_napi_get_list_free(struct netdev_napi_get_list *rsp) +{ + struct netdev_napi_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp); + } +} + +struct netdev_napi_get_list * +netdev_napi_get_dump(struct ynl_sock *ys, struct netdev_napi_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct netdev_napi_get_list); + yds.cb = netdev_napi_get_rsp_parse; + yds.rsp_cmd = NETDEV_CMD_NAPI_GET; + yds.rsp_policy = &netdev_napi_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, NETDEV_CMD_NAPI_GET, 1); + ys->req_policy = &netdev_napi_nest; + + if (req->_present.ifindex) + mnl_attr_put_u32(nlh, NETDEV_A_NAPI_IFINDEX, req->ifindex); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + netdev_napi_get_list_free(yds.first); + return NULL; +} + static const struct ynl_ntf_info netdev_ntf_info[] = { [NETDEV_CMD_DEV_ADD_NTF] = { .alloc_sz = sizeof(struct netdev_dev_get_ntf), diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h index d7daf6df3df0..481c9e45b689 100644 --- a/tools/net/ynl/generated/netdev-user.h +++ b/tools/net/ynl/generated/netdev-user.h @@ -360,4 +360,79 @@ struct netdev_queue_get_list * netdev_queue_get_dump(struct ynl_sock *ys, struct netdev_queue_get_req_dump *req); +/* ============== NETDEV_CMD_NAPI_GET ============== */ +/* NETDEV_CMD_NAPI_GET - do */ +struct netdev_napi_get_req { + struct { + __u32 id:1; + } _present; + + __u32 id; +}; + +static inline struct netdev_napi_get_req *netdev_napi_get_req_alloc(void) +{ + return calloc(1, sizeof(struct netdev_napi_get_req)); +} +void netdev_napi_get_req_free(struct netdev_napi_get_req *req); + +static inline void +netdev_napi_get_req_set_id(struct netdev_napi_get_req *req, __u32 id) +{ + req->_present.id = 1; + req->id = id; +} + +struct netdev_napi_get_rsp { + struct { + __u32 id:1; + __u32 ifindex:1; + } _present; + + __u32 id; + __u32 ifindex; +}; + +void netdev_napi_get_rsp_free(struct netdev_napi_get_rsp *rsp); + +/* + * Get information about NAPI instances configured on the system. + */ +struct netdev_napi_get_rsp * +netdev_napi_get(struct ynl_sock *ys, struct netdev_napi_get_req *req); + +/* NETDEV_CMD_NAPI_GET - dump */ +struct netdev_napi_get_req_dump { + struct { + __u32 ifindex:1; + } _present; + + __u32 ifindex; +}; + +static inline struct netdev_napi_get_req_dump * +netdev_napi_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct netdev_napi_get_req_dump)); +} +void netdev_napi_get_req_dump_free(struct netdev_napi_get_req_dump *req); + +static inline void +netdev_napi_get_req_dump_set_ifindex(struct netdev_napi_get_req_dump *req, + __u32 ifindex) +{ + req->_present.ifindex = 1; + req->ifindex = ifindex; +} + +struct netdev_napi_get_list { + struct netdev_napi_get_list *next; + struct netdev_napi_get_rsp obj __attribute__((aligned(8))); +}; + +void netdev_napi_get_list_free(struct netdev_napi_get_list *rsp); + +struct netdev_napi_get_list * +netdev_napi_get_dump(struct ynl_sock *ys, struct netdev_napi_get_req_dump *req); + #endif /* _LINUX_NETDEV_GEN_H */ -- cgit From 5a5131d66fe02337de0b1b2e021b58f0f55c6df5 Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Fri, 1 Dec 2023 15:29:02 -0800 Subject: netdev-genl: spec: Add irq in netdev netlink YAML spec Add support in netlink spec(netdev.yaml) for interrupt number among the NAPI attributes. Add code generated from the spec. Signed-off-by: Amritha Nambiar Reviewed-by: Sridhar Samudrala Link: https://lore.kernel.org/r/170147334210.5260.18178387869057516983.stgit@anambiarhost.jf.intel.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/netdev.yaml | 5 +++++ include/uapi/linux/netdev.h | 1 + tools/include/uapi/linux/netdev.h | 1 + tools/net/ynl/generated/netdev-user.c | 6 ++++++ tools/net/ynl/generated/netdev-user.h | 2 ++ 5 files changed, 15 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 76d6b2e15b67..a3a1c6ad521b 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -226,6 +226,10 @@ attribute-sets: name: id doc: ID of the NAPI instance. type: u32 + - + name: irq + doc: The associated interrupt vector number for the napi + type: u32 - name: queue attributes: @@ -384,6 +388,7 @@ operations: attributes: - id - ifindex + - irq dump: request: attributes: diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index e7bdbcb01f22..30fea409b71e 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -112,6 +112,7 @@ enum { enum { NETDEV_A_NAPI_IFINDEX = 1, NETDEV_A_NAPI_ID, + NETDEV_A_NAPI_IRQ, __NETDEV_A_NAPI_MAX, NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1) diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index e7bdbcb01f22..30fea409b71e 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -112,6 +112,7 @@ enum { enum { NETDEV_A_NAPI_IFINDEX = 1, NETDEV_A_NAPI_ID, + NETDEV_A_NAPI_IRQ, __NETDEV_A_NAPI_MAX, NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1) diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c index 906b61554698..58e5196da4bd 100644 --- a/tools/net/ynl/generated/netdev-user.c +++ b/tools/net/ynl/generated/netdev-user.c @@ -164,6 +164,7 @@ struct ynl_policy_nest netdev_queue_nest = { struct ynl_policy_attr netdev_napi_policy[NETDEV_A_NAPI_MAX + 1] = { [NETDEV_A_NAPI_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, }, [NETDEV_A_NAPI_ID] = { .name = "id", .type = YNL_PT_U32, }, + [NETDEV_A_NAPI_IRQ] = { .name = "irq", .type = YNL_PT_U32, }, }; struct ynl_policy_nest netdev_napi_nest = { @@ -210,6 +211,11 @@ int netdev_page_pool_info_parse(struct ynl_parse_arg *yarg, return MNL_CB_ERROR; dst->_present.ifindex = 1; dst->ifindex = mnl_attr_get_u32(attr); + } else if (type == NETDEV_A_NAPI_IRQ) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.irq = 1; + dst->irq = mnl_attr_get_u32(attr); } } diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h index 481c9e45b689..0c3224017c12 100644 --- a/tools/net/ynl/generated/netdev-user.h +++ b/tools/net/ynl/generated/netdev-user.h @@ -387,10 +387,12 @@ struct netdev_napi_get_rsp { struct { __u32 id:1; __u32 ifindex:1; + __u32 irq:1; } _present; __u32 id; __u32 ifindex; + __u32 irq; }; void netdev_napi_get_rsp_free(struct netdev_napi_get_rsp *rsp); -- cgit From 8481a249a0eaf0000dbb18f7689ccd50ea9835cd Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Fri, 1 Dec 2023 15:29:13 -0800 Subject: netdev-genl: spec: Add PID in netdev netlink YAML spec Add support in netlink spec(netdev.yaml) for PID of the NAPI thread. Add code generated from the spec. Signed-off-by: Amritha Nambiar Reviewed-by: Sridhar Samudrala Link: https://lore.kernel.org/r/170147335301.5260.11872351477120434501.stgit@anambiarhost.jf.intel.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/netdev.yaml | 7 +++++++ include/uapi/linux/netdev.h | 1 + tools/include/uapi/linux/netdev.h | 1 + tools/net/ynl/generated/netdev-user.c | 6 ++++++ tools/net/ynl/generated/netdev-user.h | 2 ++ 5 files changed, 17 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index a3a1c6ad521b..f2c76d103bd8 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -230,6 +230,12 @@ attribute-sets: name: irq doc: The associated interrupt vector number for the napi type: u32 + - + name: pid + doc: PID of the napi thread, if NAPI is configured to operate in + threaded mode. If NAPI is not in threaded mode (i.e. uses normal + softirq context), the attribute will be absent. + type: u32 - name: queue attributes: @@ -389,6 +395,7 @@ operations: - id - ifindex - irq + - pid dump: request: attributes: diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 30fea409b71e..424c5e28f495 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -113,6 +113,7 @@ enum { NETDEV_A_NAPI_IFINDEX = 1, NETDEV_A_NAPI_ID, NETDEV_A_NAPI_IRQ, + NETDEV_A_NAPI_PID, __NETDEV_A_NAPI_MAX, NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1) diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 30fea409b71e..424c5e28f495 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -113,6 +113,7 @@ enum { NETDEV_A_NAPI_IFINDEX = 1, NETDEV_A_NAPI_ID, NETDEV_A_NAPI_IRQ, + NETDEV_A_NAPI_PID, __NETDEV_A_NAPI_MAX, NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1) diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c index 58e5196da4bd..ed8bcb855a1d 100644 --- a/tools/net/ynl/generated/netdev-user.c +++ b/tools/net/ynl/generated/netdev-user.c @@ -165,6 +165,7 @@ struct ynl_policy_attr netdev_napi_policy[NETDEV_A_NAPI_MAX + 1] = { [NETDEV_A_NAPI_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, }, [NETDEV_A_NAPI_ID] = { .name = "id", .type = YNL_PT_U32, }, [NETDEV_A_NAPI_IRQ] = { .name = "irq", .type = YNL_PT_U32, }, + [NETDEV_A_NAPI_PID] = { .name = "pid", .type = YNL_PT_U32, }, }; struct ynl_policy_nest netdev_napi_nest = { @@ -216,6 +217,11 @@ int netdev_page_pool_info_parse(struct ynl_parse_arg *yarg, return MNL_CB_ERROR; dst->_present.irq = 1; dst->irq = mnl_attr_get_u32(attr); + } else if (type == NETDEV_A_NAPI_PID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.pid = 1; + dst->pid = mnl_attr_get_u32(attr); } } diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h index 0c3224017c12..3830cf2ab6b8 100644 --- a/tools/net/ynl/generated/netdev-user.h +++ b/tools/net/ynl/generated/netdev-user.h @@ -388,11 +388,13 @@ struct netdev_napi_get_rsp { __u32 id:1; __u32 ifindex:1; __u32 irq:1; + __u32 pid:1; } _present; __u32 id; __u32 ifindex; __u32 irq; + __u32 pid; }; void netdev_napi_get_rsp_free(struct netdev_napi_get_rsp *rsp); -- cgit From 8ebe06611666a399162de31cdd6f2f48ffa87748 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Fri, 1 Dec 2023 16:19:42 +0800 Subject: net: bridge: add document for IFLA_BR enum Add document for IFLA_BR enum so we can use it in Documentation/networking/bridge.rst. Signed-off-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Signed-off-by: Paolo Abeni --- include/uapi/linux/if_link.h | 280 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 280 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 8181ef23a7a2..a5f873c85a72 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -461,6 +461,286 @@ enum in6_addr_gen_mode { /* Bridge section */ +/** + * DOC: Bridge enum definition + * + * Please *note* that the timer values in the following section are expected + * in clock_t format, which is seconds multiplied by USER_HZ (generally + * defined as 100). + * + * @IFLA_BR_FORWARD_DELAY + * The bridge forwarding delay is the time spent in LISTENING state + * (before moving to LEARNING) and in LEARNING state (before moving + * to FORWARDING). Only relevant if STP is enabled. + * + * The valid values are between (2 * USER_HZ) and (30 * USER_HZ). + * The default value is (15 * USER_HZ). + * + * @IFLA_BR_HELLO_TIME + * The time between hello packets sent by the bridge, when it is a root + * bridge or a designated bridge. Only relevant if STP is enabled. + * + * The valid values are between (1 * USER_HZ) and (10 * USER_HZ). + * The default value is (2 * USER_HZ). + * + * @IFLA_BR_MAX_AGE + * The hello packet timeout is the time until another bridge in the + * spanning tree is assumed to be dead, after reception of its last hello + * message. Only relevant if STP is enabled. + * + * The valid values are between (6 * USER_HZ) and (40 * USER_HZ). + * The default value is (20 * USER_HZ). + * + * @IFLA_BR_AGEING_TIME + * Configure the bridge's FDB entries aging time. It is the time a MAC + * address will be kept in the FDB after a packet has been received from + * that address. After this time has passed, entries are cleaned up. + * Allow values outside the 802.1 standard specification for special cases: + * + * * 0 - entry never ages (all permanent) + * * 1 - entry disappears (no persistence) + * + * The default value is (300 * USER_HZ). + * + * @IFLA_BR_STP_STATE + * Turn spanning tree protocol on (*IFLA_BR_STP_STATE* > 0) or off + * (*IFLA_BR_STP_STATE* == 0) for this bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_PRIORITY + * Set this bridge's spanning tree priority, used during STP root bridge + * election. + * + * The valid values are between 0 and 65535. + * + * @IFLA_BR_VLAN_FILTERING + * Turn VLAN filtering on (*IFLA_BR_VLAN_FILTERING* > 0) or off + * (*IFLA_BR_VLAN_FILTERING* == 0). When disabled, the bridge will not + * consider the VLAN tag when handling packets. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_VLAN_PROTOCOL + * Set the protocol used for VLAN filtering. + * + * The valid values are 0x8100(802.1Q) or 0x88A8(802.1AD). The default value + * is 0x8100(802.1Q). + * + * @IFLA_BR_GROUP_FWD_MASK + * The group forwarding mask. This is the bitmask that is applied to + * decide whether to forward incoming frames destined to link-local + * addresses (of the form 01:80:C2:00:00:0X). + * + * The default value is 0, which means the bridge does not forward any + * link-local frames coming on this port. + * + * @IFLA_BR_ROOT_ID + * The bridge root id, read only. + * + * @IFLA_BR_BRIDGE_ID + * The bridge id, read only. + * + * @IFLA_BR_ROOT_PORT + * The bridge root port, read only. + * + * @IFLA_BR_ROOT_PATH_COST + * The bridge root path cost, read only. + * + * @IFLA_BR_TOPOLOGY_CHANGE + * The bridge topology change, read only. + * + * @IFLA_BR_TOPOLOGY_CHANGE_DETECTED + * The bridge topology change detected, read only. + * + * @IFLA_BR_HELLO_TIMER + * The bridge hello timer, read only. + * + * @IFLA_BR_TCN_TIMER + * The bridge tcn timer, read only. + * + * @IFLA_BR_TOPOLOGY_CHANGE_TIMER + * The bridge topology change timer, read only. + * + * @IFLA_BR_GC_TIMER + * The bridge gc timer, read only. + * + * @IFLA_BR_GROUP_ADDR + * Set the MAC address of the multicast group this bridge uses for STP. + * The address must be a link-local address in standard Ethernet MAC address + * format. It is an address of the form 01:80:C2:00:00:0X, with X in [0, 4..f]. + * + * The default value is 0. + * + * @IFLA_BR_FDB_FLUSH + * Flush bridge's fdb dynamic entries. + * + * @IFLA_BR_MCAST_ROUTER + * Set bridge's multicast router if IGMP snooping is enabled. + * The valid values are: + * + * * 0 - disabled. + * * 1 - automatic (queried). + * * 2 - permanently enabled. + * + * The default value is 1. + * + * @IFLA_BR_MCAST_SNOOPING + * Turn multicast snooping on (*IFLA_BR_MCAST_SNOOPING* > 0) or off + * (*IFLA_BR_MCAST_SNOOPING* == 0). + * + * The default value is 1. + * + * @IFLA_BR_MCAST_QUERY_USE_IFADDR + * If enabled use the bridge's own IP address as source address for IGMP + * queries (*IFLA_BR_MCAST_QUERY_USE_IFADDR* > 0) or the default of 0.0.0.0 + * (*IFLA_BR_MCAST_QUERY_USE_IFADDR* == 0). + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MCAST_QUERIER + * Enable (*IFLA_BR_MULTICAST_QUERIER* > 0) or disable + * (*IFLA_BR_MULTICAST_QUERIER* == 0) IGMP querier, ie sending of multicast + * queries by the bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MCAST_HASH_ELASTICITY + * Set multicast database hash elasticity, It is the maximum chain length in + * the multicast hash table. This attribute is *deprecated* and the value + * is always 16. + * + * @IFLA_BR_MCAST_HASH_MAX + * Set maximum size of the multicast hash table + * + * The default value is 4096, the value must be a power of 2. + * + * @IFLA_BR_MCAST_LAST_MEMBER_CNT + * The Last Member Query Count is the number of Group-Specific Queries + * sent before the router assumes there are no local members. The Last + * Member Query Count is also the number of Group-and-Source-Specific + * Queries sent before the router assumes there are no listeners for a + * particular source. + * + * The default value is 2. + * + * @IFLA_BR_MCAST_STARTUP_QUERY_CNT + * The Startup Query Count is the number of Queries sent out on startup, + * separated by the Startup Query Interval. + * + * The default value is 2. + * + * @IFLA_BR_MCAST_LAST_MEMBER_INTVL + * The Last Member Query Interval is the Max Response Time inserted into + * Group-Specific Queries sent in response to Leave Group messages, and + * is also the amount of time between Group-Specific Query messages. + * + * The default value is (1 * USER_HZ). + * + * @IFLA_BR_MCAST_MEMBERSHIP_INTVL + * The interval after which the bridge will leave a group, if no membership + * reports for this group are received. + * + * The default value is (260 * USER_HZ). + * + * @IFLA_BR_MCAST_QUERIER_INTVL + * The interval between queries sent by other routers. if no queries are + * seen after this delay has passed, the bridge will start to send its own + * queries (as if *IFLA_BR_MCAST_QUERIER_INTVL* was enabled). + * + * The default value is (255 * USER_HZ). + * + * @IFLA_BR_MCAST_QUERY_INTVL + * The Query Interval is the interval between General Queries sent by + * the Querier. + * + * The default value is (125 * USER_HZ). The minimum value is (1 * USER_HZ). + * + * @IFLA_BR_MCAST_QUERY_RESPONSE_INTVL + * The Max Response Time used to calculate the Max Resp Code inserted + * into the periodic General Queries. + * + * The default value is (10 * USER_HZ). + * + * @IFLA_BR_MCAST_STARTUP_QUERY_INTVL + * The interval between queries in the startup phase. + * + * The default value is (125 * USER_HZ) / 4. The minimum value is (1 * USER_HZ). + * + * @IFLA_BR_NF_CALL_IPTABLES + * Enable (*NF_CALL_IPTABLES* > 0) or disable (*NF_CALL_IPTABLES* == 0) + * iptables hooks on the bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_NF_CALL_IP6TABLES + * Enable (*NF_CALL_IP6TABLES* > 0) or disable (*NF_CALL_IP6TABLES* == 0) + * ip6tables hooks on the bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_NF_CALL_ARPTABLES + * Enable (*NF_CALL_ARPTABLES* > 0) or disable (*NF_CALL_ARPTABLES* == 0) + * arptables hooks on the bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_VLAN_DEFAULT_PVID + * VLAN ID applied to untagged and priority-tagged incoming packets. + * + * The default value is 1. Setting to the special value 0 makes all ports of + * this bridge not have a PVID by default, which means that they will + * not accept VLAN-untagged traffic. + * + * @IFLA_BR_PAD + * Bridge attribute padding type for netlink message. + * + * @IFLA_BR_VLAN_STATS_ENABLED + * Enable (*IFLA_BR_VLAN_STATS_ENABLED* == 1) or disable + * (*IFLA_BR_VLAN_STATS_ENABLED* == 0) per-VLAN stats accounting. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MCAST_STATS_ENABLED + * Enable (*IFLA_BR_MCAST_STATS_ENABLED* > 0) or disable + * (*IFLA_BR_MCAST_STATS_ENABLED* == 0) multicast (IGMP/MLD) stats + * accounting. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MCAST_IGMP_VERSION + * Set the IGMP version. + * + * The valid values are 2 and 3. The default value is 2. + * + * @IFLA_BR_MCAST_MLD_VERSION + * Set the MLD version. + * + * The valid values are 1 and 2. The default value is 1. + * + * @IFLA_BR_VLAN_STATS_PER_PORT + * Enable (*IFLA_BR_VLAN_STATS_PER_PORT* == 1) or disable + * (*IFLA_BR_VLAN_STATS_PER_PORT* == 0) per-VLAN per-port stats accounting. + * Can be changed only when there are no port VLANs configured. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MULTI_BOOLOPT + * The multi_boolopt is used to control new boolean options to avoid adding + * new netlink attributes. You can look at ``enum br_boolopt_id`` for those + * options. + * + * @IFLA_BR_MCAST_QUERIER_STATE + * Bridge mcast querier states, read only. + * + * @IFLA_BR_FDB_N_LEARNED + * The number of dynamically learned FDB entries for the current bridge, + * read only. + * + * @IFLA_BR_FDB_MAX_LEARNED + * Set the number of max dynamically learned FDB entries for the current + * bridge. + */ enum { IFLA_BR_UNSPEC, IFLA_BR_FORWARD_DELAY, -- cgit From 8c4bafdb01cc7809903aced4981f563e3708ea37 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Fri, 1 Dec 2023 16:19:43 +0800 Subject: net: bridge: add document for IFLA_BRPORT enum Add document for IFLA_BRPORT enum so we can use it in Documentation/networking/bridge.rst. Signed-off-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Signed-off-by: Paolo Abeni --- include/uapi/linux/if_link.h | 241 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 241 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index a5f873c85a72..ab9bcff96e4d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -802,11 +802,252 @@ struct ifla_bridge_id { __u8 addr[6]; /* ETH_ALEN */ }; +/** + * DOC: Bridge mode enum definition + * + * @BRIDGE_MODE_HAIRPIN + * Controls whether traffic may be sent back out of the port on which it + * was received. This option is also called reflective relay mode, and is + * used to support basic VEPA (Virtual Ethernet Port Aggregator) + * capabilities. By default, this flag is turned off and the bridge will + * not forward traffic back out of the receiving port. + */ enum { BRIDGE_MODE_UNSPEC, BRIDGE_MODE_HAIRPIN, }; +/** + * DOC: Bridge port enum definition + * + * @IFLA_BRPORT_STATE + * The operation state of the port. Here are the valid values. + * + * * 0 - port is in STP *DISABLED* state. Make this port completely + * inactive for STP. This is also called BPDU filter and could be used + * to disable STP on an untrusted port, like a leaf virtual device. + * The traffic forwarding is also stopped on this port. + * * 1 - port is in STP *LISTENING* state. Only valid if STP is enabled + * on the bridge. In this state the port listens for STP BPDUs and + * drops all other traffic frames. + * * 2 - port is in STP *LEARNING* state. Only valid if STP is enabled on + * the bridge. In this state the port will accept traffic only for the + * purpose of updating MAC address tables. + * * 3 - port is in STP *FORWARDING* state. Port is fully active. + * * 4 - port is in STP *BLOCKING* state. Only valid if STP is enabled on + * the bridge. This state is used during the STP election process. + * In this state, port will only process STP BPDUs. + * + * @IFLA_BRPORT_PRIORITY + * The STP port priority. The valid values are between 0 and 255. + * + * @IFLA_BRPORT_COST + * The STP path cost of the port. The valid values are between 1 and 65535. + * + * @IFLA_BRPORT_MODE + * Set the bridge port mode. See *BRIDGE_MODE_HAIRPIN* for more details. + * + * @IFLA_BRPORT_GUARD + * Controls whether STP BPDUs will be processed by the bridge port. By + * default, the flag is turned off to allow BPDU processing. Turning this + * flag on will disable the bridge port if a STP BPDU packet is received. + * + * If the bridge has Spanning Tree enabled, hostile devices on the network + * may send BPDU on a port and cause network failure. Setting *guard on* + * will detect and stop this by disabling the port. The port will be + * restarted if the link is brought down, or removed and reattached. + * + * @IFLA_BRPORT_PROTECT + * Controls whether a given port is allowed to become a root port or not. + * Only used when STP is enabled on the bridge. By default the flag is off. + * + * This feature is also called root port guard. If BPDU is received from a + * leaf (edge) port, it should not be elected as root port. This could + * be used if using STP on a bridge and the downstream bridges are not fully + * trusted; this prevents a hostile guest from rerouting traffic. + * + * @IFLA_BRPORT_FAST_LEAVE + * This flag allows the bridge to immediately stop multicast traffic + * forwarding on a port that receives an IGMP Leave message. It is only used + * when IGMP snooping is enabled on the bridge. By default the flag is off. + * + * @IFLA_BRPORT_LEARNING + * Controls whether a given port will learn *source* MAC addresses from + * received traffic or not. Also controls whether dynamic FDB entries + * (which can also be added by software) will be refreshed by incoming + * traffic. By default this flag is on. + * + * @IFLA_BRPORT_UNICAST_FLOOD + * Controls whether unicast traffic for which there is no FDB entry will + * be flooded towards this port. By default this flag is on. + * + * @IFLA_BRPORT_PROXYARP + * Enable proxy ARP on this port. + * + * @IFLA_BRPORT_LEARNING_SYNC + * Controls whether a given port will sync MAC addresses learned on device + * port to bridge FDB. + * + * @IFLA_BRPORT_PROXYARP_WIFI + * Enable proxy ARP on this port which meets extended requirements by + * IEEE 802.11 and Hotspot 2.0 specifications. + * + * @IFLA_BRPORT_ROOT_ID + * + * @IFLA_BRPORT_BRIDGE_ID + * + * @IFLA_BRPORT_DESIGNATED_PORT + * + * @IFLA_BRPORT_DESIGNATED_COST + * + * @IFLA_BRPORT_ID + * + * @IFLA_BRPORT_NO + * + * @IFLA_BRPORT_TOPOLOGY_CHANGE_ACK + * + * @IFLA_BRPORT_CONFIG_PENDING + * + * @IFLA_BRPORT_MESSAGE_AGE_TIMER + * + * @IFLA_BRPORT_FORWARD_DELAY_TIMER + * + * @IFLA_BRPORT_HOLD_TIMER + * + * @IFLA_BRPORT_FLUSH + * Flush bridge ports' fdb dynamic entries. + * + * @IFLA_BRPORT_MULTICAST_ROUTER + * Configure the port's multicast router presence. A port with + * a multicast router will receive all multicast traffic. + * The valid values are: + * + * * 0 disable multicast routers on this port + * * 1 let the system detect the presence of routers (default) + * * 2 permanently enable multicast traffic forwarding on this port + * * 3 enable multicast routers temporarily on this port, not depending + * on incoming queries. + * + * @IFLA_BRPORT_PAD + * + * @IFLA_BRPORT_MCAST_FLOOD + * Controls whether a given port will flood multicast traffic for which + * there is no MDB entry. By default this flag is on. + * + * @IFLA_BRPORT_MCAST_TO_UCAST + * Controls whether a given port will replicate packets using unicast + * instead of multicast. By default this flag is off. + * + * This is done by copying the packet per host and changing the multicast + * destination MAC to a unicast one accordingly. + * + * *mcast_to_unicast* works on top of the multicast snooping feature of the + * bridge. Which means unicast copies are only delivered to hosts which + * are interested in unicast and signaled this via IGMP/MLD reports previously. + * + * This feature is intended for interface types which have a more reliable + * and/or efficient way to deliver unicast packets than broadcast ones + * (e.g. WiFi). + * + * However, it should only be enabled on interfaces where no IGMPv2/MLDv1 + * report suppression takes place. IGMP/MLD report suppression issue is + * usually overcome by the network daemon (supplicant) enabling AP isolation + * and by that separating all STAs. + * + * Delivery of STA-to-STA IP multicast is made possible again by enabling + * and utilizing the bridge hairpin mode, which considers the incoming port + * as a potential outgoing port, too (see *BRIDGE_MODE_HAIRPIN* option). + * Hairpin mode is performed after multicast snooping, therefore leading + * to only deliver reports to STAs running a multicast router. + * + * @IFLA_BRPORT_VLAN_TUNNEL + * Controls whether vlan to tunnel mapping is enabled on the port. + * By default this flag is off. + * + * @IFLA_BRPORT_BCAST_FLOOD + * Controls flooding of broadcast traffic on the given port. By default + * this flag is on. + * + * @IFLA_BRPORT_GROUP_FWD_MASK + * Set the group forward mask. This is a bitmask that is applied to + * decide whether to forward incoming frames destined to link-local + * addresses. The addresses of the form are 01:80:C2:00:00:0X (defaults + * to 0, which means the bridge does not forward any link-local frames + * coming on this port). + * + * @IFLA_BRPORT_NEIGH_SUPPRESS + * Controls whether neighbor discovery (arp and nd) proxy and suppression + * is enabled on the port. By default this flag is off. + * + * @IFLA_BRPORT_ISOLATED + * Controls whether a given port will be isolated, which means it will be + * able to communicate with non-isolated ports only. By default this + * flag is off. + * + * @IFLA_BRPORT_BACKUP_PORT + * Set a backup port. If the port loses carrier all traffic will be + * redirected to the configured backup port. Set the value to 0 to disable + * it. + * + * @IFLA_BRPORT_MRP_RING_OPEN + * + * @IFLA_BRPORT_MRP_IN_OPEN + * + * @IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT + * The number of per-port EHT hosts limit. The default value is 512. + * Setting to 0 is not allowed. + * + * @IFLA_BRPORT_MCAST_EHT_HOSTS_CNT + * The current number of tracked hosts, read only. + * + * @IFLA_BRPORT_LOCKED + * Controls whether a port will be locked, meaning that hosts behind the + * port will not be able to communicate through the port unless an FDB + * entry with the unit's MAC address is in the FDB. The common use case is + * that hosts are allowed access through authentication with the IEEE 802.1X + * protocol or based on whitelists. By default this flag is off. + * + * Please note that secure 802.1X deployments should always use the + * *BR_BOOLOPT_NO_LL_LEARN* flag, to not permit the bridge to populate its + * FDB based on link-local (EAPOL) traffic received on the port. + * + * @IFLA_BRPORT_MAB + * Controls whether a port will use MAC Authentication Bypass (MAB), a + * technique through which select MAC addresses may be allowed on a locked + * port, without using 802.1X authentication. Packets with an unknown source + * MAC address generates a "locked" FDB entry on the incoming bridge port. + * The common use case is for user space to react to these bridge FDB + * notifications and optionally replace the locked FDB entry with a normal + * one, allowing traffic to pass for whitelisted MAC addresses. + * + * Setting this flag also requires *IFLA_BRPORT_LOCKED* and + * *IFLA_BRPORT_LEARNING*. *IFLA_BRPORT_LOCKED* ensures that unauthorized + * data packets are dropped, and *IFLA_BRPORT_LEARNING* allows the dynamic + * FDB entries installed by user space (as replacements for the locked FDB + * entries) to be refreshed and/or aged out. + * + * @IFLA_BRPORT_MCAST_N_GROUPS + * + * @IFLA_BRPORT_MCAST_MAX_GROUPS + * Sets the maximum number of MDB entries that can be registered for a + * given port. Attempts to register more MDB entries at the port than this + * limit allows will be rejected, whether they are done through netlink + * (e.g. the bridge tool), or IGMP or MLD membership reports. Setting a + * limit of 0 disables the limit. The default value is 0. + * + * @IFLA_BRPORT_NEIGH_VLAN_SUPPRESS + * Controls whether neighbor discovery (arp and nd) proxy and suppression is + * enabled for a given port. By default this flag is off. + * + * Note that this option only takes effect when *IFLA_BRPORT_NEIGH_SUPPRESS* + * is enabled for a given port. + * + * @IFLA_BRPORT_BACKUP_NHID + * The FDB nexthop object ID to attach to packets being redirected to a + * backup port that has VLAN tunnel mapping enabled (via the + * *IFLA_BRPORT_VLAN_TUNNEL* option). Setting a value of 0 (default) has + * the effect of not attaching any ID. + */ enum { IFLA_BRPORT_UNSPEC, IFLA_BRPORT_STATE, /* Spanning tree state */ -- cgit From 4527358b76861dfd64ee34aba45d81648fbc8a61 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 30 Nov 2023 10:52:15 -0800 Subject: bpf: introduce BPF token object Add new kind of BPF kernel object, BPF token. BPF token is meant to allow delegating privileged BPF functionality, like loading a BPF program or creating a BPF map, from privileged process to a *trusted* unprivileged process, all while having a good amount of control over which privileged operations could be performed using provided BPF token. This is achieved through mounting BPF FS instance with extra delegation mount options, which determine what operations are delegatable, and also constraining it to the owning user namespace (as mentioned in the previous patch). BPF token itself is just a derivative from BPF FS and can be created through a new bpf() syscall command, BPF_TOKEN_CREATE, which accepts BPF FS FD, which can be attained through open() API by opening BPF FS mount point. Currently, BPF token "inherits" delegated command, map types, prog type, and attach type bit sets from BPF FS as is. In the future, having an BPF token as a separate object with its own FD, we can allow to further restrict BPF token's allowable set of things either at the creation time or after the fact, allowing the process to guard itself further from unintentionally trying to load undesired kind of BPF programs. But for now we keep things simple and just copy bit sets as is. When BPF token is created from BPF FS mount, we take reference to the BPF super block's owning user namespace, and then use that namespace for checking all the {CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN} capabilities that are normally only checked against init userns (using capable()), but now we check them using ns_capable() instead (if BPF token is provided). See bpf_token_capable() for details. Such setup means that BPF token in itself is not sufficient to grant BPF functionality. User namespaced process has to *also* have necessary combination of capabilities inside that user namespace. So while previously CAP_BPF was useless when granted within user namespace, now it gains a meaning and allows container managers and sys admins to have a flexible control over which processes can and need to use BPF functionality within the user namespace (i.e., container in practice). And BPF FS delegation mount options and derived BPF tokens serve as a per-container "flag" to grant overall ability to use bpf() (plus further restrict on which parts of bpf() syscalls are treated as namespaced). Note also, BPF_TOKEN_CREATE command itself requires ns_capable(CAP_BPF) within the BPF FS owning user namespace, rounding up the ns_capable() story of BPF token. Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231130185229.2688956-4-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 41 ++++++++ include/uapi/linux/bpf.h | 37 +++++++ kernel/bpf/Makefile | 2 +- kernel/bpf/inode.c | 12 ++- kernel/bpf/syscall.c | 17 ++++ kernel/bpf/token.c | 214 +++++++++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 37 +++++++ 7 files changed, 354 insertions(+), 6 deletions(-) create mode 100644 kernel/bpf/token.c (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d3c9acc593ea..aa9cf8e5fab1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -51,6 +51,10 @@ struct module; struct bpf_func_state; struct ftrace_ops; struct cgroup; +struct bpf_token; +struct user_namespace; +struct super_block; +struct inode; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -1591,6 +1595,13 @@ struct bpf_mount_opts { u64 delegate_attachs; }; +struct bpf_token { + struct work_struct work; + atomic64_t refcnt; + struct user_namespace *userns; + u64 allowed_cmds; +}; + struct bpf_struct_ops_value; struct btf_member; @@ -2048,6 +2059,7 @@ static inline void bpf_enable_instrumentation(void) migrate_enable(); } +extern const struct super_operations bpf_super_ops; extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; extern const struct file_operations bpf_iter_fops; @@ -2182,6 +2194,8 @@ static inline void bpf_map_dec_elem_count(struct bpf_map *map) extern int sysctl_unprivileged_bpf_disabled; +bool bpf_token_capable(const struct bpf_token *token, int cap); + static inline bool bpf_allow_ptr_leaks(void) { return perfmon_capable(); @@ -2216,8 +2230,17 @@ int bpf_link_new_fd(struct bpf_link *link); struct bpf_link *bpf_link_get_from_fd(u32 ufd); struct bpf_link *bpf_link_get_curr_or_next(u32 *id); +void bpf_token_inc(struct bpf_token *token); +void bpf_token_put(struct bpf_token *token); +int bpf_token_create(union bpf_attr *attr); +struct bpf_token *bpf_token_get_from_fd(u32 ufd); + +bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); + int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); +struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir, + umode_t mode); #define BPF_ITER_FUNC_PREFIX "bpf_iter_" #define DEFINE_BPF_ITER_FUNC(target, args...) \ @@ -2580,6 +2603,24 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags) return -EOPNOTSUPP; } +static inline bool bpf_token_capable(const struct bpf_token *token, int cap) +{ + return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN)); +} + +static inline void bpf_token_inc(struct bpf_token *token) +{ +} + +static inline void bpf_token_put(struct bpf_token *token) +{ +} + +static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline void __dev_flush(void) { } diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e88746ba7d21..d4a567e5bc3c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -847,6 +847,36 @@ union bpf_iter_link_info { * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. * + * BPF_TOKEN_CREATE + * Description + * Create BPF token with embedded information about what + * BPF-related functionality it allows: + * - a set of allowed bpf() syscall commands; + * - a set of allowed BPF map types to be created with + * BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed; + * - a set of allowed BPF program types and BPF program attach + * types to be loaded with BPF_PROG_LOAD command, if + * BPF_PROG_LOAD itself is allowed. + * + * BPF token is created (derived) from an instance of BPF FS, + * assuming it has necessary delegation mount options specified. + * This BPF token can be passed as an extra parameter to various + * bpf() syscall commands to grant BPF subsystem functionality to + * unprivileged processes. + * + * When created, BPF token is "associated" with the owning + * user namespace of BPF FS instance (super block) that it was + * derived from, and subsequent BPF operations performed with + * BPF token would be performing capabilities checks (i.e., + * CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within + * that user namespace. Without BPF token, such capabilities + * have to be granted in init user namespace, making bpf() + * syscall incompatible with user namespace, for the most part. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -901,6 +931,8 @@ enum bpf_cmd { BPF_ITER_CREATE, BPF_LINK_DETACH, BPF_PROG_BIND_MAP, + BPF_TOKEN_CREATE, + __MAX_BPF_CMD, }; enum bpf_map_type { @@ -1712,6 +1744,11 @@ union bpf_attr { __u32 flags; /* extra flags */ } prog_bind_map; + struct { /* struct used by BPF_TOKEN_CREATE command */ + __u32 flags; + __u32 bpffs_fd; + } token_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index f526b7573e97..4ce95acfcaa7 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -6,7 +6,7 @@ cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse endif CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) -obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o token.o obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 220fe0f99095..6ce3f9696e72 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -99,9 +99,9 @@ static const struct inode_operations bpf_prog_iops = { }; static const struct inode_operations bpf_map_iops = { }; static const struct inode_operations bpf_link_iops = { }; -static struct inode *bpf_get_inode(struct super_block *sb, - const struct inode *dir, - umode_t mode) +struct inode *bpf_get_inode(struct super_block *sb, + const struct inode *dir, + umode_t mode) { struct inode *inode; @@ -602,11 +602,13 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) { struct bpf_mount_opts *opts = root->d_sb->s_fs_info; umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX; + u64 mask; if (mode != S_IRWXUGO) seq_printf(m, ",mode=%o", mode); - if (opts->delegate_cmds == ~0ULL) + mask = (1ULL << __MAX_BPF_CMD) - 1; + if ((opts->delegate_cmds & mask) == mask) seq_printf(m, ",delegate_cmds=any"); else if (opts->delegate_cmds) seq_printf(m, ",delegate_cmds=0x%llx", opts->delegate_cmds); @@ -639,7 +641,7 @@ static void bpf_free_inode(struct inode *inode) free_inode_nonrcu(inode); } -static const struct super_operations bpf_super_ops = { +const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .show_options = bpf_show_options, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ee33a52abf18..a156d549b356 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5377,6 +5377,20 @@ out_prog_put: return ret; } +#define BPF_TOKEN_CREATE_LAST_FIELD token_create.bpffs_fd + +static int token_create(union bpf_attr *attr) +{ + if (CHECK_ATTR(BPF_TOKEN_CREATE)) + return -EINVAL; + + /* no flags are supported yet */ + if (attr->token_create.flags) + return -EINVAL; + + return bpf_token_create(attr); +} + static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) { union bpf_attr attr; @@ -5510,6 +5524,9 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) case BPF_PROG_BIND_MAP: err = bpf_prog_bind_map(&attr); break; + case BPF_TOKEN_CREATE: + err = token_create(&attr); + break; default: err = -EINVAL; break; diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c new file mode 100644 index 000000000000..e18aaecc67e9 --- /dev/null +++ b/kernel/bpf/token.c @@ -0,0 +1,214 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +bool bpf_token_capable(const struct bpf_token *token, int cap) +{ + /* BPF token allows ns_capable() level of capabilities, but only if + * token's userns is *exactly* the same as current user's userns + */ + if (token && current_user_ns() == token->userns) { + if (ns_capable(token->userns, cap)) + return true; + if (cap != CAP_SYS_ADMIN && ns_capable(token->userns, CAP_SYS_ADMIN)) + return true; + } + /* otherwise fallback to capable() checks */ + return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN)); +} + +void bpf_token_inc(struct bpf_token *token) +{ + atomic64_inc(&token->refcnt); +} + +static void bpf_token_free(struct bpf_token *token) +{ + put_user_ns(token->userns); + kvfree(token); +} + +static void bpf_token_put_deferred(struct work_struct *work) +{ + struct bpf_token *token = container_of(work, struct bpf_token, work); + + bpf_token_free(token); +} + +void bpf_token_put(struct bpf_token *token) +{ + if (!token) + return; + + if (!atomic64_dec_and_test(&token->refcnt)) + return; + + INIT_WORK(&token->work, bpf_token_put_deferred); + schedule_work(&token->work); +} + +static int bpf_token_release(struct inode *inode, struct file *filp) +{ + struct bpf_token *token = filp->private_data; + + bpf_token_put(token); + return 0; +} + +static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) +{ + struct bpf_token *token = filp->private_data; + u64 mask; + + BUILD_BUG_ON(__MAX_BPF_CMD >= 64); + mask = (1ULL << __MAX_BPF_CMD) - 1; + if ((token->allowed_cmds & mask) == mask) + seq_printf(m, "allowed_cmds:\tany\n"); + else + seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds); +} + +#define BPF_TOKEN_INODE_NAME "bpf-token" + +static const struct inode_operations bpf_token_iops = { }; + +static const struct file_operations bpf_token_fops = { + .release = bpf_token_release, + .show_fdinfo = bpf_token_show_fdinfo, +}; + +int bpf_token_create(union bpf_attr *attr) +{ + struct bpf_mount_opts *mnt_opts; + struct bpf_token *token = NULL; + struct user_namespace *userns; + struct inode *inode; + struct file *file; + struct path path; + struct fd f; + umode_t mode; + int err, fd; + + f = fdget(attr->token_create.bpffs_fd); + if (!f.file) + return -EBADF; + + path = f.file->f_path; + path_get(&path); + fdput(f); + + if (path.dentry != path.mnt->mnt_sb->s_root) { + err = -EINVAL; + goto out_path; + } + if (path.mnt->mnt_sb->s_op != &bpf_super_ops) { + err = -EINVAL; + goto out_path; + } + err = path_permission(&path, MAY_ACCESS); + if (err) + goto out_path; + + userns = path.dentry->d_sb->s_user_ns; + /* + * Enforce that creators of BPF tokens are in the same user + * namespace as the BPF FS instance. This makes reasoning about + * permissions a lot easier and we can always relax this later. + */ + if (current_user_ns() != userns) { + err = -EPERM; + goto out_path; + } + if (!ns_capable(userns, CAP_BPF)) { + err = -EPERM; + goto out_path; + } + + mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); + inode = bpf_get_inode(path.mnt->mnt_sb, NULL, mode); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out_path; + } + + inode->i_op = &bpf_token_iops; + inode->i_fop = &bpf_token_fops; + clear_nlink(inode); /* make sure it is unlinked */ + + file = alloc_file_pseudo(inode, path.mnt, BPF_TOKEN_INODE_NAME, O_RDWR, &bpf_token_fops); + if (IS_ERR(file)) { + iput(inode); + err = PTR_ERR(file); + goto out_path; + } + + token = kvzalloc(sizeof(*token), GFP_USER); + if (!token) { + err = -ENOMEM; + goto out_file; + } + + atomic64_set(&token->refcnt, 1); + + /* remember bpffs owning userns for future ns_capable() checks */ + token->userns = get_user_ns(userns); + + mnt_opts = path.dentry->d_sb->s_fs_info; + token->allowed_cmds = mnt_opts->delegate_cmds; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) { + err = fd; + goto out_token; + } + + file->private_data = token; + fd_install(fd, file); + + path_put(&path); + return fd; + +out_token: + bpf_token_free(token); +out_file: + fput(file); +out_path: + path_put(&path); + return err; +} + +struct bpf_token *bpf_token_get_from_fd(u32 ufd) +{ + struct fd f = fdget(ufd); + struct bpf_token *token; + + if (!f.file) + return ERR_PTR(-EBADF); + if (f.file->f_op != &bpf_token_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + token = f.file->private_data; + bpf_token_inc(token); + fdput(f); + + return token; +} + +bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) +{ + /* BPF token can be used only within exactly the same userns in which + * it was created + */ + if (!token || current_user_ns() != token->userns) + return false; + + return token->allowed_cmds & (1ULL << cmd); +} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e88746ba7d21..d4a567e5bc3c 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -847,6 +847,36 @@ union bpf_iter_link_info { * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. * + * BPF_TOKEN_CREATE + * Description + * Create BPF token with embedded information about what + * BPF-related functionality it allows: + * - a set of allowed bpf() syscall commands; + * - a set of allowed BPF map types to be created with + * BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed; + * - a set of allowed BPF program types and BPF program attach + * types to be loaded with BPF_PROG_LOAD command, if + * BPF_PROG_LOAD itself is allowed. + * + * BPF token is created (derived) from an instance of BPF FS, + * assuming it has necessary delegation mount options specified. + * This BPF token can be passed as an extra parameter to various + * bpf() syscall commands to grant BPF subsystem functionality to + * unprivileged processes. + * + * When created, BPF token is "associated" with the owning + * user namespace of BPF FS instance (super block) that it was + * derived from, and subsequent BPF operations performed with + * BPF token would be performing capabilities checks (i.e., + * CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within + * that user namespace. Without BPF token, such capabilities + * have to be granted in init user namespace, making bpf() + * syscall incompatible with user namespace, for the most part. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -901,6 +931,8 @@ enum bpf_cmd { BPF_ITER_CREATE, BPF_LINK_DETACH, BPF_PROG_BIND_MAP, + BPF_TOKEN_CREATE, + __MAX_BPF_CMD, }; enum bpf_map_type { @@ -1712,6 +1744,11 @@ union bpf_attr { __u32 flags; /* extra flags */ } prog_bind_map; + struct { /* struct used by BPF_TOKEN_CREATE command */ + __u32 flags; + __u32 bpffs_fd; + } token_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF -- cgit From 688b7270b3cb75e8ac78123d719967db40336e5b Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 30 Nov 2023 10:52:16 -0800 Subject: bpf: add BPF token support to BPF_MAP_CREATE command Allow providing token_fd for BPF_MAP_CREATE command to allow controlled BPF map creation from unprivileged process through delegated BPF token. Wire through a set of allowed BPF map types to BPF token, derived from BPF FS at BPF token creation time. This, in combination with allowed_cmds allows to create a narrowly-focused BPF token (controlled by privileged agent) with a restrictive set of BPF maps that application can attempt to create. Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231130185229.2688956-5-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 + include/uapi/linux/bpf.h | 2 + kernel/bpf/inode.c | 3 +- kernel/bpf/syscall.c | 52 ++++++++++++++++------ kernel/bpf/token.c | 16 +++++++ tools/include/uapi/linux/bpf.h | 2 + .../selftests/bpf/prog_tests/libbpf_probes.c | 2 + .../testing/selftests/bpf/prog_tests/libbpf_str.c | 3 ++ 8 files changed, 67 insertions(+), 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index aa9cf8e5fab1..e08e8436df38 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1600,6 +1600,7 @@ struct bpf_token { atomic64_t refcnt; struct user_namespace *userns; u64 allowed_cmds; + u64 allowed_maps; }; struct bpf_struct_ops_value; @@ -2236,6 +2237,7 @@ int bpf_token_create(union bpf_attr *attr); struct bpf_token *bpf_token_get_from_fd(u32 ufd); bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); +bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type); int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d4a567e5bc3c..0bba3392b17a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -983,6 +983,7 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, + __MAX_BPF_MAP_TYPE }; /* Note that tracing related programs such as @@ -1433,6 +1434,7 @@ union bpf_attr { * to using 5 hash functions). */ __u64 map_extra; + __u32 map_token_fd; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 6ce3f9696e72..9c7865d1c53d 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -613,7 +613,8 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) else if (opts->delegate_cmds) seq_printf(m, ",delegate_cmds=0x%llx", opts->delegate_cmds); - if (opts->delegate_maps == ~0ULL) + mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1; + if ((opts->delegate_maps & mask) == mask) seq_printf(m, ",delegate_maps=any"); else if (opts->delegate_maps) seq_printf(m, ",delegate_maps=0x%llx", opts->delegate_maps); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a156d549b356..22e14124cd61 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1009,8 +1009,8 @@ int map_check_no_btf(const struct bpf_map *map, return -ENOTSUPP; } -static int map_check_btf(struct bpf_map *map, const struct btf *btf, - u32 btf_key_id, u32 btf_value_id) +static int map_check_btf(struct bpf_map *map, struct bpf_token *token, + const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { const struct btf_type *key_type, *value_type; u32 key_size, value_size; @@ -1038,7 +1038,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, if (!IS_ERR_OR_NULL(map->record)) { int i; - if (!bpf_capable()) { + if (!bpf_token_capable(token, CAP_BPF)) { ret = -EPERM; goto free_map_tab; } @@ -1126,11 +1126,12 @@ static bool bpf_net_capable(void) return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN); } -#define BPF_MAP_CREATE_LAST_FIELD map_extra +#define BPF_MAP_CREATE_LAST_FIELD map_token_fd /* called via syscall */ static int map_create(union bpf_attr *attr) { const struct bpf_map_ops *ops; + struct bpf_token *token = NULL; int numa_node = bpf_map_attr_numa_node(attr); u32 map_type = attr->map_type; struct bpf_map *map; @@ -1181,14 +1182,32 @@ static int map_create(union bpf_attr *attr) if (!ops->map_mem_usage) return -EINVAL; + if (attr->map_token_fd) { + token = bpf_token_get_from_fd(attr->map_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + + /* if current token doesn't grant map creation permissions, + * then we can't use this token, so ignore it and rely on + * system-wide capabilities checks + */ + if (!bpf_token_allow_cmd(token, BPF_MAP_CREATE) || + !bpf_token_allow_map_type(token, attr->map_type)) { + bpf_token_put(token); + token = NULL; + } + } + + err = -EPERM; + /* Intent here is for unprivileged_bpf_disabled to block BPF map * creation for unprivileged users; other actions depend * on fd availability and access to bpffs, so are dependent on * object creation success. Even with unprivileged BPF disabled, * capability checks are still carried out. */ - if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) - return -EPERM; + if (sysctl_unprivileged_bpf_disabled && !bpf_token_capable(token, CAP_BPF)) + goto put_token; /* check privileged map type permissions */ switch (map_type) { @@ -1221,25 +1240,27 @@ static int map_create(union bpf_attr *attr) case BPF_MAP_TYPE_LRU_PERCPU_HASH: case BPF_MAP_TYPE_STRUCT_OPS: case BPF_MAP_TYPE_CPUMAP: - if (!bpf_capable()) - return -EPERM; + if (!bpf_token_capable(token, CAP_BPF)) + goto put_token; break; case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_DEVMAP: case BPF_MAP_TYPE_DEVMAP_HASH: case BPF_MAP_TYPE_XSKMAP: - if (!bpf_net_capable()) - return -EPERM; + if (!bpf_token_capable(token, CAP_NET_ADMIN)) + goto put_token; break; default: WARN(1, "unsupported map type %d", map_type); - return -EPERM; + goto put_token; } map = ops->map_alloc(attr); - if (IS_ERR(map)) - return PTR_ERR(map); + if (IS_ERR(map)) { + err = PTR_ERR(map); + goto put_token; + } map->ops = ops; map->map_type = map_type; @@ -1276,7 +1297,7 @@ static int map_create(union bpf_attr *attr) map->btf = btf; if (attr->btf_value_type_id) { - err = map_check_btf(map, btf, attr->btf_key_type_id, + err = map_check_btf(map, token, btf, attr->btf_key_type_id, attr->btf_value_type_id); if (err) goto free_map; @@ -1297,6 +1318,7 @@ static int map_create(union bpf_attr *attr) goto free_map_sec; bpf_map_save_memcg(map); + bpf_token_put(token); err = bpf_map_new_fd(map, f_flags); if (err < 0) { @@ -1317,6 +1339,8 @@ free_map_sec: free_map: btf_put(map->btf); map->ops->map_free(map); +put_token: + bpf_token_put(token); return err; } diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c index e18aaecc67e9..06c34dae658e 100644 --- a/kernel/bpf/token.c +++ b/kernel/bpf/token.c @@ -72,6 +72,13 @@ static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) seq_printf(m, "allowed_cmds:\tany\n"); else seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds); + + BUILD_BUG_ON(__MAX_BPF_MAP_TYPE >= 64); + mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1; + if ((token->allowed_maps & mask) == mask) + seq_printf(m, "allowed_maps:\tany\n"); + else + seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); } #define BPF_TOKEN_INODE_NAME "bpf-token" @@ -161,6 +168,7 @@ int bpf_token_create(union bpf_attr *attr) mnt_opts = path.dentry->d_sb->s_fs_info; token->allowed_cmds = mnt_opts->delegate_cmds; + token->allowed_maps = mnt_opts->delegate_maps; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { @@ -212,3 +220,11 @@ bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) return token->allowed_cmds & (1ULL << cmd); } + +bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type) +{ + if (!token || type >= __MAX_BPF_MAP_TYPE) + return false; + + return token->allowed_maps & (1ULL << type); +} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index d4a567e5bc3c..0bba3392b17a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -983,6 +983,7 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, + __MAX_BPF_MAP_TYPE }; /* Note that tracing related programs such as @@ -1433,6 +1434,7 @@ union bpf_attr { * to using 5 hash functions). */ __u64 map_extra; + __u32 map_token_fd; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c index 9f766ddd946a..573249a2814d 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c @@ -68,6 +68,8 @@ void test_libbpf_probe_map_types(void) if (map_type == BPF_MAP_TYPE_UNSPEC) continue; + if (strcmp(map_type_name, "__MAX_BPF_MAP_TYPE") == 0) + continue; if (!test__start_subtest(map_type_name)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c index c440ea3311ed..2a0633f43c73 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c @@ -132,6 +132,9 @@ static void test_libbpf_bpf_map_type_str(void) const char *map_type_str; char buf[256]; + if (map_type == __MAX_BPF_MAP_TYPE) + continue; + map_type_name = btf__str_by_offset(btf, e->name_off); map_type_str = libbpf_bpf_map_type_str(map_type); ASSERT_OK_PTR(map_type_str, map_type_name); -- cgit From ee54b1a910e4d49c9a104f31ae3f5b979131adf8 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 30 Nov 2023 10:52:17 -0800 Subject: bpf: add BPF token support to BPF_BTF_LOAD command Accept BPF token FD in BPF_BTF_LOAD command to allow BTF data loading through delegated BPF token. BTF loading is a pretty straightforward operation, so as long as BPF token is created with allow_cmds granting BPF_BTF_LOAD command, kernel proceeds to parsing BTF data and creating BTF object. Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231130185229.2688956-6-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 20 ++++++++++++++++++-- tools/include/uapi/linux/bpf.h | 1 + 3 files changed, 20 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0bba3392b17a..9f9989e0d062 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1616,6 +1616,7 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 btf_log_true_size; + __u32 btf_token_fd; }; struct { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 22e14124cd61..d87c5c27cde3 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4777,15 +4777,31 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, return err; } -#define BPF_BTF_LOAD_LAST_FIELD btf_log_true_size +#define BPF_BTF_LOAD_LAST_FIELD btf_token_fd static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size) { + struct bpf_token *token = NULL; + if (CHECK_ATTR(BPF_BTF_LOAD)) return -EINVAL; - if (!bpf_capable()) + if (attr->btf_token_fd) { + token = bpf_token_get_from_fd(attr->btf_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + if (!bpf_token_allow_cmd(token, BPF_BTF_LOAD)) { + bpf_token_put(token); + token = NULL; + } + } + + if (!bpf_token_capable(token, CAP_BPF)) { + bpf_token_put(token); return -EPERM; + } + + bpf_token_put(token); return btf_new_fd(attr, uattr, uattr_size); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 0bba3392b17a..9f9989e0d062 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1616,6 +1616,7 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 btf_log_true_size; + __u32 btf_token_fd; }; struct { -- cgit From e1cef620f598853a90f17701fcb1057a6768f7b8 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 30 Nov 2023 10:52:18 -0800 Subject: bpf: add BPF token support to BPF_PROG_LOAD command Add basic support of BPF token to BPF_PROG_LOAD. Wire through a set of allowed BPF program types and attach types, derived from BPF FS at BPF token creation time. Then make sure we perform bpf_token_capable() checks everywhere where it's relevant. Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231130185229.2688956-7-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 6 ++ include/uapi/linux/bpf.h | 2 + kernel/bpf/core.c | 1 + kernel/bpf/inode.c | 6 +- kernel/bpf/syscall.c | 87 ++++++++++++++++------ kernel/bpf/token.c | 27 +++++++ tools/include/uapi/linux/bpf.h | 2 + .../selftests/bpf/prog_tests/libbpf_probes.c | 2 + .../testing/selftests/bpf/prog_tests/libbpf_str.c | 3 + 9 files changed, 110 insertions(+), 26 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e08e8436df38..20af87b59d70 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1461,6 +1461,7 @@ struct bpf_prog_aux { #ifdef CONFIG_SECURITY void *security; #endif + struct bpf_token *token; struct bpf_prog_offload *offload; struct btf *btf; struct bpf_func_info *func_info; @@ -1601,6 +1602,8 @@ struct bpf_token { struct user_namespace *userns; u64 allowed_cmds; u64 allowed_maps; + u64 allowed_progs; + u64 allowed_attachs; }; struct bpf_struct_ops_value; @@ -2238,6 +2241,9 @@ struct bpf_token *bpf_token_get_from_fd(u32 ufd); bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type); +bool bpf_token_allow_prog_type(const struct bpf_token *token, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type); int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9f9989e0d062..4df2d025c784 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1028,6 +1028,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ BPF_PROG_TYPE_NETFILTER, + __MAX_BPF_PROG_TYPE }; enum bpf_attach_type { @@ -1504,6 +1505,7 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 log_true_size; + __u32 prog_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 4b813da8d6c0..47085839af8d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2751,6 +2751,7 @@ void bpf_prog_free(struct bpf_prog *fp) if (aux->dst_prog) bpf_prog_put(aux->dst_prog); + bpf_token_put(aux->token); INIT_WORK(&aux->work, bpf_prog_free_deferred); schedule_work(&aux->work); } diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 9c7865d1c53d..5359a0929c35 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -619,12 +619,14 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) else if (opts->delegate_maps) seq_printf(m, ",delegate_maps=0x%llx", opts->delegate_maps); - if (opts->delegate_progs == ~0ULL) + mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; + if ((opts->delegate_progs & mask) == mask) seq_printf(m, ",delegate_progs=any"); else if (opts->delegate_progs) seq_printf(m, ",delegate_progs=0x%llx", opts->delegate_progs); - if (opts->delegate_attachs == ~0ULL) + mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; + if ((opts->delegate_attachs & mask) == mask) seq_printf(m, ",delegate_attachs=any"); else if (opts->delegate_attachs) seq_printf(m, ",delegate_attachs=0x%llx", opts->delegate_attachs); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index d87c5c27cde3..2c8393c21b8c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2608,13 +2608,15 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD log_true_size +#define BPF_PROG_LOAD_LAST_FIELD prog_token_fd static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog, *dst_prog = NULL; struct btf *attach_btf = NULL; + struct bpf_token *token = NULL; + bool bpf_cap; int err; char license[128]; @@ -2631,10 +2633,31 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) BPF_F_TEST_REG_INVARIANTS)) return -EINVAL; + bpf_prog_load_fixup_attach_type(attr); + + if (attr->prog_token_fd) { + token = bpf_token_get_from_fd(attr->prog_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + /* if current token doesn't grant prog loading permissions, + * then we can't use this token, so ignore it and rely on + * system-wide capabilities checks + */ + if (!bpf_token_allow_cmd(token, BPF_PROG_LOAD) || + !bpf_token_allow_prog_type(token, attr->prog_type, + attr->expected_attach_type)) { + bpf_token_put(token); + token = NULL; + } + } + + bpf_cap = bpf_token_capable(token, CAP_BPF); + err = -EPERM; + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && - !bpf_capable()) - return -EPERM; + !bpf_cap) + goto put_token; /* Intent here is for unprivileged_bpf_disabled to block BPF program * creation for unprivileged users; other actions depend @@ -2643,21 +2666,23 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) * capability checks are still carried out for these * and other operations. */ - if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) - return -EPERM; + if (sysctl_unprivileged_bpf_disabled && !bpf_cap) + goto put_token; if (attr->insn_cnt == 0 || - attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) - return -E2BIG; + attr->insn_cnt > (bpf_cap ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) { + err = -E2BIG; + goto put_token; + } if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && - !bpf_capable()) - return -EPERM; + !bpf_cap) + goto put_token; - if (is_net_admin_prog_type(type) && !bpf_net_capable()) - return -EPERM; - if (is_perfmon_prog_type(type) && !perfmon_capable()) - return -EPERM; + if (is_net_admin_prog_type(type) && !bpf_token_capable(token, CAP_NET_ADMIN)) + goto put_token; + if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON)) + goto put_token; /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog * or btf, we need to check which one it is @@ -2667,27 +2692,33 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (IS_ERR(dst_prog)) { dst_prog = NULL; attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); - if (IS_ERR(attach_btf)) - return -EINVAL; + if (IS_ERR(attach_btf)) { + err = -EINVAL; + goto put_token; + } if (!btf_is_kernel(attach_btf)) { /* attaching through specifying bpf_prog's BTF * objects directly might be supported eventually */ btf_put(attach_btf); - return -ENOTSUPP; + err = -ENOTSUPP; + goto put_token; } } } else if (attr->attach_btf_id) { /* fall back to vmlinux BTF, if BTF type ID is specified */ attach_btf = bpf_get_btf_vmlinux(); - if (IS_ERR(attach_btf)) - return PTR_ERR(attach_btf); - if (!attach_btf) - return -EINVAL; + if (IS_ERR(attach_btf)) { + err = PTR_ERR(attach_btf); + goto put_token; + } + if (!attach_btf) { + err = -EINVAL; + goto put_token; + } btf_get(attach_btf); } - bpf_prog_load_fixup_attach_type(attr); if (bpf_prog_load_check_attach(type, attr->expected_attach_type, attach_btf, attr->attach_btf_id, dst_prog)) { @@ -2695,7 +2726,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - return -EINVAL; + err = -EINVAL; + goto put_token; } /* plain bpf_prog allocation */ @@ -2705,7 +2737,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - return -ENOMEM; + err = -EINVAL; + goto put_token; } prog->expected_attach_type = attr->expected_attach_type; @@ -2716,6 +2749,10 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; + /* move token into prog->aux, reuse taken refcnt */ + prog->aux->token = token; + token = NULL; + err = security_bpf_prog_alloc(prog->aux); if (err) goto free_prog; @@ -2817,6 +2854,8 @@ free_prog: if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); bpf_prog_free(prog); +put_token: + bpf_token_put(token); return err; } @@ -3806,7 +3845,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, case BPF_PROG_TYPE_SK_LOOKUP: return attach_type == prog->expected_attach_type ? 0 : -EINVAL; case BPF_PROG_TYPE_CGROUP_SKB: - if (!bpf_net_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_NET_ADMIN)) /* cg-skb progs can be loaded by unpriv user. * check permissions at attach time. */ diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c index 06c34dae658e..5a51e6b8f6bf 100644 --- a/kernel/bpf/token.c +++ b/kernel/bpf/token.c @@ -79,6 +79,20 @@ static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) seq_printf(m, "allowed_maps:\tany\n"); else seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); + + BUILD_BUG_ON(__MAX_BPF_PROG_TYPE >= 64); + mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; + if ((token->allowed_progs & mask) == mask) + seq_printf(m, "allowed_progs:\tany\n"); + else + seq_printf(m, "allowed_progs:\t0x%llx\n", token->allowed_progs); + + BUILD_BUG_ON(__MAX_BPF_ATTACH_TYPE >= 64); + mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; + if ((token->allowed_attachs & mask) == mask) + seq_printf(m, "allowed_attachs:\tany\n"); + else + seq_printf(m, "allowed_attachs:\t0x%llx\n", token->allowed_attachs); } #define BPF_TOKEN_INODE_NAME "bpf-token" @@ -169,6 +183,8 @@ int bpf_token_create(union bpf_attr *attr) mnt_opts = path.dentry->d_sb->s_fs_info; token->allowed_cmds = mnt_opts->delegate_cmds; token->allowed_maps = mnt_opts->delegate_maps; + token->allowed_progs = mnt_opts->delegate_progs; + token->allowed_attachs = mnt_opts->delegate_attachs; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { @@ -228,3 +244,14 @@ bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type t return token->allowed_maps & (1ULL << type); } + +bool bpf_token_allow_prog_type(const struct bpf_token *token, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type) +{ + if (!token || prog_type >= __MAX_BPF_PROG_TYPE || attach_type >= __MAX_BPF_ATTACH_TYPE) + return false; + + return (token->allowed_progs & (1ULL << prog_type)) && + (token->allowed_attachs & (1ULL << attach_type)); +} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 9f9989e0d062..4df2d025c784 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1028,6 +1028,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ BPF_PROG_TYPE_NETFILTER, + __MAX_BPF_PROG_TYPE }; enum bpf_attach_type { @@ -1504,6 +1505,7 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 log_true_size; + __u32 prog_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c index 573249a2814d..4ed46ed58a7b 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c @@ -30,6 +30,8 @@ void test_libbpf_probe_prog_types(void) if (prog_type == BPF_PROG_TYPE_UNSPEC) continue; + if (strcmp(prog_type_name, "__MAX_BPF_PROG_TYPE") == 0) + continue; if (!test__start_subtest(prog_type_name)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c index 2a0633f43c73..384bc1f7a65e 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c @@ -189,6 +189,9 @@ static void test_libbpf_bpf_prog_type_str(void) const char *prog_type_str; char buf[256]; + if (prog_type == __MAX_BPF_PROG_TYPE) + continue; + prog_type_name = btf__str_by_offset(btf, e->name_off); prog_type_str = libbpf_bpf_prog_type_str(prog_type); ASSERT_OK_PTR(prog_type_str, prog_type_name); -- cgit From 7065eefb38f16c91e9ace36fb7c873e4c9857c27 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 6 Dec 2023 11:09:20 -0800 Subject: bpf: rename MAX_BPF_LINK_TYPE into __MAX_BPF_LINK_TYPE for consistency To stay consistent with the naming pattern used for similar cases in BPF UAPI (__MAX_BPF_ATTACH_TYPE, etc), rename MAX_BPF_LINK_TYPE into __MAX_BPF_LINK_TYPE. Also similar to MAX_BPF_ATTACH_TYPE and MAX_BPF_REG, add: #define MAX_BPF_LINK_TYPE __MAX_BPF_LINK_TYPE Not all __MAX_xxx enums have such #define, so I'm not sure if we should add it or not, but I figured I'll start with a completely backwards compatible way, and we can drop that, if necessary. Also adjust a selftest that used MAX_BPF_LINK_TYPE enum. Suggested-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20231206190920.1651226-1-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 4 +++- tools/include/uapi/linux/bpf.h | 4 +++- tools/testing/selftests/bpf/prog_tests/libbpf_str.c | 2 +- 3 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4df2d025c784..e0545201b55f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1108,9 +1108,11 @@ enum bpf_link_type { BPF_LINK_TYPE_TCX = 11, BPF_LINK_TYPE_UPROBE_MULTI = 12, BPF_LINK_TYPE_NETKIT = 13, - MAX_BPF_LINK_TYPE, + __MAX_BPF_LINK_TYPE, }; +#define MAX_BPF_LINK_TYPE __MAX_BPF_LINK_TYPE + enum bpf_perf_event_type { BPF_PERF_EVENT_UNSPEC = 0, BPF_PERF_EVENT_UPROBE = 1, diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 4df2d025c784..e0545201b55f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1108,9 +1108,11 @@ enum bpf_link_type { BPF_LINK_TYPE_TCX = 11, BPF_LINK_TYPE_UPROBE_MULTI = 12, BPF_LINK_TYPE_NETKIT = 13, - MAX_BPF_LINK_TYPE, + __MAX_BPF_LINK_TYPE, }; +#define MAX_BPF_LINK_TYPE __MAX_BPF_LINK_TYPE + enum bpf_perf_event_type { BPF_PERF_EVENT_UNSPEC = 0, BPF_PERF_EVENT_UPROBE = 1, diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c index 384bc1f7a65e..62ea855ec4d0 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c @@ -87,7 +87,7 @@ static void test_libbpf_bpf_link_type_str(void) const char *link_type_str; char buf[256]; - if (link_type == MAX_BPF_LINK_TYPE) + if (link_type == __MAX_BPF_LINK_TYPE) continue; link_type_name = btf__str_by_offset(btf, e->name_off); -- cgit From cb46fca88d14939da2785567253d0a297f31be27 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 29 Aug 2023 08:20:14 -0700 Subject: cxl: Add Support for Get Timestamp Add the call to the UAPI such that userspace may corelate the timestamps from the device log with system wall time, if, for example there's any sort of inaccuracy or skew in the device. Signed-off-by: Davidlohr Bueso Reviewed-by: Dave Jiang Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/20230829152014.15452-1-dave@stgolabs.net Signed-off-by: Dan Williams --- drivers/cxl/core/mbox.c | 1 + drivers/cxl/cxlmem.h | 1 + include/uapi/linux/cxl_mem.h | 1 + 3 files changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 36270dcfb42e..b86dbd25740c 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -63,6 +63,7 @@ static struct cxl_mem_command cxl_mem_commands[CXL_MEM_COMMAND_ID_MAX] = { CXL_CMD(GET_SHUTDOWN_STATE, 0, 0x1, 0), CXL_CMD(SET_SHUTDOWN_STATE, 0x1, 0, 0), CXL_CMD(GET_SCAN_MEDIA_CAPS, 0x10, 0x4, 0), + CXL_CMD(GET_TIMESTAMP, 0, 0x8, 0), }; /* diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index a2fcbca253f3..6a6becee402b 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -503,6 +503,7 @@ enum cxl_opcode { CXL_MBOX_OP_GET_FW_INFO = 0x0200, CXL_MBOX_OP_TRANSFER_FW = 0x0201, CXL_MBOX_OP_ACTIVATE_FW = 0x0202, + CXL_MBOX_OP_GET_TIMESTAMP = 0x0300, CXL_MBOX_OP_SET_TIMESTAMP = 0x0301, CXL_MBOX_OP_GET_SUPPORTED_LOGS = 0x0400, CXL_MBOX_OP_GET_LOG = 0x0401, diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index 14bc6e742148..42066f4eb890 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -46,6 +46,7 @@ ___C(GET_SCAN_MEDIA_CAPS, "Get Scan Media Capabilities"), \ ___DEPRECATED(SCAN_MEDIA, "Scan Media"), \ ___DEPRECATED(GET_SCAN_MEDIA, "Get Scan Media Results"), \ + ___C(GET_TIMESTAMP, "Get Timestamp"), \ ___C(MAX, "invalid / last command") #define ___C(a, b) CXL_MEM_COMMAND_ID_##a -- cgit From 6d72283526090850274d065cd5d60af732cc5fc8 Mon Sep 17 00:00:00 2001 From: Paul Durrant Date: Thu, 2 Nov 2023 16:21:28 +0000 Subject: KVM x86/xen: add an override for PVCLOCK_TSC_STABLE_BIT Unless explicitly told to do so (by passing 'clocksource=tsc' and 'tsc=stable:socket', and then jumping through some hoops concerning potential CPU hotplug) Xen will never use TSC as its clocksource. Hence, by default, a Xen guest will not see PVCLOCK_TSC_STABLE_BIT set in either the primary or secondary pvclock memory areas. This has led to bugs in some guest kernels which only become evident if PVCLOCK_TSC_STABLE_BIT *is* set in the pvclocks. Hence, to support such guests, give the VMM a new Xen HVM config flag to tell KVM to forcibly clear the bit in the Xen pvclocks. Signed-off-by: Paul Durrant Reviewed-by: David Woodhouse Link: https://lore.kernel.org/r/20231102162128.2353459-1-paul@xen.org Signed-off-by: Sean Christopherson --- Documentation/virt/kvm/api.rst | 6 ++++++ arch/x86/kvm/x86.c | 28 +++++++++++++++++++++++----- arch/x86/kvm/xen.c | 9 ++++++++- include/uapi/linux/kvm.h | 1 + 4 files changed, 38 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 926241e23aeb..dca83c65d97f 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -8562,6 +8562,7 @@ PVHVM guests. Valid flags are:: #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6) + #define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7) The KVM_XEN_HVM_CONFIG_HYPERCALL_MSR flag indicates that the KVM_XEN_HVM_CONFIG ioctl is available, for the guest to set its hypercall page. @@ -8605,6 +8606,11 @@ behave more correctly, not using the XEN_RUNSTATE_UPDATE flag until/unless specifically enabled (by the guest making the hypercall, causing the VMM to enable the KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG attribute). +The KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE flag indicates that KVM supports +clearing the PVCLOCK_TSC_STABLE_BIT flag in Xen pvclock sources. This will be +done when the KVM_CAP_XEN_HVM ioctl sets the +KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE flag. + 8.31 KVM_CAP_PPC_MULTITCE ------------------------- diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6d0772b47041..aa7cea9600b0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3104,7 +3104,8 @@ u64 get_kvmclock_ns(struct kvm *kvm) static void kvm_setup_guest_pvclock(struct kvm_vcpu *v, struct gfn_to_pfn_cache *gpc, - unsigned int offset) + unsigned int offset, + bool force_tsc_unstable) { struct kvm_vcpu_arch *vcpu = &v->arch; struct pvclock_vcpu_time_info *guest_hv_clock; @@ -3141,6 +3142,10 @@ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v, } memcpy(guest_hv_clock, &vcpu->hv_clock, sizeof(*guest_hv_clock)); + + if (force_tsc_unstable) + guest_hv_clock->flags &= ~PVCLOCK_TSC_STABLE_BIT; + smp_wmb(); guest_hv_clock->version = ++vcpu->hv_clock.version; @@ -3161,6 +3166,16 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) u64 tsc_timestamp, host_tsc; u8 pvclock_flags; bool use_master_clock; +#ifdef CONFIG_KVM_XEN + /* + * For Xen guests we may need to override PVCLOCK_TSC_STABLE_BIT as unless + * explicitly told to use TSC as its clocksource Xen will not set this bit. + * This default behaviour led to bugs in some guest kernels which cause + * problems if they observe PVCLOCK_TSC_STABLE_BIT in the pvclock flags. + */ + bool xen_pvclock_tsc_unstable = + ka->xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE; +#endif kernel_ns = 0; host_tsc = 0; @@ -3239,13 +3254,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->hv_clock.flags = pvclock_flags; if (vcpu->pv_time.active) - kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0); + kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0, false); #ifdef CONFIG_KVM_XEN if (vcpu->xen.vcpu_info_cache.active) kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_info_cache, - offsetof(struct compat_vcpu_info, time)); + offsetof(struct compat_vcpu_info, time), + xen_pvclock_tsc_unstable); if (vcpu->xen.vcpu_time_info_cache.active) - kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0); + kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0, + xen_pvclock_tsc_unstable); #endif kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; @@ -4646,7 +4663,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | KVM_XEN_HVM_CONFIG_SHARED_INFO | KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL | - KVM_XEN_HVM_CONFIG_EVTCHN_SEND; + KVM_XEN_HVM_CONFIG_EVTCHN_SEND | + KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE; if (sched_info_on()) r |= KVM_XEN_HVM_CONFIG_RUNSTATE | KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG; diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index e53fad915a62..e43948b87f94 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -1162,7 +1162,9 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) { /* Only some feature flags need to be *enabled* by userspace */ u32 permitted_flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | - KVM_XEN_HVM_CONFIG_EVTCHN_SEND; + KVM_XEN_HVM_CONFIG_EVTCHN_SEND | + KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE; + u32 old_flags; if (xhc->flags & ~permitted_flags) return -EINVAL; @@ -1183,9 +1185,14 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) else if (!xhc->msr && kvm->arch.xen_hvm_config.msr) static_branch_slow_dec_deferred(&kvm_xen_enabled); + old_flags = kvm->arch.xen_hvm_config.flags; memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc)); mutex_unlock(&kvm->arch.xen.xen_lock); + + if ((old_flags ^ xhc->flags) & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE) + kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE); + return 0; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index e9cb2df67a1d..175420b26e36 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1318,6 +1318,7 @@ struct kvm_x86_mce { #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6) +#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7) struct kvm_xen_hvm_config { __u32 flags; -- cgit From a5d3df8ae13fada772fbce952e9ee7b3433dba16 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 8 Nov 2023 10:34:03 +0100 Subject: KVM: remove deprecated UAPIs The deprecated interfaces were removed 15 years ago. KVM's device assignment was deprecated in 4.2 and removed 6.5 years ago; the only interest might be in compiling ancient versions of QEMU, but QEMU has been using its own imported copy of the kernel headers since June 2011. So again we go into archaeology territory; just remove the cruft. Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 12 ------ include/uapi/linux/kvm.h | 90 ------------------------------------------ virt/kvm/kvm_main.c | 5 --- 3 files changed, 107 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 926241e23aeb..9326af2a4869 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -627,18 +627,6 @@ interrupt number dequeues the interrupt. This is an asynchronous vcpu ioctl and can be invoked from any thread. -4.17 KVM_DEBUG_GUEST --------------------- - -:Capability: basic -:Architectures: none -:Type: vcpu ioctl -:Parameters: none) -:Returns: -1 on error - -Support for this has been removed. Use KVM_SET_GUEST_DEBUG instead. - - 4.18 KVM_GET_MSRS ----------------- diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index e9cb2df67a1d..b1f92a0edc35 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -16,76 +16,6 @@ #define KVM_API_VERSION 12 -/* *** Deprecated interfaces *** */ - -#define KVM_TRC_SHIFT 16 - -#define KVM_TRC_ENTRYEXIT (1 << KVM_TRC_SHIFT) -#define KVM_TRC_HANDLER (1 << (KVM_TRC_SHIFT + 1)) - -#define KVM_TRC_VMENTRY (KVM_TRC_ENTRYEXIT + 0x01) -#define KVM_TRC_VMEXIT (KVM_TRC_ENTRYEXIT + 0x02) -#define KVM_TRC_PAGE_FAULT (KVM_TRC_HANDLER + 0x01) - -#define KVM_TRC_HEAD_SIZE 12 -#define KVM_TRC_CYCLE_SIZE 8 -#define KVM_TRC_EXTRA_MAX 7 - -#define KVM_TRC_INJ_VIRQ (KVM_TRC_HANDLER + 0x02) -#define KVM_TRC_REDELIVER_EVT (KVM_TRC_HANDLER + 0x03) -#define KVM_TRC_PEND_INTR (KVM_TRC_HANDLER + 0x04) -#define KVM_TRC_IO_READ (KVM_TRC_HANDLER + 0x05) -#define KVM_TRC_IO_WRITE (KVM_TRC_HANDLER + 0x06) -#define KVM_TRC_CR_READ (KVM_TRC_HANDLER + 0x07) -#define KVM_TRC_CR_WRITE (KVM_TRC_HANDLER + 0x08) -#define KVM_TRC_DR_READ (KVM_TRC_HANDLER + 0x09) -#define KVM_TRC_DR_WRITE (KVM_TRC_HANDLER + 0x0A) -#define KVM_TRC_MSR_READ (KVM_TRC_HANDLER + 0x0B) -#define KVM_TRC_MSR_WRITE (KVM_TRC_HANDLER + 0x0C) -#define KVM_TRC_CPUID (KVM_TRC_HANDLER + 0x0D) -#define KVM_TRC_INTR (KVM_TRC_HANDLER + 0x0E) -#define KVM_TRC_NMI (KVM_TRC_HANDLER + 0x0F) -#define KVM_TRC_VMMCALL (KVM_TRC_HANDLER + 0x10) -#define KVM_TRC_HLT (KVM_TRC_HANDLER + 0x11) -#define KVM_TRC_CLTS (KVM_TRC_HANDLER + 0x12) -#define KVM_TRC_LMSW (KVM_TRC_HANDLER + 0x13) -#define KVM_TRC_APIC_ACCESS (KVM_TRC_HANDLER + 0x14) -#define KVM_TRC_TDP_FAULT (KVM_TRC_HANDLER + 0x15) -#define KVM_TRC_GTLB_WRITE (KVM_TRC_HANDLER + 0x16) -#define KVM_TRC_STLB_WRITE (KVM_TRC_HANDLER + 0x17) -#define KVM_TRC_STLB_INVAL (KVM_TRC_HANDLER + 0x18) -#define KVM_TRC_PPC_INSTR (KVM_TRC_HANDLER + 0x19) - -struct kvm_user_trace_setup { - __u32 buf_size; - __u32 buf_nr; -}; - -#define __KVM_DEPRECATED_MAIN_W_0x06 \ - _IOW(KVMIO, 0x06, struct kvm_user_trace_setup) -#define __KVM_DEPRECATED_MAIN_0x07 _IO(KVMIO, 0x07) -#define __KVM_DEPRECATED_MAIN_0x08 _IO(KVMIO, 0x08) - -#define __KVM_DEPRECATED_VM_R_0x70 _IOR(KVMIO, 0x70, struct kvm_assigned_irq) - -struct kvm_breakpoint { - __u32 enabled; - __u32 padding; - __u64 address; -}; - -struct kvm_debug_guest { - __u32 enabled; - __u32 pad; - struct kvm_breakpoint breakpoints[4]; - __u32 singlestep; -}; - -#define __KVM_DEPRECATED_VCPU_W_0x87 _IOW(KVMIO, 0x87, struct kvm_debug_guest) - -/* *** End of deprecated interfaces *** */ - - /* for KVM_SET_USER_MEMORY_REGION */ struct kvm_userspace_memory_region { __u32 slot; @@ -967,9 +897,6 @@ struct kvm_ppc_resize_hpt { */ #define KVM_GET_VCPU_MMAP_SIZE _IO(KVMIO, 0x04) /* in bytes */ #define KVM_GET_SUPPORTED_CPUID _IOWR(KVMIO, 0x05, struct kvm_cpuid2) -#define KVM_TRACE_ENABLE __KVM_DEPRECATED_MAIN_W_0x06 -#define KVM_TRACE_PAUSE __KVM_DEPRECATED_MAIN_0x07 -#define KVM_TRACE_DISABLE __KVM_DEPRECATED_MAIN_0x08 #define KVM_GET_EMULATED_CPUID _IOWR(KVMIO, 0x09, struct kvm_cpuid2) #define KVM_GET_MSR_FEATURE_INDEX_LIST _IOWR(KVMIO, 0x0a, struct kvm_msr_list) @@ -1536,20 +1463,8 @@ struct kvm_s390_ucas_mapping { _IOW(KVMIO, 0x67, struct kvm_coalesced_mmio_zone) #define KVM_UNREGISTER_COALESCED_MMIO \ _IOW(KVMIO, 0x68, struct kvm_coalesced_mmio_zone) -#define KVM_ASSIGN_PCI_DEVICE _IOR(KVMIO, 0x69, \ - struct kvm_assigned_pci_dev) #define KVM_SET_GSI_ROUTING _IOW(KVMIO, 0x6a, struct kvm_irq_routing) -/* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */ -#define KVM_ASSIGN_IRQ __KVM_DEPRECATED_VM_R_0x70 -#define KVM_ASSIGN_DEV_IRQ _IOW(KVMIO, 0x70, struct kvm_assigned_irq) #define KVM_REINJECT_CONTROL _IO(KVMIO, 0x71) -#define KVM_DEASSIGN_PCI_DEVICE _IOW(KVMIO, 0x72, \ - struct kvm_assigned_pci_dev) -#define KVM_ASSIGN_SET_MSIX_NR _IOW(KVMIO, 0x73, \ - struct kvm_assigned_msix_nr) -#define KVM_ASSIGN_SET_MSIX_ENTRY _IOW(KVMIO, 0x74, \ - struct kvm_assigned_msix_entry) -#define KVM_DEASSIGN_DEV_IRQ _IOW(KVMIO, 0x75, struct kvm_assigned_irq) #define KVM_IRQFD _IOW(KVMIO, 0x76, struct kvm_irqfd) #define KVM_CREATE_PIT2 _IOW(KVMIO, 0x77, struct kvm_pit_config) #define KVM_SET_BOOT_CPU_ID _IO(KVMIO, 0x78) @@ -1566,9 +1481,6 @@ struct kvm_s390_ucas_mapping { * KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */ #define KVM_SET_TSC_KHZ _IO(KVMIO, 0xa2) #define KVM_GET_TSC_KHZ _IO(KVMIO, 0xa3) -/* Available with KVM_CAP_PCI_2_3 */ -#define KVM_ASSIGN_SET_INTX_MASK _IOW(KVMIO, 0xa4, \ - struct kvm_assigned_pci_dev) /* Available with KVM_CAP_SIGNAL_MSI */ #define KVM_SIGNAL_MSI _IOW(KVMIO, 0xa5, struct kvm_msi) /* Available with KVM_CAP_PPC_GET_SMMU_INFO */ @@ -1621,8 +1533,6 @@ struct kvm_s390_ucas_mapping { #define KVM_SET_SREGS _IOW(KVMIO, 0x84, struct kvm_sregs) #define KVM_TRANSLATE _IOWR(KVMIO, 0x85, struct kvm_translation) #define KVM_INTERRUPT _IOW(KVMIO, 0x86, struct kvm_interrupt) -/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */ -#define KVM_DEBUG_GUEST __KVM_DEPRECATED_VCPU_W_0x87 #define KVM_GET_MSRS _IOWR(KVMIO, 0x88, struct kvm_msrs) #define KVM_SET_MSRS _IOW(KVMIO, 0x89, struct kvm_msrs) #define KVM_SET_CPUID _IOW(KVMIO, 0x8a, struct kvm_cpuid) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a20cf1f9ad29..acd67fb40183 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5497,11 +5497,6 @@ static long kvm_dev_ioctl(struct file *filp, r += PAGE_SIZE; /* coalesced mmio ring page */ #endif break; - case KVM_TRACE_ENABLE: - case KVM_TRACE_PAUSE: - case KVM_TRACE_DISABLE: - r = -EOPNOTSUPP; - break; default: return kvm_arch_dev_ioctl(filp, ioctl, arg); } -- cgit From e6a9a2cbc13bf43e4c03f57666e93d511249d5d7 Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Mon, 6 Nov 2023 14:09:58 -0800 Subject: fs/proc/task_mmu: report SOFT_DIRTY bits through the PAGEMAP_SCAN ioctl MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The PAGEMAP_SCAN ioctl returns information regarding page table entries. It is more efficient compared to reading pagemap files. CRIU can start to utilize this ioctl, but it needs info about soft-dirty bits to track memory changes. We are aware of a new method for tracking memory changes implemented in the PAGEMAP_SCAN ioctl. For CRIU, the primary advantage of this method is its usability by unprivileged users. However, it is not feasible to transparently replace the soft-dirty tracker with the new one. The main problem here is userfault descriptors that have to be preserved between pre-dump iterations. It means criu continues supporting the soft-dirty method to avoid breakage for current users. The new method will be implemented as a separate feature. [avagin@google.com: update tools/include/uapi/linux/fs.h] Link: https://lkml.kernel.org/r/20231107164139.576046-1-avagin@google.com Link: https://lkml.kernel.org/r/20231106220959.296568-1-avagin@google.com Signed-off-by: Andrei Vagin Reviewed-by: Muhammad Usama Anjum Cc: Michał Mirosław Signed-off-by: Andrew Morton --- Documentation/admin-guide/mm/pagemap.rst | 1 + fs/proc/task_mmu.c | 17 ++++++++++++++++- include/uapi/linux/fs.h | 1 + tools/include/uapi/linux/fs.h | 1 + 4 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/admin-guide/mm/pagemap.rst b/Documentation/admin-guide/mm/pagemap.rst index fe17cf210426..f5f065c67615 100644 --- a/Documentation/admin-guide/mm/pagemap.rst +++ b/Documentation/admin-guide/mm/pagemap.rst @@ -253,6 +253,7 @@ Following flags about pages are currently supported: - ``PAGE_IS_SWAPPED`` - Page is in swapped - ``PAGE_IS_PFNZERO`` - Page has zero PFN - ``PAGE_IS_HUGE`` - Page is THP or Hugetlb backed +- ``PAGE_IS_SOFT_DIRTY`` - Page is soft-dirty The ``struct pm_scan_arg`` is used as the argument of the IOCTL. diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 435b61054b5b..d19924bf0a39 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1761,7 +1761,7 @@ static int pagemap_release(struct inode *inode, struct file *file) #define PM_SCAN_CATEGORIES (PAGE_IS_WPALLOWED | PAGE_IS_WRITTEN | \ PAGE_IS_FILE | PAGE_IS_PRESENT | \ PAGE_IS_SWAPPED | PAGE_IS_PFNZERO | \ - PAGE_IS_HUGE) + PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY) #define PM_SCAN_FLAGS (PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC) struct pagemap_scan_private { @@ -1793,6 +1793,8 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p, if (is_zero_pfn(pte_pfn(pte))) categories |= PAGE_IS_PFNZERO; + if (pte_soft_dirty(pte)) + categories |= PAGE_IS_SOFT_DIRTY; } else if (is_swap_pte(pte)) { swp_entry_t swp; @@ -1806,6 +1808,8 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p, !PageAnon(pfn_swap_entry_to_page(swp))) categories |= PAGE_IS_FILE; } + if (pte_swp_soft_dirty(pte)) + categories |= PAGE_IS_SOFT_DIRTY; } return categories; @@ -1853,12 +1857,16 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p, if (is_zero_pfn(pmd_pfn(pmd))) categories |= PAGE_IS_PFNZERO; + if (pmd_soft_dirty(pmd)) + categories |= PAGE_IS_SOFT_DIRTY; } else if (is_swap_pmd(pmd)) { swp_entry_t swp; categories |= PAGE_IS_SWAPPED; if (!pmd_swp_uffd_wp(pmd)) categories |= PAGE_IS_WRITTEN; + if (pmd_swp_soft_dirty(pmd)) + categories |= PAGE_IS_SOFT_DIRTY; if (p->masks_of_interest & PAGE_IS_FILE) { swp = pmd_to_swp_entry(pmd); @@ -1905,10 +1913,14 @@ static unsigned long pagemap_hugetlb_category(pte_t pte) categories |= PAGE_IS_FILE; if (is_zero_pfn(pte_pfn(pte))) categories |= PAGE_IS_PFNZERO; + if (pte_soft_dirty(pte)) + categories |= PAGE_IS_SOFT_DIRTY; } else if (is_swap_pte(pte)) { categories |= PAGE_IS_SWAPPED; if (!pte_swp_uffd_wp_any(pte)) categories |= PAGE_IS_WRITTEN; + if (pte_swp_soft_dirty(pte)) + categories |= PAGE_IS_SOFT_DIRTY; } return categories; @@ -2007,6 +2019,9 @@ static int pagemap_scan_test_walk(unsigned long start, unsigned long end, if (wp_allowed) vma_category |= PAGE_IS_WPALLOWED; + if (vma->vm_flags & VM_SOFTDIRTY) + vma_category |= PAGE_IS_SOFT_DIRTY; + if (!pagemap_scan_is_interesting_vma(vma_category, p)) return 1; diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index da43810b7485..48ad69f7722e 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -316,6 +316,7 @@ typedef int __bitwise __kernel_rwf_t; #define PAGE_IS_SWAPPED (1 << 4) #define PAGE_IS_PFNZERO (1 << 5) #define PAGE_IS_HUGE (1 << 6) +#define PAGE_IS_SOFT_DIRTY (1 << 7) /* * struct page_region - Page region with flags diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h index da43810b7485..48ad69f7722e 100644 --- a/tools/include/uapi/linux/fs.h +++ b/tools/include/uapi/linux/fs.h @@ -316,6 +316,7 @@ typedef int __bitwise __kernel_rwf_t; #define PAGE_IS_SWAPPED (1 << 4) #define PAGE_IS_PFNZERO (1 << 5) #define PAGE_IS_HUGE (1 << 6) +#define PAGE_IS_SOFT_DIRTY (1 << 7) /* * struct page_region - Page region with flags -- cgit From 46eae99ef73302f9fb3dddcd67c374b3dffe8fd6 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 25 Oct 2023 16:02:02 +0200 Subject: add statmount(2) syscall Add a way to query attributes of a single mount instead of having to parse the complete /proc/$PID/mountinfo, which might be huge. Lookup the mount the new 64bit mount ID. If a mount needs to be queried based on path, then statx(2) can be used to first query the mount ID belonging to the path. Design is based on a suggestion by Linus: "So I'd suggest something that is very much like "statfsat()", which gets a buffer and a length, and returns an extended "struct statfs" *AND* just a string description at the end." The interface closely mimics that of statx. Handle ASCII attributes by appending after the end of the structure (as per above suggestion). Pointers to strings are stored in u64 members to make the structure the same regardless of pointer size. Strings are nul terminated. Link: https://lore.kernel.org/all/CAHk-=wh5YifP7hzKSbwJj94+DZ2czjrZsczy6GBimiogZws=rg@mail.gmail.com/ Signed-off-by: Miklos Szeredi Link: https://lore.kernel.org/r/20231025140205.3586473-5-mszeredi@redhat.com Reviewed-by: Ian Kent [Christian Brauner : various minor changes] Signed-off-by: Christian Brauner --- fs/namespace.c | 281 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/syscalls.h | 5 + include/uapi/linux/mount.h | 53 +++++++++ 3 files changed, 339 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/namespace.c b/fs/namespace.c index d3665d025acb..ae35d8b6aca8 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4683,6 +4683,287 @@ int show_path(struct seq_file *m, struct dentry *root) return 0; } +static struct vfsmount *lookup_mnt_in_ns(u64 id, struct mnt_namespace *ns) +{ + struct mount *mnt = mnt_find_id_at(ns, id); + + if (!mnt || mnt->mnt_id_unique != id) + return NULL; + + return &mnt->mnt; +} + +struct kstatmount { + struct statmount __user *const buf; + size_t const bufsize; + struct vfsmount *const mnt; + u64 const mask; + struct seq_file seq; + struct path root; + struct statmount sm; + size_t pos; + int err; +}; + +typedef int (*statmount_func_t)(struct kstatmount *); + +static int statmount_string_seq(struct kstatmount *s, statmount_func_t func) +{ + size_t rem = s->bufsize - s->pos - sizeof(s->sm); + struct seq_file *seq = &s->seq; + int ret; + + seq->count = 0; + seq->size = min(seq->size, rem); + seq->buf = kvmalloc(seq->size, GFP_KERNEL_ACCOUNT); + if (!seq->buf) + return -ENOMEM; + + ret = func(s); + if (ret) + return ret; + + if (seq_has_overflowed(seq)) { + if (seq->size == rem) + return -EOVERFLOW; + seq->size *= 2; + if (seq->size > MAX_RW_COUNT) + return -ENOMEM; + kvfree(seq->buf); + return 0; + } + + /* Done */ + return 1; +} + +static void statmount_string(struct kstatmount *s, u64 mask, statmount_func_t func, + u32 *str) +{ + int ret = s->pos + sizeof(s->sm) >= s->bufsize ? -EOVERFLOW : 0; + struct statmount *sm = &s->sm; + struct seq_file *seq = &s->seq; + + if (s->err || !(s->mask & mask)) + return; + + seq->size = PAGE_SIZE; + while (!ret) + ret = statmount_string_seq(s, func); + + if (ret < 0) { + s->err = ret; + } else { + seq->buf[seq->count++] = '\0'; + if (copy_to_user(s->buf->str + s->pos, seq->buf, seq->count)) { + s->err = -EFAULT; + } else { + *str = s->pos; + s->pos += seq->count; + } + } + kvfree(seq->buf); + sm->mask |= mask; +} + +static void statmount_numeric(struct kstatmount *s, u64 mask, statmount_func_t func) +{ + if (s->err || !(s->mask & mask)) + return; + + s->err = func(s); + s->sm.mask |= mask; +} + +static u64 mnt_to_attr_flags(struct vfsmount *mnt) +{ + unsigned int mnt_flags = READ_ONCE(mnt->mnt_flags); + u64 attr_flags = 0; + + if (mnt_flags & MNT_READONLY) + attr_flags |= MOUNT_ATTR_RDONLY; + if (mnt_flags & MNT_NOSUID) + attr_flags |= MOUNT_ATTR_NOSUID; + if (mnt_flags & MNT_NODEV) + attr_flags |= MOUNT_ATTR_NODEV; + if (mnt_flags & MNT_NOEXEC) + attr_flags |= MOUNT_ATTR_NOEXEC; + if (mnt_flags & MNT_NODIRATIME) + attr_flags |= MOUNT_ATTR_NODIRATIME; + if (mnt_flags & MNT_NOSYMFOLLOW) + attr_flags |= MOUNT_ATTR_NOSYMFOLLOW; + + if (mnt_flags & MNT_NOATIME) + attr_flags |= MOUNT_ATTR_NOATIME; + else if (mnt_flags & MNT_RELATIME) + attr_flags |= MOUNT_ATTR_RELATIME; + else + attr_flags |= MOUNT_ATTR_STRICTATIME; + + if (is_idmapped_mnt(mnt)) + attr_flags |= MOUNT_ATTR_IDMAP; + + return attr_flags; +} + +static u64 mnt_to_propagation_flags(struct mount *m) +{ + u64 propagation = 0; + + if (IS_MNT_SHARED(m)) + propagation |= MS_SHARED; + if (IS_MNT_SLAVE(m)) + propagation |= MS_SLAVE; + if (IS_MNT_UNBINDABLE(m)) + propagation |= MS_UNBINDABLE; + if (!propagation) + propagation |= MS_PRIVATE; + + return propagation; +} + +static int statmount_sb_basic(struct kstatmount *s) +{ + struct super_block *sb = s->mnt->mnt_sb; + + s->sm.sb_dev_major = MAJOR(sb->s_dev); + s->sm.sb_dev_minor = MINOR(sb->s_dev); + s->sm.sb_magic = sb->s_magic; + s->sm.sb_flags = sb->s_flags & (SB_RDONLY|SB_SYNCHRONOUS|SB_DIRSYNC|SB_LAZYTIME); + + return 0; +} + +static int statmount_mnt_basic(struct kstatmount *s) +{ + struct mount *m = real_mount(s->mnt); + + s->sm.mnt_id = m->mnt_id_unique; + s->sm.mnt_parent_id = m->mnt_parent->mnt_id_unique; + s->sm.mnt_id_old = m->mnt_id; + s->sm.mnt_parent_id_old = m->mnt_parent->mnt_id; + s->sm.mnt_attr = mnt_to_attr_flags(&m->mnt); + s->sm.mnt_propagation = mnt_to_propagation_flags(m); + s->sm.mnt_peer_group = IS_MNT_SHARED(m) ? m->mnt_group_id : 0; + s->sm.mnt_master = IS_MNT_SLAVE(m) ? m->mnt_master->mnt_group_id : 0; + + return 0; +} + +static int statmount_propagate_from(struct kstatmount *s) +{ + struct mount *m = real_mount(s->mnt); + + if (!IS_MNT_SLAVE(m)) + return 0; + + s->sm.propagate_from = get_dominating_id(m, ¤t->fs->root); + + return 0; +} + +static int statmount_mnt_root(struct kstatmount *s) +{ + struct seq_file *seq = &s->seq; + int err = show_path(seq, s->mnt->mnt_root); + + if (!err && !seq_has_overflowed(seq)) { + seq->buf[seq->count] = '\0'; + seq->count = string_unescape_inplace(seq->buf, UNESCAPE_OCTAL); + } + return err; +} + +static int statmount_mnt_point(struct kstatmount *s) +{ + struct vfsmount *mnt = s->mnt; + struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; + int err = seq_path_root(&s->seq, &mnt_path, &s->root, ""); + + return err == SEQ_SKIP ? 0 : err; +} + +static int statmount_fs_type(struct kstatmount *s) +{ + struct seq_file *seq = &s->seq; + struct super_block *sb = s->mnt->mnt_sb; + + seq_puts(seq, sb->s_type->name); + return 0; +} + +static int do_statmount(struct kstatmount *s) +{ + struct statmount *sm = &s->sm; + struct mount *m = real_mount(s->mnt); + size_t copysize = min_t(size_t, s->bufsize, sizeof(*sm)); + int err; + + /* + * Don't trigger audit denials. We just want to determine what + * mounts to show users. + */ + if (!is_path_reachable(m, m->mnt.mnt_root, &s->root) && + !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + err = security_sb_statfs(s->mnt->mnt_root); + if (err) + return err; + + statmount_numeric(s, STATMOUNT_SB_BASIC, statmount_sb_basic); + statmount_numeric(s, STATMOUNT_MNT_BASIC, statmount_mnt_basic); + statmount_numeric(s, STATMOUNT_PROPAGATE_FROM, statmount_propagate_from); + statmount_string(s, STATMOUNT_FS_TYPE, statmount_fs_type, &sm->fs_type); + statmount_string(s, STATMOUNT_MNT_ROOT, statmount_mnt_root, &sm->mnt_root); + statmount_string(s, STATMOUNT_MNT_POINT, statmount_mnt_point, &sm->mnt_point); + + if (s->err) + return s->err; + + /* Return the number of bytes copied to the buffer */ + sm->size = copysize + s->pos; + + if (copy_to_user(s->buf, sm, copysize)) + return -EFAULT; + + return 0; +} + +SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req, + struct statmount __user *, buf, size_t, bufsize, + unsigned int, flags) +{ + struct vfsmount *mnt; + struct mnt_id_req kreq; + int ret; + + if (flags) + return -EINVAL; + + if (copy_from_user(&kreq, req, sizeof(kreq))) + return -EFAULT; + + down_read(&namespace_sem); + mnt = lookup_mnt_in_ns(kreq.mnt_id, current->nsproxy->mnt_ns); + ret = -ENOENT; + if (mnt) { + struct kstatmount s = { + .mask = kreq.request_mask, + .buf = buf, + .bufsize = bufsize, + .mnt = mnt, + }; + + get_fs_root(current->fs, &s.root); + ret = do_statmount(&s); + path_put(&s.root); + } + up_read(&namespace_sem); + + return ret; +} + static void __init init_mount_tree(void) { struct vfsmount *mnt; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index fd9d12de7e92..530ca9adf5f1 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -74,6 +74,8 @@ struct landlock_ruleset_attr; enum landlock_rule_type; struct cachestat_range; struct cachestat; +struct statmount; +struct mnt_id_req; #include #include @@ -407,6 +409,9 @@ asmlinkage long sys_statfs64(const char __user *path, size_t sz, asmlinkage long sys_fstatfs(unsigned int fd, struct statfs __user *buf); asmlinkage long sys_fstatfs64(unsigned int fd, size_t sz, struct statfs64 __user *buf); +asmlinkage long sys_statmount(const struct mnt_id_req __user *req, + struct statmount __user *buf, size_t bufsize, + unsigned int flags); asmlinkage long sys_truncate(const char __user *path, long length); asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length); #if BITS_PER_LONG == 32 diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index bb242fdcfe6b..afdf4f2f6672 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -138,4 +138,57 @@ struct mount_attr { /* List of all mount_attr versions. */ #define MOUNT_ATTR_SIZE_VER0 32 /* sizeof first published struct */ + +/* + * Structure for getting mount/superblock/filesystem info with statmount(2). + * + * The interface is similar to statx(2): individual fields or groups can be + * selected with the @mask argument of statmount(). Kernel will set the @mask + * field according to the supported fields. + * + * If string fields are selected, then the caller needs to pass a buffer that + * has space after the fixed part of the structure. Nul terminated strings are + * copied there and offsets relative to @str are stored in the relevant fields. + * If the buffer is too small, then EOVERFLOW is returned. The actually used + * size is returned in @size. + */ +struct statmount { + __u32 size; /* Total size, including strings */ + __u32 __spare1; + __u64 mask; /* What results were written */ + __u32 sb_dev_major; /* Device ID */ + __u32 sb_dev_minor; + __u64 sb_magic; /* ..._SUPER_MAGIC */ + __u32 sb_flags; /* SB_{RDONLY,SYNCHRONOUS,DIRSYNC,LAZYTIME} */ + __u32 fs_type; /* [str] Filesystem type */ + __u64 mnt_id; /* Unique ID of mount */ + __u64 mnt_parent_id; /* Unique ID of parent (for root == mnt_id) */ + __u32 mnt_id_old; /* Reused IDs used in proc/.../mountinfo */ + __u32 mnt_parent_id_old; + __u64 mnt_attr; /* MOUNT_ATTR_... */ + __u64 mnt_propagation; /* MS_{SHARED,SLAVE,PRIVATE,UNBINDABLE} */ + __u64 mnt_peer_group; /* ID of shared peer group */ + __u64 mnt_master; /* Mount receives propagation from this ID */ + __u64 propagate_from; /* Propagation from in current namespace */ + __u32 mnt_root; /* [str] Root of mount relative to root of fs */ + __u32 mnt_point; /* [str] Mountpoint relative to current root */ + __u64 __spare2[50]; + char str[]; /* Variable size part containing strings */ +}; + +struct mnt_id_req { + __u64 mnt_id; + __u64 request_mask; +}; + +/* + * @mask bits for statmount(2) + */ +#define STATMOUNT_SB_BASIC 0x00000001U /* Want/got sb_... */ +#define STATMOUNT_MNT_BASIC 0x00000002U /* Want/got mnt_... */ +#define STATMOUNT_PROPAGATE_FROM 0x00000004U /* Want/got propagate_from */ +#define STATMOUNT_MNT_ROOT 0x00000008U /* Want/got mnt_root */ +#define STATMOUNT_MNT_POINT 0x00000010U /* Want/got mnt_point */ +#define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */ + #endif /* _UAPI_LINUX_MOUNT_H */ -- cgit From aa0887c4f18e280f8c2aa6964af602bd16c37f54 Mon Sep 17 00:00:00 2001 From: Vinayak Yadawad Date: Wed, 29 Nov 2023 18:20:43 +0530 Subject: wifi: nl80211: Extend del pmksa support for SAE and OWE security Current handling of del pmksa with SSID is limited to FILS security. In the current change the del pmksa support is extended to SAE/OWE security offloads as well. For OWE/SAE offloads, the PMK is generated and cached at driver/FW, so user app needs the capability to request cache deletion based on SSID for drivers supporting SAE/OWE offload. Signed-off-by: Vinayak Yadawad Link: https://msgid.link/ecdae726459e0944c377a6a6f6cb2c34d2e057d0.1701262123.git.vinayak.yadawad@broadcom.com [drop whitespace-damaged rdev_ops pointer completely, enabling tracing] Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 3 +- net/wireless/nl80211.c | 94 +++++++++++++++++++++++++++++++------------- 2 files changed, 69 insertions(+), 28 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 0cd1da2c2902..8f42d598e285 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -568,7 +568,8 @@ * @NL80211_CMD_DEL_PMKSA: Delete a PMKSA cache entry, using %NL80211_ATTR_MAC * (for the BSSID) and %NL80211_ATTR_PMKID or using %NL80211_ATTR_SSID, * %NL80211_ATTR_FILS_CACHE_ID, and %NL80211_ATTR_PMKID in case of FILS - * authentication. + * authentication. Additionally in case of SAE offload and OWE offloads + * PMKSA entry can be deleted using %NL80211_ATTR_SSID. * @NL80211_CMD_FLUSH_PMKSA: Flush all PMKSA cache entries. * * @NL80211_CMD_REG_CHANGE: indicates to userspace the regulatory domain diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 403a4a38966a..d6a20c21f094 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -12174,16 +12174,18 @@ static int nl80211_wiphy_netns(struct sk_buff *skb, struct genl_info *info) return err; } -static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info) +static int nl80211_set_pmksa(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; - int (*rdev_ops)(struct wiphy *wiphy, struct net_device *dev, - struct cfg80211_pmksa *pmksa) = NULL; struct net_device *dev = info->user_ptr[1]; struct cfg80211_pmksa pmksa; + bool ap_pmksa_caching_support = false; memset(&pmksa, 0, sizeof(struct cfg80211_pmksa)); + ap_pmksa_caching_support = wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_AP_PMKSA_CACHING); + if (!info->attrs[NL80211_ATTR_PMKID]) return -EINVAL; @@ -12192,16 +12194,15 @@ static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_MAC]) { pmksa.bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); } else if (info->attrs[NL80211_ATTR_SSID] && - info->attrs[NL80211_ATTR_FILS_CACHE_ID] && - (info->genlhdr->cmd == NL80211_CMD_DEL_PMKSA || - info->attrs[NL80211_ATTR_PMK])) { + info->attrs[NL80211_ATTR_FILS_CACHE_ID] && + info->attrs[NL80211_ATTR_PMK]) { pmksa.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); pmksa.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); - pmksa.cache_id = - nla_data(info->attrs[NL80211_ATTR_FILS_CACHE_ID]); + pmksa.cache_id = nla_data(info->attrs[NL80211_ATTR_FILS_CACHE_ID]); } else { return -EINVAL; } + if (info->attrs[NL80211_ATTR_PMK]) { pmksa.pmk = nla_data(info->attrs[NL80211_ATTR_PMK]); pmksa.pmk_len = nla_len(info->attrs[NL80211_ATTR_PMK]); @@ -12213,32 +12214,71 @@ static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_PMK_REAUTH_THRESHOLD]) pmksa.pmk_reauth_threshold = - nla_get_u8( - info->attrs[NL80211_ATTR_PMK_REAUTH_THRESHOLD]); + nla_get_u8(info->attrs[NL80211_ATTR_PMK_REAUTH_THRESHOLD]); if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT && - !(dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP && - wiphy_ext_feature_isset(&rdev->wiphy, - NL80211_EXT_FEATURE_AP_PMKSA_CACHING))) + !((dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP || + dev->ieee80211_ptr->iftype == NL80211_IFTYPE_P2P_GO) && + ap_pmksa_caching_support)) return -EOPNOTSUPP; - switch (info->genlhdr->cmd) { - case NL80211_CMD_SET_PMKSA: - rdev_ops = rdev->ops->set_pmksa; - break; - case NL80211_CMD_DEL_PMKSA: - rdev_ops = rdev->ops->del_pmksa; - break; - default: - WARN_ON(1); - break; + if (!rdev->ops->set_pmksa) + return -EOPNOTSUPP; + + return rdev_set_pmksa(rdev, dev, &pmksa); +} + +static int nl80211_del_pmksa(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct cfg80211_pmksa pmksa; + bool sae_offload_support = false; + bool owe_offload_support = false; + bool ap_pmksa_caching_support = false; + + memset(&pmksa, 0, sizeof(struct cfg80211_pmksa)); + + sae_offload_support = wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_SAE_OFFLOAD); + owe_offload_support = wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_OWE_OFFLOAD); + ap_pmksa_caching_support = wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_AP_PMKSA_CACHING); + + if (info->attrs[NL80211_ATTR_PMKID]) + pmksa.pmkid = nla_data(info->attrs[NL80211_ATTR_PMKID]); + + if (info->attrs[NL80211_ATTR_MAC]) { + pmksa.bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); + } else if (info->attrs[NL80211_ATTR_SSID]) { + /* SSID based pmksa flush suppported only for FILS, + * OWE/SAE OFFLOAD cases + */ + if (info->attrs[NL80211_ATTR_FILS_CACHE_ID] && + info->attrs[NL80211_ATTR_PMK]) { + pmksa.cache_id = nla_data(info->attrs[NL80211_ATTR_FILS_CACHE_ID]); + } else if (!sae_offload_support && !owe_offload_support) { + return -EINVAL; + } + pmksa.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); + pmksa.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); + } else { + return -EINVAL; } - if (!rdev_ops) + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT && + !((dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP || + dev->ieee80211_ptr->iftype == NL80211_IFTYPE_P2P_GO) && + ap_pmksa_caching_support)) + return -EOPNOTSUPP; + + if (!rdev->ops->del_pmksa) return -EOPNOTSUPP; - return rdev_ops(&rdev->wiphy, dev, &pmksa); + return rdev_del_pmksa(rdev, dev, &pmksa); } static int nl80211_flush_pmksa(struct sk_buff *skb, struct genl_info *info) @@ -16912,7 +16952,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { { .cmd = NL80211_CMD_SET_PMKSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = nl80211_setdel_pmksa, + .doit = nl80211_set_pmksa, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_CLEAR_SKB), @@ -16920,7 +16960,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { { .cmd = NL80211_CMD_DEL_PMKSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = nl80211_setdel_pmksa, + .doit = nl80211_del_pmksa, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), }, -- cgit From d02a12b8e4bbd188f38321849791af02d494c7fd Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 11 Dec 2023 09:05:20 +0200 Subject: wifi: cfg80211: add BSS usage reporting Sometimes there may be reasons for which a BSS that's actually found in scan cannot be used to connect to, for example a nonprimary link of an NSTR mobile AP MLD cannot be used for normal direct connections to it. Not indicating these to userspace as we do now of course avoids being able to connect to them, but it's better if they're shown to userspace and it can make an appropriate decision, without e.g. doing an additional ML probe. Thus add an indication of what a BSS can be used for, currently "normal" and "MLD link", including a reason bitmap for it being not usable. The latter can be extended later for certain BSSes if there are other reasons they cannot be used. Signed-off-by: Johannes Berg Reviewed-by: Ilan Peer Reviewed-by: Gregory Greenman Signed-off-by: Miri Korenblit Link: https://msgid.link/20231211085121.0464f25e0b1d.I9f70ca9f1440565ad9a5207d0f4d00a20cca67e7@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 60 +++++++++++++++++++++++++++++++----- include/uapi/linux/nl80211.h | 40 ++++++++++++++++++++++++ net/wireless/core.h | 3 ++ net/wireless/nl80211.c | 54 ++++++++++++++++++++++++++------ net/wireless/scan.c | 73 +++++++++++++++++++++++++++++++++----------- 5 files changed, 195 insertions(+), 35 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 324a5f710ad3..cabe57a00eaf 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2828,6 +2828,13 @@ enum cfg80211_signal_type { * the BSS that requested the scan in which the beacon/probe was received. * @chains: bitmask for filled values in @chain_signal. * @chain_signal: per-chain signal strength of last received BSS in dBm. + * @restrict_use: restrict usage, if not set, assume @use_for is + * %NL80211_BSS_USE_FOR_NORMAL. + * @use_for: bitmap of possible usage for this BSS, see + * &enum nl80211_bss_use_for + * @cannot_use_reasons: the reasons (bitmap) for not being able to connect, + * if @restrict_use is set and @use_for is zero (empty); may be 0 for + * unspecified reasons; see &enum nl80211_bss_cannot_use_reasons * @drv_data: Data to be passed through to @inform_bss */ struct cfg80211_inform_bss { @@ -2839,6 +2846,9 @@ struct cfg80211_inform_bss { u8 chains; s8 chain_signal[IEEE80211_MAX_CHAINS]; + u8 restrict_use:1, use_for:7; + u8 cannot_use_reasons; + void *drv_data; }; @@ -2890,6 +2900,11 @@ struct cfg80211_bss_ies { * @chain_signal: per-chain signal strength of last received BSS in dBm. * @bssid_index: index in the multiple BSS set * @max_bssid_indicator: max number of members in the BSS set + * @use_for: bitmap of possible usage for this BSS, see + * &enum nl80211_bss_use_for + * @cannot_use_reasons: the reasons (bitmap) for not being able to connect, + * if @restrict_use is set and @use_for is zero (empty); may be 0 for + * unspecified reasons; see &enum nl80211_bss_cannot_use_reasons * @priv: private area for driver use, has at least wiphy->bss_priv_size bytes */ struct cfg80211_bss { @@ -2915,6 +2930,9 @@ struct cfg80211_bss { u8 bssid_index; u8 max_bssid_indicator; + u8 use_for; + u8 cannot_use_reasons; + u8 priv[] __aligned(sizeof(void *)); }; @@ -4922,6 +4940,8 @@ struct cfg80211_ops { * NL80211_REGDOM_SET_BY_DRIVER. * @WIPHY_FLAG_CHANNEL_CHANGE_ON_BEACON: reg_call_notifier() is called if driver * set this flag to update channels on beacon hints. + * @WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY: support connection to non-primary link + * of an NSTR mobile AP MLD. */ enum wiphy_flags { WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK = BIT(0), @@ -4935,7 +4955,7 @@ enum wiphy_flags { WIPHY_FLAG_IBSS_RSN = BIT(8), WIPHY_FLAG_MESH_AUTH = BIT(10), WIPHY_FLAG_SUPPORTS_EXT_KCK_32 = BIT(11), - /* use hole at 12 */ + WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY = BIT(12), WIPHY_FLAG_SUPPORTS_FW_ROAM = BIT(13), WIPHY_FLAG_AP_UAPSD = BIT(14), WIPHY_FLAG_SUPPORTS_TDLS = BIT(15), @@ -7173,6 +7193,25 @@ cfg80211_inform_bss(struct wiphy *wiphy, gfp); } +/** + * __cfg80211_get_bss - get a BSS reference + * @wiphy: the wiphy this BSS struct belongs to + * @channel: the channel to search on (or %NULL) + * @bssid: the desired BSSID (or %NULL) + * @ssid: the desired SSID (or %NULL) + * @ssid_len: length of the SSID (or 0) + * @bss_type: type of BSS, see &enum ieee80211_bss_type + * @privacy: privacy filter, see &enum ieee80211_privacy + * @use_for: indicates which use is intended + */ +struct cfg80211_bss *__cfg80211_get_bss(struct wiphy *wiphy, + struct ieee80211_channel *channel, + const u8 *bssid, + const u8 *ssid, size_t ssid_len, + enum ieee80211_bss_type bss_type, + enum ieee80211_privacy privacy, + u32 use_for); + /** * cfg80211_get_bss - get a BSS reference * @wiphy: the wiphy this BSS struct belongs to @@ -7182,13 +7221,20 @@ cfg80211_inform_bss(struct wiphy *wiphy, * @ssid_len: length of the SSID (or 0) * @bss_type: type of BSS, see &enum ieee80211_bss_type * @privacy: privacy filter, see &enum ieee80211_privacy + * + * This version implies regular usage, %NL80211_BSS_USE_FOR_NORMAL. */ -struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy, - struct ieee80211_channel *channel, - const u8 *bssid, - const u8 *ssid, size_t ssid_len, - enum ieee80211_bss_type bss_type, - enum ieee80211_privacy privacy); +static inline struct cfg80211_bss * +cfg80211_get_bss(struct wiphy *wiphy, struct ieee80211_channel *channel, + const u8 *bssid, const u8 *ssid, size_t ssid_len, + enum ieee80211_bss_type bss_type, + enum ieee80211_privacy privacy) +{ + return __cfg80211_get_bss(wiphy, channel, bssid, ssid, ssid_len, + bss_type, privacy, + NL80211_BSS_USE_FOR_NORMAL); +} + static inline struct cfg80211_bss * cfg80211_get_ibss(struct wiphy *wiphy, struct ieee80211_channel *channel, diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 8f42d598e285..07fc1fec4b12 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2831,6 +2831,10 @@ enum nl80211_commands { * @NL80211_ATTR_MLO_LINK_DISABLED: Flag attribute indicating that the link is * disabled. * + * @NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA: Include BSS usage data, i.e. + * include BSSes that can only be used in restricted scenarios and/or + * cannot be used at all. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3369,6 +3373,8 @@ enum nl80211_attrs { NL80211_ATTR_MLO_LINK_DISABLED, + NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -5032,6 +5038,30 @@ enum nl80211_bss_scan_width { NL80211_BSS_CHAN_WIDTH_2, }; +/** + * enum nl80211_bss_use_for - bitmap indicating possible BSS use + * @NL80211_BSS_USE_FOR_NORMAL: Use this BSS for normal "connection", + * including IBSS/MBSS depending on the type. + * @NL80211_BSS_USE_FOR_MLD_LINK: This BSS can be used as a link in an + * MLO connection. Note that for an MLO connection, all links including + * the assoc link must have this flag set, and the assoc link must + * additionally have %NL80211_BSS_USE_FOR_NORMAL set. + */ +enum nl80211_bss_use_for { + NL80211_BSS_USE_FOR_NORMAL = 1 << 0, + NL80211_BSS_USE_FOR_MLD_LINK = 1 << 1, +}; + +/** + * enum nl80211_bss_cannot_use_reasons - reason(s) connection to a + * BSS isn't possible + * @NL80211_BSS_CANNOT_USE_NSTR_NONPRIMARY: NSTR nonprimary links aren't + * supported by the device, and this BSS entry represents one. + */ +enum nl80211_bss_cannot_use_reasons { + NL80211_BSS_CANNOT_USE_NSTR_NONPRIMARY = 1 << 0, +}; + /** * enum nl80211_bss - netlink attributes for a BSS * @@ -5084,6 +5114,14 @@ enum nl80211_bss_scan_width { * @NL80211_BSS_FREQUENCY_OFFSET: frequency offset in KHz * @NL80211_BSS_MLO_LINK_ID: MLO link ID of the BSS (u8). * @NL80211_BSS_MLD_ADDR: MLD address of this BSS if connected to it. + * @NL80211_BSS_USE_FOR: u32 bitmap attribute indicating what the BSS can be + * used for, see &enum nl80211_bss_use_for. + * @NL80211_BSS_CANNOT_USE_REASONS: Indicates the reason that this BSS cannot + * be used for all or some of the possible uses by the device reporting it, + * even though its presence was detected. + * This is a u64 attribute containing a bitmap of values from + * &enum nl80211_cannot_use_reasons, note that the attribute may be missing + * if no reasons are specified. * @__NL80211_BSS_AFTER_LAST: internal * @NL80211_BSS_MAX: highest BSS attribute */ @@ -5111,6 +5149,8 @@ enum nl80211_bss { NL80211_BSS_FREQUENCY_OFFSET, NL80211_BSS_MLO_LINK_ID, NL80211_BSS_MLD_ADDR, + NL80211_BSS_USE_FOR, + NL80211_BSS_CANNOT_USE_REASONS, /* keep last */ __NL80211_BSS_AFTER_LAST, diff --git a/net/wireless/core.h b/net/wireless/core.h index 4c692c7faf30..87c5889b15e3 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -457,6 +457,9 @@ int cfg80211_scan(struct cfg80211_registered_device *rdev); extern struct work_struct cfg80211_disconnect_work; +#define NL80211_BSS_USE_FOR_ALL (NL80211_BSS_USE_FOR_NORMAL | \ + NL80211_BSS_USE_FOR_MLD_LINK) + void cfg80211_set_dfs_state(struct wiphy *wiphy, const struct cfg80211_chan_def *chandef, enum nl80211_dfs_state dfs_state); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d6a20c21f094..2820336511a2 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -818,6 +818,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_HW_TIMESTAMP_ENABLED] = { .type = NLA_FLAG }, [NL80211_ATTR_EMA_RNR_ELEMS] = { .type = NLA_NESTED }, [NL80211_ATTR_MLO_LINK_DISABLED] = { .type = NLA_FLAG }, + [NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -10405,6 +10406,15 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, break; } + if (nla_put_u32(msg, NL80211_BSS_USE_FOR, res->use_for)) + goto nla_put_failure; + + if (res->cannot_use_reasons && + nla_put_u64_64bit(msg, NL80211_BSS_CANNOT_USE_REASONS, + res->cannot_use_reasons, + NL80211_BSS_PAD)) + goto nla_put_failure; + nla_nest_end(msg, bss); genlmsg_end(msg, hdr); @@ -10422,15 +10432,27 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb) struct cfg80211_registered_device *rdev; struct cfg80211_internal_bss *scan; struct wireless_dev *wdev; + struct nlattr **attrbuf; int start = cb->args[2], idx = 0; + bool dump_include_use_data; int err; - err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL); - if (err) + attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf), GFP_KERNEL); + if (!attrbuf) + return -ENOMEM; + + err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, attrbuf); + if (err) { + kfree(attrbuf); return err; + } /* nl80211_prepare_wdev_dump acquired it in the successful case */ __acquire(&rdev->wiphy.mtx); + dump_include_use_data = + attrbuf[NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA]; + kfree(attrbuf); + spin_lock_bh(&rdev->bss_lock); /* @@ -10447,6 +10469,9 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb) list_for_each_entry(scan, &rdev->bss_list, list) { if (++idx <= start) continue; + if (!dump_include_use_data && + !(scan->pub.use_for & NL80211_BSS_USE_FOR_NORMAL)) + continue; if (nl80211_send_bss(skb, cb, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wdev, scan) < 0) { @@ -10898,12 +10923,13 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, static struct cfg80211_bss *nl80211_assoc_bss(struct cfg80211_registered_device *rdev, const u8 *ssid, int ssid_len, - struct nlattr **attrs) + struct nlattr **attrs, + int assoc_link_id, int link_id) { struct ieee80211_channel *chan; struct cfg80211_bss *bss; const u8 *bssid; - u32 freq; + u32 freq, use_for = 0; if (!attrs[NL80211_ATTR_MAC] || !attrs[NL80211_ATTR_WIPHY_FREQ]) return ERR_PTR(-EINVAL); @@ -10918,10 +10944,16 @@ static struct cfg80211_bss *nl80211_assoc_bss(struct cfg80211_registered_device if (!chan) return ERR_PTR(-EINVAL); - bss = cfg80211_get_bss(&rdev->wiphy, chan, bssid, - ssid, ssid_len, - IEEE80211_BSS_TYPE_ESS, - IEEE80211_PRIVACY_ANY); + if (assoc_link_id >= 0) + use_for = NL80211_BSS_USE_FOR_MLD_LINK; + if (assoc_link_id == link_id) + use_for |= NL80211_BSS_USE_FOR_NORMAL; + + bss = __cfg80211_get_bss(&rdev->wiphy, chan, bssid, + ssid, ssid_len, + IEEE80211_BSS_TYPE_ESS, + IEEE80211_PRIVACY_ANY, + use_for); if (!bss) return ERR_PTR(-ENOENT); @@ -11100,7 +11132,8 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) goto free; } req.links[link_id].bss = - nl80211_assoc_bss(rdev, ssid, ssid_len, attrs); + nl80211_assoc_bss(rdev, ssid, ssid_len, attrs, + req.link_id, link_id); if (IS_ERR(req.links[link_id].bss)) { err = PTR_ERR(req.links[link_id].bss); req.links[link_id].bss = NULL; @@ -11165,7 +11198,8 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) if (req.link_id >= 0) return -EINVAL; - req.bss = nl80211_assoc_bss(rdev, ssid, ssid_len, info->attrs); + req.bss = nl80211_assoc_bss(rdev, ssid, ssid_len, info->attrs, + -1, -1); if (IS_ERR(req.bss)) return PTR_ERR(req.bss); ap_addr = req.bss->bssid; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 9e5ccffd6868..2f8c9b6f7ebc 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1535,12 +1535,13 @@ static bool cfg80211_bss_type_match(u16 capability, } /* Returned bss is reference counted and must be cleaned up appropriately. */ -struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy, - struct ieee80211_channel *channel, - const u8 *bssid, - const u8 *ssid, size_t ssid_len, - enum ieee80211_bss_type bss_type, - enum ieee80211_privacy privacy) +struct cfg80211_bss *__cfg80211_get_bss(struct wiphy *wiphy, + struct ieee80211_channel *channel, + const u8 *bssid, + const u8 *ssid, size_t ssid_len, + enum ieee80211_bss_type bss_type, + enum ieee80211_privacy privacy, + u32 use_for) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); struct cfg80211_internal_bss *bss, *res = NULL; @@ -1565,6 +1566,8 @@ struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy, continue; if (!is_valid_ether_addr(bss->pub.bssid)) continue; + if ((bss->pub.use_for & use_for) != use_for) + continue; /* Don't get expired BSS structs */ if (time_after(now, bss->ts + IEEE80211_SCAN_RESULT_EXPIRE) && !atomic_read(&bss->hold)) @@ -1582,7 +1585,7 @@ struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy, trace_cfg80211_return_bss(&res->pub); return &res->pub; } -EXPORT_SYMBOL(cfg80211_get_bss); +EXPORT_SYMBOL(__cfg80211_get_bss); static void rb_insert_bss(struct cfg80211_registered_device *rdev, struct cfg80211_internal_bss *bss) @@ -1800,6 +1803,8 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev, ether_addr_copy(known->parent_bssid, new->parent_bssid); known->pub.max_bssid_indicator = new->pub.max_bssid_indicator; known->pub.bssid_index = new->pub.bssid_index; + known->pub.use_for &= new->pub.use_for; + known->pub.cannot_use_reasons = new->pub.cannot_use_reasons; return true; } @@ -2044,6 +2049,9 @@ struct cfg80211_inform_single_bss_data { struct cfg80211_bss *source_bss; u8 max_bssid_indicator; u8 bssid_index; + + u8 use_for; + u64 cannot_use_reasons; }; /* Returned bss is reference counted and must be cleaned up appropriately. */ @@ -2089,6 +2097,8 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, tmp.ts_boottime = drv_data->boottime_ns; tmp.parent_tsf = drv_data->parent_tsf; ether_addr_copy(tmp.parent_bssid, drv_data->parent_bssid); + tmp.pub.use_for = data->use_for; + tmp.pub.cannot_use_reasons = data->cannot_use_reasons; if (data->bss_source != BSS_SOURCE_DIRECT) { tmp.pub.transmitted_bss = data->source_bss; @@ -2259,6 +2269,8 @@ cfg80211_parse_mbssid_data(struct wiphy *wiphy, .beacon_interval = tx_data->beacon_interval, .source_bss = source_bss, .bss_source = BSS_SOURCE_MBSSID, + .use_for = tx_data->use_for, + .cannot_use_reasons = tx_data->cannot_use_reasons, }; const u8 *mbssid_index_ie; const struct element *elem, *sub; @@ -2521,7 +2533,7 @@ error: return NULL; } -static bool +static u8 cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id, const struct ieee80211_neighbor_ap_info **ap_info, const u8 **tbtt_info) @@ -2540,6 +2552,7 @@ cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id, u16 params; u8 length, i, count, mld_params_offset; u8 type, lid; + u32 use_for; info = (void *)pos; count = u8_get_bits(info->tbtt_info_hdr, @@ -2549,20 +2562,22 @@ cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id, pos += sizeof(*info); if (count * length > end - pos) - return false; + return 0; type = u8_get_bits(info->tbtt_info_hdr, IEEE80211_AP_INFO_TBTT_HDR_TYPE); - /* Only accept full TBTT information. NSTR mobile APs - * use the shortened version, but we ignore them here. - */ if (type == IEEE80211_TBTT_INFO_TYPE_TBTT && length >= offsetofend(struct ieee80211_tbtt_info_ge_11, mld_params)) { mld_params_offset = offsetof(struct ieee80211_tbtt_info_ge_11, mld_params); + use_for = NL80211_BSS_USE_FOR_ALL; + } else if (type == IEEE80211_TBTT_INFO_TYPE_MLD && + length >= sizeof(struct ieee80211_rnr_mld_params)) { + mld_params_offset = 0; + use_for = NL80211_BSS_USE_FOR_MLD_LINK; } else { pos += count * length; continue; @@ -2580,7 +2595,7 @@ cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id, *ap_info = info; *tbtt_info = pos; - return true; + return use_for; } pos += length; @@ -2588,7 +2603,7 @@ cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id, } } - return false; + return 0; } static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy, @@ -2676,7 +2691,7 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy, const u8 *profile; const u8 *tbtt_info; ssize_t profile_len; - u8 link_id; + u8 link_id, use_for; if (!ieee80211_mle_basic_sta_prof_size_ok((u8 *)mle->sta_prof[i], mle->sta_prof_len[i])) @@ -2718,9 +2733,11 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy, profile_len -= 2; /* Find in RNR to look up channel information */ - if (!cfg80211_tbtt_info_for_mld_ap(tx_data->ie, tx_data->ielen, - mld_id, link_id, - &ap_info, &tbtt_info)) + use_for = cfg80211_tbtt_info_for_mld_ap(tx_data->ie, + tx_data->ielen, + mld_id, link_id, + &ap_info, &tbtt_info); + if (!use_for) continue; /* We could sanity check the BSSID is included */ @@ -2732,6 +2749,14 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy, freq = ieee80211_channel_to_freq_khz(ap_info->channel, band); data.channel = ieee80211_get_channel_khz(wiphy, freq); + if (use_for == NL80211_BSS_USE_FOR_MLD_LINK && + !(wiphy->flags & WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY)) { + use_for = 0; + data.cannot_use_reasons = + NL80211_BSS_CANNOT_USE_NSTR_NONPRIMARY; + } + data.use_for = use_for; + /* Generate new elements */ memset(new_ie, 0, IEEE80211_MAX_DATA_LEN); data.ie = new_ie; @@ -2769,6 +2794,10 @@ cfg80211_inform_bss_data(struct wiphy *wiphy, .beacon_interval = beacon_interval, .ie = ie, .ielen = ielen, + .use_for = data->restrict_use ? + data->use_for : + NL80211_BSS_USE_FOR_ALL, + .cannot_use_reasons = data->cannot_use_reasons, }; struct cfg80211_bss *res; @@ -2899,6 +2928,10 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, tmp.pub.chains = data->chains; memcpy(tmp.pub.chain_signal, data->chain_signal, IEEE80211_MAX_CHAINS); ether_addr_copy(tmp.parent_bssid, data->parent_bssid); + tmp.pub.use_for = data->restrict_use ? + data->use_for : + NL80211_BSS_USE_FOR_ALL; + tmp.pub.cannot_use_reasons = data->cannot_use_reasons; signal_valid = data->chan == channel; spin_lock_bh(&rdev->bss_lock); @@ -2930,6 +2963,10 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, .ie = mgmt->u.probe_resp.variable, .ielen = len - offsetof(struct ieee80211_mgmt, u.probe_resp.variable), + .use_for = data->restrict_use ? + data->use_for : + NL80211_BSS_USE_FOR_ALL, + .cannot_use_reasons = data->cannot_use_reasons, }; struct cfg80211_bss *res; -- cgit From b61e6b41a2f6818ee7b8f92f670a8a6ebcd25a71 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Mon, 11 Dec 2023 09:05:22 +0200 Subject: wifi: cfg80211: Add support for setting TID to link mapping Add support for setting the TID to link mapping for a non-AP MLD station. This is useful in cases user space needs to restrict the possible set of active links, e.g., since it got a BSS Transition Management request forcing to use only a subset of the valid links etc. Signed-off-by: Ilan Peer Reviewed-by: Gregory Greenman Signed-off-by: Miri Korenblit Link: https://msgid.link/20231211085121.da4d56a5f3ff.Iacf88e943326bf9c169c49b728c4a3445fdedc97@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 18 ++++++++++++++++++ include/uapi/linux/nl80211.h | 19 +++++++++++++++++++ net/wireless/nl80211.c | 37 +++++++++++++++++++++++++++++++++++++ net/wireless/rdev-ops.h | 18 ++++++++++++++++++ net/wireless/trace.h | 20 ++++++++++++++++++++ 5 files changed, 112 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index cabe57a00eaf..4d6b9d801c2f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1673,6 +1673,21 @@ struct link_station_del_parameters { u32 link_id; }; +/** + * struct cfg80211_ttlm_params: TID to link mapping parameters + * + * Used for setting a TID to link mapping. + * + * @dlink: Downlink TID to link mapping, as defined in section 9.4.2.314 + * (TID-To-Link Mapping element) in Draft P802.11be_D4.0. + * @ulink: Uplink TID to link mapping, as defined in section 9.4.2.314 + * (TID-To-Link Mapping element) in Draft P802.11be_D4.0. + */ +struct cfg80211_ttlm_params { + u16 dlink[8]; + u16 ulink[8]; +}; + /** * struct station_parameters - station parameters * @@ -4523,6 +4538,7 @@ struct mgmt_frame_regs { * @del_link_station: Remove a link of a station. * * @set_hw_timestamp: Enable/disable HW timestamping of TM/FTM frames. + * @set_ttlm: set the TID to link mapping. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -4882,6 +4898,8 @@ struct cfg80211_ops { struct link_station_del_parameters *params); int (*set_hw_timestamp)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_set_hw_timestamp *hwts); + int (*set_ttlm)(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_ttlm_params *params); }; /* diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 07fc1fec4b12..2d8468cbc457 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1328,6 +1328,11 @@ * Multi-Link reconfiguration. %NL80211_ATTR_MLO_LINKS is used to provide * information about the removed STA MLD setup links. * + * @NL80211_CMD_SET_TID_TO_LINK_MAPPING: Set the TID to Link Mapping for a + * non-AP MLD station. The %NL80211_ATTR_MLO_TTLM_DLINK and + * %NL80211_ATTR_MLO_TTLM_ULINK attributes are used to specify the + * TID to Link mapping for downlink/uplink traffic. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1583,6 +1588,8 @@ enum nl80211_commands { NL80211_CMD_LINKS_REMOVED, + NL80211_CMD_SET_TID_TO_LINK_MAPPING, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -2835,6 +2842,15 @@ enum nl80211_commands { * include BSSes that can only be used in restricted scenarios and/or * cannot be used at all. * + * @NL80211_ATTR_MLO_TTLM_DLINK: Binary attribute specifying the downlink TID to + * link mapping. The length is 8 * sizeof(u16). For each TID the link + * mapping is as defined in section 9.4.2.314 (TID-To-Link Mapping element) + * in Draft P802.11be_D4.0. + * @NL80211_ATTR_MLO_TTLM_ULINK: Binary attribute specifying the uplink TID to + * link mapping. The length is 8 * sizeof(u16). For each TID the link + * mapping is as defined in section 9.4.2.314 (TID-To-Link Mapping element) + * in Draft P802.11be_D4.0. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3375,6 +3391,9 @@ enum nl80211_attrs { NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA, + NL80211_ATTR_MLO_TTLM_DLINK, + NL80211_ATTR_MLO_TTLM_ULINK, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 2820336511a2..0dec06cdf253 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -819,6 +819,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_EMA_RNR_ELEMS] = { .type = NLA_NESTED }, [NL80211_ATTR_MLO_LINK_DISABLED] = { .type = NLA_FLAG }, [NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA] = { .type = NLA_FLAG }, + [NL80211_ATTR_MLO_TTLM_DLINK] = NLA_POLICY_EXACT_LEN(sizeof(u16) * 8), + [NL80211_ATTR_MLO_TTLM_ULINK] = NLA_POLICY_EXACT_LEN(sizeof(u16) * 8), }; /* policy for the key attributes */ @@ -16298,6 +16300,35 @@ static int nl80211_set_hw_timestamp(struct sk_buff *skb, return rdev_set_hw_timestamp(rdev, dev, &hwts); } +static int +nl80211_set_ttlm(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_ttlm_params params = {}; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; + + if (wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; + + if (!wdev->connected) + return -ENOLINK; + + if (!info->attrs[NL80211_ATTR_MLO_TTLM_DLINK] || + !info->attrs[NL80211_ATTR_MLO_TTLM_ULINK]) + return -EINVAL; + + nla_memcpy(params.dlink, + info->attrs[NL80211_ATTR_MLO_TTLM_DLINK], + sizeof(params.dlink)); + nla_memcpy(params.ulink, + info->attrs[NL80211_ATTR_MLO_TTLM_ULINK], + sizeof(params.ulink)); + + return rdev_set_ttlm(rdev, dev, ¶ms); +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -17479,6 +17510,12 @@ static const struct genl_small_ops nl80211_small_ops[] = { .flags = GENL_UNS_ADMIN_PERM, .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), }, + { + .cmd = NL80211_CMD_SET_TID_TO_LINK_MAPPING, + .doit = nl80211_set_ttlm, + .flags = GENL_UNS_ADMIN_PERM, + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), + }, }; static struct genl_family nl80211_fam __ro_after_init = { diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 2214a90cf101..2a27a3448759 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -1524,4 +1524,22 @@ rdev_set_hw_timestamp(struct cfg80211_registered_device *rdev, return ret; } + +static inline int +rdev_set_ttlm(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_ttlm_params *params) +{ + struct wiphy *wiphy = &rdev->wiphy; + int ret; + + if (!rdev->ops->set_ttlm) + return -EOPNOTSUPP; + + trace_rdev_set_ttlm(wiphy, dev, params); + ret = rdev->ops->set_ttlm(wiphy, dev, params); + trace_rdev_return_int(wiphy, ret); + + return ret; +} #endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 4de710efa47e..1f374c8a17a5 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -3979,6 +3979,26 @@ TRACE_EVENT(cfg80211_links_removed, __entry->link_mask) ); +TRACE_EVENT(rdev_set_ttlm, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_ttlm_params *params), + TP_ARGS(wiphy, netdev, params), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __array(u8, dlink, sizeof(u16) * 8) + __array(u8, ulink, sizeof(u16) * 8) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + memcpy(__entry->dlink, params->dlink, sizeof(params->dlink)); + memcpy(__entry->ulink, params->ulink, sizeof(params->ulink)); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG) +); + #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH -- cgit From dc18b89ab113e9c6c7a529316ddf7029fb55132d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 7 Dec 2023 20:06:02 -0700 Subject: io_uring/openclose: add support for IORING_OP_FIXED_FD_INSTALL io_uring can currently open/close regular files or fixed/direct descriptors. Or you can instantiate a fixed descriptor from a regular one, and then close the regular descriptor. But you currently can't turn a purely fixed/direct descriptor into a regular file descriptor. IORING_OP_FIXED_FD_INSTALL adds support for installing a direct descriptor into the normal file table, just like receiving a file descriptor or opening a new file would do. This is all nicely abstracted into receive_fd(), and hence adding support for this is truly trivial. Since direct descriptors are only usable within io_uring itself, it can be useful to turn them into real file descriptors if they ever need to be accessed via normal syscalls. This can either be a transitory thing, or just a permanent transition for a given direct descriptor. By default, new fds are installed with O_CLOEXEC set. The application can disable O_CLOEXEC by setting IORING_FIXED_FD_NO_CLOEXEC in the sqe->install_fd_flags member. Suggested-by: Christian Brauner Reviewed-by: Christian Brauner Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 9 +++++++++ io_uring/opdef.c | 9 +++++++++ io_uring/openclose.c | 44 +++++++++++++++++++++++++++++++++++++++++++ io_uring/openclose.h | 3 +++ 4 files changed, 65 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index f1c16f817742..db4b913e6b39 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -71,6 +71,7 @@ struct io_uring_sqe { __u32 uring_cmd_flags; __u32 waitid_flags; __u32 futex_flags; + __u32 install_fd_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -253,6 +254,7 @@ enum io_uring_op { IORING_OP_FUTEX_WAIT, IORING_OP_FUTEX_WAKE, IORING_OP_FUTEX_WAITV, + IORING_OP_FIXED_FD_INSTALL, /* this goes last, obviously */ IORING_OP_LAST, @@ -386,6 +388,13 @@ enum { /* Pass through the flags from sqe->file_index to cqe->flags */ #define IORING_MSG_RING_FLAGS_PASS (1U << 1) +/* + * IORING_OP_FIXED_FD_INSTALL flags (sqe->install_fd_flags) + * + * IORING_FIXED_FD_NO_CLOEXEC Don't mark the fd as O_CLOEXEC + */ +#define IORING_FIXED_FD_NO_CLOEXEC (1U << 0) + /* * IO completion data structure (Completion Queue Entry) */ diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 799db44283c7..6705634e5f52 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -469,6 +469,12 @@ const struct io_issue_def io_issue_defs[] = { .prep = io_eopnotsupp_prep, #endif }, + [IORING_OP_FIXED_FD_INSTALL] = { + .needs_file = 1, + .audit_skip = 1, + .prep = io_install_fixed_fd_prep, + .issue = io_install_fixed_fd, + }, }; const struct io_cold_def io_cold_defs[] = { @@ -704,6 +710,9 @@ const struct io_cold_def io_cold_defs[] = { [IORING_OP_FUTEX_WAITV] = { .name = "FUTEX_WAITV", }, + [IORING_OP_FIXED_FD_INSTALL] = { + .name = "FIXED_FD_INSTALL", + }, }; const char *io_uring_get_opcode(u8 opcode) diff --git a/io_uring/openclose.c b/io_uring/openclose.c index 74fc22461f48..0fe0dd305546 100644 --- a/io_uring/openclose.c +++ b/io_uring/openclose.c @@ -31,6 +31,11 @@ struct io_close { u32 file_slot; }; +struct io_fixed_install { + struct file *file; + unsigned int o_flags; +}; + static bool io_openat_force_async(struct io_open *open) { /* @@ -254,3 +259,42 @@ err: io_req_set_res(req, ret, 0); return IOU_OK; } + +int io_install_fixed_fd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_fixed_install *ifi; + unsigned int flags; + + if (sqe->off || sqe->addr || sqe->len || sqe->buf_index || + sqe->splice_fd_in || sqe->addr3) + return -EINVAL; + + /* must be a fixed file */ + if (!(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + flags = READ_ONCE(sqe->install_fd_flags); + if (flags & ~IORING_FIXED_FD_NO_CLOEXEC) + return -EINVAL; + + /* default to O_CLOEXEC, disable if IORING_FIXED_FD_NO_CLOEXEC is set */ + ifi = io_kiocb_to_cmd(req, struct io_fixed_install); + ifi->o_flags = O_CLOEXEC; + if (flags & IORING_FIXED_FD_NO_CLOEXEC) + ifi->o_flags = 0; + + return 0; +} + +int io_install_fixed_fd(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_fixed_install *ifi; + int ret; + + ifi = io_kiocb_to_cmd(req, struct io_fixed_install); + ret = receive_fd(req->file, NULL, ifi->o_flags); + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return IOU_OK; +} diff --git a/io_uring/openclose.h b/io_uring/openclose.h index 4b1c28d3a66c..8a93c98ad0ad 100644 --- a/io_uring/openclose.h +++ b/io_uring/openclose.h @@ -12,3 +12,6 @@ int io_openat2(struct io_kiocb *req, unsigned int issue_flags); int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_close(struct io_kiocb *req, unsigned int issue_flags); + +int io_install_fixed_fd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_install_fixed_fd(struct io_kiocb *req, unsigned int issue_flags); -- cgit From 805d4311a54a25d7347684fdf778c6239b190864 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Wed, 13 Dec 2023 17:00:05 +0200 Subject: media: v4l2-subdev: Add which field to struct v4l2_subdev_frame_interval Due to a historical mishap, the v4l2_subdev_frame_interval structure is the only part of the V4L2 subdev userspace API that doesn't contain a 'which' field. This prevents trying frame intervals using the subdev 'TRY' state mechanism. Adding a 'which' field is simple as the structure has 8 reserved fields. This would however break userspace as the field is currently set to 0, corresponding to V4L2_SUBDEV_FORMAT_TRY, while the corresponding ioctls currently operate on the 'ACTIVE' state. We thus need to add a new subdev client cap, V4L2_SUBDEV_CLIENT_CAP_INTERVAL_USES_WHICH, to indicate that userspace is aware of this new field. All drivers that implement the subdev .get_frame_interval() and .set_frame_interval() operations are updated to return -EINVAL when operating on the TRY state, preserving the current behaviour. While at it, fix a bad copy&paste in the documentation of the struct v4l2_subdev_frame_interval_enum 'which' field. Signed-off-by: Laurent Pinchart Reviewed-by: Philipp Zabel # for imx-media Reviewed-by: Hans Verkuil Reviewed-by: Luca Ceresoli # for tegra-video Reviewed-by: Mauro Carvalho Chehab Signed-off-by: Hans Verkuil --- .../media/v4l/vidioc-subdev-g-client-cap.rst | 5 +++++ .../media/v4l/vidioc-subdev-g-frame-interval.rst | 17 +++++++++------ drivers/media/i2c/adv7180.c | 7 ++++++ drivers/media/i2c/alvium-csi2.c | 14 ++++++++++++ drivers/media/i2c/et8ek8/et8ek8_driver.c | 14 ++++++++++++ drivers/media/i2c/imx214.c | 7 ++++++ drivers/media/i2c/imx274.c | 14 ++++++++++++ drivers/media/i2c/max9286.c | 14 ++++++++++++ drivers/media/i2c/mt9m111.c | 14 ++++++++++++ drivers/media/i2c/mt9m114.c | 14 ++++++++++++ drivers/media/i2c/mt9v011.c | 14 ++++++++++++ drivers/media/i2c/mt9v111.c | 14 ++++++++++++ drivers/media/i2c/ov2680.c | 7 ++++++ drivers/media/i2c/ov5640.c | 14 ++++++++++++ drivers/media/i2c/ov5648.c | 7 ++++++ drivers/media/i2c/ov5693.c | 7 ++++++ drivers/media/i2c/ov6650.c | 14 ++++++++++++ drivers/media/i2c/ov7251.c | 14 ++++++++++++ drivers/media/i2c/ov7670.c | 12 +++++++++++ drivers/media/i2c/ov772x.c | 14 ++++++++++++ drivers/media/i2c/ov8865.c | 7 ++++++ drivers/media/i2c/ov9650.c | 14 ++++++++++++ drivers/media/i2c/s5c73m3/s5c73m3-core.c | 14 ++++++++++++ drivers/media/i2c/s5k5baf.c | 14 ++++++++++++ drivers/media/i2c/thp7312.c | 14 ++++++++++++ drivers/media/i2c/tvp514x.c | 12 +++++++++++ drivers/media/v4l2-core/v4l2-subdev.c | 25 ++++++++++++++-------- drivers/staging/media/atomisp/i2c/atomisp-gc0310.c | 7 ++++++ drivers/staging/media/atomisp/i2c/atomisp-gc2235.c | 7 ++++++ .../staging/media/atomisp/i2c/atomisp-mt9m114.c | 7 ++++++ drivers/staging/media/atomisp/i2c/atomisp-ov2722.c | 7 ++++++ drivers/staging/media/imx/imx-ic-prp.c | 14 ++++++++++++ drivers/staging/media/imx/imx-ic-prpencvf.c | 14 ++++++++++++ drivers/staging/media/imx/imx-media-csi.c | 14 ++++++++++++ drivers/staging/media/imx/imx-media-vdic.c | 14 ++++++++++++ drivers/staging/media/tegra-video/csi.c | 7 ++++++ include/uapi/linux/v4l2-subdev.h | 15 ++++++++++--- 37 files changed, 425 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-client-cap.rst b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-client-cap.rst index 20f12a1cc0f7..810b6a859dc8 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-client-cap.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-client-cap.rst @@ -71,6 +71,11 @@ is unknown to the kernel. of 'stream' fields (referring to the stream number) with various ioctls. If this is not set (which is the default), the 'stream' fields will be forced to 0 by the kernel. + * - ``V4L2_SUBDEV_CLIENT_CAP_INTERVAL_USES_WHICH`` + - The client is aware of the :c:type:`v4l2_subdev_frame_interval` + ``which`` field. If this is not set (which is the default), the + ``which`` field is forced to ``V4L2_SUBDEV_FORMAT_ACTIVE`` by the + kernel. Return Value ============ diff --git a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-frame-interval.rst b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-frame-interval.rst index 842f962d2aea..41e0e2c8ecc3 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-frame-interval.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-frame-interval.rst @@ -58,8 +58,9 @@ struct contains the current frame interval as would be returned by a ``VIDIOC_SUBDEV_G_FRAME_INTERVAL`` call. -Calling ``VIDIOC_SUBDEV_S_FRAME_INTERVAL`` on a subdev device node that has been -registered in read-only mode is not allowed. An error is returned and the errno +If the subdev device node has been registered in read-only mode, calls to +``VIDIOC_SUBDEV_S_FRAME_INTERVAL`` are only valid if the ``which`` field is set +to ``V4L2_SUBDEV_FORMAT_TRY``, otherwise an error is returned and the errno variable is set to ``-EPERM``. Drivers must not return an error solely because the requested interval @@ -93,7 +94,11 @@ the same sub-device is not defined. - ``stream`` - Stream identifier. * - __u32 - - ``reserved``\ [8] + - ``which`` + - Active or try frame interval, from enum + :ref:`v4l2_subdev_format_whence `. + * - __u32 + - ``reserved``\ [7] - Reserved for future extensions. Applications and drivers must set the array to zero. @@ -114,9 +119,9 @@ EBUSY EINVAL The struct :c:type:`v4l2_subdev_frame_interval` - ``pad`` references a non-existing pad, or the pad doesn't support - frame intervals. + ``pad`` references a non-existing pad, the ``which`` field references a + non-existing frame interval, or the pad doesn't support frame intervals. EPERM The ``VIDIOC_SUBDEV_S_FRAME_INTERVAL`` ioctl has been called on a read-only - subdevice. + subdevice and the ``which`` field is set to ``V4L2_SUBDEV_FORMAT_ACTIVE``. diff --git a/drivers/media/i2c/adv7180.c b/drivers/media/i2c/adv7180.c index 7ed86030fb5c..409b9a37f018 100644 --- a/drivers/media/i2c/adv7180.c +++ b/drivers/media/i2c/adv7180.c @@ -469,6 +469,13 @@ static int adv7180_get_frame_interval(struct v4l2_subdev *sd, { struct adv7180_state *state = to_state(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + if (state->curr_norm & V4L2_STD_525_60) { fi->interval.numerator = 1001; fi->interval.denominator = 30000; diff --git a/drivers/media/i2c/alvium-csi2.c b/drivers/media/i2c/alvium-csi2.c index a173abb0509f..34ff7fad3877 100644 --- a/drivers/media/i2c/alvium-csi2.c +++ b/drivers/media/i2c/alvium-csi2.c @@ -1654,6 +1654,13 @@ static int alvium_g_frame_interval(struct v4l2_subdev *sd, { struct alvium_dev *alvium = sd_to_alvium(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + fi->interval = alvium->frame_interval; return 0; @@ -1703,6 +1710,13 @@ static int alvium_s_frame_interval(struct v4l2_subdev *sd, struct alvium_dev *alvium = sd_to_alvium(sd); int ret; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + if (alvium->streaming) return -EBUSY; diff --git a/drivers/media/i2c/et8ek8/et8ek8_driver.c b/drivers/media/i2c/et8ek8/et8ek8_driver.c index 71fb5aebd3df..f548b1bb75fb 100644 --- a/drivers/media/i2c/et8ek8/et8ek8_driver.c +++ b/drivers/media/i2c/et8ek8/et8ek8_driver.c @@ -1051,6 +1051,13 @@ static int et8ek8_get_frame_interval(struct v4l2_subdev *subdev, { struct et8ek8_sensor *sensor = to_et8ek8_sensor(subdev); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + memset(fi, 0, sizeof(*fi)); fi->interval = sensor->current_reglist->mode.timeperframe; @@ -1064,6 +1071,13 @@ static int et8ek8_set_frame_interval(struct v4l2_subdev *subdev, struct et8ek8_sensor *sensor = to_et8ek8_sensor(subdev); struct et8ek8_reglist *reglist; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + reglist = et8ek8_reglist_find_mode_ival(&meta_reglist, sensor->current_reglist, &fi->interval); diff --git a/drivers/media/i2c/imx214.c b/drivers/media/i2c/imx214.c index 8e832a4e3544..b148b1bd2bc3 100644 --- a/drivers/media/i2c/imx214.c +++ b/drivers/media/i2c/imx214.c @@ -905,6 +905,13 @@ static int imx214_get_frame_interval(struct v4l2_subdev *subdev, struct v4l2_subdev_state *sd_state, struct v4l2_subdev_frame_interval *fival) { + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fival->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + fival->interval.numerator = 1; fival->interval.denominator = IMX214_FPS; diff --git a/drivers/media/i2c/imx274.c b/drivers/media/i2c/imx274.c index 4040c642a36f..352da68b8b41 100644 --- a/drivers/media/i2c/imx274.c +++ b/drivers/media/i2c/imx274.c @@ -1333,6 +1333,13 @@ static int imx274_get_frame_interval(struct v4l2_subdev *sd, { struct stimx274 *imx274 = to_imx274(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + fi->interval = imx274->frame_interval; dev_dbg(&imx274->client->dev, "%s frame rate = %d / %d\n", __func__, imx274->frame_interval.numerator, @@ -1350,6 +1357,13 @@ static int imx274_set_frame_interval(struct v4l2_subdev *sd, int min, max, def; int ret; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + ret = pm_runtime_resume_and_get(&imx274->client->dev); if (ret < 0) return ret; diff --git a/drivers/media/i2c/max9286.c b/drivers/media/i2c/max9286.c index 7e8cb53d31c3..d685d445cf23 100644 --- a/drivers/media/i2c/max9286.c +++ b/drivers/media/i2c/max9286.c @@ -874,6 +874,13 @@ static int max9286_get_frame_interval(struct v4l2_subdev *sd, { struct max9286_priv *priv = sd_to_max9286(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + if (interval->pad != MAX9286_SRC_PAD) return -EINVAL; @@ -888,6 +895,13 @@ static int max9286_set_frame_interval(struct v4l2_subdev *sd, { struct max9286_priv *priv = sd_to_max9286(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + if (interval->pad != MAX9286_SRC_PAD) return -EINVAL; diff --git a/drivers/media/i2c/mt9m111.c b/drivers/media/i2c/mt9m111.c index 602954650f2e..ceeeb94c38d5 100644 --- a/drivers/media/i2c/mt9m111.c +++ b/drivers/media/i2c/mt9m111.c @@ -1051,6 +1051,13 @@ static int mt9m111_get_frame_interval(struct v4l2_subdev *sd, { struct mt9m111 *mt9m111 = container_of(sd, struct mt9m111, subdev); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + fi->interval = mt9m111->frame_interval; return 0; @@ -1068,6 +1075,13 @@ static int mt9m111_set_frame_interval(struct v4l2_subdev *sd, if (mt9m111->is_streaming) return -EBUSY; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + if (fi->pad != 0) return -EINVAL; diff --git a/drivers/media/i2c/mt9m114.c b/drivers/media/i2c/mt9m114.c index dcd94299787c..427eae13ce26 100644 --- a/drivers/media/i2c/mt9m114.c +++ b/drivers/media/i2c/mt9m114.c @@ -1592,6 +1592,13 @@ static int mt9m114_ifp_get_frame_interval(struct v4l2_subdev *sd, struct v4l2_fract *ival = &interval->interval; struct mt9m114 *sensor = ifp_to_mt9m114(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + mutex_lock(sensor->ifp.hdl.lock); ival->numerator = 1; @@ -1610,6 +1617,13 @@ static int mt9m114_ifp_set_frame_interval(struct v4l2_subdev *sd, struct mt9m114 *sensor = ifp_to_mt9m114(sd); int ret = 0; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + mutex_lock(sensor->ifp.hdl.lock); if (ival->numerator != 0 && ival->denominator != 0) diff --git a/drivers/media/i2c/mt9v011.c b/drivers/media/i2c/mt9v011.c index 3485761428ba..8834ff8786e5 100644 --- a/drivers/media/i2c/mt9v011.c +++ b/drivers/media/i2c/mt9v011.c @@ -366,6 +366,13 @@ static int mt9v011_get_frame_interval(struct v4l2_subdev *sd, struct v4l2_subdev_state *sd_state, struct v4l2_subdev_frame_interval *ival) { + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + calc_fps(sd, &ival->interval.numerator, &ival->interval.denominator); @@ -380,6 +387,13 @@ static int mt9v011_set_frame_interval(struct v4l2_subdev *sd, struct v4l2_fract *tpf = &ival->interval; u16 speed; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + speed = calc_speed(sd, tpf->numerator, tpf->denominator); mt9v011_write(sd, R0A_MT9V011_CLK_SPEED, speed); diff --git a/drivers/media/i2c/mt9v111.c b/drivers/media/i2c/mt9v111.c index 496be67c971b..b0b98ed3c150 100644 --- a/drivers/media/i2c/mt9v111.c +++ b/drivers/media/i2c/mt9v111.c @@ -730,6 +730,13 @@ static int mt9v111_set_frame_interval(struct v4l2_subdev *sd, tpf->denominator; unsigned int max_fps; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + if (!tpf->numerator) tpf->numerator = 1; @@ -779,6 +786,13 @@ static int mt9v111_get_frame_interval(struct v4l2_subdev *sd, struct mt9v111_dev *mt9v111 = sd_to_mt9v111(sd); struct v4l2_fract *tpf = &ival->interval; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + mutex_lock(&mt9v111->stream_mutex); tpf->numerator = 1; diff --git a/drivers/media/i2c/ov2680.c b/drivers/media/i2c/ov2680.c index e3ff64a9e6ca..39d321e2b7f9 100644 --- a/drivers/media/i2c/ov2680.c +++ b/drivers/media/i2c/ov2680.c @@ -558,6 +558,13 @@ static int ov2680_get_frame_interval(struct v4l2_subdev *sd, { struct ov2680_dev *sensor = to_ov2680_dev(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + mutex_lock(&sensor->lock); fi->interval = sensor->mode.frame_interval; mutex_unlock(&sensor->lock); diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c index 336bfd1ffd32..5162d45fe73b 100644 --- a/drivers/media/i2c/ov5640.c +++ b/drivers/media/i2c/ov5640.c @@ -3610,6 +3610,13 @@ static int ov5640_get_frame_interval(struct v4l2_subdev *sd, { struct ov5640_dev *sensor = to_ov5640_dev(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + mutex_lock(&sensor->lock); fi->interval = sensor->frame_interval; mutex_unlock(&sensor->lock); @@ -3625,6 +3632,13 @@ static int ov5640_set_frame_interval(struct v4l2_subdev *sd, const struct ov5640_mode_info *mode; int frame_rate, ret = 0; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + if (fi->pad != 0) return -EINVAL; diff --git a/drivers/media/i2c/ov5648.c b/drivers/media/i2c/ov5648.c index d0d7e9968f48..4b86d2631bd1 100644 --- a/drivers/media/i2c/ov5648.c +++ b/drivers/media/i2c/ov5648.c @@ -2276,6 +2276,13 @@ static int ov5648_get_frame_interval(struct v4l2_subdev *subdev, const struct ov5648_mode *mode; int ret = 0; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + mutex_lock(&sensor->mutex); mode = sensor->state.mode; diff --git a/drivers/media/i2c/ov5693.c b/drivers/media/i2c/ov5693.c index a65645811fbc..8deb28b55983 100644 --- a/drivers/media/i2c/ov5693.c +++ b/drivers/media/i2c/ov5693.c @@ -1013,6 +1013,13 @@ static int ov5693_get_frame_interval(struct v4l2_subdev *sd, ov5693->ctrls.vblank->val); unsigned int fps = DIV_ROUND_CLOSEST(OV5693_PIXEL_RATE, framesize); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + interval->interval.numerator = 1; interval->interval.denominator = fps; diff --git a/drivers/media/i2c/ov6650.c b/drivers/media/i2c/ov6650.c index a4dc45bdf3d7..b65befb22a79 100644 --- a/drivers/media/i2c/ov6650.c +++ b/drivers/media/i2c/ov6650.c @@ -806,6 +806,13 @@ static int ov6650_get_frame_interval(struct v4l2_subdev *sd, struct i2c_client *client = v4l2_get_subdevdata(sd); struct ov6650 *priv = to_ov6650(client); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + ival->interval = priv->tpf; dev_dbg(&client->dev, "Frame interval: %u/%u s\n", @@ -823,6 +830,13 @@ static int ov6650_set_frame_interval(struct v4l2_subdev *sd, struct v4l2_fract *tpf = &ival->interval; int div, ret; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + if (tpf->numerator == 0 || tpf->denominator == 0) div = 1; /* Reset to full rate */ else diff --git a/drivers/media/i2c/ov7251.c b/drivers/media/i2c/ov7251.c index 10d6b5deed83..30f61e04ecaf 100644 --- a/drivers/media/i2c/ov7251.c +++ b/drivers/media/i2c/ov7251.c @@ -1391,6 +1391,13 @@ static int ov7251_get_frame_interval(struct v4l2_subdev *subdev, { struct ov7251 *ov7251 = to_ov7251(subdev); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + mutex_lock(&ov7251->lock); fi->interval = ov7251->current_mode->timeperframe; mutex_unlock(&ov7251->lock); @@ -1406,6 +1413,13 @@ static int ov7251_set_frame_interval(struct v4l2_subdev *subdev, const struct ov7251_mode_info *new_mode; int ret = 0; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + mutex_lock(&ov7251->lock); new_mode = ov7251_find_mode_by_ival(ov7251, &fi->interval); diff --git a/drivers/media/i2c/ov7670.c b/drivers/media/i2c/ov7670.c index 463f20ece36e..0cb96b6c9990 100644 --- a/drivers/media/i2c/ov7670.c +++ b/drivers/media/i2c/ov7670.c @@ -1160,6 +1160,12 @@ static int ov7670_get_frame_interval(struct v4l2_subdev *sd, { struct ov7670_info *info = to_state(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; info->devtype->get_framerate(sd, &ival->interval); @@ -1173,6 +1179,12 @@ static int ov7670_set_frame_interval(struct v4l2_subdev *sd, struct v4l2_fract *tpf = &ival->interval; struct ov7670_info *info = to_state(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; return info->devtype->set_framerate(sd, tpf); } diff --git a/drivers/media/i2c/ov772x.c b/drivers/media/i2c/ov772x.c index a14a25946c5b..3e36a55274ef 100644 --- a/drivers/media/i2c/ov772x.c +++ b/drivers/media/i2c/ov772x.c @@ -724,6 +724,13 @@ static int ov772x_get_frame_interval(struct v4l2_subdev *sd, struct ov772x_priv *priv = to_ov772x(sd); struct v4l2_fract *tpf = &ival->interval; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + tpf->numerator = 1; tpf->denominator = priv->fps; @@ -739,6 +746,13 @@ static int ov772x_set_frame_interval(struct v4l2_subdev *sd, unsigned int fps; int ret = 0; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + mutex_lock(&priv->lock); if (priv->streaming) { diff --git a/drivers/media/i2c/ov8865.c b/drivers/media/i2c/ov8865.c index 02a595281c49..95ffe7536aa6 100644 --- a/drivers/media/i2c/ov8865.c +++ b/drivers/media/i2c/ov8865.c @@ -2846,6 +2846,13 @@ static int ov8865_get_frame_interval(struct v4l2_subdev *subdev, unsigned int framesize; unsigned int fps; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + mutex_lock(&sensor->mutex); mode = sensor->state.mode; diff --git a/drivers/media/i2c/ov9650.c b/drivers/media/i2c/ov9650.c index f528892c893f..66cd0e9ddc9a 100644 --- a/drivers/media/i2c/ov9650.c +++ b/drivers/media/i2c/ov9650.c @@ -1107,6 +1107,13 @@ static int ov965x_get_frame_interval(struct v4l2_subdev *sd, { struct ov965x *ov965x = to_ov965x(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + mutex_lock(&ov965x->lock); fi->interval = ov965x->fiv->interval; mutex_unlock(&ov965x->lock); @@ -1156,6 +1163,13 @@ static int ov965x_set_frame_interval(struct v4l2_subdev *sd, struct ov965x *ov965x = to_ov965x(sd); int ret; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + v4l2_dbg(1, debug, sd, "Setting %d/%d frame interval\n", fi->interval.numerator, fi->interval.denominator); diff --git a/drivers/media/i2c/s5c73m3/s5c73m3-core.c b/drivers/media/i2c/s5c73m3/s5c73m3-core.c index 73ca50f49812..af8d01f78c32 100644 --- a/drivers/media/i2c/s5c73m3/s5c73m3-core.c +++ b/drivers/media/i2c/s5c73m3/s5c73m3-core.c @@ -872,6 +872,13 @@ static int s5c73m3_oif_get_frame_interval(struct v4l2_subdev *sd, { struct s5c73m3 *state = oif_sd_to_s5c73m3(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + if (fi->pad != OIF_SOURCE_PAD) return -EINVAL; @@ -923,6 +930,13 @@ static int s5c73m3_oif_set_frame_interval(struct v4l2_subdev *sd, struct s5c73m3 *state = oif_sd_to_s5c73m3(sd); int ret; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + if (fi->pad != OIF_SOURCE_PAD) return -EINVAL; diff --git a/drivers/media/i2c/s5k5baf.c b/drivers/media/i2c/s5k5baf.c index 2fd1ecfeb086..de079d2c9282 100644 --- a/drivers/media/i2c/s5k5baf.c +++ b/drivers/media/i2c/s5k5baf.c @@ -1124,6 +1124,13 @@ static int s5k5baf_get_frame_interval(struct v4l2_subdev *sd, { struct s5k5baf *state = to_s5k5baf(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + mutex_lock(&state->lock); fi->interval.numerator = state->fiv; fi->interval.denominator = 10000; @@ -1162,6 +1169,13 @@ static int s5k5baf_set_frame_interval(struct v4l2_subdev *sd, { struct s5k5baf *state = to_s5k5baf(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + mutex_lock(&state->lock); __s5k5baf_set_frame_interval(state, fi); mutex_unlock(&state->lock); diff --git a/drivers/media/i2c/thp7312.c b/drivers/media/i2c/thp7312.c index d4975b180704..ad4f2b794e1a 100644 --- a/drivers/media/i2c/thp7312.c +++ b/drivers/media/i2c/thp7312.c @@ -740,6 +740,13 @@ static int thp7312_get_frame_interval(struct v4l2_subdev *sd, { struct thp7312_device *thp7312 = to_thp7312_dev(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + fi->interval.numerator = 1; fi->interval.denominator = thp7312->current_rate->fps; @@ -757,6 +764,13 @@ static int thp7312_set_frame_interval(struct v4l2_subdev *sd, unsigned int best_delta = UINT_MAX; unsigned int fps; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + /* Avoid divisions by 0, pick the highest frame if the interval is 0. */ fps = fi->interval.numerator ? DIV_ROUND_CLOSEST(fi->interval.denominator, fi->interval.numerator) diff --git a/drivers/media/i2c/tvp514x.c b/drivers/media/i2c/tvp514x.c index dee0cf992379..5a561e5bf659 100644 --- a/drivers/media/i2c/tvp514x.c +++ b/drivers/media/i2c/tvp514x.c @@ -746,6 +746,12 @@ tvp514x_get_frame_interval(struct v4l2_subdev *sd, struct tvp514x_decoder *decoder = to_decoder(sd); enum tvp514x_std current_std; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; /* get the current standard */ current_std = decoder->current_std; @@ -765,6 +771,12 @@ tvp514x_set_frame_interval(struct v4l2_subdev *sd, struct v4l2_fract *timeperframe; enum tvp514x_std current_std; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; timeperframe = &ival->interval; diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c index 405a4a2fa565..30131a37f2d5 100644 --- a/drivers/media/v4l2-core/v4l2-subdev.c +++ b/drivers/media/v4l2-core/v4l2-subdev.c @@ -291,9 +291,8 @@ static inline int check_frame_interval(struct v4l2_subdev *sd, if (!fi) return -EINVAL; - return check_pad(sd, fi->pad) ? : - check_state(sd, state, V4L2_SUBDEV_FORMAT_ACTIVE, fi->pad, - fi->stream); + return check_which(fi->which) ? : check_pad(sd, fi->pad) ? : + check_state(sd, state, fi->which, fi->pad, fi->stream); } static int call_get_frame_interval(struct v4l2_subdev *sd, @@ -537,9 +536,16 @@ subdev_ioctl_get_state(struct v4l2_subdev *sd, struct v4l2_subdev_fh *subdev_fh, which = ((struct v4l2_subdev_selection *)arg)->which; break; case VIDIOC_SUBDEV_G_FRAME_INTERVAL: - case VIDIOC_SUBDEV_S_FRAME_INTERVAL: - which = V4L2_SUBDEV_FORMAT_ACTIVE; + case VIDIOC_SUBDEV_S_FRAME_INTERVAL: { + struct v4l2_subdev_frame_interval *fi = arg; + + if (!(subdev_fh->client_caps & + V4L2_SUBDEV_CLIENT_CAP_INTERVAL_USES_WHICH)) + fi->which = V4L2_SUBDEV_FORMAT_ACTIVE; + + which = fi->which; break; + } case VIDIOC_SUBDEV_G_ROUTING: case VIDIOC_SUBDEV_S_ROUTING: which = ((struct v4l2_subdev_routing *)arg)->which; @@ -796,12 +802,12 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg, case VIDIOC_SUBDEV_S_FRAME_INTERVAL: { struct v4l2_subdev_frame_interval *fi = arg; - if (ro_subdev) - return -EPERM; - if (!client_supports_streams) fi->stream = 0; + if (fi->which != V4L2_SUBDEV_FORMAT_TRY && ro_subdev) + return -EPERM; + memset(fi->reserved, 0, sizeof(fi->reserved)); return v4l2_subdev_call(sd, pad, set_frame_interval, state, fi); } @@ -998,7 +1004,8 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg, client_cap->capabilities &= ~V4L2_SUBDEV_CLIENT_CAP_STREAMS; /* Filter out unsupported capabilities */ - client_cap->capabilities &= V4L2_SUBDEV_CLIENT_CAP_STREAMS; + client_cap->capabilities &= (V4L2_SUBDEV_CLIENT_CAP_STREAMS | + V4L2_SUBDEV_CLIENT_CAP_INTERVAL_USES_WHICH); subdev_fh->client_caps = client_cap->capabilities; diff --git a/drivers/staging/media/atomisp/i2c/atomisp-gc0310.c b/drivers/staging/media/atomisp/i2c/atomisp-gc0310.c index 006e8adac47b..5bcd634a2a44 100644 --- a/drivers/staging/media/atomisp/i2c/atomisp-gc0310.c +++ b/drivers/staging/media/atomisp/i2c/atomisp-gc0310.c @@ -500,6 +500,13 @@ static int gc0310_get_frame_interval(struct v4l2_subdev *sd, struct v4l2_subdev_state *sd_state, struct v4l2_subdev_frame_interval *interval) { + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + interval->interval.numerator = 1; interval->interval.denominator = GC0310_FPS; diff --git a/drivers/staging/media/atomisp/i2c/atomisp-gc2235.c b/drivers/staging/media/atomisp/i2c/atomisp-gc2235.c index aa257322a700..bec4c5615864 100644 --- a/drivers/staging/media/atomisp/i2c/atomisp-gc2235.c +++ b/drivers/staging/media/atomisp/i2c/atomisp-gc2235.c @@ -704,6 +704,13 @@ static int gc2235_get_frame_interval(struct v4l2_subdev *sd, { struct gc2235_device *dev = to_gc2235_sensor(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + interval->interval.numerator = 1; interval->interval.denominator = dev->res->fps; diff --git a/drivers/staging/media/atomisp/i2c/atomisp-mt9m114.c b/drivers/staging/media/atomisp/i2c/atomisp-mt9m114.c index 459c5b8233ce..20f02d18a8de 100644 --- a/drivers/staging/media/atomisp/i2c/atomisp-mt9m114.c +++ b/drivers/staging/media/atomisp/i2c/atomisp-mt9m114.c @@ -1394,6 +1394,13 @@ static int mt9m114_get_frame_interval(struct v4l2_subdev *sd, { struct mt9m114_device *dev = to_mt9m114_sensor(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + interval->interval.numerator = 1; interval->interval.denominator = mt9m114_res[dev->res].fps; diff --git a/drivers/staging/media/atomisp/i2c/atomisp-ov2722.c b/drivers/staging/media/atomisp/i2c/atomisp-ov2722.c index b3ef04d7ccca..133e346ae51b 100644 --- a/drivers/staging/media/atomisp/i2c/atomisp-ov2722.c +++ b/drivers/staging/media/atomisp/i2c/atomisp-ov2722.c @@ -851,6 +851,13 @@ static int ov2722_get_frame_interval(struct v4l2_subdev *sd, { struct ov2722_device *dev = to_ov2722_sensor(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + interval->interval.numerator = 1; interval->interval.denominator = dev->res->fps; diff --git a/drivers/staging/media/imx/imx-ic-prp.c b/drivers/staging/media/imx/imx-ic-prp.c index fb96f87e664e..2b80d54006b3 100644 --- a/drivers/staging/media/imx/imx-ic-prp.c +++ b/drivers/staging/media/imx/imx-ic-prp.c @@ -399,6 +399,13 @@ static int prp_get_frame_interval(struct v4l2_subdev *sd, { struct prp_priv *priv = sd_to_priv(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + if (fi->pad >= PRP_NUM_PADS) return -EINVAL; @@ -415,6 +422,13 @@ static int prp_set_frame_interval(struct v4l2_subdev *sd, { struct prp_priv *priv = sd_to_priv(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + if (fi->pad >= PRP_NUM_PADS) return -EINVAL; diff --git a/drivers/staging/media/imx/imx-ic-prpencvf.c b/drivers/staging/media/imx/imx-ic-prpencvf.c index 7bfe433cd322..17fd980c9d3c 100644 --- a/drivers/staging/media/imx/imx-ic-prpencvf.c +++ b/drivers/staging/media/imx/imx-ic-prpencvf.c @@ -1209,6 +1209,13 @@ static int prp_get_frame_interval(struct v4l2_subdev *sd, { struct prp_priv *priv = sd_to_priv(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + if (fi->pad >= PRPENCVF_NUM_PADS) return -EINVAL; @@ -1225,6 +1232,13 @@ static int prp_set_frame_interval(struct v4l2_subdev *sd, { struct prp_priv *priv = sd_to_priv(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + if (fi->pad >= PRPENCVF_NUM_PADS) return -EINVAL; diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c index 4308fdc9b58e..785aac881922 100644 --- a/drivers/staging/media/imx/imx-media-csi.c +++ b/drivers/staging/media/imx/imx-media-csi.c @@ -908,6 +908,13 @@ static int csi_get_frame_interval(struct v4l2_subdev *sd, { struct csi_priv *priv = v4l2_get_subdevdata(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + if (fi->pad >= CSI_NUM_PADS) return -EINVAL; @@ -928,6 +935,13 @@ static int csi_set_frame_interval(struct v4l2_subdev *sd, struct v4l2_fract *input_fi; int ret = 0; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + mutex_lock(&priv->lock); input_fi = &priv->frame_interval[CSI_SINK_PAD]; diff --git a/drivers/staging/media/imx/imx-media-vdic.c b/drivers/staging/media/imx/imx-media-vdic.c index a51b37679239..09da4103a8db 100644 --- a/drivers/staging/media/imx/imx-media-vdic.c +++ b/drivers/staging/media/imx/imx-media-vdic.c @@ -786,6 +786,13 @@ static int vdic_get_frame_interval(struct v4l2_subdev *sd, { struct vdic_priv *priv = v4l2_get_subdevdata(sd); + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + if (fi->pad >= VDIC_NUM_PADS) return -EINVAL; @@ -806,6 +813,13 @@ static int vdic_set_frame_interval(struct v4l2_subdev *sd, struct v4l2_fract *input_fi, *output_fi; int ret = 0; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + mutex_lock(&priv->lock); input_fi = &priv->frame_interval[priv->active_input_pad]; diff --git a/drivers/staging/media/tegra-video/csi.c b/drivers/staging/media/tegra-video/csi.c index b1b666179be5..255cccd0c5fd 100644 --- a/drivers/staging/media/tegra-video/csi.c +++ b/drivers/staging/media/tegra-video/csi.c @@ -231,6 +231,13 @@ static int tegra_csi_get_frame_interval(struct v4l2_subdev *subdev, if (!IS_ENABLED(CONFIG_VIDEO_TEGRA_TPG)) return -ENOIOCTLCMD; + /* + * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2 + * subdev active state API. + */ + if (vfi->which != V4L2_SUBDEV_FORMAT_ACTIVE) + return -EINVAL; + vfi->interval.numerator = 1; vfi->interval.denominator = csi_chan->framerate; diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h index f0fbb4a7c150..7048c51581c6 100644 --- a/include/uapi/linux/v4l2-subdev.h +++ b/include/uapi/linux/v4l2-subdev.h @@ -116,13 +116,15 @@ struct v4l2_subdev_frame_size_enum { * @pad: pad number, as reported by the media API * @interval: frame interval in seconds * @stream: stream number, defined in subdev routing + * @which: interval type (from enum v4l2_subdev_format_whence) * @reserved: drivers and applications must zero this array */ struct v4l2_subdev_frame_interval { __u32 pad; struct v4l2_fract interval; __u32 stream; - __u32 reserved[8]; + __u32 which; + __u32 reserved[7]; }; /** @@ -133,7 +135,7 @@ struct v4l2_subdev_frame_interval { * @width: frame width in pixels * @height: frame height in pixels * @interval: frame interval in seconds - * @which: format type (from enum v4l2_subdev_format_whence) + * @which: interval type (from enum v4l2_subdev_format_whence) * @stream: stream number, defined in subdev routing * @reserved: drivers and applications must zero this array */ @@ -239,7 +241,14 @@ struct v4l2_subdev_routing { * set (which is the default), the 'stream' fields will be forced to 0 by the * kernel. */ -#define V4L2_SUBDEV_CLIENT_CAP_STREAMS (1ULL << 0) +#define V4L2_SUBDEV_CLIENT_CAP_STREAMS (1ULL << 0) + +/* + * The client is aware of the struct v4l2_subdev_frame_interval which field. If + * this is not set (which is the default), the which field is forced to + * V4L2_SUBDEV_FORMAT_ACTIVE by the kernel. + */ +#define V4L2_SUBDEV_CLIENT_CAP_INTERVAL_USES_WHICH (1ULL << 1) /** * struct v4l2_subdev_client_capability - Capabilities of the client accessing -- cgit From e6795330f88b4f643c649a02662d47b779340535 Mon Sep 17 00:00:00 2001 From: Larysa Zaremba Date: Tue, 5 Dec 2023 22:08:38 +0100 Subject: xdp: Add VLAN tag hint Implement functionality that enables drivers to expose VLAN tag to XDP code. VLAN tag is represented by 2 variables: - protocol ID, which is passed to bpf code in BE - VLAN TCI, in host byte order Acked-by: Stanislav Fomichev Signed-off-by: Larysa Zaremba Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/20231205210847.28460-10-larysa.zaremba@intel.com Signed-off-by: Alexei Starovoitov --- Documentation/netlink/specs/netdev.yaml | 4 ++++ Documentation/networking/xdp-rx-metadata.rst | 8 ++++++- include/net/xdp.h | 6 +++++ include/uapi/linux/netdev.h | 3 +++ net/core/xdp.c | 33 ++++++++++++++++++++++++++++ tools/include/uapi/linux/netdev.h | 3 +++ tools/net/ynl/generated/netdev-user.c | 1 + 7 files changed, 57 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index eef6358ec587..aeec090e1387 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -54,6 +54,10 @@ definitions: name: hash doc: Device is capable of exposing receive packet hash via bpf_xdp_metadata_rx_hash(). + - + name: vlan-tag + doc: + Device is capable of exposing receive packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag(). - type: flags name: xsk-flags diff --git a/Documentation/networking/xdp-rx-metadata.rst b/Documentation/networking/xdp-rx-metadata.rst index e3e9420fd817..a6e0ece18be5 100644 --- a/Documentation/networking/xdp-rx-metadata.rst +++ b/Documentation/networking/xdp-rx-metadata.rst @@ -20,7 +20,13 @@ Currently, the following kfuncs are supported. In the future, as more metadata is supported, this set will grow: .. kernel-doc:: net/core/xdp.c - :identifiers: bpf_xdp_metadata_rx_timestamp bpf_xdp_metadata_rx_hash + :identifiers: bpf_xdp_metadata_rx_timestamp + +.. kernel-doc:: net/core/xdp.c + :identifiers: bpf_xdp_metadata_rx_hash + +.. kernel-doc:: net/core/xdp.c + :identifiers: bpf_xdp_metadata_rx_vlan_tag An XDP program can use these kfuncs to read the metadata into stack variables for its own consumption. Or, to pass the metadata on to other diff --git a/include/net/xdp.h b/include/net/xdp.h index b7d6fe61381f..8cd04a74dba5 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -404,6 +404,10 @@ void xdp_attachment_setup(struct xdp_attachment_info *info, NETDEV_XDP_RX_METADATA_HASH, \ bpf_xdp_metadata_rx_hash, \ xmo_rx_hash) \ + XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_VLAN_TAG, \ + NETDEV_XDP_RX_METADATA_VLAN_TAG, \ + bpf_xdp_metadata_rx_vlan_tag, \ + xmo_rx_vlan_tag) \ enum xdp_rx_metadata { #define XDP_METADATA_KFUNC(name, _, __, ___) name, @@ -465,6 +469,8 @@ struct xdp_metadata_ops { int (*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp); int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash, enum xdp_rss_hash_type *rss_type); + int (*xmo_rx_vlan_tag)(const struct xdp_md *ctx, __be16 *vlan_proto, + u16 *vlan_tci); }; #ifdef CONFIG_NET diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 6244c0164976..966638b08ccf 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -44,10 +44,13 @@ enum netdev_xdp_act { * timestamp via bpf_xdp_metadata_rx_timestamp(). * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet * hash via bpf_xdp_metadata_rx_hash(). + * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive + * packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag(). */ enum netdev_xdp_rx_metadata { NETDEV_XDP_RX_METADATA_TIMESTAMP = 1, NETDEV_XDP_RX_METADATA_HASH = 2, + NETDEV_XDP_RX_METADATA_VLAN_TAG = 4, }; /** diff --git a/net/core/xdp.c b/net/core/xdp.c index b6f1d6dab3f2..4869c1c2d8f3 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -736,6 +736,39 @@ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash, return -EOPNOTSUPP; } +/** + * bpf_xdp_metadata_rx_vlan_tag - Get XDP packet outermost VLAN tag + * @ctx: XDP context pointer. + * @vlan_proto: Destination pointer for VLAN Tag protocol identifier (TPID). + * @vlan_tci: Destination pointer for VLAN TCI (VID + DEI + PCP) + * + * In case of success, ``vlan_proto`` contains *Tag protocol identifier (TPID)*, + * usually ``ETH_P_8021Q`` or ``ETH_P_8021AD``, but some networks can use + * custom TPIDs. ``vlan_proto`` is stored in **network byte order (BE)** + * and should be used as follows: + * ``if (vlan_proto == bpf_htons(ETH_P_8021Q)) do_something();`` + * + * ``vlan_tci`` contains the remaining 16 bits of a VLAN tag. + * Driver is expected to provide those in **host byte order (usually LE)**, + * so the bpf program should not perform byte conversion. + * According to 802.1Q standard, *VLAN TCI (Tag control information)* + * is a bit field that contains: + * *VLAN identifier (VID)* that can be read with ``vlan_tci & 0xfff``, + * *Drop eligible indicator (DEI)* - 1 bit, + * *Priority code point (PCP)* - 3 bits. + * For detailed meaning of DEI and PCP, please refer to other sources. + * + * Return: + * * Returns 0 on success or ``-errno`` on error. + * * ``-EOPNOTSUPP`` : device driver doesn't implement kfunc + * * ``-ENODATA`` : VLAN tag was not stripped or is not available + */ +__bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx, + __be16 *vlan_proto, u16 *vlan_tci) +{ + return -EOPNOTSUPP; +} + __bpf_kfunc_end_defs(); BTF_SET8_START(xdp_metadata_kfunc_ids) diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 6244c0164976..966638b08ccf 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -44,10 +44,13 @@ enum netdev_xdp_act { * timestamp via bpf_xdp_metadata_rx_timestamp(). * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet * hash via bpf_xdp_metadata_rx_hash(). + * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive + * packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag(). */ enum netdev_xdp_rx_metadata { NETDEV_XDP_RX_METADATA_TIMESTAMP = 1, NETDEV_XDP_RX_METADATA_HASH = 2, + NETDEV_XDP_RX_METADATA_VLAN_TAG = 4, }; /** diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c index 3b9dee94d4ce..e3fe748086bd 100644 --- a/tools/net/ynl/generated/netdev-user.c +++ b/tools/net/ynl/generated/netdev-user.c @@ -53,6 +53,7 @@ const char *netdev_xdp_act_str(enum netdev_xdp_act value) static const char * const netdev_xdp_rx_metadata_strmap[] = { [0] = "timestamp", [1] = "hash", + [2] = "vlan-tag", }; const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value) -- cgit From 13e59344fb9d3c9d3acd138ae320b5b67b658694 Mon Sep 17 00:00:00 2001 From: Ahmed Zaki Date: Tue, 12 Dec 2023 17:33:16 -0700 Subject: net: ethtool: add support for symmetric-xor RSS hash Symmetric RSS hash functions are beneficial in applications that monitor both Tx and Rx packets of the same flow (IDS, software firewalls, ..etc). Getting all traffic of the same flow on the same RX queue results in higher CPU cache efficiency. A NIC that supports "symmetric-xor" can achieve this RSS hash symmetry by XORing the source and destination fields and pass the values to the RSS hash algorithm. The user may request RSS hash symmetry for a specific algorithm, via: # ethtool -X eth0 hfunc symmetric-xor or turn symmetry off (asymmetric) by: # ethtool -X eth0 hfunc The specific fields for each flow type should then be specified as usual via: # ethtool -N|-U eth0 rx-flow-hash s|d|f|n Reviewed-by: Wojciech Drewek Signed-off-by: Ahmed Zaki Link: https://lore.kernel.org/r/20231213003321.605376-4-ahmed.zaki@intel.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/ethtool.yaml | 4 ++++ Documentation/networking/ethtool-netlink.rst | 6 +++++- Documentation/networking/scaling.rst | 15 ++++++++++++++ include/linux/ethtool.h | 6 ++++++ include/uapi/linux/ethtool.h | 13 +++++++++++- include/uapi/linux/ethtool_netlink.h | 1 + net/ethtool/ioctl.c | 30 ++++++++++++++++++++++++---- net/ethtool/rss.c | 5 +++++ 8 files changed, 74 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 5c7a65b009b4..197208f419dc 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -908,6 +908,9 @@ attribute-sets: - name: hkey type: binary + - + name: input_xfrm + type: u32 - name: plca attributes: @@ -1598,6 +1601,7 @@ operations: - hfunc - indir - hkey + - input_xfrm dump: *rss-get-op - name: plca-get-cfg diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 6a49624a9cbf..d583d9abf2f8 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1774,12 +1774,16 @@ Kernel response contents: ``ETHTOOL_A_RSS_HFUNC`` u32 RSS hash func ``ETHTOOL_A_RSS_INDIR`` binary Indir table bytes ``ETHTOOL_A_RSS_HKEY`` binary Hash key bytes + ``ETHTOOL_A_RSS_INPUT_XFRM`` u32 RSS input data transformation ===================================== ====== ========================== ETHTOOL_A_RSS_HFUNC attribute is bitmap indicating the hash function being used. Current supported options are toeplitz, xor or crc32. -ETHTOOL_A_RSS_INDIR attribute returns RSS indrection table where each byte +ETHTOOL_A_RSS_INDIR attribute returns RSS indirection table where each byte indicates queue number. +ETHTOOL_A_RSS_INPUT_XFRM attribute is a bitmap indicating the type of +transformation applied to the input protocol fields before given to the RSS +hfunc. Current supported option is symmetric-xor. PLCA_GET_CFG ============ diff --git a/Documentation/networking/scaling.rst b/Documentation/networking/scaling.rst index 03ae19a689fc..4eb50bcb9d42 100644 --- a/Documentation/networking/scaling.rst +++ b/Documentation/networking/scaling.rst @@ -44,6 +44,21 @@ by masking out the low order seven bits of the computed hash for the packet (usually a Toeplitz hash), taking this number as a key into the indirection table and reading the corresponding value. +Some NICs support symmetric RSS hashing where, if the IP (source address, +destination address) and TCP/UDP (source port, destination port) tuples +are swapped, the computed hash is the same. This is beneficial in some +applications that monitor TCP/IP flows (IDS, firewalls, ...etc) and need +both directions of the flow to land on the same Rx queue (and CPU). The +"Symmetric-XOR" is a type of RSS algorithms that achieves this hash +symmetry by XORing the input source and destination fields of the IP +and/or L4 protocols. This, however, results in reduced input entropy and +could potentially be exploited. Specifically, the algorithm XORs the input +as follows:: + + # (SRC_IP ^ DST_IP, SRC_IP ^ DST_IP, SRC_PORT ^ DST_PORT, SRC_PORT ^ DST_PORT) + +The result is then fed to the underlying RSS algorithm. + Some advanced NICs allow steering packets to queues based on programmable filters. For example, webserver bound TCP port 80 packets can be directed to their own receive queue. Such “n-tuple” filters can diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 66fe254c3e51..cfcd952a1d4f 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -615,6 +615,8 @@ struct ethtool_mm_stats { * to allocate a new RSS context; on return this field will * contain the ID of the newly allocated context. * @rss_delete: Set to non-ZERO to remove the @rss_context context. + * @input_xfrm: Defines how the input data is transformed. Valid values are one + * of %RXH_XFRM_*. */ struct ethtool_rxfh_param { u8 hfunc; @@ -624,6 +626,7 @@ struct ethtool_rxfh_param { u8 *key; u32 rss_context; u8 rss_delete; + u8 input_xfrm; }; /** @@ -632,6 +635,8 @@ struct ethtool_rxfh_param { * parameter. * @cap_rss_ctx_supported: indicates if the driver supports RSS * contexts. + * @cap_rss_sym_xor_supported: indicates if the driver supports symmetric-xor + * RSS. * @supported_coalesce_params: supported types of interrupt coalescing. * @supported_ring_params: supported ring params. * @get_drvinfo: Report driver/device information. Modern drivers no @@ -811,6 +816,7 @@ struct ethtool_rxfh_param { struct ethtool_ops { u32 cap_link_lanes_supported:1; u32 cap_rss_ctx_supported:1; + u32 cap_rss_sym_xor_supported:1; u32 supported_coalesce_params; u32 supported_ring_params; void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index f7fba0dc87e5..0787d561ace0 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1266,6 +1266,8 @@ struct ethtool_rxfh_indir { * hardware hash key. * @hfunc: Defines the current RSS hash function used by HW (or to be set to). * Valid values are one of the %ETH_RSS_HASH_*. + * @input_xfrm: Defines how the input data is transformed. Valid values are one + * of %RXH_XFRM_*. * @rsvd8: Reserved for future use; see the note on reserved space. * @rsvd32: Reserved for future use; see the note on reserved space. * @rss_config: RX ring/queue index for each hash value i.e., indirection table @@ -1285,7 +1287,8 @@ struct ethtool_rxfh { __u32 indir_size; __u32 key_size; __u8 hfunc; - __u8 rsvd8[3]; + __u8 input_xfrm; + __u8 rsvd8[2]; __u32 rsvd32; __u32 rss_config[]; }; @@ -1992,6 +1995,14 @@ static inline int ethtool_validate_duplex(__u8 duplex) #define WOL_MODE_COUNT 8 +/* RSS hash function data + * XOR the corresponding source and destination fields of each specified + * protocol. Both copies of the XOR'ed fields are fed into the RSS and RXHASH + * calculation. Note that this XORing reduces the input set entropy and could + * be exploited to reduce the RSS queue spread. + */ +#define RXH_XFRM_SYM_XOR (1 << 0) + /* L2-L4 network traffic flow types */ #define TCP_V4_FLOW 0x01 /* hash or spec (tcp_ip4_spec) */ #define UDP_V4_FLOW 0x02 /* hash or spec (udp_ip4_spec) */ diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 73e2c10dc2cc..3f89074aa06c 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -908,6 +908,7 @@ enum { ETHTOOL_A_RSS_HFUNC, /* u32 */ ETHTOOL_A_RSS_INDIR, /* binary */ ETHTOOL_A_RSS_HKEY, /* binary */ + ETHTOOL_A_RSS_INPUT_XFRM, /* u32 */ __ETHTOOL_A_RSS_CNT, ETHTOOL_A_RSS_MAX = (__ETHTOOL_A_RSS_CNT - 1), diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 86e5fc64b711..86d47425038b 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -972,18 +972,35 @@ static int ethtool_rxnfc_copy_to_user(void __user *useraddr, static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, u32 cmd, void __user *useraddr) { + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_rxfh_param rxfh = {}; struct ethtool_rxnfc info; size_t info_size = sizeof(info); int rc; - if (!dev->ethtool_ops->set_rxnfc) + if (!ops->set_rxnfc || !ops->get_rxfh) return -EOPNOTSUPP; rc = ethtool_rxnfc_copy_struct(cmd, &info, &info_size, useraddr); if (rc) return rc; - rc = dev->ethtool_ops->set_rxnfc(dev, &info); + rc = ops->get_rxfh(dev, &rxfh); + if (rc) + return rc; + + /* Sanity check: if symmetric-xor is set, then: + * 1 - no other fields besides IP src/dst and/or L4 src/dst + * 2 - If src is set, dst must also be set + */ + if ((rxfh.input_xfrm & RXH_XFRM_SYM_XOR) && + ((info.data & ~(RXH_IP_SRC | RXH_IP_DST | + RXH_L4_B_0_1 | RXH_L4_B_2_3)) || + (!!(info.data & RXH_IP_SRC) ^ !!(info.data & RXH_IP_DST)) || + (!!(info.data & RXH_L4_B_0_1) ^ !!(info.data & RXH_L4_B_2_3)))) + return -EINVAL; + + rc = ops->set_rxnfc(dev, &info); if (rc) return rc; @@ -1198,7 +1215,7 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, user_key_size = rxfh.key_size; /* Check that reserved fields are 0 for now */ - if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd8[2] || rxfh.rsvd32) + if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32) return -EINVAL; /* Most drivers don't handle rss_context, check it's 0 as well */ if (rxfh.rss_context && !ops->cap_rss_ctx_supported) @@ -1271,11 +1288,15 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, return -EFAULT; /* Check that reserved fields are 0 for now */ - if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd8[2] || rxfh.rsvd32) + if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32) return -EINVAL; /* Most drivers don't handle rss_context, check it's 0 as well */ if (rxfh.rss_context && !ops->cap_rss_ctx_supported) return -EOPNOTSUPP; + /* Check input data transformation capabilities */ + if ((rxfh.input_xfrm & RXH_XFRM_SYM_XOR) && + !ops->cap_rss_sym_xor_supported) + return -EOPNOTSUPP; /* If either indir, hash key or function is valid, proceed further. * Must request at least one change: indir size, hash key or function. @@ -1341,6 +1362,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, rxfh_dev.hfunc = rxfh.hfunc; rxfh_dev.rss_context = rxfh.rss_context; + rxfh_dev.input_xfrm = rxfh.input_xfrm; ret = ops->set_rxfh(dev, &rxfh_dev, extack); if (ret) diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index efc9f4409e40..71679137eff2 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -13,6 +13,7 @@ struct rss_reply_data { u32 indir_size; u32 hkey_size; u32 hfunc; + u32 input_xfrm; u32 *indir_table; u8 *hkey; }; @@ -97,6 +98,7 @@ rss_prepare_data(const struct ethnl_req_info *req_base, goto out_ops; data->hfunc = rxfh.hfunc; + data->input_xfrm = rxfh.input_xfrm; out_ops: ethnl_ops_complete(dev); return ret; @@ -110,6 +112,7 @@ rss_reply_size(const struct ethnl_req_info *req_base, int len; len = nla_total_size(sizeof(u32)) + /* _RSS_HFUNC */ + nla_total_size(sizeof(u32)) + /* _RSS_INPUT_XFRM */ nla_total_size(sizeof(u32) * data->indir_size) + /* _RSS_INDIR */ nla_total_size(data->hkey_size); /* _RSS_HKEY */ @@ -124,6 +127,8 @@ rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, if ((data->hfunc && nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) || + (data->input_xfrm && + nla_put_u32(skb, ETHTOOL_A_RSS_INPUT_XFRM, data->input_xfrm)) || (data->indir_size && nla_put(skb, ETHTOOL_A_RSS_INDIR, sizeof(u32) * data->indir_size, data->indir_table)) || -- cgit From b4c2bea8ceaa50cd42a8f73667389d801a3ecf2d Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 25 Oct 2023 16:02:03 +0200 Subject: add listmount(2) syscall Add way to query the children of a particular mount. This is a more flexible way to iterate the mount tree than having to parse /proc/self/mountinfo. Lookup the mount by the new 64bit mount ID. If a mount needs to be queried based on path, then statx(2) can be used to first query the mount ID belonging to the path. Return an array of new (64bit) mount ID's. Without privileges only mounts are listed which are reachable from the task's root. Folded into this patch are several later improvements. Keeping them separate would make the history pointlessly confusing: * Recursive listing of mounts is the default now (cf. [1]). * Remove explicit LISTMOUNT_UNREACHABLE flag (cf. [1]) and fail if mount is unreachable from current root. This also makes permission checking consistent with statmount() (cf. [3]). * Start listing mounts in unique mount ID order (cf. [2]) to allow continuing listmount() from a midpoint. * Allow to continue listmount(). The @request_mask parameter is renamed and to @param to be usable by both statmount() and listmount(). If @param is set to a mount id then listmount() will continue listing mounts from that id on. This allows listing mounts in multiple listmount invocations without having to resize the buffer. If @param is zero then the listing starts from the beginning (cf. [4]). * Don't return EOVERFLOW, instead return the buffer size which allows to detect a full buffer as well (cf. [4]). Signed-off-by: Miklos Szeredi Link: https://lore.kernel.org/r/20231025140205.3586473-6-mszeredi@redhat.com Reviewed-by: Ian Kent Link: https://lore.kernel.org/r/20231128160337.29094-2-mszeredi@redhat.com [1] (folded) Link: https://lore.kernel.org/r/20231128160337.29094-3-mszeredi@redhat.com [2] (folded) Link: https://lore.kernel.org/r/20231128160337.29094-4-mszeredi@redhat.com [3] (folded) Link: https://lore.kernel.org/r/20231128160337.29094-5-mszeredi@redhat.com [4] (folded) [Christian Brauner : various smaller fixes] Signed-off-by: Christian Brauner --- fs/namespace.c | 86 ++++++++++++++++++++++++++++++++++++++++++++-- include/linux/syscalls.h | 3 ++ include/uapi/linux/mount.h | 14 +++++++- 3 files changed, 100 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/namespace.c b/fs/namespace.c index 7f1618ed2aba..873185b8a84b 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -32,6 +32,7 @@ #include #include #include +#include #include "pnode.h" #include "internal.h" @@ -1009,7 +1010,7 @@ void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct m static inline struct mount *node_to_mount(struct rb_node *node) { - return rb_entry(node, struct mount, mnt_node); + return node ? rb_entry(node, struct mount, mnt_node) : NULL; } static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt) @@ -4945,7 +4946,7 @@ static int prepare_kstatmount(struct kstatmount *ks, struct mnt_id_req *kreq, return -EFAULT; memset(ks, 0, sizeof(*ks)); - ks->mask = kreq->request_mask; + ks->mask = kreq->param; ks->buf = buf; ks->bufsize = bufsize; ks->seq.size = seq_size; @@ -4999,6 +5000,87 @@ retry: return ret; } +static struct mount *listmnt_next(struct mount *curr) +{ + return node_to_mount(rb_next(&curr->mnt_node)); +} + +static ssize_t do_listmount(struct mount *first, struct path *orig, u64 mnt_id, + u64 __user *buf, size_t bufsize, + const struct path *root) +{ + struct mount *r; + ssize_t ctr; + int err; + + /* + * Don't trigger audit denials. We just want to determine what + * mounts to show users. + */ + if (!is_path_reachable(real_mount(orig->mnt), orig->dentry, root) && + !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + err = security_sb_statfs(orig->dentry); + if (err) + return err; + + for (ctr = 0, r = first; r && ctr < bufsize; r = listmnt_next(r)) { + if (r->mnt_id_unique == mnt_id) + continue; + if (!is_path_reachable(r, r->mnt.mnt_root, orig)) + continue; + ctr = array_index_nospec(ctr, bufsize); + if (put_user(r->mnt_id_unique, buf + ctr)) + return -EFAULT; + if (check_add_overflow(ctr, 1, &ctr)) + return -ERANGE; + } + return ctr; +} + +SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, + u64 __user *, buf, size_t, bufsize, unsigned int, flags) +{ + struct mnt_namespace *ns = current->nsproxy->mnt_ns; + struct mnt_id_req kreq; + struct mount *first; + struct path root, orig; + u64 mnt_id, last_mnt_id; + ssize_t ret; + + if (flags) + return -EINVAL; + + if (copy_from_user(&kreq, req, sizeof(kreq))) + return -EFAULT; + mnt_id = kreq.mnt_id; + last_mnt_id = kreq.param; + + down_read(&namespace_sem); + get_fs_root(current->fs, &root); + if (mnt_id == LSMT_ROOT) { + orig = root; + } else { + ret = -ENOENT; + orig.mnt = lookup_mnt_in_ns(mnt_id, ns); + if (!orig.mnt) + goto err; + orig.dentry = orig.mnt->mnt_root; + } + if (!last_mnt_id) + first = node_to_mount(rb_first(&ns->mounts)); + else + first = mnt_find_id_at(ns, last_mnt_id + 1); + + ret = do_listmount(first, &orig, mnt_id, buf, bufsize, &root); +err: + path_put(&root); + up_read(&namespace_sem); + return ret; +} + + static void __init init_mount_tree(void) { struct vfsmount *mnt; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 530ca9adf5f1..2d6d3e76e3f7 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -412,6 +412,9 @@ asmlinkage long sys_fstatfs64(unsigned int fd, size_t sz, asmlinkage long sys_statmount(const struct mnt_id_req __user *req, struct statmount __user *buf, size_t bufsize, unsigned int flags); +asmlinkage long sys_listmount(const struct mnt_id_req __user *req, + u64 __user *buf, size_t bufsize, + unsigned int flags); asmlinkage long sys_truncate(const char __user *path, long length); asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length); #if BITS_PER_LONG == 32 diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index afdf4f2f6672..dc9a0112d819 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -176,9 +176,16 @@ struct statmount { char str[]; /* Variable size part containing strings */ }; +/* + * Structure for passing mount ID and miscellaneous parameters to statmount(2) + * and listmount(2). + * + * For statmount(2) @param represents the request mask. + * For listmount(2) @param represents the last listed mount id (or zero). + */ struct mnt_id_req { __u64 mnt_id; - __u64 request_mask; + __u64 param; }; /* @@ -191,4 +198,9 @@ struct mnt_id_req { #define STATMOUNT_MNT_POINT 0x00000010U /* Want/got mnt_point */ #define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */ +/* + * Special @mnt_id values that can be passed to listmount + */ +#define LSMT_ROOT 0xffffffffffffffff /* root mount */ + #endif /* _UAPI_LINUX_MOUNT_H */ -- cgit From 35e27a5744131996061e6e323f1bcb4c827ae867 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 29 Nov 2023 12:27:15 +0100 Subject: fs: keep struct mnt_id_req extensible Make it extensible so that we have the liberty to reuse it in future mount-id based apis. Treat zero size as the first published struct. Signed-off-by: Christian Brauner --- fs/namespace.c | 34 ++++++++++++++++++++++++++++++---- include/uapi/linux/mount.h | 5 +++++ 2 files changed, 35 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/namespace.c b/fs/namespace.c index 873185b8a84b..918e8f89ce35 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4956,6 +4956,30 @@ static int prepare_kstatmount(struct kstatmount *ks, struct mnt_id_req *kreq, return 0; } +static int copy_mnt_id_req(const struct mnt_id_req __user *req, + struct mnt_id_req *kreq) +{ + int ret; + size_t usize; + + BUILD_BUG_ON(sizeof(struct mnt_id_req) != MNT_ID_REQ_SIZE_VER0); + + ret = get_user(usize, &req->size); + if (ret) + return -EFAULT; + if (unlikely(usize > PAGE_SIZE)) + return -E2BIG; + if (unlikely(usize < MNT_ID_REQ_SIZE_VER0)) + return -EINVAL; + memset(kreq, 0, sizeof(*kreq)); + ret = copy_struct_from_user(kreq, sizeof(*kreq), req, usize); + if (ret) + return ret; + if (kreq->spare != 0) + return -EINVAL; + return 0; +} + SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req, struct statmount __user *, buf, size_t, bufsize, unsigned int, flags) @@ -4970,8 +4994,9 @@ SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req, if (flags) return -EINVAL; - if (copy_from_user(&kreq, req, sizeof(kreq))) - return -EFAULT; + ret = copy_mnt_id_req(req, &kreq); + if (ret) + return ret; retry: ret = prepare_kstatmount(&ks, &kreq, buf, bufsize, seq_size); @@ -5052,8 +5077,9 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, if (flags) return -EINVAL; - if (copy_from_user(&kreq, req, sizeof(kreq))) - return -EFAULT; + ret = copy_mnt_id_req(req, &kreq); + if (ret) + return ret; mnt_id = kreq.mnt_id; last_mnt_id = kreq.param; diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index dc9a0112d819..ad5478dbad00 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -184,10 +184,15 @@ struct statmount { * For listmount(2) @param represents the last listed mount id (or zero). */ struct mnt_id_req { + __u32 size; + __u32 spare; __u64 mnt_id; __u64 param; }; +/* List of all mnt_id_req versions. */ +#define MNT_ID_REQ_SIZE_VER0 24 /* sizeof first published struct */ + /* * @mask bits for statmount(2) */ -- cgit From 074b3cf442c518631f4b6d11d7fdfe143e17e955 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 12 Dec 2023 20:43:15 -0800 Subject: wifi: nl80211: fix grammar & spellos Correct spelling as reported by codespell. Correct run-on sentences and other grammar issues. Add hyphenation of adjectives. Correct some punctuation. Signed-off-by: Randy Dunlap Cc: Johannes Berg Cc: linux-wireless@vger.kernel.org Cc: Kalle Valo Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Link: https://msgid.link/20231213044315.19459-1-rdunlap@infradead.org Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 74 ++++++++++++++++++++++---------------------- 1 file changed, 37 insertions(+), 37 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 2d8468cbc457..a682b54bd3ba 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -72,7 +72,7 @@ * For drivers supporting TDLS with external setup (WIPHY_FLAG_SUPPORTS_TDLS * and WIPHY_FLAG_TDLS_EXTERNAL_SETUP), the station lifetime is as follows: * - a setup station entry is added, not yet authorized, without any rate - * or capability information, this just exists to avoid race conditions + * or capability information; this just exists to avoid race conditions * - when the TDLS setup is done, a single NL80211_CMD_SET_STATION is valid * to add rate and capability information to the station and at the same * time mark it authorized. @@ -87,7 +87,7 @@ * DOC: Frame transmission/registration support * * Frame transmission and registration support exists to allow userspace - * management entities such as wpa_supplicant react to management frames + * management entities such as wpa_supplicant to react to management frames * that are not being handled by the kernel. This includes, for example, * certain classes of action frames that cannot be handled in the kernel * for various reasons. @@ -113,7 +113,7 @@ * * Frame transmission allows userspace to send for example the required * responses to action frames. It is subject to some sanity checking, - * but many frames can be transmitted. When a frame was transmitted, its + * but many frames can be transmitted. When a frame is transmitted, its * status is indicated to the sending socket. * * For more technical details, see the corresponding command descriptions @@ -123,7 +123,7 @@ /** * DOC: Virtual interface / concurrency capabilities * - * Some devices are able to operate with virtual MACs, they can have + * Some devices are able to operate with virtual MACs; they can have * more than one virtual interface. The capability handling for this * is a bit complex though, as there may be a number of restrictions * on the types of concurrency that are supported. @@ -135,7 +135,7 @@ * Once concurrency is desired, more attributes must be observed: * To start with, since some interface types are purely managed in * software, like the AP-VLAN type in mac80211 for example, there's - * an additional list of these, they can be added at any time and + * an additional list of these; they can be added at any time and * are only restricted by some semantic restrictions (e.g. AP-VLAN * cannot be added without a corresponding AP interface). This list * is exported in the %NL80211_ATTR_SOFTWARE_IFTYPES attribute. @@ -164,7 +164,7 @@ * Packet coalesce feature helps to reduce number of received interrupts * to host by buffering these packets in firmware/hardware for some * predefined time. Received interrupt will be generated when one of the - * following events occur. + * following events occurs. * a) Expiration of hardware timer whose expiration time is set to maximum * coalescing delay of matching coalesce rule. * b) Coalescing buffer in hardware reaches its limit. @@ -174,7 +174,7 @@ * rule. * a) Maximum coalescing delay * b) List of packet patterns which needs to be matched - * c) Condition for coalescence. pattern 'match' or 'no match' + * c) Condition for coalescence: pattern 'match' or 'no match' * Multiple such rules can be created. */ @@ -213,7 +213,7 @@ /** * DOC: FILS shared key authentication offload * - * FILS shared key authentication offload can be advertized by drivers by + * FILS shared key authentication offload can be advertised by drivers by * setting @NL80211_EXT_FEATURE_FILS_SK_OFFLOAD flag. The drivers that support * FILS shared key authentication offload should be able to construct the * authentication and association frames for FILS shared key authentication and @@ -239,7 +239,7 @@ * The PMKSA can be maintained in userspace persistently so that it can be used * later after reboots or wifi turn off/on also. * - * %NL80211_ATTR_FILS_CACHE_ID is the cache identifier advertized by a FILS + * %NL80211_ATTR_FILS_CACHE_ID is the cache identifier advertised by a FILS * capable AP supporting PMK caching. It specifies the scope within which the * PMKSAs are cached in an ESS. %NL80211_CMD_SET_PMKSA and * %NL80211_CMD_DEL_PMKSA are enhanced to allow support for PMKSA caching based @@ -290,12 +290,12 @@ * If the configuration needs to be applied for specific peer then the MAC * address of the peer needs to be passed in %NL80211_ATTR_MAC, otherwise the * configuration will be applied for all the connected peers in the vif except - * any peers that have peer specific configuration for the TID by default; if - * the %NL80211_TID_CONFIG_ATTR_OVERRIDE flag is set, peer specific values + * any peers that have peer-specific configuration for the TID by default; if + * the %NL80211_TID_CONFIG_ATTR_OVERRIDE flag is set, peer-specific values * will be overwritten. * - * All this configuration is valid only for STA's current connection - * i.e. the configuration will be reset to default when the STA connects back + * All this configuration is valid only for STA's current connection, + * i.e., the configuration will be reset to default when the STA connects back * after disconnection/roaming, and this configuration will be cleared when * the interface goes down. */ @@ -521,7 +521,7 @@ * %NL80211_ATTR_SCHED_SCAN_PLANS. If %NL80211_ATTR_SCHED_SCAN_PLANS is * not specified and only %NL80211_ATTR_SCHED_SCAN_INTERVAL is specified, * scheduled scan will run in an infinite loop with the specified interval. - * These attributes are mutually exculsive, + * These attributes are mutually exclusive, * i.e. NL80211_ATTR_SCHED_SCAN_INTERVAL must not be passed if * NL80211_ATTR_SCHED_SCAN_PLANS is defined. * If for some reason scheduled scan is aborted by the driver, all scan @@ -552,7 +552,7 @@ * %NL80211_CMD_STOP_SCHED_SCAN command is received or when the interface * is brought down while a scheduled scan was running. * - * @NL80211_CMD_GET_SURVEY: get survey resuls, e.g. channel occupation + * @NL80211_CMD_GET_SURVEY: get survey results, e.g. channel occupation * or noise level * @NL80211_CMD_NEW_SURVEY_RESULTS: survey data notification (as a reply to * NL80211_CMD_GET_SURVEY and on the "scan" multicast group) @@ -563,7 +563,7 @@ * using %NL80211_ATTR_SSID, %NL80211_ATTR_FILS_CACHE_ID, * %NL80211_ATTR_PMKID, and %NL80211_ATTR_PMK in case of FILS * authentication where %NL80211_ATTR_FILS_CACHE_ID is the identifier - * advertized by a FILS capable AP identifying the scope of PMKSA in an + * advertised by a FILS capable AP identifying the scope of PMKSA in an * ESS. * @NL80211_CMD_DEL_PMKSA: Delete a PMKSA cache entry, using %NL80211_ATTR_MAC * (for the BSSID) and %NL80211_ATTR_PMKID or using %NL80211_ATTR_SSID, @@ -608,7 +608,7 @@ * BSSID in case of station mode). %NL80211_ATTR_SSID is used to specify * the SSID (mainly for association, but is included in authentication * request, too, to help BSS selection. %NL80211_ATTR_WIPHY_FREQ + - * %NL80211_ATTR_WIPHY_FREQ_OFFSET is used to specify the frequence of the + * %NL80211_ATTR_WIPHY_FREQ_OFFSET is used to specify the frequency of the * channel in MHz. %NL80211_ATTR_AUTH_TYPE is used to specify the * authentication type. %NL80211_ATTR_IE is used to define IEs * (VendorSpecificInfo, but also including RSN IE and FT IEs) to be added @@ -817,7 +817,7 @@ * reached. * @NL80211_CMD_SET_CHANNEL: Set the channel (using %NL80211_ATTR_WIPHY_FREQ * and the attributes determining channel width) the given interface - * (identifed by %NL80211_ATTR_IFINDEX) shall operate on. + * (identified by %NL80211_ATTR_IFINDEX) shall operate on. * In case multiple channels are supported by the device, the mechanism * with which it switches channels is implementation-defined. * When a monitor interface is given, it can only switch channel while @@ -889,7 +889,7 @@ * inform userspace of the new replay counter. * * @NL80211_CMD_PMKSA_CANDIDATE: This is used as an event to inform userspace - * of PMKSA caching dandidates. + * of PMKSA caching candidates. * * @NL80211_CMD_TDLS_OPER: Perform a high-level TDLS command (e.g. link setup). * In addition, this can be used as an event to request userspace to take @@ -925,7 +925,7 @@ * * @NL80211_CMD_PROBE_CLIENT: Probe an associated station on an AP interface * by sending a null data frame to it and reporting when the frame is - * acknowleged. This is used to allow timing out inactive clients. Uses + * acknowledged. This is used to allow timing out inactive clients. Uses * %NL80211_ATTR_IFINDEX and %NL80211_ATTR_MAC. The command returns a * direct reply with an %NL80211_ATTR_COOKIE that is later used to match * up the event with the request. The event includes the same data and @@ -1847,7 +1847,7 @@ enum nl80211_commands { * using %CMD_CONTROL_PORT_FRAME. If control port routing over NL80211 is * to be used then userspace must also use the %NL80211_ATTR_SOCKET_OWNER * flag. When used with %NL80211_ATTR_CONTROL_PORT_NO_PREAUTH, pre-auth - * frames are not forwared over the control port. + * frames are not forwarded over the control port. * * @NL80211_ATTR_TESTDATA: Testmode data blob, passed through to the driver. * We recommend using nested, driver-specific attributes within this. @@ -1984,10 +1984,10 @@ enum nl80211_commands { * bit. Depending on which antennas are selected in the bitmap, 802.11n * drivers can derive which chainmasks to use (if all antennas belonging to * a particular chain are disabled this chain should be disabled) and if - * a chain has diversity antennas wether diversity should be used or not. + * a chain has diversity antennas whether diversity should be used or not. * HT capabilities (STBC, TX Beamforming, Antenna selection) can be * derived from the available chains after applying the antenna mask. - * Non-802.11n drivers can derive wether to use diversity or not. + * Non-802.11n drivers can derive whether to use diversity or not. * Drivers may reject configurations or RX/TX mask combinations they cannot * support by returning -EINVAL. * @@ -2557,7 +2557,7 @@ enum nl80211_commands { * from successful FILS authentication and is used with * %NL80211_CMD_CONNECT. * - * @NL80211_ATTR_FILS_CACHE_ID: A 2-octet identifier advertized by a FILS AP + * @NL80211_ATTR_FILS_CACHE_ID: A 2-octet identifier advertised by a FILS AP * identifying the scope of PMKSAs. This is used with * @NL80211_CMD_SET_PMKSA and @NL80211_CMD_DEL_PMKSA. * @@ -4200,7 +4200,7 @@ enum nl80211_wmm_rule { * (100 * dBm). * @NL80211_FREQUENCY_ATTR_DFS_STATE: current state for DFS * (enum nl80211_dfs_state) - * @NL80211_FREQUENCY_ATTR_DFS_TIME: time in miliseconds for how long + * @NL80211_FREQUENCY_ATTR_DFS_TIME: time in milliseconds for how long * this channel is in this DFS state. * @NL80211_FREQUENCY_ATTR_NO_HT40_MINUS: HT40- isn't possible with this * channel as the control channel @@ -5518,7 +5518,7 @@ enum nl80211_tx_rate_setting { * (%NL80211_TID_CONFIG_ATTR_TIDS, %NL80211_TID_CONFIG_ATTR_OVERRIDE). * @NL80211_TID_CONFIG_ATTR_PEER_SUPP: same as the previous per-vif one, but * per peer instead. - * @NL80211_TID_CONFIG_ATTR_OVERRIDE: flag attribue, if set indicates + * @NL80211_TID_CONFIG_ATTR_OVERRIDE: flag attribute, if set indicates * that the new configuration overrides all previous peer * configurations, otherwise previous peer specific configurations * should be left untouched. @@ -5901,7 +5901,7 @@ enum nl80211_attr_coalesce_rule { /** * enum nl80211_coalesce_condition - coalesce rule conditions - * @NL80211_COALESCE_CONDITION_MATCH: coalaesce Rx packets when patterns + * @NL80211_COALESCE_CONDITION_MATCH: coalesce Rx packets when patterns * in a rule are matched. * @NL80211_COALESCE_CONDITION_NO_MATCH: coalesce Rx packets when patterns * in a rule are not matched. @@ -6000,7 +6000,7 @@ enum nl80211_if_combination_attrs { * enum nl80211_plink_state - state of a mesh peer link finite state machine * * @NL80211_PLINK_LISTEN: initial state, considered the implicit - * state of non existent mesh peer links + * state of non-existent mesh peer links * @NL80211_PLINK_OPN_SNT: mesh plink open frame has been sent to * this mesh peer * @NL80211_PLINK_OPN_RCVD: mesh plink open frame has been received @@ -6293,7 +6293,7 @@ enum nl80211_feature_flags { * request to use RRM (see %NL80211_ATTR_USE_RRM) with * %NL80211_CMD_ASSOCIATE and %NL80211_CMD_CONNECT requests, which will set * the ASSOC_REQ_USE_RRM flag in the association request even if - * NL80211_FEATURE_QUIET is not advertized. + * NL80211_FEATURE_QUIET is not advertised. * @NL80211_EXT_FEATURE_MU_MIMO_AIR_SNIFFER: This device supports MU-MIMO air * sniffer which means that it can be configured to hear packets from * certain groups which can be configured by the @@ -6305,7 +6305,7 @@ enum nl80211_feature_flags { * the BSS that the interface that requested the scan is connected to * (if available). * @NL80211_EXT_FEATURE_BSS_PARENT_TSF: Per BSS, this driver reports the - * time the last beacon/probe was received. For a non MLO connection, the + * time the last beacon/probe was received. For a non-MLO connection, the * time is the TSF of the BSS that the interface that requested the scan is * connected to (if available). For an MLO connection, the time is the TSF * of the BSS corresponding with link ID specified in the scan request (if @@ -6313,7 +6313,7 @@ enum nl80211_feature_flags { * @NL80211_EXT_FEATURE_SET_SCAN_DWELL: This driver supports configuration of * channel dwell time. * @NL80211_EXT_FEATURE_BEACON_RATE_LEGACY: Driver supports beacon rate - * configuration (AP/mesh), supporting a legacy (non HT/VHT) rate. + * configuration (AP/mesh), supporting a legacy (non-HT/VHT) rate. * @NL80211_EXT_FEATURE_BEACON_RATE_HT: Driver supports beacon rate * configuration (AP/mesh) with HT rates. * @NL80211_EXT_FEATURE_BEACON_RATE_VHT: Driver supports beacon rate @@ -6649,7 +6649,7 @@ enum nl80211_timeout_reason { * request parameters IE in the probe request * @NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP: accept broadcast probe responses * @NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE: send probe request frames at - * rate of at least 5.5M. In case non OCE AP is discovered in the channel, + * rate of at least 5.5M. In case non-OCE AP is discovered in the channel, * only the first probe req in the channel will be sent in high rate. * @NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION: allow probe request * tx deferral (dot11FILSProbeDelay shall be set to 15ms) @@ -6685,7 +6685,7 @@ enum nl80211_timeout_reason { * received on the 2.4/5 GHz channels to actively scan only the 6GHz * channels on which APs are expected to be found. Note that when not set, * the scan logic would scan all 6GHz channels, but since transmission of - * probe requests on non PSC channels is limited, it is highly likely that + * probe requests on non-PSC channels is limited, it is highly likely that * these channels would passively be scanned. Also note that when the flag * is set, in addition to the colocated APs, PSC channels would also be * scanned if the user space has asked for it. @@ -7017,7 +7017,7 @@ enum nl80211_nan_func_term_reason { * The instance ID for the follow up Service Discovery Frame. This is u8. * @NL80211_NAN_FUNC_FOLLOW_UP_REQ_ID: relevant if the function's type * is follow up. This is a u8. - * The requestor instance ID for the follow up Service Discovery Frame. + * The requester instance ID for the follow up Service Discovery Frame. * @NL80211_NAN_FUNC_FOLLOW_UP_DEST: the MAC address of the recipient of the * follow up Service Discovery Frame. This is a binary attribute. * @NL80211_NAN_FUNC_CLOSE_RANGE: is this function limited for devices in a @@ -7407,7 +7407,7 @@ enum nl80211_peer_measurement_attrs { * @NL80211_PMSR_FTM_CAPA_ATTR_TRIGGER_BASED: flag attribute indicating if * trigger based ranging measurement is supported * @NL80211_PMSR_FTM_CAPA_ATTR_NON_TRIGGER_BASED: flag attribute indicating - * if non trigger based ranging measurement is supported + * if non-trigger-based ranging measurement is supported * * @NUM_NL80211_PMSR_FTM_CAPA_ATTR: internal * @NL80211_PMSR_FTM_CAPA_ATTR_MAX: highest attribute number @@ -7461,7 +7461,7 @@ enum nl80211_peer_measurement_ftm_capa { * if neither %NL80211_PMSR_FTM_REQ_ATTR_TRIGGER_BASED nor * %NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED is set, EDCA based * ranging will be used. - * @NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED: request non trigger based + * @NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED: request non-trigger-based * ranging measurement (flag) * This attribute and %NL80211_PMSR_FTM_REQ_ATTR_TRIGGER_BASED are * mutually exclusive. @@ -7539,7 +7539,7 @@ enum nl80211_peer_measurement_ftm_failure_reasons { * @NL80211_PMSR_FTM_RESP_ATTR_NUM_FTMR_ATTEMPTS: number of FTM Request frames * transmitted (u32, optional) * @NL80211_PMSR_FTM_RESP_ATTR_NUM_FTMR_SUCCESSES: number of FTM Request frames - * that were acknowleged (u32, optional) + * that were acknowledged (u32, optional) * @NL80211_PMSR_FTM_RESP_ATTR_BUSY_RETRY_TIME: retry time received from the * busy peer (u32, seconds) * @NL80211_PMSR_FTM_RESP_ATTR_NUM_BURSTS_EXP: actual number of bursts exponent -- cgit From b059aef76c519226730dd18777c0e15dad4fae21 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 14 Dec 2023 17:57:35 -0800 Subject: netlink: specs: mptcp: rename the MPTCP path management spec We assume in handful of places that the name of the spec is the same as the name of the family. We could fix that but it seems like a fair assumption to make. Rename the MPTCP spec instead. Reviewed-by: Mat Martineau Reviewed-by: Donald Hunter Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- Documentation/netlink/specs/mptcp.yaml | 393 ------------------------------ Documentation/netlink/specs/mptcp_pm.yaml | 393 ++++++++++++++++++++++++++++++ MAINTAINERS | 2 +- include/uapi/linux/mptcp_pm.h | 2 +- net/mptcp/mptcp_pm_gen.c | 2 +- net/mptcp/mptcp_pm_gen.h | 2 +- 6 files changed, 397 insertions(+), 397 deletions(-) delete mode 100644 Documentation/netlink/specs/mptcp.yaml create mode 100644 Documentation/netlink/specs/mptcp_pm.yaml (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/mptcp.yaml b/Documentation/netlink/specs/mptcp.yaml deleted file mode 100644 index 49f90cfb4698..000000000000 --- a/Documentation/netlink/specs/mptcp.yaml +++ /dev/null @@ -1,393 +0,0 @@ -# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) - -name: mptcp_pm -protocol: genetlink-legacy -doc: Multipath TCP. - -c-family-name: mptcp-pm-name -c-version-name: mptcp-pm-ver -max-by-define: true -kernel-policy: per-op -cmd-cnt-name: --mptcp-pm-cmd-after-last - -definitions: - - - type: enum - name: event-type - enum-name: mptcp-event-type - name-prefix: mptcp-event- - entries: - - - name: unspec - doc: unused event - - - name: created - doc: - token, family, saddr4 | saddr6, daddr4 | daddr6, sport, dport - A new MPTCP connection has been created. It is the good time to - allocate memory and send ADD_ADDR if needed. Depending on the - traffic-patterns it can take a long time until the - MPTCP_EVENT_ESTABLISHED is sent. - - - name: established - doc: - token, family, saddr4 | saddr6, daddr4 | daddr6, sport, dport - A MPTCP connection is established (can start new subflows). - - - name: closed - doc: - token - A MPTCP connection has stopped. - - - name: announced - value: 6 - doc: - token, rem_id, family, daddr4 | daddr6 [, dport] - A new address has been announced by the peer. - - - name: removed - doc: - token, rem_id - An address has been lost by the peer. - - - name: sub-established - value: 10 - doc: - token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport, - dport, backup, if_idx [, error] - A new subflow has been established. 'error' should not be set. - - - name: sub-closed - doc: - token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport, - dport, backup, if_idx [, error] - A subflow has been closed. An error (copy of sk_err) could be set if an - error has been detected for this subflow. - - - name: sub-priority - value: 13 - doc: - token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport, - dport, backup, if_idx [, error] - The priority of a subflow has changed. 'error' should not be set. - - - name: listener-created - value: 15 - doc: - family, sport, saddr4 | saddr6 - A new PM listener is created. - - - name: listener-closed - doc: - family, sport, saddr4 | saddr6 - A PM listener is closed. - -attribute-sets: - - - name: address - name-prefix: mptcp-pm-addr-attr- - attributes: - - - name: unspec - type: unused - value: 0 - - - name: family - type: u16 - - - name: id - type: u8 - - - name: addr4 - type: u32 - byte-order: big-endian - - - name: addr6 - type: binary - checks: - exact-len: 16 - - - name: port - type: u16 - byte-order: big-endian - - - name: flags - type: u32 - - - name: if-idx - type: s32 - - - name: subflow-attribute - name-prefix: mptcp-subflow-attr- - attributes: - - - name: unspec - type: unused - value: 0 - - - name: token-rem - type: u32 - - - name: token-loc - type: u32 - - - name: relwrite-seq - type: u32 - - - name: map-seq - type: u64 - - - name: map-sfseq - type: u32 - - - name: ssn-offset - type: u32 - - - name: map-datalen - type: u16 - - - name: flags - type: u32 - - - name: id-rem - type: u8 - - - name: id-loc - type: u8 - - - name: pad - type: pad - - - name: endpoint - name-prefix: mptcp-pm-endpoint- - attributes: - - - name: addr - type: nest - nested-attributes: address - - - name: attr - name-prefix: mptcp-pm-attr- - attr-cnt-name: --mptcp-attr-after-last - attributes: - - - name: unspec - type: unused - value: 0 - - - name: addr - type: nest - nested-attributes: address - - - name: rcv-add-addrs - type: u32 - - - name: subflows - type: u32 - - - name: token - type: u32 - - - name: loc-id - type: u8 - - - name: addr-remote - type: nest - nested-attributes: address - - - name: event-attr - enum-name: mptcp-event-attr - name-prefix: mptcp-attr- - attributes: - - - name: unspec - type: unused - value: 0 - - - name: token - type: u32 - - - name: family - type: u16 - - - name: loc-id - type: u8 - - - name: rem-id - type: u8 - - - name: saddr4 - type: u32 - byte-order: big-endian - - - name: saddr6 - type: binary - checks: - min-len: 16 - - - name: daddr4 - type: u32 - byte-order: big-endian - - - name: daddr6 - type: binary - checks: - min-len: 16 - - - name: sport - type: u16 - byte-order: big-endian - - - name: dport - type: u16 - byte-order: big-endian - - - name: backup - type: u8 - - - name: error - type: u8 - - - name: flags - type: u16 - - - name: timeout - type: u32 - - - name: if_idx - type: u32 - - - name: reset-reason - type: u32 - - - name: reset-flags - type: u32 - - - name: server-side - type: u8 - -operations: - list: - - - name: unspec - doc: unused - value: 0 - - - name: add-addr - doc: Add endpoint - attribute-set: endpoint - dont-validate: [ strict ] - flags: [ uns-admin-perm ] - do: &add-addr-attrs - request: - attributes: - - addr - - - name: del-addr - doc: Delete endpoint - attribute-set: endpoint - dont-validate: [ strict ] - flags: [ uns-admin-perm ] - do: *add-addr-attrs - - - name: get-addr - doc: Get endpoint information - attribute-set: endpoint - dont-validate: [ strict ] - flags: [ uns-admin-perm ] - do: &get-addr-attrs - request: - attributes: - - addr - reply: - attributes: - - addr - dump: - reply: - attributes: - - addr - - - name: flush-addrs - doc: flush addresses - attribute-set: endpoint - dont-validate: [ strict ] - flags: [ uns-admin-perm ] - do: *add-addr-attrs - - - name: set-limits - doc: Set protocol limits - attribute-set: attr - dont-validate: [ strict ] - flags: [ uns-admin-perm ] - do: &mptcp-limits - request: - attributes: - - rcv-add-addrs - - subflows - - - name: get-limits - doc: Get protocol limits - attribute-set: attr - dont-validate: [ strict ] - do: &mptcp-get-limits - request: - attributes: - - rcv-add-addrs - - subflows - reply: - attributes: - - rcv-add-addrs - - subflows - - - name: set-flags - doc: Change endpoint flags - attribute-set: attr - dont-validate: [ strict ] - flags: [ uns-admin-perm ] - do: &mptcp-set-flags - request: - attributes: - - addr - - token - - addr-remote - - - name: announce - doc: announce new sf - attribute-set: attr - dont-validate: [ strict ] - flags: [ uns-admin-perm ] - do: &announce-add - request: - attributes: - - addr - - token - - - name: remove - doc: announce removal - attribute-set: attr - dont-validate: [ strict ] - flags: [ uns-admin-perm ] - do: - request: - attributes: - - token - - loc-id - - - name: subflow-create - doc: todo - attribute-set: attr - dont-validate: [ strict ] - flags: [ uns-admin-perm ] - do: &sf-create - request: - attributes: - - addr - - token - - addr-remote - - - name: subflow-destroy - doc: todo - attribute-set: attr - dont-validate: [ strict ] - flags: [ uns-admin-perm ] - do: *sf-create diff --git a/Documentation/netlink/specs/mptcp_pm.yaml b/Documentation/netlink/specs/mptcp_pm.yaml new file mode 100644 index 000000000000..49f90cfb4698 --- /dev/null +++ b/Documentation/netlink/specs/mptcp_pm.yaml @@ -0,0 +1,393 @@ +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) + +name: mptcp_pm +protocol: genetlink-legacy +doc: Multipath TCP. + +c-family-name: mptcp-pm-name +c-version-name: mptcp-pm-ver +max-by-define: true +kernel-policy: per-op +cmd-cnt-name: --mptcp-pm-cmd-after-last + +definitions: + - + type: enum + name: event-type + enum-name: mptcp-event-type + name-prefix: mptcp-event- + entries: + - + name: unspec + doc: unused event + - + name: created + doc: + token, family, saddr4 | saddr6, daddr4 | daddr6, sport, dport + A new MPTCP connection has been created. It is the good time to + allocate memory and send ADD_ADDR if needed. Depending on the + traffic-patterns it can take a long time until the + MPTCP_EVENT_ESTABLISHED is sent. + - + name: established + doc: + token, family, saddr4 | saddr6, daddr4 | daddr6, sport, dport + A MPTCP connection is established (can start new subflows). + - + name: closed + doc: + token + A MPTCP connection has stopped. + - + name: announced + value: 6 + doc: + token, rem_id, family, daddr4 | daddr6 [, dport] + A new address has been announced by the peer. + - + name: removed + doc: + token, rem_id + An address has been lost by the peer. + - + name: sub-established + value: 10 + doc: + token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport, + dport, backup, if_idx [, error] + A new subflow has been established. 'error' should not be set. + - + name: sub-closed + doc: + token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport, + dport, backup, if_idx [, error] + A subflow has been closed. An error (copy of sk_err) could be set if an + error has been detected for this subflow. + - + name: sub-priority + value: 13 + doc: + token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport, + dport, backup, if_idx [, error] + The priority of a subflow has changed. 'error' should not be set. + - + name: listener-created + value: 15 + doc: + family, sport, saddr4 | saddr6 + A new PM listener is created. + - + name: listener-closed + doc: + family, sport, saddr4 | saddr6 + A PM listener is closed. + +attribute-sets: + - + name: address + name-prefix: mptcp-pm-addr-attr- + attributes: + - + name: unspec + type: unused + value: 0 + - + name: family + type: u16 + - + name: id + type: u8 + - + name: addr4 + type: u32 + byte-order: big-endian + - + name: addr6 + type: binary + checks: + exact-len: 16 + - + name: port + type: u16 + byte-order: big-endian + - + name: flags + type: u32 + - + name: if-idx + type: s32 + - + name: subflow-attribute + name-prefix: mptcp-subflow-attr- + attributes: + - + name: unspec + type: unused + value: 0 + - + name: token-rem + type: u32 + - + name: token-loc + type: u32 + - + name: relwrite-seq + type: u32 + - + name: map-seq + type: u64 + - + name: map-sfseq + type: u32 + - + name: ssn-offset + type: u32 + - + name: map-datalen + type: u16 + - + name: flags + type: u32 + - + name: id-rem + type: u8 + - + name: id-loc + type: u8 + - + name: pad + type: pad + - + name: endpoint + name-prefix: mptcp-pm-endpoint- + attributes: + - + name: addr + type: nest + nested-attributes: address + - + name: attr + name-prefix: mptcp-pm-attr- + attr-cnt-name: --mptcp-attr-after-last + attributes: + - + name: unspec + type: unused + value: 0 + - + name: addr + type: nest + nested-attributes: address + - + name: rcv-add-addrs + type: u32 + - + name: subflows + type: u32 + - + name: token + type: u32 + - + name: loc-id + type: u8 + - + name: addr-remote + type: nest + nested-attributes: address + - + name: event-attr + enum-name: mptcp-event-attr + name-prefix: mptcp-attr- + attributes: + - + name: unspec + type: unused + value: 0 + - + name: token + type: u32 + - + name: family + type: u16 + - + name: loc-id + type: u8 + - + name: rem-id + type: u8 + - + name: saddr4 + type: u32 + byte-order: big-endian + - + name: saddr6 + type: binary + checks: + min-len: 16 + - + name: daddr4 + type: u32 + byte-order: big-endian + - + name: daddr6 + type: binary + checks: + min-len: 16 + - + name: sport + type: u16 + byte-order: big-endian + - + name: dport + type: u16 + byte-order: big-endian + - + name: backup + type: u8 + - + name: error + type: u8 + - + name: flags + type: u16 + - + name: timeout + type: u32 + - + name: if_idx + type: u32 + - + name: reset-reason + type: u32 + - + name: reset-flags + type: u32 + - + name: server-side + type: u8 + +operations: + list: + - + name: unspec + doc: unused + value: 0 + - + name: add-addr + doc: Add endpoint + attribute-set: endpoint + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: &add-addr-attrs + request: + attributes: + - addr + - + name: del-addr + doc: Delete endpoint + attribute-set: endpoint + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: *add-addr-attrs + - + name: get-addr + doc: Get endpoint information + attribute-set: endpoint + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: &get-addr-attrs + request: + attributes: + - addr + reply: + attributes: + - addr + dump: + reply: + attributes: + - addr + - + name: flush-addrs + doc: flush addresses + attribute-set: endpoint + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: *add-addr-attrs + - + name: set-limits + doc: Set protocol limits + attribute-set: attr + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: &mptcp-limits + request: + attributes: + - rcv-add-addrs + - subflows + - + name: get-limits + doc: Get protocol limits + attribute-set: attr + dont-validate: [ strict ] + do: &mptcp-get-limits + request: + attributes: + - rcv-add-addrs + - subflows + reply: + attributes: + - rcv-add-addrs + - subflows + - + name: set-flags + doc: Change endpoint flags + attribute-set: attr + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: &mptcp-set-flags + request: + attributes: + - addr + - token + - addr-remote + - + name: announce + doc: announce new sf + attribute-set: attr + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: &announce-add + request: + attributes: + - addr + - token + - + name: remove + doc: announce removal + attribute-set: attr + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: + request: + attributes: + - token + - loc-id + - + name: subflow-create + doc: todo + attribute-set: attr + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: &sf-create + request: + attributes: + - addr + - token + - addr-remote + - + name: subflow-destroy + doc: todo + attribute-set: attr + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: *sf-create diff --git a/MAINTAINERS b/MAINTAINERS index daf440129535..dda78b4ce707 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15099,7 +15099,7 @@ W: https://github.com/multipath-tcp/mptcp_net-next/wiki B: https://github.com/multipath-tcp/mptcp_net-next/issues T: git https://github.com/multipath-tcp/mptcp_net-next.git export-net T: git https://github.com/multipath-tcp/mptcp_net-next.git export -F: Documentation/netlink/specs/mptcp.yaml +F: Documentation/netlink/specs/mptcp_pm.yaml F: Documentation/networking/mptcp-sysctl.rst F: include/net/mptcp.h F: include/trace/events/mptcp.h diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h index b5d11aece408..50589e5dd6a3 100644 --- a/include/uapi/linux/mptcp_pm.h +++ b/include/uapi/linux/mptcp_pm.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* Do not edit directly, auto-generated from: */ -/* Documentation/netlink/specs/mptcp.yaml */ +/* Documentation/netlink/specs/mptcp_pm.yaml */ /* YNL-GEN uapi header */ #ifndef _UAPI_LINUX_MPTCP_PM_H diff --git a/net/mptcp/mptcp_pm_gen.c b/net/mptcp/mptcp_pm_gen.c index a2325e70ddab..670da7822e6c 100644 --- a/net/mptcp/mptcp_pm_gen.c +++ b/net/mptcp/mptcp_pm_gen.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* Do not edit directly, auto-generated from: */ -/* Documentation/netlink/specs/mptcp.yaml */ +/* Documentation/netlink/specs/mptcp_pm.yaml */ /* YNL-GEN kernel source */ #include diff --git a/net/mptcp/mptcp_pm_gen.h b/net/mptcp/mptcp_pm_gen.h index 10579d184587..ac9fc7225b6a 100644 --- a/net/mptcp/mptcp_pm_gen.h +++ b/net/mptcp/mptcp_pm_gen.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* Do not edit directly, auto-generated from: */ -/* Documentation/netlink/specs/mptcp.yaml */ +/* Documentation/netlink/specs/mptcp_pm.yaml */ /* YNL-GEN kernel header */ #ifndef _LINUX_MPTCP_PM_GEN_H -- cgit From 61fbf20312bdd1394a9cac67ed8f706e205511af Mon Sep 17 00:00:00 2001 From: Dmitry Antipov Date: Thu, 14 Dec 2023 12:04:15 +0300 Subject: usb: gadget: f_fs: fix fortify warning When compiling with gcc version 14.0.0 20231206 (experimental) and CONFIG_FORTIFY_SOURCE=y, I've noticed the following warning: ... In function 'fortify_memcpy_chk', inlined from '__ffs_func_bind_do_os_desc' at drivers/usb/gadget/function/f_fs.c:2934:3: ./include/linux/fortify-string.h:588:25: warning: call to '__read_overflow2_field' declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Wattribute-warning] 588 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ This call to 'memcpy()' is interpreted as an attempt to copy both 'CompatibleID' and 'SubCompatibleID' of 'struct usb_ext_compat_desc' from an address of the first one, which causes an overread warning. Since we actually want to copy both of them at once, use the convenient 'struct_group()' and 'sizeof_field()' here. Signed-off-by: Dmitry Antipov Link: https://lore.kernel.org/r/20231214090428.27292-1-dmantipov@yandex.ru Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_fs.c | 5 ++--- include/uapi/linux/usb/functionfs.h | 6 ++++-- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index efe3e3b85769..dafedc33928d 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -2931,9 +2931,8 @@ static int __ffs_func_bind_do_os_desc(enum ffs_os_desc_type type, t = &func->function.os_desc_table[desc->bFirstInterfaceNumber]; t->if_id = func->interfaces_nums[desc->bFirstInterfaceNumber]; - memcpy(t->os_desc->ext_compat_id, &desc->CompatibleID, - ARRAY_SIZE(desc->CompatibleID) + - ARRAY_SIZE(desc->SubCompatibleID)); + memcpy(t->os_desc->ext_compat_id, &desc->IDs, + sizeof_field(struct usb_ext_compat_desc, IDs)); length = sizeof(*desc); } break; diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h index d77ee6b65328..078098e73fd3 100644 --- a/include/uapi/linux/usb/functionfs.h +++ b/include/uapi/linux/usb/functionfs.h @@ -73,8 +73,10 @@ struct usb_os_desc_header { struct usb_ext_compat_desc { __u8 bFirstInterfaceNumber; __u8 Reserved1; - __u8 CompatibleID[8]; - __u8 SubCompatibleID[8]; + __struct_group(/* no tag */, IDs, /* no attrs */, + __u8 CompatibleID[8]; + __u8 SubCompatibleID[8]; + ); __u8 Reserved2[6]; }; -- cgit From a7565fc8399725d00cc006c35d0621a5cb5f9554 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 13 Dec 2023 14:40:14 -0800 Subject: mei: fix spellos in mei.h For include/uapi/linux/mei.h, correct spellos reported by codespell. Signed-off-by: Randy Dunlap Cc: Tomas Winkler Cc: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20231213224014.23187-1-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/mei.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mei.h b/include/uapi/linux/mei.h index 171c5cce3641..68a0272e99b7 100644 --- a/include/uapi/linux/mei.h +++ b/include/uapi/linux/mei.h @@ -100,14 +100,14 @@ struct mei_connect_client_data_vtag { * a FW client on a tagged channel. From this point on, every read * and write will communicate with the associated FW client * on the tagged channel. - * Upone close() the communication is terminated. + * Upon close() the communication is terminated. * * The IOCTL argument is a struct with a union that contains * the input parameter and the output parameter for this IOCTL. * * The input parameter is UUID of the FW Client, a vtag [0,255]. * The output parameter is the properties of the FW client - * (FW protocool version and max message size). + * (FW protocol version and max message size). * * Clients that do not support tagged connection * will respond with -EOPNOTSUPP. -- cgit From 3634783be125381c6d390938d08cbcc47fed3b73 Mon Sep 17 00:00:00 2001 From: Alice Ryhl Date: Fri, 8 Dec 2023 15:28:01 +0000 Subject: binder: use enum for binder ioctls All of the other constants in this file are defined using enums, so make the constants more consistent by defining the ioctls in an enum as well. This is necessary for Rust Binder since the _IO macros are too complicated for bindgen to see that they expand to integer constants. Replacing the #defines with an enum forces bindgen to evaluate them properly, which allows us to access them from Rust. I originally intended to include this change in the first patch of the Rust Binder patchset [1], but at plumbers Carlos Llamas told me that this change has been discussed previously [2] and suggested that I send it upstream separately. Link: https://lore.kernel.org/rust-for-linux/20231101-rust-binder-v1-1-08ba9197f637@google.com/ [1] Link: https://lore.kernel.org/all/YoIK2l6xbQMPGZHy@kroah.com/ [2] Signed-off-by: Alice Ryhl Acked-by: Carlos Llamas Link: https://lore.kernel.org/r/20231208152801.3425772-1-aliceryhl@google.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/android/binder.h | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 5f636b5afcd7..d44a8118b2ed 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -251,20 +251,22 @@ struct binder_extended_error { __s32 param; }; -#define BINDER_WRITE_READ _IOWR('b', 1, struct binder_write_read) -#define BINDER_SET_IDLE_TIMEOUT _IOW('b', 3, __s64) -#define BINDER_SET_MAX_THREADS _IOW('b', 5, __u32) -#define BINDER_SET_IDLE_PRIORITY _IOW('b', 6, __s32) -#define BINDER_SET_CONTEXT_MGR _IOW('b', 7, __s32) -#define BINDER_THREAD_EXIT _IOW('b', 8, __s32) -#define BINDER_VERSION _IOWR('b', 9, struct binder_version) -#define BINDER_GET_NODE_DEBUG_INFO _IOWR('b', 11, struct binder_node_debug_info) -#define BINDER_GET_NODE_INFO_FOR_REF _IOWR('b', 12, struct binder_node_info_for_ref) -#define BINDER_SET_CONTEXT_MGR_EXT _IOW('b', 13, struct flat_binder_object) -#define BINDER_FREEZE _IOW('b', 14, struct binder_freeze_info) -#define BINDER_GET_FROZEN_INFO _IOWR('b', 15, struct binder_frozen_status_info) -#define BINDER_ENABLE_ONEWAY_SPAM_DETECTION _IOW('b', 16, __u32) -#define BINDER_GET_EXTENDED_ERROR _IOWR('b', 17, struct binder_extended_error) +enum { + BINDER_WRITE_READ = _IOWR('b', 1, struct binder_write_read), + BINDER_SET_IDLE_TIMEOUT = _IOW('b', 3, __s64), + BINDER_SET_MAX_THREADS = _IOW('b', 5, __u32), + BINDER_SET_IDLE_PRIORITY = _IOW('b', 6, __s32), + BINDER_SET_CONTEXT_MGR = _IOW('b', 7, __s32), + BINDER_THREAD_EXIT = _IOW('b', 8, __s32), + BINDER_VERSION = _IOWR('b', 9, struct binder_version), + BINDER_GET_NODE_DEBUG_INFO = _IOWR('b', 11, struct binder_node_debug_info), + BINDER_GET_NODE_INFO_FOR_REF = _IOWR('b', 12, struct binder_node_info_for_ref), + BINDER_SET_CONTEXT_MGR_EXT = _IOW('b', 13, struct flat_binder_object), + BINDER_FREEZE = _IOW('b', 14, struct binder_freeze_info), + BINDER_GET_FROZEN_INFO = _IOWR('b', 15, struct binder_frozen_status_info), + BINDER_ENABLE_ONEWAY_SPAM_DETECTION = _IOW('b', 16, __u32), + BINDER_GET_EXTENDED_ERROR = _IOWR('b', 17, struct binder_extended_error), +}; /* * NOTE: Two special error codes you should check for when calling -- cgit From acd288666979a49538d70e0c0d86e1118b445058 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 22 Nov 2023 15:03:55 +0900 Subject: misc: pci_endpoint_test: Use INTX instead of LEGACY In the root complex pci endpoint test function driver, change macros and functions names using the term "legacy" to use "intx" instead to match the term used in the PCI specifications. Link: https://lore.kernel.org/r/20231122060406.14695-6-dlemoal@kernel.org Signed-off-by: Damien Le Moal Signed-off-by: Lorenzo Pieralisi Reviewed-by: Christoph Hellwig --- drivers/misc/pci_endpoint_test.c | 30 +++++++++++++++--------------- include/uapi/linux/pcitest.h | 3 ++- 2 files changed, 17 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c index af519088732d..2d7822d9dfe9 100644 --- a/drivers/misc/pci_endpoint_test.c +++ b/drivers/misc/pci_endpoint_test.c @@ -28,14 +28,14 @@ #define DRV_MODULE_NAME "pci-endpoint-test" #define IRQ_TYPE_UNDEFINED -1 -#define IRQ_TYPE_LEGACY 0 +#define IRQ_TYPE_INTX 0 #define IRQ_TYPE_MSI 1 #define IRQ_TYPE_MSIX 2 #define PCI_ENDPOINT_TEST_MAGIC 0x0 #define PCI_ENDPOINT_TEST_COMMAND 0x4 -#define COMMAND_RAISE_LEGACY_IRQ BIT(0) +#define COMMAND_RAISE_INTX_IRQ BIT(0) #define COMMAND_RAISE_MSI_IRQ BIT(1) #define COMMAND_RAISE_MSIX_IRQ BIT(2) #define COMMAND_READ BIT(3) @@ -183,8 +183,8 @@ static bool pci_endpoint_test_alloc_irq_vectors(struct pci_endpoint_test *test, bool res = true; switch (type) { - case IRQ_TYPE_LEGACY: - irq = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_LEGACY); + case IRQ_TYPE_INTX: + irq = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_INTX); if (irq < 0) dev_err(dev, "Failed to get Legacy interrupt\n"); break; @@ -244,7 +244,7 @@ static bool pci_endpoint_test_request_irq(struct pci_endpoint_test *test) fail: switch (irq_type) { - case IRQ_TYPE_LEGACY: + case IRQ_TYPE_INTX: dev_err(dev, "Failed to request IRQ %d for Legacy\n", pci_irq_vector(pdev, i)); break; @@ -291,15 +291,15 @@ static bool pci_endpoint_test_bar(struct pci_endpoint_test *test, return true; } -static bool pci_endpoint_test_legacy_irq(struct pci_endpoint_test *test) +static bool pci_endpoint_test_intx_irq(struct pci_endpoint_test *test) { u32 val; pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE, - IRQ_TYPE_LEGACY); + IRQ_TYPE_INTX); pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 0); pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND, - COMMAND_RAISE_LEGACY_IRQ); + COMMAND_RAISE_INTX_IRQ); val = wait_for_completion_timeout(&test->irq_raised, msecs_to_jiffies(1000)); if (!val) @@ -385,7 +385,7 @@ static bool pci_endpoint_test_copy(struct pci_endpoint_test *test, if (use_dma) flags |= FLAG_USE_DMA; - if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) { + if (irq_type < IRQ_TYPE_INTX || irq_type > IRQ_TYPE_MSIX) { dev_err(dev, "Invalid IRQ type option\n"); goto err; } @@ -521,7 +521,7 @@ static bool pci_endpoint_test_write(struct pci_endpoint_test *test, if (use_dma) flags |= FLAG_USE_DMA; - if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) { + if (irq_type < IRQ_TYPE_INTX || irq_type > IRQ_TYPE_MSIX) { dev_err(dev, "Invalid IRQ type option\n"); goto err; } @@ -621,7 +621,7 @@ static bool pci_endpoint_test_read(struct pci_endpoint_test *test, if (use_dma) flags |= FLAG_USE_DMA; - if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) { + if (irq_type < IRQ_TYPE_INTX || irq_type > IRQ_TYPE_MSIX) { dev_err(dev, "Invalid IRQ type option\n"); goto err; } @@ -691,7 +691,7 @@ static bool pci_endpoint_test_set_irq(struct pci_endpoint_test *test, struct pci_dev *pdev = test->pdev; struct device *dev = &pdev->dev; - if (req_irq_type < IRQ_TYPE_LEGACY || req_irq_type > IRQ_TYPE_MSIX) { + if (req_irq_type < IRQ_TYPE_INTX || req_irq_type > IRQ_TYPE_MSIX) { dev_err(dev, "Invalid IRQ type option\n"); return false; } @@ -737,8 +737,8 @@ static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd, goto ret; ret = pci_endpoint_test_bar(test, bar); break; - case PCITEST_LEGACY_IRQ: - ret = pci_endpoint_test_legacy_irq(test); + case PCITEST_INTX_IRQ: + ret = pci_endpoint_test_intx_irq(test); break; case PCITEST_MSI: case PCITEST_MSIX: @@ -801,7 +801,7 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev, test->irq_type = IRQ_TYPE_UNDEFINED; if (no_msi) - irq_type = IRQ_TYPE_LEGACY; + irq_type = IRQ_TYPE_INTX; data = (struct pci_endpoint_test_data *)ent->driver_data; if (data) { diff --git a/include/uapi/linux/pcitest.h b/include/uapi/linux/pcitest.h index f9c1af8d141b..94b46b043b53 100644 --- a/include/uapi/linux/pcitest.h +++ b/include/uapi/linux/pcitest.h @@ -11,7 +11,8 @@ #define __UAPI_LINUX_PCITEST_H #define PCITEST_BAR _IO('P', 0x1) -#define PCITEST_LEGACY_IRQ _IO('P', 0x2) +#define PCITEST_INTX_IRQ _IO('P', 0x2) +#define PCITEST_LEGACY_IRQ PCITEST_INTX_IRQ #define PCITEST_MSI _IOW('P', 0x3, int) #define PCITEST_WRITE _IOW('P', 0x4, unsigned long) #define PCITEST_READ _IOW('P', 0x5, unsigned long) -- cgit From 13b127d2578432e1e521310b69944c5a1b30679c Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sat, 16 Dec 2023 13:30:00 +0100 Subject: devlink: add a command to set notification filter and use it for multicasts Currently the user listening on a socket for devlink notifications gets always all messages for all existing instances, even if he is interested only in one of those. That may cause unnecessary overhead on setups with thousands of instances present. User is currently able to narrow down the devlink objects replies to dump commands by specifying select attributes. Allow similar approach for notifications. Introduce a new devlink NOTIFY_FILTER_SET which the user passes the select attributes. Store these per-socket and use them for filtering messages during multicast send. Signed-off-by: Jiri Pirko Signed-off-by: Paolo Abeni --- Documentation/netlink/specs/devlink.yaml | 10 +++ include/uapi/linux/devlink.h | 2 + net/devlink/devl_internal.h | 34 +++++++++- net/devlink/netlink.c | 108 +++++++++++++++++++++++++++++++ net/devlink/netlink_gen.c | 15 ++++- net/devlink/netlink_gen.h | 4 +- 6 files changed, 169 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml index c3a438197964..88bfcb3c3346 100644 --- a/Documentation/netlink/specs/devlink.yaml +++ b/Documentation/netlink/specs/devlink.yaml @@ -2254,3 +2254,13 @@ operations: - bus-name - dev-name - selftests + + - + name: notify-filter-set + doc: Set notification messages socket filter. + attribute-set: devlink + do: + request: + attributes: + - bus-name + - dev-name diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index b3c8383d342d..130cae0d3e20 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -139,6 +139,8 @@ enum devlink_command { DEVLINK_CMD_SELFTESTS_GET, /* can dump */ DEVLINK_CMD_SELFTESTS_RUN, + DEVLINK_CMD_NOTIFY_FILTER_SET, + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h index 84dc9628d3f2..82e0fb3bbebf 100644 --- a/net/devlink/devl_internal.h +++ b/net/devlink/devl_internal.h @@ -191,11 +191,41 @@ static inline bool devlink_nl_notify_need(struct devlink *devlink) DEVLINK_MCGRP_CONFIG); } +struct devlink_obj_desc { + struct rcu_head rcu; + const char *bus_name; + const char *dev_name; + long data[]; +}; + +static inline void devlink_nl_obj_desc_init(struct devlink_obj_desc *desc, + struct devlink *devlink) +{ + memset(desc, 0, sizeof(*desc)); + desc->bus_name = devlink->dev->bus->name; + desc->dev_name = dev_name(devlink->dev); +} + +int devlink_nl_notify_filter(struct sock *dsk, struct sk_buff *skb, void *data); + +static inline void devlink_nl_notify_send_desc(struct devlink *devlink, + struct sk_buff *msg, + struct devlink_obj_desc *desc) +{ + genlmsg_multicast_netns_filtered(&devlink_nl_family, + devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, + GFP_KERNEL, + devlink_nl_notify_filter, desc); +} + static inline void devlink_nl_notify_send(struct devlink *devlink, struct sk_buff *msg) { - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); + struct devlink_obj_desc desc; + + devlink_nl_obj_desc_init(&desc, devlink); + devlink_nl_notify_send_desc(devlink, msg, &desc); } /* Notify */ diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c index fa9afe3e6d9b..3176be2585cb 100644 --- a/net/devlink/netlink.c +++ b/net/devlink/netlink.c @@ -17,6 +17,111 @@ static const struct genl_multicast_group devlink_nl_mcgrps[] = { [DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME }, }; +struct devlink_nl_sock_priv { + struct devlink_obj_desc __rcu *flt; + spinlock_t flt_lock; /* Protects flt. */ +}; + +static void devlink_nl_sock_priv_init(void *priv) +{ + struct devlink_nl_sock_priv *sk_priv = priv; + + spin_lock_init(&sk_priv->flt_lock); +} + +static void devlink_nl_sock_priv_destroy(void *priv) +{ + struct devlink_nl_sock_priv *sk_priv = priv; + struct devlink_obj_desc *flt; + + flt = rcu_dereference_protected(sk_priv->flt, true); + kfree_rcu(flt, rcu); +} + +int devlink_nl_notify_filter_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_nl_sock_priv *sk_priv; + struct nlattr **attrs = info->attrs; + struct devlink_obj_desc *flt; + size_t data_offset = 0; + size_t data_size = 0; + char *pos; + + if (attrs[DEVLINK_ATTR_BUS_NAME]) + data_size = size_add(data_size, + nla_len(attrs[DEVLINK_ATTR_BUS_NAME]) + 1); + if (attrs[DEVLINK_ATTR_DEV_NAME]) + data_size = size_add(data_size, + nla_len(attrs[DEVLINK_ATTR_DEV_NAME]) + 1); + + flt = kzalloc(size_add(sizeof(*flt), data_size), GFP_KERNEL); + if (!flt) + return -ENOMEM; + + pos = (char *) flt->data; + if (attrs[DEVLINK_ATTR_BUS_NAME]) { + data_offset += nla_strscpy(pos, + attrs[DEVLINK_ATTR_BUS_NAME], + data_size) + 1; + flt->bus_name = pos; + pos += data_offset; + } + if (attrs[DEVLINK_ATTR_DEV_NAME]) { + nla_strscpy(pos, attrs[DEVLINK_ATTR_DEV_NAME], + data_size - data_offset); + flt->dev_name = pos; + } + + /* Don't attach empty filter. */ + if (!flt->bus_name && !flt->dev_name) { + kfree(flt); + flt = NULL; + } + + sk_priv = genl_sk_priv_get(&devlink_nl_family, NETLINK_CB(skb).sk); + if (IS_ERR(sk_priv)) { + kfree(flt); + return PTR_ERR(sk_priv); + } + spin_lock(&sk_priv->flt_lock); + flt = rcu_replace_pointer(sk_priv->flt, flt, + lockdep_is_held(&sk_priv->flt_lock)); + spin_unlock(&sk_priv->flt_lock); + kfree_rcu(flt, rcu); + return 0; +} + +static bool devlink_obj_desc_match(const struct devlink_obj_desc *desc, + const struct devlink_obj_desc *flt) +{ + if (desc->bus_name && flt->bus_name && + strcmp(desc->bus_name, flt->bus_name)) + return false; + if (desc->dev_name && flt->dev_name && + strcmp(desc->dev_name, flt->dev_name)) + return false; + return true; +} + +int devlink_nl_notify_filter(struct sock *dsk, struct sk_buff *skb, void *data) +{ + struct devlink_obj_desc *desc = data; + struct devlink_nl_sock_priv *sk_priv; + struct devlink_obj_desc *flt; + int ret = 0; + + rcu_read_lock(); + sk_priv = __genl_sk_priv_get(&devlink_nl_family, dsk); + if (!IS_ERR_OR_NULL(sk_priv)) { + flt = rcu_dereference(sk_priv->flt); + if (flt) + ret = !devlink_obj_desc_match(desc, flt); + } + rcu_read_unlock(); + return ret; +} + int devlink_nl_put_nested_handle(struct sk_buff *msg, struct net *net, struct devlink *devlink, int attrtype) { @@ -256,4 +361,7 @@ struct genl_family devlink_nl_family __ro_after_init = { .resv_start_op = DEVLINK_CMD_SELFTESTS_RUN + 1, .mcgrps = devlink_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(devlink_nl_mcgrps), + .sock_priv_size = sizeof(struct devlink_nl_sock_priv), + .sock_priv_init = devlink_nl_sock_priv_init, + .sock_priv_destroy = devlink_nl_sock_priv_destroy, }; diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c index 95f9b4350ab7..1cb0e05305d2 100644 --- a/net/devlink/netlink_gen.c +++ b/net/devlink/netlink_gen.c @@ -560,8 +560,14 @@ static const struct nla_policy devlink_selftests_run_nl_policy[DEVLINK_ATTR_SELF [DEVLINK_ATTR_SELFTESTS] = NLA_POLICY_NESTED(devlink_dl_selftest_id_nl_policy), }; +/* DEVLINK_CMD_NOTIFY_FILTER_SET - do */ +static const struct nla_policy devlink_notify_filter_set_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + /* Ops table for devlink */ -const struct genl_split_ops devlink_nl_ops[73] = { +const struct genl_split_ops devlink_nl_ops[74] = { { .cmd = DEVLINK_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT, @@ -1233,4 +1239,11 @@ const struct genl_split_ops devlink_nl_ops[73] = { .maxattr = DEVLINK_ATTR_SELFTESTS, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, + { + .cmd = DEVLINK_CMD_NOTIFY_FILTER_SET, + .doit = devlink_nl_notify_filter_set_doit, + .policy = devlink_notify_filter_set_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_CMD_CAP_DO, + }, }; diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h index 02f3c0bfae0e..8f2bd50ddf5e 100644 --- a/net/devlink/netlink_gen.h +++ b/net/devlink/netlink_gen.h @@ -16,7 +16,7 @@ extern const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_F extern const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1]; /* Ops table for devlink */ -extern const struct genl_split_ops devlink_nl_ops[73]; +extern const struct genl_split_ops devlink_nl_ops[74]; int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); @@ -142,5 +142,7 @@ int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_selftests_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int devlink_nl_selftests_run_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_notify_filter_set_doit(struct sk_buff *skb, + struct genl_info *info); #endif /* _LINUX_DEVLINK_GEN_H */ -- cgit From d17aff807f845cf93926c28705216639c7279110 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 19 Dec 2023 07:37:35 -0800 Subject: Revert BPF token-related functionality This patch includes the following revert (one conflicting BPF FS patch and three token patch sets, represented by merge commits): - revert 0f5d5454c723 "Merge branch 'bpf-fs-mount-options-parsing-follow-ups'"; - revert 750e785796bb "bpf: Support uid and gid when mounting bpffs"; - revert 733763285acf "Merge branch 'bpf-token-support-in-libbpf-s-bpf-object'"; - revert c35919dcce28 "Merge branch 'bpf-token-and-bpf-fs-based-delegation'". Link: https://lore.kernel.org/bpf/CAHk-=wg7JuFYwGy=GOMbRCtOL+jwSQsdUaBsRWkDVYbxipbM5A@mail.gmail.com Signed-off-by: Andrii Nakryiko --- drivers/media/rc/bpf-lirc.c | 2 +- include/linux/bpf.h | 85 +- include/linux/filter.h | 2 +- include/linux/lsm_hook_defs.h | 15 +- include/linux/security.h | 43 +- include/uapi/linux/bpf.h | 42 - kernel/bpf/Makefile | 2 +- kernel/bpf/arraymap.c | 2 +- kernel/bpf/bpf_lsm.c | 15 +- kernel/bpf/cgroup.c | 6 +- kernel/bpf/core.c | 3 +- kernel/bpf/helpers.c | 6 +- kernel/bpf/inode.c | 326 +------ kernel/bpf/syscall.c | 215 ++-- kernel/bpf/token.c | 271 ----- kernel/bpf/verifier.c | 13 +- kernel/trace/bpf_trace.c | 2 +- net/core/filter.c | 36 +- net/ipv4/bpf_tcp_ca.c | 2 +- net/netfilter/nf_bpf_link.c | 2 +- security/security.c | 101 +- security/selinux/hooks.c | 47 +- tools/include/uapi/linux/bpf.h | 42 - tools/lib/bpf/Build | 2 +- tools/lib/bpf/bpf.c | 37 +- tools/lib/bpf/bpf.h | 35 +- tools/lib/bpf/btf.c | 7 +- tools/lib/bpf/elf.c | 2 + tools/lib/bpf/features.c | 478 --------- tools/lib/bpf/libbpf.c | 573 ++++++++--- tools/lib/bpf/libbpf.h | 37 +- tools/lib/bpf/libbpf.map | 1 - tools/lib/bpf/libbpf_internal.h | 36 +- tools/lib/bpf/libbpf_probes.c | 8 +- tools/lib/bpf/str_error.h | 3 - .../selftests/bpf/prog_tests/libbpf_probes.c | 4 - .../testing/selftests/bpf/prog_tests/libbpf_str.c | 6 - tools/testing/selftests/bpf/prog_tests/token.c | 1031 -------------------- tools/testing/selftests/bpf/progs/priv_map.c | 13 - tools/testing/selftests/bpf/progs/priv_prog.c | 13 - 40 files changed, 641 insertions(+), 2925 deletions(-) delete mode 100644 kernel/bpf/token.c delete mode 100644 tools/lib/bpf/features.c delete mode 100644 tools/testing/selftests/bpf/prog_tests/token.c delete mode 100644 tools/testing/selftests/bpf/progs/priv_map.c delete mode 100644 tools/testing/selftests/bpf/progs/priv_prog.c (limited to 'include/uapi/linux') diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index 6d07693c6b9f..fe17c7f98e81 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -110,7 +110,7 @@ lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; case BPF_FUNC_trace_printk: - if (bpf_token_capable(prog->aux->token, CAP_PERFMON)) + if (perfmon_capable()) return bpf_get_trace_printk_proto(); fallthrough; default: diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2f54cc0436c4..7a8d4c81a39a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -52,10 +52,6 @@ struct module; struct bpf_func_state; struct ftrace_ops; struct cgroup; -struct bpf_token; -struct user_namespace; -struct super_block; -struct inode; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -1488,7 +1484,6 @@ struct bpf_prog_aux { #ifdef CONFIG_SECURITY void *security; #endif - struct bpf_token *token; struct bpf_prog_offload *offload; struct btf *btf; struct bpf_func_info *func_info; @@ -1613,31 +1608,6 @@ struct bpf_link_primer { u32 id; }; -struct bpf_mount_opts { - kuid_t uid; - kgid_t gid; - umode_t mode; - - /* BPF token-related delegation options */ - u64 delegate_cmds; - u64 delegate_maps; - u64 delegate_progs; - u64 delegate_attachs; -}; - -struct bpf_token { - struct work_struct work; - atomic64_t refcnt; - struct user_namespace *userns; - u64 allowed_cmds; - u64 allowed_maps; - u64 allowed_progs; - u64 allowed_attachs; -#ifdef CONFIG_SECURITY - void *security; -#endif -}; - struct bpf_struct_ops_value; struct btf_member; @@ -2097,7 +2067,6 @@ static inline void bpf_enable_instrumentation(void) migrate_enable(); } -extern const struct super_operations bpf_super_ops; extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; extern const struct file_operations bpf_iter_fops; @@ -2232,26 +2201,24 @@ static inline void bpf_map_dec_elem_count(struct bpf_map *map) extern int sysctl_unprivileged_bpf_disabled; -bool bpf_token_capable(const struct bpf_token *token, int cap); - -static inline bool bpf_allow_ptr_leaks(const struct bpf_token *token) +static inline bool bpf_allow_ptr_leaks(void) { - return bpf_token_capable(token, CAP_PERFMON); + return perfmon_capable(); } -static inline bool bpf_allow_uninit_stack(const struct bpf_token *token) +static inline bool bpf_allow_uninit_stack(void) { - return bpf_token_capable(token, CAP_PERFMON); + return perfmon_capable(); } -static inline bool bpf_bypass_spec_v1(const struct bpf_token *token) +static inline bool bpf_bypass_spec_v1(void) { - return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON); + return cpu_mitigations_off() || perfmon_capable(); } -static inline bool bpf_bypass_spec_v4(const struct bpf_token *token) +static inline bool bpf_bypass_spec_v4(void) { - return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON); + return cpu_mitigations_off() || perfmon_capable(); } int bpf_map_new_fd(struct bpf_map *map, int flags); @@ -2268,21 +2235,8 @@ int bpf_link_new_fd(struct bpf_link *link); struct bpf_link *bpf_link_get_from_fd(u32 ufd); struct bpf_link *bpf_link_get_curr_or_next(u32 *id); -void bpf_token_inc(struct bpf_token *token); -void bpf_token_put(struct bpf_token *token); -int bpf_token_create(union bpf_attr *attr); -struct bpf_token *bpf_token_get_from_fd(u32 ufd); - -bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); -bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type); -bool bpf_token_allow_prog_type(const struct bpf_token *token, - enum bpf_prog_type prog_type, - enum bpf_attach_type attach_type); - int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); -struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir, - umode_t mode); #define BPF_ITER_FUNC_PREFIX "bpf_iter_" #define DEFINE_BPF_ITER_FUNC(target, args...) \ @@ -2526,8 +2480,7 @@ const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type struct bpf_prog *bpf_prog_by_id(u32 id); struct bpf_link *bpf_link_by_id(u32 id); -const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id, - const struct bpf_prog *prog); +const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id); void bpf_task_storage_free(struct task_struct *task); void bpf_cgrp_storage_free(struct cgroup *cgroup); bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); @@ -2646,24 +2599,6 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags) return -EOPNOTSUPP; } -static inline bool bpf_token_capable(const struct bpf_token *token, int cap) -{ - return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN)); -} - -static inline void bpf_token_inc(struct bpf_token *token) -{ -} - -static inline void bpf_token_put(struct bpf_token *token) -{ -} - -static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd) -{ - return ERR_PTR(-EOPNOTSUPP); -} - static inline void __dev_flush(void) { } @@ -2787,7 +2722,7 @@ static inline int btf_struct_access(struct bpf_verifier_log *log, } static inline const struct bpf_func_proto * -bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +bpf_base_func_proto(enum bpf_func_id func_id) { return NULL; } diff --git a/include/linux/filter.h b/include/linux/filter.h index 12d907f17d36..68fb6c8142fe 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1139,7 +1139,7 @@ static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) return false; if (!bpf_jit_harden) return false; - if (bpf_jit_harden == 1 && bpf_token_capable(prog->aux->token, CAP_BPF)) + if (bpf_jit_harden == 1 && bpf_capable()) return false; return true; diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 3fdd00b452ac..ff217a5ce552 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -398,17 +398,10 @@ LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule) LSM_HOOK(int, 0, bpf, int cmd, union bpf_attr *attr, unsigned int size) LSM_HOOK(int, 0, bpf_map, struct bpf_map *map, fmode_t fmode) LSM_HOOK(int, 0, bpf_prog, struct bpf_prog *prog) -LSM_HOOK(int, 0, bpf_map_create, struct bpf_map *map, union bpf_attr *attr, - struct bpf_token *token) -LSM_HOOK(void, LSM_RET_VOID, bpf_map_free, struct bpf_map *map) -LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr, - struct bpf_token *token) -LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog) -LSM_HOOK(int, 0, bpf_token_create, struct bpf_token *token, union bpf_attr *attr, - struct path *path) -LSM_HOOK(void, LSM_RET_VOID, bpf_token_free, struct bpf_token *token) -LSM_HOOK(int, 0, bpf_token_cmd, const struct bpf_token *token, enum bpf_cmd cmd) -LSM_HOOK(int, 0, bpf_token_capable, const struct bpf_token *token, int cap) +LSM_HOOK(int, 0, bpf_map_alloc_security, struct bpf_map *map) +LSM_HOOK(void, LSM_RET_VOID, bpf_map_free_security, struct bpf_map *map) +LSM_HOOK(int, 0, bpf_prog_alloc_security, struct bpf_prog_aux *aux) +LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free_security, struct bpf_prog_aux *aux) #endif /* CONFIG_BPF_SYSCALL */ LSM_HOOK(int, 0, locked_down, enum lockdown_reason what) diff --git a/include/linux/security.h b/include/linux/security.h index 00809d2d5c38..1d1df326c881 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -32,7 +32,6 @@ #include #include #include -#include struct linux_binprm; struct cred; @@ -2021,22 +2020,15 @@ static inline void securityfs_remove(struct dentry *dentry) union bpf_attr; struct bpf_map; struct bpf_prog; -struct bpf_token; +struct bpf_prog_aux; #ifdef CONFIG_SECURITY extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size); extern int security_bpf_map(struct bpf_map *map, fmode_t fmode); extern int security_bpf_prog(struct bpf_prog *prog); -extern int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, - struct bpf_token *token); +extern int security_bpf_map_alloc(struct bpf_map *map); extern void security_bpf_map_free(struct bpf_map *map); -extern int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, - struct bpf_token *token); -extern void security_bpf_prog_free(struct bpf_prog *prog); -extern int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, - struct path *path); -extern void security_bpf_token_free(struct bpf_token *token); -extern int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd); -extern int security_bpf_token_capable(const struct bpf_token *token, int cap); +extern int security_bpf_prog_alloc(struct bpf_prog_aux *aux); +extern void security_bpf_prog_free(struct bpf_prog_aux *aux); #else static inline int security_bpf(int cmd, union bpf_attr *attr, unsigned int size) @@ -2054,8 +2046,7 @@ static inline int security_bpf_prog(struct bpf_prog *prog) return 0; } -static inline int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, - struct bpf_token *token) +static inline int security_bpf_map_alloc(struct bpf_map *map) { return 0; } @@ -2063,33 +2054,13 @@ static inline int security_bpf_map_create(struct bpf_map *map, union bpf_attr *a static inline void security_bpf_map_free(struct bpf_map *map) { } -static inline int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, - struct bpf_token *token) +static inline int security_bpf_prog_alloc(struct bpf_prog_aux *aux) { return 0; } -static inline void security_bpf_prog_free(struct bpf_prog *prog) +static inline void security_bpf_prog_free(struct bpf_prog_aux *aux) { } - -static inline int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, - struct path *path) -{ - return 0; -} - -static inline void security_bpf_token_free(struct bpf_token *token) -{ } - -static inline int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd) -{ - return 0; -} - -static inline int security_bpf_token_capable(const struct bpf_token *token, int cap) -{ - return 0; -} #endif /* CONFIG_SECURITY */ #endif /* CONFIG_BPF_SYSCALL */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 42f4d3090efe..754e68ca8744 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -847,36 +847,6 @@ union bpf_iter_link_info { * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. * - * BPF_TOKEN_CREATE - * Description - * Create BPF token with embedded information about what - * BPF-related functionality it allows: - * - a set of allowed bpf() syscall commands; - * - a set of allowed BPF map types to be created with - * BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed; - * - a set of allowed BPF program types and BPF program attach - * types to be loaded with BPF_PROG_LOAD command, if - * BPF_PROG_LOAD itself is allowed. - * - * BPF token is created (derived) from an instance of BPF FS, - * assuming it has necessary delegation mount options specified. - * This BPF token can be passed as an extra parameter to various - * bpf() syscall commands to grant BPF subsystem functionality to - * unprivileged processes. - * - * When created, BPF token is "associated" with the owning - * user namespace of BPF FS instance (super block) that it was - * derived from, and subsequent BPF operations performed with - * BPF token would be performing capabilities checks (i.e., - * CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within - * that user namespace. Without BPF token, such capabilities - * have to be granted in init user namespace, making bpf() - * syscall incompatible with user namespace, for the most part. - * - * Return - * A new file descriptor (a nonnegative integer), or -1 if an - * error occurred (in which case, *errno* is set appropriately). - * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -931,8 +901,6 @@ enum bpf_cmd { BPF_ITER_CREATE, BPF_LINK_DETACH, BPF_PROG_BIND_MAP, - BPF_TOKEN_CREATE, - __MAX_BPF_CMD, }; enum bpf_map_type { @@ -983,7 +951,6 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, - __MAX_BPF_MAP_TYPE }; /* Note that tracing related programs such as @@ -1028,7 +995,6 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ BPF_PROG_TYPE_NETFILTER, - __MAX_BPF_PROG_TYPE }; enum bpf_attach_type { @@ -1437,7 +1403,6 @@ union bpf_attr { * to using 5 hash functions). */ __u64 map_extra; - __u32 map_token_fd; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -1507,7 +1472,6 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 log_true_size; - __u32 prog_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -1620,7 +1584,6 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 btf_log_true_size; - __u32 btf_token_fd; }; struct { @@ -1751,11 +1714,6 @@ union bpf_attr { __u32 flags; /* extra flags */ } prog_bind_map; - struct { /* struct used by BPF_TOKEN_CREATE command */ - __u32 flags; - __u32 bpffs_fd; - } token_create; - } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 4ce95acfcaa7..f526b7573e97 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -6,7 +6,7 @@ cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse endif CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) -obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o token.o +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 13358675ff2e..0bdbbbeab155 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -82,7 +82,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; int numa_node = bpf_map_attr_numa_node(attr); u32 elem_size, index_mask, max_entries; - bool bypass_spec_v1 = bpf_bypass_spec_v1(NULL); + bool bypass_spec_v1 = bpf_bypass_spec_v1(); u64 array_size, mask64; struct bpf_array *array; diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 63b4dc495125..e8e910395bf6 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -260,15 +260,9 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) BTF_SET_START(sleepable_lsm_hooks) BTF_ID(func, bpf_lsm_bpf) BTF_ID(func, bpf_lsm_bpf_map) -BTF_ID(func, bpf_lsm_bpf_map_create) -BTF_ID(func, bpf_lsm_bpf_map_free) +BTF_ID(func, bpf_lsm_bpf_map_alloc_security) +BTF_ID(func, bpf_lsm_bpf_map_free_security) BTF_ID(func, bpf_lsm_bpf_prog) -BTF_ID(func, bpf_lsm_bpf_prog_load) -BTF_ID(func, bpf_lsm_bpf_prog_free) -BTF_ID(func, bpf_lsm_bpf_token_create) -BTF_ID(func, bpf_lsm_bpf_token_free) -BTF_ID(func, bpf_lsm_bpf_token_cmd) -BTF_ID(func, bpf_lsm_bpf_token_capable) BTF_ID(func, bpf_lsm_bprm_check_security) BTF_ID(func, bpf_lsm_bprm_committed_creds) BTF_ID(func, bpf_lsm_bprm_committing_creds) @@ -363,8 +357,9 @@ BTF_ID(func, bpf_lsm_userns_create) BTF_SET_END(sleepable_lsm_hooks) BTF_SET_START(untrusted_lsm_hooks) -BTF_ID(func, bpf_lsm_bpf_map_free) -BTF_ID(func, bpf_lsm_bpf_prog_free) +BTF_ID(func, bpf_lsm_bpf_map_free_security) +BTF_ID(func, bpf_lsm_bpf_prog_alloc_security) +BTF_ID(func, bpf_lsm_bpf_prog_free_security) BTF_ID(func, bpf_lsm_file_alloc_security) BTF_ID(func, bpf_lsm_file_free_security) #ifdef CONFIG_SECURITY_NETWORK diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 98e0e3835b28..491d20038cbe 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1630,7 +1630,7 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id, prog); + return bpf_base_func_proto(func_id); } } @@ -2191,7 +2191,7 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id, prog); + return bpf_base_func_proto(func_id); } } @@ -2348,7 +2348,7 @@ cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id, prog); + return bpf_base_func_proto(func_id); } } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 14ace23d517b..ea6843be2616 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -682,7 +682,7 @@ static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp) void bpf_prog_kallsyms_add(struct bpf_prog *fp) { if (!bpf_prog_kallsyms_candidate(fp) || - !bpf_token_capable(fp->aux->token, CAP_BPF)) + !bpf_capable()) return; bpf_prog_ksym_set_addr(fp); @@ -2779,7 +2779,6 @@ void bpf_prog_free(struct bpf_prog *fp) if (aux->dst_prog) bpf_prog_put(aux->dst_prog); - bpf_token_put(aux->token); INIT_WORK(&aux->work, bpf_prog_free_deferred); schedule_work(&aux->work); } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 07fd4b5704f3..be72824f32b2 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1679,7 +1679,7 @@ const struct bpf_func_proto bpf_probe_read_kernel_str_proto __weak; const struct bpf_func_proto bpf_task_pt_regs_proto __weak; const struct bpf_func_proto * -bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +bpf_base_func_proto(enum bpf_func_id func_id) { switch (func_id) { case BPF_FUNC_map_lookup_elem: @@ -1730,7 +1730,7 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) break; } - if (!bpf_token_capable(prog->aux->token, CAP_BPF)) + if (!bpf_capable()) return NULL; switch (func_id) { @@ -1788,7 +1788,7 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) break; } - if (!bpf_token_capable(prog->aux->token, CAP_PERFMON)) + if (!perfmon_capable()) return NULL; switch (func_id) { diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 4383b3d13a55..1aafb2ff2e95 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -20,7 +20,6 @@ #include #include #include -#include #include "preload/bpf_preload.h" enum bpf_type { @@ -99,9 +98,9 @@ static const struct inode_operations bpf_prog_iops = { }; static const struct inode_operations bpf_map_iops = { }; static const struct inode_operations bpf_link_iops = { }; -struct inode *bpf_get_inode(struct super_block *sb, - const struct inode *dir, - umode_t mode) +static struct inode *bpf_get_inode(struct super_block *sb, + const struct inode *dir, + umode_t mode) { struct inode *inode; @@ -595,183 +594,15 @@ struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type typ } EXPORT_SYMBOL(bpf_prog_get_type_path); -struct bpffs_btf_enums { - const struct btf *btf; - const struct btf_type *cmd_t; - const struct btf_type *map_t; - const struct btf_type *prog_t; - const struct btf_type *attach_t; -}; - -static int find_bpffs_btf_enums(struct bpffs_btf_enums *info) -{ - const struct btf *btf; - const struct btf_type *t; - const char *name; - int i, n; - - memset(info, 0, sizeof(*info)); - - btf = bpf_get_btf_vmlinux(); - if (IS_ERR(btf)) - return PTR_ERR(btf); - if (!btf) - return -ENOENT; - - info->btf = btf; - - for (i = 1, n = btf_nr_types(btf); i < n; i++) { - t = btf_type_by_id(btf, i); - if (!btf_type_is_enum(t)) - continue; - - name = btf_name_by_offset(btf, t->name_off); - if (!name) - continue; - - if (strcmp(name, "bpf_cmd") == 0) - info->cmd_t = t; - else if (strcmp(name, "bpf_map_type") == 0) - info->map_t = t; - else if (strcmp(name, "bpf_prog_type") == 0) - info->prog_t = t; - else if (strcmp(name, "bpf_attach_type") == 0) - info->attach_t = t; - else - continue; - - if (info->cmd_t && info->map_t && info->prog_t && info->attach_t) - return 0; - } - - return -ESRCH; -} - -static bool find_btf_enum_const(const struct btf *btf, const struct btf_type *enum_t, - const char *prefix, const char *str, int *value) -{ - const struct btf_enum *e; - const char *name; - int i, n, pfx_len = strlen(prefix); - - *value = 0; - - if (!btf || !enum_t) - return false; - - for (i = 0, n = btf_vlen(enum_t); i < n; i++) { - e = &btf_enum(enum_t)[i]; - - name = btf_name_by_offset(btf, e->name_off); - if (!name || strncasecmp(name, prefix, pfx_len) != 0) - continue; - - /* match symbolic name case insensitive and ignoring prefix */ - if (strcasecmp(name + pfx_len, str) == 0) { - *value = e->val; - return true; - } - } - - return false; -} - -static void seq_print_delegate_opts(struct seq_file *m, - const char *opt_name, - const struct btf *btf, - const struct btf_type *enum_t, - const char *prefix, - u64 delegate_msk, u64 any_msk) -{ - const struct btf_enum *e; - bool first = true; - const char *name; - u64 msk; - int i, n, pfx_len = strlen(prefix); - - delegate_msk &= any_msk; /* clear unknown bits */ - - if (delegate_msk == 0) - return; - - seq_printf(m, ",%s", opt_name); - if (delegate_msk == any_msk) { - seq_printf(m, "=any"); - return; - } - - if (btf && enum_t) { - for (i = 0, n = btf_vlen(enum_t); i < n; i++) { - e = &btf_enum(enum_t)[i]; - name = btf_name_by_offset(btf, e->name_off); - if (!name || strncasecmp(name, prefix, pfx_len) != 0) - continue; - msk = 1ULL << e->val; - if (delegate_msk & msk) { - /* emit lower-case name without prefix */ - seq_printf(m, "%c", first ? '=' : ':'); - name += pfx_len; - while (*name) { - seq_printf(m, "%c", tolower(*name)); - name++; - } - - delegate_msk &= ~msk; - first = false; - } - } - } - if (delegate_msk) - seq_printf(m, "%c0x%llx", first ? '=' : ':', delegate_msk); -} - /* * Display the mount options in /proc/mounts. */ static int bpf_show_options(struct seq_file *m, struct dentry *root) { - struct bpf_mount_opts *opts = root->d_sb->s_fs_info; - struct inode *inode = d_inode(root); - umode_t mode = inode->i_mode & S_IALLUGO & ~S_ISVTX; - u64 mask; - - if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID)) - seq_printf(m, ",uid=%u", - from_kuid_munged(&init_user_ns, inode->i_uid)); - if (!gid_eq(inode->i_gid, GLOBAL_ROOT_GID)) - seq_printf(m, ",gid=%u", - from_kgid_munged(&init_user_ns, inode->i_gid)); + umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX; + if (mode != S_IRWXUGO) seq_printf(m, ",mode=%o", mode); - - if (opts->delegate_cmds || opts->delegate_maps || - opts->delegate_progs || opts->delegate_attachs) { - struct bpffs_btf_enums info; - - /* ignore errors, fallback to hex */ - (void)find_bpffs_btf_enums(&info); - - mask = (1ULL << __MAX_BPF_CMD) - 1; - seq_print_delegate_opts(m, "delegate_cmds", - info.btf, info.cmd_t, "BPF_", - opts->delegate_cmds, mask); - - mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1; - seq_print_delegate_opts(m, "delegate_maps", - info.btf, info.map_t, "BPF_MAP_TYPE_", - opts->delegate_maps, mask); - - mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; - seq_print_delegate_opts(m, "delegate_progs", - info.btf, info.prog_t, "BPF_PROG_TYPE_", - opts->delegate_progs, mask); - - mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; - seq_print_delegate_opts(m, "delegate_attachs", - info.btf, info.attach_t, "BPF_", - opts->delegate_attachs, mask); - } - return 0; } @@ -786,7 +617,7 @@ static void bpf_free_inode(struct inode *inode) free_inode_nonrcu(inode); } -const struct super_operations bpf_super_ops = { +static const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .show_options = bpf_show_options, @@ -794,33 +625,23 @@ const struct super_operations bpf_super_ops = { }; enum { - OPT_UID, - OPT_GID, OPT_MODE, - OPT_DELEGATE_CMDS, - OPT_DELEGATE_MAPS, - OPT_DELEGATE_PROGS, - OPT_DELEGATE_ATTACHS, }; static const struct fs_parameter_spec bpf_fs_parameters[] = { - fsparam_u32 ("uid", OPT_UID), - fsparam_u32 ("gid", OPT_GID), fsparam_u32oct ("mode", OPT_MODE), - fsparam_string ("delegate_cmds", OPT_DELEGATE_CMDS), - fsparam_string ("delegate_maps", OPT_DELEGATE_MAPS), - fsparam_string ("delegate_progs", OPT_DELEGATE_PROGS), - fsparam_string ("delegate_attachs", OPT_DELEGATE_ATTACHS), {} }; +struct bpf_mount_opts { + umode_t mode; +}; + static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) { - struct bpf_mount_opts *opts = fc->s_fs_info; + struct bpf_mount_opts *opts = fc->fs_private; struct fs_parse_result result; - kuid_t uid; - kgid_t gid; - int opt, err; + int opt; opt = fs_parse(fc, bpf_fs_parameters, param, &result); if (opt < 0) { @@ -841,104 +662,12 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) } switch (opt) { - case OPT_UID: - uid = make_kuid(current_user_ns(), result.uint_32); - if (!uid_valid(uid)) - goto bad_value; - - /* - * The requested uid must be representable in the - * filesystem's idmapping. - */ - if (!kuid_has_mapping(fc->user_ns, uid)) - goto bad_value; - - opts->uid = uid; - break; - case OPT_GID: - gid = make_kgid(current_user_ns(), result.uint_32); - if (!gid_valid(gid)) - goto bad_value; - - /* - * The requested gid must be representable in the - * filesystem's idmapping. - */ - if (!kgid_has_mapping(fc->user_ns, gid)) - goto bad_value; - - opts->gid = gid; - break; case OPT_MODE: opts->mode = result.uint_32 & S_IALLUGO; break; - case OPT_DELEGATE_CMDS: - case OPT_DELEGATE_MAPS: - case OPT_DELEGATE_PROGS: - case OPT_DELEGATE_ATTACHS: { - struct bpffs_btf_enums info; - const struct btf_type *enum_t; - const char *enum_pfx; - u64 *delegate_msk, msk = 0; - char *p; - int val; - - /* ignore errors, fallback to hex */ - (void)find_bpffs_btf_enums(&info); - - switch (opt) { - case OPT_DELEGATE_CMDS: - delegate_msk = &opts->delegate_cmds; - enum_t = info.cmd_t; - enum_pfx = "BPF_"; - break; - case OPT_DELEGATE_MAPS: - delegate_msk = &opts->delegate_maps; - enum_t = info.map_t; - enum_pfx = "BPF_MAP_TYPE_"; - break; - case OPT_DELEGATE_PROGS: - delegate_msk = &opts->delegate_progs; - enum_t = info.prog_t; - enum_pfx = "BPF_PROG_TYPE_"; - break; - case OPT_DELEGATE_ATTACHS: - delegate_msk = &opts->delegate_attachs; - enum_t = info.attach_t; - enum_pfx = "BPF_"; - break; - default: - return -EINVAL; - } - - while ((p = strsep(¶m->string, ":"))) { - if (strcmp(p, "any") == 0) { - msk |= ~0ULL; - } else if (find_btf_enum_const(info.btf, enum_t, enum_pfx, p, &val)) { - msk |= 1ULL << val; - } else { - err = kstrtou64(p, 0, &msk); - if (err) - return err; - } - } - - /* Setting delegation mount options requires privileges */ - if (msk && !capable(CAP_SYS_ADMIN)) - return -EPERM; - - *delegate_msk |= msk; - break; - } - default: - /* ignore unknown mount options */ - break; } return 0; - -bad_value: - return invalfc(fc, "Bad value for '%s'", param->key); } struct bpf_preload_ops *bpf_preload_ops; @@ -1010,14 +739,10 @@ out: static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) { static const struct tree_descr bpf_rfiles[] = { { "" } }; - struct bpf_mount_opts *opts = sb->s_fs_info; + struct bpf_mount_opts *opts = fc->fs_private; struct inode *inode; int ret; - /* Mounting an instance of BPF FS requires privileges */ - if (fc->user_ns != &init_user_ns && !capable(CAP_SYS_ADMIN)) - return -EPERM; - ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles); if (ret) return ret; @@ -1025,8 +750,6 @@ static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_op = &bpf_super_ops; inode = sb->s_root->d_inode; - inode->i_uid = opts->uid; - inode->i_gid = opts->gid; inode->i_op = &bpf_dir_iops; inode->i_mode &= ~S_IALLUGO; populate_bpffs(sb->s_root); @@ -1041,7 +764,7 @@ static int bpf_get_tree(struct fs_context *fc) static void bpf_free_fc(struct fs_context *fc) { - kfree(fc->s_fs_info); + kfree(fc->fs_private); } static const struct fs_context_operations bpf_context_ops = { @@ -1062,35 +785,18 @@ static int bpf_init_fs_context(struct fs_context *fc) return -ENOMEM; opts->mode = S_IRWXUGO; - opts->uid = current_fsuid(); - opts->gid = current_fsgid(); - - /* start out with no BPF token delegation enabled */ - opts->delegate_cmds = 0; - opts->delegate_maps = 0; - opts->delegate_progs = 0; - opts->delegate_attachs = 0; - fc->s_fs_info = opts; + fc->fs_private = opts; fc->ops = &bpf_context_ops; return 0; } -static void bpf_kill_super(struct super_block *sb) -{ - struct bpf_mount_opts *opts = sb->s_fs_info; - - kill_litter_super(sb); - kfree(opts); -} - static struct file_system_type bpf_fs_type = { .owner = THIS_MODULE, .name = "bpf", .init_fs_context = bpf_init_fs_context, .parameters = bpf_fs_parameters, - .kill_sb = bpf_kill_super, - .fs_flags = FS_USERNS_MOUNT, + .kill_sb = kill_litter_super, }; static int __init bpf_init(void) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 8faa1a20edf8..1bf9805ee185 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1011,8 +1011,8 @@ int map_check_no_btf(const struct bpf_map *map, return -ENOTSUPP; } -static int map_check_btf(struct bpf_map *map, struct bpf_token *token, - const struct btf *btf, u32 btf_key_id, u32 btf_value_id) +static int map_check_btf(struct bpf_map *map, const struct btf *btf, + u32 btf_key_id, u32 btf_value_id) { const struct btf_type *key_type, *value_type; u32 key_size, value_size; @@ -1040,7 +1040,7 @@ static int map_check_btf(struct bpf_map *map, struct bpf_token *token, if (!IS_ERR_OR_NULL(map->record)) { int i; - if (!bpf_token_capable(token, CAP_BPF)) { + if (!bpf_capable()) { ret = -EPERM; goto free_map_tab; } @@ -1123,17 +1123,11 @@ free_map_tab: return ret; } -static bool bpf_net_capable(void) -{ - return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN); -} - -#define BPF_MAP_CREATE_LAST_FIELD map_token_fd +#define BPF_MAP_CREATE_LAST_FIELD map_extra /* called via syscall */ static int map_create(union bpf_attr *attr) { const struct bpf_map_ops *ops; - struct bpf_token *token = NULL; int numa_node = bpf_map_attr_numa_node(attr); u32 map_type = attr->map_type; struct bpf_map *map; @@ -1184,32 +1178,14 @@ static int map_create(union bpf_attr *attr) if (!ops->map_mem_usage) return -EINVAL; - if (attr->map_token_fd) { - token = bpf_token_get_from_fd(attr->map_token_fd); - if (IS_ERR(token)) - return PTR_ERR(token); - - /* if current token doesn't grant map creation permissions, - * then we can't use this token, so ignore it and rely on - * system-wide capabilities checks - */ - if (!bpf_token_allow_cmd(token, BPF_MAP_CREATE) || - !bpf_token_allow_map_type(token, attr->map_type)) { - bpf_token_put(token); - token = NULL; - } - } - - err = -EPERM; - /* Intent here is for unprivileged_bpf_disabled to block BPF map * creation for unprivileged users; other actions depend * on fd availability and access to bpffs, so are dependent on * object creation success. Even with unprivileged BPF disabled, * capability checks are still carried out. */ - if (sysctl_unprivileged_bpf_disabled && !bpf_token_capable(token, CAP_BPF)) - goto put_token; + if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) + return -EPERM; /* check privileged map type permissions */ switch (map_type) { @@ -1242,27 +1218,25 @@ static int map_create(union bpf_attr *attr) case BPF_MAP_TYPE_LRU_PERCPU_HASH: case BPF_MAP_TYPE_STRUCT_OPS: case BPF_MAP_TYPE_CPUMAP: - if (!bpf_token_capable(token, CAP_BPF)) - goto put_token; + if (!bpf_capable()) + return -EPERM; break; case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_DEVMAP: case BPF_MAP_TYPE_DEVMAP_HASH: case BPF_MAP_TYPE_XSKMAP: - if (!bpf_token_capable(token, CAP_NET_ADMIN)) - goto put_token; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; break; default: WARN(1, "unsupported map type %d", map_type); - goto put_token; + return -EPERM; } map = ops->map_alloc(attr); - if (IS_ERR(map)) { - err = PTR_ERR(map); - goto put_token; - } + if (IS_ERR(map)) + return PTR_ERR(map); map->ops = ops; map->map_type = map_type; @@ -1299,7 +1273,7 @@ static int map_create(union bpf_attr *attr) map->btf = btf; if (attr->btf_value_type_id) { - err = map_check_btf(map, token, btf, attr->btf_key_type_id, + err = map_check_btf(map, btf, attr->btf_key_type_id, attr->btf_value_type_id); if (err) goto free_map; @@ -1311,16 +1285,15 @@ static int map_create(union bpf_attr *attr) attr->btf_vmlinux_value_type_id; } - err = security_bpf_map_create(map, attr, token); + err = security_bpf_map_alloc(map); if (err) - goto free_map_sec; + goto free_map; err = bpf_map_alloc_id(map); if (err) goto free_map_sec; bpf_map_save_memcg(map); - bpf_token_put(token); err = bpf_map_new_fd(map, f_flags); if (err < 0) { @@ -1341,8 +1314,6 @@ free_map_sec: free_map: btf_put(map->btf); map->ops->map_free(map); -put_token: - bpf_token_put(token); return err; } @@ -2173,7 +2144,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) kvfree(aux->func_info); kfree(aux->func_info_aux); free_uid(aux->user); - security_bpf_prog_free(aux->prog); + security_bpf_prog_free(aux); bpf_prog_free(aux->prog); } @@ -2619,15 +2590,13 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD prog_token_fd +#define BPF_PROG_LOAD_LAST_FIELD log_true_size static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog, *dst_prog = NULL; struct btf *attach_btf = NULL; - struct bpf_token *token = NULL; - bool bpf_cap; int err; char license[128]; @@ -2644,31 +2613,10 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) BPF_F_TEST_REG_INVARIANTS)) return -EINVAL; - bpf_prog_load_fixup_attach_type(attr); - - if (attr->prog_token_fd) { - token = bpf_token_get_from_fd(attr->prog_token_fd); - if (IS_ERR(token)) - return PTR_ERR(token); - /* if current token doesn't grant prog loading permissions, - * then we can't use this token, so ignore it and rely on - * system-wide capabilities checks - */ - if (!bpf_token_allow_cmd(token, BPF_PROG_LOAD) || - !bpf_token_allow_prog_type(token, attr->prog_type, - attr->expected_attach_type)) { - bpf_token_put(token); - token = NULL; - } - } - - bpf_cap = bpf_token_capable(token, CAP_BPF); - err = -EPERM; - if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && - !bpf_cap) - goto put_token; + !bpf_capable()) + return -EPERM; /* Intent here is for unprivileged_bpf_disabled to block BPF program * creation for unprivileged users; other actions depend @@ -2677,23 +2625,21 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) * capability checks are still carried out for these * and other operations. */ - if (sysctl_unprivileged_bpf_disabled && !bpf_cap) - goto put_token; + if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) + return -EPERM; if (attr->insn_cnt == 0 || - attr->insn_cnt > (bpf_cap ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) { - err = -E2BIG; - goto put_token; - } + attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) + return -E2BIG; if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && - !bpf_cap) - goto put_token; + !bpf_capable()) + return -EPERM; - if (is_net_admin_prog_type(type) && !bpf_token_capable(token, CAP_NET_ADMIN)) - goto put_token; - if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON)) - goto put_token; + if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN) && !capable(CAP_SYS_ADMIN)) + return -EPERM; + if (is_perfmon_prog_type(type) && !perfmon_capable()) + return -EPERM; /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog * or btf, we need to check which one it is @@ -2703,33 +2649,27 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (IS_ERR(dst_prog)) { dst_prog = NULL; attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); - if (IS_ERR(attach_btf)) { - err = -EINVAL; - goto put_token; - } + if (IS_ERR(attach_btf)) + return -EINVAL; if (!btf_is_kernel(attach_btf)) { /* attaching through specifying bpf_prog's BTF * objects directly might be supported eventually */ btf_put(attach_btf); - err = -ENOTSUPP; - goto put_token; + return -ENOTSUPP; } } } else if (attr->attach_btf_id) { /* fall back to vmlinux BTF, if BTF type ID is specified */ attach_btf = bpf_get_btf_vmlinux(); - if (IS_ERR(attach_btf)) { - err = PTR_ERR(attach_btf); - goto put_token; - } - if (!attach_btf) { - err = -EINVAL; - goto put_token; - } + if (IS_ERR(attach_btf)) + return PTR_ERR(attach_btf); + if (!attach_btf) + return -EINVAL; btf_get(attach_btf); } + bpf_prog_load_fixup_attach_type(attr); if (bpf_prog_load_check_attach(type, attr->expected_attach_type, attach_btf, attr->attach_btf_id, dst_prog)) { @@ -2737,8 +2677,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - err = -EINVAL; - goto put_token; + return -EINVAL; } /* plain bpf_prog allocation */ @@ -2748,8 +2687,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - err = -EINVAL; - goto put_token; + return -ENOMEM; } prog->expected_attach_type = attr->expected_attach_type; @@ -2760,9 +2698,9 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; - /* move token into prog->aux, reuse taken refcnt */ - prog->aux->token = token; - token = NULL; + err = security_bpf_prog_alloc(prog->aux); + if (err) + goto free_prog; prog->aux->user = get_current_user(); prog->len = attr->insn_cnt; @@ -2771,12 +2709,12 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (copy_from_bpfptr(prog->insns, make_bpfptr(attr->insns, uattr.is_kernel), bpf_prog_insn_size(prog)) != 0) - goto free_prog; + goto free_prog_sec; /* copy eBPF program license from user space */ if (strncpy_from_bpfptr(license, make_bpfptr(attr->license, uattr.is_kernel), sizeof(license) - 1) < 0) - goto free_prog; + goto free_prog_sec; license[sizeof(license) - 1] = 0; /* eBPF programs must be GPL compatible to use GPL-ed functions */ @@ -2790,29 +2728,25 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (bpf_prog_is_dev_bound(prog->aux)) { err = bpf_prog_dev_bound_init(prog, attr); if (err) - goto free_prog; + goto free_prog_sec; } if (type == BPF_PROG_TYPE_EXT && dst_prog && bpf_prog_is_dev_bound(dst_prog->aux)) { err = bpf_prog_dev_bound_inherit(prog, dst_prog); if (err) - goto free_prog; + goto free_prog_sec; } /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) - goto free_prog; + goto free_prog_sec; prog->aux->load_time = ktime_get_boottime_ns(); err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name, sizeof(attr->prog_name)); if (err < 0) - goto free_prog; - - err = security_bpf_prog_load(prog, attr, token); - if (err) goto free_prog_sec; /* run eBPF verifier */ @@ -2858,16 +2792,13 @@ free_used_maps: */ __bpf_prog_put_noref(prog, prog->aux->real_func_cnt); return err; - free_prog_sec: - security_bpf_prog_free(prog); -free_prog: free_uid(prog->aux->user); + security_bpf_prog_free(prog->aux); +free_prog: if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); bpf_prog_free(prog); -put_token: - bpf_token_put(token); return err; } @@ -3857,7 +3788,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, case BPF_PROG_TYPE_SK_LOOKUP: return attach_type == prog->expected_attach_type ? 0 : -EINVAL; case BPF_PROG_TYPE_CGROUP_SKB: - if (!bpf_token_capable(prog->aux->token, CAP_NET_ADMIN)) + if (!capable(CAP_NET_ADMIN)) /* cg-skb progs can be loaded by unpriv user. * check permissions at attach time. */ @@ -4060,7 +3991,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) static int bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { - if (!bpf_net_capable()) + if (!capable(CAP_NET_ADMIN)) return -EPERM; if (CHECK_ATTR(BPF_PROG_QUERY)) return -EINVAL; @@ -4828,31 +4759,15 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, return err; } -#define BPF_BTF_LOAD_LAST_FIELD btf_token_fd +#define BPF_BTF_LOAD_LAST_FIELD btf_log_true_size static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size) { - struct bpf_token *token = NULL; - if (CHECK_ATTR(BPF_BTF_LOAD)) return -EINVAL; - if (attr->btf_token_fd) { - token = bpf_token_get_from_fd(attr->btf_token_fd); - if (IS_ERR(token)) - return PTR_ERR(token); - if (!bpf_token_allow_cmd(token, BPF_BTF_LOAD)) { - bpf_token_put(token); - token = NULL; - } - } - - if (!bpf_token_capable(token, CAP_BPF)) { - bpf_token_put(token); + if (!bpf_capable()) return -EPERM; - } - - bpf_token_put(token); return btf_new_fd(attr, uattr, uattr_size); } @@ -5470,20 +5385,6 @@ out_prog_put: return ret; } -#define BPF_TOKEN_CREATE_LAST_FIELD token_create.bpffs_fd - -static int token_create(union bpf_attr *attr) -{ - if (CHECK_ATTR(BPF_TOKEN_CREATE)) - return -EINVAL; - - /* no flags are supported yet */ - if (attr->token_create.flags) - return -EINVAL; - - return bpf_token_create(attr); -} - static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) { union bpf_attr attr; @@ -5617,9 +5518,6 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) case BPF_PROG_BIND_MAP: err = bpf_prog_bind_map(&attr); break; - case BPF_TOKEN_CREATE: - err = token_create(&attr); - break; default: err = -EINVAL; break; @@ -5726,7 +5624,7 @@ static const struct bpf_func_proto bpf_sys_bpf_proto = { const struct bpf_func_proto * __weak tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { - return bpf_base_func_proto(func_id, prog); + return bpf_base_func_proto(func_id); } BPF_CALL_1(bpf_sys_close, u32, fd) @@ -5776,8 +5674,7 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sys_bpf: - return !bpf_token_capable(prog->aux->token, CAP_PERFMON) - ? NULL : &bpf_sys_bpf_proto; + return !perfmon_capable() ? NULL : &bpf_sys_bpf_proto; case BPF_FUNC_btf_find_by_name_kind: return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c deleted file mode 100644 index a86fccd57e2d..000000000000 --- a/kernel/bpf/token.c +++ /dev/null @@ -1,271 +0,0 @@ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -bool bpf_token_capable(const struct bpf_token *token, int cap) -{ - /* BPF token allows ns_capable() level of capabilities, but only if - * token's userns is *exactly* the same as current user's userns - */ - if (token && current_user_ns() == token->userns) { - if (ns_capable(token->userns, cap) || - (cap != CAP_SYS_ADMIN && ns_capable(token->userns, CAP_SYS_ADMIN))) - return security_bpf_token_capable(token, cap) == 0; - } - /* otherwise fallback to capable() checks */ - return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN)); -} - -void bpf_token_inc(struct bpf_token *token) -{ - atomic64_inc(&token->refcnt); -} - -static void bpf_token_free(struct bpf_token *token) -{ - security_bpf_token_free(token); - put_user_ns(token->userns); - kvfree(token); -} - -static void bpf_token_put_deferred(struct work_struct *work) -{ - struct bpf_token *token = container_of(work, struct bpf_token, work); - - bpf_token_free(token); -} - -void bpf_token_put(struct bpf_token *token) -{ - if (!token) - return; - - if (!atomic64_dec_and_test(&token->refcnt)) - return; - - INIT_WORK(&token->work, bpf_token_put_deferred); - schedule_work(&token->work); -} - -static int bpf_token_release(struct inode *inode, struct file *filp) -{ - struct bpf_token *token = filp->private_data; - - bpf_token_put(token); - return 0; -} - -static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) -{ - struct bpf_token *token = filp->private_data; - u64 mask; - - BUILD_BUG_ON(__MAX_BPF_CMD >= 64); - mask = (1ULL << __MAX_BPF_CMD) - 1; - if ((token->allowed_cmds & mask) == mask) - seq_printf(m, "allowed_cmds:\tany\n"); - else - seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds); - - BUILD_BUG_ON(__MAX_BPF_MAP_TYPE >= 64); - mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1; - if ((token->allowed_maps & mask) == mask) - seq_printf(m, "allowed_maps:\tany\n"); - else - seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); - - BUILD_BUG_ON(__MAX_BPF_PROG_TYPE >= 64); - mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; - if ((token->allowed_progs & mask) == mask) - seq_printf(m, "allowed_progs:\tany\n"); - else - seq_printf(m, "allowed_progs:\t0x%llx\n", token->allowed_progs); - - BUILD_BUG_ON(__MAX_BPF_ATTACH_TYPE >= 64); - mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; - if ((token->allowed_attachs & mask) == mask) - seq_printf(m, "allowed_attachs:\tany\n"); - else - seq_printf(m, "allowed_attachs:\t0x%llx\n", token->allowed_attachs); -} - -#define BPF_TOKEN_INODE_NAME "bpf-token" - -static const struct inode_operations bpf_token_iops = { }; - -static const struct file_operations bpf_token_fops = { - .release = bpf_token_release, - .show_fdinfo = bpf_token_show_fdinfo, -}; - -int bpf_token_create(union bpf_attr *attr) -{ - struct bpf_mount_opts *mnt_opts; - struct bpf_token *token = NULL; - struct user_namespace *userns; - struct inode *inode; - struct file *file; - struct path path; - struct fd f; - umode_t mode; - int err, fd; - - f = fdget(attr->token_create.bpffs_fd); - if (!f.file) - return -EBADF; - - path = f.file->f_path; - path_get(&path); - fdput(f); - - if (path.dentry != path.mnt->mnt_sb->s_root) { - err = -EINVAL; - goto out_path; - } - if (path.mnt->mnt_sb->s_op != &bpf_super_ops) { - err = -EINVAL; - goto out_path; - } - err = path_permission(&path, MAY_ACCESS); - if (err) - goto out_path; - - userns = path.dentry->d_sb->s_user_ns; - /* - * Enforce that creators of BPF tokens are in the same user - * namespace as the BPF FS instance. This makes reasoning about - * permissions a lot easier and we can always relax this later. - */ - if (current_user_ns() != userns) { - err = -EPERM; - goto out_path; - } - if (!ns_capable(userns, CAP_BPF)) { - err = -EPERM; - goto out_path; - } - - mnt_opts = path.dentry->d_sb->s_fs_info; - if (mnt_opts->delegate_cmds == 0 && - mnt_opts->delegate_maps == 0 && - mnt_opts->delegate_progs == 0 && - mnt_opts->delegate_attachs == 0) { - err = -ENOENT; /* no BPF token delegation is set up */ - goto out_path; - } - - mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); - inode = bpf_get_inode(path.mnt->mnt_sb, NULL, mode); - if (IS_ERR(inode)) { - err = PTR_ERR(inode); - goto out_path; - } - - inode->i_op = &bpf_token_iops; - inode->i_fop = &bpf_token_fops; - clear_nlink(inode); /* make sure it is unlinked */ - - file = alloc_file_pseudo(inode, path.mnt, BPF_TOKEN_INODE_NAME, O_RDWR, &bpf_token_fops); - if (IS_ERR(file)) { - iput(inode); - err = PTR_ERR(file); - goto out_path; - } - - token = kvzalloc(sizeof(*token), GFP_USER); - if (!token) { - err = -ENOMEM; - goto out_file; - } - - atomic64_set(&token->refcnt, 1); - - /* remember bpffs owning userns for future ns_capable() checks */ - token->userns = get_user_ns(userns); - - token->allowed_cmds = mnt_opts->delegate_cmds; - token->allowed_maps = mnt_opts->delegate_maps; - token->allowed_progs = mnt_opts->delegate_progs; - token->allowed_attachs = mnt_opts->delegate_attachs; - - err = security_bpf_token_create(token, attr, &path); - if (err) - goto out_token; - - fd = get_unused_fd_flags(O_CLOEXEC); - if (fd < 0) { - err = fd; - goto out_token; - } - - file->private_data = token; - fd_install(fd, file); - - path_put(&path); - return fd; - -out_token: - bpf_token_free(token); -out_file: - fput(file); -out_path: - path_put(&path); - return err; -} - -struct bpf_token *bpf_token_get_from_fd(u32 ufd) -{ - struct fd f = fdget(ufd); - struct bpf_token *token; - - if (!f.file) - return ERR_PTR(-EBADF); - if (f.file->f_op != &bpf_token_fops) { - fdput(f); - return ERR_PTR(-EINVAL); - } - - token = f.file->private_data; - bpf_token_inc(token); - fdput(f); - - return token; -} - -bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) -{ - /* BPF token can be used only within exactly the same userns in which - * it was created - */ - if (!token || current_user_ns() != token->userns) - return false; - if (!(token->allowed_cmds & (1ULL << cmd))) - return false; - return security_bpf_token_cmd(token, cmd) == 0; -} - -bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type) -{ - if (!token || type >= __MAX_BPF_MAP_TYPE) - return false; - - return token->allowed_maps & (1ULL << type); -} - -bool bpf_token_allow_prog_type(const struct bpf_token *token, - enum bpf_prog_type prog_type, - enum bpf_attach_type attach_type) -{ - if (!token || prog_type >= __MAX_BPF_PROG_TYPE || attach_type >= __MAX_BPF_ATTACH_TYPE) - return false; - - return (token->allowed_progs & (1ULL << prog_type)) && - (token->allowed_attachs & (1ULL << attach_type)); -} diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9456ee0ad129..4ceec8c2a484 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -20594,12 +20594,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 env->prog = *prog; env->ops = bpf_verifier_ops[env->prog->type]; env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel); - - env->allow_ptr_leaks = bpf_allow_ptr_leaks(env->prog->aux->token); - env->allow_uninit_stack = bpf_allow_uninit_stack(env->prog->aux->token); - env->bypass_spec_v1 = bpf_bypass_spec_v1(env->prog->aux->token); - env->bypass_spec_v4 = bpf_bypass_spec_v4(env->prog->aux->token); - env->bpf_capable = is_priv = bpf_token_capable(env->prog->aux->token, CAP_BPF); + is_priv = bpf_capable(); bpf_get_btf_vmlinux(); @@ -20631,6 +20626,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (attr->prog_flags & BPF_F_ANY_ALIGNMENT) env->strict_alignment = false; + env->allow_ptr_leaks = bpf_allow_ptr_leaks(); + env->allow_uninit_stack = bpf_allow_uninit_stack(); + env->bypass_spec_v1 = bpf_bypass_spec_v1(); + env->bypass_spec_v4 = bpf_bypass_spec_v4(); + env->bpf_capable = bpf_capable(); + if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 492d60e9c480..7ac6c52b25eb 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1629,7 +1629,7 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_trace_vprintk: return bpf_get_trace_vprintk_proto(); default: - return bpf_base_func_proto(func_id, prog); + return bpf_base_func_proto(func_id); } } diff --git a/net/core/filter.c b/net/core/filter.c index 3cc52b82bab8..24061f29c9dd 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -87,7 +87,7 @@ #include "dev.h" static const struct bpf_func_proto * -bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); +bpf_sk_base_func_proto(enum bpf_func_id func_id); int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len) { @@ -7862,7 +7862,7 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id, prog); + return bpf_base_func_proto(func_id); } } @@ -7955,7 +7955,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return NULL; } default: - return bpf_sk_base_func_proto(func_id, prog); + return bpf_sk_base_func_proto(func_id); } } @@ -7974,7 +7974,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; default: - return bpf_sk_base_func_proto(func_id, prog); + return bpf_sk_base_func_proto(func_id); } } @@ -8161,7 +8161,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #endif #endif default: - return bpf_sk_base_func_proto(func_id, prog); + return bpf_sk_base_func_proto(func_id); } } @@ -8220,7 +8220,7 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #endif #endif default: - return bpf_sk_base_func_proto(func_id, prog); + return bpf_sk_base_func_proto(func_id); } #if IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES) @@ -8281,7 +8281,7 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_tcp_sock_proto; #endif /* CONFIG_INET */ default: - return bpf_sk_base_func_proto(func_id, prog); + return bpf_sk_base_func_proto(func_id); } } @@ -8323,7 +8323,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_cgroup_classid_curr_proto; #endif default: - return bpf_sk_base_func_proto(func_id, prog); + return bpf_sk_base_func_proto(func_id); } } @@ -8367,7 +8367,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skc_lookup_tcp_proto; #endif default: - return bpf_sk_base_func_proto(func_id, prog); + return bpf_sk_base_func_proto(func_id); } } @@ -8378,7 +8378,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_load_bytes: return &bpf_flow_dissector_load_bytes_proto; default: - return bpf_sk_base_func_proto(func_id, prog); + return bpf_sk_base_func_proto(func_id); } } @@ -8405,7 +8405,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; default: - return bpf_sk_base_func_proto(func_id, prog); + return bpf_sk_base_func_proto(func_id); } } @@ -8580,7 +8580,7 @@ static bool cg_skb_is_valid_access(int off, int size, return false; case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_end): - if (!bpf_token_capable(prog->aux->token, CAP_BPF)) + if (!bpf_capable()) return false; break; } @@ -8592,7 +8592,7 @@ static bool cg_skb_is_valid_access(int off, int size, case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; case bpf_ctx_range(struct __sk_buff, tstamp): - if (!bpf_token_capable(prog->aux->token, CAP_BPF)) + if (!bpf_capable()) return false; break; default: @@ -11236,7 +11236,7 @@ sk_reuseport_func_proto(enum bpf_func_id func_id, case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id, prog); + return bpf_base_func_proto(func_id); } } @@ -11418,7 +11418,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_sk_release: return &bpf_sk_release_proto; default: - return bpf_sk_base_func_proto(func_id, prog); + return bpf_sk_base_func_proto(func_id); } } @@ -11752,7 +11752,7 @@ const struct bpf_func_proto bpf_sock_from_file_proto = { }; static const struct bpf_func_proto * -bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +bpf_sk_base_func_proto(enum bpf_func_id func_id) { const struct bpf_func_proto *func; @@ -11781,10 +11781,10 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id, prog); + return bpf_base_func_proto(func_id); } - if (!bpf_token_capable(prog->aux->token, CAP_PERFMON)) + if (!perfmon_capable()) return NULL; return func; diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 634cfafa583d..ae8b15e6896f 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -191,7 +191,7 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id, prog); + return bpf_base_func_proto(func_id); } } diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c index 5257d5e7eb09..0e4beae421f8 100644 --- a/net/netfilter/nf_bpf_link.c +++ b/net/netfilter/nf_bpf_link.c @@ -314,7 +314,7 @@ static bool nf_is_valid_access(int off, int size, enum bpf_access_type type, static const struct bpf_func_proto * bpf_nf_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { - return bpf_base_func_proto(func_id, prog); + return bpf_base_func_proto(func_id); } const struct bpf_verifier_ops netfilter_verifier_ops = { diff --git a/security/security.c b/security/security.c index 088a79c35c26..dcb3e7014f9b 100644 --- a/security/security.c +++ b/security/security.c @@ -5167,87 +5167,29 @@ int security_bpf_prog(struct bpf_prog *prog) } /** - * security_bpf_map_create() - Check if BPF map creation is allowed - * @map: BPF map object - * @attr: BPF syscall attributes used to create BPF map - * @token: BPF token used to grant user access - * - * Do a check when the kernel creates a new BPF map. This is also the - * point where LSM blob is allocated for LSMs that need them. - * - * Return: Returns 0 on success, error on failure. - */ -int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, - struct bpf_token *token) -{ - return call_int_hook(bpf_map_create, 0, map, attr, token); -} - -/** - * security_bpf_prog_load() - Check if loading of BPF program is allowed - * @prog: BPF program object - * @attr: BPF syscall attributes used to create BPF program - * @token: BPF token used to grant user access to BPF subsystem - * - * Perform an access control check when the kernel loads a BPF program and - * allocates associated BPF program object. This hook is also responsible for - * allocating any required LSM state for the BPF program. - * - * Return: Returns 0 on success, error on failure. - */ -int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, - struct bpf_token *token) -{ - return call_int_hook(bpf_prog_load, 0, prog, attr, token); -} - -/** - * security_bpf_token_create() - Check if creating of BPF token is allowed - * @token: BPF token object - * @attr: BPF syscall attributes used to create BPF token - * @path: path pointing to BPF FS mount point from which BPF token is created - * - * Do a check when the kernel instantiates a new BPF token object from BPF FS - * instance. This is also the point where LSM blob can be allocated for LSMs. - * - * Return: Returns 0 on success, error on failure. - */ -int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, - struct path *path) -{ - return call_int_hook(bpf_token_create, 0, token, attr, path); -} - -/** - * security_bpf_token_cmd() - Check if BPF token is allowed to delegate - * requested BPF syscall command - * @token: BPF token object - * @cmd: BPF syscall command requested to be delegated by BPF token + * security_bpf_map_alloc() - Allocate a bpf map LSM blob + * @map: bpf map * - * Do a check when the kernel decides whether provided BPF token should allow - * delegation of requested BPF syscall command. + * Initialize the security field inside bpf map. * * Return: Returns 0 on success, error on failure. */ -int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd) +int security_bpf_map_alloc(struct bpf_map *map) { - return call_int_hook(bpf_token_cmd, 0, token, cmd); + return call_int_hook(bpf_map_alloc_security, 0, map); } /** - * security_bpf_token_capable() - Check if BPF token is allowed to delegate - * requested BPF-related capability - * @token: BPF token object - * @cap: capabilities requested to be delegated by BPF token + * security_bpf_prog_alloc() - Allocate a bpf program LSM blob + * @aux: bpf program aux info struct * - * Do a check when the kernel decides whether provided BPF token should allow - * delegation of requested BPF-related capabilities. + * Initialize the security field inside bpf program. * * Return: Returns 0 on success, error on failure. */ -int security_bpf_token_capable(const struct bpf_token *token, int cap) +int security_bpf_prog_alloc(struct bpf_prog_aux *aux) { - return call_int_hook(bpf_token_capable, 0, token, cap); + return call_int_hook(bpf_prog_alloc_security, 0, aux); } /** @@ -5258,29 +5200,18 @@ int security_bpf_token_capable(const struct bpf_token *token, int cap) */ void security_bpf_map_free(struct bpf_map *map) { - call_void_hook(bpf_map_free, map); -} - -/** - * security_bpf_prog_free() - Free a BPF program's LSM blob - * @prog: BPF program struct - * - * Clean up the security information stored inside BPF program. - */ -void security_bpf_prog_free(struct bpf_prog *prog) -{ - call_void_hook(bpf_prog_free, prog); + call_void_hook(bpf_map_free_security, map); } /** - * security_bpf_token_free() - Free a BPF token's LSM blob - * @token: BPF token struct + * security_bpf_prog_free() - Free a bpf program's LSM blob + * @aux: bpf program aux info struct * - * Clean up the security information stored inside BPF token. + * Clean up the security information stored inside bpf prog. */ -void security_bpf_token_free(struct bpf_token *token) +void security_bpf_prog_free(struct bpf_prog_aux *aux) { - call_void_hook(bpf_token_free, token); + call_void_hook(bpf_prog_free_security, aux); } #endif /* CONFIG_BPF_SYSCALL */ diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 1501e95366a1..feda711c6b7b 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6783,8 +6783,7 @@ static int selinux_bpf_prog(struct bpf_prog *prog) BPF__PROG_RUN, NULL); } -static int selinux_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, - struct bpf_token *token) +static int selinux_bpf_map_alloc(struct bpf_map *map) { struct bpf_security_struct *bpfsec; @@ -6806,8 +6805,7 @@ static void selinux_bpf_map_free(struct bpf_map *map) kfree(bpfsec); } -static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, - struct bpf_token *token) +static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux) { struct bpf_security_struct *bpfsec; @@ -6816,39 +6814,16 @@ static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, return -ENOMEM; bpfsec->sid = current_sid(); - prog->aux->security = bpfsec; + aux->security = bpfsec; return 0; } -static void selinux_bpf_prog_free(struct bpf_prog *prog) +static void selinux_bpf_prog_free(struct bpf_prog_aux *aux) { - struct bpf_security_struct *bpfsec = prog->aux->security; + struct bpf_security_struct *bpfsec = aux->security; - prog->aux->security = NULL; - kfree(bpfsec); -} - -static int selinux_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, - struct path *path) -{ - struct bpf_security_struct *bpfsec; - - bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); - if (!bpfsec) - return -ENOMEM; - - bpfsec->sid = current_sid(); - token->security = bpfsec; - - return 0; -} - -static void selinux_bpf_token_free(struct bpf_token *token) -{ - struct bpf_security_struct *bpfsec = token->security; - - token->security = NULL; + aux->security = NULL; kfree(bpfsec); } #endif @@ -7204,9 +7179,8 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(bpf, selinux_bpf), LSM_HOOK_INIT(bpf_map, selinux_bpf_map), LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog), - LSM_HOOK_INIT(bpf_map_free, selinux_bpf_map_free), - LSM_HOOK_INIT(bpf_prog_free, selinux_bpf_prog_free), - LSM_HOOK_INIT(bpf_token_free, selinux_bpf_token_free), + LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free), + LSM_HOOK_INIT(bpf_prog_free_security, selinux_bpf_prog_free), #endif #ifdef CONFIG_PERF_EVENTS @@ -7263,9 +7237,8 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(audit_rule_init, selinux_audit_rule_init), #endif #ifdef CONFIG_BPF_SYSCALL - LSM_HOOK_INIT(bpf_map_create, selinux_bpf_map_create), - LSM_HOOK_INIT(bpf_prog_load, selinux_bpf_prog_load), - LSM_HOOK_INIT(bpf_token_create, selinux_bpf_token_create), + LSM_HOOK_INIT(bpf_map_alloc_security, selinux_bpf_map_alloc), + LSM_HOOK_INIT(bpf_prog_alloc_security, selinux_bpf_prog_alloc), #endif #ifdef CONFIG_PERF_EVENTS LSM_HOOK_INIT(perf_event_alloc, selinux_perf_event_alloc), diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e0545201b55f..7f24d898efbb 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -847,36 +847,6 @@ union bpf_iter_link_info { * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. * - * BPF_TOKEN_CREATE - * Description - * Create BPF token with embedded information about what - * BPF-related functionality it allows: - * - a set of allowed bpf() syscall commands; - * - a set of allowed BPF map types to be created with - * BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed; - * - a set of allowed BPF program types and BPF program attach - * types to be loaded with BPF_PROG_LOAD command, if - * BPF_PROG_LOAD itself is allowed. - * - * BPF token is created (derived) from an instance of BPF FS, - * assuming it has necessary delegation mount options specified. - * This BPF token can be passed as an extra parameter to various - * bpf() syscall commands to grant BPF subsystem functionality to - * unprivileged processes. - * - * When created, BPF token is "associated" with the owning - * user namespace of BPF FS instance (super block) that it was - * derived from, and subsequent BPF operations performed with - * BPF token would be performing capabilities checks (i.e., - * CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within - * that user namespace. Without BPF token, such capabilities - * have to be granted in init user namespace, making bpf() - * syscall incompatible with user namespace, for the most part. - * - * Return - * A new file descriptor (a nonnegative integer), or -1 if an - * error occurred (in which case, *errno* is set appropriately). - * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -931,8 +901,6 @@ enum bpf_cmd { BPF_ITER_CREATE, BPF_LINK_DETACH, BPF_PROG_BIND_MAP, - BPF_TOKEN_CREATE, - __MAX_BPF_CMD, }; enum bpf_map_type { @@ -983,7 +951,6 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, - __MAX_BPF_MAP_TYPE }; /* Note that tracing related programs such as @@ -1028,7 +995,6 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ BPF_PROG_TYPE_NETFILTER, - __MAX_BPF_PROG_TYPE }; enum bpf_attach_type { @@ -1437,7 +1403,6 @@ union bpf_attr { * to using 5 hash functions). */ __u64 map_extra; - __u32 map_token_fd; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -1507,7 +1472,6 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 log_true_size; - __u32 prog_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -1620,7 +1584,6 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 btf_log_true_size; - __u32 btf_token_fd; }; struct { @@ -1751,11 +1714,6 @@ union bpf_attr { __u32 flags; /* extra flags */ } prog_bind_map; - struct { /* struct used by BPF_TOKEN_CREATE command */ - __u32 flags; - __u32 bpffs_fd; - } token_create; - } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index b6619199a706..2d0c282c8588 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1,4 +1,4 @@ libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \ netlink.o bpf_prog_linfo.o libbpf_probes.o hashmap.o \ btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \ - usdt.o zip.o elf.o features.o + usdt.o zip.o elf.o diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 0ad8e532b3cf..9dc9625651dc 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -103,7 +103,7 @@ int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts) * [0] https://lore.kernel.org/bpf/20201201215900.3569844-1-guro@fb.com/ * [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper") */ -int probe_memcg_account(int token_fd) +int probe_memcg_account(void) { const size_t attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd); struct bpf_insn insns[] = { @@ -120,7 +120,6 @@ int probe_memcg_account(int token_fd) attr.insns = ptr_to_u64(insns); attr.insn_cnt = insn_cnt; attr.license = ptr_to_u64("GPL"); - attr.prog_token_fd = token_fd; prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, attr_sz); if (prog_fd >= 0) { @@ -147,7 +146,7 @@ int bump_rlimit_memlock(void) struct rlimit rlim; /* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */ - if (memlock_bumped || feat_supported(NULL, FEAT_MEMCG_ACCOUNT)) + if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT)) return 0; memlock_bumped = true; @@ -170,7 +169,7 @@ int bpf_map_create(enum bpf_map_type map_type, __u32 max_entries, const struct bpf_map_create_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, map_token_fd); + const size_t attr_sz = offsetofend(union bpf_attr, map_extra); union bpf_attr attr; int fd; @@ -182,7 +181,7 @@ int bpf_map_create(enum bpf_map_type map_type, return libbpf_err(-EINVAL); attr.map_type = map_type; - if (map_name && feat_supported(NULL, FEAT_PROG_NAME)) + if (map_name && kernel_supports(NULL, FEAT_PROG_NAME)) libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name)); attr.key_size = key_size; attr.value_size = value_size; @@ -199,8 +198,6 @@ int bpf_map_create(enum bpf_map_type map_type, attr.numa_node = OPTS_GET(opts, numa_node, 0); attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0); - attr.map_token_fd = OPTS_GET(opts, token_fd, 0); - fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz); return libbpf_err_errno(fd); } @@ -235,7 +232,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, size_t insn_cnt, struct bpf_prog_load_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd); + const size_t attr_sz = offsetofend(union bpf_attr, log_true_size); void *finfo = NULL, *linfo = NULL; const char *func_info, *line_info; __u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd; @@ -264,9 +261,8 @@ int bpf_prog_load(enum bpf_prog_type prog_type, attr.prog_flags = OPTS_GET(opts, prog_flags, 0); attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0); attr.kern_version = OPTS_GET(opts, kern_version, 0); - attr.prog_token_fd = OPTS_GET(opts, token_fd, 0); - if (prog_name && feat_supported(NULL, FEAT_PROG_NAME)) + if (prog_name && kernel_supports(NULL, FEAT_PROG_NAME)) libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name)); attr.license = ptr_to_u64(license); @@ -1186,7 +1182,7 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd) int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, btf_token_fd); + const size_t attr_sz = offsetofend(union bpf_attr, btf_log_true_size); union bpf_attr attr; char *log_buf; size_t log_size; @@ -1211,8 +1207,6 @@ int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts attr.btf = ptr_to_u64(btf_data); attr.btf_size = btf_size; - attr.btf_token_fd = OPTS_GET(opts, token_fd, 0); - /* log_level == 0 and log_buf != NULL means "try loading without * log_buf, but retry with log_buf and log_level=1 on error", which is * consistent across low-level and high-level BTF and program loading @@ -1293,20 +1287,3 @@ int bpf_prog_bind_map(int prog_fd, int map_fd, ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, attr_sz); return libbpf_err_errno(ret); } - -int bpf_token_create(int bpffs_fd, struct bpf_token_create_opts *opts) -{ - const size_t attr_sz = offsetofend(union bpf_attr, token_create); - union bpf_attr attr; - int fd; - - if (!OPTS_VALID(opts, bpf_token_create_opts)) - return libbpf_err(-EINVAL); - - memset(&attr, 0, attr_sz); - attr.token_create.bpffs_fd = bpffs_fd; - attr.token_create.flags = OPTS_GET(opts, flags, 0); - - fd = sys_bpf_fd(BPF_TOKEN_CREATE, &attr, attr_sz); - return libbpf_err_errno(fd); -} diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 991b86bfe7e4..d0f53772bdc0 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -51,11 +51,8 @@ struct bpf_map_create_opts { __u32 numa_node; __u32 map_ifindex; - - __u32 token_fd; - size_t :0; }; -#define bpf_map_create_opts__last_field token_fd +#define bpf_map_create_opts__last_field map_ifindex LIBBPF_API int bpf_map_create(enum bpf_map_type map_type, const char *map_name, @@ -105,10 +102,9 @@ struct bpf_prog_load_opts { * If kernel doesn't support this feature, log_size is left unchanged. */ __u32 log_true_size; - __u32 token_fd; size_t :0; }; -#define bpf_prog_load_opts__last_field token_fd +#define bpf_prog_load_opts__last_field log_true_size LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type, const char *prog_name, const char *license, @@ -134,10 +130,9 @@ struct bpf_btf_load_opts { * If kernel doesn't support this feature, log_size is left unchanged. */ __u32 log_true_size; - __u32 token_fd; size_t :0; }; -#define bpf_btf_load_opts__last_field token_fd +#define bpf_btf_load_opts__last_field log_true_size LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts); @@ -645,30 +640,6 @@ struct bpf_test_run_opts { LIBBPF_API int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts); -struct bpf_token_create_opts { - size_t sz; /* size of this struct for forward/backward compatibility */ - __u32 flags; - size_t :0; -}; -#define bpf_token_create_opts__last_field flags - -/** - * @brief **bpf_token_create()** creates a new instance of BPF token derived - * from specified BPF FS mount point. - * - * BPF token created with this API can be passed to bpf() syscall for - * commands like BPF_PROG_LOAD, BPF_MAP_CREATE, etc. - * - * @param bpffs_fd FD for BPF FS instance from which to derive a BPF token - * instance. - * @param opts optional BPF token creation options, can be NULL - * - * @return BPF token FD > 0, on success; negative error code, otherwise (errno - * is also set to the error code) - */ -LIBBPF_API int bpf_token_create(int bpffs_fd, - struct bpf_token_create_opts *opts); - #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 63033c334320..ee95fd379d4d 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1317,9 +1317,7 @@ struct btf *btf__parse_split(const char *path, struct btf *base_btf) static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian); -int btf_load_into_kernel(struct btf *btf, - char *log_buf, size_t log_sz, __u32 log_level, - int token_fd) +int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level) { LIBBPF_OPTS(bpf_btf_load_opts, opts); __u32 buf_sz = 0, raw_size; @@ -1369,7 +1367,6 @@ retry_load: opts.log_level = log_level; } - opts.token_fd = token_fd; btf->fd = bpf_btf_load(raw_data, raw_size, &opts); if (btf->fd < 0) { /* time to turn on verbose mode and try again */ @@ -1397,7 +1394,7 @@ done: int btf__load_into_kernel(struct btf *btf) { - return btf_load_into_kernel(btf, NULL, 0, 0, 0); + return btf_load_into_kernel(btf, NULL, 0, 0); } int btf__fd(const struct btf *btf) diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c index c92e02394159..b02faec748a5 100644 --- a/tools/lib/bpf/elf.c +++ b/tools/lib/bpf/elf.c @@ -11,6 +11,8 @@ #include "libbpf_internal.h" #include "str_error.h" +#define STRERR_BUFSIZE 128 + /* A SHT_GNU_versym section holds 16-bit words. This bit is set if * the symbol is hidden and can only be seen when referenced using an * explicit version number. This is a GNU extension. diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c deleted file mode 100644 index ce98a334be21..000000000000 --- a/tools/lib/bpf/features.c +++ /dev/null @@ -1,478 +0,0 @@ -// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) -/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ -#include -#include -#include "bpf.h" -#include "libbpf.h" -#include "libbpf_common.h" -#include "libbpf_internal.h" -#include "str_error.h" - -static inline __u64 ptr_to_u64(const void *ptr) -{ - return (__u64)(unsigned long)ptr; -} - -static int probe_fd(int fd) -{ - if (fd >= 0) - close(fd); - return fd >= 0; -} - -static int probe_kern_prog_name(int token_fd) -{ - const size_t attr_sz = offsetofend(union bpf_attr, prog_name); - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - union bpf_attr attr; - int ret; - - memset(&attr, 0, attr_sz); - attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; - attr.license = ptr_to_u64("GPL"); - attr.insns = ptr_to_u64(insns); - attr.insn_cnt = (__u32)ARRAY_SIZE(insns); - attr.prog_token_fd = token_fd; - libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name)); - - /* make sure loading with name works */ - ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS); - return probe_fd(ret); -} - -static int probe_kern_global_data(int token_fd) -{ - char *cp, errmsg[STRERR_BUFSIZE]; - struct bpf_insn insns[] = { - BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), - BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - LIBBPF_OPTS(bpf_map_create_opts, map_opts, .token_fd = token_fd); - LIBBPF_OPTS(bpf_prog_load_opts, prog_opts, .token_fd = token_fd); - int ret, map, insn_cnt = ARRAY_SIZE(insns); - - map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, &map_opts); - if (map < 0) { - ret = -errno; - cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); - pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", - __func__, cp, -ret); - return ret; - } - - insns[0].imm = map; - - ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts); - close(map); - return probe_fd(ret); -} - -static int probe_kern_btf(int token_fd) -{ - static const char strs[] = "\0int"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs), token_fd)); -} - -static int probe_kern_btf_func(int token_fd) -{ - static const char strs[] = "\0int\0x\0a"; - /* void x(int a) {} */ - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* FUNC_PROTO */ /* [2] */ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), - BTF_PARAM_ENC(7, 1), - /* FUNC x */ /* [3] */ - BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs), token_fd)); -} - -static int probe_kern_btf_func_global(int token_fd) -{ - static const char strs[] = "\0int\0x\0a"; - /* static void x(int a) {} */ - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* FUNC_PROTO */ /* [2] */ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), - BTF_PARAM_ENC(7, 1), - /* FUNC x BTF_FUNC_GLOBAL */ /* [3] */ - BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs), token_fd)); -} - -static int probe_kern_btf_datasec(int token_fd) -{ - static const char strs[] = "\0x\0.data"; - /* static int a; */ - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* VAR x */ /* [2] */ - BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), - BTF_VAR_STATIC, - /* DATASEC val */ /* [3] */ - BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), - BTF_VAR_SECINFO_ENC(2, 0, 4), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs), token_fd)); -} - -static int probe_kern_btf_float(int token_fd) -{ - static const char strs[] = "\0float"; - __u32 types[] = { - /* float */ - BTF_TYPE_FLOAT_ENC(1, 4), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs), token_fd)); -} - -static int probe_kern_btf_decl_tag(int token_fd) -{ - static const char strs[] = "\0tag"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* VAR x */ /* [2] */ - BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), - BTF_VAR_STATIC, - /* attr */ - BTF_TYPE_DECL_TAG_ENC(1, 2, -1), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs), token_fd)); -} - -static int probe_kern_btf_type_tag(int token_fd) -{ - static const char strs[] = "\0tag"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* attr */ - BTF_TYPE_TYPE_TAG_ENC(1, 1), /* [2] */ - /* ptr */ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), /* [3] */ - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs), token_fd)); -} - -static int probe_kern_array_mmap(int token_fd) -{ - LIBBPF_OPTS(bpf_map_create_opts, opts, - .map_flags = BPF_F_MMAPABLE, - .token_fd = token_fd, - ); - int fd; - - fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts); - return probe_fd(fd); -} - -static int probe_kern_exp_attach_type(int token_fd) -{ - LIBBPF_OPTS(bpf_prog_load_opts, opts, - .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, - .token_fd = token_fd, - ); - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int fd, insn_cnt = ARRAY_SIZE(insns); - - /* use any valid combination of program type and (optional) - * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS) - * to see if kernel supports expected_attach_type field for - * BPF_PROG_LOAD command - */ - fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts); - return probe_fd(fd); -} - -static int probe_kern_probe_read_kernel(int token_fd) -{ - LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd); - struct bpf_insn insns[] = { - BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), /* r1 = r10 (fp) */ - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), /* r1 += -8 */ - BPF_MOV64_IMM(BPF_REG_2, 8), /* r2 = 8 */ - BPF_MOV64_IMM(BPF_REG_3, 0), /* r3 = 0 */ - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel), - BPF_EXIT_INSN(), - }; - int fd, insn_cnt = ARRAY_SIZE(insns); - - fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts); - return probe_fd(fd); -} - -static int probe_prog_bind_map(int token_fd) -{ - char *cp, errmsg[STRERR_BUFSIZE]; - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - LIBBPF_OPTS(bpf_map_create_opts, map_opts, .token_fd = token_fd); - LIBBPF_OPTS(bpf_prog_load_opts, prog_opts, .token_fd = token_fd); - int ret, map, prog, insn_cnt = ARRAY_SIZE(insns); - - map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, &map_opts); - if (map < 0) { - ret = -errno; - cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); - pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", - __func__, cp, -ret); - return ret; - } - - prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts); - if (prog < 0) { - close(map); - return 0; - } - - ret = bpf_prog_bind_map(prog, map, NULL); - - close(map); - close(prog); - - return ret >= 0; -} - -static int probe_module_btf(int token_fd) -{ - static const char strs[] = "\0int"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), - }; - struct bpf_btf_info info; - __u32 len = sizeof(info); - char name[16]; - int fd, err; - - fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs), token_fd); - if (fd < 0) - return 0; /* BTF not supported at all */ - - memset(&info, 0, sizeof(info)); - info.name = ptr_to_u64(name); - info.name_len = sizeof(name); - - /* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer; - * kernel's module BTF support coincides with support for - * name/name_len fields in struct bpf_btf_info. - */ - err = bpf_btf_get_info_by_fd(fd, &info, &len); - close(fd); - return !err; -} - -static int probe_perf_link(int token_fd) -{ - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd); - int prog_fd, link_fd, err; - - prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", - insns, ARRAY_SIZE(insns), &opts); - if (prog_fd < 0) - return -errno; - - /* use invalid perf_event FD to get EBADF, if link is supported; - * otherwise EINVAL should be returned - */ - link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL); - err = -errno; /* close() can clobber errno */ - - if (link_fd >= 0) - close(link_fd); - close(prog_fd); - - return link_fd < 0 && err == -EBADF; -} - -static int probe_uprobe_multi_link(int token_fd) -{ - LIBBPF_OPTS(bpf_prog_load_opts, load_opts, - .expected_attach_type = BPF_TRACE_UPROBE_MULTI, - .token_fd = token_fd, - ); - LIBBPF_OPTS(bpf_link_create_opts, link_opts); - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int prog_fd, link_fd, err; - unsigned long offset = 0; - - prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", - insns, ARRAY_SIZE(insns), &load_opts); - if (prog_fd < 0) - return -errno; - - /* Creating uprobe in '/' binary should fail with -EBADF. */ - link_opts.uprobe_multi.path = "/"; - link_opts.uprobe_multi.offsets = &offset; - link_opts.uprobe_multi.cnt = 1; - - link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); - err = -errno; /* close() can clobber errno */ - - if (link_fd >= 0) - close(link_fd); - close(prog_fd); - - return link_fd < 0 && err == -EBADF; -} - -static int probe_kern_bpf_cookie(int token_fd) -{ - struct bpf_insn insns[] = { - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie), - BPF_EXIT_INSN(), - }; - LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd); - int ret, insn_cnt = ARRAY_SIZE(insns); - - ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts); - return probe_fd(ret); -} - -static int probe_kern_btf_enum64(int token_fd) -{ - static const char strs[] = "\0enum64"; - __u32 types[] = { - BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs), token_fd)); -} - -typedef int (*feature_probe_fn)(int /* token_fd */); - -static struct kern_feature_cache feature_cache; - -static struct kern_feature_desc { - const char *desc; - feature_probe_fn probe; -} feature_probes[__FEAT_CNT] = { - [FEAT_PROG_NAME] = { - "BPF program name", probe_kern_prog_name, - }, - [FEAT_GLOBAL_DATA] = { - "global variables", probe_kern_global_data, - }, - [FEAT_BTF] = { - "minimal BTF", probe_kern_btf, - }, - [FEAT_BTF_FUNC] = { - "BTF functions", probe_kern_btf_func, - }, - [FEAT_BTF_GLOBAL_FUNC] = { - "BTF global function", probe_kern_btf_func_global, - }, - [FEAT_BTF_DATASEC] = { - "BTF data section and variable", probe_kern_btf_datasec, - }, - [FEAT_ARRAY_MMAP] = { - "ARRAY map mmap()", probe_kern_array_mmap, - }, - [FEAT_EXP_ATTACH_TYPE] = { - "BPF_PROG_LOAD expected_attach_type attribute", - probe_kern_exp_attach_type, - }, - [FEAT_PROBE_READ_KERN] = { - "bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel, - }, - [FEAT_PROG_BIND_MAP] = { - "BPF_PROG_BIND_MAP support", probe_prog_bind_map, - }, - [FEAT_MODULE_BTF] = { - "module BTF support", probe_module_btf, - }, - [FEAT_BTF_FLOAT] = { - "BTF_KIND_FLOAT support", probe_kern_btf_float, - }, - [FEAT_PERF_LINK] = { - "BPF perf link support", probe_perf_link, - }, - [FEAT_BTF_DECL_TAG] = { - "BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag, - }, - [FEAT_BTF_TYPE_TAG] = { - "BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag, - }, - [FEAT_MEMCG_ACCOUNT] = { - "memcg-based memory accounting", probe_memcg_account, - }, - [FEAT_BPF_COOKIE] = { - "BPF cookie support", probe_kern_bpf_cookie, - }, - [FEAT_BTF_ENUM64] = { - "BTF_KIND_ENUM64 support", probe_kern_btf_enum64, - }, - [FEAT_SYSCALL_WRAPPER] = { - "Kernel using syscall wrapper", probe_kern_syscall_wrapper, - }, - [FEAT_UPROBE_MULTI_LINK] = { - "BPF multi-uprobe link support", probe_uprobe_multi_link, - }, -}; - -bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id) -{ - struct kern_feature_desc *feat = &feature_probes[feat_id]; - int ret; - - /* assume global feature cache, unless custom one is provided */ - if (!cache) - cache = &feature_cache; - - if (READ_ONCE(cache->res[feat_id]) == FEAT_UNKNOWN) { - ret = feat->probe(cache->token_fd); - if (ret > 0) { - WRITE_ONCE(cache->res[feat_id], FEAT_SUPPORTED); - } else if (ret == 0) { - WRITE_ONCE(cache->res[feat_id], FEAT_MISSING); - } else { - pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret); - WRITE_ONCE(cache->res[feat_id], FEAT_MISSING); - } - } - - return READ_ONCE(cache->res[feat_id]) == FEAT_SUPPORTED; -} diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 4b5ff9508e18..ac54ebc0629f 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -59,8 +59,6 @@ #define BPF_FS_MAGIC 0xcafe4a11 #endif -#define BPF_FS_DEFAULT_PATH "/sys/fs/bpf" - #define BPF_INSN_SZ (sizeof(struct bpf_insn)) /* vsprintf() in __base_pr() uses nonliteral format string. It may break @@ -695,10 +693,6 @@ struct bpf_object { struct usdt_manager *usdt_man; - struct kern_feature_cache *feat_cache; - char *token_path; - int token_fd; - char path[]; }; @@ -2198,7 +2192,7 @@ static int build_map_pin_path(struct bpf_map *map, const char *path) int err; if (!path) - path = BPF_FS_DEFAULT_PATH; + path = "/sys/fs/bpf"; err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map)); if (err) @@ -3285,7 +3279,7 @@ skip_exception_cb: } else { /* currently BPF_BTF_LOAD only supports log_level 1 */ err = btf_load_into_kernel(kern_btf, obj->log_buf, obj->log_size, - obj->log_level ? 1 : 0, obj->token_fd); + obj->log_level ? 1 : 0); } if (sanitize) { if (!err) { @@ -4608,63 +4602,6 @@ int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries) return 0; } -static int bpf_object_prepare_token(struct bpf_object *obj) -{ - const char *bpffs_path; - int bpffs_fd = -1, token_fd, err; - bool mandatory; - enum libbpf_print_level level; - - /* token is already set up */ - if (obj->token_fd > 0) - return 0; - /* token is explicitly prevented */ - if (obj->token_fd < 0) { - pr_debug("object '%s': token is prevented, skipping...\n", obj->name); - /* reset to zero to avoid extra checks during map_create and prog_load steps */ - obj->token_fd = 0; - return 0; - } - - mandatory = obj->token_path != NULL; - level = mandatory ? LIBBPF_WARN : LIBBPF_DEBUG; - - bpffs_path = obj->token_path ?: BPF_FS_DEFAULT_PATH; - bpffs_fd = open(bpffs_path, O_DIRECTORY, O_RDWR); - if (bpffs_fd < 0) { - err = -errno; - __pr(level, "object '%s': failed (%d) to open BPF FS mount at '%s'%s\n", - obj->name, err, bpffs_path, - mandatory ? "" : ", skipping optional step..."); - return mandatory ? err : 0; - } - - token_fd = bpf_token_create(bpffs_fd, 0); - close(bpffs_fd); - if (token_fd < 0) { - if (!mandatory && token_fd == -ENOENT) { - pr_debug("object '%s': BPF FS at '%s' doesn't have BPF token delegation set up, skipping...\n", - obj->name, bpffs_path); - return 0; - } - __pr(level, "object '%s': failed (%d) to create BPF token from '%s'%s\n", - obj->name, token_fd, bpffs_path, - mandatory ? "" : ", skipping optional step..."); - return mandatory ? token_fd : 0; - } - - obj->feat_cache = calloc(1, sizeof(*obj->feat_cache)); - if (!obj->feat_cache) { - close(token_fd); - return -ENOMEM; - } - - obj->token_fd = token_fd; - obj->feat_cache->token_fd = token_fd; - - return 0; -} - static int bpf_object__probe_loading(struct bpf_object *obj) { @@ -4674,7 +4611,6 @@ bpf_object__probe_loading(struct bpf_object *obj) BPF_EXIT_INSN(), }; int ret, insn_cnt = ARRAY_SIZE(insns); - LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = obj->token_fd); if (obj->gen_loader) return 0; @@ -4684,9 +4620,9 @@ bpf_object__probe_loading(struct bpf_object *obj) pr_warn("Failed to bump RLIMIT_MEMLOCK (err = %d), you might need to do it explicitly!\n", ret); /* make sure basic loading works */ - ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &opts); + ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); if (ret < 0) - ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts); + ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL); if (ret < 0) { ret = errno; cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); @@ -4701,18 +4637,462 @@ bpf_object__probe_loading(struct bpf_object *obj) return 0; } +static int probe_fd(int fd) +{ + if (fd >= 0) + close(fd); + return fd >= 0; +} + +static int probe_kern_prog_name(void) +{ + const size_t attr_sz = offsetofend(union bpf_attr, prog_name); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.license = ptr_to_u64("GPL"); + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = (__u32)ARRAY_SIZE(insns); + libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name)); + + /* make sure loading with name works */ + ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS); + return probe_fd(ret); +} + +static int probe_kern_global_data(void) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int ret, map, insn_cnt = ARRAY_SIZE(insns); + + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, NULL); + if (map < 0) { + ret = -errno; + cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); + pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", + __func__, cp, -ret); + return ret; + } + + insns[0].imm = map; + + ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); + close(map); + return probe_fd(ret); +} + +static int probe_kern_btf(void) +{ + static const char strs[] = "\0int"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_func(void) +{ + static const char strs[] = "\0int\0x\0a"; + /* void x(int a) {} */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* FUNC_PROTO */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), + BTF_PARAM_ENC(7, 1), + /* FUNC x */ /* [3] */ + BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_func_global(void) +{ + static const char strs[] = "\0int\0x\0a"; + /* static void x(int a) {} */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* FUNC_PROTO */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), + BTF_PARAM_ENC(7, 1), + /* FUNC x BTF_FUNC_GLOBAL */ /* [3] */ + BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_datasec(void) +{ + static const char strs[] = "\0x\0.data"; + /* static int a; */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* DATASEC val */ /* [3] */ + BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(2, 0, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_float(void) +{ + static const char strs[] = "\0float"; + __u32 types[] = { + /* float */ + BTF_TYPE_FLOAT_ENC(1, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_decl_tag(void) +{ + static const char strs[] = "\0tag"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* attr */ + BTF_TYPE_DECL_TAG_ENC(1, 2, -1), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_type_tag(void) +{ + static const char strs[] = "\0tag"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* attr */ + BTF_TYPE_TYPE_TAG_ENC(1, 1), /* [2] */ + /* ptr */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), /* [3] */ + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_array_mmap(void) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_MMAPABLE); + int fd; + + fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts); + return probe_fd(fd); +} + +static int probe_kern_exp_attach_type(void) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int fd, insn_cnt = ARRAY_SIZE(insns); + + /* use any valid combination of program type and (optional) + * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS) + * to see if kernel supports expected_attach_type field for + * BPF_PROG_LOAD command + */ + fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts); + return probe_fd(fd); +} + +static int probe_kern_probe_read_kernel(void) +{ + struct bpf_insn insns[] = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), /* r1 = r10 (fp) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), /* r1 += -8 */ + BPF_MOV64_IMM(BPF_REG_2, 8), /* r2 = 8 */ + BPF_MOV64_IMM(BPF_REG_3, 0), /* r3 = 0 */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel), + BPF_EXIT_INSN(), + }; + int fd, insn_cnt = ARRAY_SIZE(insns); + + fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL); + return probe_fd(fd); +} + +static int probe_prog_bind_map(void) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int ret, map, prog, insn_cnt = ARRAY_SIZE(insns); + + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, NULL); + if (map < 0) { + ret = -errno; + cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); + pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", + __func__, cp, -ret); + return ret; + } + + prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); + if (prog < 0) { + close(map); + return 0; + } + + ret = bpf_prog_bind_map(prog, map, NULL); + + close(map); + close(prog); + + return ret >= 0; +} + +static int probe_module_btf(void) +{ + static const char strs[] = "\0int"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), + }; + struct bpf_btf_info info; + __u32 len = sizeof(info); + char name[16]; + int fd, err; + + fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs)); + if (fd < 0) + return 0; /* BTF not supported at all */ + + memset(&info, 0, sizeof(info)); + info.name = ptr_to_u64(name); + info.name_len = sizeof(name); + + /* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer; + * kernel's module BTF support coincides with support for + * name/name_len fields in struct bpf_btf_info. + */ + err = bpf_btf_get_info_by_fd(fd, &info, &len); + close(fd); + return !err; +} + +static int probe_perf_link(void) +{ + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int prog_fd, link_fd, err; + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", + insns, ARRAY_SIZE(insns), NULL); + if (prog_fd < 0) + return -errno; + + /* use invalid perf_event FD to get EBADF, if link is supported; + * otherwise EINVAL should be returned + */ + link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL); + err = -errno; /* close() can clobber errno */ + + if (link_fd >= 0) + close(link_fd); + close(prog_fd); + + return link_fd < 0 && err == -EBADF; +} + +static int probe_uprobe_multi_link(void) +{ + LIBBPF_OPTS(bpf_prog_load_opts, load_opts, + .expected_attach_type = BPF_TRACE_UPROBE_MULTI, + ); + LIBBPF_OPTS(bpf_link_create_opts, link_opts); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int prog_fd, link_fd, err; + unsigned long offset = 0; + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", + insns, ARRAY_SIZE(insns), &load_opts); + if (prog_fd < 0) + return -errno; + + /* Creating uprobe in '/' binary should fail with -EBADF. */ + link_opts.uprobe_multi.path = "/"; + link_opts.uprobe_multi.offsets = &offset; + link_opts.uprobe_multi.cnt = 1; + + link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); + err = -errno; /* close() can clobber errno */ + + if (link_fd >= 0) + close(link_fd); + close(prog_fd); + + return link_fd < 0 && err == -EBADF; +} + +static int probe_kern_bpf_cookie(void) +{ + struct bpf_insn insns[] = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie), + BPF_EXIT_INSN(), + }; + int ret, insn_cnt = ARRAY_SIZE(insns); + + ret = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", insns, insn_cnt, NULL); + return probe_fd(ret); +} + +static int probe_kern_btf_enum64(void) +{ + static const char strs[] = "\0enum64"; + __u32 types[] = { + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_syscall_wrapper(void); + +enum kern_feature_result { + FEAT_UNKNOWN = 0, + FEAT_SUPPORTED = 1, + FEAT_MISSING = 2, +}; + +typedef int (*feature_probe_fn)(void); + +static struct kern_feature_desc { + const char *desc; + feature_probe_fn probe; + enum kern_feature_result res; +} feature_probes[__FEAT_CNT] = { + [FEAT_PROG_NAME] = { + "BPF program name", probe_kern_prog_name, + }, + [FEAT_GLOBAL_DATA] = { + "global variables", probe_kern_global_data, + }, + [FEAT_BTF] = { + "minimal BTF", probe_kern_btf, + }, + [FEAT_BTF_FUNC] = { + "BTF functions", probe_kern_btf_func, + }, + [FEAT_BTF_GLOBAL_FUNC] = { + "BTF global function", probe_kern_btf_func_global, + }, + [FEAT_BTF_DATASEC] = { + "BTF data section and variable", probe_kern_btf_datasec, + }, + [FEAT_ARRAY_MMAP] = { + "ARRAY map mmap()", probe_kern_array_mmap, + }, + [FEAT_EXP_ATTACH_TYPE] = { + "BPF_PROG_LOAD expected_attach_type attribute", + probe_kern_exp_attach_type, + }, + [FEAT_PROBE_READ_KERN] = { + "bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel, + }, + [FEAT_PROG_BIND_MAP] = { + "BPF_PROG_BIND_MAP support", probe_prog_bind_map, + }, + [FEAT_MODULE_BTF] = { + "module BTF support", probe_module_btf, + }, + [FEAT_BTF_FLOAT] = { + "BTF_KIND_FLOAT support", probe_kern_btf_float, + }, + [FEAT_PERF_LINK] = { + "BPF perf link support", probe_perf_link, + }, + [FEAT_BTF_DECL_TAG] = { + "BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag, + }, + [FEAT_BTF_TYPE_TAG] = { + "BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag, + }, + [FEAT_MEMCG_ACCOUNT] = { + "memcg-based memory accounting", probe_memcg_account, + }, + [FEAT_BPF_COOKIE] = { + "BPF cookie support", probe_kern_bpf_cookie, + }, + [FEAT_BTF_ENUM64] = { + "BTF_KIND_ENUM64 support", probe_kern_btf_enum64, + }, + [FEAT_SYSCALL_WRAPPER] = { + "Kernel using syscall wrapper", probe_kern_syscall_wrapper, + }, + [FEAT_UPROBE_MULTI_LINK] = { + "BPF multi-uprobe link support", probe_uprobe_multi_link, + }, +}; + bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) { + struct kern_feature_desc *feat = &feature_probes[feat_id]; + int ret; + if (obj && obj->gen_loader) /* To generate loader program assume the latest kernel * to avoid doing extra prog_load, map_create syscalls. */ return true; - if (obj->token_fd) - return feat_supported(obj->feat_cache, feat_id); + if (READ_ONCE(feat->res) == FEAT_UNKNOWN) { + ret = feat->probe(); + if (ret > 0) { + WRITE_ONCE(feat->res, FEAT_SUPPORTED); + } else if (ret == 0) { + WRITE_ONCE(feat->res, FEAT_MISSING); + } else { + pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret); + WRITE_ONCE(feat->res, FEAT_MISSING); + } + } - return feat_supported(NULL, feat_id); + return READ_ONCE(feat->res) == FEAT_SUPPORTED; } static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) @@ -4831,7 +5211,6 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.map_flags = def->map_flags; create_attr.numa_node = map->numa_node; create_attr.map_extra = map->map_extra; - create_attr.token_fd = obj->token_fd; if (bpf_map__is_struct_ops(map)) create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; @@ -6667,7 +7046,6 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog load_attr.attach_btf_id = prog->attach_btf_id; load_attr.kern_version = kern_version; load_attr.prog_ifindex = prog->prog_ifindex; - load_attr.token_fd = obj->token_fd; /* specify func_info/line_info only if kernel supports them */ btf_fd = bpf_object__btf_fd(obj); @@ -7129,10 +7507,10 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, size_t obj_buf_sz, const struct bpf_object_open_opts *opts) { - const char *obj_name, *kconfig, *btf_tmp_path, *token_path; + const char *obj_name, *kconfig, *btf_tmp_path; struct bpf_object *obj; char tmp_name[64]; - int err, token_fd; + int err; char *log_buf; size_t log_size; __u32 log_level; @@ -7166,28 +7544,6 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, if (log_size && !log_buf) return ERR_PTR(-EINVAL); - token_path = OPTS_GET(opts, bpf_token_path, NULL); - token_fd = OPTS_GET(opts, bpf_token_fd, -1); - /* non-empty token path can't be combined with invalid token FD */ - if (token_path && token_path[0] != '\0' && token_fd < 0) - return ERR_PTR(-EINVAL); - /* empty token path can't be combined with valid token FD */ - if (token_path && token_path[0] == '\0' && token_fd > 0) - return ERR_PTR(-EINVAL); - /* if user didn't specify bpf_token_path/bpf_token_fd explicitly, - * check if LIBBPF_BPF_TOKEN_PATH envvar was set and treat it as - * bpf_token_path option - */ - if (token_fd == 0 && !token_path) - token_path = getenv("LIBBPF_BPF_TOKEN_PATH"); - /* empty token_path is equivalent to invalid token_fd */ - if (token_path && token_path[0] == '\0') { - token_path = NULL; - token_fd = -1; - } - if (token_path && strlen(token_path) >= PATH_MAX) - return ERR_PTR(-ENAMETOOLONG); - obj = bpf_object__new(path, obj_buf, obj_buf_sz, obj_name); if (IS_ERR(obj)) return obj; @@ -7196,19 +7552,6 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, obj->log_size = log_size; obj->log_level = log_level; - obj->token_fd = token_fd <= 0 ? token_fd : dup_good_fd(token_fd); - if (token_fd > 0 && obj->token_fd < 0) { - err = -errno; - goto out; - } - if (token_path) { - obj->token_path = strdup(token_path); - if (!obj->token_path) { - err = -ENOMEM; - goto out; - } - } - btf_tmp_path = OPTS_GET(opts, btf_custom_path, NULL); if (btf_tmp_path) { if (strlen(btf_tmp_path) >= PATH_MAX) { @@ -7719,8 +8062,7 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch if (obj->gen_loader) bpf_gen__init(obj->gen_loader, extra_log_level, obj->nr_programs, obj->nr_maps); - err = bpf_object_prepare_token(obj); - err = err ? : bpf_object__probe_loading(obj); + err = bpf_object__probe_loading(obj); err = err ? : bpf_object__load_vmlinux_btf(obj, false); err = err ? : bpf_object__resolve_externs(obj, obj->kconfig); err = err ? : bpf_object__sanitize_and_load_btf(obj); @@ -8257,11 +8599,6 @@ void bpf_object__close(struct bpf_object *obj) } zfree(&obj->programs); - zfree(&obj->feat_cache); - zfree(&obj->token_path); - if (obj->token_fd > 0) - close(obj->token_fd); - free(obj); } @@ -10275,7 +10612,7 @@ static const char *arch_specific_syscall_pfx(void) #endif } -int probe_kern_syscall_wrapper(int token_fd) +static int probe_kern_syscall_wrapper(void) { char syscall_name[64]; const char *ksys_pfx; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 916904bd2a7a..6cd9c501624f 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -177,45 +177,10 @@ struct bpf_object_open_opts { * logs through its print callback. */ __u32 kernel_log_level; - /* FD of a BPF token instantiated by user through bpf_token_create() - * API. BPF object will keep dup()'ed FD internally, so passed token - * FD can be closed after BPF object/skeleton open step. - * - * Setting bpf_token_fd to negative value disables libbpf's automatic - * attempt to create BPF token from default BPF FS mount point - * (/sys/fs/bpf), in case this default behavior is undesirable. - * - * If bpf_token_path and bpf_token_fd are not specified, libbpf will - * consult LIBBPF_BPF_TOKEN_PATH environment variable. If set, it will - * be taken as a value of bpf_token_path option and will force libbpf - * to either create BPF token from provided custom BPF FS path, or - * will disable implicit BPF token creation, if envvar value is an - * empty string. - * - * bpf_token_path and bpf_token_fd are mutually exclusive and only one - * of those options should be set. Either of them overrides - * LIBBPF_BPF_TOKEN_PATH envvar. - */ - int bpf_token_fd; - /* Path to BPF FS mount point to derive BPF token from. - * - * Created BPF token will be used for all bpf() syscall operations - * that accept BPF token (e.g., map creation, BTF and program loads, - * etc) automatically within instantiated BPF object. - * - * Setting bpf_token_path option to empty string disables libbpf's - * automatic attempt to create BPF token from default BPF FS mount - * point (/sys/fs/bpf), in case this default behavior is undesirable. - * - * bpf_token_path and bpf_token_fd are mutually exclusive and only one - * of those options should be set. Either of them overrides - * LIBBPF_BPF_TOKEN_PATH envvar. - */ - const char *bpf_token_path; size_t :0; }; -#define bpf_object_open_opts__last_field bpf_token_path +#define bpf_object_open_opts__last_field kernel_log_level /** * @brief **bpf_object__open()** creates a bpf_object by opening diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index df7657b65c47..91c5aef7dae7 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -401,7 +401,6 @@ LIBBPF_1.3.0 { bpf_program__attach_netkit; bpf_program__attach_tcx; bpf_program__attach_uprobe_multi; - bpf_token_create; ring__avail_data_size; ring__consume; ring__consumer_pos; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 4cda32298c49..b5d334754e5d 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -360,32 +360,15 @@ enum kern_feature_id { __FEAT_CNT, }; -enum kern_feature_result { - FEAT_UNKNOWN = 0, - FEAT_SUPPORTED = 1, - FEAT_MISSING = 2, -}; - -struct kern_feature_cache { - enum kern_feature_result res[__FEAT_CNT]; - int token_fd; -}; - -bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id); +int probe_memcg_account(void); bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id); - -int probe_kern_syscall_wrapper(int token_fd); -int probe_memcg_account(int token_fd); int bump_rlimit_memlock(void); int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz); int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz); int libbpf__load_raw_btf(const char *raw_types, size_t types_len, - const char *str_sec, size_t str_len, - int token_fd); -int btf_load_into_kernel(struct btf *btf, - char *log_buf, size_t log_sz, __u32 log_level, - int token_fd); + const char *str_sec, size_t str_len); +int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level); struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf); void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type, @@ -549,17 +532,6 @@ static inline bool is_ldimm64_insn(struct bpf_insn *insn) return insn->code == (BPF_LD | BPF_IMM | BPF_DW); } -/* Unconditionally dup FD, ensuring it doesn't use [0, 2] range. - * Original FD is not closed or altered in any other way. - * Preserves original FD value, if it's invalid (negative). - */ -static inline int dup_good_fd(int fd) -{ - if (fd < 0) - return fd; - return fcntl(fd, F_DUPFD_CLOEXEC, 3); -} - /* if fd is stdin, stdout, or stderr, dup to a fd greater than 2 * Takes ownership of the fd passed in, and closes it if calling * fcntl(fd, F_DUPFD_CLOEXEC, 3). @@ -571,7 +543,7 @@ static inline int ensure_good_fd(int fd) if (fd < 0) return fd; if (fd < 3) { - fd = dup_good_fd(fd); + fd = fcntl(fd, F_DUPFD_CLOEXEC, 3); saved_errno = errno; close(old_fd); errno = saved_errno; diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 8e7437006639..9c4db90b92b6 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -219,8 +219,7 @@ int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts) } int libbpf__load_raw_btf(const char *raw_types, size_t types_len, - const char *str_sec, size_t str_len, - int token_fd) + const char *str_sec, size_t str_len) { struct btf_header hdr = { .magic = BTF_MAGIC, @@ -230,7 +229,6 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len, .str_off = types_len, .str_len = str_len, }; - LIBBPF_OPTS(bpf_btf_load_opts, opts, .token_fd = token_fd); int btf_fd, btf_len; __u8 *raw_btf; @@ -243,7 +241,7 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len, memcpy(raw_btf + hdr.hdr_len, raw_types, hdr.type_len); memcpy(raw_btf + hdr.hdr_len + hdr.type_len, str_sec, hdr.str_len); - btf_fd = bpf_btf_load(raw_btf, btf_len, &opts); + btf_fd = bpf_btf_load(raw_btf, btf_len, NULL); free(raw_btf); return btf_fd; @@ -273,7 +271,7 @@ static int load_local_storage_btf(void) }; return libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs), 0); + strs, sizeof(strs)); } static int probe_map_create(enum bpf_map_type map_type) diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h index 626d7ffb03d6..a139334d57b6 100644 --- a/tools/lib/bpf/str_error.h +++ b/tools/lib/bpf/str_error.h @@ -2,8 +2,5 @@ #ifndef __LIBBPF_STR_ERROR_H #define __LIBBPF_STR_ERROR_H -#define STRERR_BUFSIZE 128 - char *libbpf_strerror_r(int err, char *dst, int len); - #endif /* __LIBBPF_STR_ERROR_H */ diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c index 4ed46ed58a7b..9f766ddd946a 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c @@ -30,8 +30,6 @@ void test_libbpf_probe_prog_types(void) if (prog_type == BPF_PROG_TYPE_UNSPEC) continue; - if (strcmp(prog_type_name, "__MAX_BPF_PROG_TYPE") == 0) - continue; if (!test__start_subtest(prog_type_name)) continue; @@ -70,8 +68,6 @@ void test_libbpf_probe_map_types(void) if (map_type == BPF_MAP_TYPE_UNSPEC) continue; - if (strcmp(map_type_name, "__MAX_BPF_MAP_TYPE") == 0) - continue; if (!test__start_subtest(map_type_name)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c index 62ea855ec4d0..eb34d612d6f8 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c @@ -132,9 +132,6 @@ static void test_libbpf_bpf_map_type_str(void) const char *map_type_str; char buf[256]; - if (map_type == __MAX_BPF_MAP_TYPE) - continue; - map_type_name = btf__str_by_offset(btf, e->name_off); map_type_str = libbpf_bpf_map_type_str(map_type); ASSERT_OK_PTR(map_type_str, map_type_name); @@ -189,9 +186,6 @@ static void test_libbpf_bpf_prog_type_str(void) const char *prog_type_str; char buf[256]; - if (prog_type == __MAX_BPF_PROG_TYPE) - continue; - prog_type_name = btf__str_by_offset(btf, e->name_off); prog_type_str = libbpf_bpf_prog_type_str(prog_type); ASSERT_OK_PTR(prog_type_str, prog_type_name); diff --git a/tools/testing/selftests/bpf/prog_tests/token.c b/tools/testing/selftests/bpf/prog_tests/token.c deleted file mode 100644 index b5dce630e0e1..000000000000 --- a/tools/testing/selftests/bpf/prog_tests/token.c +++ /dev/null @@ -1,1031 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ -#define _GNU_SOURCE -#include -#include -#include "cap_helpers.h" -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include "priv_map.skel.h" -#include "priv_prog.skel.h" -#include "dummy_st_ops_success.skel.h" - -static inline int sys_mount(const char *dev_name, const char *dir_name, - const char *type, unsigned long flags, - const void *data) -{ - return syscall(__NR_mount, dev_name, dir_name, type, flags, data); -} - -static inline int sys_fsopen(const char *fsname, unsigned flags) -{ - return syscall(__NR_fsopen, fsname, flags); -} - -static inline int sys_fspick(int dfd, const char *path, unsigned flags) -{ - return syscall(__NR_fspick, dfd, path, flags); -} - -static inline int sys_fsconfig(int fs_fd, unsigned cmd, const char *key, const void *val, int aux) -{ - return syscall(__NR_fsconfig, fs_fd, cmd, key, val, aux); -} - -static inline int sys_fsmount(int fs_fd, unsigned flags, unsigned ms_flags) -{ - return syscall(__NR_fsmount, fs_fd, flags, ms_flags); -} - -static inline int sys_move_mount(int from_dfd, const char *from_path, - int to_dfd, const char *to_path, - unsigned flags) -{ - return syscall(__NR_move_mount, from_dfd, from_path, to_dfd, to_path, flags); -} - -static int drop_priv_caps(__u64 *old_caps) -{ - return cap_disable_effective((1ULL << CAP_BPF) | - (1ULL << CAP_PERFMON) | - (1ULL << CAP_NET_ADMIN) | - (1ULL << CAP_SYS_ADMIN), old_caps); -} - -static int restore_priv_caps(__u64 old_caps) -{ - return cap_enable_effective(old_caps, NULL); -} - -static int set_delegate_mask(int fs_fd, const char *key, __u64 mask, const char *mask_str) -{ - char buf[32]; - int err; - - if (!mask_str) { - if (mask == ~0ULL) { - mask_str = "any"; - } else { - snprintf(buf, sizeof(buf), "0x%llx", (unsigned long long)mask); - mask_str = buf; - } - } - - err = sys_fsconfig(fs_fd, FSCONFIG_SET_STRING, key, - mask_str, 0); - if (err < 0) - err = -errno; - return err; -} - -#define zclose(fd) do { if (fd >= 0) close(fd); fd = -1; } while (0) - -struct bpffs_opts { - __u64 cmds; - __u64 maps; - __u64 progs; - __u64 attachs; - const char *cmds_str; - const char *maps_str; - const char *progs_str; - const char *attachs_str; -}; - -static int create_bpffs_fd(void) -{ - int fs_fd; - - /* create VFS context */ - fs_fd = sys_fsopen("bpf", 0); - ASSERT_GE(fs_fd, 0, "fs_fd"); - - return fs_fd; -} - -static int materialize_bpffs_fd(int fs_fd, struct bpffs_opts *opts) -{ - int mnt_fd, err; - - /* set up token delegation mount options */ - err = set_delegate_mask(fs_fd, "delegate_cmds", opts->cmds, opts->cmds_str); - if (!ASSERT_OK(err, "fs_cfg_cmds")) - return err; - err = set_delegate_mask(fs_fd, "delegate_maps", opts->maps, opts->maps_str); - if (!ASSERT_OK(err, "fs_cfg_maps")) - return err; - err = set_delegate_mask(fs_fd, "delegate_progs", opts->progs, opts->progs_str); - if (!ASSERT_OK(err, "fs_cfg_progs")) - return err; - err = set_delegate_mask(fs_fd, "delegate_attachs", opts->attachs, opts->attachs_str); - if (!ASSERT_OK(err, "fs_cfg_attachs")) - return err; - - /* instantiate FS object */ - err = sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); - if (err < 0) - return -errno; - - /* create O_PATH fd for detached mount */ - mnt_fd = sys_fsmount(fs_fd, 0, 0); - if (err < 0) - return -errno; - - return mnt_fd; -} - -/* send FD over Unix domain (AF_UNIX) socket */ -static int sendfd(int sockfd, int fd) -{ - struct msghdr msg = {}; - struct cmsghdr *cmsg; - int fds[1] = { fd }, err; - char iobuf[1]; - struct iovec io = { - .iov_base = iobuf, - .iov_len = sizeof(iobuf), - }; - union { - char buf[CMSG_SPACE(sizeof(fds))]; - struct cmsghdr align; - } u; - - msg.msg_iov = &io; - msg.msg_iovlen = 1; - msg.msg_control = u.buf; - msg.msg_controllen = sizeof(u.buf); - cmsg = CMSG_FIRSTHDR(&msg); - cmsg->cmsg_level = SOL_SOCKET; - cmsg->cmsg_type = SCM_RIGHTS; - cmsg->cmsg_len = CMSG_LEN(sizeof(fds)); - memcpy(CMSG_DATA(cmsg), fds, sizeof(fds)); - - err = sendmsg(sockfd, &msg, 0); - if (err < 0) - err = -errno; - if (!ASSERT_EQ(err, 1, "sendmsg")) - return -EINVAL; - - return 0; -} - -/* receive FD over Unix domain (AF_UNIX) socket */ -static int recvfd(int sockfd, int *fd) -{ - struct msghdr msg = {}; - struct cmsghdr *cmsg; - int fds[1], err; - char iobuf[1]; - struct iovec io = { - .iov_base = iobuf, - .iov_len = sizeof(iobuf), - }; - union { - char buf[CMSG_SPACE(sizeof(fds))]; - struct cmsghdr align; - } u; - - msg.msg_iov = &io; - msg.msg_iovlen = 1; - msg.msg_control = u.buf; - msg.msg_controllen = sizeof(u.buf); - - err = recvmsg(sockfd, &msg, 0); - if (err < 0) - err = -errno; - if (!ASSERT_EQ(err, 1, "recvmsg")) - return -EINVAL; - - cmsg = CMSG_FIRSTHDR(&msg); - if (!ASSERT_OK_PTR(cmsg, "cmsg_null") || - !ASSERT_EQ(cmsg->cmsg_len, CMSG_LEN(sizeof(fds)), "cmsg_len") || - !ASSERT_EQ(cmsg->cmsg_level, SOL_SOCKET, "cmsg_level") || - !ASSERT_EQ(cmsg->cmsg_type, SCM_RIGHTS, "cmsg_type")) - return -EINVAL; - - memcpy(fds, CMSG_DATA(cmsg), sizeof(fds)); - *fd = fds[0]; - - return 0; -} - -static ssize_t write_nointr(int fd, const void *buf, size_t count) -{ - ssize_t ret; - - do { - ret = write(fd, buf, count); - } while (ret < 0 && errno == EINTR); - - return ret; -} - -static int write_file(const char *path, const void *buf, size_t count) -{ - int fd; - ssize_t ret; - - fd = open(path, O_WRONLY | O_CLOEXEC | O_NOCTTY | O_NOFOLLOW); - if (fd < 0) - return -1; - - ret = write_nointr(fd, buf, count); - close(fd); - if (ret < 0 || (size_t)ret != count) - return -1; - - return 0; -} - -static int create_and_enter_userns(void) -{ - uid_t uid; - gid_t gid; - char map[100]; - - uid = getuid(); - gid = getgid(); - - if (unshare(CLONE_NEWUSER)) - return -1; - - if (write_file("/proc/self/setgroups", "deny", sizeof("deny") - 1) && - errno != ENOENT) - return -1; - - snprintf(map, sizeof(map), "0 %d 1", uid); - if (write_file("/proc/self/uid_map", map, strlen(map))) - return -1; - - - snprintf(map, sizeof(map), "0 %d 1", gid); - if (write_file("/proc/self/gid_map", map, strlen(map))) - return -1; - - if (setgid(0)) - return -1; - - if (setuid(0)) - return -1; - - return 0; -} - -typedef int (*child_callback_fn)(int); - -static void child(int sock_fd, struct bpffs_opts *opts, child_callback_fn callback) -{ - LIBBPF_OPTS(bpf_map_create_opts, map_opts); - int mnt_fd = -1, fs_fd = -1, err = 0, bpffs_fd = -1; - - /* setup userns with root mappings */ - err = create_and_enter_userns(); - if (!ASSERT_OK(err, "create_and_enter_userns")) - goto cleanup; - - /* setup mountns to allow creating BPF FS (fsopen("bpf")) from unpriv process */ - err = unshare(CLONE_NEWNS); - if (!ASSERT_OK(err, "create_mountns")) - goto cleanup; - - err = sys_mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0); - if (!ASSERT_OK(err, "remount_root")) - goto cleanup; - - fs_fd = create_bpffs_fd(); - if (!ASSERT_GE(fs_fd, 0, "create_bpffs_fd")) { - err = -EINVAL; - goto cleanup; - } - - /* ensure unprivileged child cannot set delegation options */ - err = set_delegate_mask(fs_fd, "delegate_cmds", 0x1, NULL); - ASSERT_EQ(err, -EPERM, "delegate_cmd_eperm"); - err = set_delegate_mask(fs_fd, "delegate_maps", 0x1, NULL); - ASSERT_EQ(err, -EPERM, "delegate_maps_eperm"); - err = set_delegate_mask(fs_fd, "delegate_progs", 0x1, NULL); - ASSERT_EQ(err, -EPERM, "delegate_progs_eperm"); - err = set_delegate_mask(fs_fd, "delegate_attachs", 0x1, NULL); - ASSERT_EQ(err, -EPERM, "delegate_attachs_eperm"); - - /* pass BPF FS context object to parent */ - err = sendfd(sock_fd, fs_fd); - if (!ASSERT_OK(err, "send_fs_fd")) - goto cleanup; - zclose(fs_fd); - - /* avoid mucking around with mount namespaces and mounting at - * well-known path, just get detach-mounted BPF FS fd back from parent - */ - err = recvfd(sock_fd, &mnt_fd); - if (!ASSERT_OK(err, "recv_mnt_fd")) - goto cleanup; - - /* try to fspick() BPF FS and try to add some delegation options */ - fs_fd = sys_fspick(mnt_fd, "", FSPICK_EMPTY_PATH); - if (!ASSERT_GE(fs_fd, 0, "bpffs_fspick")) { - err = -EINVAL; - goto cleanup; - } - - /* ensure unprivileged child cannot reconfigure to set delegation options */ - err = set_delegate_mask(fs_fd, "delegate_cmds", 0, "any"); - if (!ASSERT_EQ(err, -EPERM, "delegate_cmd_eperm_reconfig")) { - err = -EINVAL; - goto cleanup; - } - err = set_delegate_mask(fs_fd, "delegate_maps", 0, "any"); - if (!ASSERT_EQ(err, -EPERM, "delegate_maps_eperm_reconfig")) { - err = -EINVAL; - goto cleanup; - } - err = set_delegate_mask(fs_fd, "delegate_progs", 0, "any"); - if (!ASSERT_EQ(err, -EPERM, "delegate_progs_eperm_reconfig")) { - err = -EINVAL; - goto cleanup; - } - err = set_delegate_mask(fs_fd, "delegate_attachs", 0, "any"); - if (!ASSERT_EQ(err, -EPERM, "delegate_attachs_eperm_reconfig")) { - err = -EINVAL; - goto cleanup; - } - zclose(fs_fd); - - bpffs_fd = openat(mnt_fd, ".", 0, O_RDWR); - if (!ASSERT_GE(bpffs_fd, 0, "bpffs_open")) { - err = -EINVAL; - goto cleanup; - } - - /* do custom test logic with customly set up BPF FS instance */ - err = callback(bpffs_fd); - if (!ASSERT_OK(err, "test_callback")) - goto cleanup; - - err = 0; -cleanup: - zclose(sock_fd); - zclose(mnt_fd); - zclose(fs_fd); - zclose(bpffs_fd); - - exit(-err); -} - -static int wait_for_pid(pid_t pid) -{ - int status, ret; - -again: - ret = waitpid(pid, &status, 0); - if (ret == -1) { - if (errno == EINTR) - goto again; - - return -1; - } - - if (!WIFEXITED(status)) - return -1; - - return WEXITSTATUS(status); -} - -static void parent(int child_pid, struct bpffs_opts *bpffs_opts, int sock_fd) -{ - int fs_fd = -1, mnt_fd = -1, err; - - err = recvfd(sock_fd, &fs_fd); - if (!ASSERT_OK(err, "recv_bpffs_fd")) - goto cleanup; - - mnt_fd = materialize_bpffs_fd(fs_fd, bpffs_opts); - if (!ASSERT_GE(mnt_fd, 0, "materialize_bpffs_fd")) { - err = -EINVAL; - goto cleanup; - } - zclose(fs_fd); - - /* pass BPF FS context object to parent */ - err = sendfd(sock_fd, mnt_fd); - if (!ASSERT_OK(err, "send_mnt_fd")) - goto cleanup; - zclose(mnt_fd); - - err = wait_for_pid(child_pid); - ASSERT_OK(err, "waitpid_child"); - -cleanup: - zclose(sock_fd); - zclose(fs_fd); - zclose(mnt_fd); - - if (child_pid > 0) - (void)kill(child_pid, SIGKILL); -} - -static void subtest_userns(struct bpffs_opts *bpffs_opts, child_callback_fn cb) -{ - int sock_fds[2] = { -1, -1 }; - int child_pid = 0, err; - - err = socketpair(AF_UNIX, SOCK_STREAM, 0, sock_fds); - if (!ASSERT_OK(err, "socketpair")) - goto cleanup; - - child_pid = fork(); - if (!ASSERT_GE(child_pid, 0, "fork")) - goto cleanup; - - if (child_pid == 0) { - zclose(sock_fds[0]); - return child(sock_fds[1], bpffs_opts, cb); - - } else { - zclose(sock_fds[1]); - return parent(child_pid, bpffs_opts, sock_fds[0]); - } - -cleanup: - zclose(sock_fds[0]); - zclose(sock_fds[1]); - if (child_pid > 0) - (void)kill(child_pid, SIGKILL); -} - -static int userns_map_create(int mnt_fd) -{ - LIBBPF_OPTS(bpf_map_create_opts, map_opts); - int err, token_fd = -1, map_fd = -1; - __u64 old_caps = 0; - - /* create BPF token from BPF FS mount */ - token_fd = bpf_token_create(mnt_fd, NULL); - if (!ASSERT_GT(token_fd, 0, "token_create")) { - err = -EINVAL; - goto cleanup; - } - - /* while inside non-init userns, we need both a BPF token *and* - * CAP_BPF inside current userns to create privileged map; let's test - * that neither BPF token alone nor namespaced CAP_BPF is sufficient - */ - err = drop_priv_caps(&old_caps); - if (!ASSERT_OK(err, "drop_caps")) - goto cleanup; - - /* no token, no CAP_BPF -> fail */ - map_opts.token_fd = 0; - map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "wo_token_wo_bpf", 0, 8, 1, &map_opts); - if (!ASSERT_LT(map_fd, 0, "stack_map_wo_token_wo_cap_bpf_should_fail")) { - err = -EINVAL; - goto cleanup; - } - - /* token without CAP_BPF -> fail */ - map_opts.token_fd = token_fd; - map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "w_token_wo_bpf", 0, 8, 1, &map_opts); - if (!ASSERT_LT(map_fd, 0, "stack_map_w_token_wo_cap_bpf_should_fail")) { - err = -EINVAL; - goto cleanup; - } - - /* get back effective local CAP_BPF (and CAP_SYS_ADMIN) */ - err = restore_priv_caps(old_caps); - if (!ASSERT_OK(err, "restore_caps")) - goto cleanup; - - /* CAP_BPF without token -> fail */ - map_opts.token_fd = 0; - map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "wo_token_w_bpf", 0, 8, 1, &map_opts); - if (!ASSERT_LT(map_fd, 0, "stack_map_wo_token_w_cap_bpf_should_fail")) { - err = -EINVAL; - goto cleanup; - } - - /* finally, namespaced CAP_BPF + token -> success */ - map_opts.token_fd = token_fd; - map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "w_token_w_bpf", 0, 8, 1, &map_opts); - if (!ASSERT_GT(map_fd, 0, "stack_map_w_token_w_cap_bpf")) { - err = -EINVAL; - goto cleanup; - } - -cleanup: - zclose(token_fd); - zclose(map_fd); - return err; -} - -static int userns_btf_load(int mnt_fd) -{ - LIBBPF_OPTS(bpf_btf_load_opts, btf_opts); - int err, token_fd = -1, btf_fd = -1; - const void *raw_btf_data; - struct btf *btf = NULL; - __u32 raw_btf_size; - __u64 old_caps = 0; - - /* create BPF token from BPF FS mount */ - token_fd = bpf_token_create(mnt_fd, NULL); - if (!ASSERT_GT(token_fd, 0, "token_create")) { - err = -EINVAL; - goto cleanup; - } - - /* while inside non-init userns, we need both a BPF token *and* - * CAP_BPF inside current userns to create privileged map; let's test - * that neither BPF token alone nor namespaced CAP_BPF is sufficient - */ - err = drop_priv_caps(&old_caps); - if (!ASSERT_OK(err, "drop_caps")) - goto cleanup; - - /* setup a trivial BTF data to load to the kernel */ - btf = btf__new_empty(); - if (!ASSERT_OK_PTR(btf, "empty_btf")) - goto cleanup; - - ASSERT_GT(btf__add_int(btf, "int", 4, 0), 0, "int_type"); - - raw_btf_data = btf__raw_data(btf, &raw_btf_size); - if (!ASSERT_OK_PTR(raw_btf_data, "raw_btf_data")) - goto cleanup; - - /* no token + no CAP_BPF -> failure */ - btf_opts.token_fd = 0; - btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts); - if (!ASSERT_LT(btf_fd, 0, "no_token_no_cap_should_fail")) - goto cleanup; - - /* token + no CAP_BPF -> failure */ - btf_opts.token_fd = token_fd; - btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts); - if (!ASSERT_LT(btf_fd, 0, "token_no_cap_should_fail")) - goto cleanup; - - /* get back effective local CAP_BPF (and CAP_SYS_ADMIN) */ - err = restore_priv_caps(old_caps); - if (!ASSERT_OK(err, "restore_caps")) - goto cleanup; - - /* token + CAP_BPF -> success */ - btf_opts.token_fd = token_fd; - btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts); - if (!ASSERT_GT(btf_fd, 0, "token_and_cap_success")) - goto cleanup; - - err = 0; -cleanup: - btf__free(btf); - zclose(btf_fd); - zclose(token_fd); - return err; -} - -static int userns_prog_load(int mnt_fd) -{ - LIBBPF_OPTS(bpf_prog_load_opts, prog_opts); - int err, token_fd = -1, prog_fd = -1; - struct bpf_insn insns[] = { - /* bpf_jiffies64() requires CAP_BPF */ - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_jiffies64), - /* bpf_get_current_task() requires CAP_PERFMON */ - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_current_task), - /* r0 = 0; exit; */ - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - size_t insn_cnt = ARRAY_SIZE(insns); - __u64 old_caps = 0; - - /* create BPF token from BPF FS mount */ - token_fd = bpf_token_create(mnt_fd, NULL); - if (!ASSERT_GT(token_fd, 0, "token_create")) { - err = -EINVAL; - goto cleanup; - } - - /* validate we can successfully load BPF program with token; this - * being XDP program (CAP_NET_ADMIN) using bpf_jiffies64() (CAP_BPF) - * and bpf_get_current_task() (CAP_PERFMON) helpers validates we have - * BPF token wired properly in a bunch of places in the kernel - */ - prog_opts.token_fd = token_fd; - prog_opts.expected_attach_type = BPF_XDP; - prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", - insns, insn_cnt, &prog_opts); - if (!ASSERT_GT(prog_fd, 0, "prog_fd")) { - err = -EPERM; - goto cleanup; - } - - /* no token + caps -> failure */ - prog_opts.token_fd = 0; - prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", - insns, insn_cnt, &prog_opts); - if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) { - err = -EPERM; - goto cleanup; - } - - err = drop_priv_caps(&old_caps); - if (!ASSERT_OK(err, "drop_caps")) - goto cleanup; - - /* no caps + token -> failure */ - prog_opts.token_fd = token_fd; - prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", - insns, insn_cnt, &prog_opts); - if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) { - err = -EPERM; - goto cleanup; - } - - /* no caps + no token -> definitely a failure */ - prog_opts.token_fd = 0; - prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", - insns, insn_cnt, &prog_opts); - if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) { - err = -EPERM; - goto cleanup; - } - - err = 0; -cleanup: - zclose(prog_fd); - zclose(token_fd); - return err; -} - -static int userns_obj_priv_map(int mnt_fd) -{ - LIBBPF_OPTS(bpf_object_open_opts, opts); - char buf[256]; - struct priv_map *skel; - int err, token_fd; - - skel = priv_map__open_and_load(); - if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) { - priv_map__destroy(skel); - return -EINVAL; - } - - /* use bpf_token_path to provide BPF FS path */ - snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd); - opts.bpf_token_path = buf; - skel = priv_map__open_opts(&opts); - if (!ASSERT_OK_PTR(skel, "obj_token_path_open")) - return -EINVAL; - - err = priv_map__load(skel); - priv_map__destroy(skel); - if (!ASSERT_OK(err, "obj_token_path_load")) - return -EINVAL; - - /* create token and pass it through bpf_token_fd */ - token_fd = bpf_token_create(mnt_fd, NULL); - if (!ASSERT_GT(token_fd, 0, "create_token")) - return -EINVAL; - - opts.bpf_token_path = NULL; - opts.bpf_token_fd = token_fd; - skel = priv_map__open_opts(&opts); - if (!ASSERT_OK_PTR(skel, "obj_token_fd_open")) - return -EINVAL; - - /* we can close our token FD, bpf_object owns dup()'ed FD now */ - close(token_fd); - - err = priv_map__load(skel); - priv_map__destroy(skel); - if (!ASSERT_OK(err, "obj_token_fd_load")) - return -EINVAL; - - return 0; -} - -static int userns_obj_priv_prog(int mnt_fd) -{ - LIBBPF_OPTS(bpf_object_open_opts, opts); - char buf[256]; - struct priv_prog *skel; - int err; - - skel = priv_prog__open_and_load(); - if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) { - priv_prog__destroy(skel); - return -EINVAL; - } - - /* use bpf_token_path to provide BPF FS path */ - snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd); - opts.bpf_token_path = buf; - skel = priv_prog__open_opts(&opts); - if (!ASSERT_OK_PTR(skel, "obj_token_path_open")) - return -EINVAL; - - err = priv_prog__load(skel); - priv_prog__destroy(skel); - if (!ASSERT_OK(err, "obj_token_path_load")) - return -EINVAL; - - return 0; -} - -/* this test is called with BPF FS that doesn't delegate BPF_BTF_LOAD command, - * which should cause struct_ops application to fail, as BTF won't be uploaded - * into the kernel, even if STRUCT_OPS programs themselves are allowed - */ -static int validate_struct_ops_load(int mnt_fd, bool expect_success) -{ - LIBBPF_OPTS(bpf_object_open_opts, opts); - char buf[256]; - struct dummy_st_ops_success *skel; - int err; - - snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd); - opts.bpf_token_path = buf; - skel = dummy_st_ops_success__open_opts(&opts); - if (!ASSERT_OK_PTR(skel, "obj_token_path_open")) - return -EINVAL; - - err = dummy_st_ops_success__load(skel); - dummy_st_ops_success__destroy(skel); - if (expect_success) { - if (!ASSERT_OK(err, "obj_token_path_load")) - return -EINVAL; - } else /* expect failure */ { - if (!ASSERT_ERR(err, "obj_token_path_load")) - return -EINVAL; - } - - return 0; -} - -static int userns_obj_priv_btf_fail(int mnt_fd) -{ - return validate_struct_ops_load(mnt_fd, false /* should fail */); -} - -static int userns_obj_priv_btf_success(int mnt_fd) -{ - return validate_struct_ops_load(mnt_fd, true /* should succeed */); -} - -#define TOKEN_ENVVAR "LIBBPF_BPF_TOKEN_PATH" -#define TOKEN_BPFFS_CUSTOM "/bpf-token-fs" - -static int userns_obj_priv_implicit_token(int mnt_fd) -{ - LIBBPF_OPTS(bpf_object_open_opts, opts); - struct dummy_st_ops_success *skel; - int err; - - /* before we mount BPF FS with token delegation, struct_ops skeleton - * should fail to load - */ - skel = dummy_st_ops_success__open_and_load(); - if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) { - dummy_st_ops_success__destroy(skel); - return -EINVAL; - } - - /* mount custom BPF FS over /sys/fs/bpf so that libbpf can create BPF - * token automatically and implicitly - */ - err = sys_move_mount(mnt_fd, "", AT_FDCWD, "/sys/fs/bpf", MOVE_MOUNT_F_EMPTY_PATH); - if (!ASSERT_OK(err, "move_mount_bpffs")) - return -EINVAL; - - /* disable implicit BPF token creation by setting - * LIBBPF_BPF_TOKEN_PATH envvar to empty value, load should fail - */ - err = setenv(TOKEN_ENVVAR, "", 1 /*overwrite*/); - if (!ASSERT_OK(err, "setenv_token_path")) - return -EINVAL; - skel = dummy_st_ops_success__open_and_load(); - if (!ASSERT_ERR_PTR(skel, "obj_token_envvar_disabled_load")) { - unsetenv(TOKEN_ENVVAR); - dummy_st_ops_success__destroy(skel); - return -EINVAL; - } - unsetenv(TOKEN_ENVVAR); - - /* now the same struct_ops skeleton should succeed thanks to libppf - * creating BPF token from /sys/fs/bpf mount point - */ - skel = dummy_st_ops_success__open_and_load(); - if (!ASSERT_OK_PTR(skel, "obj_implicit_token_load")) - return -EINVAL; - - dummy_st_ops_success__destroy(skel); - - /* now disable implicit token through empty bpf_token_path, should fail */ - opts.bpf_token_path = ""; - skel = dummy_st_ops_success__open_opts(&opts); - if (!ASSERT_OK_PTR(skel, "obj_empty_token_path_open")) - return -EINVAL; - - err = dummy_st_ops_success__load(skel); - dummy_st_ops_success__destroy(skel); - if (!ASSERT_ERR(err, "obj_empty_token_path_load")) - return -EINVAL; - - /* now disable implicit token through negative bpf_token_fd, should fail */ - opts.bpf_token_path = NULL; - opts.bpf_token_fd = -1; - skel = dummy_st_ops_success__open_opts(&opts); - if (!ASSERT_OK_PTR(skel, "obj_neg_token_fd_open")) - return -EINVAL; - - err = dummy_st_ops_success__load(skel); - dummy_st_ops_success__destroy(skel); - if (!ASSERT_ERR(err, "obj_neg_token_fd_load")) - return -EINVAL; - - return 0; -} - -static int userns_obj_priv_implicit_token_envvar(int mnt_fd) -{ - LIBBPF_OPTS(bpf_object_open_opts, opts); - struct dummy_st_ops_success *skel; - int err; - - /* before we mount BPF FS with token delegation, struct_ops skeleton - * should fail to load - */ - skel = dummy_st_ops_success__open_and_load(); - if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) { - dummy_st_ops_success__destroy(skel); - return -EINVAL; - } - - /* mount custom BPF FS over custom location, so libbpf can't create - * BPF token implicitly, unless pointed to it through - * LIBBPF_BPF_TOKEN_PATH envvar - */ - rmdir(TOKEN_BPFFS_CUSTOM); - if (!ASSERT_OK(mkdir(TOKEN_BPFFS_CUSTOM, 0777), "mkdir_bpffs_custom")) - goto err_out; - err = sys_move_mount(mnt_fd, "", AT_FDCWD, TOKEN_BPFFS_CUSTOM, MOVE_MOUNT_F_EMPTY_PATH); - if (!ASSERT_OK(err, "move_mount_bpffs")) - goto err_out; - - /* even though we have BPF FS with delegation, it's not at default - * /sys/fs/bpf location, so we still fail to load until envvar is set up - */ - skel = dummy_st_ops_success__open_and_load(); - if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load2")) { - dummy_st_ops_success__destroy(skel); - goto err_out; - } - - err = setenv(TOKEN_ENVVAR, TOKEN_BPFFS_CUSTOM, 1 /*overwrite*/); - if (!ASSERT_OK(err, "setenv_token_path")) - goto err_out; - - /* now the same struct_ops skeleton should succeed thanks to libppf - * creating BPF token from custom mount point - */ - skel = dummy_st_ops_success__open_and_load(); - if (!ASSERT_OK_PTR(skel, "obj_implicit_token_load")) - goto err_out; - - dummy_st_ops_success__destroy(skel); - - /* now disable implicit token through empty bpf_token_path, envvar - * will be ignored, should fail - */ - opts.bpf_token_path = ""; - skel = dummy_st_ops_success__open_opts(&opts); - if (!ASSERT_OK_PTR(skel, "obj_empty_token_path_open")) - goto err_out; - - err = dummy_st_ops_success__load(skel); - dummy_st_ops_success__destroy(skel); - if (!ASSERT_ERR(err, "obj_empty_token_path_load")) - goto err_out; - - /* now disable implicit token through negative bpf_token_fd, envvar - * will be ignored, should fail - */ - opts.bpf_token_path = NULL; - opts.bpf_token_fd = -1; - skel = dummy_st_ops_success__open_opts(&opts); - if (!ASSERT_OK_PTR(skel, "obj_neg_token_fd_open")) - goto err_out; - - err = dummy_st_ops_success__load(skel); - dummy_st_ops_success__destroy(skel); - if (!ASSERT_ERR(err, "obj_neg_token_fd_load")) - goto err_out; - - rmdir(TOKEN_BPFFS_CUSTOM); - unsetenv(TOKEN_ENVVAR); - return 0; -err_out: - rmdir(TOKEN_BPFFS_CUSTOM); - unsetenv(TOKEN_ENVVAR); - return -EINVAL; -} - -#define bit(n) (1ULL << (n)) - -void test_token(void) -{ - if (test__start_subtest("map_token")) { - struct bpffs_opts opts = { - .cmds_str = "map_create", - .maps_str = "stack", - }; - - subtest_userns(&opts, userns_map_create); - } - if (test__start_subtest("btf_token")) { - struct bpffs_opts opts = { - .cmds = 1ULL << BPF_BTF_LOAD, - }; - - subtest_userns(&opts, userns_btf_load); - } - if (test__start_subtest("prog_token")) { - struct bpffs_opts opts = { - .cmds_str = "PROG_LOAD", - .progs_str = "XDP", - .attachs_str = "xdp", - }; - - subtest_userns(&opts, userns_prog_load); - } - if (test__start_subtest("obj_priv_map")) { - struct bpffs_opts opts = { - .cmds = bit(BPF_MAP_CREATE), - .maps = bit(BPF_MAP_TYPE_QUEUE), - }; - - subtest_userns(&opts, userns_obj_priv_map); - } - if (test__start_subtest("obj_priv_prog")) { - struct bpffs_opts opts = { - .cmds = bit(BPF_PROG_LOAD), - .progs = bit(BPF_PROG_TYPE_KPROBE), - .attachs = ~0ULL, - }; - - subtest_userns(&opts, userns_obj_priv_prog); - } - if (test__start_subtest("obj_priv_btf_fail")) { - struct bpffs_opts opts = { - /* disallow BTF loading */ - .cmds = bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD), - .maps = bit(BPF_MAP_TYPE_STRUCT_OPS), - .progs = bit(BPF_PROG_TYPE_STRUCT_OPS), - .attachs = ~0ULL, - }; - - subtest_userns(&opts, userns_obj_priv_btf_fail); - } - if (test__start_subtest("obj_priv_btf_success")) { - struct bpffs_opts opts = { - /* allow BTF loading */ - .cmds = bit(BPF_BTF_LOAD) | bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD), - .maps = bit(BPF_MAP_TYPE_STRUCT_OPS), - .progs = bit(BPF_PROG_TYPE_STRUCT_OPS), - .attachs = ~0ULL, - }; - - subtest_userns(&opts, userns_obj_priv_btf_success); - } - if (test__start_subtest("obj_priv_implicit_token")) { - struct bpffs_opts opts = { - /* allow BTF loading */ - .cmds = bit(BPF_BTF_LOAD) | bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD), - .maps = bit(BPF_MAP_TYPE_STRUCT_OPS), - .progs = bit(BPF_PROG_TYPE_STRUCT_OPS), - .attachs = ~0ULL, - }; - - subtest_userns(&opts, userns_obj_priv_implicit_token); - } - if (test__start_subtest("obj_priv_implicit_token_envvar")) { - struct bpffs_opts opts = { - /* allow BTF loading */ - .cmds = bit(BPF_BTF_LOAD) | bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD), - .maps = bit(BPF_MAP_TYPE_STRUCT_OPS), - .progs = bit(BPF_PROG_TYPE_STRUCT_OPS), - .attachs = ~0ULL, - }; - - subtest_userns(&opts, userns_obj_priv_implicit_token_envvar); - } -} diff --git a/tools/testing/selftests/bpf/progs/priv_map.c b/tools/testing/selftests/bpf/progs/priv_map.c deleted file mode 100644 index 9085be50f03b..000000000000 --- a/tools/testing/selftests/bpf/progs/priv_map.c +++ /dev/null @@ -1,13 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ - -#include "vmlinux.h" -#include - -char _license[] SEC("license") = "GPL"; - -struct { - __uint(type, BPF_MAP_TYPE_QUEUE); - __uint(max_entries, 1); - __type(value, __u32); -} priv_map SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/priv_prog.c b/tools/testing/selftests/bpf/progs/priv_prog.c deleted file mode 100644 index 3c7b2b618c8a..000000000000 --- a/tools/testing/selftests/bpf/progs/priv_prog.c +++ /dev/null @@ -1,13 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ - -#include "vmlinux.h" -#include - -char _license[] SEC("license") = "GPL"; - -SEC("kprobe") -int kprobe_prog(void *ctx) -{ - return 1; -} -- cgit From 849d18e27be9a1253f2318cb4549cc857219d991 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 14 Dec 2023 14:21:05 -0800 Subject: md: Remove deprecated CONFIG_MD_LINEAR md-linear has been marked as deprecated for 2.5 years. Remove it. Cc: Christoph Hellwig Cc: Jens Axboe Cc: Neil Brown Cc: Guoqing Jiang Cc: Mateusz Grzonka Cc: Jes Sorensen Signed-off-by: Song Liu Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Link: https://lore.kernel.org/r/20231214222107.2016042-2-song@kernel.org --- drivers/md/Kconfig | 13 -- drivers/md/Makefile | 6 +- drivers/md/md-autodetect.c | 8 +- drivers/md/md-linear.c | 318 ----------------------------------------- drivers/md/md.c | 2 +- include/uapi/linux/raid/md_p.h | 8 +- include/uapi/linux/raid/md_u.h | 7 +- 7 files changed, 8 insertions(+), 354 deletions(-) delete mode 100644 drivers/md/md-linear.c (limited to 'include/uapi/linux') diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 2a8b081bce7d..0c721e0e5921 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -61,19 +61,6 @@ config MD_BITMAP_FILE various kernel APIs and can only work with files on a file system not actually sitting on the MD device. -config MD_LINEAR - tristate "Linear (append) mode (deprecated)" - depends on BLK_DEV_MD - help - If you say Y here, then your multiple devices driver will be able to - use the so-called linear mode, i.e. it will combine the hard disk - partitions by simply appending one to the other. - - To compile this as a module, choose M here: the module - will be called linear. - - If unsure, say Y. - config MD_RAID0 tristate "RAID-0 (striping) mode" depends on BLK_DEV_MD diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 84291e38dca8..c72f76cf7b63 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -29,16 +29,14 @@ dm-zoned-y += dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o md-mod-y += md.o md-bitmap.o raid456-y += raid5.o raid5-cache.o raid5-ppl.o -linear-y += md-linear.o multipath-y += md-multipath.o faulty-y += md-faulty.o # Note: link order is important. All raid personalities -# and must come before md.o, as they each initialise -# themselves, and md.o may use the personalities when it +# and must come before md.o, as they each initialise +# themselves, and md.o may use the personalities when it # auto-initialised. -obj-$(CONFIG_MD_LINEAR) += linear.o obj-$(CONFIG_MD_RAID0) += raid0.o obj-$(CONFIG_MD_RAID1) += raid1.o obj-$(CONFIG_MD_RAID10) += raid10.o diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c index 4b80165afd23..b2a00f213c2c 100644 --- a/drivers/md/md-autodetect.c +++ b/drivers/md/md-autodetect.c @@ -49,7 +49,6 @@ static int md_setup_ents __initdata; * instead of just one. -- KTK * 18May2000: Added support for persistent-superblock arrays: * md=n,0,factor,fault,device-list uses RAID0 for device n - * md=n,-1,factor,fault,device-list uses LINEAR for device n * md=n,device-list reads a RAID superblock from the devices * elements in device-list are read by name_to_kdev_t so can be * a hex number or something like /dev/hda1 /dev/sdb @@ -88,7 +87,7 @@ static int __init md_setup(char *str) md_setup_ents++; switch (get_option(&str, &level)) { /* RAID level */ case 2: /* could be 0 or -1.. */ - if (level == 0 || level == LEVEL_LINEAR) { + if (level == 0) { if (get_option(&str, &factor) != 2 || /* Chunk Size */ get_option(&str, &fault) != 2) { printk(KERN_WARNING "md: Too few arguments supplied to md=.\n"); @@ -96,10 +95,7 @@ static int __init md_setup(char *str) } md_setup_args[ent].level = level; md_setup_args[ent].chunk = 1 << (factor+12); - if (level == LEVEL_LINEAR) - pername = "linear"; - else - pername = "raid0"; + pername = "raid0"; break; } fallthrough; diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c deleted file mode 100644 index 8eca7693b793..000000000000 --- a/drivers/md/md-linear.c +++ /dev/null @@ -1,318 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - linear.c : Multiple Devices driver for Linux - Copyright (C) 1994-96 Marc ZYNGIER - or - - - Linear mode management functions. - -*/ - -#include -#include -#include -#include -#include -#include -#include "md.h" -#include "md-linear.h" - -/* - * find which device holds a particular offset - */ -static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector) -{ - int lo, mid, hi; - struct linear_conf *conf; - - lo = 0; - hi = mddev->raid_disks - 1; - conf = mddev->private; - - /* - * Binary Search - */ - - while (hi > lo) { - - mid = (hi + lo) / 2; - if (sector < conf->disks[mid].end_sector) - hi = mid; - else - lo = mid + 1; - } - - return conf->disks + lo; -} - -static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disks) -{ - struct linear_conf *conf; - sector_t array_sectors; - - conf = mddev->private; - WARN_ONCE(sectors || raid_disks, - "%s does not support generic reshape\n", __func__); - array_sectors = conf->array_sectors; - - return array_sectors; -} - -static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks) -{ - struct linear_conf *conf; - struct md_rdev *rdev; - int i, cnt; - - conf = kzalloc(struct_size(conf, disks, raid_disks), GFP_KERNEL); - if (!conf) - return NULL; - - /* - * conf->raid_disks is copy of mddev->raid_disks. The reason to - * keep a copy of mddev->raid_disks in struct linear_conf is, - * mddev->raid_disks may not be consistent with pointers number of - * conf->disks[] when it is updated in linear_add() and used to - * iterate old conf->disks[] earray in linear_congested(). - * Here conf->raid_disks is always consitent with number of - * pointers in conf->disks[] array, and mddev->private is updated - * with rcu_assign_pointer() in linear_addr(), such race can be - * avoided. - */ - conf->raid_disks = raid_disks; - - cnt = 0; - conf->array_sectors = 0; - - rdev_for_each(rdev, mddev) { - int j = rdev->raid_disk; - struct dev_info *disk = conf->disks + j; - sector_t sectors; - - if (j < 0 || j >= raid_disks || disk->rdev) { - pr_warn("md/linear:%s: disk numbering problem. Aborting!\n", - mdname(mddev)); - goto out; - } - - disk->rdev = rdev; - if (mddev->chunk_sectors) { - sectors = rdev->sectors; - sector_div(sectors, mddev->chunk_sectors); - rdev->sectors = sectors * mddev->chunk_sectors; - } - - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - - conf->array_sectors += rdev->sectors; - cnt++; - } - if (cnt != raid_disks) { - pr_warn("md/linear:%s: not enough drives present. Aborting!\n", - mdname(mddev)); - goto out; - } - - /* - * Here we calculate the device offsets. - */ - conf->disks[0].end_sector = conf->disks[0].rdev->sectors; - - for (i = 1; i < raid_disks; i++) - conf->disks[i].end_sector = - conf->disks[i-1].end_sector + - conf->disks[i].rdev->sectors; - - return conf; - -out: - kfree(conf); - return NULL; -} - -static int linear_run (struct mddev *mddev) -{ - struct linear_conf *conf; - int ret; - - if (md_check_no_bitmap(mddev)) - return -EINVAL; - conf = linear_conf(mddev, mddev->raid_disks); - - if (!conf) - return 1; - mddev->private = conf; - md_set_array_sectors(mddev, linear_size(mddev, 0, 0)); - - ret = md_integrity_register(mddev); - if (ret) { - kfree(conf); - mddev->private = NULL; - } - return ret; -} - -static int linear_add(struct mddev *mddev, struct md_rdev *rdev) -{ - /* Adding a drive to a linear array allows the array to grow. - * It is permitted if the new drive has a matching superblock - * already on it, with raid_disk equal to raid_disks. - * It is achieved by creating a new linear_private_data structure - * and swapping it in in-place of the current one. - * The current one is never freed until the array is stopped. - * This avoids races. - */ - struct linear_conf *newconf, *oldconf; - - if (rdev->saved_raid_disk != mddev->raid_disks) - return -EINVAL; - - rdev->raid_disk = rdev->saved_raid_disk; - rdev->saved_raid_disk = -1; - - newconf = linear_conf(mddev,mddev->raid_disks+1); - - if (!newconf) - return -ENOMEM; - - /* newconf->raid_disks already keeps a copy of * the increased - * value of mddev->raid_disks, WARN_ONCE() is just used to make - * sure of this. It is possible that oldconf is still referenced - * in linear_congested(), therefore kfree_rcu() is used to free - * oldconf until no one uses it anymore. - */ - oldconf = rcu_dereference_protected(mddev->private, - lockdep_is_held(&mddev->reconfig_mutex)); - mddev->raid_disks++; - WARN_ONCE(mddev->raid_disks != newconf->raid_disks, - "copied raid_disks doesn't match mddev->raid_disks"); - rcu_assign_pointer(mddev->private, newconf); - md_set_array_sectors(mddev, linear_size(mddev, 0, 0)); - set_capacity_and_notify(mddev->gendisk, mddev->array_sectors); - kfree_rcu(oldconf, rcu); - return 0; -} - -static void linear_free(struct mddev *mddev, void *priv) -{ - struct linear_conf *conf = priv; - - kfree(conf); -} - -static bool linear_make_request(struct mddev *mddev, struct bio *bio) -{ - struct dev_info *tmp_dev; - sector_t start_sector, end_sector, data_offset; - sector_t bio_sector = bio->bi_iter.bi_sector; - - if (unlikely(bio->bi_opf & REQ_PREFLUSH) - && md_flush_request(mddev, bio)) - return true; - - tmp_dev = which_dev(mddev, bio_sector); - start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors; - end_sector = tmp_dev->end_sector; - data_offset = tmp_dev->rdev->data_offset; - - if (unlikely(bio_sector >= end_sector || - bio_sector < start_sector)) - goto out_of_bounds; - - if (unlikely(is_rdev_broken(tmp_dev->rdev))) { - md_error(mddev, tmp_dev->rdev); - bio_io_error(bio); - return true; - } - - if (unlikely(bio_end_sector(bio) > end_sector)) { - /* This bio crosses a device boundary, so we have to split it */ - struct bio *split = bio_split(bio, end_sector - bio_sector, - GFP_NOIO, &mddev->bio_set); - bio_chain(split, bio); - submit_bio_noacct(bio); - bio = split; - } - - md_account_bio(mddev, &bio); - bio_set_dev(bio, tmp_dev->rdev->bdev); - bio->bi_iter.bi_sector = bio->bi_iter.bi_sector - - start_sector + data_offset; - - if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !bdev_max_discard_sectors(bio->bi_bdev))) { - /* Just ignore it */ - bio_endio(bio); - } else { - if (mddev->gendisk) - trace_block_bio_remap(bio, disk_devt(mddev->gendisk), - bio_sector); - mddev_check_write_zeroes(mddev, bio); - submit_bio_noacct(bio); - } - return true; - -out_of_bounds: - pr_err("md/linear:%s: make_request: Sector %llu out of bounds on dev %pg: %llu sectors, offset %llu\n", - mdname(mddev), - (unsigned long long)bio->bi_iter.bi_sector, - tmp_dev->rdev->bdev, - (unsigned long long)tmp_dev->rdev->sectors, - (unsigned long long)start_sector); - bio_io_error(bio); - return true; -} - -static void linear_status (struct seq_file *seq, struct mddev *mddev) -{ - seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2); -} - -static void linear_error(struct mddev *mddev, struct md_rdev *rdev) -{ - if (!test_and_set_bit(MD_BROKEN, &mddev->flags)) { - char *md_name = mdname(mddev); - - pr_crit("md/linear%s: Disk failure on %pg detected, failing array.\n", - md_name, rdev->bdev); - } -} - -static void linear_quiesce(struct mddev *mddev, int state) -{ -} - -static struct md_personality linear_personality = -{ - .name = "linear", - .level = LEVEL_LINEAR, - .owner = THIS_MODULE, - .make_request = linear_make_request, - .run = linear_run, - .free = linear_free, - .status = linear_status, - .hot_add_disk = linear_add, - .size = linear_size, - .quiesce = linear_quiesce, - .error_handler = linear_error, -}; - -static int __init linear_init (void) -{ - return register_md_personality (&linear_personality); -} - -static void linear_exit (void) -{ - unregister_md_personality (&linear_personality); -} - -module_init(linear_init); -module_exit(linear_exit); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Linear device concatenation personality for MD (deprecated)"); -MODULE_ALIAS("md-personality-1"); /* LINEAR - deprecated*/ -MODULE_ALIAS("md-linear"); -MODULE_ALIAS("md-level--1"); diff --git a/drivers/md/md.c b/drivers/md/md.c index 66b9e60b15c6..83f5a785c782 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8124,7 +8124,7 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev) return; mddev->pers->error_handler(mddev, rdev); - if (mddev->pers->level == 0 || mddev->pers->level == LEVEL_LINEAR) + if (mddev->pers->level == 0) return; if (mddev->degraded && !test_bit(MD_BROKEN, &mddev->flags)) diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h index 6c0aa577730f..b36e282a413d 100644 --- a/include/uapi/linux/raid/md_p.h +++ b/include/uapi/linux/raid/md_p.h @@ -2,15 +2,11 @@ /* md_p.h : physical layout of Linux RAID devices Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman - + This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2, or (at your option) any later version. - - You should have received a copy of the GNU General Public License - (for example /usr/src/linux/COPYING); if not, write to the Free - Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #ifndef _MD_P_H @@ -237,7 +233,7 @@ struct mdp_superblock_1 { char set_name[32]; /* set and interpreted by user-space */ __le64 ctime; /* lo 40 bits are seconds, top 24 are microseconds or 0*/ - __le32 level; /* -4 (multipath), -1 (linear), 0,1,4,5 */ + __le32 level; /* -4 (multipath), 0,1,4,5 */ __le32 layout; /* only for raid5 and raid10 currently */ __le64 size; /* used size of component devices, in 512byte sectors */ diff --git a/include/uapi/linux/raid/md_u.h b/include/uapi/linux/raid/md_u.h index 105307244961..c285f76e5d8d 100644 --- a/include/uapi/linux/raid/md_u.h +++ b/include/uapi/linux/raid/md_u.h @@ -2,15 +2,11 @@ /* md_u.h : user <=> kernel API between Linux raidtools and RAID drivers Copyright (C) 1998 Ingo Molnar - + This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2, or (at your option) any later version. - - You should have received a copy of the GNU General Public License - (for example /usr/src/linux/COPYING); if not, write to the Free - Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #ifndef _UAPI_MD_U_H @@ -109,7 +105,6 @@ typedef struct mdu_array_info_s { /* non-obvious values for 'level' */ #define LEVEL_MULTIPATH (-4) -#define LEVEL_LINEAR (-1) #define LEVEL_FAULTY (-5) /* we need a value for 'no level specified' and 0 -- cgit From d8730f0cf4effa015bc5e8840d8f8fb3cdb01aab Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 14 Dec 2023 14:21:06 -0800 Subject: md: Remove deprecated CONFIG_MD_MULTIPATH md-multipath has been marked as deprecated for 2.5 years. Remove it. Cc: Christoph Hellwig Cc: Jens Axboe Cc: Neil Brown Cc: Guoqing Jiang Cc: Mateusz Grzonka Cc: Jes Sorensen Signed-off-by: Song Liu Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Link: https://lore.kernel.org/r/20231214222107.2016042-3-song@kernel.org --- drivers/md/Kconfig | 11 - drivers/md/Makefile | 2 - drivers/md/md-multipath.c | 463 ----------------------------------------- drivers/md/md.c | 241 ++++++++++----------- include/uapi/linux/raid/md_p.h | 2 +- include/uapi/linux/raid/md_u.h | 1 - 6 files changed, 109 insertions(+), 611 deletions(-) delete mode 100644 drivers/md/md-multipath.c (limited to 'include/uapi/linux') diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 0c721e0e5921..de4f47fe5a03 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -159,17 +159,6 @@ config MD_RAID456 If unsure, say Y. -config MD_MULTIPATH - tristate "Multipath I/O support (deprecated)" - depends on BLK_DEV_MD - help - MD_MULTIPATH provides a simple multi-path personality for use - the MD framework. It is not under active development. New - projects should consider using DM_MULTIPATH which has more - features and more testing. - - If unsure, say N. - config MD_FAULTY tristate "Faulty test module for MD (deprecated)" depends on BLK_DEV_MD diff --git a/drivers/md/Makefile b/drivers/md/Makefile index c72f76cf7b63..6287c73399e7 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -29,7 +29,6 @@ dm-zoned-y += dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o md-mod-y += md.o md-bitmap.o raid456-y += raid5.o raid5-cache.o raid5-ppl.o -multipath-y += md-multipath.o faulty-y += md-faulty.o # Note: link order is important. All raid personalities @@ -41,7 +40,6 @@ obj-$(CONFIG_MD_RAID0) += raid0.o obj-$(CONFIG_MD_RAID1) += raid1.o obj-$(CONFIG_MD_RAID10) += raid10.o obj-$(CONFIG_MD_RAID456) += raid456.o -obj-$(CONFIG_MD_MULTIPATH) += multipath.o obj-$(CONFIG_MD_FAULTY) += faulty.o obj-$(CONFIG_MD_CLUSTER) += md-cluster.o obj-$(CONFIG_BCACHE) += bcache/ diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c deleted file mode 100644 index 19c8625ea642..000000000000 --- a/drivers/md/md-multipath.c +++ /dev/null @@ -1,463 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * multipath.c : Multiple Devices driver for Linux - * - * Copyright (C) 1999, 2000, 2001 Ingo Molnar, Red Hat - * - * Copyright (C) 1996, 1997, 1998 Ingo Molnar, Miguel de Icaza, Gadi Oxman - * - * MULTIPATH management functions. - * - * derived from raid1.c. - */ - -#include -#include -#include -#include -#include -#include "md.h" -#include "md-multipath.h" - -#define MAX_WORK_PER_DISK 128 - -#define NR_RESERVED_BUFS 32 - -static int multipath_map (struct mpconf *conf) -{ - int i, disks = conf->raid_disks; - - /* - * Later we do read balancing on the read side - * now we use the first available disk. - */ - - for (i = 0; i < disks; i++) { - struct md_rdev *rdev = conf->multipaths[i].rdev; - - if (rdev && test_bit(In_sync, &rdev->flags) && - !test_bit(Faulty, &rdev->flags)) { - atomic_inc(&rdev->nr_pending); - return i; - } - } - - pr_crit_ratelimited("multipath_map(): no more operational IO paths?\n"); - return (-1); -} - -static void multipath_reschedule_retry (struct multipath_bh *mp_bh) -{ - unsigned long flags; - struct mddev *mddev = mp_bh->mddev; - struct mpconf *conf = mddev->private; - - spin_lock_irqsave(&conf->device_lock, flags); - list_add(&mp_bh->retry_list, &conf->retry_list); - spin_unlock_irqrestore(&conf->device_lock, flags); - md_wakeup_thread(mddev->thread); -} - -/* - * multipath_end_bh_io() is called when we have finished servicing a multipathed - * operation and are ready to return a success/failure code to the buffer - * cache layer. - */ -static void multipath_end_bh_io(struct multipath_bh *mp_bh, blk_status_t status) -{ - struct bio *bio = mp_bh->master_bio; - struct mpconf *conf = mp_bh->mddev->private; - - bio->bi_status = status; - bio_endio(bio); - mempool_free(mp_bh, &conf->pool); -} - -static void multipath_end_request(struct bio *bio) -{ - struct multipath_bh *mp_bh = bio->bi_private; - struct mpconf *conf = mp_bh->mddev->private; - struct md_rdev *rdev = conf->multipaths[mp_bh->path].rdev; - - if (!bio->bi_status) - multipath_end_bh_io(mp_bh, 0); - else if (!(bio->bi_opf & REQ_RAHEAD)) { - /* - * oops, IO error: - */ - md_error (mp_bh->mddev, rdev); - pr_info("multipath: %pg: rescheduling sector %llu\n", - rdev->bdev, - (unsigned long long)bio->bi_iter.bi_sector); - multipath_reschedule_retry(mp_bh); - } else - multipath_end_bh_io(mp_bh, bio->bi_status); - rdev_dec_pending(rdev, conf->mddev); -} - -static bool multipath_make_request(struct mddev *mddev, struct bio * bio) -{ - struct mpconf *conf = mddev->private; - struct multipath_bh * mp_bh; - struct multipath_info *multipath; - - if (unlikely(bio->bi_opf & REQ_PREFLUSH) - && md_flush_request(mddev, bio)) - return true; - - md_account_bio(mddev, &bio); - mp_bh = mempool_alloc(&conf->pool, GFP_NOIO); - - mp_bh->master_bio = bio; - mp_bh->mddev = mddev; - - mp_bh->path = multipath_map(conf); - if (mp_bh->path < 0) { - bio_io_error(bio); - mempool_free(mp_bh, &conf->pool); - return true; - } - multipath = conf->multipaths + mp_bh->path; - - bio_init_clone(multipath->rdev->bdev, &mp_bh->bio, bio, GFP_NOIO); - - mp_bh->bio.bi_iter.bi_sector += multipath->rdev->data_offset; - mp_bh->bio.bi_opf |= REQ_FAILFAST_TRANSPORT; - mp_bh->bio.bi_end_io = multipath_end_request; - mp_bh->bio.bi_private = mp_bh; - mddev_check_write_zeroes(mddev, &mp_bh->bio); - submit_bio_noacct(&mp_bh->bio); - return true; -} - -static void multipath_status(struct seq_file *seq, struct mddev *mddev) -{ - struct mpconf *conf = mddev->private; - int i; - - lockdep_assert_held(&mddev->lock); - - seq_printf (seq, " [%d/%d] [", conf->raid_disks, - conf->raid_disks - mddev->degraded); - for (i = 0; i < conf->raid_disks; i++) { - struct md_rdev *rdev = READ_ONCE(conf->multipaths[i].rdev); - - seq_printf(seq, "%s", - rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_"); - } - seq_putc(seq, ']'); -} - -/* - * Careful, this can execute in IRQ contexts as well! - */ -static void multipath_error (struct mddev *mddev, struct md_rdev *rdev) -{ - struct mpconf *conf = mddev->private; - - if (conf->raid_disks - mddev->degraded <= 1) { - /* - * Uh oh, we can do nothing if this is our last path, but - * first check if this is a queued request for a device - * which has just failed. - */ - pr_warn("multipath: only one IO path left and IO error.\n"); - /* leave it active... it's all we have */ - return; - } - /* - * Mark disk as unusable - */ - if (test_and_clear_bit(In_sync, &rdev->flags)) { - unsigned long flags; - spin_lock_irqsave(&conf->device_lock, flags); - mddev->degraded++; - spin_unlock_irqrestore(&conf->device_lock, flags); - } - set_bit(Faulty, &rdev->flags); - set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); - pr_err("multipath: IO failure on %pg, disabling IO path.\n" - "multipath: Operation continuing on %d IO paths.\n", - rdev->bdev, - conf->raid_disks - mddev->degraded); -} - -static void print_multipath_conf(struct mpconf *conf) -{ - int i; - struct multipath_info *tmp; - - pr_debug("MULTIPATH conf printout:\n"); - if (!conf) { - pr_debug("(conf==NULL)\n"); - return; - } - pr_debug(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded, - conf->raid_disks); - - lockdep_assert_held(&conf->mddev->reconfig_mutex); - for (i = 0; i < conf->raid_disks; i++) { - tmp = conf->multipaths + i; - if (tmp->rdev) - pr_debug(" disk%d, o:%d, dev:%pg\n", - i,!test_bit(Faulty, &tmp->rdev->flags), - tmp->rdev->bdev); - } -} - -static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev) -{ - struct mpconf *conf = mddev->private; - int err = -EEXIST; - int path; - struct multipath_info *p; - int first = 0; - int last = mddev->raid_disks - 1; - - if (rdev->raid_disk >= 0) - first = last = rdev->raid_disk; - - print_multipath_conf(conf); - - for (path = first; path <= last; path++) - if ((p=conf->multipaths+path)->rdev == NULL) { - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - - err = md_integrity_add_rdev(rdev, mddev); - if (err) - break; - spin_lock_irq(&conf->device_lock); - mddev->degraded--; - rdev->raid_disk = path; - set_bit(In_sync, &rdev->flags); - spin_unlock_irq(&conf->device_lock); - WRITE_ONCE(p->rdev, rdev); - err = 0; - break; - } - - print_multipath_conf(conf); - - return err; -} - -static int multipath_remove_disk(struct mddev *mddev, struct md_rdev *rdev) -{ - struct mpconf *conf = mddev->private; - int err = 0; - int number = rdev->raid_disk; - struct multipath_info *p = conf->multipaths + number; - - print_multipath_conf(conf); - - if (rdev == p->rdev) { - if (test_bit(In_sync, &rdev->flags) || - atomic_read(&rdev->nr_pending)) { - pr_warn("hot-remove-disk, slot %d is identified but is still operational!\n", number); - err = -EBUSY; - goto abort; - } - WRITE_ONCE(p->rdev, NULL); - err = md_integrity_register(mddev); - } -abort: - - print_multipath_conf(conf); - return err; -} - -/* - * This is a kernel thread which: - * - * 1. Retries failed read operations on working multipaths. - * 2. Updates the raid superblock when problems encounter. - * 3. Performs writes following reads for array syncronising. - */ - -static void multipathd(struct md_thread *thread) -{ - struct mddev *mddev = thread->mddev; - struct multipath_bh *mp_bh; - struct bio *bio; - unsigned long flags; - struct mpconf *conf = mddev->private; - struct list_head *head = &conf->retry_list; - - md_check_recovery(mddev); - for (;;) { - spin_lock_irqsave(&conf->device_lock, flags); - if (list_empty(head)) - break; - mp_bh = list_entry(head->prev, struct multipath_bh, retry_list); - list_del(head->prev); - spin_unlock_irqrestore(&conf->device_lock, flags); - - bio = &mp_bh->bio; - bio->bi_iter.bi_sector = mp_bh->master_bio->bi_iter.bi_sector; - - if ((mp_bh->path = multipath_map (conf))<0) { - pr_err("multipath: %pg: unrecoverable IO read error for block %llu\n", - bio->bi_bdev, - (unsigned long long)bio->bi_iter.bi_sector); - multipath_end_bh_io(mp_bh, BLK_STS_IOERR); - } else { - pr_err("multipath: %pg: redirecting sector %llu to another IO path\n", - bio->bi_bdev, - (unsigned long long)bio->bi_iter.bi_sector); - *bio = *(mp_bh->master_bio); - bio->bi_iter.bi_sector += - conf->multipaths[mp_bh->path].rdev->data_offset; - bio_set_dev(bio, conf->multipaths[mp_bh->path].rdev->bdev); - bio->bi_opf |= REQ_FAILFAST_TRANSPORT; - bio->bi_end_io = multipath_end_request; - bio->bi_private = mp_bh; - submit_bio_noacct(bio); - } - } - spin_unlock_irqrestore(&conf->device_lock, flags); -} - -static sector_t multipath_size(struct mddev *mddev, sector_t sectors, int raid_disks) -{ - WARN_ONCE(sectors || raid_disks, - "%s does not support generic reshape\n", __func__); - - return mddev->dev_sectors; -} - -static int multipath_run (struct mddev *mddev) -{ - struct mpconf *conf; - int disk_idx; - struct multipath_info *disk; - struct md_rdev *rdev; - int working_disks; - int ret; - - if (md_check_no_bitmap(mddev)) - return -EINVAL; - - if (mddev->level != LEVEL_MULTIPATH) { - pr_warn("multipath: %s: raid level not set to multipath IO (%d)\n", - mdname(mddev), mddev->level); - goto out; - } - /* - * copy the already verified devices into our private MULTIPATH - * bookkeeping area. [whatever we allocate in multipath_run(), - * should be freed in multipath_free()] - */ - - conf = kzalloc(sizeof(struct mpconf), GFP_KERNEL); - mddev->private = conf; - if (!conf) - goto out; - - conf->multipaths = kcalloc(mddev->raid_disks, - sizeof(struct multipath_info), - GFP_KERNEL); - if (!conf->multipaths) - goto out_free_conf; - - working_disks = 0; - rdev_for_each(rdev, mddev) { - disk_idx = rdev->raid_disk; - if (disk_idx < 0 || - disk_idx >= mddev->raid_disks) - continue; - - disk = conf->multipaths + disk_idx; - disk->rdev = rdev; - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - - if (!test_bit(Faulty, &rdev->flags)) - working_disks++; - } - - conf->raid_disks = mddev->raid_disks; - conf->mddev = mddev; - spin_lock_init(&conf->device_lock); - INIT_LIST_HEAD(&conf->retry_list); - - if (!working_disks) { - pr_warn("multipath: no operational IO paths for %s\n", - mdname(mddev)); - goto out_free_conf; - } - mddev->degraded = conf->raid_disks - working_disks; - - ret = mempool_init_kmalloc_pool(&conf->pool, NR_RESERVED_BUFS, - sizeof(struct multipath_bh)); - if (ret) - goto out_free_conf; - - rcu_assign_pointer(mddev->thread, - md_register_thread(multipathd, mddev, "multipath")); - if (!mddev->thread) - goto out_free_conf; - - pr_info("multipath: array %s active with %d out of %d IO paths\n", - mdname(mddev), conf->raid_disks - mddev->degraded, - mddev->raid_disks); - /* - * Ok, everything is just fine now - */ - md_set_array_sectors(mddev, multipath_size(mddev, 0, 0)); - - if (md_integrity_register(mddev)) - goto out_free_conf; - - return 0; - -out_free_conf: - mempool_exit(&conf->pool); - kfree(conf->multipaths); - kfree(conf); - mddev->private = NULL; -out: - return -EIO; -} - -static void multipath_free(struct mddev *mddev, void *priv) -{ - struct mpconf *conf = priv; - - mempool_exit(&conf->pool); - kfree(conf->multipaths); - kfree(conf); -} - -static struct md_personality multipath_personality = -{ - .name = "multipath", - .level = LEVEL_MULTIPATH, - .owner = THIS_MODULE, - .make_request = multipath_make_request, - .run = multipath_run, - .free = multipath_free, - .status = multipath_status, - .error_handler = multipath_error, - .hot_add_disk = multipath_add_disk, - .hot_remove_disk= multipath_remove_disk, - .size = multipath_size, -}; - -static int __init multipath_init (void) -{ - return register_md_personality (&multipath_personality); -} - -static void __exit multipath_exit (void) -{ - unregister_md_personality (&multipath_personality); -} - -module_init(multipath_init); -module_exit(multipath_exit); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("simple multi-path personality for MD (deprecated)"); -MODULE_ALIAS("md-personality-7"); /* MULTIPATH */ -MODULE_ALIAS("md-multipath"); -MODULE_ALIAS("md-level--4"); diff --git a/drivers/md/md.c b/drivers/md/md.c index 83f5a785c782..e351e6c51cc7 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1287,17 +1287,11 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor rdev->sb_size = MD_SB_BYTES; rdev->badblocks.shift = -1; - if (sb->level == LEVEL_MULTIPATH) - rdev->desc_nr = -1; - else - rdev->desc_nr = sb->this_disk.number; - - /* not spare disk, or LEVEL_MULTIPATH */ - if (sb->level == LEVEL_MULTIPATH || - (rdev->desc_nr >= 0 && - rdev->desc_nr < MD_SB_DISKS && - sb->disks[rdev->desc_nr].state & - ((1<desc_nr = sb->this_disk.number; + + /* not spare disk */ + if (rdev->desc_nr >= 0 && rdev->desc_nr < MD_SB_DISKS && + sb->disks[rdev->desc_nr].state & ((1<level != LEVEL_MULTIPATH) { - desc = sb->disks + rdev->desc_nr; + desc = sb->disks + rdev->desc_nr; - if (desc->state & (1<flags); - else if (desc->state & (1<raid_disk < mddev->raid_disks */) { - set_bit(In_sync, &rdev->flags); + if (desc->state & (1<flags); + else if (desc->state & (1<flags); + rdev->raid_disk = desc->raid_disk; + rdev->saved_raid_disk = desc->raid_disk; + } else if (desc->state & (1<minor_version >= 91) { + rdev->recovery_offset = 0; rdev->raid_disk = desc->raid_disk; - rdev->saved_raid_disk = desc->raid_disk; - } else if (desc->state & (1<minor_version >= 91) { - rdev->recovery_offset = 0; - rdev->raid_disk = desc->raid_disk; - } } - if (desc->state & (1<flags); - if (desc->state & (1<flags); - } else /* MULTIPATH are always insync */ - set_bit(In_sync, &rdev->flags); + } + if (desc->state & (1<flags); + if (desc->state & (1<flags); return 0; } @@ -1758,10 +1749,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ && rdev->new_data_offset < sb_start + (rdev->sb_size/512)) return -EINVAL; - if (sb->level == cpu_to_le32(LEVEL_MULTIPATH)) - rdev->desc_nr = -1; - else - rdev->desc_nr = le32_to_cpu(sb->dev_number); + rdev->desc_nr = le32_to_cpu(sb->dev_number); if (!rdev->bb_page) { rdev->bb_page = alloc_page(GFP_KERNEL); @@ -1814,12 +1802,10 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ sb->level != 0) return -EINVAL; - /* not spare disk, or LEVEL_MULTIPATH */ - if (sb->level == cpu_to_le32(LEVEL_MULTIPATH) || - (rdev->desc_nr >= 0 && - rdev->desc_nr < le32_to_cpu(sb->max_dev) && - (le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX || - le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL))) + /* not spare disk */ + if (rdev->desc_nr >= 0 && rdev->desc_nr < le32_to_cpu(sb->max_dev) && + (le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX || + le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL)) spare_disk = false; if (!refdev) { @@ -1862,6 +1848,7 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struc { struct mdp_superblock_1 *sb = page_address(rdev->sb_page); __u64 ev1 = le64_to_cpu(sb->events); + int role; rdev->raid_disk = -1; clear_bit(Faulty, &rdev->flags); @@ -1977,88 +1964,85 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struc /* just a hot-add of a new device, leave raid_disk at -1 */ return 0; } - if (mddev->level != LEVEL_MULTIPATH) { - int role; - if (rdev->desc_nr < 0 || - rdev->desc_nr >= le32_to_cpu(sb->max_dev)) { - role = MD_DISK_ROLE_SPARE; - rdev->desc_nr = -1; - } else if (mddev->pers == NULL && freshest && ev1 < mddev->events) { - /* - * If we are assembling, and our event counter is smaller than the - * highest event counter, we cannot trust our superblock about the role. - * It could happen that our rdev was marked as Faulty, and all other - * superblocks were updated with +1 event counter. - * Then, before the next superblock update, which typically happens when - * remove_and_add_spares() removes the device from the array, there was - * a crash or reboot. - * If we allow current rdev without consulting the freshest superblock, - * we could cause data corruption. - * Note that in this case our event counter is smaller by 1 than the - * highest, otherwise, this rdev would not be allowed into array; - * both kernel and mdadm allow event counter difference of 1. - */ - struct mdp_superblock_1 *freshest_sb = page_address(freshest->sb_page); - u32 freshest_max_dev = le32_to_cpu(freshest_sb->max_dev); - - if (rdev->desc_nr >= freshest_max_dev) { - /* this is unexpected, better not proceed */ - pr_warn("md: %s: rdev[%pg]: desc_nr(%d) >= freshest(%pg)->sb->max_dev(%u)\n", - mdname(mddev), rdev->bdev, rdev->desc_nr, - freshest->bdev, freshest_max_dev); - return -EUCLEAN; - } - role = le16_to_cpu(freshest_sb->dev_roles[rdev->desc_nr]); - pr_debug("md: %s: rdev[%pg]: role=%d(0x%x) according to freshest %pg\n", - mdname(mddev), rdev->bdev, role, role, freshest->bdev); - } else { - role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]); + if (rdev->desc_nr < 0 || + rdev->desc_nr >= le32_to_cpu(sb->max_dev)) { + role = MD_DISK_ROLE_SPARE; + rdev->desc_nr = -1; + } else if (mddev->pers == NULL && freshest && ev1 < mddev->events) { + /* + * If we are assembling, and our event counter is smaller than the + * highest event counter, we cannot trust our superblock about the role. + * It could happen that our rdev was marked as Faulty, and all other + * superblocks were updated with +1 event counter. + * Then, before the next superblock update, which typically happens when + * remove_and_add_spares() removes the device from the array, there was + * a crash or reboot. + * If we allow current rdev without consulting the freshest superblock, + * we could cause data corruption. + * Note that in this case our event counter is smaller by 1 than the + * highest, otherwise, this rdev would not be allowed into array; + * both kernel and mdadm allow event counter difference of 1. + */ + struct mdp_superblock_1 *freshest_sb = page_address(freshest->sb_page); + u32 freshest_max_dev = le32_to_cpu(freshest_sb->max_dev); + + if (rdev->desc_nr >= freshest_max_dev) { + /* this is unexpected, better not proceed */ + pr_warn("md: %s: rdev[%pg]: desc_nr(%d) >= freshest(%pg)->sb->max_dev(%u)\n", + mdname(mddev), rdev->bdev, rdev->desc_nr, + freshest->bdev, freshest_max_dev); + return -EUCLEAN; } - switch(role) { - case MD_DISK_ROLE_SPARE: /* spare */ - break; - case MD_DISK_ROLE_FAULTY: /* faulty */ - set_bit(Faulty, &rdev->flags); - break; - case MD_DISK_ROLE_JOURNAL: /* journal device */ - if (!(le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)) { - /* journal device without journal feature */ - pr_warn("md: journal device provided without journal feature, ignoring the device\n"); - return -EINVAL; - } - set_bit(Journal, &rdev->flags); - rdev->journal_tail = le64_to_cpu(sb->journal_tail); - rdev->raid_disk = 0; - break; - default: - rdev->saved_raid_disk = role; - if ((le32_to_cpu(sb->feature_map) & - MD_FEATURE_RECOVERY_OFFSET)) { - rdev->recovery_offset = le64_to_cpu(sb->recovery_offset); - if (!(le32_to_cpu(sb->feature_map) & - MD_FEATURE_RECOVERY_BITMAP)) - rdev->saved_raid_disk = -1; - } else { - /* - * If the array is FROZEN, then the device can't - * be in_sync with rest of array. - */ - if (!test_bit(MD_RECOVERY_FROZEN, - &mddev->recovery)) - set_bit(In_sync, &rdev->flags); - } - rdev->raid_disk = role; - break; + + role = le16_to_cpu(freshest_sb->dev_roles[rdev->desc_nr]); + pr_debug("md: %s: rdev[%pg]: role=%d(0x%x) according to freshest %pg\n", + mdname(mddev), rdev->bdev, role, role, freshest->bdev); + } else { + role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]); + } + switch (role) { + case MD_DISK_ROLE_SPARE: /* spare */ + break; + case MD_DISK_ROLE_FAULTY: /* faulty */ + set_bit(Faulty, &rdev->flags); + break; + case MD_DISK_ROLE_JOURNAL: /* journal device */ + if (!(le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)) { + /* journal device without journal feature */ + pr_warn("md: journal device provided without journal feature, ignoring the device\n"); + return -EINVAL; } - if (sb->devflags & WriteMostly1) - set_bit(WriteMostly, &rdev->flags); - if (sb->devflags & FailFast1) - set_bit(FailFast, &rdev->flags); - if (le32_to_cpu(sb->feature_map) & MD_FEATURE_REPLACEMENT) - set_bit(Replacement, &rdev->flags); - } else /* MULTIPATH are always insync */ - set_bit(In_sync, &rdev->flags); + set_bit(Journal, &rdev->flags); + rdev->journal_tail = le64_to_cpu(sb->journal_tail); + rdev->raid_disk = 0; + break; + default: + rdev->saved_raid_disk = role; + if ((le32_to_cpu(sb->feature_map) & + MD_FEATURE_RECOVERY_OFFSET)) { + rdev->recovery_offset = le64_to_cpu(sb->recovery_offset); + if (!(le32_to_cpu(sb->feature_map) & + MD_FEATURE_RECOVERY_BITMAP)) + rdev->saved_raid_disk = -1; + } else { + /* + * If the array is FROZEN, then the device can't + * be in_sync with rest of array. + */ + if (!test_bit(MD_RECOVERY_FROZEN, + &mddev->recovery)) + set_bit(In_sync, &rdev->flags); + } + rdev->raid_disk = role; + break; + } + if (sb->devflags & WriteMostly1) + set_bit(WriteMostly, &rdev->flags); + if (sb->devflags & FailFast1) + set_bit(FailFast, &rdev->flags); + if (le32_to_cpu(sb->feature_map) & MD_FEATURE_REPLACEMENT) + set_bit(Replacement, &rdev->flags); return 0; } @@ -2876,10 +2860,6 @@ rewrite: } else pr_debug("md: %pg (skipping faulty)\n", rdev->bdev); - - if (mddev->level == LEVEL_MULTIPATH) - /* only need to write one superblock... */ - break; } if (md_super_wait(mddev) < 0) goto rewrite; @@ -3880,13 +3860,8 @@ static int analyze_sbs(struct mddev *mddev) continue; } } - if (mddev->level == LEVEL_MULTIPATH) { - rdev->desc_nr = i++; - rdev->raid_disk = rdev->desc_nr; - set_bit(In_sync, &rdev->flags); - } else if (rdev->raid_disk >= - (mddev->raid_disks - min(0, mddev->delta_disks)) && - !test_bit(Journal, &rdev->flags)) { + if (rdev->raid_disk >= (mddev->raid_disks - min(0, mddev->delta_disks)) && + !test_bit(Journal, &rdev->flags)) { rdev->raid_disk = -1; clear_bit(In_sync, &rdev->flags); } diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h index b36e282a413d..5a43c23f53bf 100644 --- a/include/uapi/linux/raid/md_p.h +++ b/include/uapi/linux/raid/md_p.h @@ -233,7 +233,7 @@ struct mdp_superblock_1 { char set_name[32]; /* set and interpreted by user-space */ __le64 ctime; /* lo 40 bits are seconds, top 24 are microseconds or 0*/ - __le32 level; /* -4 (multipath), 0,1,4,5 */ + __le32 level; /* 0,1,4,5 */ __le32 layout; /* only for raid5 and raid10 currently */ __le64 size; /* used size of component devices, in 512byte sectors */ diff --git a/include/uapi/linux/raid/md_u.h b/include/uapi/linux/raid/md_u.h index c285f76e5d8d..b44bbc356643 100644 --- a/include/uapi/linux/raid/md_u.h +++ b/include/uapi/linux/raid/md_u.h @@ -104,7 +104,6 @@ typedef struct mdu_array_info_s { } mdu_array_info_t; /* non-obvious values for 'level' */ -#define LEVEL_MULTIPATH (-4) #define LEVEL_FAULTY (-5) /* we need a value for 'no level specified' and 0 -- cgit From 415c7451872b0d037760795edd3961eaa63276ea Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 14 Dec 2023 14:21:07 -0800 Subject: md: Remove deprecated CONFIG_MD_FAULTY md-faulty has been marked as deprecated for 2.5 years. Remove it. Cc: Christoph Hellwig Cc: Jens Axboe Cc: Neil Brown Cc: Guoqing Jiang Cc: Mateusz Grzonka Cc: Jes Sorensen Signed-off-by: Song Liu Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Link: https://lore.kernel.org/r/20231214222107.2016042-4-song@kernel.org --- drivers/md/Kconfig | 10 -- drivers/md/Makefile | 2 - drivers/md/md-faulty.c | 365 ----------------------------------------- include/uapi/linux/raid/md_u.h | 3 - 4 files changed, 380 deletions(-) delete mode 100644 drivers/md/md-faulty.c (limited to 'include/uapi/linux') diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index de4f47fe5a03..f6dc2acdf1ed 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -159,16 +159,6 @@ config MD_RAID456 If unsure, say Y. -config MD_FAULTY - tristate "Faulty test module for MD (deprecated)" - depends on BLK_DEV_MD - help - The "faulty" module allows for a block device that occasionally returns - read or write errors. It is useful for testing. - - In unsure, say N. - - config MD_CLUSTER tristate "Cluster Support for MD" depends on BLK_DEV_MD diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 6287c73399e7..027d7cfeca3f 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -29,7 +29,6 @@ dm-zoned-y += dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o md-mod-y += md.o md-bitmap.o raid456-y += raid5.o raid5-cache.o raid5-ppl.o -faulty-y += md-faulty.o # Note: link order is important. All raid personalities # and must come before md.o, as they each initialise @@ -40,7 +39,6 @@ obj-$(CONFIG_MD_RAID0) += raid0.o obj-$(CONFIG_MD_RAID1) += raid1.o obj-$(CONFIG_MD_RAID10) += raid10.o obj-$(CONFIG_MD_RAID456) += raid456.o -obj-$(CONFIG_MD_FAULTY) += faulty.o obj-$(CONFIG_MD_CLUSTER) += md-cluster.o obj-$(CONFIG_BCACHE) += bcache/ obj-$(CONFIG_BLK_DEV_MD) += md-mod.o diff --git a/drivers/md/md-faulty.c b/drivers/md/md-faulty.c deleted file mode 100644 index a039e8e20f55..000000000000 --- a/drivers/md/md-faulty.c +++ /dev/null @@ -1,365 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * faulty.c : Multiple Devices driver for Linux - * - * Copyright (C) 2004 Neil Brown - * - * fautly-device-simulator personality for md - */ - - -/* - * The "faulty" personality causes some requests to fail. - * - * Possible failure modes are: - * reads fail "randomly" but succeed on retry - * writes fail "randomly" but succeed on retry - * reads for some address fail and then persist until a write - * reads for some address fail and then persist irrespective of write - * writes for some address fail and persist - * all writes fail - * - * Different modes can be active at a time, but only - * one can be set at array creation. Others can be added later. - * A mode can be one-shot or recurrent with the recurrence being - * once in every N requests. - * The bottom 5 bits of the "layout" indicate the mode. The - * remainder indicate a period, or 0 for one-shot. - * - * There is an implementation limit on the number of concurrently - * persisting-faulty blocks. When a new fault is requested that would - * exceed the limit, it is ignored. - * All current faults can be clear using a layout of "0". - * - * Requests are always sent to the device. If they are to fail, - * we clone the bio and insert a new b_end_io into the chain. - */ - -#define WriteTransient 0 -#define ReadTransient 1 -#define WritePersistent 2 -#define ReadPersistent 3 -#define WriteAll 4 /* doesn't go to device */ -#define ReadFixable 5 -#define Modes 6 - -#define ClearErrors 31 -#define ClearFaults 30 - -#define AllPersist 100 /* internal use only */ -#define NoPersist 101 - -#define ModeMask 0x1f -#define ModeShift 5 - -#define MaxFault 50 -#include -#include -#include -#include -#include "md.h" -#include - - -static void faulty_fail(struct bio *bio) -{ - struct bio *b = bio->bi_private; - - b->bi_iter.bi_size = bio->bi_iter.bi_size; - b->bi_iter.bi_sector = bio->bi_iter.bi_sector; - - bio_put(bio); - - bio_io_error(b); -} - -struct faulty_conf { - int period[Modes]; - atomic_t counters[Modes]; - sector_t faults[MaxFault]; - int modes[MaxFault]; - int nfaults; - struct md_rdev *rdev; -}; - -static int check_mode(struct faulty_conf *conf, int mode) -{ - if (conf->period[mode] == 0 && - atomic_read(&conf->counters[mode]) <= 0) - return 0; /* no failure, no decrement */ - - - if (atomic_dec_and_test(&conf->counters[mode])) { - if (conf->period[mode]) - atomic_set(&conf->counters[mode], conf->period[mode]); - return 1; - } - return 0; -} - -static int check_sector(struct faulty_conf *conf, sector_t start, sector_t end, int dir) -{ - /* If we find a ReadFixable sector, we fix it ... */ - int i; - for (i=0; infaults; i++) - if (conf->faults[i] >= start && - conf->faults[i] < end) { - /* found it ... */ - switch (conf->modes[i] * 2 + dir) { - case WritePersistent*2+WRITE: return 1; - case ReadPersistent*2+READ: return 1; - case ReadFixable*2+READ: return 1; - case ReadFixable*2+WRITE: - conf->modes[i] = NoPersist; - return 0; - case AllPersist*2+READ: - case AllPersist*2+WRITE: return 1; - default: - return 0; - } - } - return 0; -} - -static void add_sector(struct faulty_conf *conf, sector_t start, int mode) -{ - int i; - int n = conf->nfaults; - for (i=0; infaults; i++) - if (conf->faults[i] == start) { - switch(mode) { - case NoPersist: conf->modes[i] = mode; return; - case WritePersistent: - if (conf->modes[i] == ReadPersistent || - conf->modes[i] == ReadFixable) - conf->modes[i] = AllPersist; - else - conf->modes[i] = WritePersistent; - return; - case ReadPersistent: - if (conf->modes[i] == WritePersistent) - conf->modes[i] = AllPersist; - else - conf->modes[i] = ReadPersistent; - return; - case ReadFixable: - if (conf->modes[i] == WritePersistent || - conf->modes[i] == ReadPersistent) - conf->modes[i] = AllPersist; - else - conf->modes[i] = ReadFixable; - return; - } - } else if (conf->modes[i] == NoPersist) - n = i; - - if (n >= MaxFault) - return; - conf->faults[n] = start; - conf->modes[n] = mode; - if (conf->nfaults == n) - conf->nfaults = n+1; -} - -static bool faulty_make_request(struct mddev *mddev, struct bio *bio) -{ - struct faulty_conf *conf = mddev->private; - int failit = 0; - - if (bio_data_dir(bio) == WRITE) { - /* write request */ - if (atomic_read(&conf->counters[WriteAll])) { - /* special case - don't decrement, don't submit_bio_noacct, - * just fail immediately - */ - bio_io_error(bio); - return true; - } - - if (check_sector(conf, bio->bi_iter.bi_sector, - bio_end_sector(bio), WRITE)) - failit = 1; - if (check_mode(conf, WritePersistent)) { - add_sector(conf, bio->bi_iter.bi_sector, - WritePersistent); - failit = 1; - } - if (check_mode(conf, WriteTransient)) - failit = 1; - } else { - /* read request */ - if (check_sector(conf, bio->bi_iter.bi_sector, - bio_end_sector(bio), READ)) - failit = 1; - if (check_mode(conf, ReadTransient)) - failit = 1; - if (check_mode(conf, ReadPersistent)) { - add_sector(conf, bio->bi_iter.bi_sector, - ReadPersistent); - failit = 1; - } - if (check_mode(conf, ReadFixable)) { - add_sector(conf, bio->bi_iter.bi_sector, - ReadFixable); - failit = 1; - } - } - - md_account_bio(mddev, &bio); - if (failit) { - struct bio *b = bio_alloc_clone(conf->rdev->bdev, bio, GFP_NOIO, - &mddev->bio_set); - - b->bi_private = bio; - b->bi_end_io = faulty_fail; - bio = b; - } else - bio_set_dev(bio, conf->rdev->bdev); - - submit_bio_noacct(bio); - return true; -} - -static void faulty_status(struct seq_file *seq, struct mddev *mddev) -{ - struct faulty_conf *conf = mddev->private; - int n; - - if ((n=atomic_read(&conf->counters[WriteTransient])) != 0) - seq_printf(seq, " WriteTransient=%d(%d)", - n, conf->period[WriteTransient]); - - if ((n=atomic_read(&conf->counters[ReadTransient])) != 0) - seq_printf(seq, " ReadTransient=%d(%d)", - n, conf->period[ReadTransient]); - - if ((n=atomic_read(&conf->counters[WritePersistent])) != 0) - seq_printf(seq, " WritePersistent=%d(%d)", - n, conf->period[WritePersistent]); - - if ((n=atomic_read(&conf->counters[ReadPersistent])) != 0) - seq_printf(seq, " ReadPersistent=%d(%d)", - n, conf->period[ReadPersistent]); - - - if ((n=atomic_read(&conf->counters[ReadFixable])) != 0) - seq_printf(seq, " ReadFixable=%d(%d)", - n, conf->period[ReadFixable]); - - if ((n=atomic_read(&conf->counters[WriteAll])) != 0) - seq_printf(seq, " WriteAll"); - - seq_printf(seq, " nfaults=%d", conf->nfaults); -} - - -static int faulty_reshape(struct mddev *mddev) -{ - int mode = mddev->new_layout & ModeMask; - int count = mddev->new_layout >> ModeShift; - struct faulty_conf *conf = mddev->private; - - if (mddev->new_layout < 0) - return 0; - - /* new layout */ - if (mode == ClearFaults) - conf->nfaults = 0; - else if (mode == ClearErrors) { - int i; - for (i=0 ; i < Modes ; i++) { - conf->period[i] = 0; - atomic_set(&conf->counters[i], 0); - } - } else if (mode < Modes) { - conf->period[mode] = count; - if (!count) count++; - atomic_set(&conf->counters[mode], count); - } else - return -EINVAL; - mddev->new_layout = -1; - mddev->layout = -1; /* makes sure further changes come through */ - return 0; -} - -static sector_t faulty_size(struct mddev *mddev, sector_t sectors, int raid_disks) -{ - WARN_ONCE(raid_disks, - "%s does not support generic reshape\n", __func__); - - if (sectors == 0) - return mddev->dev_sectors; - - return sectors; -} - -static int faulty_run(struct mddev *mddev) -{ - struct md_rdev *rdev; - int i; - struct faulty_conf *conf; - - if (md_check_no_bitmap(mddev)) - return -EINVAL; - - conf = kmalloc(sizeof(*conf), GFP_KERNEL); - if (!conf) - return -ENOMEM; - - for (i=0; icounters[i], 0); - conf->period[i] = 0; - } - conf->nfaults = 0; - - rdev_for_each(rdev, mddev) { - conf->rdev = rdev; - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - } - - md_set_array_sectors(mddev, faulty_size(mddev, 0, 0)); - mddev->private = conf; - - faulty_reshape(mddev); - - return 0; -} - -static void faulty_free(struct mddev *mddev, void *priv) -{ - struct faulty_conf *conf = priv; - - kfree(conf); -} - -static struct md_personality faulty_personality = -{ - .name = "faulty", - .level = LEVEL_FAULTY, - .owner = THIS_MODULE, - .make_request = faulty_make_request, - .run = faulty_run, - .free = faulty_free, - .status = faulty_status, - .check_reshape = faulty_reshape, - .size = faulty_size, -}; - -static int __init raid_init(void) -{ - return register_md_personality(&faulty_personality); -} - -static void raid_exit(void) -{ - unregister_md_personality(&faulty_personality); -} - -module_init(raid_init); -module_exit(raid_exit); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Fault injection personality for MD (deprecated)"); -MODULE_ALIAS("md-personality-10"); /* faulty */ -MODULE_ALIAS("md-faulty"); -MODULE_ALIAS("md-level--5"); diff --git a/include/uapi/linux/raid/md_u.h b/include/uapi/linux/raid/md_u.h index b44bbc356643..7be89a4906e7 100644 --- a/include/uapi/linux/raid/md_u.h +++ b/include/uapi/linux/raid/md_u.h @@ -103,9 +103,6 @@ typedef struct mdu_array_info_s { } mdu_array_info_t; -/* non-obvious values for 'level' */ -#define LEVEL_FAULTY (-5) - /* we need a value for 'no level specified' and 0 * means 'raid0', so we need something else. This is * for internal use only -- cgit From 838bebb4c926a573839ff1bfe1b654a6ed0f9779 Mon Sep 17 00:00:00 2001 From: Feng Liu Date: Tue, 19 Dec 2023 11:32:39 +0200 Subject: virtio: Define feature bit for administration virtqueue Introduce VIRTIO_F_ADMIN_VQ which is used for administration virtqueue support. Signed-off-by: Feng Liu Reviewed-by: Parav Pandit Reviewed-by: Jiri Pirko Acked-by: Michael S. Tsirkin Signed-off-by: Yishai Hadas Link: https://lore.kernel.org/r/20231219093247.170936-2-yishaih@nvidia.com Signed-off-by: Alex Williamson --- include/uapi/linux/virtio_config.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h index 8881aea60f6f..2445f365bce7 100644 --- a/include/uapi/linux/virtio_config.h +++ b/include/uapi/linux/virtio_config.h @@ -52,7 +52,7 @@ * rest are per-device feature bits. */ #define VIRTIO_TRANSPORT_F_START 28 -#define VIRTIO_TRANSPORT_F_END 41 +#define VIRTIO_TRANSPORT_F_END 42 #ifndef VIRTIO_CONFIG_NO_LEGACY /* Do we get callbacks when the ring is completely used, even if we've @@ -114,4 +114,10 @@ * This feature indicates that the driver can reset a queue individually. */ #define VIRTIO_F_RING_RESET 40 + +/* + * This feature indicates that the device support administration virtqueues. + */ +#define VIRTIO_F_ADMIN_VQ 41 + #endif /* _UAPI_LINUX_VIRTIO_CONFIG_H */ -- cgit From fd27ef6b44bec26915c5b2b22c13856d9f0ba17a Mon Sep 17 00:00:00 2001 From: Feng Liu Date: Tue, 19 Dec 2023 11:32:40 +0200 Subject: virtio-pci: Introduce admin virtqueue Introduce support for the admin virtqueue. By negotiating VIRTIO_F_ADMIN_VQ feature, driver detects capability and creates one administration virtqueue. Administration virtqueue implementation in virtio pci generic layer, enables multiple types of upper layer drivers such as vfio, net, blk to utilize it. Signed-off-by: Feng Liu Reviewed-by: Parav Pandit Reviewed-by: Jiri Pirko Acked-by: Michael S. Tsirkin Signed-off-by: Yishai Hadas Link: https://lore.kernel.org/r/20231219093247.170936-3-yishaih@nvidia.com Signed-off-by: Alex Williamson --- drivers/virtio/virtio.c | 37 +++++++++++++++-- drivers/virtio/virtio_pci_common.c | 3 ++ drivers/virtio/virtio_pci_common.h | 15 ++++++- drivers/virtio/virtio_pci_modern.c | 75 +++++++++++++++++++++++++++++++++- drivers/virtio/virtio_pci_modern_dev.c | 24 ++++++++++- include/linux/virtio_config.h | 4 ++ include/linux/virtio_pci_modern.h | 2 + include/uapi/linux/virtio_pci.h | 5 +++ 8 files changed, 157 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 3893dc29eb26..f4080692b351 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -302,9 +302,15 @@ static int virtio_dev_probe(struct device *_d) if (err) goto err; + if (dev->config->create_avq) { + err = dev->config->create_avq(dev); + if (err) + goto err; + } + err = drv->probe(dev); if (err) - goto err; + goto err_probe; /* If probe didn't do it, mark device DRIVER_OK ourselves. */ if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK)) @@ -316,6 +322,10 @@ static int virtio_dev_probe(struct device *_d) virtio_config_enable(dev); return 0; + +err_probe: + if (dev->config->destroy_avq) + dev->config->destroy_avq(dev); err: virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED); return err; @@ -331,6 +341,9 @@ static void virtio_dev_remove(struct device *_d) drv->remove(dev); + if (dev->config->destroy_avq) + dev->config->destroy_avq(dev); + /* Driver should have reset device. */ WARN_ON_ONCE(dev->config->get_status(dev)); @@ -489,13 +502,20 @@ EXPORT_SYMBOL_GPL(unregister_virtio_device); int virtio_device_freeze(struct virtio_device *dev) { struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); + int ret; virtio_config_disable(dev); dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED; - if (drv && drv->freeze) - return drv->freeze(dev); + if (drv && drv->freeze) { + ret = drv->freeze(dev); + if (ret) + return ret; + } + + if (dev->config->destroy_avq) + dev->config->destroy_avq(dev); return 0; } @@ -532,10 +552,16 @@ int virtio_device_restore(struct virtio_device *dev) if (ret) goto err; + if (dev->config->create_avq) { + ret = dev->config->create_avq(dev); + if (ret) + goto err; + } + if (drv->restore) { ret = drv->restore(dev); if (ret) - goto err; + goto err_restore; } /* If restore didn't do it, mark device DRIVER_OK ourselves. */ @@ -546,6 +572,9 @@ int virtio_device_restore(struct virtio_device *dev) return 0; +err_restore: + if (dev->config->destroy_avq) + dev->config->destroy_avq(dev); err: virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED); return ret; diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 7a5593997e0e..fafd13d0e4d4 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -236,6 +236,9 @@ void vp_del_vqs(struct virtio_device *vdev) int i; list_for_each_entry_safe(vq, n, &vdev->vqs, list) { + if (vp_dev->is_avq(vdev, vq->index)) + continue; + if (vp_dev->per_vq_vectors) { int v = vp_dev->vqs[vq->index]->msix_vector; diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index 4b773bd7c58c..7306128e63e9 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -41,6 +41,14 @@ struct virtio_pci_vq_info { unsigned int msix_vector; }; +struct virtio_pci_admin_vq { + /* Virtqueue info associated with this admin queue. */ + struct virtio_pci_vq_info info; + /* Name of the admin queue: avq.$vq_index. */ + char name[10]; + u16 vq_index; +}; + /* Our device structure */ struct virtio_pci_device { struct virtio_device vdev; @@ -58,9 +66,13 @@ struct virtio_pci_device { spinlock_t lock; struct list_head virtqueues; - /* array of all queues for house-keeping */ + /* Array of all virtqueues reported in the + * PCI common config num_queues field + */ struct virtio_pci_vq_info **vqs; + struct virtio_pci_admin_vq admin_vq; + /* MSI-X support */ int msix_enabled; int intx_enabled; @@ -86,6 +98,7 @@ struct virtio_pci_device { void (*del_vq)(struct virtio_pci_vq_info *info); u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector); + bool (*is_avq)(struct virtio_device *vdev, unsigned int index); }; /* Constants for MSI-X */ diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index ee6a386d250b..ce915018b5b0 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -19,6 +19,8 @@ #define VIRTIO_RING_NO_LEGACY #include "virtio_pci_common.h" +#define VIRTIO_AVQ_SGS_MAX 4 + static u64 vp_get_features(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); @@ -26,6 +28,16 @@ static u64 vp_get_features(struct virtio_device *vdev) return vp_modern_get_features(&vp_dev->mdev); } +static bool vp_is_avq(struct virtio_device *vdev, unsigned int index) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + + if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) + return false; + + return index == vp_dev->admin_vq.vq_index; +} + static void vp_transport_features(struct virtio_device *vdev, u64 features) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); @@ -37,6 +49,9 @@ static void vp_transport_features(struct virtio_device *vdev, u64 features) if (features & BIT_ULL(VIRTIO_F_RING_RESET)) __virtio_set_bit(vdev, VIRTIO_F_RING_RESET); + + if (features & BIT_ULL(VIRTIO_F_ADMIN_VQ)) + __virtio_set_bit(vdev, VIRTIO_F_ADMIN_VQ); } static int __vp_check_common_size_one_feature(struct virtio_device *vdev, u32 fbit, @@ -69,6 +84,9 @@ static int vp_check_common_size(struct virtio_device *vdev) if (vp_check_common_size_one_feature(vdev, VIRTIO_F_RING_RESET, queue_reset)) return -EINVAL; + if (vp_check_common_size_one_feature(vdev, VIRTIO_F_ADMIN_VQ, admin_queue_num)) + return -EINVAL; + return 0; } @@ -345,6 +363,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, struct virtio_pci_modern_device *mdev = &vp_dev->mdev; bool (*notify)(struct virtqueue *vq); struct virtqueue *vq; + bool is_avq; u16 num; int err; @@ -353,11 +372,13 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, else notify = vp_notify; - if (index >= vp_modern_get_num_queues(mdev)) + is_avq = vp_is_avq(&vp_dev->vdev, index); + if (index >= vp_modern_get_num_queues(mdev) && !is_avq) return ERR_PTR(-EINVAL); + num = is_avq ? + VIRTIO_AVQ_SGS_MAX : vp_modern_get_queue_size(mdev, index); /* Check if queue is either not available or already active. */ - num = vp_modern_get_queue_size(mdev, index); if (!num || vp_modern_get_queue_enable(mdev, index)) return ERR_PTR(-ENOENT); @@ -383,6 +404,9 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, goto err; } + if (is_avq) + vp_dev->admin_vq.info.vq = vq; + return vq; err: @@ -418,6 +442,9 @@ static void del_vq(struct virtio_pci_vq_info *info) struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); struct virtio_pci_modern_device *mdev = &vp_dev->mdev; + if (vp_is_avq(&vp_dev->vdev, vq->index)) + vp_dev->admin_vq.info.vq = NULL; + if (vp_dev->msix_enabled) vp_modern_queue_vector(mdev, vq->index, VIRTIO_MSI_NO_VECTOR); @@ -527,6 +554,45 @@ static bool vp_get_shm_region(struct virtio_device *vdev, return true; } +static int vp_modern_create_avq(struct virtio_device *vdev) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_pci_admin_vq *avq; + struct virtqueue *vq; + u16 admin_q_num; + + if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) + return 0; + + admin_q_num = vp_modern_avq_num(&vp_dev->mdev); + if (!admin_q_num) + return -EINVAL; + + avq = &vp_dev->admin_vq; + avq->vq_index = vp_modern_avq_index(&vp_dev->mdev); + sprintf(avq->name, "avq.%u", avq->vq_index); + vq = vp_dev->setup_vq(vp_dev, &vp_dev->admin_vq.info, avq->vq_index, NULL, + avq->name, NULL, VIRTIO_MSI_NO_VECTOR); + if (IS_ERR(vq)) { + dev_err(&vdev->dev, "failed to setup admin virtqueue, err=%ld", + PTR_ERR(vq)); + return PTR_ERR(vq); + } + + vp_modern_set_queue_enable(&vp_dev->mdev, avq->info.vq->index, true); + return 0; +} + +static void vp_modern_destroy_avq(struct virtio_device *vdev) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + + if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) + return; + + vp_dev->del_vq(&vp_dev->admin_vq.info); +} + static const struct virtio_config_ops virtio_pci_config_nodev_ops = { .get = NULL, .set = NULL, @@ -545,6 +611,8 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = { .get_shm_region = vp_get_shm_region, .disable_vq_and_reset = vp_modern_disable_vq_and_reset, .enable_vq_after_reset = vp_modern_enable_vq_after_reset, + .create_avq = vp_modern_create_avq, + .destroy_avq = vp_modern_destroy_avq, }; static const struct virtio_config_ops virtio_pci_config_ops = { @@ -565,6 +633,8 @@ static const struct virtio_config_ops virtio_pci_config_ops = { .get_shm_region = vp_get_shm_region, .disable_vq_and_reset = vp_modern_disable_vq_and_reset, .enable_vq_after_reset = vp_modern_enable_vq_after_reset, + .create_avq = vp_modern_create_avq, + .destroy_avq = vp_modern_destroy_avq, }; /* the PCI probing function */ @@ -588,6 +658,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) vp_dev->config_vector = vp_config_vector; vp_dev->setup_vq = setup_vq; vp_dev->del_vq = del_vq; + vp_dev->is_avq = vp_is_avq; vp_dev->isr = mdev->isr; vp_dev->vdev.id = mdev->id; diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c index 7de8b1ebabac..0d3dbfaf4b23 100644 --- a/drivers/virtio/virtio_pci_modern_dev.c +++ b/drivers/virtio/virtio_pci_modern_dev.c @@ -207,6 +207,10 @@ static inline void check_offsets(void) offsetof(struct virtio_pci_modern_common_cfg, queue_notify_data)); BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_RESET != offsetof(struct virtio_pci_modern_common_cfg, queue_reset)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_ADM_Q_IDX != + offsetof(struct virtio_pci_modern_common_cfg, admin_queue_index)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_ADM_Q_NUM != + offsetof(struct virtio_pci_modern_common_cfg, admin_queue_num)); } /* @@ -296,7 +300,7 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev) mdev->common = vp_modern_map_capability(mdev, common, sizeof(struct virtio_pci_common_cfg), 4, 0, offsetofend(struct virtio_pci_modern_common_cfg, - queue_reset), + admin_queue_num), &mdev->common_len, NULL); if (!mdev->common) goto err_map_common; @@ -719,6 +723,24 @@ void __iomem *vp_modern_map_vq_notify(struct virtio_pci_modern_device *mdev, } EXPORT_SYMBOL_GPL(vp_modern_map_vq_notify); +u16 vp_modern_avq_num(struct virtio_pci_modern_device *mdev) +{ + struct virtio_pci_modern_common_cfg __iomem *cfg; + + cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common; + return vp_ioread16(&cfg->admin_queue_num); +} +EXPORT_SYMBOL_GPL(vp_modern_avq_num); + +u16 vp_modern_avq_index(struct virtio_pci_modern_device *mdev) +{ + struct virtio_pci_modern_common_cfg __iomem *cfg; + + cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common; + return vp_ioread16(&cfg->admin_queue_index); +} +EXPORT_SYMBOL_GPL(vp_modern_avq_index); + MODULE_VERSION("0.1"); MODULE_DESCRIPTION("Modern Virtio PCI Device"); MODULE_AUTHOR("Jason Wang "); diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 2b3438de2c4d..da9b271b54db 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -93,6 +93,8 @@ typedef void vq_callback_t(struct virtqueue *); * Returns 0 on success or error status * If disable_vq_and_reset is set, then enable_vq_after_reset must also be * set. + * @create_avq: create admin virtqueue resource. + * @destroy_avq: destroy admin virtqueue resource. */ struct virtio_config_ops { void (*get)(struct virtio_device *vdev, unsigned offset, @@ -120,6 +122,8 @@ struct virtio_config_ops { struct virtio_shm_region *region, u8 id); int (*disable_vq_and_reset)(struct virtqueue *vq); int (*enable_vq_after_reset)(struct virtqueue *vq); + int (*create_avq)(struct virtio_device *vdev); + void (*destroy_avq)(struct virtio_device *vdev); }; /* If driver didn't advertise the feature, it will never appear. */ diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h index a09e13a577a9..c0b1b1ca1163 100644 --- a/include/linux/virtio_pci_modern.h +++ b/include/linux/virtio_pci_modern.h @@ -125,4 +125,6 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev); void vp_modern_remove(struct virtio_pci_modern_device *mdev); int vp_modern_get_queue_reset(struct virtio_pci_modern_device *mdev, u16 index); void vp_modern_set_queue_reset(struct virtio_pci_modern_device *mdev, u16 index); +u16 vp_modern_avq_num(struct virtio_pci_modern_device *mdev); +u16 vp_modern_avq_index(struct virtio_pci_modern_device *mdev); #endif diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index 44f4dd2add18..240ddeef7eae 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -175,6 +175,9 @@ struct virtio_pci_modern_common_cfg { __le16 queue_notify_data; /* read-write */ __le16 queue_reset; /* read-write */ + + __le16 admin_queue_index; /* read-only */ + __le16 admin_queue_num; /* read-only */ }; /* Fields in VIRTIO_PCI_CAP_PCI_CFG: */ @@ -215,6 +218,8 @@ struct virtio_pci_cfg_cap { #define VIRTIO_PCI_COMMON_Q_USEDHI 52 #define VIRTIO_PCI_COMMON_Q_NDATA 56 #define VIRTIO_PCI_COMMON_Q_RESET 58 +#define VIRTIO_PCI_COMMON_ADM_Q_IDX 60 +#define VIRTIO_PCI_COMMON_ADM_Q_NUM 62 #endif /* VIRTIO_PCI_NO_MODERN */ -- cgit From 92792ac752aa80d5ee71bc291d90edd06cd76bd1 Mon Sep 17 00:00:00 2001 From: Feng Liu Date: Tue, 19 Dec 2023 11:32:41 +0200 Subject: virtio-pci: Introduce admin command sending function Add support for sending admin command through admin virtqueue interface. Abort any inflight admin commands once device reset completes. Activate admin queue when device becomes ready; deactivate on device reset. To comply to the below specification statement [1], the admin virtqueue is activated for upper layer users only after setting DRIVER_OK status. [1] The driver MUST NOT send any buffer available notifications to the device before setting DRIVER_OK. Signed-off-by: Feng Liu Reviewed-by: Parav Pandit Acked-by: Michael S. Tsirkin Signed-off-by: Yishai Hadas Link: https://lore.kernel.org/r/20231219093247.170936-4-yishaih@nvidia.com Signed-off-by: Alex Williamson --- drivers/virtio/virtio_pci_common.h | 6 ++ drivers/virtio/virtio_pci_modern.c | 143 ++++++++++++++++++++++++++++++++++++- include/linux/virtio.h | 8 +++ include/uapi/linux/virtio_pci.h | 22 ++++++ 4 files changed, 177 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index 7306128e63e9..282d087a9266 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -29,6 +29,7 @@ #include #include #include +#include struct virtio_pci_vq_info { /* the actual virtqueue */ @@ -44,6 +45,8 @@ struct virtio_pci_vq_info { struct virtio_pci_admin_vq { /* Virtqueue info associated with this admin queue. */ struct virtio_pci_vq_info info; + /* serializing admin commands execution and virtqueue deletion */ + struct mutex cmd_lock; /* Name of the admin queue: avq.$vq_index. */ char name[10]; u16 vq_index; @@ -152,4 +155,7 @@ static inline void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev) int virtio_pci_modern_probe(struct virtio_pci_device *); void virtio_pci_modern_remove(struct virtio_pci_device *); +int vp_modern_admin_cmd_exec(struct virtio_device *vdev, + struct virtio_admin_cmd *cmd); + #endif diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index ce915018b5b0..9bd66300a80a 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -38,6 +38,132 @@ static bool vp_is_avq(struct virtio_device *vdev, unsigned int index) return index == vp_dev->admin_vq.vq_index; } +static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq, + struct scatterlist **sgs, + unsigned int out_num, + unsigned int in_num, + void *data) +{ + struct virtqueue *vq; + int ret, len; + + vq = admin_vq->info.vq; + if (!vq) + return -EIO; + + ret = virtqueue_add_sgs(vq, sgs, out_num, in_num, data, GFP_KERNEL); + if (ret < 0) + return -EIO; + + if (unlikely(!virtqueue_kick(vq))) + return -EIO; + + while (!virtqueue_get_buf(vq, &len) && + !virtqueue_is_broken(vq)) + cpu_relax(); + + if (virtqueue_is_broken(vq)) + return -EIO; + + return 0; +} + +int vp_modern_admin_cmd_exec(struct virtio_device *vdev, + struct virtio_admin_cmd *cmd) +{ + struct scatterlist *sgs[VIRTIO_AVQ_SGS_MAX], hdr, stat; + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_admin_cmd_status *va_status; + unsigned int out_num = 0, in_num = 0; + struct virtio_admin_cmd_hdr *va_hdr; + u16 status; + int ret; + + if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) + return -EOPNOTSUPP; + + va_status = kzalloc(sizeof(*va_status), GFP_KERNEL); + if (!va_status) + return -ENOMEM; + + va_hdr = kzalloc(sizeof(*va_hdr), GFP_KERNEL); + if (!va_hdr) { + ret = -ENOMEM; + goto err_alloc; + } + + va_hdr->opcode = cmd->opcode; + va_hdr->group_type = cmd->group_type; + va_hdr->group_member_id = cmd->group_member_id; + + /* Add header */ + sg_init_one(&hdr, va_hdr, sizeof(*va_hdr)); + sgs[out_num] = &hdr; + out_num++; + + if (cmd->data_sg) { + sgs[out_num] = cmd->data_sg; + out_num++; + } + + /* Add return status */ + sg_init_one(&stat, va_status, sizeof(*va_status)); + sgs[out_num + in_num] = &stat; + in_num++; + + if (cmd->result_sg) { + sgs[out_num + in_num] = cmd->result_sg; + in_num++; + } + + mutex_lock(&vp_dev->admin_vq.cmd_lock); + ret = virtqueue_exec_admin_cmd(&vp_dev->admin_vq, sgs, + out_num, in_num, sgs); + mutex_unlock(&vp_dev->admin_vq.cmd_lock); + + if (ret) { + dev_err(&vdev->dev, + "Failed to execute command on admin vq: %d\n.", ret); + goto err_cmd_exec; + } + + status = le16_to_cpu(va_status->status); + if (status != VIRTIO_ADMIN_STATUS_OK) { + dev_err(&vdev->dev, + "admin command error: status(%#x) qualifier(%#x)\n", + status, le16_to_cpu(va_status->status_qualifier)); + ret = -status; + } + +err_cmd_exec: + kfree(va_hdr); +err_alloc: + kfree(va_status); + return ret; +} + +static void vp_modern_avq_activate(struct virtio_device *vdev) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq; + + if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) + return; + + __virtqueue_unbreak(admin_vq->info.vq); +} + +static void vp_modern_avq_deactivate(struct virtio_device *vdev) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq; + + if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) + return; + + __virtqueue_break(admin_vq->info.vq); +} + static void vp_transport_features(struct virtio_device *vdev, u64 features) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); @@ -213,6 +339,8 @@ static void vp_set_status(struct virtio_device *vdev, u8 status) /* We should never be setting status to 0. */ BUG_ON(status == 0); vp_modern_set_status(&vp_dev->mdev, status); + if (status & VIRTIO_CONFIG_S_DRIVER_OK) + vp_modern_avq_activate(vdev); } static void vp_reset(struct virtio_device *vdev) @@ -229,6 +357,9 @@ static void vp_reset(struct virtio_device *vdev) */ while (vp_modern_get_status(mdev)) msleep(1); + + vp_modern_avq_deactivate(vdev); + /* Flush pending VQ/configuration callbacks. */ vp_synchronize_vectors(vdev); } @@ -404,8 +535,11 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, goto err; } - if (is_avq) + if (is_avq) { + mutex_lock(&vp_dev->admin_vq.cmd_lock); vp_dev->admin_vq.info.vq = vq; + mutex_unlock(&vp_dev->admin_vq.cmd_lock); + } return vq; @@ -442,8 +576,11 @@ static void del_vq(struct virtio_pci_vq_info *info) struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); struct virtio_pci_modern_device *mdev = &vp_dev->mdev; - if (vp_is_avq(&vp_dev->vdev, vq->index)) + if (vp_is_avq(&vp_dev->vdev, vq->index)) { + mutex_lock(&vp_dev->admin_vq.cmd_lock); vp_dev->admin_vq.info.vq = NULL; + mutex_unlock(&vp_dev->admin_vq.cmd_lock); + } if (vp_dev->msix_enabled) vp_modern_queue_vector(mdev, vq->index, @@ -662,6 +799,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) vp_dev->isr = mdev->isr; vp_dev->vdev.id = mdev->id; + mutex_init(&vp_dev->admin_vq.cmd_lock); return 0; } @@ -669,5 +807,6 @@ void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev) { struct virtio_pci_modern_device *mdev = &vp_dev->mdev; + mutex_destroy(&vp_dev->admin_vq.cmd_lock); vp_modern_remove(mdev); } diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 4cc614a38376..b0201747a263 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -103,6 +103,14 @@ int virtqueue_resize(struct virtqueue *vq, u32 num, int virtqueue_reset(struct virtqueue *vq, void (*recycle)(struct virtqueue *vq, void *buf)); +struct virtio_admin_cmd { + __le16 opcode; + __le16 group_type; + __le64 group_member_id; + struct scatterlist *data_sg; + struct scatterlist *result_sg; +}; + /** * struct virtio_device - representation of a device using virtio * @index: unique position on the virtio bus diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index 240ddeef7eae..187fd9e34a30 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -223,4 +223,26 @@ struct virtio_pci_cfg_cap { #endif /* VIRTIO_PCI_NO_MODERN */ +/* Admin command status. */ +#define VIRTIO_ADMIN_STATUS_OK 0 + +struct __packed virtio_admin_cmd_hdr { + __le16 opcode; + /* + * 1 - SR-IOV + * 2-65535 - reserved + */ + __le16 group_type; + /* Unused, reserved for future extensions. */ + __u8 reserved1[12]; + __le64 group_member_id; +}; + +struct __packed virtio_admin_cmd_status { + __le16 status; + __le16 status_qualifier; + /* Unused, reserved for future extensions. */ + __u8 reserved2[4]; +}; + #endif -- cgit From 388431b9f59bbfde2b5f2fe032b0836158b09ad0 Mon Sep 17 00:00:00 2001 From: Feng Liu Date: Tue, 19 Dec 2023 11:32:42 +0200 Subject: virtio-pci: Introduce admin commands Introduces admin commands, as follow: The "list query" command can be used by the driver to query the set of admin commands supported by the virtio device. The "list use" command is used to inform the virtio device which admin commands the driver will use. The "legacy common cfg rd/wr" commands are used to read from/write into the legacy common configuration structure. The "legacy dev cfg rd/wr" commands are used to read from/write into the legacy device configuration structure. The "notify info" command is used to query the notification region information. Signed-off-by: Feng Liu Reviewed-by: Parav Pandit Reviewed-by: Jiri Pirko Acked-by: Michael S. Tsirkin Signed-off-by: Yishai Hadas Link: https://lore.kernel.org/r/20231219093247.170936-5-yishaih@nvidia.com Signed-off-by: Alex Williamson --- include/uapi/linux/virtio_pci.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index 187fd9e34a30..ef3810dee7ef 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -226,6 +226,20 @@ struct virtio_pci_cfg_cap { /* Admin command status. */ #define VIRTIO_ADMIN_STATUS_OK 0 +/* Admin command opcode. */ +#define VIRTIO_ADMIN_CMD_LIST_QUERY 0x0 +#define VIRTIO_ADMIN_CMD_LIST_USE 0x1 + +/* Admin command group type. */ +#define VIRTIO_ADMIN_GROUP_TYPE_SRIOV 0x1 + +/* Transitional device admin command. */ +#define VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE 0x2 +#define VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ 0x3 +#define VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_WRITE 0x4 +#define VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ 0x5 +#define VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO 0x6 + struct __packed virtio_admin_cmd_hdr { __le16 opcode; /* @@ -245,4 +259,31 @@ struct __packed virtio_admin_cmd_status { __u8 reserved2[4]; }; +struct __packed virtio_admin_cmd_legacy_wr_data { + __u8 offset; /* Starting offset of the register(s) to write. */ + __u8 reserved[7]; + __u8 registers[]; +}; + +struct __packed virtio_admin_cmd_legacy_rd_data { + __u8 offset; /* Starting offset of the register(s) to read. */ +}; + +#define VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_END 0 +#define VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_OWNER_DEV 0x1 +#define VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_OWNER_MEM 0x2 + +#define VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO 4 + +struct __packed virtio_admin_cmd_notify_info_data { + __u8 flags; /* 0 = end of list, 1 = owner device, 2 = member device */ + __u8 bar; /* BAR of the member or the owner device */ + __u8 padding[6]; + __le64 offset; /* Offset within bar. */ +}; + +struct virtio_admin_cmd_notify_info_result { + struct virtio_admin_cmd_notify_info_data entries[VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO]; +}; + #endif -- cgit From e37a11fca41864c9f652ff81296b82e6f65a4242 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sun, 17 Dec 2023 10:32:36 +0200 Subject: bridge: add MDB state mask uAPI attribute Currently, the 'state' field in 'struct br_port_msg' can be set to 1 if the MDB entry is permanent or 0 if it is temporary. Additional states might be added in the future. In a similar fashion to 'NDA_NDM_STATE_MASK', add an MDB state mask uAPI attribute that will allow the upcoming bulk deletion API to bulk delete MDB entries with a certain state or any state. Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 2e23f99dc0f1..a5b743a2f775 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -757,6 +757,7 @@ enum { MDBE_ATTR_VNI, MDBE_ATTR_IFINDEX, MDBE_ATTR_SRC_VNI, + MDBE_ATTR_STATE_MASK, __MDBE_ATTR_MAX, }; #define MDBE_ATTR_MAX (__MDBE_ATTR_MAX - 1) -- cgit From cbc2fe9d9cb226347365753f50d81bc48cc3c52e Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 13 Dec 2023 13:57:41 +0800 Subject: kexec_file: add kexec_file flag to control debug printing Patch series "kexec_file: print out debugging message if required", v4. Currently, specifying '-d' on kexec command will print a lot of debugging informationabout kexec/kdump loading with kexec_load interface. However, kexec_file_load prints nothing even though '-d' is specified. It's very inconvenient to debug or analyze the kexec/kdump loading when something wrong happened with kexec/kdump itself or develper want to check the kexec/kdump loading. In this patchset, a kexec_file flag is KEXEC_FILE_DEBUG added and checked in code. If it's passed in, debugging message of kexec_file code will be printed out and can be seen from console and dmesg. Otherwise, the debugging message is printed like beofre when pr_debug() is taken. Note: **** ===== 1) The code in kexec-tools utility also need be changed to support passing KEXEC_FILE_DEBUG to kernel when 'kexec -s -d' is specified. The patch link is here: ========= [PATCH] kexec_file: add kexec_file flag to support debug printing http://lists.infradead.org/pipermail/kexec/2023-November/028505.html 2) s390 also has kexec_file code, while I am not sure what debugging information is necessary. So leave it to s390 developer. Test: **** ==== Testing was done in v1 on x86_64 and arm64. For v4, tested on x86_64 again. And on x86_64, the printed messages look like below: -------------------------------------------------------------- kexec measurement buffer for the loaded kernel at 0x207fffe000. Loaded purgatory at 0x207fff9000 Loaded boot_param, command line and misc at 0x207fff3000 bufsz=0x1180 memsz=0x1180 Loaded 64bit kernel at 0x207c000000 bufsz=0xc88200 memsz=0x3c4a000 Loaded initrd at 0x2079e79000 bufsz=0x2186280 memsz=0x2186280 Final command line is: root=/dev/mapper/fedora_intel--knightslanding--lb--02-root ro rd.lvm.lv=fedora_intel-knightslanding-lb-02/root console=ttyS0,115200N81 crashkernel=256M E820 memmap: 0000000000000000-000000000009a3ff (1) 000000000009a400-000000000009ffff (2) 00000000000e0000-00000000000fffff (2) 0000000000100000-000000006ff83fff (1) 000000006ff84000-000000007ac50fff (2) ...... 000000207fff6150-000000207fff615f (128) 000000207fff6160-000000207fff714f (1) 000000207fff7150-000000207fff715f (128) 000000207fff7160-000000207fff814f (1) 000000207fff8150-000000207fff815f (128) 000000207fff8160-000000207fffffff (1) nr_segments = 5 segment[0]: buf=0x000000004e5ece74 bufsz=0x211 mem=0x207fffe000 memsz=0x1000 segment[1]: buf=0x000000009e871498 bufsz=0x4000 mem=0x207fff9000 memsz=0x5000 segment[2]: buf=0x00000000d879f1fe bufsz=0x1180 mem=0x207fff3000 memsz=0x2000 segment[3]: buf=0x000000001101cd86 bufsz=0xc88200 mem=0x207c000000 memsz=0x3c4a000 segment[4]: buf=0x00000000c6e38ac7 bufsz=0x2186280 mem=0x2079e79000 memsz=0x2187000 kexec_file_load: type:0, start:0x207fff91a0 head:0x109e004002 flags:0x8 --------------------------------------------------------------------------- This patch (of 7): When specifying 'kexec -c -d', kexec_load interface will print loading information, e.g the regions where kernel/initrd/purgatory/cmdline are put, the memmap passed to 2nd kernel taken as system RAM ranges, and printing all contents of struct kexec_segment, etc. These are very helpful for analyzing or positioning what's happening when kexec/kdump itself failed. The debugging printing for kexec_load interface is made in user space utility kexec-tools. Whereas, with kexec_file_load interface, 'kexec -s -d' print nothing. Because kexec_file code is mostly implemented in kernel space, and the debugging printing functionality is missed. It's not convenient when debugging kexec/kdump loading and jumping with kexec_file_load interface. Now add KEXEC_FILE_DEBUG to kexec_file flag to control the debugging message printing. And add global variable kexec_file_dbg_print and macro kexec_dprintk() to facilitate the printing. This is a preparation, later kexec_dprintk() will be used to replace the existing pr_debug(). Once 'kexec -s -d' is specified, it will print out kexec/kdump loading information. If '-d' is not specified, it regresses to pr_debug(). Link: https://lkml.kernel.org/r/20231213055747.61826-1-bhe@redhat.com Link: https://lkml.kernel.org/r/20231213055747.61826-2-bhe@redhat.com Signed-off-by: Baoquan He Cc: Conor Dooley Cc: Joe Perches Cc: Nathan Chancellor Signed-off-by: Andrew Morton --- include/linux/kexec.h | 9 ++++++++- include/uapi/linux/kexec.h | 1 + kernel/kexec_core.c | 2 ++ kernel/kexec_file.c | 3 +++ 4 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 8227455192b7..400cb6c02176 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -403,7 +403,7 @@ bool kexec_load_permitted(int kexec_image_type); /* List of defined/legal kexec file flags */ #define KEXEC_FILE_FLAGS (KEXEC_FILE_UNLOAD | KEXEC_FILE_ON_CRASH | \ - KEXEC_FILE_NO_INITRAMFS) + KEXEC_FILE_NO_INITRAMFS | KEXEC_FILE_DEBUG) /* flag to track if kexec reboot is in progress */ extern bool kexec_in_progress; @@ -500,6 +500,13 @@ static inline int crash_hotplug_memory_support(void) { return 0; } static inline unsigned int crash_get_elfcorehdr_size(void) { return 0; } #endif +extern bool kexec_file_dbg_print; + +#define kexec_dprintk(fmt, ...) \ + printk("%s" fmt, \ + kexec_file_dbg_print ? KERN_INFO : KERN_DEBUG, \ + ##__VA_ARGS__) + #else /* !CONFIG_KEXEC_CORE */ struct pt_regs; struct task_struct; diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index 01766dd839b0..c17bb096ea68 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -25,6 +25,7 @@ #define KEXEC_FILE_UNLOAD 0x00000001 #define KEXEC_FILE_ON_CRASH 0x00000002 #define KEXEC_FILE_NO_INITRAMFS 0x00000004 +#define KEXEC_FILE_DEBUG 0x00000008 /* These values match the ELF architecture values. * Unless there is a good reason that should continue to be the case. diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index bc4c096ab1f3..64072acef2b6 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -52,6 +52,8 @@ atomic_t __kexec_lock = ATOMIC_INIT(0); /* Flag to indicate we are going to kexec a new kernel */ bool kexec_in_progress = false; +bool kexec_file_dbg_print; + int kexec_should_crash(struct task_struct *p) { /* diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index ba3ef30921b8..3ee204474de6 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -123,6 +123,8 @@ void kimage_file_post_load_cleanup(struct kimage *image) */ kfree(image->image_loader_data); image->image_loader_data = NULL; + + kexec_file_dbg_print = false; } #ifdef CONFIG_KEXEC_SIG @@ -278,6 +280,7 @@ kimage_file_alloc_init(struct kimage **rimage, int kernel_fd, if (!image) return -ENOMEM; + kexec_file_dbg_print = !!(flags & KEXEC_FILE_DEBUG); image->file_mode = 1; if (kexec_on_panic) { -- cgit From 1ef83969bb12e594fe44ceba406095e80a824c91 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 11 Dec 2023 15:12:04 -0500 Subject: uapi/linux/resource.h: fix include We should't be depending on time.h; we should only be pulling in other uapi headers. Signed-off-by: Kent Overstreet --- include/uapi/linux/resource.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/resource.h b/include/uapi/linux/resource.h index ac5d6a3031db..4fc22908bc09 100644 --- a/include/uapi/linux/resource.h +++ b/include/uapi/linux/resource.h @@ -2,7 +2,7 @@ #ifndef _UAPI_LINUX_RESOURCE_H #define _UAPI_LINUX_RESOURCE_H -#include +#include #include /* -- cgit From d293b1a89694fc4918d9a4330a71ba2458f9d581 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 21 Dec 2023 09:02:57 -0700 Subject: io_uring/kbuf: add method for returning provided buffer ring head The tail of the provided ring buffer is shared between the kernel and the application, but the head is private to the kernel as the application doesn't need to see it. However, this also prevents the application from knowing how many buffers the kernel has consumed. Usually this is fine, as the information is inherently racy in that the kernel could be consuming buffers continually, but for cleanup purposes it may be relevant to know how many buffers are still left in the ring. Add IORING_REGISTER_PBUF_STATUS which will return status for a given provided buffer ring. Right now it just returns the head, but space is reserved for more information later in, if needed. Link: https://github.com/axboe/liburing/discussions/1020 Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 10 ++++++++++ io_uring/kbuf.c | 26 ++++++++++++++++++++++++++ io_uring/kbuf.h | 1 + io_uring/register.c | 6 ++++++ 4 files changed, 43 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index db4b913e6b39..7a673b52827b 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -567,6 +567,9 @@ enum { /* register a range of fixed file slots for automatic slot allocation */ IORING_REGISTER_FILE_ALLOC_RANGE = 25, + /* return status information for a buffer group */ + IORING_REGISTER_PBUF_STATUS = 26, + /* this goes last */ IORING_REGISTER_LAST, @@ -693,6 +696,13 @@ struct io_uring_buf_reg { __u64 resv[3]; }; +/* argument for IORING_REGISTER_PBUF_STATUS */ +struct io_uring_buf_status { + __u32 buf_group; /* input */ + __u32 head; /* output */ + __u32 resv[8]; +}; + /* * io_uring_restriction->opcode values */ diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index 72b6af1d2ed3..18df5a9d2f5e 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -750,6 +750,32 @@ int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) return 0; } +int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg) +{ + struct io_uring_buf_status buf_status; + struct io_buffer_list *bl; + int i; + + if (copy_from_user(&buf_status, arg, sizeof(buf_status))) + return -EFAULT; + + for (i = 0; i < ARRAY_SIZE(buf_status.resv); i++) + if (buf_status.resv[i]) + return -EINVAL; + + bl = io_buffer_get_list(ctx, buf_status.buf_group); + if (!bl) + return -ENOENT; + if (!bl->is_mapped) + return -EINVAL; + + buf_status.head = bl->head; + if (copy_to_user(arg, &buf_status, sizeof(buf_status))) + return -EFAULT; + + return 0; +} + void *io_pbuf_get_address(struct io_ring_ctx *ctx, unsigned long bgid) { struct io_buffer_list *bl; diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h index 9be5960817ea..53dfaa71a397 100644 --- a/io_uring/kbuf.h +++ b/io_uring/kbuf.h @@ -53,6 +53,7 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags); int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg); int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg); +int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg); void io_kbuf_mmap_list_free(struct io_ring_ctx *ctx); diff --git a/io_uring/register.c b/io_uring/register.c index a4286029e920..708dd1d89add 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -542,6 +542,12 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_register_file_alloc_range(ctx, arg); break; + case IORING_REGISTER_PBUF_STATUS: + ret = -EINVAL; + if (!arg || nr_args != 1) + break; + ret = io_register_pbuf_status(ctx, arg); + break; default: ret = -EINVAL; break; -- cgit From 41a313d875e0c5822efb50e8221b8d58811609bb Mon Sep 17 00:00:00 2001 From: Andrei Otcheretianski Date: Wed, 20 Dec 2023 13:41:34 +0200 Subject: wifi: cfg80211: reg: Support P2P operation on DFS channels FCC-594280 D01 Section B.3 allows peer-to-peer and ad hoc devices to operate on DFS channels while they operate under the control of a concurrent DFS master. For example, it is possible to have a P2P GO on a DFS channel as long as BSS connection is active on the same channel. Allow such operation by adding additional regulatory flags to indicate DFS concurrent channels and capable devices. Add the required relaxations in DFS regulatory checks. Signed-off-by: Andrei Otcheretianski Reviewed-by: Gregory Greenman Signed-off-by: Miri Korenblit Link: https://msgid.link/20231220133549.bdfb8a9c7c54.I973563562969a27fea8ec5685b96a3a47afe142f@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 + include/uapi/linux/nl80211.h | 16 ++++++++ net/wireless/chan.c | 94 ++++++++++++++++++++++++++++++++++++++++---- net/wireless/nl80211.c | 3 ++ net/wireless/reg.c | 2 + 5 files changed, 110 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 92b956944c9f..501d4421514f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -117,6 +117,7 @@ struct wiphy; * This may be due to the driver or due to regulatory bandwidth * restrictions. * @IEEE80211_CHAN_NO_EHT: EHT operation is not permitted on this channel. + * @IEEE80211_CHAN_DFS_CONCURRENT: See %NL80211_RRF_DFS_CONCURRENT */ enum ieee80211_channel_flags { IEEE80211_CHAN_DISABLED = 1<<0, @@ -140,6 +141,7 @@ enum ieee80211_channel_flags { IEEE80211_CHAN_16MHZ = 1<<18, IEEE80211_CHAN_NO_320MHZ = 1<<19, IEEE80211_CHAN_NO_EHT = 1<<20, + IEEE80211_CHAN_DFS_CONCURRENT = 1<<21, }; #define IEEE80211_CHAN_NO_HT40 \ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index a682b54bd3ba..466da830e65f 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4256,6 +4256,10 @@ enum nl80211_wmm_rule { * in current regulatory domain. * @NL80211_FREQUENCY_ATTR_PSD: Power spectral density (in dBm) that * is allowed on this channel in current regulatory domain. + * @NL80211_FREQUENCY_ATTR_DFS_CONCURRENT: Operation on this channel is + * allowed for peer-to-peer or adhoc communication under the control + * of a DFS master which operates on the same channel (FCC-594280 D01 + * Section B.3). Should be used together with %NL80211_RRF_DFS only. * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number * currently defined * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use @@ -4295,6 +4299,7 @@ enum nl80211_frequency_attr { NL80211_FREQUENCY_ATTR_NO_320MHZ, NL80211_FREQUENCY_ATTR_NO_EHT, NL80211_FREQUENCY_ATTR_PSD, + NL80211_FREQUENCY_ATTR_DFS_CONCURRENT, /* keep last */ __NL80211_FREQUENCY_ATTR_AFTER_LAST, @@ -4500,6 +4505,10 @@ enum nl80211_sched_scan_match_attr { * @NL80211_RRF_NO_320MHZ: 320MHz operation not allowed * @NL80211_RRF_NO_EHT: EHT operation not allowed * @NL80211_RRF_PSD: Ruleset has power spectral density value + * @NL80211_RRF_DFS_CONCURRENT: Operation on this channel is allowed for + peer-to-peer or adhoc communication under the control of a DFS master + which operates on the same channel (FCC-594280 D01 Section B.3). + Should be used together with %NL80211_RRF_DFS only. */ enum nl80211_reg_rule_flags { NL80211_RRF_NO_OFDM = 1<<0, @@ -4521,6 +4530,7 @@ enum nl80211_reg_rule_flags { NL80211_RRF_NO_320MHZ = 1<<18, NL80211_RRF_NO_EHT = 1<<19, NL80211_RRF_PSD = 1<<20, + NL80211_RRF_DFS_CONCURRENT = 1<<21, }; #define NL80211_RRF_PASSIVE_SCAN NL80211_RRF_NO_IR @@ -6492,6 +6502,11 @@ enum nl80211_feature_flags { * @NL80211_EXT_FEATURE_OWE_OFFLOAD_AP: Driver/Device wants to do OWE DH IE * handling in AP mode. * + * @NL80211_EXT_FEATURE_DFS_CONCURRENT: The device supports peer-to-peer or + * ad hoc operation on DFS channels under the control of a concurrent + * DFS master on the same channel as described in FCC-594280 D01 + * (Section B.3). This, for example, allows P2P GO and P2P clients to + * operate on DFS channels as long as there's a concurrent BSS connection. * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -6565,6 +6580,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_AUTH_AND_DEAUTH_RANDOM_TA, NL80211_EXT_FEATURE_OWE_OFFLOAD, NL80211_EXT_FEATURE_OWE_OFFLOAD_AP, + NL80211_EXT_FEATURE_DFS_CONCURRENT, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/chan.c b/net/wireless/chan.c index dfb4893421d7..ceb9174c5c3d 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -515,9 +515,83 @@ static u32 cfg80211_get_end_freq(u32 center_freq, return end_freq; } +static bool +cfg80211_dfs_permissive_check_wdev(struct cfg80211_registered_device *rdev, + enum nl80211_iftype iftype, + struct wireless_dev *wdev, + struct ieee80211_channel *chan) +{ + unsigned int link_id; + + for_each_valid_link(wdev, link_id) { + struct ieee80211_channel *other_chan = NULL; + struct cfg80211_chan_def chandef = {}; + int ret; + + /* In order to avoid daisy chaining only allow BSS STA */ + if (wdev->iftype != NL80211_IFTYPE_STATION || + !wdev->links[link_id].client.current_bss) + continue; + + other_chan = + wdev->links[link_id].client.current_bss->pub.channel; + + if (!other_chan) + continue; + + if (chan == other_chan) + return true; + + /* continue if we can't get the channel */ + ret = rdev_get_channel(rdev, wdev, link_id, &chandef); + if (ret) + continue; + + if (cfg80211_is_sub_chan(&chandef, chan, false)) + return true; + } + + return false; +} + +/* + * Check if P2P GO is allowed to operate on a DFS channel + */ +static bool cfg80211_dfs_permissive_chan(struct wiphy *wiphy, + enum nl80211_iftype iftype, + struct ieee80211_channel *chan) +{ + struct wireless_dev *wdev; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + + lockdep_assert_held(&rdev->wiphy.mtx); + + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_DFS_CONCURRENT) || + !(chan->flags & IEEE80211_CHAN_DFS_CONCURRENT)) + return false; + + /* only valid for P2P GO */ + if (iftype != NL80211_IFTYPE_P2P_GO) + return false; + + /* + * Allow only if there's a concurrent BSS + */ + list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { + bool ret = cfg80211_dfs_permissive_check_wdev(rdev, iftype, + wdev, chan); + if (ret) + return ret; + } + + return false; +} + static int cfg80211_get_chans_dfs_required(struct wiphy *wiphy, u32 center_freq, - u32 bandwidth) + u32 bandwidth, + enum nl80211_iftype iftype) { struct ieee80211_channel *c; u32 freq, start_freq, end_freq; @@ -530,9 +604,11 @@ static int cfg80211_get_chans_dfs_required(struct wiphy *wiphy, if (!c) return -EINVAL; - if (c->flags & IEEE80211_CHAN_RADAR) + if (c->flags & IEEE80211_CHAN_RADAR && + !cfg80211_dfs_permissive_chan(wiphy, iftype, c)) return 1; } + return 0; } @@ -558,7 +634,7 @@ int cfg80211_chandef_dfs_required(struct wiphy *wiphy, ret = cfg80211_get_chans_dfs_required(wiphy, ieee80211_chandef_to_khz(chandef), - width); + width, iftype); if (ret < 0) return ret; else if (ret > 0) @@ -569,7 +645,7 @@ int cfg80211_chandef_dfs_required(struct wiphy *wiphy, ret = cfg80211_get_chans_dfs_required(wiphy, MHZ_TO_KHZ(chandef->center_freq2), - width); + width, iftype); if (ret < 0) return ret; else if (ret > 0) @@ -1337,15 +1413,19 @@ static bool _cfg80211_reg_can_beacon(struct wiphy *wiphy, bool check_no_ir) { bool res; - u32 prohibited_flags = IEEE80211_CHAN_DISABLED | - IEEE80211_CHAN_RADAR; + u32 prohibited_flags = IEEE80211_CHAN_DISABLED; + int dfs_required; trace_cfg80211_reg_can_beacon(wiphy, chandef, iftype, check_no_ir); if (check_no_ir) prohibited_flags |= IEEE80211_CHAN_NO_IR; - if (cfg80211_chandef_dfs_required(wiphy, chandef, iftype) > 0 && + dfs_required = cfg80211_chandef_dfs_required(wiphy, chandef, iftype); + if (dfs_required != 0) + prohibited_flags |= IEEE80211_CHAN_RADAR; + + if (dfs_required > 0 && cfg80211_chandef_dfs_available(wiphy, chandef)) { /* We can skip IEEE80211_CHAN_NO_IR if chandef dfs available */ prohibited_flags = IEEE80211_CHAN_DISABLED; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 8b45fb420f4c..bd65c3ccc5e7 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1201,6 +1201,9 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, if ((chan->flags & IEEE80211_CHAN_NO_EHT) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_EHT)) goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_DFS_CONCURRENT) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_DFS_CONCURRENT)) + goto nla_put_failure; } if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 2ef4f6cc7a32..9a61b3322fd2 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1593,6 +1593,8 @@ static u32 map_regdom_flags(u32 rd_flags) channel_flags |= IEEE80211_CHAN_NO_320MHZ; if (rd_flags & NL80211_RRF_NO_EHT) channel_flags |= IEEE80211_CHAN_NO_EHT; + if (rd_flags & NL80211_RRF_DFS_CONCURRENT) + channel_flags |= IEEE80211_CHAN_DFS_CONCURRENT; if (rd_flags & NL80211_RRF_PSD) channel_flags |= IEEE80211_CHAN_PSD; return channel_flags; -- cgit From 645f3d85129d8aac3b896ba685fbc20a31c2c036 Mon Sep 17 00:00:00 2001 From: Mukesh Sisodiya Date: Wed, 20 Dec 2023 13:41:38 +0200 Subject: wifi: cfg80211: handle UHB AP and STA power type UHB AP send supported power type(LPI, SP, VLP) in beacon and probe response IE and STA should connect to these AP only if their regulatory support the AP power type. Beacon/Probe response are reported to userspace with reason "STA regulatory not supporting to connect to AP based on transmitted power type" and it should not connect to AP. Signed-off-by: Mukesh Sisodiya Reviewed-by: Gregory Greenman Signed-off-by: Miri Korenblit Link: https://msgid.link/20231220133549.cbfbef9170a9.I432f78438de18aa9f5c9006be12e41dc34cc47c5@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 1 + include/net/cfg80211.h | 6 ++++++ include/uapi/linux/nl80211.h | 13 +++++++++++++ net/wireless/nl80211.c | 6 ++++++ net/wireless/reg.c | 4 ++++ net/wireless/scan.c | 38 ++++++++++++++++++++++++++++++++++++++ 6 files changed, 68 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 8ad008591e32..2f5554482047 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2720,6 +2720,7 @@ static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len) #define IEEE80211_6GHZ_CTRL_REG_LPI_AP 0 #define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 +#define IEEE80211_6GHZ_CTRL_REG_VLP_AP 2 /** * struct ieee80211_he_6ghz_oper - HE 6 GHz operation Information field diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 745974d45ea4..cf79656ce09c 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -118,6 +118,10 @@ struct wiphy; * restrictions. * @IEEE80211_CHAN_NO_EHT: EHT operation is not permitted on this channel. * @IEEE80211_CHAN_DFS_CONCURRENT: See %NL80211_RRF_DFS_CONCURRENT + * @IEEE80211_CHAN_NO_UHB_VLP_CLIENT: Client connection with VLP AP + * not permitted using this channel + * @IEEE80211_CHAN_NO_UHB_AFC_CLIENT: Client connection with AFC AP + * not permitted using this channel */ enum ieee80211_channel_flags { IEEE80211_CHAN_DISABLED = 1<<0, @@ -142,6 +146,8 @@ enum ieee80211_channel_flags { IEEE80211_CHAN_NO_320MHZ = 1<<19, IEEE80211_CHAN_NO_EHT = 1<<20, IEEE80211_CHAN_DFS_CONCURRENT = 1<<21, + IEEE80211_CHAN_NO_UHB_VLP_CLIENT= 1<<22, + IEEE80211_CHAN_NO_UHB_AFC_CLIENT= 1<<23, }; #define IEEE80211_CHAN_NO_HT40 \ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 466da830e65f..1ccdcae24372 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4260,6 +4260,10 @@ enum nl80211_wmm_rule { * allowed for peer-to-peer or adhoc communication under the control * of a DFS master which operates on the same channel (FCC-594280 D01 * Section B.3). Should be used together with %NL80211_RRF_DFS only. + * @NL80211_FREQUENCY_ATTR_NO_UHB_VLP_CLIENT: Client connection to VLP AP + * not allowed using this channel + * @NL80211_FREQUENCY_ATTR_NO_UHB_AFC_CLIENT: Client connection to AFC AP + * not allowed using this channel * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number * currently defined * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use @@ -4300,6 +4304,8 @@ enum nl80211_frequency_attr { NL80211_FREQUENCY_ATTR_NO_EHT, NL80211_FREQUENCY_ATTR_PSD, NL80211_FREQUENCY_ATTR_DFS_CONCURRENT, + NL80211_FREQUENCY_ATTR_NO_UHB_VLP_CLIENT, + NL80211_FREQUENCY_ATTR_NO_UHB_AFC_CLIENT, /* keep last */ __NL80211_FREQUENCY_ATTR_AFTER_LAST, @@ -4509,6 +4515,8 @@ enum nl80211_sched_scan_match_attr { peer-to-peer or adhoc communication under the control of a DFS master which operates on the same channel (FCC-594280 D01 Section B.3). Should be used together with %NL80211_RRF_DFS only. + * @NL80211_RRF_NO_UHB_VLP_CLIENT: Client connection to VLP AP not allowed + * @NL80211_RRF_NO_UHB_AFC_CLIENT: Client connection to AFC AP not allowed */ enum nl80211_reg_rule_flags { NL80211_RRF_NO_OFDM = 1<<0, @@ -4531,6 +4539,8 @@ enum nl80211_reg_rule_flags { NL80211_RRF_NO_EHT = 1<<19, NL80211_RRF_PSD = 1<<20, NL80211_RRF_DFS_CONCURRENT = 1<<21, + NL80211_RRF_NO_UHB_VLP_CLIENT = 1<<22, + NL80211_RRF_NO_UHB_AFC_CLIENT = 1<<23, }; #define NL80211_RRF_PASSIVE_SCAN NL80211_RRF_NO_IR @@ -5086,9 +5096,12 @@ enum nl80211_bss_use_for { * BSS isn't possible * @NL80211_BSS_CANNOT_USE_NSTR_NONPRIMARY: NSTR nonprimary links aren't * supported by the device, and this BSS entry represents one. + * @NL80211_BSS_CANNOT_USE_UHB_PWR_MISMATCH: STA is not supporting + * the AP power type (SP, VLP, AP) that the AP uses. */ enum nl80211_bss_cannot_use_reasons { NL80211_BSS_CANNOT_USE_NSTR_NONPRIMARY = 1 << 0, + NL80211_BSS_CANNOT_USE_UHB_PWR_MISMATCH = 1 << 1, }; /** diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 534ef3fe0696..60877b532993 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1204,6 +1204,12 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, if ((chan->flags & IEEE80211_CHAN_DFS_CONCURRENT) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_DFS_CONCURRENT)) goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_NO_UHB_VLP_CLIENT) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_UHB_VLP_CLIENT)) + goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_NO_UHB_AFC_CLIENT) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_UHB_AFC_CLIENT)) + goto nla_put_failure; } if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 44684df64734..2741b626919a 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1595,6 +1595,10 @@ static u32 map_regdom_flags(u32 rd_flags) channel_flags |= IEEE80211_CHAN_NO_EHT; if (rd_flags & NL80211_RRF_DFS_CONCURRENT) channel_flags |= IEEE80211_CHAN_DFS_CONCURRENT; + if (rd_flags & NL80211_RRF_NO_UHB_VLP_CLIENT) + channel_flags |= IEEE80211_CHAN_NO_UHB_VLP_CLIENT; + if (rd_flags & NL80211_RRF_NO_UHB_AFC_CLIENT) + channel_flags |= IEEE80211_CHAN_NO_UHB_AFC_CLIENT; if (rd_flags & NL80211_RRF_PSD) channel_flags |= IEEE80211_CHAN_PSD; return channel_flags; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 3d260c99c348..a601f1c7f835 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -2848,6 +2848,36 @@ cfg80211_inform_bss_data(struct wiphy *wiphy, } EXPORT_SYMBOL(cfg80211_inform_bss_data); +static bool cfg80211_uhb_power_type_valid(const u8 *ie, + size_t ielen, + const u32 flags) +{ + const struct element *tmp; + struct ieee80211_he_operation *he_oper; + + tmp = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_OPERATION, ie, ielen); + if (tmp && tmp->datalen >= sizeof(*he_oper) + 1) { + const struct ieee80211_he_6ghz_oper *he_6ghz_oper; + + he_oper = (void *)&tmp->data[1]; + he_6ghz_oper = ieee80211_he_6ghz_oper(he_oper); + + if (!he_6ghz_oper) + return false; + + switch (u8_get_bits(he_6ghz_oper->control, + IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) { + case IEEE80211_6GHZ_CTRL_REG_LPI_AP: + return true; + case IEEE80211_6GHZ_CTRL_REG_SP_AP: + return !(flags & IEEE80211_CHAN_NO_UHB_AFC_CLIENT); + case IEEE80211_6GHZ_CTRL_REG_VLP_AP: + return !(flags & IEEE80211_CHAN_NO_UHB_VLP_CLIENT); + } + } + return false; +} + /* cfg80211_inform_bss_width_frame helper */ static struct cfg80211_bss * cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, @@ -2906,6 +2936,14 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, if (!channel) return NULL; + if (channel->band == NL80211_BAND_6GHZ && + !cfg80211_uhb_power_type_valid(variable, ielen, channel->flags)) { + data->restrict_use = 1; + data->use_for = 0; + data->cannot_use_reasons = + NL80211_BSS_CANNOT_USE_UHB_PWR_MISMATCH; + } + if (ext) { const struct ieee80211_s1g_bcn_compat_ie *compat; const struct element *elem; -- cgit From ea67677dbb0d30b993b15790d6cee24c900dd597 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 22 Dec 2023 14:54:37 +0000 Subject: lsm: Add a __counted_by() annotation to lsm_ctx.ctx The ctx in struct lsm_ctx is an array of size ctx_len, tell the compiler about this using __counted_by() where supported to improve the ability to detect overflow issues. Reported-by: Aishwarya TCV Signed-off-by: Mark Brown Signed-off-by: Paul Moore --- include/uapi/linux/lsm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/lsm.h b/include/uapi/linux/lsm.h index f0386880a78e..f8aef9ade549 100644 --- a/include/uapi/linux/lsm.h +++ b/include/uapi/linux/lsm.h @@ -9,6 +9,7 @@ #ifndef _UAPI_LINUX_LSM_H #define _UAPI_LINUX_LSM_H +#include #include #include @@ -36,7 +37,7 @@ struct lsm_ctx { __u64 flags; __u64 len; __u64 ctx_len; - __u8 ctx[]; + __u8 ctx[] __counted_by(ctx_len); }; /* -- cgit From 01fd1617dbc6f558efd1811f2bc433659d1e8304 Mon Sep 17 00:00:00 2001 From: Wen Gu Date: Tue, 19 Dec 2023 22:26:14 +0800 Subject: net/smc: support extended GID in SMC-D lgr netlink attribute Virtual ISM devices introduced in SMCv2.1 requires a 128 bit extended GID vs. the existing ISM 64bit GID. So the 2nd 64 bit of extended GID should be included in SMC-D linkgroup netlink attribute as well. Signed-off-by: Wen Gu Signed-off-by: David S. Miller --- include/uapi/linux/smc.h | 2 ++ include/uapi/linux/smc_diag.h | 2 ++ net/smc/smc_core.c | 6 ++++++ net/smc/smc_diag.c | 2 ++ 4 files changed, 12 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 837fcd4b0abc..b531e3ef011a 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -160,6 +160,8 @@ enum { SMC_NLA_LGR_D_CHID, /* u16 */ SMC_NLA_LGR_D_PAD, /* flag */ SMC_NLA_LGR_D_V2_COMMON, /* nest */ + SMC_NLA_LGR_D_EXT_GID, /* u64 */ + SMC_NLA_LGR_D_PEER_EXT_GID, /* u64 */ __SMC_NLA_LGR_D_MAX, SMC_NLA_LGR_D_MAX = __SMC_NLA_LGR_D_MAX - 1 }; diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h index 8cb3a6fef553..58eceb7f5df2 100644 --- a/include/uapi/linux/smc_diag.h +++ b/include/uapi/linux/smc_diag.h @@ -107,6 +107,8 @@ struct smcd_diag_dmbinfo { /* SMC-D Socket internals */ __aligned_u64 my_gid; /* My GID */ __aligned_u64 token; /* Token of DMB */ __aligned_u64 peer_token; /* Token of remote DMBE */ + __aligned_u64 peer_gid_ext; /* Peer GID (extended part) */ + __aligned_u64 my_gid_ext; /* My GID (extended part) */ }; #endif /* _UAPI_SMC_DIAG_H_ */ diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 672eff087732..95cc95458e2d 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -526,9 +526,15 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_GID, smcd_gid.gid, SMC_NLA_LGR_D_PAD)) goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_EXT_GID, + smcd_gid.gid_ext, SMC_NLA_LGR_D_PAD)) + goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_GID, lgr->peer_gid.gid, SMC_NLA_LGR_D_PAD)) goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_EXT_GID, + lgr->peer_gid.gid_ext, SMC_NLA_LGR_D_PAD)) + goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_D_VLAN_ID, lgr->vlan_id)) goto errattr; if (nla_put_u32(skb, SMC_NLA_LGR_D_CONNS_NUM, lgr->conns_num)) diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index c180c180d0d1..3fbe14e09ad8 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -175,8 +175,10 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, dinfo.linkid = *((u32 *)conn->lgr->id); dinfo.peer_gid = conn->lgr->peer_gid.gid; + dinfo.peer_gid_ext = conn->lgr->peer_gid.gid_ext; smcd->ops->get_local_gid(smcd, &smcd_gid); dinfo.my_gid = smcd_gid.gid; + dinfo.my_gid_ext = smcd_gid.gid_ext; dinfo.token = conn->rmb_desc->token; dinfo.peer_token = conn->peer_token; -- cgit From 42f39036cda808d3de243192a2cf5125f12f3047 Mon Sep 17 00:00:00 2001 From: Victor Nogueira Date: Tue, 19 Dec 2023 15:16:23 -0300 Subject: net/sched: act_mirred: Allow mirred to block So far the mirred action has dealt with syntax that handles mirror/redirection for netdev. A matching packet is redirected or mirrored to a target netdev. In this patch we enable mirred to mirror to a tc block as well. IOW, the new syntax looks as follows: ... mirred [index INDEX] < | > > Examples of mirroring or redirecting to a tc block: $ tc filter add block 22 protocol ip pref 25 \ flower dst_ip 192.168.0.0/16 action mirred egress mirror blockid 22 $ tc filter add block 22 protocol ip pref 25 \ flower dst_ip 10.10.10.10/32 action mirred egress redirect blockid 22 Co-developed-by: Jamal Hadi Salim Signed-off-by: Jamal Hadi Salim Co-developed-by: Pedro Tammela Signed-off-by: Pedro Tammela Signed-off-by: Victor Nogueira Signed-off-by: David S. Miller --- include/net/tc_act/tc_mirred.h | 1 + include/uapi/linux/tc_act/tc_mirred.h | 1 + net/sched/act_mirred.c | 119 +++++++++++++++++++++++++++++++++- 3 files changed, 119 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index 32ce8ea36950..75722d967bf2 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -8,6 +8,7 @@ struct tcf_mirred { struct tc_action common; int tcfm_eaction; + u32 tcfm_blockid; bool tcfm_mac_header_xmit; struct net_device __rcu *tcfm_dev; netdevice_tracker tcfm_dev_tracker; diff --git a/include/uapi/linux/tc_act/tc_mirred.h b/include/uapi/linux/tc_act/tc_mirred.h index 2500a0005d05..c61e76f3c23b 100644 --- a/include/uapi/linux/tc_act/tc_mirred.h +++ b/include/uapi/linux/tc_act/tc_mirred.h @@ -21,6 +21,7 @@ enum { TCA_MIRRED_TM, TCA_MIRRED_PARMS, TCA_MIRRED_PAD, + TCA_MIRRED_BLOCKID, __TCA_MIRRED_MAX }; #define TCA_MIRRED_MAX (__TCA_MIRRED_MAX - 1) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index a1be8f3c4a8e..d1f9794ca9b7 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -85,6 +85,7 @@ static void tcf_mirred_release(struct tc_action *a) static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { [TCA_MIRRED_PARMS] = { .len = sizeof(struct tc_mirred) }, + [TCA_MIRRED_BLOCKID] = NLA_POLICY_MIN(NLA_U32, 1), }; static struct tc_action_ops act_mirred_ops; @@ -136,6 +137,17 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, if (exists && bind) return 0; + if (tb[TCA_MIRRED_BLOCKID] && parm->ifindex) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot specify Block ID and dev simultaneously"); + if (exists) + tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, index); + + return -EINVAL; + } + switch (parm->eaction) { case TCA_EGRESS_MIRROR: case TCA_EGRESS_REDIR: @@ -152,9 +164,10 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, } if (!exists) { - if (!parm->ifindex) { + if (!parm->ifindex && !tb[TCA_MIRRED_BLOCKID]) { tcf_idr_cleanup(tn, index); - NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist"); + NL_SET_ERR_MSG_MOD(extack, + "Must specify device or block"); return -EINVAL; } ret = tcf_idr_create_from_flags(tn, index, est, a, @@ -192,6 +205,11 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, tcf_mirred_replace_dev(m, ndev); netdev_tracker_alloc(ndev, &m->tcfm_dev_tracker, GFP_ATOMIC); m->tcfm_mac_header_xmit = mac_header_xmit; + m->tcfm_blockid = 0; + } else if (tb[TCA_MIRRED_BLOCKID]) { + tcf_mirred_replace_dev(m, NULL); + m->tcfm_mac_header_xmit = false; + m->tcfm_blockid = nla_get_u32(tb[TCA_MIRRED_BLOCKID]); } goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); m->tcfm_eaction = parm->eaction; @@ -316,6 +334,89 @@ out: return retval; } +static int tcf_blockcast_redir(struct sk_buff *skb, struct tcf_mirred *m, + struct tcf_block *block, int m_eaction, + const u32 exception_ifindex, int retval) +{ + struct net_device *dev_prev = NULL; + struct net_device *dev = NULL; + unsigned long index; + int mirred_eaction; + + mirred_eaction = tcf_mirred_act_wants_ingress(m_eaction) ? + TCA_INGRESS_MIRROR : TCA_EGRESS_MIRROR; + + xa_for_each(&block->ports, index, dev) { + if (index == exception_ifindex) + continue; + + if (!dev_prev) + goto assign_prev; + + tcf_mirred_to_dev(skb, m, dev_prev, + dev_is_mac_header_xmit(dev), + mirred_eaction, retval); +assign_prev: + dev_prev = dev; + } + + if (dev_prev) + return tcf_mirred_to_dev(skb, m, dev_prev, + dev_is_mac_header_xmit(dev_prev), + m_eaction, retval); + + return retval; +} + +static int tcf_blockcast_mirror(struct sk_buff *skb, struct tcf_mirred *m, + struct tcf_block *block, int m_eaction, + const u32 exception_ifindex, int retval) +{ + struct net_device *dev = NULL; + unsigned long index; + + xa_for_each(&block->ports, index, dev) { + if (index == exception_ifindex) + continue; + + tcf_mirred_to_dev(skb, m, dev, + dev_is_mac_header_xmit(dev), + m_eaction, retval); + } + + return retval; +} + +static int tcf_blockcast(struct sk_buff *skb, struct tcf_mirred *m, + const u32 blockid, struct tcf_result *res, + int retval) +{ + const u32 exception_ifindex = skb->dev->ifindex; + struct tcf_block *block; + bool is_redirect; + int m_eaction; + + m_eaction = READ_ONCE(m->tcfm_eaction); + is_redirect = tcf_mirred_is_act_redirect(m_eaction); + + /* we are already under rcu protection, so can call block lookup + * directly. + */ + block = tcf_block_lookup(dev_net(skb->dev), blockid); + if (!block || xa_empty(&block->ports)) { + tcf_action_inc_overlimit_qstats(&m->common); + return retval; + } + + if (is_redirect) + return tcf_blockcast_redir(skb, m, block, m_eaction, + exception_ifindex, retval); + + /* If it's not redirect, it is mirror */ + return tcf_blockcast_mirror(skb, m, block, m_eaction, exception_ifindex, + retval); +} + TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) @@ -326,6 +427,7 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb, bool m_mac_header_xmit; struct net_device *dev; int m_eaction; + u32 blockid; nest_level = __this_cpu_inc_return(mirred_nest_level); if (unlikely(nest_level > MIRRED_NEST_LIMIT)) { @@ -338,6 +440,12 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb, tcf_lastuse_update(&m->tcf_tm); tcf_action_update_bstats(&m->common, skb); + blockid = READ_ONCE(m->tcfm_blockid); + if (blockid) { + retval = tcf_blockcast(skb, m, blockid, res, retval); + goto dec_nest_level; + } + dev = rcu_dereference_bh(m->tcfm_dev); if (unlikely(!dev)) { pr_notice_once("tc mirred: target device is gone\n"); @@ -379,6 +487,7 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, }; struct net_device *dev; struct tcf_t t; + u32 blockid; spin_lock_bh(&m->tcf_lock); opt.action = m->tcf_action; @@ -390,6 +499,10 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, if (nla_put(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt)) goto nla_put_failure; + blockid = m->tcfm_blockid; + if (blockid && nla_put_u32(skb, TCA_MIRRED_BLOCKID, blockid)) + goto nla_put_failure; + tcf_tm_dump(&t, &m->tcf_tm); if (nla_put_64bit(skb, TCA_MIRRED_TM, sizeof(t), &t, TCA_MIRRED_PAD)) goto nla_put_failure; @@ -420,6 +533,8 @@ static int mirred_device_event(struct notifier_block *unused, * net_device are already rcu protected. */ RCU_INIT_POINTER(m->tcfm_dev, NULL); + } else if (m->tcfm_blockid) { + m->tcfm_blockid = 0; } spin_unlock_bh(&m->tcf_lock); } -- cgit From d0c3891db2d279b2f5ff8fd174e0b09e75dea039 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Tue, 19 Dec 2023 16:53:46 -0700 Subject: ethtool: reformat kerneldoc for struct ethtool_link_settings The kernel doc comments for struct ethtool_link_settings includes documentation for three fields that were never present there, leading to these docs-build warnings: ./include/uapi/linux/ethtool.h:2207: warning: Excess struct member 'supported' description in 'ethtool_link_settings' ./include/uapi/linux/ethtool.h:2207: warning: Excess struct member 'advertising' description in 'ethtool_link_settings' ./include/uapi/linux/ethtool.h:2207: warning: Excess struct member 'lp_advertising' description in 'ethtool_link_settings' Remove the entries to make the warnings go away. There was some information there on how data in >link_mode_masks is formatted; move that to the body of the comment to preserve it. Signed-off-by: Jonathan Corbet Reviewed-by: Randy Dunlap Signed-off-by: David S. Miller --- include/uapi/linux/ethtool.h | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 0787d561ace0..85c412c23ab5 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2139,18 +2139,6 @@ enum ethtool_reset_flags { * refused. For drivers: ignore this field (use kernel's * __ETHTOOL_LINK_MODE_MASK_NBITS instead), any change to it will * be overwritten by kernel. - * @supported: Bitmap with each bit meaning given by - * %ethtool_link_mode_bit_indices for the link modes, physical - * connectors and other link features for which the interface - * supports autonegotiation or auto-detection. Read-only. - * @advertising: Bitmap with each bit meaning given by - * %ethtool_link_mode_bit_indices for the link modes, physical - * connectors and other link features that are advertised through - * autonegotiation or enabled for auto-detection. - * @lp_advertising: Bitmap with each bit meaning given by - * %ethtool_link_mode_bit_indices for the link modes, and other - * link features that the link partner advertised through - * autonegotiation; 0 if unknown or not applicable. Read-only. * @transceiver: Used to distinguish different possible PHY types, * reported consistently by PHYLIB. Read-only. * @master_slave_cfg: Master/slave port mode. @@ -2192,6 +2180,21 @@ enum ethtool_reset_flags { * %set_link_ksettings() should validate all fields other than @cmd * and @link_mode_masks_nwords that are not described as read-only or * deprecated, and must ignore all fields described as read-only. + * + * @link_mode_masks is divided into three bitfields, each of length + * @link_mode_masks_nwords: + * - supported: Bitmap with each bit meaning given by + * %ethtool_link_mode_bit_indices for the link modes, physical + * connectors and other link features for which the interface + * supports autonegotiation or auto-detection. Read-only. + * - advertising: Bitmap with each bit meaning given by + * %ethtool_link_mode_bit_indices for the link modes, physical + * connectors and other link features that are advertised through + * autonegotiation or enabled for auto-detection. + * - lp_advertising: Bitmap with each bit meaning given by + * %ethtool_link_mode_bit_indices for the link modes, and other + * link features that the link partner advertised through + * autonegotiation; 0 if unknown or not applicable. Read-only. */ struct ethtool_link_settings { __u32 cmd; -- cgit From adef440691bab824e39c1b17382322d195e1fab0 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 6 Dec 2023 02:36:56 -0800 Subject: userfaultfd: UFFDIO_MOVE uABI Implement the uABI of UFFDIO_MOVE ioctl. UFFDIO_COPY performs ~20% better than UFFDIO_MOVE when the application needs pages to be allocated [1]. However, with UFFDIO_MOVE, if pages are available (in userspace) for recycling, as is usually the case in heap compaction algorithms, then we can avoid the page allocation and memcpy (done by UFFDIO_COPY). Also, since the pages are recycled in the userspace, we avoid the need to release (via madvise) the pages back to the kernel [2]. We see over 40% reduction (on a Google pixel 6 device) in the compacting thread's completion time by using UFFDIO_MOVE vs. UFFDIO_COPY. This was measured using a benchmark that emulates a heap compaction implementation using userfaultfd (to allow concurrent accesses by application threads). More details of the usecase are explained in [2]. Furthermore, UFFDIO_MOVE enables moving swapped-out pages without touching them within the same vma. Today, it can only be done by mremap, however it forces splitting the vma. [1] https://lore.kernel.org/all/1425575884-2574-1-git-send-email-aarcange@redhat.com/ [2] https://lore.kernel.org/linux-mm/CA+EESO4uO84SSnBhArH4HvLNhaUQ5nZKNKXqxRCyjniNVjp0Aw@mail.gmail.com/ Update for the ioctl_userfaultfd(2) manpage: UFFDIO_MOVE (Since Linux xxx) Move a continuous memory chunk into the userfault registered range and optionally wake up the blocked thread. The source and destination addresses and the number of bytes to move are specified by the src, dst, and len fields of the uffdio_move structure pointed to by argp: struct uffdio_move { __u64 dst; /* Destination of move */ __u64 src; /* Source of move */ __u64 len; /* Number of bytes to move */ __u64 mode; /* Flags controlling behavior of move */ __s64 move; /* Number of bytes moved, or negated error */ }; The following value may be bitwise ORed in mode to change the behavior of the UFFDIO_MOVE operation: UFFDIO_MOVE_MODE_DONTWAKE Do not wake up the thread that waits for page-fault resolution UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES Allow holes in the source virtual range that is being moved. When not specified, the holes will result in ENOENT error. When specified, the holes will be accounted as successfully moved memory. This is mostly useful to move hugepage aligned virtual regions without knowing if there are transparent hugepages in the regions or not, but preventing the risk of having to split the hugepage during the operation. The move field is used by the kernel to return the number of bytes that was actually moved, or an error (a negated errno- style value). If the value returned in move doesn't match the value that was specified in len, the operation fails with the error EAGAIN. The move field is output-only; it is not read by the UFFDIO_MOVE operation. The operation may fail for various reasons. Usually, remapping of pages that are not exclusive to the given process fail; once KSM might deduplicate pages or fork() COW-shares pages during fork() with child processes, they are no longer exclusive. Further, the kernel might only perform lightweight checks for detecting whether the pages are exclusive, and return -EBUSY in case that check fails. To make the operation more likely to succeed, KSM should be disabled, fork() should be avoided or MADV_DONTFORK should be configured for the source VMA before fork(). This ioctl(2) operation returns 0 on success. In this case, the entire area was moved. On error, -1 is returned and errno is set to indicate the error. Possible errors include: EAGAIN The number of bytes moved (i.e., the value returned in the move field) does not equal the value that was specified in the len field. EINVAL Either dst or len was not a multiple of the system page size, or the range specified by src and len or dst and len was invalid. EINVAL An invalid bit was specified in the mode field. ENOENT The source virtual memory range has unmapped holes and UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES is not set. EEXIST The destination virtual memory range is fully or partially mapped. EBUSY The pages in the source virtual memory range are either pinned or not exclusive to the process. The kernel might only perform lightweight checks for detecting whether the pages are exclusive. To make the operation more likely to succeed, KSM should be disabled, fork() should be avoided or MADV_DONTFORK should be configured for the source virtual memory area before fork(). ENOMEM Allocating memory needed for the operation failed. ESRCH The target process has exited at the time of a UFFDIO_MOVE operation. Link: https://lkml.kernel.org/r/20231206103702.3873743-3-surenb@google.com Signed-off-by: Andrea Arcangeli Signed-off-by: Suren Baghdasaryan Cc: Al Viro Cc: Axel Rasmussen Cc: Brian Geffon Cc: Christian Brauner Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jann Horn Cc: Kalesh Singh Cc: Liam R. Howlett Cc: Lokesh Gidra Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Rapoport (IBM) Cc: Nicolas Geoffray Cc: Peter Xu Cc: Ryan Roberts Cc: Shuah Khan Cc: ZhangPeng Signed-off-by: Andrew Morton --- Documentation/admin-guide/mm/userfaultfd.rst | 3 + fs/userfaultfd.c | 72 ++++ include/linux/rmap.h | 5 + include/linux/userfaultfd_k.h | 11 + include/uapi/linux/userfaultfd.h | 29 +- mm/huge_memory.c | 122 ++++++ mm/khugepaged.c | 3 + mm/rmap.c | 6 + mm/userfaultfd.c | 614 +++++++++++++++++++++++++++ 9 files changed, 864 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/admin-guide/mm/userfaultfd.rst b/Documentation/admin-guide/mm/userfaultfd.rst index 203e26da5f92..e5cc8848dcb3 100644 --- a/Documentation/admin-guide/mm/userfaultfd.rst +++ b/Documentation/admin-guide/mm/userfaultfd.rst @@ -113,6 +113,9 @@ events, except page fault notifications, may be generated: areas. ``UFFD_FEATURE_MINOR_SHMEM`` is the analogous feature indicating support for shmem virtual memory areas. +- ``UFFD_FEATURE_MOVE`` indicates that the kernel supports moving an + existing page contents from userspace. + The userland application should set the feature flags it intends to use when invoking the ``UFFDIO_API`` ioctl, to request that those features be enabled if supported. diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index e8af40b05549..6e2a4d6a0d8f 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -2005,6 +2005,75 @@ static inline unsigned int uffd_ctx_features(__u64 user_features) return (unsigned int)user_features | UFFD_FEATURE_INITIALIZED; } +static int userfaultfd_move(struct userfaultfd_ctx *ctx, + unsigned long arg) +{ + __s64 ret; + struct uffdio_move uffdio_move; + struct uffdio_move __user *user_uffdio_move; + struct userfaultfd_wake_range range; + struct mm_struct *mm = ctx->mm; + + user_uffdio_move = (struct uffdio_move __user *) arg; + + if (atomic_read(&ctx->mmap_changing)) + return -EAGAIN; + + if (copy_from_user(&uffdio_move, user_uffdio_move, + /* don't copy "move" last field */ + sizeof(uffdio_move)-sizeof(__s64))) + return -EFAULT; + + /* Do not allow cross-mm moves. */ + if (mm != current->mm) + return -EINVAL; + + ret = validate_range(mm, uffdio_move.dst, uffdio_move.len); + if (ret) + return ret; + + ret = validate_range(mm, uffdio_move.src, uffdio_move.len); + if (ret) + return ret; + + if (uffdio_move.mode & ~(UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES| + UFFDIO_MOVE_MODE_DONTWAKE)) + return -EINVAL; + + if (mmget_not_zero(mm)) { + mmap_read_lock(mm); + + /* Re-check after taking mmap_lock */ + if (likely(!atomic_read(&ctx->mmap_changing))) + ret = move_pages(ctx, mm, uffdio_move.dst, uffdio_move.src, + uffdio_move.len, uffdio_move.mode); + else + ret = -EINVAL; + + mmap_read_unlock(mm); + mmput(mm); + } else { + return -ESRCH; + } + + if (unlikely(put_user(ret, &user_uffdio_move->move))) + return -EFAULT; + if (ret < 0) + goto out; + + /* len == 0 would wake all */ + VM_WARN_ON(!ret); + range.len = ret; + if (!(uffdio_move.mode & UFFDIO_MOVE_MODE_DONTWAKE)) { + range.start = uffdio_move.dst; + wake_userfault(ctx, &range); + } + ret = range.len == uffdio_move.len ? 0 : -EAGAIN; + +out: + return ret; +} + /* * userland asks for a certain API version and we return which bits * and ioctl commands are implemented in this kernel for such API @@ -2097,6 +2166,9 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd, case UFFDIO_ZEROPAGE: ret = userfaultfd_zeropage(ctx, arg); break; + case UFFDIO_MOVE: + ret = userfaultfd_move(ctx, arg); + break; case UFFDIO_WRITEPROTECT: ret = userfaultfd_writeprotect(ctx, arg); break; diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 3c2fc291b071..af6a32b6f3e7 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -121,6 +121,11 @@ static inline void anon_vma_lock_write(struct anon_vma *anon_vma) down_write(&anon_vma->root->rwsem); } +static inline int anon_vma_trylock_write(struct anon_vma *anon_vma) +{ + return down_write_trylock(&anon_vma->root->rwsem); +} + static inline void anon_vma_unlock_write(struct anon_vma *anon_vma) { up_write(&anon_vma->root->rwsem); diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index f2dc19f40d05..e4056547fbe6 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -93,6 +93,17 @@ extern int mwriteprotect_range(struct mm_struct *dst_mm, extern long uffd_wp_range(struct vm_area_struct *vma, unsigned long start, unsigned long len, bool enable_wp); +/* move_pages */ +void double_pt_lock(spinlock_t *ptl1, spinlock_t *ptl2); +void double_pt_unlock(spinlock_t *ptl1, spinlock_t *ptl2); +ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm, + unsigned long dst_start, unsigned long src_start, + unsigned long len, __u64 flags); +int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval, + struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma, + unsigned long dst_addr, unsigned long src_addr); + /* mm helpers */ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, struct vm_userfaultfd_ctx vm_ctx) diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 0dbc81015018..2841e4ea8f2c 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -41,7 +41,8 @@ UFFD_FEATURE_WP_HUGETLBFS_SHMEM | \ UFFD_FEATURE_WP_UNPOPULATED | \ UFFD_FEATURE_POISON | \ - UFFD_FEATURE_WP_ASYNC) + UFFD_FEATURE_WP_ASYNC | \ + UFFD_FEATURE_MOVE) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -50,6 +51,7 @@ ((__u64)1 << _UFFDIO_WAKE | \ (__u64)1 << _UFFDIO_COPY | \ (__u64)1 << _UFFDIO_ZEROPAGE | \ + (__u64)1 << _UFFDIO_MOVE | \ (__u64)1 << _UFFDIO_WRITEPROTECT | \ (__u64)1 << _UFFDIO_CONTINUE | \ (__u64)1 << _UFFDIO_POISON) @@ -73,6 +75,7 @@ #define _UFFDIO_WAKE (0x02) #define _UFFDIO_COPY (0x03) #define _UFFDIO_ZEROPAGE (0x04) +#define _UFFDIO_MOVE (0x05) #define _UFFDIO_WRITEPROTECT (0x06) #define _UFFDIO_CONTINUE (0x07) #define _UFFDIO_POISON (0x08) @@ -92,6 +95,8 @@ struct uffdio_copy) #define UFFDIO_ZEROPAGE _IOWR(UFFDIO, _UFFDIO_ZEROPAGE, \ struct uffdio_zeropage) +#define UFFDIO_MOVE _IOWR(UFFDIO, _UFFDIO_MOVE, \ + struct uffdio_move) #define UFFDIO_WRITEPROTECT _IOWR(UFFDIO, _UFFDIO_WRITEPROTECT, \ struct uffdio_writeprotect) #define UFFDIO_CONTINUE _IOWR(UFFDIO, _UFFDIO_CONTINUE, \ @@ -222,6 +227,9 @@ struct uffdio_api { * asynchronous mode is supported in which the write fault is * automatically resolved and write-protection is un-set. * It implies UFFD_FEATURE_WP_UNPOPULATED. + * + * UFFD_FEATURE_MOVE indicates that the kernel supports moving an + * existing page contents from userspace. */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) @@ -239,6 +247,7 @@ struct uffdio_api { #define UFFD_FEATURE_WP_UNPOPULATED (1<<13) #define UFFD_FEATURE_POISON (1<<14) #define UFFD_FEATURE_WP_ASYNC (1<<15) +#define UFFD_FEATURE_MOVE (1<<16) __u64 features; __u64 ioctls; @@ -347,6 +356,24 @@ struct uffdio_poison { __s64 updated; }; +struct uffdio_move { + __u64 dst; + __u64 src; + __u64 len; + /* + * Especially if used to atomically remove memory from the + * address space the wake on the dst range is not needed. + */ +#define UFFDIO_MOVE_MODE_DONTWAKE ((__u64)1<<0) +#define UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES ((__u64)1<<1) + __u64 mode; + /* + * "move" is written by the ioctl and must be at the end: the + * copy_from_user will not read the last 8 bytes. + */ + __s64 move; +}; + /* * Flags for the userfaultfd(2) system call itself. */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 387b030c7f15..6be1a380a298 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2141,6 +2141,128 @@ unlock: return ret; } +#ifdef CONFIG_USERFAULTFD +/* + * The PT lock for src_pmd and the mmap_lock for reading are held by + * the caller, but it must return after releasing the page_table_lock. + * Just move the page from src_pmd to dst_pmd if possible. + * Return zero if succeeded in moving the page, -EAGAIN if it needs to be + * repeated by the caller, or other errors in case of failure. + */ +int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval, + struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + unsigned long dst_addr, unsigned long src_addr) +{ + pmd_t _dst_pmd, src_pmdval; + struct page *src_page; + struct folio *src_folio; + struct anon_vma *src_anon_vma; + spinlock_t *src_ptl, *dst_ptl; + pgtable_t src_pgtable; + struct mmu_notifier_range range; + int err = 0; + + src_pmdval = *src_pmd; + src_ptl = pmd_lockptr(mm, src_pmd); + + lockdep_assert_held(src_ptl); + mmap_assert_locked(mm); + + /* Sanity checks before the operation */ + if (WARN_ON_ONCE(!pmd_none(dst_pmdval)) || WARN_ON_ONCE(src_addr & ~HPAGE_PMD_MASK) || + WARN_ON_ONCE(dst_addr & ~HPAGE_PMD_MASK)) { + spin_unlock(src_ptl); + return -EINVAL; + } + + if (!pmd_trans_huge(src_pmdval)) { + spin_unlock(src_ptl); + if (is_pmd_migration_entry(src_pmdval)) { + pmd_migration_entry_wait(mm, &src_pmdval); + return -EAGAIN; + } + return -ENOENT; + } + + src_page = pmd_page(src_pmdval); + if (unlikely(!PageAnonExclusive(src_page))) { + spin_unlock(src_ptl); + return -EBUSY; + } + + src_folio = page_folio(src_page); + folio_get(src_folio); + spin_unlock(src_ptl); + + flush_cache_range(src_vma, src_addr, src_addr + HPAGE_PMD_SIZE); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, src_addr, + src_addr + HPAGE_PMD_SIZE); + mmu_notifier_invalidate_range_start(&range); + + folio_lock(src_folio); + + /* + * split_huge_page walks the anon_vma chain without the page + * lock. Serialize against it with the anon_vma lock, the page + * lock is not enough. + */ + src_anon_vma = folio_get_anon_vma(src_folio); + if (!src_anon_vma) { + err = -EAGAIN; + goto unlock_folio; + } + anon_vma_lock_write(src_anon_vma); + + dst_ptl = pmd_lockptr(mm, dst_pmd); + double_pt_lock(src_ptl, dst_ptl); + if (unlikely(!pmd_same(*src_pmd, src_pmdval) || + !pmd_same(*dst_pmd, dst_pmdval))) { + err = -EAGAIN; + goto unlock_ptls; + } + if (folio_maybe_dma_pinned(src_folio) || + !PageAnonExclusive(&src_folio->page)) { + err = -EBUSY; + goto unlock_ptls; + } + + if (WARN_ON_ONCE(!folio_test_head(src_folio)) || + WARN_ON_ONCE(!folio_test_anon(src_folio))) { + err = -EBUSY; + goto unlock_ptls; + } + + folio_move_anon_rmap(src_folio, dst_vma); + WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr)); + + src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd); + /* Folio got pinned from under us. Put it back and fail the move. */ + if (folio_maybe_dma_pinned(src_folio)) { + set_pmd_at(mm, src_addr, src_pmd, src_pmdval); + err = -EBUSY; + goto unlock_ptls; + } + + _dst_pmd = mk_huge_pmd(&src_folio->page, dst_vma->vm_page_prot); + /* Follow mremap() behavior and treat the entry dirty after the move */ + _dst_pmd = pmd_mkwrite(pmd_mkdirty(_dst_pmd), dst_vma); + set_pmd_at(mm, dst_addr, dst_pmd, _dst_pmd); + + src_pgtable = pgtable_trans_huge_withdraw(mm, src_pmd); + pgtable_trans_huge_deposit(mm, dst_pmd, src_pgtable); +unlock_ptls: + double_pt_unlock(src_ptl, dst_ptl); + anon_vma_unlock_write(src_anon_vma); + put_anon_vma(src_anon_vma); +unlock_folio: + /* unblock rmap walks */ + folio_unlock(src_folio); + mmu_notifier_invalidate_range_end(&range); + folio_put(src_folio); + return err; +} +#endif /* CONFIG_USERFAULTFD */ + /* * Returns page table lock pointer if a given pmd maps a thp, NULL otherwise. * diff --git a/mm/khugepaged.c b/mm/khugepaged.c index d72aecd3624a..de174d049e71 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1140,6 +1140,9 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, * Prevent all access to pagetables with the exception of * gup_fast later handled by the ptep_clear_flush and the VM * handled by the anon_vma lock + PG_lock. + * + * UFFDIO_MOVE is prevented to race as well thanks to the + * mmap_lock. */ mmap_write_lock(mm); result = hugepage_vma_revalidate(mm, address, true, &vma, cc); diff --git a/mm/rmap.c b/mm/rmap.c index 15a55304aa3b..846fc79f3ca9 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -490,6 +490,12 @@ void __init anon_vma_init(void) * page_remove_rmap() that the anon_vma pointer from page->mapping is valid * if there is a mapcount, we can dereference the anon_vma after observing * those. + * + * NOTE: the caller should normally hold folio lock when calling this. If + * not, the caller needs to double check the anon_vma didn't change after + * taking the anon_vma lock for either read or write (UFFDIO_MOVE can modify it + * concurrently without folio lock protection). See folio_lock_anon_vma_read() + * which has already covered that, and comment above remap_pages(). */ struct anon_vma *folio_get_anon_vma(struct folio *folio) { diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 0b6ca553bebe..9ec814e47e99 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -842,3 +842,617 @@ out_unlock: mmap_read_unlock(dst_mm); return err; } + + +void double_pt_lock(spinlock_t *ptl1, + spinlock_t *ptl2) + __acquires(ptl1) + __acquires(ptl2) +{ + spinlock_t *ptl_tmp; + + if (ptl1 > ptl2) { + /* exchange ptl1 and ptl2 */ + ptl_tmp = ptl1; + ptl1 = ptl2; + ptl2 = ptl_tmp; + } + /* lock in virtual address order to avoid lock inversion */ + spin_lock(ptl1); + if (ptl1 != ptl2) + spin_lock_nested(ptl2, SINGLE_DEPTH_NESTING); + else + __acquire(ptl2); +} + +void double_pt_unlock(spinlock_t *ptl1, + spinlock_t *ptl2) + __releases(ptl1) + __releases(ptl2) +{ + spin_unlock(ptl1); + if (ptl1 != ptl2) + spin_unlock(ptl2); + else + __release(ptl2); +} + + +static int move_present_pte(struct mm_struct *mm, + struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma, + unsigned long dst_addr, unsigned long src_addr, + pte_t *dst_pte, pte_t *src_pte, + pte_t orig_dst_pte, pte_t orig_src_pte, + spinlock_t *dst_ptl, spinlock_t *src_ptl, + struct folio *src_folio) +{ + int err = 0; + + double_pt_lock(dst_ptl, src_ptl); + + if (!pte_same(*src_pte, orig_src_pte) || + !pte_same(*dst_pte, orig_dst_pte)) { + err = -EAGAIN; + goto out; + } + if (folio_test_large(src_folio) || + folio_maybe_dma_pinned(src_folio) || + !PageAnonExclusive(&src_folio->page)) { + err = -EBUSY; + goto out; + } + + folio_move_anon_rmap(src_folio, dst_vma); + WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr)); + + orig_src_pte = ptep_clear_flush(src_vma, src_addr, src_pte); + /* Folio got pinned from under us. Put it back and fail the move. */ + if (folio_maybe_dma_pinned(src_folio)) { + set_pte_at(mm, src_addr, src_pte, orig_src_pte); + err = -EBUSY; + goto out; + } + + orig_dst_pte = mk_pte(&src_folio->page, dst_vma->vm_page_prot); + /* Follow mremap() behavior and treat the entry dirty after the move */ + orig_dst_pte = pte_mkwrite(pte_mkdirty(orig_dst_pte), dst_vma); + + set_pte_at(mm, dst_addr, dst_pte, orig_dst_pte); +out: + double_pt_unlock(dst_ptl, src_ptl); + return err; +} + +static int move_swap_pte(struct mm_struct *mm, + unsigned long dst_addr, unsigned long src_addr, + pte_t *dst_pte, pte_t *src_pte, + pte_t orig_dst_pte, pte_t orig_src_pte, + spinlock_t *dst_ptl, spinlock_t *src_ptl) +{ + if (!pte_swp_exclusive(orig_src_pte)) + return -EBUSY; + + double_pt_lock(dst_ptl, src_ptl); + + if (!pte_same(*src_pte, orig_src_pte) || + !pte_same(*dst_pte, orig_dst_pte)) { + double_pt_unlock(dst_ptl, src_ptl); + return -EAGAIN; + } + + orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte); + set_pte_at(mm, dst_addr, dst_pte, orig_src_pte); + double_pt_unlock(dst_ptl, src_ptl); + + return 0; +} + +/* + * The mmap_lock for reading is held by the caller. Just move the page + * from src_pmd to dst_pmd if possible, and return true if succeeded + * in moving the page. + */ +static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, + struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma, + unsigned long dst_addr, unsigned long src_addr, + __u64 mode) +{ + swp_entry_t entry; + pte_t orig_src_pte, orig_dst_pte; + pte_t src_folio_pte; + spinlock_t *src_ptl, *dst_ptl; + pte_t *src_pte = NULL; + pte_t *dst_pte = NULL; + + struct folio *src_folio = NULL; + struct anon_vma *src_anon_vma = NULL; + struct mmu_notifier_range range; + int err = 0; + + flush_cache_range(src_vma, src_addr, src_addr + PAGE_SIZE); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, + src_addr, src_addr + PAGE_SIZE); + mmu_notifier_invalidate_range_start(&range); +retry: + dst_pte = pte_offset_map_nolock(mm, dst_pmd, dst_addr, &dst_ptl); + + /* Retry if a huge pmd materialized from under us */ + if (unlikely(!dst_pte)) { + err = -EAGAIN; + goto out; + } + + src_pte = pte_offset_map_nolock(mm, src_pmd, src_addr, &src_ptl); + + /* + * We held the mmap_lock for reading so MADV_DONTNEED + * can zap transparent huge pages under us, or the + * transparent huge page fault can establish new + * transparent huge pages under us. + */ + if (unlikely(!src_pte)) { + err = -EAGAIN; + goto out; + } + + /* Sanity checks before the operation */ + if (WARN_ON_ONCE(pmd_none(*dst_pmd)) || WARN_ON_ONCE(pmd_none(*src_pmd)) || + WARN_ON_ONCE(pmd_trans_huge(*dst_pmd)) || WARN_ON_ONCE(pmd_trans_huge(*src_pmd))) { + err = -EINVAL; + goto out; + } + + spin_lock(dst_ptl); + orig_dst_pte = *dst_pte; + spin_unlock(dst_ptl); + if (!pte_none(orig_dst_pte)) { + err = -EEXIST; + goto out; + } + + spin_lock(src_ptl); + orig_src_pte = *src_pte; + spin_unlock(src_ptl); + if (pte_none(orig_src_pte)) { + if (!(mode & UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES)) + err = -ENOENT; + else /* nothing to do to move a hole */ + err = 0; + goto out; + } + + /* If PTE changed after we locked the folio them start over */ + if (src_folio && unlikely(!pte_same(src_folio_pte, orig_src_pte))) { + err = -EAGAIN; + goto out; + } + + if (pte_present(orig_src_pte)) { + /* + * Pin and lock both source folio and anon_vma. Since we are in + * RCU read section, we can't block, so on contention have to + * unmap the ptes, obtain the lock and retry. + */ + if (!src_folio) { + struct folio *folio; + + /* + * Pin the page while holding the lock to be sure the + * page isn't freed under us + */ + spin_lock(src_ptl); + if (!pte_same(orig_src_pte, *src_pte)) { + spin_unlock(src_ptl); + err = -EAGAIN; + goto out; + } + + folio = vm_normal_folio(src_vma, src_addr, orig_src_pte); + if (!folio || !PageAnonExclusive(&folio->page)) { + spin_unlock(src_ptl); + err = -EBUSY; + goto out; + } + + folio_get(folio); + src_folio = folio; + src_folio_pte = orig_src_pte; + spin_unlock(src_ptl); + + if (!folio_trylock(src_folio)) { + pte_unmap(&orig_src_pte); + pte_unmap(&orig_dst_pte); + src_pte = dst_pte = NULL; + /* now we can block and wait */ + folio_lock(src_folio); + goto retry; + } + + if (WARN_ON_ONCE(!folio_test_anon(src_folio))) { + err = -EBUSY; + goto out; + } + } + + /* at this point we have src_folio locked */ + if (folio_test_large(src_folio)) { + err = split_folio(src_folio); + if (err) + goto out; + } + + if (!src_anon_vma) { + /* + * folio_referenced walks the anon_vma chain + * without the folio lock. Serialize against it with + * the anon_vma lock, the folio lock is not enough. + */ + src_anon_vma = folio_get_anon_vma(src_folio); + if (!src_anon_vma) { + /* page was unmapped from under us */ + err = -EAGAIN; + goto out; + } + if (!anon_vma_trylock_write(src_anon_vma)) { + pte_unmap(&orig_src_pte); + pte_unmap(&orig_dst_pte); + src_pte = dst_pte = NULL; + /* now we can block and wait */ + anon_vma_lock_write(src_anon_vma); + goto retry; + } + } + + err = move_present_pte(mm, dst_vma, src_vma, + dst_addr, src_addr, dst_pte, src_pte, + orig_dst_pte, orig_src_pte, + dst_ptl, src_ptl, src_folio); + } else { + entry = pte_to_swp_entry(orig_src_pte); + if (non_swap_entry(entry)) { + if (is_migration_entry(entry)) { + pte_unmap(&orig_src_pte); + pte_unmap(&orig_dst_pte); + src_pte = dst_pte = NULL; + migration_entry_wait(mm, src_pmd, src_addr); + err = -EAGAIN; + } else + err = -EFAULT; + goto out; + } + + err = move_swap_pte(mm, dst_addr, src_addr, + dst_pte, src_pte, + orig_dst_pte, orig_src_pte, + dst_ptl, src_ptl); + } + +out: + if (src_anon_vma) { + anon_vma_unlock_write(src_anon_vma); + put_anon_vma(src_anon_vma); + } + if (src_folio) { + folio_unlock(src_folio); + folio_put(src_folio); + } + if (dst_pte) + pte_unmap(dst_pte); + if (src_pte) + pte_unmap(src_pte); + mmu_notifier_invalidate_range_end(&range); + + return err; +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline bool move_splits_huge_pmd(unsigned long dst_addr, + unsigned long src_addr, + unsigned long src_end) +{ + return (src_addr & ~HPAGE_PMD_MASK) || (dst_addr & ~HPAGE_PMD_MASK) || + src_end - src_addr < HPAGE_PMD_SIZE; +} +#else +static inline bool move_splits_huge_pmd(unsigned long dst_addr, + unsigned long src_addr, + unsigned long src_end) +{ + /* This is unreachable anyway, just to avoid warnings when HPAGE_PMD_SIZE==0 */ + return false; +} +#endif + +static inline bool vma_move_compatible(struct vm_area_struct *vma) +{ + return !(vma->vm_flags & (VM_PFNMAP | VM_IO | VM_HUGETLB | + VM_MIXEDMAP | VM_SHADOW_STACK)); +} + +static int validate_move_areas(struct userfaultfd_ctx *ctx, + struct vm_area_struct *src_vma, + struct vm_area_struct *dst_vma) +{ + /* Only allow moving if both have the same access and protection */ + if ((src_vma->vm_flags & VM_ACCESS_FLAGS) != (dst_vma->vm_flags & VM_ACCESS_FLAGS) || + pgprot_val(src_vma->vm_page_prot) != pgprot_val(dst_vma->vm_page_prot)) + return -EINVAL; + + /* Only allow moving if both are mlocked or both aren't */ + if ((src_vma->vm_flags & VM_LOCKED) != (dst_vma->vm_flags & VM_LOCKED)) + return -EINVAL; + + /* + * For now, we keep it simple and only move between writable VMAs. + * Access flags are equal, therefore cheching only the source is enough. + */ + if (!(src_vma->vm_flags & VM_WRITE)) + return -EINVAL; + + /* Check if vma flags indicate content which can be moved */ + if (!vma_move_compatible(src_vma) || !vma_move_compatible(dst_vma)) + return -EINVAL; + + /* Ensure dst_vma is registered in uffd we are operating on */ + if (!dst_vma->vm_userfaultfd_ctx.ctx || + dst_vma->vm_userfaultfd_ctx.ctx != ctx) + return -EINVAL; + + /* Only allow moving across anonymous vmas */ + if (!vma_is_anonymous(src_vma) || !vma_is_anonymous(dst_vma)) + return -EINVAL; + + /* + * Ensure the dst_vma has a anon_vma or this page + * would get a NULL anon_vma when moved in the + * dst_vma. + */ + if (unlikely(anon_vma_prepare(dst_vma))) + return -ENOMEM; + + return 0; +} + +/** + * move_pages - move arbitrary anonymous pages of an existing vma + * @ctx: pointer to the userfaultfd context + * @mm: the address space to move pages + * @dst_start: start of the destination virtual memory range + * @src_start: start of the source virtual memory range + * @len: length of the virtual memory range + * @mode: flags from uffdio_move.mode + * + * Must be called with mmap_lock held for read. + * + * move_pages() remaps arbitrary anonymous pages atomically in zero + * copy. It only works on non shared anonymous pages because those can + * be relocated without generating non linear anon_vmas in the rmap + * code. + * + * It provides a zero copy mechanism to handle userspace page faults. + * The source vma pages should have mapcount == 1, which can be + * enforced by using madvise(MADV_DONTFORK) on src vma. + * + * The thread receiving the page during the userland page fault + * will receive the faulting page in the source vma through the network, + * storage or any other I/O device (MADV_DONTFORK in the source vma + * avoids move_pages() to fail with -EBUSY if the process forks before + * move_pages() is called), then it will call move_pages() to map the + * page in the faulting address in the destination vma. + * + * This userfaultfd command works purely via pagetables, so it's the + * most efficient way to move physical non shared anonymous pages + * across different virtual addresses. Unlike mremap()/mmap()/munmap() + * it does not create any new vmas. The mapping in the destination + * address is atomic. + * + * It only works if the vma protection bits are identical from the + * source and destination vma. + * + * It can remap non shared anonymous pages within the same vma too. + * + * If the source virtual memory range has any unmapped holes, or if + * the destination virtual memory range is not a whole unmapped hole, + * move_pages() will fail respectively with -ENOENT or -EEXIST. This + * provides a very strict behavior to avoid any chance of memory + * corruption going unnoticed if there are userland race conditions. + * Only one thread should resolve the userland page fault at any given + * time for any given faulting address. This means that if two threads + * try to both call move_pages() on the same destination address at the + * same time, the second thread will get an explicit error from this + * command. + * + * The command retval will return "len" is successful. The command + * however can be interrupted by fatal signals or errors. If + * interrupted it will return the number of bytes successfully + * remapped before the interruption if any, or the negative error if + * none. It will never return zero. Either it will return an error or + * an amount of bytes successfully moved. If the retval reports a + * "short" remap, the move_pages() command should be repeated by + * userland with src+retval, dst+reval, len-retval if it wants to know + * about the error that interrupted it. + * + * The UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES flag can be specified to + * prevent -ENOENT errors to materialize if there are holes in the + * source virtual range that is being remapped. The holes will be + * accounted as successfully remapped in the retval of the + * command. This is mostly useful to remap hugepage naturally aligned + * virtual regions without knowing if there are transparent hugepage + * in the regions or not, but preventing the risk of having to split + * the hugepmd during the remap. + * + * If there's any rmap walk that is taking the anon_vma locks without + * first obtaining the folio lock (the only current instance is + * folio_referenced), they will have to verify if the folio->mapping + * has changed after taking the anon_vma lock. If it changed they + * should release the lock and retry obtaining a new anon_vma, because + * it means the anon_vma was changed by move_pages() before the lock + * could be obtained. This is the only additional complexity added to + * the rmap code to provide this anonymous page remapping functionality. + */ +ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm, + unsigned long dst_start, unsigned long src_start, + unsigned long len, __u64 mode) +{ + struct vm_area_struct *src_vma, *dst_vma; + unsigned long src_addr, dst_addr; + pmd_t *src_pmd, *dst_pmd; + long err = -EINVAL; + ssize_t moved = 0; + + /* Sanitize the command parameters. */ + if (WARN_ON_ONCE(src_start & ~PAGE_MASK) || + WARN_ON_ONCE(dst_start & ~PAGE_MASK) || + WARN_ON_ONCE(len & ~PAGE_MASK)) + goto out; + + /* Does the address range wrap, or is the span zero-sized? */ + if (WARN_ON_ONCE(src_start + len <= src_start) || + WARN_ON_ONCE(dst_start + len <= dst_start)) + goto out; + + /* + * Make sure the vma is not shared, that the src and dst remap + * ranges are both valid and fully within a single existing + * vma. + */ + src_vma = find_vma(mm, src_start); + if (!src_vma || (src_vma->vm_flags & VM_SHARED)) + goto out; + if (src_start < src_vma->vm_start || + src_start + len > src_vma->vm_end) + goto out; + + dst_vma = find_vma(mm, dst_start); + if (!dst_vma || (dst_vma->vm_flags & VM_SHARED)) + goto out; + if (dst_start < dst_vma->vm_start || + dst_start + len > dst_vma->vm_end) + goto out; + + err = validate_move_areas(ctx, src_vma, dst_vma); + if (err) + goto out; + + for (src_addr = src_start, dst_addr = dst_start; + src_addr < src_start + len;) { + spinlock_t *ptl; + pmd_t dst_pmdval; + unsigned long step_size; + + /* + * Below works because anonymous area would not have a + * transparent huge PUD. If file-backed support is added, + * that case would need to be handled here. + */ + src_pmd = mm_find_pmd(mm, src_addr); + if (unlikely(!src_pmd)) { + if (!(mode & UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES)) { + err = -ENOENT; + break; + } + src_pmd = mm_alloc_pmd(mm, src_addr); + if (unlikely(!src_pmd)) { + err = -ENOMEM; + break; + } + } + dst_pmd = mm_alloc_pmd(mm, dst_addr); + if (unlikely(!dst_pmd)) { + err = -ENOMEM; + break; + } + + dst_pmdval = pmdp_get_lockless(dst_pmd); + /* + * If the dst_pmd is mapped as THP don't override it and just + * be strict. If dst_pmd changes into TPH after this check, the + * move_pages_huge_pmd() will detect the change and retry + * while move_pages_pte() will detect the change and fail. + */ + if (unlikely(pmd_trans_huge(dst_pmdval))) { + err = -EEXIST; + break; + } + + ptl = pmd_trans_huge_lock(src_pmd, src_vma); + if (ptl) { + if (pmd_devmap(*src_pmd)) { + spin_unlock(ptl); + err = -ENOENT; + break; + } + + /* Check if we can move the pmd without splitting it. */ + if (move_splits_huge_pmd(dst_addr, src_addr, src_start + len) || + !pmd_none(dst_pmdval)) { + struct folio *folio = pfn_folio(pmd_pfn(*src_pmd)); + + if (!folio || !PageAnonExclusive(&folio->page)) { + spin_unlock(ptl); + err = -EBUSY; + break; + } + + spin_unlock(ptl); + split_huge_pmd(src_vma, src_pmd, src_addr); + /* The folio will be split by move_pages_pte() */ + continue; + } + + err = move_pages_huge_pmd(mm, dst_pmd, src_pmd, + dst_pmdval, dst_vma, src_vma, + dst_addr, src_addr); + step_size = HPAGE_PMD_SIZE; + } else { + if (pmd_none(*src_pmd)) { + if (!(mode & UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES)) { + err = -ENOENT; + break; + } + if (unlikely(__pte_alloc(mm, src_pmd))) { + err = -ENOMEM; + break; + } + } + + if (unlikely(pte_alloc(mm, dst_pmd))) { + err = -ENOMEM; + break; + } + + err = move_pages_pte(mm, dst_pmd, src_pmd, + dst_vma, src_vma, + dst_addr, src_addr, mode); + step_size = PAGE_SIZE; + } + + cond_resched(); + + if (fatal_signal_pending(current)) { + /* Do not override an error */ + if (!err || err == -EAGAIN) + err = -EINTR; + break; + } + + if (err) { + if (err == -EAGAIN) + continue; + break; + } + + /* Proceed to the next page */ + dst_addr += step_size; + src_addr += step_size; + moved += step_size; + } + +out: + VM_WARN_ON(moved < 0); + VM_WARN_ON(err > 0); + VM_WARN_ON(!moved && !err); + return moved ? moved : err; +} -- cgit From 02018c544ef113e980a2349eba89003d6f399d22 Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Thu, 21 Dec 2023 19:00:34 +0100 Subject: net: phy: Introduce ethernet link topology representation Link topologies containing multiple network PHYs attached to the same net_device can be found when using a PHY as a media converter for use with an SFP connector, on which an SFP transceiver containing a PHY can be used. With the current model, the transceiver's PHY can't be used for operations such as cable testing, timestamping, macsec offload, etc. The reason being that most of the logic for these configuration, coming from either ethtool netlink or ioctls tend to use netdev->phydev, which in multi-phy systems will reference the PHY closest to the MAC. Introduce a numbering scheme allowing to enumerate PHY devices that belong to any netdev, which can in turn allow userspace to take more precise decisions with regard to each PHY's configuration. The numbering is maintained per-netdev, in a phy_device_list. The numbering works similarly to a netdevice's ifindex, with identifiers that are only recycled once INT_MAX has been reached. This prevents races that could occur between PHY listing and SFP transceiver removal/insertion. The identifiers are assigned at phy_attach time, as the numbering depends on the netdevice the phy is attached to. Signed-off-by: Maxime Chevallier Signed-off-by: David S. Miller --- MAINTAINERS | 2 + drivers/net/phy/Makefile | 2 +- drivers/net/phy/phy_device.c | 7 ++++ drivers/net/phy/phy_link_topology.c | 66 +++++++++++++++++++++++++++++++++ include/linux/netdevice.h | 4 +- include/linux/phy.h | 4 ++ include/linux/phy_link_topology.h | 67 ++++++++++++++++++++++++++++++++++ include/linux/phy_link_topology_core.h | 19 ++++++++++ include/uapi/linux/ethtool.h | 16 ++++++++ net/core/dev.c | 3 ++ 10 files changed, 188 insertions(+), 2 deletions(-) create mode 100644 drivers/net/phy/phy_link_topology.c create mode 100644 include/linux/phy_link_topology.h create mode 100644 include/linux/phy_link_topology_core.h (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 2b916990d7f0..79ac49b113dc 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7871,6 +7871,8 @@ F: include/linux/mii.h F: include/linux/of_net.h F: include/linux/phy.h F: include/linux/phy_fixed.h +F: include/linux/phy_link_topology.h +F: include/linux/phy_link_topology_core.h F: include/linux/phylib_stubs.h F: include/linux/platform_data/mdio-bcm-unimac.h F: include/linux/platform_data/mdio-gpio.h diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 6097afd44392..f218954fd7a8 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -2,7 +2,7 @@ # Makefile for Linux PHY drivers libphy-y := phy.o phy-c45.o phy-core.o phy_device.o \ - linkmode.o + linkmode.o phy_link_topology.o mdio-bus-y += mdio_bus.o mdio_device.o ifdef CONFIG_MDIO_DEVICE diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 3611ea64875e..ab8ae976a2f8 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include @@ -1491,6 +1492,11 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, if (phydev->sfp_bus_attached) dev->sfp_bus = phydev->sfp_bus; + + err = phy_link_topo_add_phy(&dev->link_topo, phydev, + PHY_UPSTREAM_MAC, dev); + if (err) + goto error; } /* Some Ethernet drivers try to connect to a PHY device before @@ -1820,6 +1826,7 @@ void phy_detach(struct phy_device *phydev) if (dev) { phydev->attached_dev->phydev = NULL; phydev->attached_dev = NULL; + phy_link_topo_del_phy(&dev->link_topo, phydev); } phydev->phylink = NULL; diff --git a/drivers/net/phy/phy_link_topology.c b/drivers/net/phy/phy_link_topology.c new file mode 100644 index 000000000000..34e7e08fbfc3 --- /dev/null +++ b/drivers/net/phy/phy_link_topology.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Infrastructure to handle all PHY devices connected to a given netdev, + * either directly or indirectly attached. + * + * Copyright (c) 2023 Maxime Chevallier + */ + +#include +#include +#include +#include +#include + +int phy_link_topo_add_phy(struct phy_link_topology *topo, + struct phy_device *phy, + enum phy_upstream upt, void *upstream) +{ + struct phy_device_node *pdn; + int ret; + + pdn = kzalloc(sizeof(*pdn), GFP_KERNEL); + if (!pdn) + return -ENOMEM; + + pdn->phy = phy; + switch (upt) { + case PHY_UPSTREAM_MAC: + pdn->upstream.netdev = (struct net_device *)upstream; + if (phy_on_sfp(phy)) + pdn->parent_sfp_bus = pdn->upstream.netdev->sfp_bus; + break; + case PHY_UPSTREAM_PHY: + pdn->upstream.phydev = (struct phy_device *)upstream; + if (phy_on_sfp(phy)) + pdn->parent_sfp_bus = pdn->upstream.phydev->sfp_bus; + break; + default: + ret = -EINVAL; + goto err; + } + pdn->upstream_type = upt; + + ret = xa_alloc_cyclic(&topo->phys, &phy->phyindex, pdn, xa_limit_32b, + &topo->next_phy_index, GFP_KERNEL); + if (ret) + goto err; + + return 0; + +err: + kfree(pdn); + return ret; +} +EXPORT_SYMBOL_GPL(phy_link_topo_add_phy); + +void phy_link_topo_del_phy(struct phy_link_topology *topo, + struct phy_device *phy) +{ + struct phy_device_node *pdn = xa_erase(&topo->phys, phy->phyindex); + + phy->phyindex = 0; + + kfree(pdn); +} +EXPORT_SYMBOL_GPL(phy_link_topo_del_phy); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 75c7725e5e4f..5baa5517f533 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -40,7 +40,6 @@ #include #endif #include - #include #include #include @@ -52,6 +51,7 @@ #include #include #include +#include struct netpoll_info; struct device; @@ -2047,6 +2047,7 @@ enum netdev_stat_type { * @fcoe_ddp_xid: Max exchange id for FCoE LRO by ddp * * @priomap: XXX: need comments on this one + * @link_topo: Physical link topology tracking attached PHYs * @phydev: Physical device may attach itself * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. @@ -2441,6 +2442,7 @@ struct net_device { #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map __rcu *priomap; #endif + struct phy_link_topology link_topo; struct phy_device *phydev; struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; diff --git a/include/linux/phy.h b/include/linux/phy.h index ede891776d8b..ea9416797b89 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -547,6 +547,9 @@ struct macsec_ops; * @drv: Pointer to the driver for this PHY instance * @devlink: Create a link between phy dev and mac dev, if the external phy * used by current mac interface is managed by another mac interface. + * @phyindex: Unique id across the phy's parent tree of phys to address the PHY + * from userspace, similar to ifindex. A zero index means the PHY + * wasn't assigned an id yet. * @phy_id: UID for this device found during discovery * @c45_ids: 802.3-c45 Device Identifiers if is_c45. * @is_c45: Set to true if this PHY uses clause 45 addressing. @@ -646,6 +649,7 @@ struct phy_device { struct device_link *devlink; + u32 phyindex; u32 phy_id; struct phy_c45_device_ids c45_ids; diff --git a/include/linux/phy_link_topology.h b/include/linux/phy_link_topology.h new file mode 100644 index 000000000000..91902263ec0e --- /dev/null +++ b/include/linux/phy_link_topology.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PHY device list allow maintaining a list of PHY devices that are + * part of a netdevice's link topology. PHYs can for example be chained, + * as is the case when using a PHY that exposes an SFP module, on which an + * SFP transceiver that embeds a PHY is connected. + * + * This list can then be used by userspace to leverage individual PHY + * capabilities. + */ +#ifndef __PHY_LINK_TOPOLOGY_H +#define __PHY_LINK_TOPOLOGY_H + +#include +#include + +struct xarray; +struct phy_device; +struct net_device; +struct sfp_bus; + +struct phy_device_node { + enum phy_upstream upstream_type; + + union { + struct net_device *netdev; + struct phy_device *phydev; + } upstream; + + struct sfp_bus *parent_sfp_bus; + + struct phy_device *phy; +}; + +static inline struct phy_device * +phy_link_topo_get_phy(struct phy_link_topology *topo, u32 phyindex) +{ + struct phy_device_node *pdn = xa_load(&topo->phys, phyindex); + + if (pdn) + return pdn->phy; + + return NULL; +} + +#if IS_ENABLED(CONFIG_PHYLIB) +int phy_link_topo_add_phy(struct phy_link_topology *topo, + struct phy_device *phy, + enum phy_upstream upt, void *upstream); + +void phy_link_topo_del_phy(struct phy_link_topology *lt, struct phy_device *phy); + +#else +static inline int phy_link_topo_add_phy(struct phy_link_topology *topo, + struct phy_device *phy, + enum phy_upstream upt, void *upstream) +{ + return 0; +} + +static inline void phy_link_topo_del_phy(struct phy_link_topology *topo, + struct phy_device *phy) +{ +} +#endif + +#endif /* __PHY_LINK_TOPOLOGY_H */ diff --git a/include/linux/phy_link_topology_core.h b/include/linux/phy_link_topology_core.h new file mode 100644 index 000000000000..78c75f909489 --- /dev/null +++ b/include/linux/phy_link_topology_core.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PHY_LINK_TOPOLOGY_CORE_H +#define __PHY_LINK_TOPOLOGY_CORE_H + +struct xarray; + +struct phy_link_topology { + struct xarray phys; + + u32 next_phy_index; +}; + +static inline void phy_link_topo_init(struct phy_link_topology *topo) +{ + xa_init_flags(&topo->phys, XA_FLAGS_ALLOC1); + topo->next_phy_index = 1; +} + +#endif /* __PHY_LINK_TOPOLOGY_CORE_H */ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 85c412c23ab5..60801df9d8c0 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2219,4 +2219,20 @@ struct ethtool_link_settings { * __u32 map_lp_advertising[link_mode_masks_nwords]; */ }; + +/** + * enum phy_upstream - Represents the upstream component a given PHY device + * is connected to, as in what is on the other end of the MII bus. Most PHYs + * will be attached to an Ethernet MAC controller, but in some cases, there's + * an intermediate PHY used as a media-converter, which will driver another + * MII interface as its output. + * @PHY_UPSTREAM_MAC: Upstream component is a MAC (a switch port, + * or ethernet controller) + * @PHY_UPSTREAM_PHY: Upstream component is a PHY (likely a media converter) + */ +enum phy_upstream { + PHY_UPSTREAM_MAC, + PHY_UPSTREAM_PHY, +}; + #endif /* _UAPI_LINUX_ETHTOOL_H */ diff --git a/net/core/dev.c b/net/core/dev.c index f9d4b550ef4b..df04cbf77551 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -153,6 +153,7 @@ #include #include #include +#include #include "dev.h" #include "net-sysfs.h" @@ -10875,6 +10876,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, #ifdef CONFIG_NET_SCHED hash_init(dev->qdisc_hash); #endif + phy_link_topo_init(&dev->link_topo); + dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); -- cgit From 2ab0edb505faa9ac90dee1732571390f074e8113 Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Thu, 21 Dec 2023 19:00:38 +0100 Subject: net: ethtool: Allow passing a phy index for some commands Some netlink commands are target towards ethernet PHYs, to control some of their features. As there's several such commands, add the ability to pass a PHY index in the ethnl request, which will populate the generic ethnl_req_info with the relevant phydev when the command targets a PHY. Signed-off-by: Maxime Chevallier Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 7 +++++++ include/uapi/linux/ethtool_netlink.h | 1 + net/ethtool/netlink.c | 24 ++++++++++++++++++++++++ net/ethtool/netlink.h | 7 +++++-- 4 files changed, 37 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index d583d9abf2f8..3ca6c21e74af 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -57,6 +57,7 @@ Structure of this header is ``ETHTOOL_A_HEADER_DEV_INDEX`` u32 device ifindex ``ETHTOOL_A_HEADER_DEV_NAME`` string device name ``ETHTOOL_A_HEADER_FLAGS`` u32 flags common for all requests + ``ETHTOOL_A_HEADER_PHY_INDEX`` u32 phy device index ============================== ====== ============================= ``ETHTOOL_A_HEADER_DEV_INDEX`` and ``ETHTOOL_A_HEADER_DEV_NAME`` identify the @@ -81,6 +82,12 @@ the behaviour is backward compatible, i.e. requests from old clients not aware of the flag should be interpreted the way the client expects. A client must not set flags it does not understand. +``ETHTOOL_A_HEADER_PHY_INDEX`` identify the ethernet PHY the message relates to. +As there are numerous commands that are related to PHY configuration, and because +we can have more than one PHY on the link, the PHY index can be passed in the +request for the commands that needs it. It is however not mandatory, and if it +is not passed for commands that target a PHY, the net_device.phydev pointer +is used, as a fallback that keeps the legacy behaviour. Bit sets ======== diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 3f89074aa06c..422e8cfdd98c 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -133,6 +133,7 @@ enum { ETHTOOL_A_HEADER_DEV_INDEX, /* u32 */ ETHTOOL_A_HEADER_DEV_NAME, /* string */ ETHTOOL_A_HEADER_FLAGS, /* u32 - ETHTOOL_FLAG_* */ + ETHTOOL_A_HEADER_PHY_INDEX, /* u32 */ /* add new constants above here */ __ETHTOOL_A_HEADER_CNT, diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index fe3553f60bf3..1c26766ce996 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -4,6 +4,7 @@ #include #include #include "netlink.h" +#include static struct genl_family ethtool_genl_family; @@ -20,6 +21,7 @@ const struct nla_policy ethnl_header_policy[] = { .len = ALTIFNAMSIZ - 1 }, [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, ETHTOOL_FLAGS_BASIC), + [ETHTOOL_A_HEADER_PHY_INDEX] = NLA_POLICY_MIN(NLA_U32, 1), }; const struct nla_policy ethnl_header_policy_stats[] = { @@ -28,6 +30,7 @@ const struct nla_policy ethnl_header_policy_stats[] = { .len = ALTIFNAMSIZ - 1 }, [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, ETHTOOL_FLAGS_STATS), + [ETHTOOL_A_HEADER_PHY_INDEX] = NLA_POLICY_MIN(NLA_U32, 1), }; int ethnl_ops_begin(struct net_device *dev) @@ -91,6 +94,7 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, { struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy)]; const struct nlattr *devname_attr; + struct phy_device *phydev = NULL; struct net_device *dev = NULL; u32 flags = 0; int ret; @@ -145,6 +149,26 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, return -EINVAL; } + if (dev) { + if (tb[ETHTOOL_A_HEADER_PHY_INDEX]) { + u32 phy_index = nla_get_u32(tb[ETHTOOL_A_HEADER_PHY_INDEX]); + + phydev = phy_link_topo_get_phy(&dev->link_topo, + phy_index); + if (!phydev) { + NL_SET_ERR_MSG_ATTR(extack, header, + "no phy matches phy index"); + return -EINVAL; + } + } else { + /* If we need a PHY but no phy index is specified, fallback + * to dev->phydev + */ + phydev = dev->phydev; + } + } + + req_info->phydev = phydev; req_info->dev = dev; req_info->flags = flags; return 0; diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 9a333a8d04c1..def84e2def9e 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -250,6 +250,7 @@ static inline unsigned int ethnl_reply_header_size(void) * @dev: network device the request is for (may be null) * @dev_tracker: refcount tracker for @dev reference * @flags: request flags common for all request types + * @phydev: phy_device connected to @dev this request is for (may be null) * * This is a common base for request specific structures holding data from * parsed userspace request. These always embed struct ethnl_req_info at @@ -259,6 +260,7 @@ struct ethnl_req_info { struct net_device *dev; netdevice_tracker dev_tracker; u32 flags; + struct phy_device *phydev; }; static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info) @@ -395,9 +397,10 @@ extern const struct ethnl_request_ops ethnl_rss_request_ops; extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops; extern const struct ethnl_request_ops ethnl_plca_status_request_ops; extern const struct ethnl_request_ops ethnl_mm_request_ops; +extern const struct ethnl_request_ops ethnl_phy_request_ops; -extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; -extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; +extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_PHY_INDEX + 1]; +extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_PHY_INDEX + 1]; extern const struct nla_policy ethnl_strset_get_policy[ETHTOOL_A_STRSET_COUNTS_ONLY + 1]; extern const struct nla_policy ethnl_linkinfo_get_policy[ETHTOOL_A_LINKINFO_HEADER + 1]; extern const struct nla_policy ethnl_linkinfo_set_policy[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL + 1]; -- cgit From 63d5eaf35ac36cad00cfb3809d794ef0078c822b Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Thu, 21 Dec 2023 19:00:40 +0100 Subject: net: ethtool: Introduce a command to list PHYs on an interface As we have the ability to track the PHYs connected to a net_device through the link_topology, we can expose this list to userspace. This allows userspace to use these identifiers for phy-specific commands and take the decision of which PHY to target by knowing the link topology. Add PHY_GET and PHY_DUMP, which can be a filtered DUMP operation to list devices on only one interface. Signed-off-by: Maxime Chevallier Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 44 ++++ include/uapi/linux/ethtool_netlink.h | 29 +++ net/ethtool/Makefile | 2 +- net/ethtool/netlink.c | 9 + net/ethtool/netlink.h | 5 + net/ethtool/phy.c | 306 +++++++++++++++++++++++++++ 6 files changed, 394 insertions(+), 1 deletion(-) create mode 100644 net/ethtool/phy.c (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 3ca6c21e74af..97ff787a7dd8 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -2011,6 +2011,49 @@ The attributes are propagated to the driver through the following structure: .. kernel-doc:: include/linux/ethtool.h :identifiers: ethtool_mm_cfg +PHY_GET +======= + +Retrieve information about a given Ethernet PHY sitting on the link. As there +can be more than one PHY, the DUMP operation can be used to list the PHYs +present on a given interface, by passing an interface index or name in +the dump request + +Request contents: + + ==================================== ====== ========================== + ``ETHTOOL_A_PHY_HEADER`` nested request header + ==================================== ====== ========================== + +Kernel response contents: + + ===================================== ====== ========================== + ``ETHTOOL_A_PHY_HEADER`` nested request header + ``ETHTOOL_A_PHY_INDEX`` u32 the phy's unique index, that can + be used for phy-specific requests + ``ETHTOOL_A_PHY_DRVNAME`` string the phy driver name + ``ETHTOOL_A_PHY_NAME`` string the phy device name + ``ETHTOOL_A_PHY_UPSTREAM_TYPE`` u32 the type of device this phy is + connected to + ``ETHTOOL_A_PHY_UPSTREAM_PHY`` nested if the phy is connected to another + phy, this nest contains info on + that connection + ``ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME`` string if the phy controls an sfp bus, + the name of the sfp bus + ``ETHTOOL_A_PHY_ID`` u32 the phy id if the phy is C22 + ===================================== ====== ========================== + +When ``ETHTOOL_A_PHY_UPSTREAM_TYPE`` is PHY_UPSTREAM_PHY, the PHY's parent is +another PHY. Information on the parent PHY will be set in the +``ETHTOOL_A_PHY_UPSTREAM_PHY`` nest, which has the following structure : + + =================================== ====== ========================== + ``ETHTOOL_A_PHY_UPSTREAM_INDEX`` u32 the PHY index of the upstream PHY + ``ETHTOOL_A_PHY_UPSTREAM_SFP_NAME`` string if this PHY is connected to it's + parent PHY through an SFP bus, the + name of this sfp bus + =================================== ====== ========================== + Request translation =================== @@ -2117,4 +2160,5 @@ are netlink only. n/a ``ETHTOOL_MSG_PLCA_GET_STATUS`` n/a ``ETHTOOL_MSG_MM_GET`` n/a ``ETHTOOL_MSG_MM_SET`` + n/a ``ETHTOOL_MSG_PHY_GET`` =================================== ===================================== diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 422e8cfdd98c..00cd7ad16709 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -57,6 +57,7 @@ enum { ETHTOOL_MSG_PLCA_GET_STATUS, ETHTOOL_MSG_MM_GET, ETHTOOL_MSG_MM_SET, + ETHTOOL_MSG_PHY_GET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -109,6 +110,8 @@ enum { ETHTOOL_MSG_PLCA_NTF, ETHTOOL_MSG_MM_GET_REPLY, ETHTOOL_MSG_MM_NTF, + ETHTOOL_MSG_PHY_GET_REPLY, + ETHTOOL_MSG_PHY_NTF, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -977,6 +980,32 @@ enum { ETHTOOL_A_MM_MAX = (__ETHTOOL_A_MM_CNT - 1) }; +enum { + ETHTOOL_A_PHY_UPSTREAM_UNSPEC, + ETHTOOL_A_PHY_UPSTREAM_INDEX, /* u32 */ + ETHTOOL_A_PHY_UPSTREAM_SFP_NAME, /* string */ + + /* add new constants above here */ + __ETHTOOL_A_PHY_UPSTREAM_CNT, + ETHTOOL_A_PHY_UPSTREAM_MAX = (__ETHTOOL_A_PHY_UPSTREAM_CNT - 1) +}; + +enum { + ETHTOOL_A_PHY_UNSPEC, + ETHTOOL_A_PHY_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_PHY_INDEX, /* u32 */ + ETHTOOL_A_PHY_DRVNAME, /* string */ + ETHTOOL_A_PHY_NAME, /* string */ + ETHTOOL_A_PHY_UPSTREAM_TYPE, /* u8 */ + ETHTOOL_A_PHY_UPSTREAM, /* nest - _A_PHY_UPSTREAM_* */ + ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME, /* string */ + ETHTOOL_A_PHY_ID, /* u32 */ + + /* add new constants above here */ + __ETHTOOL_A_PHY_CNT, + ETHTOOL_A_PHY_MAX = (__ETHTOOL_A_PHY_CNT - 1) +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 504f954a1b28..0ccd0e9afd3f 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -8,4 +8,4 @@ ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ tunnels.o fec.o eeprom.o stats.o phc_vclocks.o mm.o \ - module.o pse-pd.o plca.o mm.o + module.o pse-pd.o plca.o mm.o phy.o diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 1c26766ce996..92b0dd8ca046 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -1153,6 +1153,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_mm_set_policy, .maxattr = ARRAY_SIZE(ethnl_mm_set_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_PHY_GET, + .doit = ethnl_phy_doit, + .start = ethnl_phy_start, + .dumpit = ethnl_phy_dumpit, + .done = ethnl_phy_done, + .policy = ethnl_phy_get_policy, + .maxattr = ARRAY_SIZE(ethnl_phy_get_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index def84e2def9e..5e6a43e35a09 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -444,6 +444,7 @@ extern const struct nla_policy ethnl_plca_set_cfg_policy[ETHTOOL_A_PLCA_MAX + 1] extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADER + 1]; extern const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1]; extern const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1]; +extern const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1]; int ethnl_set_features(struct sk_buff *skb, struct genl_info *info); int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info); @@ -451,6 +452,10 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info); int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info); int ethnl_tunnel_info_start(struct netlink_callback *cb); int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int ethnl_phy_start(struct netlink_callback *cb); +int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info); +int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int ethnl_phy_done(struct netlink_callback *cb); extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN]; diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c new file mode 100644 index 000000000000..5add2840aaeb --- /dev/null +++ b/net/ethtool/phy.c @@ -0,0 +1,306 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2023 Bootlin + * + */ +#include "common.h" +#include "netlink.h" + +#include +#include +#include + +struct phy_req_info { + struct ethnl_req_info base; + struct phy_device_node pdn; +}; + +#define PHY_REQINFO(__req_base) \ + container_of(__req_base, struct phy_req_info, base) + +const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1] = { + [ETHTOOL_A_PHY_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), +}; + +/* Caller holds rtnl */ +static ssize_t +ethnl_phy_reply_size(const struct ethnl_req_info *req_base, + struct netlink_ext_ack *extack) +{ + struct phy_link_topology *topo; + struct phy_device_node *pdn; + struct phy_device *phydev; + unsigned long index; + size_t size; + + ASSERT_RTNL(); + + topo = &req_base->dev->link_topo; + + size = nla_total_size(0); + + xa_for_each(&topo->phys, index, pdn) { + phydev = pdn->phy; + + /* ETHTOOL_A_PHY_INDEX */ + size += nla_total_size(sizeof(u32)); + + /* ETHTOOL_A_DRVNAME */ + size += nla_total_size(strlen(phydev->drv->name) + 1); + + /* ETHTOOL_A_NAME */ + size += nla_total_size(strlen(dev_name(&phydev->mdio.dev)) + 1); + + /* ETHTOOL_A_PHY_UPSTREAM_TYPE */ + size += nla_total_size(sizeof(u8)); + + /* ETHTOOL_A_PHY_ID */ + size += nla_total_size(sizeof(u32)); + + if (phy_on_sfp(phydev)) { + const char *upstream_sfp_name = sfp_get_name(pdn->parent_sfp_bus); + + /* ETHTOOL_A_PHY_UPSTREAM_SFP_NAME */ + if (upstream_sfp_name) + size += nla_total_size(strlen(upstream_sfp_name) + 1); + + /* ETHTOOL_A_PHY_UPSTREAM_INDEX */ + size += nla_total_size(sizeof(u32)); + } + + /* ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME */ + if (phydev->sfp_bus) { + const char *sfp_name = sfp_get_name(phydev->sfp_bus); + + if (sfp_name) + size += nla_total_size(strlen(sfp_name) + 1); + } + } + + return size; +} + +static int +ethnl_phy_fill_reply(const struct ethnl_req_info *req_base, struct sk_buff *skb) +{ + struct phy_req_info *req_info = PHY_REQINFO(req_base); + struct phy_device_node *pdn = &req_info->pdn; + struct phy_device *phydev = pdn->phy; + enum phy_upstream ptype; + struct nlattr *nest; + + ptype = pdn->upstream_type; + + if (nla_put_u32(skb, ETHTOOL_A_PHY_INDEX, phydev->phyindex) || + nla_put_string(skb, ETHTOOL_A_PHY_DRVNAME, phydev->drv->name) || + nla_put_string(skb, ETHTOOL_A_PHY_NAME, dev_name(&phydev->mdio.dev)) || + nla_put_u8(skb, ETHTOOL_A_PHY_UPSTREAM_TYPE, ptype) || + nla_put_u32(skb, ETHTOOL_A_PHY_ID, phydev->phy_id)) + return -EMSGSIZE; + + if (ptype == PHY_UPSTREAM_PHY) { + struct phy_device *upstream = pdn->upstream.phydev; + const char *sfp_upstream_name; + + nest = nla_nest_start(skb, ETHTOOL_A_PHY_UPSTREAM); + if (!nest) + return -EMSGSIZE; + + /* Parent index */ + if (nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_INDEX, upstream->phyindex)) + return -EMSGSIZE; + + if (pdn->parent_sfp_bus) { + sfp_upstream_name = sfp_get_name(pdn->parent_sfp_bus); + if (sfp_upstream_name && nla_put_string(skb, + ETHTOOL_A_PHY_UPSTREAM_SFP_NAME, + sfp_upstream_name)) + return -EMSGSIZE; + } + + nla_nest_end(skb, nest); + } + + if (phydev->sfp_bus) { + const char *sfp_name = sfp_get_name(phydev->sfp_bus); + + if (sfp_name && + nla_put_string(skb, ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME, + sfp_name)) + return -EMSGSIZE; + } + + return 0; +} + +static int ethnl_phy_parse_request(struct ethnl_req_info *req_base, + struct nlattr **tb) +{ + struct phy_link_topology *topo = &req_base->dev->link_topo; + struct phy_req_info *req_info = PHY_REQINFO(req_base); + struct phy_device_node *pdn; + + if (!req_base->phydev) + return 0; + + pdn = xa_load(&topo->phys, req_base->phydev->phyindex); + memcpy(&req_info->pdn, pdn, sizeof(*pdn)); + + return 0; +} + +int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct phy_req_info req_info = {}; + struct nlattr **tb = info->attrs; + struct sk_buff *rskb; + void *reply_payload; + int reply_len; + int ret; + + ret = ethnl_parse_header_dev_get(&req_info.base, + tb[ETHTOOL_A_PHY_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + + rtnl_lock(); + + ret = ethnl_phy_parse_request(&req_info.base, tb); + if (ret < 0) + goto err_unlock_rtnl; + + /* No PHY, return early */ + if (!req_info.pdn.phy) + goto err_unlock_rtnl; + + ret = ethnl_phy_reply_size(&req_info.base, info->extack); + if (ret < 0) + goto err_unlock_rtnl; + reply_len = ret + ethnl_reply_header_size(); + + rskb = ethnl_reply_init(reply_len, req_info.base.dev, + ETHTOOL_MSG_PHY_GET_REPLY, + ETHTOOL_A_PHY_HEADER, + info, &reply_payload); + if (!rskb) { + ret = -ENOMEM; + goto err_unlock_rtnl; + } + + ret = ethnl_phy_fill_reply(&req_info.base, rskb); + if (ret) + goto err_free_msg; + + rtnl_unlock(); + ethnl_parse_header_dev_put(&req_info.base); + genlmsg_end(rskb, reply_payload); + + return genlmsg_reply(rskb, info); + +err_free_msg: + nlmsg_free(rskb); +err_unlock_rtnl: + rtnl_unlock(); + ethnl_parse_header_dev_put(&req_info.base); + return ret; +} + +struct ethnl_phy_dump_ctx { + struct phy_req_info *phy_req_info; +}; + +int ethnl_phy_start(struct netlink_callback *cb) +{ + const struct genl_dumpit_info *info = genl_dumpit_info(cb); + struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; + struct nlattr **tb = info->info.attrs; + int ret; + + BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); + + ctx->phy_req_info = kzalloc(sizeof(*ctx->phy_req_info), GFP_KERNEL); + if (!ctx->phy_req_info) + return -ENOMEM; + + ret = ethnl_parse_header_dev_get(&ctx->phy_req_info->base, + tb[ETHTOOL_A_PHY_HEADER], + sock_net(cb->skb->sk), cb->extack, + false); + return ret; +} + +int ethnl_phy_done(struct netlink_callback *cb) +{ + struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; + + kfree(ctx->phy_req_info); + + return 0; +} + +static int ethnl_phy_dump_one_dev(struct sk_buff *skb, struct net_device *dev, + struct netlink_callback *cb) +{ + struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; + struct phy_req_info *pri = ctx->phy_req_info; + struct phy_device_node *pdn; + unsigned long index = 1; + int ret = 0; + void *ehdr; + + pri->base.dev = dev; + + xa_for_each(&dev->link_topo.phys, index, pdn) { + ehdr = ethnl_dump_put(skb, cb, + ETHTOOL_MSG_PHY_GET_REPLY); + if (!ehdr) { + ret = -EMSGSIZE; + break; + } + + ret = ethnl_fill_reply_header(skb, dev, + ETHTOOL_A_PHY_HEADER); + if (ret < 0) { + genlmsg_cancel(skb, ehdr); + break; + } + + memcpy(&pri->pdn, pdn, sizeof(*pdn)); + ret = ethnl_phy_fill_reply(&pri->base, skb); + + genlmsg_end(skb, ehdr); + } + + return ret; +} + +int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; + struct net *net = sock_net(skb->sk); + unsigned long ifindex = 1; + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + + if (ctx->phy_req_info->base.dev) { + ret = ethnl_phy_dump_one_dev(skb, ctx->phy_req_info->base.dev, cb); + ethnl_parse_header_dev_put(&ctx->phy_req_info->base); + ctx->phy_req_info->base.dev = NULL; + } else { + for_each_netdev_dump(net, dev, ifindex) { + ret = ethnl_phy_dump_one_dev(skb, dev, cb); + if (ret) + break; + } + } + rtnl_unlock(); + + if (ret == -EMSGSIZE && skb->len) + return skb->len; + return ret; +} + -- cgit From ba24ea129126362e7139fed4e13701ca5b71ac0b Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Thu, 21 Dec 2023 16:31:03 -0500 Subject: net/sched: Retire ipt action The tc ipt action was intended to run all netfilter/iptables target. Unfortunately it has not benefitted over the years from proper updates when netfilter changes, and for that reason it has remained rudimentary. Pinging a bunch of people that i was aware were using this indicates that removing it wont affect them. Retire it to reduce maintenance efforts. Buh-bye. Reviewed-by: Victor Noguiera Reviewed-by: Pedro Tammela Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/tc_act/tc_ipt.h | 17 -- include/net/tc_wrapper.h | 4 - include/uapi/linux/pkt_cls.h | 4 +- include/uapi/linux/tc_act/tc_ipt.h | 20 -- net/sched/Makefile | 1 - net/sched/act_ipt.c | 464 ------------------------------ tools/testing/selftests/tc-testing/config | 1 - tools/testing/selftests/tc-testing/tdc.sh | 1 - 8 files changed, 2 insertions(+), 510 deletions(-) delete mode 100644 include/net/tc_act/tc_ipt.h delete mode 100644 include/uapi/linux/tc_act/tc_ipt.h delete mode 100644 net/sched/act_ipt.c (limited to 'include/uapi/linux') diff --git a/include/net/tc_act/tc_ipt.h b/include/net/tc_act/tc_ipt.h deleted file mode 100644 index 4225fcb1c6ba..000000000000 --- a/include/net/tc_act/tc_ipt.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __NET_TC_IPT_H -#define __NET_TC_IPT_H - -#include - -struct xt_entry_target; - -struct tcf_ipt { - struct tc_action common; - u32 tcfi_hook; - char *tcfi_tname; - struct xt_entry_target *tcfi_t; -}; -#define to_ipt(a) ((struct tcf_ipt *)a) - -#endif /* __NET_TC_IPT_H */ diff --git a/include/net/tc_wrapper.h b/include/net/tc_wrapper.h index a6d481b5bcbc..a608546bcefc 100644 --- a/include/net/tc_wrapper.h +++ b/include/net/tc_wrapper.h @@ -117,10 +117,6 @@ static inline int tc_act(struct sk_buff *skb, const struct tc_action *a, if (a->ops->act == tcf_ife_act) return tcf_ife_act(skb, a, res); #endif -#if IS_BUILTIN(CONFIG_NET_ACT_IPT) - if (a->ops->act == tcf_ipt_act) - return tcf_ipt_act(skb, a, res); -#endif #if IS_BUILTIN(CONFIG_NET_ACT_SIMP) if (a->ops->act == tcf_simp_act) return tcf_simp_act(skb, a, res); diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index c7082cc60d21..2fec9b51d28d 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -99,7 +99,7 @@ enum { * versions. */ #define TCA_ACT_GACT 5 -#define TCA_ACT_IPT 6 +#define TCA_ACT_IPT 6 /* obsoleted, can be reused */ #define TCA_ACT_PEDIT 7 #define TCA_ACT_MIRRED 8 #define TCA_ACT_NAT 9 @@ -120,7 +120,7 @@ enum tca_id { TCA_ID_UNSPEC = 0, TCA_ID_POLICE = 1, TCA_ID_GACT = TCA_ACT_GACT, - TCA_ID_IPT = TCA_ACT_IPT, + TCA_ID_IPT = TCA_ACT_IPT, /* Obsoleted, can be reused */ TCA_ID_PEDIT = TCA_ACT_PEDIT, TCA_ID_MIRRED = TCA_ACT_MIRRED, TCA_ID_NAT = TCA_ACT_NAT, diff --git a/include/uapi/linux/tc_act/tc_ipt.h b/include/uapi/linux/tc_act/tc_ipt.h deleted file mode 100644 index c48d7da6750d..000000000000 --- a/include/uapi/linux/tc_act/tc_ipt.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef __LINUX_TC_IPT_H -#define __LINUX_TC_IPT_H - -#include - -enum { - TCA_IPT_UNSPEC, - TCA_IPT_TABLE, - TCA_IPT_HOOK, - TCA_IPT_INDEX, - TCA_IPT_CNT, - TCA_IPT_TM, - TCA_IPT_TARG, - TCA_IPT_PAD, - __TCA_IPT_MAX -}; -#define TCA_IPT_MAX (__TCA_IPT_MAX - 1) - -#endif diff --git a/net/sched/Makefile b/net/sched/Makefile index b5fd49641d91..82c3f78ca486 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -13,7 +13,6 @@ obj-$(CONFIG_NET_ACT_POLICE) += act_police.o obj-$(CONFIG_NET_ACT_GACT) += act_gact.o obj-$(CONFIG_NET_ACT_MIRRED) += act_mirred.o obj-$(CONFIG_NET_ACT_SAMPLE) += act_sample.o -obj-$(CONFIG_NET_ACT_IPT) += act_ipt.o obj-$(CONFIG_NET_ACT_NAT) += act_nat.o obj-$(CONFIG_NET_ACT_PEDIT) += act_pedit.o obj-$(CONFIG_NET_ACT_SIMP) += act_simple.o diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c deleted file mode 100644 index 598d6e299152..000000000000 --- a/net/sched/act_ipt.c +++ /dev/null @@ -1,464 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * net/sched/act_ipt.c iptables target interface - * - *TODO: Add other tables. For now we only support the ipv4 table targets - * - * Copyright: Jamal Hadi Salim (2002-13) - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include - - -static struct tc_action_ops act_ipt_ops; -static struct tc_action_ops act_xt_ops; - -static int ipt_init_target(struct net *net, struct xt_entry_target *t, - char *table, unsigned int hook) -{ - struct xt_tgchk_param par; - struct xt_target *target; - struct ipt_entry e = {}; - int ret = 0; - - target = xt_request_find_target(AF_INET, t->u.user.name, - t->u.user.revision); - if (IS_ERR(target)) - return PTR_ERR(target); - - t->u.kernel.target = target; - memset(&par, 0, sizeof(par)); - par.net = net; - par.table = table; - par.entryinfo = &e; - par.target = target; - par.targinfo = t->data; - par.hook_mask = 1 << hook; - par.family = NFPROTO_IPV4; - - ret = xt_check_target(&par, t->u.target_size - sizeof(*t), 0, false); - if (ret < 0) { - module_put(t->u.kernel.target->me); - return ret; - } - return 0; -} - -static void ipt_destroy_target(struct xt_entry_target *t, struct net *net) -{ - struct xt_tgdtor_param par = { - .target = t->u.kernel.target, - .targinfo = t->data, - .family = NFPROTO_IPV4, - .net = net, - }; - if (par.target->destroy != NULL) - par.target->destroy(&par); - module_put(par.target->me); -} - -static void tcf_ipt_release(struct tc_action *a) -{ - struct tcf_ipt *ipt = to_ipt(a); - - if (ipt->tcfi_t) { - ipt_destroy_target(ipt->tcfi_t, a->idrinfo->net); - kfree(ipt->tcfi_t); - } - kfree(ipt->tcfi_tname); -} - -static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { - [TCA_IPT_TABLE] = { .type = NLA_STRING, .len = IFNAMSIZ }, - [TCA_IPT_HOOK] = NLA_POLICY_RANGE(NLA_U32, NF_INET_PRE_ROUTING, - NF_INET_NUMHOOKS), - [TCA_IPT_INDEX] = { .type = NLA_U32 }, - [TCA_IPT_TARG] = { .len = sizeof(struct xt_entry_target) }, -}; - -static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, - struct nlattr *est, struct tc_action **a, - const struct tc_action_ops *ops, - struct tcf_proto *tp, u32 flags) -{ - struct tc_action_net *tn = net_generic(net, id); - bool bind = flags & TCA_ACT_FLAGS_BIND; - struct nlattr *tb[TCA_IPT_MAX + 1]; - struct tcf_ipt *ipt; - struct xt_entry_target *td, *t; - char *tname; - bool exists = false; - int ret = 0, err; - u32 hook = 0; - u32 index = 0; - - if (nla == NULL) - return -EINVAL; - - err = nla_parse_nested_deprecated(tb, TCA_IPT_MAX, nla, ipt_policy, - NULL); - if (err < 0) - return err; - - if (tb[TCA_IPT_INDEX] != NULL) - index = nla_get_u32(tb[TCA_IPT_INDEX]); - - err = tcf_idr_check_alloc(tn, &index, a, bind); - if (err < 0) - return err; - exists = err; - if (exists && bind) - return 0; - - if (tb[TCA_IPT_HOOK] == NULL || tb[TCA_IPT_TARG] == NULL) { - if (exists) - tcf_idr_release(*a, bind); - else - tcf_idr_cleanup(tn, index); - return -EINVAL; - } - - td = (struct xt_entry_target *)nla_data(tb[TCA_IPT_TARG]); - if (nla_len(tb[TCA_IPT_TARG]) != td->u.target_size) { - if (exists) - tcf_idr_release(*a, bind); - else - tcf_idr_cleanup(tn, index); - return -EINVAL; - } - - if (!exists) { - ret = tcf_idr_create(tn, index, est, a, ops, bind, - false, flags); - if (ret) { - tcf_idr_cleanup(tn, index); - return ret; - } - ret = ACT_P_CREATED; - } else { - if (bind)/* dont override defaults */ - return 0; - - if (!(flags & TCA_ACT_FLAGS_REPLACE)) { - tcf_idr_release(*a, bind); - return -EEXIST; - } - } - - err = -EINVAL; - hook = nla_get_u32(tb[TCA_IPT_HOOK]); - switch (hook) { - case NF_INET_PRE_ROUTING: - break; - case NF_INET_POST_ROUTING: - break; - default: - goto err1; - } - - if (tb[TCA_IPT_TABLE]) { - /* mangle only for now */ - if (nla_strcmp(tb[TCA_IPT_TABLE], "mangle")) - goto err1; - } - - tname = kstrdup("mangle", GFP_KERNEL); - if (unlikely(!tname)) - goto err1; - - t = kmemdup(td, td->u.target_size, GFP_KERNEL); - if (unlikely(!t)) - goto err2; - - err = ipt_init_target(net, t, tname, hook); - if (err < 0) - goto err3; - - ipt = to_ipt(*a); - - spin_lock_bh(&ipt->tcf_lock); - if (ret != ACT_P_CREATED) { - ipt_destroy_target(ipt->tcfi_t, net); - kfree(ipt->tcfi_tname); - kfree(ipt->tcfi_t); - } - ipt->tcfi_tname = tname; - ipt->tcfi_t = t; - ipt->tcfi_hook = hook; - spin_unlock_bh(&ipt->tcf_lock); - return ret; - -err3: - kfree(t); -err2: - kfree(tname); -err1: - tcf_idr_release(*a, bind); - return err; -} - -static int tcf_ipt_init(struct net *net, struct nlattr *nla, - struct nlattr *est, struct tc_action **a, - struct tcf_proto *tp, - u32 flags, struct netlink_ext_ack *extack) -{ - return __tcf_ipt_init(net, act_ipt_ops.net_id, nla, est, - a, &act_ipt_ops, tp, flags); -} - -static int tcf_xt_init(struct net *net, struct nlattr *nla, - struct nlattr *est, struct tc_action **a, - struct tcf_proto *tp, - u32 flags, struct netlink_ext_ack *extack) -{ - return __tcf_ipt_init(net, act_xt_ops.net_id, nla, est, - a, &act_xt_ops, tp, flags); -} - -static bool tcf_ipt_act_check(struct sk_buff *skb) -{ - const struct iphdr *iph; - unsigned int nhoff, len; - - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - return false; - - nhoff = skb_network_offset(skb); - iph = ip_hdr(skb); - if (iph->ihl < 5 || iph->version != 4) - return false; - - len = skb_ip_totlen(skb); - if (skb->len < nhoff + len || len < (iph->ihl * 4u)) - return false; - - return pskb_may_pull(skb, iph->ihl * 4u); -} - -TC_INDIRECT_SCOPE int tcf_ipt_act(struct sk_buff *skb, - const struct tc_action *a, - struct tcf_result *res) -{ - char saved_cb[sizeof_field(struct sk_buff, cb)]; - int ret = 0, result = 0; - struct tcf_ipt *ipt = to_ipt(a); - struct xt_action_param par; - struct nf_hook_state state = { - .net = dev_net(skb->dev), - .in = skb->dev, - .hook = ipt->tcfi_hook, - .pf = NFPROTO_IPV4, - }; - - if (skb_protocol(skb, false) != htons(ETH_P_IP)) - return TC_ACT_UNSPEC; - - if (skb_unclone(skb, GFP_ATOMIC)) - return TC_ACT_UNSPEC; - - if (!tcf_ipt_act_check(skb)) - return TC_ACT_UNSPEC; - - if (state.hook == NF_INET_POST_ROUTING) { - if (!skb_dst(skb)) - return TC_ACT_UNSPEC; - - state.out = skb->dev; - } - - memcpy(saved_cb, skb->cb, sizeof(saved_cb)); - - spin_lock(&ipt->tcf_lock); - - tcf_lastuse_update(&ipt->tcf_tm); - bstats_update(&ipt->tcf_bstats, skb); - - /* yes, we have to worry about both in and out dev - * worry later - danger - this API seems to have changed - * from earlier kernels - */ - par.state = &state; - par.target = ipt->tcfi_t->u.kernel.target; - par.targinfo = ipt->tcfi_t->data; - - memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); - - ret = par.target->target(skb, &par); - - switch (ret) { - case NF_ACCEPT: - result = TC_ACT_OK; - break; - case NF_DROP: - result = TC_ACT_SHOT; - ipt->tcf_qstats.drops++; - break; - case XT_CONTINUE: - result = TC_ACT_PIPE; - break; - default: - net_notice_ratelimited("tc filter: Bogus netfilter code %d assume ACCEPT\n", - ret); - result = TC_ACT_OK; - break; - } - spin_unlock(&ipt->tcf_lock); - - memcpy(skb->cb, saved_cb, sizeof(skb->cb)); - - return result; - -} - -static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, - int ref) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tcf_ipt *ipt = to_ipt(a); - struct xt_entry_target *t; - struct tcf_t tm; - struct tc_cnt c; - - /* for simple targets kernel size == user size - * user name = target name - * for foolproof you need to not assume this - */ - - spin_lock_bh(&ipt->tcf_lock); - t = kmemdup(ipt->tcfi_t, ipt->tcfi_t->u.user.target_size, GFP_ATOMIC); - if (unlikely(!t)) - goto nla_put_failure; - - c.bindcnt = atomic_read(&ipt->tcf_bindcnt) - bind; - c.refcnt = refcount_read(&ipt->tcf_refcnt) - ref; - strcpy(t->u.user.name, ipt->tcfi_t->u.kernel.target->name); - - if (nla_put(skb, TCA_IPT_TARG, ipt->tcfi_t->u.user.target_size, t) || - nla_put_u32(skb, TCA_IPT_INDEX, ipt->tcf_index) || - nla_put_u32(skb, TCA_IPT_HOOK, ipt->tcfi_hook) || - nla_put(skb, TCA_IPT_CNT, sizeof(struct tc_cnt), &c) || - nla_put_string(skb, TCA_IPT_TABLE, ipt->tcfi_tname)) - goto nla_put_failure; - - tcf_tm_dump(&tm, &ipt->tcf_tm); - if (nla_put_64bit(skb, TCA_IPT_TM, sizeof(tm), &tm, TCA_IPT_PAD)) - goto nla_put_failure; - - spin_unlock_bh(&ipt->tcf_lock); - kfree(t); - return skb->len; - -nla_put_failure: - spin_unlock_bh(&ipt->tcf_lock); - nlmsg_trim(skb, b); - kfree(t); - return -1; -} - -static struct tc_action_ops act_ipt_ops = { - .kind = "ipt", - .id = TCA_ID_IPT, - .owner = THIS_MODULE, - .act = tcf_ipt_act, - .dump = tcf_ipt_dump, - .cleanup = tcf_ipt_release, - .init = tcf_ipt_init, - .size = sizeof(struct tcf_ipt), -}; - -static __net_init int ipt_init_net(struct net *net) -{ - struct tc_action_net *tn = net_generic(net, act_ipt_ops.net_id); - - return tc_action_net_init(net, tn, &act_ipt_ops); -} - -static void __net_exit ipt_exit_net(struct list_head *net_list) -{ - tc_action_net_exit(net_list, act_ipt_ops.net_id); -} - -static struct pernet_operations ipt_net_ops = { - .init = ipt_init_net, - .exit_batch = ipt_exit_net, - .id = &act_ipt_ops.net_id, - .size = sizeof(struct tc_action_net), -}; - -static struct tc_action_ops act_xt_ops = { - .kind = "xt", - .id = TCA_ID_XT, - .owner = THIS_MODULE, - .act = tcf_ipt_act, - .dump = tcf_ipt_dump, - .cleanup = tcf_ipt_release, - .init = tcf_xt_init, - .size = sizeof(struct tcf_ipt), -}; - -static __net_init int xt_init_net(struct net *net) -{ - struct tc_action_net *tn = net_generic(net, act_xt_ops.net_id); - - return tc_action_net_init(net, tn, &act_xt_ops); -} - -static void __net_exit xt_exit_net(struct list_head *net_list) -{ - tc_action_net_exit(net_list, act_xt_ops.net_id); -} - -static struct pernet_operations xt_net_ops = { - .init = xt_init_net, - .exit_batch = xt_exit_net, - .id = &act_xt_ops.net_id, - .size = sizeof(struct tc_action_net), -}; - -MODULE_AUTHOR("Jamal Hadi Salim(2002-13)"); -MODULE_DESCRIPTION("Iptables target actions"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("act_xt"); - -static int __init ipt_init_module(void) -{ - int ret1, ret2; - - ret1 = tcf_register_action(&act_xt_ops, &xt_net_ops); - if (ret1 < 0) - pr_err("Failed to load xt action\n"); - - ret2 = tcf_register_action(&act_ipt_ops, &ipt_net_ops); - if (ret2 < 0) - pr_err("Failed to load ipt action\n"); - - if (ret1 < 0 && ret2 < 0) { - return ret1; - } else - return 0; -} - -static void __exit ipt_cleanup_module(void) -{ - tcf_unregister_action(&act_ipt_ops, &ipt_net_ops); - tcf_unregister_action(&act_xt_ops, &xt_net_ops); -} - -module_init(ipt_init_module); -module_exit(ipt_cleanup_module); diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index 012aa33b341b..c60acba951c2 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -82,7 +82,6 @@ CONFIG_NET_ACT_GACT=m CONFIG_GACT_PROB=y CONFIG_NET_ACT_MIRRED=m CONFIG_NET_ACT_SAMPLE=m -CONFIG_NET_ACT_IPT=m CONFIG_NET_ACT_NAT=m CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh index 407fa53822a0..c53ede8b730d 100755 --- a/tools/testing/selftests/tc-testing/tdc.sh +++ b/tools/testing/selftests/tc-testing/tdc.sh @@ -20,7 +20,6 @@ try_modprobe act_ct try_modprobe act_ctinfo try_modprobe act_gact try_modprobe act_gate -try_modprobe act_ipt try_modprobe act_mirred try_modprobe act_mpls try_modprobe act_nat -- cgit From 41bc3e8fc1f728085da0ca6dbc1bef4a2ddb543c Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 23 Dec 2023 09:01:50 -0500 Subject: net/sched: Remove uapi support for rsvp classifier commit 265b4da82dbf ("net/sched: Retire rsvp classifier") retired the TC RSVP classifier. Remove UAPI for it. Iproute2 will sync by equally removing it from user space. Reviewed-by: Victor Nogueira Reviewed-by: Pedro Tammela Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 31 ------------------------------- tools/include/uapi/linux/pkt_cls.h | 31 ------------------------------- 2 files changed, 62 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 2fec9b51d28d..fe922b61b99e 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -280,37 +280,6 @@ struct tc_u32_pcnt { #define TC_U32_MAXDEPTH 8 - -/* RSVP filter */ - -enum { - TCA_RSVP_UNSPEC, - TCA_RSVP_CLASSID, - TCA_RSVP_DST, - TCA_RSVP_SRC, - TCA_RSVP_PINFO, - TCA_RSVP_POLICE, - TCA_RSVP_ACT, - __TCA_RSVP_MAX -}; - -#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 ) - -struct tc_rsvp_gpi { - __u32 key; - __u32 mask; - int offset; -}; - -struct tc_rsvp_pinfo { - struct tc_rsvp_gpi dpi; - struct tc_rsvp_gpi spi; - __u8 protocol; - __u8 tunnelid; - __u8 tunnelhdr; - __u8 pad; -}; - /* ROUTE filter */ enum { diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h index 3faee0199a9b..82eccb6a4994 100644 --- a/tools/include/uapi/linux/pkt_cls.h +++ b/tools/include/uapi/linux/pkt_cls.h @@ -204,37 +204,6 @@ struct tc_u32_pcnt { #define TC_U32_MAXDEPTH 8 - -/* RSVP filter */ - -enum { - TCA_RSVP_UNSPEC, - TCA_RSVP_CLASSID, - TCA_RSVP_DST, - TCA_RSVP_SRC, - TCA_RSVP_PINFO, - TCA_RSVP_POLICE, - TCA_RSVP_ACT, - __TCA_RSVP_MAX -}; - -#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 ) - -struct tc_rsvp_gpi { - __u32 key; - __u32 mask; - int offset; -}; - -struct tc_rsvp_pinfo { - struct tc_rsvp_gpi dpi; - struct tc_rsvp_gpi spi; - __u8 protocol; - __u8 tunnelid; - __u8 tunnelhdr; - __u8 pad; -}; - /* ROUTE filter */ enum { -- cgit From 82b2545ed9a465e4c470d2dbbb461522f767c56f Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 23 Dec 2023 09:01:51 -0500 Subject: net/sched: Remove uapi support for tcindex classifier commit 8c710f75256b ("net/sched: Retire tcindex classifier") retired the TC tcindex classifier. Remove UAPI for it. Iproute2 will sync by equally removing it from user space. Reviewed-by: Victor Nogueira Reviewed-by: Pedro Tammela Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 16 ---------------- tools/include/uapi/linux/pkt_cls.h | 16 ---------------- 2 files changed, 32 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index fe922b61b99e..ea277039f89d 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -310,22 +310,6 @@ enum { #define TCA_FW_MAX (__TCA_FW_MAX - 1) -/* TC index filter */ - -enum { - TCA_TCINDEX_UNSPEC, - TCA_TCINDEX_HASH, - TCA_TCINDEX_MASK, - TCA_TCINDEX_SHIFT, - TCA_TCINDEX_FALL_THROUGH, - TCA_TCINDEX_CLASSID, - TCA_TCINDEX_POLICE, - TCA_TCINDEX_ACT, - __TCA_TCINDEX_MAX -}; - -#define TCA_TCINDEX_MAX (__TCA_TCINDEX_MAX - 1) - /* Flow filter */ enum { diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h index 82eccb6a4994..bd4b227ab4ba 100644 --- a/tools/include/uapi/linux/pkt_cls.h +++ b/tools/include/uapi/linux/pkt_cls.h @@ -234,22 +234,6 @@ enum { #define TCA_FW_MAX (__TCA_FW_MAX - 1) -/* TC index filter */ - -enum { - TCA_TCINDEX_UNSPEC, - TCA_TCINDEX_HASH, - TCA_TCINDEX_MASK, - TCA_TCINDEX_SHIFT, - TCA_TCINDEX_FALL_THROUGH, - TCA_TCINDEX_CLASSID, - TCA_TCINDEX_POLICE, - TCA_TCINDEX_ACT, - __TCA_TCINDEX_MAX -}; - -#define TCA_TCINDEX_MAX (__TCA_TCINDEX_MAX - 1) - /* Flow filter */ enum { -- cgit From fe3b739a5472968d8d349522b6816bc4db82bc0f Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 23 Dec 2023 09:01:52 -0500 Subject: net/sched: Remove uapi support for dsmark qdisc Commit bbe77c14ee61 ("net/sched: Retire dsmark qdisc") retired the dsmark classifier. Remove UAPI support for it. Iproute2 will sync by equally removing it from user space. Reviewed-by: Victor Nogueira Reviewed-by: Pedro Tammela Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 14 -------------- tools/include/uapi/linux/pkt_sched.h | 14 -------------- 2 files changed, 28 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index f762a10bfb78..1e3a2b9ddf7e 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -557,20 +557,6 @@ enum { #define TCA_CBQ_MAX (__TCA_CBQ_MAX - 1) -/* dsmark section */ - -enum { - TCA_DSMARK_UNSPEC, - TCA_DSMARK_INDICES, - TCA_DSMARK_DEFAULT_INDEX, - TCA_DSMARK_SET_TC_INDEX, - TCA_DSMARK_MASK, - TCA_DSMARK_VALUE, - __TCA_DSMARK_MAX, -}; - -#define TCA_DSMARK_MAX (__TCA_DSMARK_MAX - 1) - /* ATM section */ enum { diff --git a/tools/include/uapi/linux/pkt_sched.h b/tools/include/uapi/linux/pkt_sched.h index 5c903abc9fa5..0f164f1458fd 100644 --- a/tools/include/uapi/linux/pkt_sched.h +++ b/tools/include/uapi/linux/pkt_sched.h @@ -537,20 +537,6 @@ enum { #define TCA_CBQ_MAX (__TCA_CBQ_MAX - 1) -/* dsmark section */ - -enum { - TCA_DSMARK_UNSPEC, - TCA_DSMARK_INDICES, - TCA_DSMARK_DEFAULT_INDEX, - TCA_DSMARK_SET_TC_INDEX, - TCA_DSMARK_MASK, - TCA_DSMARK_VALUE, - __TCA_DSMARK_MAX, -}; - -#define TCA_DSMARK_MAX (__TCA_DSMARK_MAX - 1) - /* ATM section */ enum { -- cgit From 26cc8714fc7f79a806c3d7ffa215b984c384ab4d Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 23 Dec 2023 09:01:53 -0500 Subject: net/sched: Remove uapi support for ATM qdisc Commit fb38306ceb9e ("net/sched: Retire ATM qdisc") retired the ATM qdisc. Remove UAPI for it. Iproute2 will sync by equally removing it from user space. Reviewed-by: Victor Nogueira Reviewed-by: Pedro Tammela Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 15 --------------- tools/include/uapi/linux/pkt_sched.h | 15 --------------- 2 files changed, 30 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 1e3a2b9ddf7e..28f08acdad52 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -557,21 +557,6 @@ enum { #define TCA_CBQ_MAX (__TCA_CBQ_MAX - 1) -/* ATM section */ - -enum { - TCA_ATM_UNSPEC, - TCA_ATM_FD, /* file/socket descriptor */ - TCA_ATM_PTR, /* pointer to descriptor - later */ - TCA_ATM_HDR, /* LL header */ - TCA_ATM_EXCESS, /* excess traffic class (0 for CLP) */ - TCA_ATM_ADDR, /* PVC address (for output only) */ - TCA_ATM_STATE, /* VC state (ATM_VS_*; for output only) */ - __TCA_ATM_MAX, -}; - -#define TCA_ATM_MAX (__TCA_ATM_MAX - 1) - /* Network emulator */ enum { diff --git a/tools/include/uapi/linux/pkt_sched.h b/tools/include/uapi/linux/pkt_sched.h index 0f164f1458fd..fc695429bc59 100644 --- a/tools/include/uapi/linux/pkt_sched.h +++ b/tools/include/uapi/linux/pkt_sched.h @@ -537,21 +537,6 @@ enum { #define TCA_CBQ_MAX (__TCA_CBQ_MAX - 1) -/* ATM section */ - -enum { - TCA_ATM_UNSPEC, - TCA_ATM_FD, /* file/socket descriptor */ - TCA_ATM_PTR, /* pointer to descriptor - later */ - TCA_ATM_HDR, /* LL header */ - TCA_ATM_EXCESS, /* excess traffic class (0 for CLP) */ - TCA_ATM_ADDR, /* PVC address (for output only) */ - TCA_ATM_STATE, /* VC state (ATM_VS_*; for output only) */ - __TCA_ATM_MAX, -}; - -#define TCA_ATM_MAX (__TCA_ATM_MAX - 1) - /* Network emulator */ enum { -- cgit From 33241dca486264193ed68167c8eeae1fb197f3df Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 23 Dec 2023 09:01:54 -0500 Subject: net/sched: Remove uapi support for CBQ qdisc Commit 051d44209842 ("net/sched: Retire CBQ qdisc") retired the CBQ qdisc. Remove UAPI for it. Iproute2 will sync by equally removing it from user space. Reviewed-by: Victor Nogueira Reviewed-by: Pedro Tammela Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 80 ------------------------------------ tools/include/uapi/linux/pkt_sched.h | 80 ------------------------------------ 2 files changed, 160 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 28f08acdad52..a3cd0c2dc995 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -477,86 +477,6 @@ enum { #define TCA_HFSC_MAX (__TCA_HFSC_MAX - 1) - -/* CBQ section */ - -#define TC_CBQ_MAXPRIO 8 -#define TC_CBQ_MAXLEVEL 8 -#define TC_CBQ_DEF_EWMA 5 - -struct tc_cbq_lssopt { - unsigned char change; - unsigned char flags; -#define TCF_CBQ_LSS_BOUNDED 1 -#define TCF_CBQ_LSS_ISOLATED 2 - unsigned char ewma_log; - unsigned char level; -#define TCF_CBQ_LSS_FLAGS 1 -#define TCF_CBQ_LSS_EWMA 2 -#define TCF_CBQ_LSS_MAXIDLE 4 -#define TCF_CBQ_LSS_MINIDLE 8 -#define TCF_CBQ_LSS_OFFTIME 0x10 -#define TCF_CBQ_LSS_AVPKT 0x20 - __u32 maxidle; - __u32 minidle; - __u32 offtime; - __u32 avpkt; -}; - -struct tc_cbq_wrropt { - unsigned char flags; - unsigned char priority; - unsigned char cpriority; - unsigned char __reserved; - __u32 allot; - __u32 weight; -}; - -struct tc_cbq_ovl { - unsigned char strategy; -#define TC_CBQ_OVL_CLASSIC 0 -#define TC_CBQ_OVL_DELAY 1 -#define TC_CBQ_OVL_LOWPRIO 2 -#define TC_CBQ_OVL_DROP 3 -#define TC_CBQ_OVL_RCLASSIC 4 - unsigned char priority2; - __u16 pad; - __u32 penalty; -}; - -struct tc_cbq_police { - unsigned char police; - unsigned char __res1; - unsigned short __res2; -}; - -struct tc_cbq_fopt { - __u32 split; - __u32 defmap; - __u32 defchange; -}; - -struct tc_cbq_xstats { - __u32 borrows; - __u32 overactions; - __s32 avgidle; - __s32 undertime; -}; - -enum { - TCA_CBQ_UNSPEC, - TCA_CBQ_LSSOPT, - TCA_CBQ_WRROPT, - TCA_CBQ_FOPT, - TCA_CBQ_OVL_STRATEGY, - TCA_CBQ_RATE, - TCA_CBQ_RTAB, - TCA_CBQ_POLICE, - __TCA_CBQ_MAX, -}; - -#define TCA_CBQ_MAX (__TCA_CBQ_MAX - 1) - /* Network emulator */ enum { diff --git a/tools/include/uapi/linux/pkt_sched.h b/tools/include/uapi/linux/pkt_sched.h index fc695429bc59..587481a19433 100644 --- a/tools/include/uapi/linux/pkt_sched.h +++ b/tools/include/uapi/linux/pkt_sched.h @@ -457,86 +457,6 @@ enum { #define TCA_HFSC_MAX (__TCA_HFSC_MAX - 1) - -/* CBQ section */ - -#define TC_CBQ_MAXPRIO 8 -#define TC_CBQ_MAXLEVEL 8 -#define TC_CBQ_DEF_EWMA 5 - -struct tc_cbq_lssopt { - unsigned char change; - unsigned char flags; -#define TCF_CBQ_LSS_BOUNDED 1 -#define TCF_CBQ_LSS_ISOLATED 2 - unsigned char ewma_log; - unsigned char level; -#define TCF_CBQ_LSS_FLAGS 1 -#define TCF_CBQ_LSS_EWMA 2 -#define TCF_CBQ_LSS_MAXIDLE 4 -#define TCF_CBQ_LSS_MINIDLE 8 -#define TCF_CBQ_LSS_OFFTIME 0x10 -#define TCF_CBQ_LSS_AVPKT 0x20 - __u32 maxidle; - __u32 minidle; - __u32 offtime; - __u32 avpkt; -}; - -struct tc_cbq_wrropt { - unsigned char flags; - unsigned char priority; - unsigned char cpriority; - unsigned char __reserved; - __u32 allot; - __u32 weight; -}; - -struct tc_cbq_ovl { - unsigned char strategy; -#define TC_CBQ_OVL_CLASSIC 0 -#define TC_CBQ_OVL_DELAY 1 -#define TC_CBQ_OVL_LOWPRIO 2 -#define TC_CBQ_OVL_DROP 3 -#define TC_CBQ_OVL_RCLASSIC 4 - unsigned char priority2; - __u16 pad; - __u32 penalty; -}; - -struct tc_cbq_police { - unsigned char police; - unsigned char __res1; - unsigned short __res2; -}; - -struct tc_cbq_fopt { - __u32 split; - __u32 defmap; - __u32 defchange; -}; - -struct tc_cbq_xstats { - __u32 borrows; - __u32 overactions; - __s32 avgidle; - __s32 undertime; -}; - -enum { - TCA_CBQ_UNSPEC, - TCA_CBQ_LSSOPT, - TCA_CBQ_WRROPT, - TCA_CBQ_FOPT, - TCA_CBQ_OVL_STRATEGY, - TCA_CBQ_RATE, - TCA_CBQ_RTAB, - TCA_CBQ_POLICE, - __TCA_CBQ_MAX, -}; - -#define TCA_CBQ_MAX (__TCA_CBQ_MAX - 1) - /* Network emulator */ enum { -- cgit From 0dd415d155050f5c1cf360b97f905d42d44f33ed Mon Sep 17 00:00:00 2001 From: Ahmed Zaki Date: Thu, 21 Dec 2023 11:42:35 -0700 Subject: net: ethtool: add a NO_CHANGE uAPI for new RXFH's input_xfrm Add a NO_CHANGE uAPI value for the new RXFH/RSS input_xfrm uAPI field. This needed so that user-space can set other RSS values (hkey or indir table) without affecting input_xfrm. Should have been part of [1]. Link: https://lore.kernel.org/netdev/20231213003321.605376-1-ahmed.zaki@intel.com/ [1] Fixes: 13e59344fb9d ("net: ethtool: add support for symmetric-xor RSS hash") Reviewed-by: Jacob Keller Signed-off-by: Ahmed Zaki Link: https://lore.kernel.org/r/20231221184235.9192-3-ahmed.zaki@intel.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/ethtool.h | 1 + net/ethtool/ioctl.c | 6 ++++-- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 60801df9d8c0..01ba529dbb6d 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2002,6 +2002,7 @@ static inline int ethtool_validate_duplex(__u8 duplex) * be exploited to reduce the RSS queue spread. */ #define RXH_XFRM_SYM_XOR (1 << 0) +#define RXH_XFRM_NO_CHANGE 0xff /* L2-L4 network traffic flow types */ #define TCP_V4_FLOW 0x01 /* hash or spec (tcp_ip4_spec) */ diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 9adc240b8f0e..4c4f46dfc251 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1304,14 +1304,16 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, return -EOPNOTSUPP; /* If either indir, hash key or function is valid, proceed further. - * Must request at least one change: indir size, hash key or function. + * Must request at least one change: indir size, hash key, function + * or input transformation. */ if ((rxfh.indir_size && rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE && rxfh.indir_size != dev_indir_size) || (rxfh.key_size && (rxfh.key_size != dev_key_size)) || (rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE && - rxfh.key_size == 0 && rxfh.hfunc == ETH_RSS_HASH_NO_CHANGE)) + rxfh.key_size == 0 && rxfh.hfunc == ETH_RSS_HASH_NO_CHANGE && + rxfh.input_xfrm == RXH_XFRM_NO_CHANGE)) return -EINVAL; if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) -- cgit From 76ac8e29855b06331d77a1d237a28ce97ac67a38 Mon Sep 17 00:00:00 2001 From: Crescent CY Hsieh Date: Fri, 1 Dec 2023 15:15:53 +0800 Subject: tty: serial: Cleanup the bit shift with macro This patch replaces the bit shift code with "_BITUL()" macro inside "serial_rs485" struct. Signed-off-by: Crescent CY Hsieh Link: https://lore.kernel.org/r/20231201071554.258607-2-crescentcy.hsieh@moxa.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/serial.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/serial.h b/include/uapi/linux/serial.h index 53bc1af67a41..6c75ebdd7797 100644 --- a/include/uapi/linux/serial.h +++ b/include/uapi/linux/serial.h @@ -11,6 +11,7 @@ #ifndef _UAPI_LINUX_SERIAL_H #define _UAPI_LINUX_SERIAL_H +#include #include #include @@ -140,14 +141,14 @@ struct serial_icounter_struct { */ struct serial_rs485 { __u32 flags; -#define SER_RS485_ENABLED (1 << 0) -#define SER_RS485_RTS_ON_SEND (1 << 1) -#define SER_RS485_RTS_AFTER_SEND (1 << 2) -#define SER_RS485_RX_DURING_TX (1 << 4) -#define SER_RS485_TERMINATE_BUS (1 << 5) -#define SER_RS485_ADDRB (1 << 6) -#define SER_RS485_ADDR_RECV (1 << 7) -#define SER_RS485_ADDR_DEST (1 << 8) +#define SER_RS485_ENABLED _BITUL(0) +#define SER_RS485_RTS_ON_SEND _BITUL(1) +#define SER_RS485_RTS_AFTER_SEND _BITUL(2) +#define SER_RS485_RX_DURING_TX _BITUL(3) +#define SER_RS485_TERMINATE_BUS _BITUL(4) +#define SER_RS485_ADDRB _BITUL(5) +#define SER_RS485_ADDR_RECV _BITUL(6) +#define SER_RS485_ADDR_DEST _BITUL(7) __u32 delay_rts_before_send; __u32 delay_rts_after_send; -- cgit From 6056f20f27e99fb67582f299468328505f130e36 Mon Sep 17 00:00:00 2001 From: Crescent CY Hsieh Date: Fri, 1 Dec 2023 15:15:54 +0800 Subject: tty: serial: Add RS422 flag to struct serial_rs485 Add "SER_RS485_MODE_RS422" flag to struct serial_rs485, so that serial port can switch interface into RS422 if supported by using ioctl command "TIOCSRS485". By treating RS422 as a mode of RS485, which means while enabling RS422 there are two flags need to be set (SER_RS485_ENABLED and SER_RS485_MODE_RS422), it would make things much easier. For example some places that checks for "SER_RS485_ENABLED" won't need to be rewritten. Signed-off-by: Crescent CY Hsieh Link: https://lore.kernel.org/r/20231201071554.258607-3-crescentcy.hsieh@moxa.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/serial_core.c | 6 ++++++ include/uapi/linux/serial.h | 2 ++ 2 files changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 1147fb1b39f2..d35371c076b2 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -1370,6 +1370,12 @@ static void uart_sanitize_serial_rs485(struct uart_port *port, struct serial_rs4 return; } + /* Clear other RS485 flags but SER_RS485_TERMINATE_BUS and return if enabling RS422 */ + if (rs485->flags & SER_RS485_MODE_RS422) { + rs485->flags &= (SER_RS485_ENABLED | SER_RS485_MODE_RS422 | SER_RS485_TERMINATE_BUS); + return; + } + /* Pick sane settings if the user hasn't */ if ((supported_flags & (SER_RS485_RTS_ON_SEND|SER_RS485_RTS_AFTER_SEND)) && !(rs485->flags & SER_RS485_RTS_ON_SEND) == diff --git a/include/uapi/linux/serial.h b/include/uapi/linux/serial.h index 6c75ebdd7797..9086367db043 100644 --- a/include/uapi/linux/serial.h +++ b/include/uapi/linux/serial.h @@ -138,6 +138,7 @@ struct serial_icounter_struct { * * %SER_RS485_ADDRB - Enable RS485 addressing mode. * * %SER_RS485_ADDR_RECV - Receive address filter (enables @addr_recv). Requires %SER_RS485_ADDRB. * * %SER_RS485_ADDR_DEST - Destination address (enables @addr_dest). Requires %SER_RS485_ADDRB. + * * %SER_RS485_MODE_RS422 - Enable RS422. Requires %SER_RS485_ENABLED. */ struct serial_rs485 { __u32 flags; @@ -149,6 +150,7 @@ struct serial_rs485 { #define SER_RS485_ADDRB _BITUL(5) #define SER_RS485_ADDR_RECV _BITUL(6) #define SER_RS485_ADDR_DEST _BITUL(7) +#define SER_RS485_MODE_RS422 _BITUL(8) __u32 delay_rts_before_send; __u32 delay_rts_after_send; -- cgit From 98e20e5e13d2811898921f999288be7151a11954 Mon Sep 17 00:00:00 2001 From: Quentin Deslandes Date: Tue, 26 Dec 2023 14:07:42 +0100 Subject: bpfilter: remove bpfilter bpfilter was supposed to convert iptables filtering rules into BPF programs on the fly, from the kernel, through a usermode helper. The base code for the UMH was introduced in 2018, and couple of attempts (2, 3) tried to introduce the BPF program generate features but were abandoned. bpfilter now sits in a kernel tree unused and unusable, occasionally causing confusion amongst Linux users (4, 5). As bpfilter is now developed in a dedicated repository on GitHub (6), it was suggested a couple of times this year (LSFMM/BPF 2023, LPC 2023) to remove the deprecated kernel part of the project. This is the purpose of this patch. [1]: https://lore.kernel.org/lkml/20180522022230.2492505-1-ast@kernel.org/ [2]: https://lore.kernel.org/bpf/20210829183608.2297877-1-me@ubique.spb.ru/#t [3]: https://lore.kernel.org/lkml/20221224000402.476079-1-qde@naccy.de/ [4]: https://dxuuu.xyz/bpfilter.html [5]: https://github.com/linuxkit/linuxkit/pull/3904 [6]: https://github.com/facebook/bpfilter Signed-off-by: Quentin Deslandes Link: https://lore.kernel.org/r/20231226130745.465988-1-qde@naccy.de Signed-off-by: Alexei Starovoitov --- arch/loongarch/configs/loongson3_defconfig | 1 - include/linux/bpfilter.h | 24 ----- include/uapi/linux/bpfilter.h | 21 ----- net/Kconfig | 2 - net/Makefile | 1 - net/bpfilter/.gitignore | 2 - net/bpfilter/Kconfig | 23 ----- net/bpfilter/Makefile | 20 ----- net/bpfilter/bpfilter_kern.c | 136 ----------------------------- net/bpfilter/bpfilter_umh_blob.S | 7 -- net/bpfilter/main.c | 64 -------------- net/bpfilter/msgfmt.h | 17 ---- net/ipv4/Makefile | 2 - net/ipv4/bpfilter/Makefile | 2 - net/ipv4/bpfilter/sockopt.c | 71 --------------- net/ipv4/ip_sockglue.c | 12 --- tools/bpf/bpftool/feature.c | 4 - tools/testing/selftests/bpf/config.aarch64 | 1 - tools/testing/selftests/bpf/config.s390x | 1 - tools/testing/selftests/bpf/config.x86_64 | 1 - tools/testing/selftests/hid/config | 1 - 21 files changed, 413 deletions(-) delete mode 100644 include/linux/bpfilter.h delete mode 100644 include/uapi/linux/bpfilter.h delete mode 100644 net/bpfilter/.gitignore delete mode 100644 net/bpfilter/Kconfig delete mode 100644 net/bpfilter/Makefile delete mode 100644 net/bpfilter/bpfilter_kern.c delete mode 100644 net/bpfilter/bpfilter_umh_blob.S delete mode 100644 net/bpfilter/main.c delete mode 100644 net/bpfilter/msgfmt.h delete mode 100644 net/ipv4/bpfilter/Makefile delete mode 100644 net/ipv4/bpfilter/sockopt.c (limited to 'include/uapi/linux') diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig index 9c333d133c30..60e331af9839 100644 --- a/arch/loongarch/configs/loongson3_defconfig +++ b/arch/loongarch/configs/loongson3_defconfig @@ -276,7 +276,6 @@ CONFIG_BRIDGE_EBT_T_NAT=m CONFIG_BRIDGE_EBT_ARP=m CONFIG_BRIDGE_EBT_IP=m CONFIG_BRIDGE_EBT_IP6=m -CONFIG_BPFILTER=y CONFIG_IP_SCTP=m CONFIG_RDS=y CONFIG_L2TP=m diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h deleted file mode 100644 index 736ded4905e0..000000000000 --- a/include/linux/bpfilter.h +++ /dev/null @@ -1,24 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_BPFILTER_H -#define _LINUX_BPFILTER_H - -#include -#include -#include - -struct sock; -int bpfilter_ip_set_sockopt(struct sock *sk, int optname, sockptr_t optval, - unsigned int optlen); -int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval, - int __user *optlen); - -struct bpfilter_umh_ops { - struct umd_info info; - /* since ip_getsockopt() can run in parallel, serialize access to umh */ - struct mutex lock; - int (*sockopt)(struct sock *sk, int optname, sockptr_t optval, - unsigned int optlen, bool is_set); - int (*start)(void); -}; -extern struct bpfilter_umh_ops bpfilter_ops; -#endif diff --git a/include/uapi/linux/bpfilter.h b/include/uapi/linux/bpfilter.h deleted file mode 100644 index cbc1f5813f50..000000000000 --- a/include/uapi/linux/bpfilter.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _UAPI_LINUX_BPFILTER_H -#define _UAPI_LINUX_BPFILTER_H - -#include - -enum { - BPFILTER_IPT_SO_SET_REPLACE = 64, - BPFILTER_IPT_SO_SET_ADD_COUNTERS = 65, - BPFILTER_IPT_SET_MAX, -}; - -enum { - BPFILTER_IPT_SO_GET_INFO = 64, - BPFILTER_IPT_SO_GET_ENTRIES = 65, - BPFILTER_IPT_SO_GET_REVISION_MATCH = 66, - BPFILTER_IPT_SO_GET_REVISION_TARGET = 67, - BPFILTER_IPT_GET_MAX, -}; - -#endif /* _UAPI_LINUX_BPFILTER_H */ diff --git a/net/Kconfig b/net/Kconfig index 3ec6bc98fa05..4adc47d0c9c2 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -233,8 +233,6 @@ source "net/bridge/netfilter/Kconfig" endif -source "net/bpfilter/Kconfig" - source "net/dccp/Kconfig" source "net/sctp/Kconfig" source "net/rds/Kconfig" diff --git a/net/Makefile b/net/Makefile index 4c4dc535453d..b06b5539e7a6 100644 --- a/net/Makefile +++ b/net/Makefile @@ -19,7 +19,6 @@ obj-$(CONFIG_TLS) += tls/ obj-$(CONFIG_XFRM) += xfrm/ obj-$(CONFIG_UNIX_SCM) += unix/ obj-y += ipv6/ -obj-$(CONFIG_BPFILTER) += bpfilter/ obj-$(CONFIG_PACKET) += packet/ obj-$(CONFIG_NET_KEY) += key/ obj-$(CONFIG_BRIDGE) += bridge/ diff --git a/net/bpfilter/.gitignore b/net/bpfilter/.gitignore deleted file mode 100644 index f34e85ee8204..000000000000 --- a/net/bpfilter/.gitignore +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -bpfilter_umh diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig deleted file mode 100644 index 3d4a21462458..000000000000 --- a/net/bpfilter/Kconfig +++ /dev/null @@ -1,23 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -menuconfig BPFILTER - bool "BPF based packet filtering framework (BPFILTER)" - depends on BPF && INET - select USERMODE_DRIVER - help - This builds experimental bpfilter framework that is aiming to - provide netfilter compatible functionality via BPF - -if BPFILTER -config BPFILTER_UMH - tristate "bpfilter kernel module with user mode helper" - depends on CC_CAN_LINK - depends on m || CC_CAN_LINK_STATIC - default m - help - This builds bpfilter kernel module with embedded user mode helper - - Note: To compile this as built-in, your toolchain must support - building static binaries, since rootfs isn't mounted at the time - when __init functions are called and do_execv won't be able to find - the elf interpreter. -endif diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile deleted file mode 100644 index cdac82b8c53a..000000000000 --- a/net/bpfilter/Makefile +++ /dev/null @@ -1,20 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# Makefile for the Linux BPFILTER layer. -# - -userprogs := bpfilter_umh -bpfilter_umh-objs := main.o -userccflags += -I $(srctree)/tools/include/ -I $(srctree)/tools/include/uapi - -ifeq ($(CONFIG_BPFILTER_UMH), y) -# builtin bpfilter_umh should be linked with -static -# since rootfs isn't mounted at the time of __init -# function is called and do_execv won't find elf interpreter -userldflags += -static -endif - -$(obj)/bpfilter_umh_blob.o: $(obj)/bpfilter_umh - -obj-$(CONFIG_BPFILTER_UMH) += bpfilter.o -bpfilter-objs += bpfilter_kern.o bpfilter_umh_blob.o diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c deleted file mode 100644 index 97e129e3f31c..000000000000 --- a/net/bpfilter/bpfilter_kern.c +++ /dev/null @@ -1,136 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include -#include -#include -#include -#include -#include -#include -#include -#include "msgfmt.h" - -extern char bpfilter_umh_start; -extern char bpfilter_umh_end; - -static void shutdown_umh(void) -{ - struct umd_info *info = &bpfilter_ops.info; - struct pid *tgid = info->tgid; - - if (tgid) { - kill_pid(tgid, SIGKILL, 1); - wait_event(tgid->wait_pidfd, thread_group_exited(tgid)); - umd_cleanup_helper(info); - } -} - -static void __stop_umh(void) -{ - if (IS_ENABLED(CONFIG_INET)) - shutdown_umh(); -} - -static int bpfilter_send_req(struct mbox_request *req) -{ - struct mbox_reply reply; - loff_t pos = 0; - ssize_t n; - - if (!bpfilter_ops.info.tgid) - return -EFAULT; - pos = 0; - n = kernel_write(bpfilter_ops.info.pipe_to_umh, req, sizeof(*req), - &pos); - if (n != sizeof(*req)) { - pr_err("write fail %zd\n", n); - goto stop; - } - pos = 0; - n = kernel_read(bpfilter_ops.info.pipe_from_umh, &reply, sizeof(reply), - &pos); - if (n != sizeof(reply)) { - pr_err("read fail %zd\n", n); - goto stop; - } - return reply.status; -stop: - __stop_umh(); - return -EFAULT; -} - -static int bpfilter_process_sockopt(struct sock *sk, int optname, - sockptr_t optval, unsigned int optlen, - bool is_set) -{ - struct mbox_request req = { - .is_set = is_set, - .pid = current->pid, - .cmd = optname, - .addr = (uintptr_t)optval.user, - .len = optlen, - }; - if (sockptr_is_kernel(optval)) { - pr_err("kernel access not supported\n"); - return -EFAULT; - } - return bpfilter_send_req(&req); -} - -static int start_umh(void) -{ - struct mbox_request req = { .pid = current->pid }; - int err; - - /* fork usermode process */ - err = fork_usermode_driver(&bpfilter_ops.info); - if (err) - return err; - pr_info("Loaded bpfilter_umh pid %d\n", pid_nr(bpfilter_ops.info.tgid)); - - /* health check that usermode process started correctly */ - if (bpfilter_send_req(&req) != 0) { - shutdown_umh(); - return -EFAULT; - } - - return 0; -} - -static int __init load_umh(void) -{ - int err; - - err = umd_load_blob(&bpfilter_ops.info, - &bpfilter_umh_start, - &bpfilter_umh_end - &bpfilter_umh_start); - if (err) - return err; - - mutex_lock(&bpfilter_ops.lock); - err = start_umh(); - if (!err && IS_ENABLED(CONFIG_INET)) { - bpfilter_ops.sockopt = &bpfilter_process_sockopt; - bpfilter_ops.start = &start_umh; - } - mutex_unlock(&bpfilter_ops.lock); - if (err) - umd_unload_blob(&bpfilter_ops.info); - return err; -} - -static void __exit fini_umh(void) -{ - mutex_lock(&bpfilter_ops.lock); - if (IS_ENABLED(CONFIG_INET)) { - shutdown_umh(); - bpfilter_ops.start = NULL; - bpfilter_ops.sockopt = NULL; - } - mutex_unlock(&bpfilter_ops.lock); - - umd_unload_blob(&bpfilter_ops.info); -} -module_init(load_umh); -module_exit(fini_umh); -MODULE_LICENSE("GPL"); diff --git a/net/bpfilter/bpfilter_umh_blob.S b/net/bpfilter/bpfilter_umh_blob.S deleted file mode 100644 index 40311d10d2f2..000000000000 --- a/net/bpfilter/bpfilter_umh_blob.S +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - .section .init.rodata, "a" - .global bpfilter_umh_start -bpfilter_umh_start: - .incbin "net/bpfilter/bpfilter_umh" - .global bpfilter_umh_end -bpfilter_umh_end: diff --git a/net/bpfilter/main.c b/net/bpfilter/main.c deleted file mode 100644 index 291a92546246..000000000000 --- a/net/bpfilter/main.c +++ /dev/null @@ -1,64 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#define _GNU_SOURCE -#include -#include -#include -#include -#include -#include -#include "../../include/uapi/linux/bpf.h" -#include -#include "msgfmt.h" - -FILE *debug_f; - -static int handle_get_cmd(struct mbox_request *cmd) -{ - switch (cmd->cmd) { - case 0: - return 0; - default: - break; - } - return -ENOPROTOOPT; -} - -static int handle_set_cmd(struct mbox_request *cmd) -{ - return -ENOPROTOOPT; -} - -static void loop(void) -{ - while (1) { - struct mbox_request req; - struct mbox_reply reply; - int n; - - n = read(0, &req, sizeof(req)); - if (n != sizeof(req)) { - fprintf(debug_f, "invalid request %d\n", n); - return; - } - - reply.status = req.is_set ? - handle_set_cmd(&req) : - handle_get_cmd(&req); - - n = write(1, &reply, sizeof(reply)); - if (n != sizeof(reply)) { - fprintf(debug_f, "reply failed %d\n", n); - return; - } - } -} - -int main(void) -{ - debug_f = fopen("/dev/kmsg", "w"); - setvbuf(debug_f, 0, _IOLBF, 0); - fprintf(debug_f, "<5>Started bpfilter\n"); - loop(); - fclose(debug_f); - return 0; -} diff --git a/net/bpfilter/msgfmt.h b/net/bpfilter/msgfmt.h deleted file mode 100644 index 98d121c62945..000000000000 --- a/net/bpfilter/msgfmt.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NET_BPFILTER_MSGFMT_H -#define _NET_BPFILTER_MSGFMT_H - -struct mbox_request { - __u64 addr; - __u32 len; - __u32 is_set; - __u32 cmd; - __u32 pid; -}; - -struct mbox_reply { - __u32 status; -}; - -#endif diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index e144a02a6a61..ec36d2ec059e 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -16,8 +16,6 @@ obj-y := route.o inetpeer.o protocol.o \ inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \ metrics.o netlink.o nexthop.o udp_tunnel_stub.o -obj-$(CONFIG_BPFILTER) += bpfilter/ - obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o obj-$(CONFIG_PROC_FS) += proc.o diff --git a/net/ipv4/bpfilter/Makefile b/net/ipv4/bpfilter/Makefile deleted file mode 100644 index 00af5305e05a..000000000000 --- a/net/ipv4/bpfilter/Makefile +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_BPFILTER) += sockopt.o diff --git a/net/ipv4/bpfilter/sockopt.c b/net/ipv4/bpfilter/sockopt.c deleted file mode 100644 index 193bcc2acccc..000000000000 --- a/net/ipv4/bpfilter/sockopt.c +++ /dev/null @@ -1,71 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include -#include -#include -#include -#include -#include -#include -#include -#include - -struct bpfilter_umh_ops bpfilter_ops; -EXPORT_SYMBOL_GPL(bpfilter_ops); - -static int bpfilter_mbox_request(struct sock *sk, int optname, sockptr_t optval, - unsigned int optlen, bool is_set) -{ - int err; - mutex_lock(&bpfilter_ops.lock); - if (!bpfilter_ops.sockopt) { - mutex_unlock(&bpfilter_ops.lock); - request_module("bpfilter"); - mutex_lock(&bpfilter_ops.lock); - - if (!bpfilter_ops.sockopt) { - err = -ENOPROTOOPT; - goto out; - } - } - if (bpfilter_ops.info.tgid && - thread_group_exited(bpfilter_ops.info.tgid)) - umd_cleanup_helper(&bpfilter_ops.info); - - if (!bpfilter_ops.info.tgid) { - err = bpfilter_ops.start(); - if (err) - goto out; - } - err = bpfilter_ops.sockopt(sk, optname, optval, optlen, is_set); -out: - mutex_unlock(&bpfilter_ops.lock); - return err; -} - -int bpfilter_ip_set_sockopt(struct sock *sk, int optname, sockptr_t optval, - unsigned int optlen) -{ - return bpfilter_mbox_request(sk, optname, optval, optlen, true); -} - -int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval, - int __user *optlen) -{ - int len; - - if (get_user(len, optlen)) - return -EFAULT; - - return bpfilter_mbox_request(sk, optname, USER_SOCKPTR(optval), len, - false); -} - -static int __init bpfilter_sockopt_init(void) -{ - mutex_init(&bpfilter_ops.lock); - bpfilter_ops.info.tgid = NULL; - bpfilter_ops.info.driver_name = "bpfilter_umh"; - - return 0; -} -device_initcall(bpfilter_sockopt_init); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 66247e8b429e..7aa9dc0e6760 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -47,8 +47,6 @@ #include #include -#include - /* * SOL_IP control messages. */ @@ -1411,11 +1409,6 @@ int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, return -ENOPROTOOPT; err = do_ip_setsockopt(sk, level, optname, optval, optlen); -#if IS_ENABLED(CONFIG_BPFILTER_UMH) - if (optname >= BPFILTER_IPT_SO_SET_REPLACE && - optname < BPFILTER_IPT_SET_MAX) - err = bpfilter_ip_set_sockopt(sk, optname, optval, optlen); -#endif #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IP_HDRINCL && @@ -1763,11 +1756,6 @@ int ip_getsockopt(struct sock *sk, int level, err = do_ip_getsockopt(sk, level, optname, USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); -#if IS_ENABLED(CONFIG_BPFILTER_UMH) - if (optname >= BPFILTER_IPT_SO_GET_INFO && - optname < BPFILTER_IPT_GET_MAX) - err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen); -#endif #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS && diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index edda4fc2c4d0..708733b0ea06 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -426,10 +426,6 @@ static void probe_kernel_image_config(const char *define_prefix) { "CONFIG_BPF_STREAM_PARSER", }, /* xt_bpf module for passing BPF programs to netfilter */ { "CONFIG_NETFILTER_XT_MATCH_BPF", }, - /* bpfilter back-end for iptables */ - { "CONFIG_BPFILTER", }, - /* bpftilter module with "user mode helper" */ - { "CONFIG_BPFILTER_UMH", }, /* test_bpf module for BPF tests */ { "CONFIG_TEST_BPF", }, diff --git a/tools/testing/selftests/bpf/config.aarch64 b/tools/testing/selftests/bpf/config.aarch64 index 29c8635c5722..3720b7611523 100644 --- a/tools/testing/selftests/bpf/config.aarch64 +++ b/tools/testing/selftests/bpf/config.aarch64 @@ -11,7 +11,6 @@ CONFIG_BLK_DEV_IO_TRACE=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_SD=y CONFIG_BONDING=y -CONFIG_BPFILTER=y CONFIG_BPF_JIT_ALWAYS_ON=y CONFIG_BPF_JIT_DEFAULT_ON=y CONFIG_BPF_PRELOAD_UMD=y diff --git a/tools/testing/selftests/bpf/config.s390x b/tools/testing/selftests/bpf/config.s390x index e93330382849..706931a8c2c6 100644 --- a/tools/testing/selftests/bpf/config.s390x +++ b/tools/testing/selftests/bpf/config.s390x @@ -9,7 +9,6 @@ CONFIG_BPF_JIT_ALWAYS_ON=y CONFIG_BPF_JIT_DEFAULT_ON=y CONFIG_BPF_PRELOAD=y CONFIG_BPF_PRELOAD_UMD=y -CONFIG_BPFILTER=y CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_FREEZER=y diff --git a/tools/testing/selftests/bpf/config.x86_64 b/tools/testing/selftests/bpf/config.x86_64 index b946088017f1..5680befae8c6 100644 --- a/tools/testing/selftests/bpf/config.x86_64 +++ b/tools/testing/selftests/bpf/config.x86_64 @@ -19,7 +19,6 @@ CONFIG_BOOTTIME_TRACING=y CONFIG_BPF_JIT_ALWAYS_ON=y CONFIG_BPF_PRELOAD=y CONFIG_BPF_PRELOAD_UMD=y -CONFIG_BPFILTER=y CONFIG_BSD_DISKLABEL=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_CFS_BANDWIDTH=y diff --git a/tools/testing/selftests/hid/config b/tools/testing/selftests/hid/config index 4f425178b56f..1758b055f295 100644 --- a/tools/testing/selftests/hid/config +++ b/tools/testing/selftests/hid/config @@ -1,5 +1,4 @@ CONFIG_BPF_EVENTS=y -CONFIG_BPFILTER=y CONFIG_BPF_JIT_ALWAYS_ON=y CONFIG_BPF_JIT=y CONFIG_BPF_KPROBE_OVERRIDE=y -- cgit From fe1eb24bd5ade085914248c527044e942f75e06a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 4 Jan 2024 16:04:35 -0800 Subject: Revert "Introduce PHY listing and link_topology tracking" This reverts commit 32bb4515e34469975abc936deb0a116c4a445817. This reverts commit d078d480639a4f3b5fc2d56247afa38e0956483a. This reverts commit fcc4b105caa4b844bf043375bf799c20a9c99db1. This reverts commit 345237dbc1bdbb274c9fb9ec38976261ff4a40b8. This reverts commit 7db69ec9cfb8b4ab50420262631fb2d1908b25bf. This reverts commit 95132a018f00f5dad38bdcfd4180d1af955d46f6. This reverts commit 63d5eaf35ac36cad00cfb3809d794ef0078c822b. This reverts commit c29451aefcb42359905d18678de38e52eccb3bb5. This reverts commit 2ab0edb505faa9ac90dee1732571390f074e8113. This reverts commit dedd702a35793ab462fce4c737eeba0badf9718e. This reverts commit 034fcc210349b873ece7356905be5c6ca11eef2a. This reverts commit 9c5625f559ad6fe9f6f733c11475bf470e637d34. This reverts commit 02018c544ef113e980a2349eba89003d6f399d22. Looks like we need more time for reviews, and incremental changes will be hard to make sense of. So revert. Link: https://lore.kernel.org/all/ZZP6FV5sXEf+xd58@shell.armlinux.org.uk/ Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/ethtool.yaml | 68 ------ Documentation/networking/ethtool-netlink.rst | 51 ----- Documentation/networking/index.rst | 1 - Documentation/networking/phy-link-topology.rst | 121 ---------- MAINTAINERS | 2 - drivers/net/phy/Makefile | 2 +- drivers/net/phy/at803x.c | 2 - drivers/net/phy/marvell-88x2222.c | 2 - drivers/net/phy/marvell.c | 2 - drivers/net/phy/marvell10g.c | 2 - drivers/net/phy/phy_device.c | 55 ----- drivers/net/phy/phy_link_topology.c | 66 ------ drivers/net/phy/phylink.c | 3 +- drivers/net/phy/sfp-bus.c | 15 +- include/linux/netdevice.h | 4 +- include/linux/phy.h | 6 - include/linux/phy_link_topology.h | 67 ------ include/linux/phy_link_topology_core.h | 19 -- include/linux/sfp.h | 8 +- include/uapi/linux/ethtool.h | 16 -- include/uapi/linux/ethtool_netlink.h | 30 --- net/core/dev.c | 3 - net/ethtool/Makefile | 2 +- net/ethtool/cabletest.c | 12 +- net/ethtool/netlink.c | 33 --- net/ethtool/netlink.h | 12 +- net/ethtool/phy.c | 306 ------------------------- net/ethtool/plca.c | 13 +- net/ethtool/pse-pd.c | 9 +- net/ethtool/strset.c | 15 +- 30 files changed, 35 insertions(+), 912 deletions(-) delete mode 100644 Documentation/networking/phy-link-topology.rst delete mode 100644 drivers/net/phy/phy_link_topology.c delete mode 100644 include/linux/phy_link_topology.h delete mode 100644 include/linux/phy_link_topology_core.h delete mode 100644 net/ethtool/phy.c (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 7f6fb1f61dd4..197208f419dc 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -16,11 +16,6 @@ definitions: name: stringset type: enum entries: [] - - - name: phy-upstream-type - enum-name: - type: enum - entries: [ mac, phy ] attribute-sets: - @@ -35,9 +30,6 @@ attribute-sets: - name: flags type: u32 - - - name: phy-index - type: u32 - name: bitset-bit @@ -950,45 +942,6 @@ attribute-sets: - name: burst-tmr type: u32 - - - name: phy-upstream - attributes: - - - name: index - type: u32 - - - name: sfp-name - type: string - - - name: phy - attributes: - - - name: header - type: nest - nested-attributes: header - - - name: index - type: u32 - - - name: drvname - type: string - - - name: name - type: string - - - name: upstream-type - type: u8 - enum: phy-upstream-type - - - name: upstream - type: nest - nested-attributes: phy-upstream - - - name: downstream-sfp-name - type: string - - - name: id - type: u32 operations: enum-model: directional @@ -1740,24 +1693,3 @@ operations: name: mm-ntf doc: Notification for change in MAC Merge configuration. notify: mm-get - - - name: phy-get - doc: Get PHY devices attached to an interface - - attribute-set: phy - - do: &phy-get-op - request: - attributes: - - header - reply: - attributes: - - header - - index - - drvname - - name - - upstream-type - - upstream - - downstream-sfp-name - - id - dump: *phy-get-op diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 97ff787a7dd8..d583d9abf2f8 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -57,7 +57,6 @@ Structure of this header is ``ETHTOOL_A_HEADER_DEV_INDEX`` u32 device ifindex ``ETHTOOL_A_HEADER_DEV_NAME`` string device name ``ETHTOOL_A_HEADER_FLAGS`` u32 flags common for all requests - ``ETHTOOL_A_HEADER_PHY_INDEX`` u32 phy device index ============================== ====== ============================= ``ETHTOOL_A_HEADER_DEV_INDEX`` and ``ETHTOOL_A_HEADER_DEV_NAME`` identify the @@ -82,12 +81,6 @@ the behaviour is backward compatible, i.e. requests from old clients not aware of the flag should be interpreted the way the client expects. A client must not set flags it does not understand. -``ETHTOOL_A_HEADER_PHY_INDEX`` identify the ethernet PHY the message relates to. -As there are numerous commands that are related to PHY configuration, and because -we can have more than one PHY on the link, the PHY index can be passed in the -request for the commands that needs it. It is however not mandatory, and if it -is not passed for commands that target a PHY, the net_device.phydev pointer -is used, as a fallback that keeps the legacy behaviour. Bit sets ======== @@ -2011,49 +2004,6 @@ The attributes are propagated to the driver through the following structure: .. kernel-doc:: include/linux/ethtool.h :identifiers: ethtool_mm_cfg -PHY_GET -======= - -Retrieve information about a given Ethernet PHY sitting on the link. As there -can be more than one PHY, the DUMP operation can be used to list the PHYs -present on a given interface, by passing an interface index or name in -the dump request - -Request contents: - - ==================================== ====== ========================== - ``ETHTOOL_A_PHY_HEADER`` nested request header - ==================================== ====== ========================== - -Kernel response contents: - - ===================================== ====== ========================== - ``ETHTOOL_A_PHY_HEADER`` nested request header - ``ETHTOOL_A_PHY_INDEX`` u32 the phy's unique index, that can - be used for phy-specific requests - ``ETHTOOL_A_PHY_DRVNAME`` string the phy driver name - ``ETHTOOL_A_PHY_NAME`` string the phy device name - ``ETHTOOL_A_PHY_UPSTREAM_TYPE`` u32 the type of device this phy is - connected to - ``ETHTOOL_A_PHY_UPSTREAM_PHY`` nested if the phy is connected to another - phy, this nest contains info on - that connection - ``ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME`` string if the phy controls an sfp bus, - the name of the sfp bus - ``ETHTOOL_A_PHY_ID`` u32 the phy id if the phy is C22 - ===================================== ====== ========================== - -When ``ETHTOOL_A_PHY_UPSTREAM_TYPE`` is PHY_UPSTREAM_PHY, the PHY's parent is -another PHY. Information on the parent PHY will be set in the -``ETHTOOL_A_PHY_UPSTREAM_PHY`` nest, which has the following structure : - - =================================== ====== ========================== - ``ETHTOOL_A_PHY_UPSTREAM_INDEX`` u32 the PHY index of the upstream PHY - ``ETHTOOL_A_PHY_UPSTREAM_SFP_NAME`` string if this PHY is connected to it's - parent PHY through an SFP bus, the - name of this sfp bus - =================================== ====== ========================== - Request translation =================== @@ -2160,5 +2110,4 @@ are netlink only. n/a ``ETHTOOL_MSG_PLCA_GET_STATUS`` n/a ``ETHTOOL_MSG_MM_GET`` n/a ``ETHTOOL_MSG_MM_SET`` - n/a ``ETHTOOL_MSG_PHY_GET`` =================================== ===================================== diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index a2c45a75a4a6..69f3d6dcd9fd 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -88,7 +88,6 @@ Contents: operstates packet_mmap phonet - phy-link-topology pktgen plip ppp_generic diff --git a/Documentation/networking/phy-link-topology.rst b/Documentation/networking/phy-link-topology.rst deleted file mode 100644 index 1fd8e904ef4b..000000000000 --- a/Documentation/networking/phy-link-topology.rst +++ /dev/null @@ -1,121 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 - -================= -PHY link topology -================= - -Overview -======== - -The PHY link topology representation in the networking stack aims at representing -the hardware layout for any given Ethernet link. - -An Ethernet Interface from userspace's point of view is nothing but a -:c:type:`struct net_device `, which exposes configuration options -through the legacy ioctls and the ethool netlink commands. The base assumption -when designing these configuration channels were that the link looked -something like this :: - - +-----------------------+ +----------+ +--------------+ - | Ethernet Controller / | | Ethernet | | Connector / | - | MAC | ------ | PHY | ---- | Port | ---... to LP - +-----------------------+ +----------+ +--------------+ - struct net_device struct phy_device - -Commands that needs to configure the PHY will go through the net_device.phydev -field to reach the PHY and perform the relevant configuration. - -This assumption falls apart in more complex topologies that can arise when, -for example, using SFP transceivers (although that's not the only specific case). - -Here, we have 2 basic scenarios. Either the MAC is able to output a serialized -interface, that can directly be fed to an SFP cage, such as SGMII, 1000BaseX, -10GBaseR, etc. - -The link topology then looks like this (when an SFP module is inserted) :: - - +-----+ SGMII +------------+ - | MAC | ------- | SFP Module | - +-----+ +------------+ - -Knowing that some modules embed a PHY, the actual link is more like :: - - +-----+ SGMII +--------------+ - | MAC | -------- | PHY (on SFP) | - +-----+ +--------------+ - -In this case, the SFP PHY is handled by phylib, and registered by phylink through -its SFP upstream ops. - -Now some Ethernet controllers aren't able to output a serialized interface, so -we can't directly connect them to an SFP cage. However, some PHYs can be used -as media-converters, to translate the non-serialized MAC MII interface to a -serialized MII interface fed to the SFP :: - - +-----+ RGMII +-----------------------+ SGMII +--------------+ - | MAC | ------- | PHY (media converter) | ------- | PHY (on SFP) | - +-----+ +-----------------------+ +--------------+ - -This is where the model of having a single net_device.phydev pointer shows its -limitations, as we now have 2 PHYs on the link. - -The phy_link topology framework aims at providing a way to keep track of every -PHY on the link, for use by both kernel drivers and subsystems, but also to -report the topology to userspace, allowing to target individual PHYs in configuration -commands. - -API -=== - -The :c:type:`struct phy_link_topology ` is a per-netdevice -resource, that gets initialized at netdevice creation. Once it's initialized, -it is then possible to register PHYs to the topology through : - -:c:func:`phy_link_topo_add_phy` - -Besides registering the PHY to the topology, this call will also assign a unique -index to the PHY, which can then be reported to userspace to refer to this PHY -(akin to the ifindex). This index is a u32, ranging from 1 to U32_MAX. The value -0 is reserved to indicate the PHY doesn't belong to any topology yet. - -The PHY can then be removed from the topology through - -:c:func:`phy_link_topo_del_phy` - -These function are already hooked into the phylib subsystem, so all PHYs that -are linked to a net_device through :c:func:`phy_attach_direct` will automatically -join the netdev's topology. - -PHYs that are on a SFP module will also be automatically registered IF the SFP -upstream is phylink (so, no media-converter). - -PHY drivers that can be used as SFP upstream need to call :c:func:`phy_sfp_attach_phy` -and :c:func:`phy_sfp_detach_phy`, which can be used as a -.attach_phy / .detach_phy implementation for the -:c:type:`struct sfp_upstream_ops `. - -UAPI -==== - -There exist a set of netlink commands to query the link topology from userspace, -see ``Documentation/networking/ethtool-netlink.rst``. - -The whole point of having a topology representation is to assign the phyindex -field in :c:type:`struct phy_device `. This index is reported to -userspace using the ``ETHTOOL_MSG_PHY_GET`` ethtnl command. Performing a DUMP operation -will result in all PHYs from all net_device being listed. The DUMP command -accepts either a ``ETHTOOL_A_HEADER_DEV_INDEX`` or ``ETHTOOL_A_HEADER_DEV_NAME`` -to be passed in the request to filter the DUMP to a single net_device. - -The retrieved index can then be passed as a request parameter using the -``ETHTOOL_A_HEADER_PHY_INDEX`` field in the following ethnl commands : - -* ``ETHTOOL_MSG_STRSET_GET`` to get the stats string set from a given PHY -* ``ETHTOOL_MSG_CABLE_TEST_ACT`` and ``ETHTOOL_MSG_CABLE_TEST_ACT``, to perform - cable testing on a given PHY on the link (most likely the outermost PHY) -* ``ETHTOOL_MSG_PSE_SET`` and ``ETHTOOL_MSG_PSE_GET`` for PHY-controlled PoE and PSE settings -* ``ETHTOOL_MSG_PLCA_GET_CFG``, ``ETHTOOL_MSG_PLCA_SET_CFG`` and ``ETHTOOL_MSG_PLCA_GET_STATUS`` - to set the PLCA (Physical Layer Collision Avoidance) parameters - -Note that the PHY index can be passed to other requests, which will silently -ignore it if present and irrelevant. diff --git a/MAINTAINERS b/MAINTAINERS index 79ac49b113dc..2b916990d7f0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7871,8 +7871,6 @@ F: include/linux/mii.h F: include/linux/of_net.h F: include/linux/phy.h F: include/linux/phy_fixed.h -F: include/linux/phy_link_topology.h -F: include/linux/phy_link_topology_core.h F: include/linux/phylib_stubs.h F: include/linux/platform_data/mdio-bcm-unimac.h F: include/linux/platform_data/mdio-gpio.h diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index f218954fd7a8..6097afd44392 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -2,7 +2,7 @@ # Makefile for Linux PHY drivers libphy-y := phy.o phy-c45.o phy-core.o phy_device.o \ - linkmode.o phy_link_topology.o + linkmode.o mdio-bus-y += mdio_bus.o mdio_device.o ifdef CONFIG_MDIO_DEVICE diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index aaf6c654aaed..19cfbf36fe80 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -1452,8 +1452,6 @@ static const struct sfp_upstream_ops at8031_sfp_ops = { .attach = phy_sfp_attach, .detach = phy_sfp_detach, .module_insert = at8031_sfp_insert, - .connect_phy = phy_sfp_connect_phy, - .disconnect_phy = phy_sfp_disconnect_phy, }; static int at8031_parse_dt(struct phy_device *phydev) diff --git a/drivers/net/phy/marvell-88x2222.c b/drivers/net/phy/marvell-88x2222.c index 3f77bbc7e04f..e3aa30dad2e6 100644 --- a/drivers/net/phy/marvell-88x2222.c +++ b/drivers/net/phy/marvell-88x2222.c @@ -555,8 +555,6 @@ static const struct sfp_upstream_ops sfp_phy_ops = { .link_down = mv2222_sfp_link_down, .attach = phy_sfp_attach, .detach = phy_sfp_detach, - .connect_phy = phy_sfp_connect_phy, - .disconnect_phy = phy_sfp_disconnect_phy, }; static int mv2222_probe(struct phy_device *phydev) diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 674e29bce2cc..eba652a4c1d8 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -3254,8 +3254,6 @@ static const struct sfp_upstream_ops m88e1510_sfp_ops = { .module_remove = m88e1510_sfp_remove, .attach = phy_sfp_attach, .detach = phy_sfp_detach, - .connect_phy = phy_sfp_connect_phy, - .disconnect_phy = phy_sfp_disconnect_phy, }; static int m88e1510_probe(struct phy_device *phydev) diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index 6642eb642d4b..ad43e280930c 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -503,8 +503,6 @@ static int mv3310_sfp_insert(void *upstream, const struct sfp_eeprom_id *id) static const struct sfp_upstream_ops mv3310_sfp_ops = { .attach = phy_sfp_attach, .detach = phy_sfp_detach, - .connect_phy = phy_sfp_connect_phy, - .disconnect_phy = phy_sfp_disconnect_phy, .module_insert = mv3310_sfp_insert, }; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 1e595762afea..3611ea64875e 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -29,7 +29,6 @@ #include #include #include -#include #include #include #include @@ -266,14 +265,6 @@ static void phy_mdio_device_remove(struct mdio_device *mdiodev) static struct phy_driver genphy_driver; -static struct phy_link_topology *phy_get_link_topology(struct phy_device *phydev) -{ - if (phydev->attached_dev) - return &phydev->attached_dev->link_topo; - - return NULL; -} - static LIST_HEAD(phy_fixup_list); static DEFINE_MUTEX(phy_fixup_lock); @@ -1363,46 +1354,6 @@ phy_standalone_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(phy_standalone); -/** - * phy_sfp_connect_phy - Connect the SFP module's PHY to the upstream PHY - * @upstream: pointer to the upstream phy device - * @phy: pointer to the SFP module's phy device - * - * This helper allows keeping track of PHY devices on the link. It adds the - * SFP module's phy to the phy namespace of the upstream phy - */ -int phy_sfp_connect_phy(void *upstream, struct phy_device *phy) -{ - struct phy_device *phydev = upstream; - struct phy_link_topology *topo = phy_get_link_topology(phydev); - - if (topo) - return phy_link_topo_add_phy(topo, phy, PHY_UPSTREAM_PHY, phydev); - - return 0; -} -EXPORT_SYMBOL(phy_sfp_connect_phy); - -/** - * phy_sfp_disconnect_phy - Disconnect the SFP module's PHY from the upstream PHY - * @upstream: pointer to the upstream phy device - * @phy: pointer to the SFP module's phy device - * - * This helper allows keeping track of PHY devices on the link. It removes the - * SFP module's phy to the phy namespace of the upstream phy. As the module phy - * will be destroyed, re-inserting the same module will add a new phy with a - * new index. - */ -void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy) -{ - struct phy_device *phydev = upstream; - struct phy_link_topology *topo = phy_get_link_topology(phydev); - - if (topo) - phy_link_topo_del_phy(topo, phy); -} -EXPORT_SYMBOL(phy_sfp_disconnect_phy); - /** * phy_sfp_attach - attach the SFP bus to the PHY upstream network device * @upstream: pointer to the phy device @@ -1540,11 +1491,6 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, if (phydev->sfp_bus_attached) dev->sfp_bus = phydev->sfp_bus; - - err = phy_link_topo_add_phy(&dev->link_topo, phydev, - PHY_UPSTREAM_MAC, dev); - if (err) - goto error; } /* Some Ethernet drivers try to connect to a PHY device before @@ -1874,7 +1820,6 @@ void phy_detach(struct phy_device *phydev) if (dev) { phydev->attached_dev->phydev = NULL; phydev->attached_dev = NULL; - phy_link_topo_del_phy(&dev->link_topo, phydev); } phydev->phylink = NULL; diff --git a/drivers/net/phy/phy_link_topology.c b/drivers/net/phy/phy_link_topology.c deleted file mode 100644 index 34e7e08fbfc3..000000000000 --- a/drivers/net/phy/phy_link_topology.c +++ /dev/null @@ -1,66 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * Infrastructure to handle all PHY devices connected to a given netdev, - * either directly or indirectly attached. - * - * Copyright (c) 2023 Maxime Chevallier - */ - -#include -#include -#include -#include -#include - -int phy_link_topo_add_phy(struct phy_link_topology *topo, - struct phy_device *phy, - enum phy_upstream upt, void *upstream) -{ - struct phy_device_node *pdn; - int ret; - - pdn = kzalloc(sizeof(*pdn), GFP_KERNEL); - if (!pdn) - return -ENOMEM; - - pdn->phy = phy; - switch (upt) { - case PHY_UPSTREAM_MAC: - pdn->upstream.netdev = (struct net_device *)upstream; - if (phy_on_sfp(phy)) - pdn->parent_sfp_bus = pdn->upstream.netdev->sfp_bus; - break; - case PHY_UPSTREAM_PHY: - pdn->upstream.phydev = (struct phy_device *)upstream; - if (phy_on_sfp(phy)) - pdn->parent_sfp_bus = pdn->upstream.phydev->sfp_bus; - break; - default: - ret = -EINVAL; - goto err; - } - pdn->upstream_type = upt; - - ret = xa_alloc_cyclic(&topo->phys, &phy->phyindex, pdn, xa_limit_32b, - &topo->next_phy_index, GFP_KERNEL); - if (ret) - goto err; - - return 0; - -err: - kfree(pdn); - return ret; -} -EXPORT_SYMBOL_GPL(phy_link_topo_add_phy); - -void phy_link_topo_del_phy(struct phy_link_topology *topo, - struct phy_device *phy) -{ - struct phy_device_node *pdn = xa_erase(&topo->phys, phy->phyindex); - - phy->phyindex = 0; - - kfree(pdn); -} -EXPORT_SYMBOL_GPL(phy_link_topo_del_phy); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index a816391add12..ed0b4ccaa6a6 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -3385,8 +3385,7 @@ static int phylink_sfp_connect_phy(void *upstream, struct phy_device *phy) return ret; } -static void phylink_sfp_disconnect_phy(void *upstream, - struct phy_device *phydev) +static void phylink_sfp_disconnect_phy(void *upstream) { phylink_disconnect_phy(upstream); } diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index fb1c102714b5..6fa679b36290 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -486,7 +486,7 @@ static void sfp_unregister_bus(struct sfp_bus *bus) bus->socket_ops->stop(bus->sfp); bus->socket_ops->detach(bus->sfp); if (bus->phydev && ops && ops->disconnect_phy) - ops->disconnect_phy(bus->upstream, bus->phydev); + ops->disconnect_phy(bus->upstream); } bus->registered = false; } @@ -742,7 +742,7 @@ void sfp_remove_phy(struct sfp_bus *bus) const struct sfp_upstream_ops *ops = sfp_get_upstream_ops(bus); if (ops && ops->disconnect_phy) - ops->disconnect_phy(bus->upstream, bus->phydev); + ops->disconnect_phy(bus->upstream); bus->phydev = NULL; } EXPORT_SYMBOL_GPL(sfp_remove_phy); @@ -859,14 +859,3 @@ void sfp_unregister_socket(struct sfp_bus *bus) sfp_bus_put(bus); } EXPORT_SYMBOL_GPL(sfp_unregister_socket); - -const char *sfp_get_name(struct sfp_bus *bus) -{ - ASSERT_RTNL(); - - if (bus->sfp_dev) - return dev_name(bus->sfp_dev); - - return NULL; -} -EXPORT_SYMBOL_GPL(sfp_get_name); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e265aa1f2169..118c40258d07 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -40,6 +40,7 @@ #include #endif #include + #include #include #include @@ -51,7 +52,6 @@ #include #include #include -#include struct netpoll_info; struct device; @@ -2047,7 +2047,6 @@ enum netdev_stat_type { * @fcoe_ddp_xid: Max exchange id for FCoE LRO by ddp * * @priomap: XXX: need comments on this one - * @link_topo: Physical link topology tracking attached PHYs * @phydev: Physical device may attach itself * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. @@ -2442,7 +2441,6 @@ struct net_device { #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map __rcu *priomap; #endif - struct phy_link_topology link_topo; struct phy_device *phydev; struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; diff --git a/include/linux/phy.h b/include/linux/phy.h index 6cb9d843aee9..e9e85d347587 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -544,9 +544,6 @@ struct macsec_ops; * @drv: Pointer to the driver for this PHY instance * @devlink: Create a link between phy dev and mac dev, if the external phy * used by current mac interface is managed by another mac interface. - * @phyindex: Unique id across the phy's parent tree of phys to address the PHY - * from userspace, similar to ifindex. A zero index means the PHY - * wasn't assigned an id yet. * @phy_id: UID for this device found during discovery * @c45_ids: 802.3-c45 Device Identifiers if is_c45. * @is_c45: Set to true if this PHY uses clause 45 addressing. @@ -646,7 +643,6 @@ struct phy_device { struct device_link *devlink; - u32 phyindex; u32 phy_id; struct phy_c45_device_ids c45_ids; @@ -1726,8 +1722,6 @@ int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); int __phy_resume(struct phy_device *phydev); int phy_loopback(struct phy_device *phydev, bool enable); -int phy_sfp_connect_phy(void *upstream, struct phy_device *phy); -void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy); void phy_sfp_attach(void *upstream, struct sfp_bus *bus); void phy_sfp_detach(void *upstream, struct sfp_bus *bus); int phy_sfp_probe(struct phy_device *phydev, diff --git a/include/linux/phy_link_topology.h b/include/linux/phy_link_topology.h deleted file mode 100644 index 91902263ec0e..000000000000 --- a/include/linux/phy_link_topology.h +++ /dev/null @@ -1,67 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * PHY device list allow maintaining a list of PHY devices that are - * part of a netdevice's link topology. PHYs can for example be chained, - * as is the case when using a PHY that exposes an SFP module, on which an - * SFP transceiver that embeds a PHY is connected. - * - * This list can then be used by userspace to leverage individual PHY - * capabilities. - */ -#ifndef __PHY_LINK_TOPOLOGY_H -#define __PHY_LINK_TOPOLOGY_H - -#include -#include - -struct xarray; -struct phy_device; -struct net_device; -struct sfp_bus; - -struct phy_device_node { - enum phy_upstream upstream_type; - - union { - struct net_device *netdev; - struct phy_device *phydev; - } upstream; - - struct sfp_bus *parent_sfp_bus; - - struct phy_device *phy; -}; - -static inline struct phy_device * -phy_link_topo_get_phy(struct phy_link_topology *topo, u32 phyindex) -{ - struct phy_device_node *pdn = xa_load(&topo->phys, phyindex); - - if (pdn) - return pdn->phy; - - return NULL; -} - -#if IS_ENABLED(CONFIG_PHYLIB) -int phy_link_topo_add_phy(struct phy_link_topology *topo, - struct phy_device *phy, - enum phy_upstream upt, void *upstream); - -void phy_link_topo_del_phy(struct phy_link_topology *lt, struct phy_device *phy); - -#else -static inline int phy_link_topo_add_phy(struct phy_link_topology *topo, - struct phy_device *phy, - enum phy_upstream upt, void *upstream) -{ - return 0; -} - -static inline void phy_link_topo_del_phy(struct phy_link_topology *topo, - struct phy_device *phy) -{ -} -#endif - -#endif /* __PHY_LINK_TOPOLOGY_H */ diff --git a/include/linux/phy_link_topology_core.h b/include/linux/phy_link_topology_core.h deleted file mode 100644 index 78c75f909489..000000000000 --- a/include/linux/phy_link_topology_core.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PHY_LINK_TOPOLOGY_CORE_H -#define __PHY_LINK_TOPOLOGY_CORE_H - -struct xarray; - -struct phy_link_topology { - struct xarray phys; - - u32 next_phy_index; -}; - -static inline void phy_link_topo_init(struct phy_link_topology *topo) -{ - xa_init_flags(&topo->phys, XA_FLAGS_ALLOC1); - topo->next_phy_index = 1; -} - -#endif /* __PHY_LINK_TOPOLOGY_CORE_H */ diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 55c0ab17c9e2..9346cd44814d 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -544,7 +544,7 @@ struct sfp_upstream_ops { void (*link_down)(void *priv); void (*link_up)(void *priv); int (*connect_phy)(void *priv, struct phy_device *); - void (*disconnect_phy)(void *priv, struct phy_device *); + void (*disconnect_phy)(void *priv); }; #if IS_ENABLED(CONFIG_SFP) @@ -570,7 +570,6 @@ struct sfp_bus *sfp_bus_find_fwnode(const struct fwnode_handle *fwnode); int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, const struct sfp_upstream_ops *ops); void sfp_bus_del_upstream(struct sfp_bus *bus); -const char *sfp_get_name(struct sfp_bus *bus); #else static inline int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, @@ -649,11 +648,6 @@ static inline int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, static inline void sfp_bus_del_upstream(struct sfp_bus *bus) { } - -static inline const char *sfp_get_name(struct sfp_bus *bus) -{ - return NULL; -} #endif #endif diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 01ba529dbb6d..06ef6b78b7de 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2220,20 +2220,4 @@ struct ethtool_link_settings { * __u32 map_lp_advertising[link_mode_masks_nwords]; */ }; - -/** - * enum phy_upstream - Represents the upstream component a given PHY device - * is connected to, as in what is on the other end of the MII bus. Most PHYs - * will be attached to an Ethernet MAC controller, but in some cases, there's - * an intermediate PHY used as a media-converter, which will driver another - * MII interface as its output. - * @PHY_UPSTREAM_MAC: Upstream component is a MAC (a switch port, - * or ethernet controller) - * @PHY_UPSTREAM_PHY: Upstream component is a PHY (likely a media converter) - */ -enum phy_upstream { - PHY_UPSTREAM_MAC, - PHY_UPSTREAM_PHY, -}; - #endif /* _UAPI_LINUX_ETHTOOL_H */ diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 00cd7ad16709..3f89074aa06c 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -57,7 +57,6 @@ enum { ETHTOOL_MSG_PLCA_GET_STATUS, ETHTOOL_MSG_MM_GET, ETHTOOL_MSG_MM_SET, - ETHTOOL_MSG_PHY_GET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -110,8 +109,6 @@ enum { ETHTOOL_MSG_PLCA_NTF, ETHTOOL_MSG_MM_GET_REPLY, ETHTOOL_MSG_MM_NTF, - ETHTOOL_MSG_PHY_GET_REPLY, - ETHTOOL_MSG_PHY_NTF, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -136,7 +133,6 @@ enum { ETHTOOL_A_HEADER_DEV_INDEX, /* u32 */ ETHTOOL_A_HEADER_DEV_NAME, /* string */ ETHTOOL_A_HEADER_FLAGS, /* u32 - ETHTOOL_FLAG_* */ - ETHTOOL_A_HEADER_PHY_INDEX, /* u32 */ /* add new constants above here */ __ETHTOOL_A_HEADER_CNT, @@ -980,32 +976,6 @@ enum { ETHTOOL_A_MM_MAX = (__ETHTOOL_A_MM_CNT - 1) }; -enum { - ETHTOOL_A_PHY_UPSTREAM_UNSPEC, - ETHTOOL_A_PHY_UPSTREAM_INDEX, /* u32 */ - ETHTOOL_A_PHY_UPSTREAM_SFP_NAME, /* string */ - - /* add new constants above here */ - __ETHTOOL_A_PHY_UPSTREAM_CNT, - ETHTOOL_A_PHY_UPSTREAM_MAX = (__ETHTOOL_A_PHY_UPSTREAM_CNT - 1) -}; - -enum { - ETHTOOL_A_PHY_UNSPEC, - ETHTOOL_A_PHY_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_PHY_INDEX, /* u32 */ - ETHTOOL_A_PHY_DRVNAME, /* string */ - ETHTOOL_A_PHY_NAME, /* string */ - ETHTOOL_A_PHY_UPSTREAM_TYPE, /* u8 */ - ETHTOOL_A_PHY_UPSTREAM, /* nest - _A_PHY_UPSTREAM_* */ - ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME, /* string */ - ETHTOOL_A_PHY_ID, /* u32 */ - - /* add new constants above here */ - __ETHTOOL_A_PHY_CNT, - ETHTOOL_A_PHY_MAX = (__ETHTOOL_A_PHY_CNT - 1) -}; - /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 diff --git a/net/core/dev.c b/net/core/dev.c index bc4ac49d4643..f01a9b858347 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -153,7 +153,6 @@ #include #include #include -#include #include "dev.h" #include "net-sysfs.h" @@ -10876,8 +10875,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, #ifdef CONFIG_NET_SCHED hash_init(dev->qdisc_hash); #endif - phy_link_topo_init(&dev->link_topo); - dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 0ccd0e9afd3f..504f954a1b28 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -8,4 +8,4 @@ ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ tunnels.o fec.o eeprom.o stats.o phc_vclocks.o mm.o \ - module.o pse-pd.o plca.o mm.o phy.o + module.o pse-pd.o plca.o mm.o diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c index 6b00d0800f23..06a151165c31 100644 --- a/net/ethtool/cabletest.c +++ b/net/ethtool/cabletest.c @@ -69,7 +69,7 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info) return ret; dev = req_info.dev; - if (!req_info.phydev) { + if (!dev->phydev) { ret = -EOPNOTSUPP; goto out_dev_put; } @@ -85,12 +85,12 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info) if (ret < 0) goto out_rtnl; - ret = ops->start_cable_test(req_info.phydev, info->extack); + ret = ops->start_cable_test(dev->phydev, info->extack); ethnl_ops_complete(dev); if (!ret) - ethnl_cable_test_started(req_info.phydev, + ethnl_cable_test_started(dev->phydev, ETHTOOL_MSG_CABLE_TEST_NTF); out_rtnl: @@ -321,7 +321,7 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) return ret; dev = req_info.dev; - if (!req_info.phydev) { + if (!dev->phydev) { ret = -EOPNOTSUPP; goto out_dev_put; } @@ -342,12 +342,12 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) if (ret < 0) goto out_rtnl; - ret = ops->start_cable_test_tdr(req_info.phydev, info->extack, &cfg); + ret = ops->start_cable_test_tdr(dev->phydev, info->extack, &cfg); ethnl_ops_complete(dev); if (!ret) - ethnl_cable_test_started(req_info.phydev, + ethnl_cable_test_started(dev->phydev, ETHTOOL_MSG_CABLE_TEST_TDR_NTF); out_rtnl: diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 92b0dd8ca046..fe3553f60bf3 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -4,7 +4,6 @@ #include #include #include "netlink.h" -#include static struct genl_family ethtool_genl_family; @@ -21,7 +20,6 @@ const struct nla_policy ethnl_header_policy[] = { .len = ALTIFNAMSIZ - 1 }, [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, ETHTOOL_FLAGS_BASIC), - [ETHTOOL_A_HEADER_PHY_INDEX] = NLA_POLICY_MIN(NLA_U32, 1), }; const struct nla_policy ethnl_header_policy_stats[] = { @@ -30,7 +28,6 @@ const struct nla_policy ethnl_header_policy_stats[] = { .len = ALTIFNAMSIZ - 1 }, [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, ETHTOOL_FLAGS_STATS), - [ETHTOOL_A_HEADER_PHY_INDEX] = NLA_POLICY_MIN(NLA_U32, 1), }; int ethnl_ops_begin(struct net_device *dev) @@ -94,7 +91,6 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, { struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy)]; const struct nlattr *devname_attr; - struct phy_device *phydev = NULL; struct net_device *dev = NULL; u32 flags = 0; int ret; @@ -149,26 +145,6 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, return -EINVAL; } - if (dev) { - if (tb[ETHTOOL_A_HEADER_PHY_INDEX]) { - u32 phy_index = nla_get_u32(tb[ETHTOOL_A_HEADER_PHY_INDEX]); - - phydev = phy_link_topo_get_phy(&dev->link_topo, - phy_index); - if (!phydev) { - NL_SET_ERR_MSG_ATTR(extack, header, - "no phy matches phy index"); - return -EINVAL; - } - } else { - /* If we need a PHY but no phy index is specified, fallback - * to dev->phydev - */ - phydev = dev->phydev; - } - } - - req_info->phydev = phydev; req_info->dev = dev; req_info->flags = flags; return 0; @@ -1153,15 +1129,6 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_mm_set_policy, .maxattr = ARRAY_SIZE(ethnl_mm_set_policy) - 1, }, - { - .cmd = ETHTOOL_MSG_PHY_GET, - .doit = ethnl_phy_doit, - .start = ethnl_phy_start, - .dumpit = ethnl_phy_dumpit, - .done = ethnl_phy_done, - .policy = ethnl_phy_get_policy, - .maxattr = ARRAY_SIZE(ethnl_phy_get_policy) - 1, - }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 5e6a43e35a09..9a333a8d04c1 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -250,7 +250,6 @@ static inline unsigned int ethnl_reply_header_size(void) * @dev: network device the request is for (may be null) * @dev_tracker: refcount tracker for @dev reference * @flags: request flags common for all request types - * @phydev: phy_device connected to @dev this request is for (may be null) * * This is a common base for request specific structures holding data from * parsed userspace request. These always embed struct ethnl_req_info at @@ -260,7 +259,6 @@ struct ethnl_req_info { struct net_device *dev; netdevice_tracker dev_tracker; u32 flags; - struct phy_device *phydev; }; static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info) @@ -397,10 +395,9 @@ extern const struct ethnl_request_ops ethnl_rss_request_ops; extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops; extern const struct ethnl_request_ops ethnl_plca_status_request_ops; extern const struct ethnl_request_ops ethnl_mm_request_ops; -extern const struct ethnl_request_ops ethnl_phy_request_ops; -extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_PHY_INDEX + 1]; -extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_PHY_INDEX + 1]; +extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; +extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_strset_get_policy[ETHTOOL_A_STRSET_COUNTS_ONLY + 1]; extern const struct nla_policy ethnl_linkinfo_get_policy[ETHTOOL_A_LINKINFO_HEADER + 1]; extern const struct nla_policy ethnl_linkinfo_set_policy[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL + 1]; @@ -444,7 +441,6 @@ extern const struct nla_policy ethnl_plca_set_cfg_policy[ETHTOOL_A_PLCA_MAX + 1] extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADER + 1]; extern const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1]; extern const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1]; -extern const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1]; int ethnl_set_features(struct sk_buff *skb, struct genl_info *info); int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info); @@ -452,10 +448,6 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info); int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info); int ethnl_tunnel_info_start(struct netlink_callback *cb); int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb); -int ethnl_phy_start(struct netlink_callback *cb); -int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info); -int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb); -int ethnl_phy_done(struct netlink_callback *cb); extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN]; diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c deleted file mode 100644 index 5add2840aaeb..000000000000 --- a/net/ethtool/phy.c +++ /dev/null @@ -1,306 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright 2023 Bootlin - * - */ -#include "common.h" -#include "netlink.h" - -#include -#include -#include - -struct phy_req_info { - struct ethnl_req_info base; - struct phy_device_node pdn; -}; - -#define PHY_REQINFO(__req_base) \ - container_of(__req_base, struct phy_req_info, base) - -const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1] = { - [ETHTOOL_A_PHY_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), -}; - -/* Caller holds rtnl */ -static ssize_t -ethnl_phy_reply_size(const struct ethnl_req_info *req_base, - struct netlink_ext_ack *extack) -{ - struct phy_link_topology *topo; - struct phy_device_node *pdn; - struct phy_device *phydev; - unsigned long index; - size_t size; - - ASSERT_RTNL(); - - topo = &req_base->dev->link_topo; - - size = nla_total_size(0); - - xa_for_each(&topo->phys, index, pdn) { - phydev = pdn->phy; - - /* ETHTOOL_A_PHY_INDEX */ - size += nla_total_size(sizeof(u32)); - - /* ETHTOOL_A_DRVNAME */ - size += nla_total_size(strlen(phydev->drv->name) + 1); - - /* ETHTOOL_A_NAME */ - size += nla_total_size(strlen(dev_name(&phydev->mdio.dev)) + 1); - - /* ETHTOOL_A_PHY_UPSTREAM_TYPE */ - size += nla_total_size(sizeof(u8)); - - /* ETHTOOL_A_PHY_ID */ - size += nla_total_size(sizeof(u32)); - - if (phy_on_sfp(phydev)) { - const char *upstream_sfp_name = sfp_get_name(pdn->parent_sfp_bus); - - /* ETHTOOL_A_PHY_UPSTREAM_SFP_NAME */ - if (upstream_sfp_name) - size += nla_total_size(strlen(upstream_sfp_name) + 1); - - /* ETHTOOL_A_PHY_UPSTREAM_INDEX */ - size += nla_total_size(sizeof(u32)); - } - - /* ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME */ - if (phydev->sfp_bus) { - const char *sfp_name = sfp_get_name(phydev->sfp_bus); - - if (sfp_name) - size += nla_total_size(strlen(sfp_name) + 1); - } - } - - return size; -} - -static int -ethnl_phy_fill_reply(const struct ethnl_req_info *req_base, struct sk_buff *skb) -{ - struct phy_req_info *req_info = PHY_REQINFO(req_base); - struct phy_device_node *pdn = &req_info->pdn; - struct phy_device *phydev = pdn->phy; - enum phy_upstream ptype; - struct nlattr *nest; - - ptype = pdn->upstream_type; - - if (nla_put_u32(skb, ETHTOOL_A_PHY_INDEX, phydev->phyindex) || - nla_put_string(skb, ETHTOOL_A_PHY_DRVNAME, phydev->drv->name) || - nla_put_string(skb, ETHTOOL_A_PHY_NAME, dev_name(&phydev->mdio.dev)) || - nla_put_u8(skb, ETHTOOL_A_PHY_UPSTREAM_TYPE, ptype) || - nla_put_u32(skb, ETHTOOL_A_PHY_ID, phydev->phy_id)) - return -EMSGSIZE; - - if (ptype == PHY_UPSTREAM_PHY) { - struct phy_device *upstream = pdn->upstream.phydev; - const char *sfp_upstream_name; - - nest = nla_nest_start(skb, ETHTOOL_A_PHY_UPSTREAM); - if (!nest) - return -EMSGSIZE; - - /* Parent index */ - if (nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_INDEX, upstream->phyindex)) - return -EMSGSIZE; - - if (pdn->parent_sfp_bus) { - sfp_upstream_name = sfp_get_name(pdn->parent_sfp_bus); - if (sfp_upstream_name && nla_put_string(skb, - ETHTOOL_A_PHY_UPSTREAM_SFP_NAME, - sfp_upstream_name)) - return -EMSGSIZE; - } - - nla_nest_end(skb, nest); - } - - if (phydev->sfp_bus) { - const char *sfp_name = sfp_get_name(phydev->sfp_bus); - - if (sfp_name && - nla_put_string(skb, ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME, - sfp_name)) - return -EMSGSIZE; - } - - return 0; -} - -static int ethnl_phy_parse_request(struct ethnl_req_info *req_base, - struct nlattr **tb) -{ - struct phy_link_topology *topo = &req_base->dev->link_topo; - struct phy_req_info *req_info = PHY_REQINFO(req_base); - struct phy_device_node *pdn; - - if (!req_base->phydev) - return 0; - - pdn = xa_load(&topo->phys, req_base->phydev->phyindex); - memcpy(&req_info->pdn, pdn, sizeof(*pdn)); - - return 0; -} - -int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info) -{ - struct phy_req_info req_info = {}; - struct nlattr **tb = info->attrs; - struct sk_buff *rskb; - void *reply_payload; - int reply_len; - int ret; - - ret = ethnl_parse_header_dev_get(&req_info.base, - tb[ETHTOOL_A_PHY_HEADER], - genl_info_net(info), info->extack, - true); - if (ret < 0) - return ret; - - rtnl_lock(); - - ret = ethnl_phy_parse_request(&req_info.base, tb); - if (ret < 0) - goto err_unlock_rtnl; - - /* No PHY, return early */ - if (!req_info.pdn.phy) - goto err_unlock_rtnl; - - ret = ethnl_phy_reply_size(&req_info.base, info->extack); - if (ret < 0) - goto err_unlock_rtnl; - reply_len = ret + ethnl_reply_header_size(); - - rskb = ethnl_reply_init(reply_len, req_info.base.dev, - ETHTOOL_MSG_PHY_GET_REPLY, - ETHTOOL_A_PHY_HEADER, - info, &reply_payload); - if (!rskb) { - ret = -ENOMEM; - goto err_unlock_rtnl; - } - - ret = ethnl_phy_fill_reply(&req_info.base, rskb); - if (ret) - goto err_free_msg; - - rtnl_unlock(); - ethnl_parse_header_dev_put(&req_info.base); - genlmsg_end(rskb, reply_payload); - - return genlmsg_reply(rskb, info); - -err_free_msg: - nlmsg_free(rskb); -err_unlock_rtnl: - rtnl_unlock(); - ethnl_parse_header_dev_put(&req_info.base); - return ret; -} - -struct ethnl_phy_dump_ctx { - struct phy_req_info *phy_req_info; -}; - -int ethnl_phy_start(struct netlink_callback *cb) -{ - const struct genl_dumpit_info *info = genl_dumpit_info(cb); - struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; - struct nlattr **tb = info->info.attrs; - int ret; - - BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); - - ctx->phy_req_info = kzalloc(sizeof(*ctx->phy_req_info), GFP_KERNEL); - if (!ctx->phy_req_info) - return -ENOMEM; - - ret = ethnl_parse_header_dev_get(&ctx->phy_req_info->base, - tb[ETHTOOL_A_PHY_HEADER], - sock_net(cb->skb->sk), cb->extack, - false); - return ret; -} - -int ethnl_phy_done(struct netlink_callback *cb) -{ - struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; - - kfree(ctx->phy_req_info); - - return 0; -} - -static int ethnl_phy_dump_one_dev(struct sk_buff *skb, struct net_device *dev, - struct netlink_callback *cb) -{ - struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; - struct phy_req_info *pri = ctx->phy_req_info; - struct phy_device_node *pdn; - unsigned long index = 1; - int ret = 0; - void *ehdr; - - pri->base.dev = dev; - - xa_for_each(&dev->link_topo.phys, index, pdn) { - ehdr = ethnl_dump_put(skb, cb, - ETHTOOL_MSG_PHY_GET_REPLY); - if (!ehdr) { - ret = -EMSGSIZE; - break; - } - - ret = ethnl_fill_reply_header(skb, dev, - ETHTOOL_A_PHY_HEADER); - if (ret < 0) { - genlmsg_cancel(skb, ehdr); - break; - } - - memcpy(&pri->pdn, pdn, sizeof(*pdn)); - ret = ethnl_phy_fill_reply(&pri->base, skb); - - genlmsg_end(skb, ehdr); - } - - return ret; -} - -int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb) -{ - struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; - struct net *net = sock_net(skb->sk); - unsigned long ifindex = 1; - struct net_device *dev; - int ret = 0; - - rtnl_lock(); - - if (ctx->phy_req_info->base.dev) { - ret = ethnl_phy_dump_one_dev(skb, ctx->phy_req_info->base.dev, cb); - ethnl_parse_header_dev_put(&ctx->phy_req_info->base); - ctx->phy_req_info->base.dev = NULL; - } else { - for_each_netdev_dump(net, dev, ifindex) { - ret = ethnl_phy_dump_one_dev(skb, dev, cb); - if (ret) - break; - } - } - rtnl_unlock(); - - if (ret == -EMSGSIZE && skb->len) - return skb->len; - return ret; -} - diff --git a/net/ethtool/plca.c b/net/ethtool/plca.c index 2b3e419f4dc2..b1e2e3b5027f 100644 --- a/net/ethtool/plca.c +++ b/net/ethtool/plca.c @@ -61,7 +61,7 @@ static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base, int ret; // check that the PHY device is available and connected - if (!req_base->phydev) { + if (!dev->phydev) { ret = -EOPNOTSUPP; goto out; } @@ -80,7 +80,7 @@ static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base, memset(&data->plca_cfg, 0xff, sizeof_field(struct plca_reply_data, plca_cfg)); - ret = ops->get_plca_cfg(req_base->phydev, &data->plca_cfg); + ret = ops->get_plca_cfg(dev->phydev, &data->plca_cfg); ethnl_ops_complete(dev); out: @@ -141,6 +141,7 @@ const struct nla_policy ethnl_plca_set_cfg_policy[] = { static int ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info) { + struct net_device *dev = req_info->dev; const struct ethtool_phy_ops *ops; struct nlattr **tb = info->attrs; struct phy_plca_cfg plca_cfg; @@ -148,7 +149,7 @@ ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info) int ret; // check that the PHY device is available and connected - if (!req_info->phydev) + if (!dev->phydev) return -EOPNOTSUPP; ops = ethtool_phy_ops; @@ -167,7 +168,7 @@ ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info) if (!mod) return 0; - ret = ops->set_plca_cfg(req_info->phydev, &plca_cfg, info->extack); + ret = ops->set_plca_cfg(dev->phydev, &plca_cfg, info->extack); return ret < 0 ? ret : 1; } @@ -203,7 +204,7 @@ static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base, int ret; // check that the PHY device is available and connected - if (!req_base->phydev) { + if (!dev->phydev) { ret = -EOPNOTSUPP; goto out; } @@ -222,7 +223,7 @@ static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base, memset(&data->plca_st, 0xff, sizeof_field(struct plca_reply_data, plca_st)); - ret = ops->get_plca_status(req_base->phydev, &data->plca_st); + ret = ops->get_plca_status(dev->phydev, &data->plca_st); ethnl_ops_complete(dev); out: return ret; diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c index 4a1c8d37bd3d..cc478af77111 100644 --- a/net/ethtool/pse-pd.c +++ b/net/ethtool/pse-pd.c @@ -31,10 +31,12 @@ const struct nla_policy ethnl_pse_get_policy[ETHTOOL_A_PSE_HEADER + 1] = { [ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; -static int pse_get_pse_attributes(struct phy_device *phydev, +static int pse_get_pse_attributes(struct net_device *dev, struct netlink_ext_ack *extack, struct pse_reply_data *data) { + struct phy_device *phydev = dev->phydev; + if (!phydev) { NL_SET_ERR_MSG(extack, "No PHY is attached"); return -EOPNOTSUPP; @@ -62,7 +64,7 @@ static int pse_prepare_data(const struct ethnl_req_info *req_base, if (ret < 0) return ret; - ret = pse_get_pse_attributes(req_base->phydev, info->extack, data); + ret = pse_get_pse_attributes(dev, info->extack, data); ethnl_ops_complete(dev); @@ -122,6 +124,7 @@ ethnl_set_pse_validate(struct ethnl_req_info *req_info, struct genl_info *info) static int ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info) { + struct net_device *dev = req_info->dev; struct pse_control_config config = {}; struct nlattr **tb = info->attrs; struct phy_device *phydev; @@ -129,7 +132,7 @@ ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info) /* this values are already validated by the ethnl_pse_set_policy */ config.admin_cotrol = nla_get_u32(tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]); - phydev = req_info->phydev; + phydev = dev->phydev; if (!phydev) { NL_SET_ERR_MSG(info->extack, "No PHY is attached"); return -EOPNOTSUPP; diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c index 70c00631c51f..c678b484a079 100644 --- a/net/ethtool/strset.c +++ b/net/ethtool/strset.c @@ -233,18 +233,17 @@ static void strset_cleanup_data(struct ethnl_reply_data *reply_base) } static int strset_prepare_set(struct strset_info *info, struct net_device *dev, - struct phy_device *phydev, unsigned int id, - bool counts_only) + unsigned int id, bool counts_only) { const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops; const struct ethtool_ops *ops = dev->ethtool_ops; void *strings; int count, ret; - if (id == ETH_SS_PHY_STATS && phydev && + if (id == ETH_SS_PHY_STATS && dev->phydev && !ops->get_ethtool_phy_stats && phy_ops && phy_ops->get_sset_count) - ret = phy_ops->get_sset_count(phydev); + ret = phy_ops->get_sset_count(dev->phydev); else if (ops->get_sset_count && ops->get_strings) ret = ops->get_sset_count(dev, id); else @@ -259,10 +258,10 @@ static int strset_prepare_set(struct strset_info *info, struct net_device *dev, strings = kcalloc(count, ETH_GSTRING_LEN, GFP_KERNEL); if (!strings) return -ENOMEM; - if (id == ETH_SS_PHY_STATS && phydev && + if (id == ETH_SS_PHY_STATS && dev->phydev && !ops->get_ethtool_phy_stats && phy_ops && phy_ops->get_strings) - phy_ops->get_strings(phydev, strings); + phy_ops->get_strings(dev->phydev, strings); else ops->get_strings(dev, id, strings); info->strings = strings; @@ -306,8 +305,8 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base, !data->sets[i].per_dev) continue; - ret = strset_prepare_set(&data->sets[i], dev, req_base->phydev, - i, req_info->counts_only); + ret = strset_prepare_set(&data->sets[i], dev, i, + req_info->counts_only); if (ret < 0) goto err_ops; } -- cgit From 8a6286c1804e2c7144aef3154a0357c4b496e10b Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 3 Jan 2024 14:28:36 +0100 Subject: dpll: expose fractional frequency offset value to user Add a new netlink attribute to expose fractional frequency offset value for a pin. Add an op to get the value from the driver. Signed-off-by: Jiri Pirko Acked-by: Vadim Fedorenko Acked-by: Arkadiusz Kubalewski Link: https://lore.kernel.org/r/20240103132838.1501801-2-jiri@resnulli.us Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/dpll.yaml | 11 +++++++++++ drivers/dpll/dpll_netlink.c | 24 ++++++++++++++++++++++++ include/linux/dpll.h | 3 +++ include/uapi/linux/dpll.h | 1 + 4 files changed, 39 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index cf8abe1c0550..b14aed18065f 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -296,6 +296,16 @@ attribute-sets: - name: phase-offset type: s64 + - + name: fractional-frequency-offset + type: sint + doc: | + The FFO (Fractional Frequency Offset) between the RX and TX + symbol rate on the media associated with the pin: + (rx_frequency-tx_frequency)/rx_frequency + Value is in PPM (parts per million). + This may be implemented for example for pin of type + PIN_TYPE_SYNCE_ETH_PORT. - name: pin-parent-device subset-of: pin @@ -460,6 +470,7 @@ operations: - phase-adjust-min - phase-adjust-max - phase-adjust + - fractional-frequency-offset dump: pre: dpll-lock-dumpit diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index 21c627e9401a..3370dbddb86b 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -263,6 +263,27 @@ dpll_msg_add_phase_offset(struct sk_buff *msg, struct dpll_pin *pin, return 0; } +static int dpll_msg_add_ffo(struct sk_buff *msg, struct dpll_pin *pin, + struct dpll_pin_ref *ref, + struct netlink_ext_ack *extack) +{ + const struct dpll_pin_ops *ops = dpll_pin_ops(ref); + struct dpll_device *dpll = ref->dpll; + s64 ffo; + int ret; + + if (!ops->ffo_get) + return 0; + ret = ops->ffo_get(pin, dpll_pin_on_dpll_priv(dpll, pin), + dpll, dpll_priv(dpll), &ffo, extack); + if (ret) { + if (ret == -ENODATA) + return 0; + return ret; + } + return nla_put_sint(msg, DPLL_A_PIN_FRACTIONAL_FREQUENCY_OFFSET, ffo); +} + static int dpll_msg_add_pin_freq(struct sk_buff *msg, struct dpll_pin *pin, struct dpll_pin_ref *ref, struct netlink_ext_ack *extack) @@ -440,6 +461,9 @@ dpll_cmd_pin_get_one(struct sk_buff *msg, struct dpll_pin *pin, prop->phase_range.max)) return -EMSGSIZE; ret = dpll_msg_add_pin_phase_adjust(msg, pin, ref, extack); + if (ret) + return ret; + ret = dpll_msg_add_ffo(msg, pin, ref, extack); if (ret) return ret; if (xa_empty(&pin->parent_refs)) diff --git a/include/linux/dpll.h b/include/linux/dpll.h index b1a5f9ca8ee5..9cf896ea1d41 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -77,6 +77,9 @@ struct dpll_pin_ops { const struct dpll_device *dpll, void *dpll_priv, const s32 phase_adjust, struct netlink_ext_ack *extack); + int (*ffo_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + s64 *ffo, struct netlink_ext_ack *extack); }; struct dpll_pin_frequency { diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h index 715a491d2727..b4e947f9bfbc 100644 --- a/include/uapi/linux/dpll.h +++ b/include/uapi/linux/dpll.h @@ -179,6 +179,7 @@ enum dpll_a_pin { DPLL_A_PIN_PHASE_ADJUST_MAX, DPLL_A_PIN_PHASE_ADJUST, DPLL_A_PIN_PHASE_OFFSET, + DPLL_A_PIN_FRACTIONAL_FREQUENCY_OFFSET, __DPLL_A_PIN_MAX, DPLL_A_PIN_MAX = (__DPLL_A_PIN_MAX - 1) -- cgit From 35967bdcff325f4572b21b0d0005318da7e03f53 Mon Sep 17 00:00:00 2001 From: Changyuan Lyu Date: Wed, 20 Dec 2023 12:49:06 -0800 Subject: virtio_pmem: support feature SHMEM_REGION This patch adds the support for feature VIRTIO_PMEM_F_SHMEM_REGION (virtio spec v1.2 section 5.19.5.2 [1]). During feature negotiation, if VIRTIO_PMEM_F_SHMEM_REGION is offered by the device, the driver looks for a shared memory region of id 0. If it is found, this feature is understood. Otherwise, this feature bit is cleared. During probe, if VIRTIO_PMEM_F_SHMEM_REGION has been negotiated, virtio pmem ignores the `start` and `size` fields in device config and uses the physical address range of shared memory region 0. [1] https://docs.oasis-open.org/virtio/virtio/v1.2/csd01/virtio-v1.2-csd01.html#x1-6480002 Signed-off-by: Changyuan Lyu Message-Id: <20231220204906.566922-1-changyuanl@google.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/nvdimm/virtio_pmem.c | 36 ++++++++++++++++++++++++++++++++---- include/uapi/linux/virtio_pmem.h | 7 +++++++ 2 files changed, 39 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c index a92eb172f0e7..4ceced5cefcf 100644 --- a/drivers/nvdimm/virtio_pmem.c +++ b/drivers/nvdimm/virtio_pmem.c @@ -29,12 +29,27 @@ static int init_vq(struct virtio_pmem *vpmem) return 0; }; +static int virtio_pmem_validate(struct virtio_device *vdev) +{ + struct virtio_shm_region shm_reg; + + if (virtio_has_feature(vdev, VIRTIO_PMEM_F_SHMEM_REGION) && + !virtio_get_shm_region(vdev, &shm_reg, (u8)VIRTIO_PMEM_SHMEM_REGION_ID) + ) { + dev_notice(&vdev->dev, "failed to get shared memory region %d\n", + VIRTIO_PMEM_SHMEM_REGION_ID); + __virtio_clear_bit(vdev, VIRTIO_PMEM_F_SHMEM_REGION); + } + return 0; +} + static int virtio_pmem_probe(struct virtio_device *vdev) { struct nd_region_desc ndr_desc = {}; struct nd_region *nd_region; struct virtio_pmem *vpmem; struct resource res; + struct virtio_shm_region shm_reg; int err = 0; if (!vdev->config->get) { @@ -57,10 +72,16 @@ static int virtio_pmem_probe(struct virtio_device *vdev) goto out_err; } - virtio_cread_le(vpmem->vdev, struct virtio_pmem_config, - start, &vpmem->start); - virtio_cread_le(vpmem->vdev, struct virtio_pmem_config, - size, &vpmem->size); + if (virtio_has_feature(vdev, VIRTIO_PMEM_F_SHMEM_REGION)) { + virtio_get_shm_region(vdev, &shm_reg, (u8)VIRTIO_PMEM_SHMEM_REGION_ID); + vpmem->start = shm_reg.addr; + vpmem->size = shm_reg.len; + } else { + virtio_cread_le(vpmem->vdev, struct virtio_pmem_config, + start, &vpmem->start); + virtio_cread_le(vpmem->vdev, struct virtio_pmem_config, + size, &vpmem->size); + } res.start = vpmem->start; res.end = vpmem->start + vpmem->size - 1; @@ -122,10 +143,17 @@ static void virtio_pmem_remove(struct virtio_device *vdev) virtio_reset_device(vdev); } +static unsigned int features[] = { + VIRTIO_PMEM_F_SHMEM_REGION, +}; + static struct virtio_driver virtio_pmem_driver = { + .feature_table = features, + .feature_table_size = ARRAY_SIZE(features), .driver.name = KBUILD_MODNAME, .driver.owner = THIS_MODULE, .id_table = id_table, + .validate = virtio_pmem_validate, .probe = virtio_pmem_probe, .remove = virtio_pmem_remove, }; diff --git a/include/uapi/linux/virtio_pmem.h b/include/uapi/linux/virtio_pmem.h index d676b3620383..ede4f3564977 100644 --- a/include/uapi/linux/virtio_pmem.h +++ b/include/uapi/linux/virtio_pmem.h @@ -14,6 +14,13 @@ #include #include +/* Feature bits */ +/* guest physical address range will be indicated as shared memory region 0 */ +#define VIRTIO_PMEM_F_SHMEM_REGION 0 + +/* shmid of the shared memory region corresponding to the pmem */ +#define VIRTIO_PMEM_SHMEM_REGION_ID 0 + struct virtio_pmem_config { __le64 start; __le64 size; -- cgit From 8c6eabae3807e048b9f17733af5e20500fbf858c Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Wed, 10 Jan 2024 20:10:09 -0800 Subject: iommufd: Add IOMMU_HWPT_INVALIDATE In nested translation, the stage-1 page table is user-managed but cached by the IOMMU hardware, so an update on present page table entries in the stage-1 page table should be followed with a cache invalidation. Add an IOMMU_HWPT_INVALIDATE ioctl to support such a cache invalidation. It takes hwpt_id to specify the iommu_domain, and a multi-entry array to support multiple invalidation data in one ioctl. enum iommu_hwpt_invalidate_data_type is defined to tag the data type of the entries in the multi-entry array. Link: https://lore.kernel.org/r/20240111041015.47920-3-yi.l.liu@intel.com Reviewed-by: Kevin Tian Co-developed-by: Nicolin Chen Signed-off-by: Nicolin Chen Signed-off-by: Yi Liu Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommufd/hw_pagetable.c | 41 +++++++++++++++++++++++++++++++ drivers/iommu/iommufd/iommufd_private.h | 10 ++++++++ drivers/iommu/iommufd/main.c | 3 +++ include/uapi/linux/iommufd.h | 43 +++++++++++++++++++++++++++++++++ 4 files changed, 97 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index cbb5df0a6c32..4e8711f19f72 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -371,3 +371,44 @@ int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd) iommufd_put_object(ucmd->ictx, &hwpt_paging->common.obj); return rc; } + +int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd) +{ + struct iommu_hwpt_invalidate *cmd = ucmd->cmd; + struct iommu_user_data_array data_array = { + .type = cmd->data_type, + .uptr = u64_to_user_ptr(cmd->data_uptr), + .entry_len = cmd->entry_len, + .entry_num = cmd->entry_num, + }; + struct iommufd_hw_pagetable *hwpt; + u32 done_num = 0; + int rc; + + if (cmd->__reserved) { + rc = -EOPNOTSUPP; + goto out; + } + + if (cmd->entry_num && (!cmd->data_uptr || !cmd->entry_len)) { + rc = -EINVAL; + goto out; + } + + hwpt = iommufd_get_hwpt_nested(ucmd, cmd->hwpt_id); + if (IS_ERR(hwpt)) { + rc = PTR_ERR(hwpt); + goto out; + } + + rc = hwpt->domain->ops->cache_invalidate_user(hwpt->domain, + &data_array); + done_num = data_array.entry_num; + + iommufd_put_object(ucmd->ictx, &hwpt->obj); +out: + cmd->entry_num = done_num; + if (iommufd_ucmd_respond(ucmd, sizeof(*cmd))) + return -EFAULT; + return rc; +} diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index abae041e256f..991f864d1f9b 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -328,6 +328,15 @@ iommufd_get_hwpt_paging(struct iommufd_ucmd *ucmd, u32 id) IOMMUFD_OBJ_HWPT_PAGING), struct iommufd_hwpt_paging, common.obj); } + +static inline struct iommufd_hw_pagetable * +iommufd_get_hwpt_nested(struct iommufd_ucmd *ucmd, u32 id) +{ + return container_of(iommufd_get_object(ucmd->ictx, id, + IOMMUFD_OBJ_HWPT_NESTED), + struct iommufd_hw_pagetable, obj); +} + int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd); int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd); @@ -345,6 +354,7 @@ void iommufd_hwpt_paging_abort(struct iommufd_object *obj); void iommufd_hwpt_nested_destroy(struct iommufd_object *obj); void iommufd_hwpt_nested_abort(struct iommufd_object *obj); int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd); +int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd); static inline void iommufd_hw_pagetable_put(struct iommufd_ctx *ictx, struct iommufd_hw_pagetable *hwpt) diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index c9091e46d208..39b32932c61e 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -322,6 +322,7 @@ union ucmd_buffer { struct iommu_hw_info info; struct iommu_hwpt_alloc hwpt; struct iommu_hwpt_get_dirty_bitmap get_dirty_bitmap; + struct iommu_hwpt_invalidate cache; struct iommu_hwpt_set_dirty_tracking set_dirty_tracking; struct iommu_ioas_alloc alloc; struct iommu_ioas_allow_iovas allow_iovas; @@ -360,6 +361,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { __reserved), IOCTL_OP(IOMMU_HWPT_GET_DIRTY_BITMAP, iommufd_hwpt_get_dirty_bitmap, struct iommu_hwpt_get_dirty_bitmap, data), + IOCTL_OP(IOMMU_HWPT_INVALIDATE, iommufd_hwpt_invalidate, + struct iommu_hwpt_invalidate, __reserved), IOCTL_OP(IOMMU_HWPT_SET_DIRTY_TRACKING, iommufd_hwpt_set_dirty_tracking, struct iommu_hwpt_set_dirty_tracking, __reserved), IOCTL_OP(IOMMU_IOAS_ALLOC, iommufd_ioas_alloc_ioctl, diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 0b2bc6252e2c..824560c50ec6 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -49,6 +49,7 @@ enum { IOMMUFD_CMD_GET_HW_INFO, IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING, IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP, + IOMMUFD_CMD_HWPT_INVALIDATE, }; /** @@ -613,4 +614,46 @@ struct iommu_hwpt_get_dirty_bitmap { #define IOMMU_HWPT_GET_DIRTY_BITMAP _IO(IOMMUFD_TYPE, \ IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP) +/** + * enum iommu_hwpt_invalidate_data_type - IOMMU HWPT Cache Invalidation + * Data Type + * @IOMMU_HWPT_INVALIDATE_DATA_VTD_S1: Invalidation data for VTD_S1 + */ +enum iommu_hwpt_invalidate_data_type { + IOMMU_HWPT_INVALIDATE_DATA_VTD_S1, +}; + +/** + * struct iommu_hwpt_invalidate - ioctl(IOMMU_HWPT_INVALIDATE) + * @size: sizeof(struct iommu_hwpt_invalidate) + * @hwpt_id: ID of a nested HWPT for cache invalidation + * @data_uptr: User pointer to an array of driver-specific cache invalidation + * data. + * @data_type: One of enum iommu_hwpt_invalidate_data_type, defining the data + * type of all the entries in the invalidation request array. It + * should be a type supported by the hwpt pointed by @hwpt_id. + * @entry_len: Length (in bytes) of a request entry in the request array + * @entry_num: Input the number of cache invalidation requests in the array. + * Output the number of requests successfully handled by kernel. + * @__reserved: Must be 0. + * + * Invalidate the iommu cache for user-managed page table. Modifications on a + * user-managed page table should be followed by this operation to sync cache. + * Each ioctl can support one or more cache invalidation requests in the array + * that has a total size of @entry_len * @entry_num. + * + * An empty invalidation request array by setting @entry_num==0 is allowed, and + * @entry_len and @data_uptr would be ignored in this case. This can be used to + * check if the given @data_type is supported or not by kernel. + */ +struct iommu_hwpt_invalidate { + __u32 size; + __u32 hwpt_id; + __aligned_u64 data_uptr; + __u32 data_type; + __u32 entry_len; + __u32 entry_num; + __u32 __reserved; +}; +#define IOMMU_HWPT_INVALIDATE _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_INVALIDATE) #endif -- cgit From 393a5778b72a7b551493d0fd3fbe0282154058fe Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Wed, 10 Jan 2024 20:10:14 -0800 Subject: iommufd: Add data structure for Intel VT-d stage-1 cache invalidation This adds the data structure invalidating caches for the nested domain allocated with IOMMU_HWPT_DATA_VTD_S1 type. Link: https://lore.kernel.org/r/20240111041015.47920-8-yi.l.liu@intel.com Reviewed-by: Kevin Tian Signed-off-by: Lu Baolu Signed-off-by: Yi Liu Signed-off-by: Jason Gunthorpe --- include/uapi/linux/iommufd.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 824560c50ec6..1dfeaa2e649e 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -623,6 +623,42 @@ enum iommu_hwpt_invalidate_data_type { IOMMU_HWPT_INVALIDATE_DATA_VTD_S1, }; +/** + * enum iommu_hwpt_vtd_s1_invalidate_flags - Flags for Intel VT-d + * stage-1 cache invalidation + * @IOMMU_VTD_INV_FLAGS_LEAF: Indicates whether the invalidation applies + * to all-levels page structure cache or just + * the leaf PTE cache. + */ +enum iommu_hwpt_vtd_s1_invalidate_flags { + IOMMU_VTD_INV_FLAGS_LEAF = 1 << 0, +}; + +/** + * struct iommu_hwpt_vtd_s1_invalidate - Intel VT-d cache invalidation + * (IOMMU_HWPT_INVALIDATE_DATA_VTD_S1) + * @addr: The start address of the range to be invalidated. It needs to + * be 4KB aligned. + * @npages: Number of contiguous 4K pages to be invalidated. + * @flags: Combination of enum iommu_hwpt_vtd_s1_invalidate_flags + * @__reserved: Must be 0 + * + * The Intel VT-d specific invalidation data for user-managed stage-1 cache + * invalidation in nested translation. Userspace uses this structure to + * tell the impacted cache scope after modifying the stage-1 page table. + * + * Invalidating all the caches related to the page table by setting @addr + * to be 0 and @npages to be U64_MAX. + * + * The device TLB will be invalidated automatically if ATS is enabled. + */ +struct iommu_hwpt_vtd_s1_invalidate { + __aligned_u64 addr; + __aligned_u64 npages; + __u32 flags; + __u32 __reserved; +}; + /** * struct iommu_hwpt_invalidate - ioctl(IOMMU_HWPT_INVALIDATE) * @size: sizeof(struct iommu_hwpt_invalidate) -- cgit From 173431b274a9a54fc10b273b46e67f46bcf62d2e Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Wed, 10 Jan 2024 08:58:26 +1030 Subject: btrfs: defrag: reject unknown flags of btrfs_ioctl_defrag_range_args Add extra sanity check for btrfs_ioctl_defrag_range_args::flags. This is not really to enhance fuzzing tests, but as a preparation for future expansion on btrfs_ioctl_defrag_range_args. In the future we're going to add new members, allowing more fine tuning for btrfs defrag. Without the -ENONOTSUPP error, there would be no way to detect if the kernel supports those new defrag features. CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Filipe Manana Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 4 ++++ include/uapi/linux/btrfs.h | 3 +++ 2 files changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index fea5d37528b8..5d42319b43f2 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2602,6 +2602,10 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp) ret = -EFAULT; goto out; } + if (range.flags & ~BTRFS_DEFRAG_RANGE_FLAGS_SUPP) { + ret = -EOPNOTSUPP; + goto out; + } /* compression requires us to start the IO */ if ((range.flags & BTRFS_DEFRAG_RANGE_COMPRESS)) { range.flags |= BTRFS_DEFRAG_RANGE_START_IO; diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 7c29d82db9ee..f8bc34a6bcfa 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -614,6 +614,9 @@ struct btrfs_ioctl_clone_range_args { */ #define BTRFS_DEFRAG_RANGE_COMPRESS 1 #define BTRFS_DEFRAG_RANGE_START_IO 2 +#define BTRFS_DEFRAG_RANGE_FLAGS_SUPP (BTRFS_DEFRAG_RANGE_COMPRESS | \ + BTRFS_DEFRAG_RANGE_START_IO) + struct btrfs_ioctl_defrag_range_args { /* start of the defrag operation */ __u64 start; -- cgit From e15c99be0c915bbe70dfe55450d268d7bd5bdac8 Mon Sep 17 00:00:00 2001 From: Christoph Niedermaier Date: Fri, 19 Jan 2024 12:35:16 +0100 Subject: tty: serial: Fix bit order in RS485 flag definitions Since the commit 93f3350c46fa ("RS485: fix inconsistencies in the meaning of some variables"), the definition for bit 3 has been removed. But with the switch to bit shift macros in commit 76ac8e29855b ("tty: serial: Cleanup the bit shift with macro"), this gap wasn't preserved. To avoid a break in user/kernel api of the system skip bit 3 again and add a placeholder comment. Signed-off-by: Christoph Niedermaier Fixes: 76ac8e29855b ("tty: serial: Cleanup the bit shift with macro") Fixes: 6056f20f27e9 ("tty: serial: Add RS422 flag to struct serial_rs485") Reviewed-by: Jiri Slaby Cc: Greg Kroah-Hartman Cc: Crescent CY Hsieh Cc: Jiri Slaby Cc: Lukas Wunner Cc: Lino Sanfilippo Cc: Hugo Villeneuve Link: https://lore.kernel.org/r/20240119113516.2944-1-cniedermaier@dh-electronics.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/serial.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/serial.h b/include/uapi/linux/serial.h index 9086367db043..de9b4733607e 100644 --- a/include/uapi/linux/serial.h +++ b/include/uapi/linux/serial.h @@ -145,12 +145,13 @@ struct serial_rs485 { #define SER_RS485_ENABLED _BITUL(0) #define SER_RS485_RTS_ON_SEND _BITUL(1) #define SER_RS485_RTS_AFTER_SEND _BITUL(2) -#define SER_RS485_RX_DURING_TX _BITUL(3) -#define SER_RS485_TERMINATE_BUS _BITUL(4) -#define SER_RS485_ADDRB _BITUL(5) -#define SER_RS485_ADDR_RECV _BITUL(6) -#define SER_RS485_ADDR_DEST _BITUL(7) -#define SER_RS485_MODE_RS422 _BITUL(8) +/* Placeholder for bit 3: SER_RS485_RTS_BEFORE_SEND, which isn't used anymore */ +#define SER_RS485_RX_DURING_TX _BITUL(4) +#define SER_RS485_TERMINATE_BUS _BITUL(5) +#define SER_RS485_ADDRB _BITUL(6) +#define SER_RS485_ADDR_RECV _BITUL(7) +#define SER_RS485_ADDR_DEST _BITUL(8) +#define SER_RS485_MODE_RS422 _BITUL(9) __u32 delay_rts_before_send; __u32 delay_rts_after_send; -- cgit From 292781c3c5485ce33bd22b2ef1b2bed709b4d672 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 1 Feb 2024 23:33:29 +0100 Subject: netfilter: nft_compat: reject unused compat flag Flag (1 << 0) is ignored is set, never used, reject it it with EINVAL instead. Fixes: 0ca743a55991 ("netfilter: nf_tables: add compatibility layer for x_tables") Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 ++ net/netfilter/nft_compat.c | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index ca30232b7bc8..117c6a9b845b 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -285,9 +285,11 @@ enum nft_rule_attributes { /** * enum nft_rule_compat_flags - nf_tables rule compat flags * + * @NFT_RULE_COMPAT_F_UNUSED: unused * @NFT_RULE_COMPAT_F_INV: invert the check result */ enum nft_rule_compat_flags { + NFT_RULE_COMPAT_F_UNUSED = (1 << 0), NFT_RULE_COMPAT_F_INV = (1 << 1), NFT_RULE_COMPAT_F_MASK = NFT_RULE_COMPAT_F_INV, }; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 001b6841a4b6..ed71d5ecbe0a 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -212,7 +212,8 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv) return -EINVAL; flags = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_FLAGS])); - if (flags & ~NFT_RULE_COMPAT_F_MASK) + if (flags & NFT_RULE_COMPAT_F_UNUSED || + flags & ~NFT_RULE_COMPAT_F_MASK) return -EINVAL; if (flags & NFT_RULE_COMPAT_F_INV) *inv = true; -- cgit