From ec5ad331680c96ef3dd30dc297b206988023b9e1 Mon Sep 17 00:00:00 2001 From: Max Staudt Date: Sat, 18 Jun 2022 20:01:34 +0200 Subject: tty: Add N_CAN327 line discipline ID for ELM327 based CAN driver The actual driver will be added via the CAN tree. Acked-by: Marc Kleine-Budde Signed-off-by: Max Staudt Link: https://lore.kernel.org/r/20220618180134.9890-1-max@enpas.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/tty.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tty.h b/include/uapi/linux/tty.h index 9d0f06bfbac3..68aeae2addec 100644 --- a/include/uapi/linux/tty.h +++ b/include/uapi/linux/tty.h @@ -38,8 +38,9 @@ #define N_NULL 27 /* Null ldisc used for error handling */ #define N_MCTP 28 /* MCTP-over-serial */ #define N_DEVELOPMENT 29 /* Manual out-of-tree testing */ +#define N_CAN327 30 /* ELM327 based OBD-II interfaces */ /* Always the newest line discipline + 1 */ -#define NR_LDISCS 30 +#define NR_LDISCS 31 #endif /* _UAPI_LINUX_TTY_H */ -- cgit From f8d3da4ef8faf027261e06b7864583930dd7c7b9 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Wed, 6 Jul 2022 16:25:47 -0700 Subject: bpf: Add flags arg to bpf_dynptr_read and bpf_dynptr_write APIs Commit 13bbbfbea759 ("bpf: Add bpf_dynptr_read and bpf_dynptr_write") added the bpf_dynptr_write() and bpf_dynptr_read() APIs. However, it will be needed for some dynptr types to pass in flags as well (e.g. when writing to a skb, the user may like to invalidate the hash or recompute the checksum). This patch adds a "u64 flags" arg to the bpf_dynptr_read() and bpf_dynptr_write() APIs before their UAPI signature freezes where we then cannot change them anymore with a 5.19.x released kernel. Fixes: 13bbbfbea759 ("bpf: Add bpf_dynptr_read and bpf_dynptr_write") Signed-off-by: Joanne Koong Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/r/20220706232547.4016651-1-joannelkoong@gmail.com --- include/uapi/linux/bpf.h | 11 +++++++---- kernel/bpf/helpers.c | 12 ++++++++---- tools/include/uapi/linux/bpf.h | 11 +++++++---- tools/testing/selftests/bpf/progs/dynptr_fail.c | 10 +++++----- tools/testing/selftests/bpf/progs/dynptr_success.c | 4 ++-- 5 files changed, 29 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f4009dbdf62d..ef78e0e1a754 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5222,22 +5222,25 @@ union bpf_attr { * Return * Nothing. Always succeeds. * - * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset) + * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset, u64 flags) * Description * Read *len* bytes from *src* into *dst*, starting from *offset* * into *src*. + * *flags* is currently unused. * Return * 0 on success, -E2BIG if *offset* + *len* exceeds the length - * of *src*'s data, -EINVAL if *src* is an invalid dynptr. + * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if + * *flags* is not 0. * - * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len) + * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) * Description * Write *len* bytes from *src* into *dst*, starting from *offset* * into *dst*. + * *flags* is currently unused. * Return * 0 on success, -E2BIG if *offset* + *len* exceeds the length * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* - * is a read-only dynptr. + * is a read-only dynptr or if *flags* is not 0. * * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len) * Description diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 225806a02efb..bb1254f07667 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1497,11 +1497,12 @@ const struct bpf_func_proto bpf_dynptr_from_mem_proto = { .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT, }; -BPF_CALL_4(bpf_dynptr_read, void *, dst, u32, len, struct bpf_dynptr_kern *, src, u32, offset) +BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, struct bpf_dynptr_kern *, src, + u32, offset, u64, flags) { int err; - if (!src->data) + if (!src->data || flags) return -EINVAL; err = bpf_dynptr_check_off_len(src, offset, len); @@ -1521,13 +1522,15 @@ const struct bpf_func_proto bpf_dynptr_read_proto = { .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_PTR_TO_DYNPTR, .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, }; -BPF_CALL_4(bpf_dynptr_write, struct bpf_dynptr_kern *, dst, u32, offset, void *, src, u32, len) +BPF_CALL_5(bpf_dynptr_write, struct bpf_dynptr_kern *, dst, u32, offset, void *, src, + u32, len, u64, flags) { int err; - if (!dst->data || bpf_dynptr_is_rdonly(dst)) + if (!dst->data || flags || bpf_dynptr_is_rdonly(dst)) return -EINVAL; err = bpf_dynptr_check_off_len(dst, offset, len); @@ -1547,6 +1550,7 @@ const struct bpf_func_proto bpf_dynptr_write_proto = { .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, + .arg5_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_dynptr_data, struct bpf_dynptr_kern *, ptr, u32, offset, u32, len) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f4009dbdf62d..ef78e0e1a754 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5222,22 +5222,25 @@ union bpf_attr { * Return * Nothing. Always succeeds. * - * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset) + * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset, u64 flags) * Description * Read *len* bytes from *src* into *dst*, starting from *offset* * into *src*. + * *flags* is currently unused. * Return * 0 on success, -E2BIG if *offset* + *len* exceeds the length - * of *src*'s data, -EINVAL if *src* is an invalid dynptr. + * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if + * *flags* is not 0. * - * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len) + * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) * Description * Write *len* bytes from *src* into *dst*, starting from *offset* * into *dst*. + * *flags* is currently unused. * Return * 0 on success, -E2BIG if *offset* + *len* exceeds the length * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* - * is a read-only dynptr. + * is a read-only dynptr or if *flags* is not 0. * * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len) * Description diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c index d811cff73597..0a26c243e6e9 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_fail.c +++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c @@ -140,12 +140,12 @@ int use_after_invalid(void *ctx) bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(read_data), 0, &ptr); - bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0); + bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); bpf_ringbuf_submit_dynptr(&ptr, 0); /* this should fail */ - bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0); + bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); return 0; } @@ -338,7 +338,7 @@ int invalid_helper2(void *ctx) get_map_val_dynptr(&ptr); /* this should fail */ - bpf_dynptr_read(read_data, sizeof(read_data), (void *)&ptr + 8, 0); + bpf_dynptr_read(read_data, sizeof(read_data), (void *)&ptr + 8, 0, 0); return 0; } @@ -377,7 +377,7 @@ int invalid_write2(void *ctx) memcpy((void *)&ptr + 8, &x, sizeof(x)); /* this should fail */ - bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0); + bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); bpf_ringbuf_submit_dynptr(&ptr, 0); @@ -473,7 +473,7 @@ int invalid_read2(void *ctx) get_map_val_dynptr(&ptr); /* this should fail */ - bpf_dynptr_read(read_data, sizeof(read_data), (void *)&ptr + 1, 0); + bpf_dynptr_read(read_data, sizeof(read_data), (void *)&ptr + 1, 0, 0); return 0; } diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c index d67be48df4b2..a3a6103c8569 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_success.c +++ b/tools/testing/selftests/bpf/progs/dynptr_success.c @@ -43,10 +43,10 @@ int test_read_write(void *ctx) bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(write_data), 0, &ptr); /* Write data into the dynptr */ - err = err ?: bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data)); + err = bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data), 0); /* Read the data that was written into the dynptr */ - err = err ?: bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0); + err = err ?: bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); /* Ensure the data we read matches the data we wrote */ for (i = 0; i < sizeof(read_data); i++) { -- cgit From 2a96271fb66c499e4a89d76a89d3d01170c10bef Mon Sep 17 00:00:00 2001 From: Siarhei Vishniakou Date: Fri, 8 Jul 2022 21:59:23 -0700 Subject: Input: document the units for resolution of size axes Today, the resolution of size axes is not documented. As a result, it's not clear what the canonical interpretation of this value should be. On Android, there is a need to calculate the size of the touch ellipse in physical units (millimeters). After reviewing linux source, it turned out that most of the existing usages are already interpreting this value as "units/mm". This documentation will make it explicit. This will help device implementations with correctly following the linux specs, and will ensure that the devices will work on Android without needing further customized parameters for scaling of major/minor values. Signed-off-by: Siarhei Vishniakou Reviewed-by: Jeff LaBundy Link: https://lore.kernel.org/r/20220520084514.3451193-1-svv@google.com Signed-off-by: Dmitry Torokhov --- include/uapi/linux/input.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index ee3127461ee0..328cf545c029 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -78,10 +78,13 @@ struct input_id { * Note that input core does not clamp reported values to the * [minimum, maximum] limits, such task is left to userspace. * - * The default resolution for main axes (ABS_X, ABS_Y, ABS_Z) - * is reported in units per millimeter (units/mm), resolution - * for rotational axes (ABS_RX, ABS_RY, ABS_RZ) is reported - * in units per radian. + * The default resolution for main axes (ABS_X, ABS_Y, ABS_Z, + * ABS_MT_POSITION_X, ABS_MT_POSITION_Y) is reported in units + * per millimeter (units/mm), resolution for rotational axes + * (ABS_RX, ABS_RY, ABS_RZ) is reported in units per radian. + * The resolution for the size axes (ABS_MT_TOUCH_MAJOR, + * ABS_MT_TOUCH_MINOR, ABS_MT_WIDTH_MAJOR, ABS_MT_WIDTH_MINOR) + * is reported in units per millimeter (units/mm). * When INPUT_PROP_ACCELEROMETER is set the resolution changes. * The main axes (ABS_X, ABS_Y, ABS_Z) are then reported in * units per g (units/g) and in units per degree per second -- cgit From 1b870fa5573e260bc74d19f381ab0dd971a8d8e7 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 14 Jul 2022 07:27:31 -0400 Subject: kvm: stats: tell userspace which values are boolean Some of the statistics values exported by KVM are always only 0 or 1. It can be useful to export this fact to userspace so that it can track them specially (for example by polling the value every now and then to compute a % of time spent in a specific state). Therefore, add "boolean value" as a new "unit". While it is not exactly a unit, it walks and quacks like one. In particular, using the type would be wrong because boolean values could be instantaneous or peak values (e.g. "is the rmap allocated?") or even two-bucket histograms (e.g. "number of posted vs. non-posted interrupt injections"). Suggested-by: Amneesh Singh Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 6 ++++++ arch/x86/kvm/x86.c | 2 +- include/linux/kvm_host.h | 11 ++++++++++- include/uapi/linux/kvm.h | 1 + 4 files changed, 18 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 11e00a46c610..48bf6e49a7de 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5657,6 +5657,7 @@ by a string of size ``name_size``. #define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) + #define KVM_STATS_UNIT_BOOLEAN (0x4 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_CYCLES #define KVM_STATS_BASE_SHIFT 8 @@ -5724,6 +5725,11 @@ Bits 4-7 of ``flags`` encode the unit: It indicates that the statistics data is used to measure time or latency. * ``KVM_STATS_UNIT_CYCLES`` It indicates that the statistics data is used to measure CPU clock cycles. + * ``KVM_STATS_UNIT_BOOLEAN`` + It indicates that the statistic will always be either 0 or 1. Boolean + statistics of "peak" type will never go back from 1 to 0. Boolean + statistics can be linear histograms (with two buckets) but not logarithmic + histograms. Bits 8-11 of ``flags``, together with ``exponent``, encode the scale of the unit: diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 26d0cac32f73..0c3e85e8fce9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -298,7 +298,7 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, directed_yield_successful), STATS_DESC_COUNTER(VCPU, preemption_reported), STATS_DESC_COUNTER(VCPU, preemption_other), - STATS_DESC_ICOUNTER(VCPU, guest_mode) + STATS_DESC_IBOOLEAN(VCPU, guest_mode) }; const struct kvm_stats_header kvm_vcpu_stats_header = { diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 83cf7fd842e0..90a45ef7203b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1822,6 +1822,15 @@ struct _kvm_stats_desc { STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_NONE, \ KVM_STATS_BASE_POW10, 0) +/* Instantaneous boolean value, read only */ +#define STATS_DESC_IBOOLEAN(SCOPE, name) \ + STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_BOOLEAN, \ + KVM_STATS_BASE_POW10, 0) +/* Peak (sticky) boolean value, read/write */ +#define STATS_DESC_PBOOLEAN(SCOPE, name) \ + STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_BOOLEAN, \ + KVM_STATS_BASE_POW10, 0) + /* Cumulative time in nanosecond */ #define STATS_DESC_TIME_NSEC(SCOPE, name) \ STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ @@ -1853,7 +1862,7 @@ struct _kvm_stats_desc { HALT_POLL_HIST_COUNT), \ STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_wait_hist, \ HALT_POLL_HIST_COUNT), \ - STATS_DESC_ICOUNTER(VCPU_GENERIC, blocking) + STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking) extern struct dentry *kvm_debugfs_dir; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 5088bd9f1922..811897dadcae 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -2083,6 +2083,7 @@ struct kvm_stats_header { #define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_BOOLEAN (0x4 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_CYCLES #define KVM_STATS_BASE_SHIFT 8 -- cgit From 450a563924ae9437758bd468c5b7cee9468ce749 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 19 Jul 2022 12:52:29 +0000 Subject: KVM: stats: Fix value for KVM_STATS_UNIT_MAX for boolean stats commit 1b870fa5573e ("kvm: stats: tell userspace which values are boolean") added a new stat unit (boolean) but failed to raise KVM_STATS_UNIT_MAX. Fix by pointing UNIT_MAX at the new max value of UNIT_BOOLEAN. Fixes: 1b870fa5573e ("kvm: stats: tell userspace which values are boolean") Reported-by: Janis Schoetterl-Glausch Signed-off-by: Oliver Upton Message-Id: <20220719125229.2934273-1-oupton@google.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 2 +- include/uapi/linux/kvm.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 6e090fb96a0e..98a283930307 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5658,7 +5658,7 @@ by a string of size ``name_size``. #define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_BOOLEAN (0x4 << KVM_STATS_UNIT_SHIFT) - #define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_CYCLES + #define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_BOOLEAN #define KVM_STATS_BASE_SHIFT 8 #define KVM_STATS_BASE_MASK (0xF << KVM_STATS_BASE_SHIFT) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 811897dadcae..860f867c50c0 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -2084,7 +2084,7 @@ struct kvm_stats_header { #define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_BOOLEAN (0x4 << KVM_STATS_UNIT_SHIFT) -#define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_CYCLES +#define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_BOOLEAN #define KVM_STATS_BASE_SHIFT 8 #define KVM_STATS_BASE_MASK (0xF << KVM_STATS_BASE_SHIFT) -- cgit From b9ba8a4463cd78d0aee520c4bf2569820ac29929 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 27 May 2022 10:55:07 -0600 Subject: io_uring: add support for level triggered poll By default, the POLL_ADD command does edge triggered poll - if we get a non-zero mask on the initial poll attempt, we complete the request successfully. Support level triggered by always waiting for a notification, regardless of whether or not the initial mask matches the file state. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 3 +++ io_uring/poll.c | 15 ++++++++++----- 2 files changed, 13 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 0ad3da28d2fc..4927bb69387a 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -229,10 +229,13 @@ enum io_uring_op { * * IORING_POLL_UPDATE Update existing poll request, matching * sqe->addr as the old user_data field. + * + * IORING_POLL_LEVEL Level triggered poll. */ #define IORING_POLL_ADD_MULTI (1U << 0) #define IORING_POLL_UPDATE_EVENTS (1U << 1) #define IORING_POLL_UPDATE_USER_DATA (1U << 2) +#define IORING_POLL_ADD_LEVEL (1U << 3) /* * ASYNC_CANCEL flags. diff --git a/io_uring/poll.c b/io_uring/poll.c index b80f7fa26123..558dc170468a 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -423,11 +423,13 @@ static int __io_arm_poll_handler(struct io_kiocb *req, atomic_set(&req->poll_refs, 1); mask = vfs_poll(req->file, &ipt->pt) & poll->events; - if (mask && (poll->events & EPOLLONESHOT)) { + if (mask && + ((poll->events & (EPOLLET|EPOLLONESHOT)) == (EPOLLET|EPOLLONESHOT))) { io_poll_remove_entries(req); /* no one else has access to the req, forget about the ref */ return mask; } + if (!mask && unlikely(ipt->error || !ipt->nr_entries)) { io_poll_remove_entries(req); if (!ipt->error) @@ -439,7 +441,7 @@ static int __io_arm_poll_handler(struct io_kiocb *req, io_poll_req_insert(req); spin_unlock(&ctx->completion_lock); - if (mask) { + if (mask && (poll->events & EPOLLET)) { /* can't multishot if failed, just queue the event we've got */ if (unlikely(ipt->error || !ipt->nr_entries)) { poll->events |= EPOLLONESHOT; @@ -475,7 +477,7 @@ int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags) struct io_ring_ctx *ctx = req->ctx; struct async_poll *apoll; struct io_poll_table ipt; - __poll_t mask = POLLPRI | POLLERR; + __poll_t mask = POLLPRI | POLLERR | EPOLLET; int ret; if (!def->pollin && !def->pollout) @@ -638,7 +640,10 @@ static __poll_t io_poll_parse_events(const struct io_uring_sqe *sqe, #endif if (!(flags & IORING_POLL_ADD_MULTI)) events |= EPOLLONESHOT; - return demangle_poll(events) | (events & (EPOLLEXCLUSIVE|EPOLLONESHOT)); + if (!(flags & IORING_POLL_ADD_LEVEL)) + events |= EPOLLET; + return demangle_poll(events) | + (events & (EPOLLEXCLUSIVE|EPOLLONESHOT|EPOLLET)); } int io_poll_remove_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) @@ -679,7 +684,7 @@ int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (sqe->buf_index || sqe->off || sqe->addr) return -EINVAL; flags = READ_ONCE(sqe->len); - if (flags & ~IORING_POLL_ADD_MULTI) + if (flags & ~(IORING_POLL_ADD_MULTI|IORING_POLL_ADD_LEVEL)) return -EINVAL; if ((flags & IORING_POLL_ADD_MULTI) && (req->flags & REQ_F_CQE_SKIP)) return -EINVAL; -- cgit From 97bbdc06a4446bc69d8ba71d722abae542a6b70c Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 16 Jun 2022 10:22:08 +0100 Subject: io_uring: add IORING_SETUP_SINGLE_ISSUER Add a new IORING_SETUP_SINGLE_ISSUER flag and the userspace visible part of it, i.e. put limitations of submitters. Also, don't allow it together with IOPOLL as we're not going to put it to good use. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/4bcc41ee467fdf04c8aab8baf6ce3ba21858c3d4.1655371007.git.asml.silence@gmail.com Reviewed-by: Hao Xu Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 5 ++++- io_uring/io_uring.c | 7 +++++-- io_uring/io_uring_types.h | 1 + io_uring/tctx.c | 27 ++++++++++++++++++++++++--- io_uring/tctx.h | 4 ++-- 5 files changed, 36 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 4927bb69387a..d7ae81b10893 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -140,9 +140,12 @@ enum { * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN. */ #define IORING_SETUP_TASKRUN_FLAG (1U << 9) - #define IORING_SETUP_SQE128 (1U << 10) /* SQEs are 128 byte */ #define IORING_SETUP_CQE32 (1U << 11) /* CQEs are 32 byte */ +/* + * Only one task is allowed to submit requests + */ +#define IORING_SETUP_SINGLE_ISSUER (1U << 12) enum io_uring_op { IORING_OP_NOP, diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 85a479594b05..06772139b7da 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2457,6 +2457,8 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) io_destroy_buffers(ctx); if (ctx->sq_creds) put_cred(ctx->sq_creds); + if (ctx->submitter_task) + put_task_struct(ctx->submitter_task); /* there are no registered resources left, nobody uses it */ if (ctx->rsrc_node) @@ -3189,7 +3191,7 @@ static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file) if (fd < 0) return fd; - ret = io_uring_add_tctx_node(ctx); + ret = __io_uring_add_tctx_node(ctx, false); if (ret) { put_unused_fd(fd); return ret; @@ -3409,7 +3411,8 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params) IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ | IORING_SETUP_R_DISABLED | IORING_SETUP_SUBMIT_ALL | IORING_SETUP_COOP_TASKRUN | IORING_SETUP_TASKRUN_FLAG | - IORING_SETUP_SQE128 | IORING_SETUP_CQE32)) + IORING_SETUP_SQE128 | IORING_SETUP_CQE32 | + IORING_SETUP_SINGLE_ISSUER)) return -EINVAL; return io_uring_create(entries, &p, params); diff --git a/io_uring/io_uring_types.h b/io_uring/io_uring_types.h index 1f8db2dd7af7..8b00243abf65 100644 --- a/io_uring/io_uring_types.h +++ b/io_uring/io_uring_types.h @@ -243,6 +243,7 @@ struct io_ring_ctx { /* Keep this last, we don't need it for the fast path */ struct io_restriction restrictions; + struct task_struct *submitter_task; /* slow path rsrc auxilary data, used by update/register */ struct io_rsrc_node *rsrc_backup_node; diff --git a/io_uring/tctx.c b/io_uring/tctx.c index 5a5d4f908529..a819da8fc85c 100644 --- a/io_uring/tctx.c +++ b/io_uring/tctx.c @@ -94,12 +94,32 @@ __cold int io_uring_alloc_task_context(struct task_struct *task, return 0; } -int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) +static int io_register_submitter(struct io_ring_ctx *ctx) +{ + int ret = 0; + + mutex_lock(&ctx->uring_lock); + if (!ctx->submitter_task) + ctx->submitter_task = get_task_struct(current); + else if (ctx->submitter_task != current) + ret = -EEXIST; + mutex_unlock(&ctx->uring_lock); + + return ret; +} + +int __io_uring_add_tctx_node(struct io_ring_ctx *ctx, bool submitter) { struct io_uring_task *tctx = current->io_uring; struct io_tctx_node *node; int ret; + if ((ctx->flags & IORING_SETUP_SINGLE_ISSUER) && submitter) { + ret = io_register_submitter(ctx); + if (ret) + return ret; + } + if (unlikely(!tctx)) { ret = io_uring_alloc_task_context(current, ctx); if (unlikely(ret)) @@ -133,7 +153,8 @@ int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) list_add(&node->ctx_node, &ctx->tctx_list); mutex_unlock(&ctx->uring_lock); } - tctx->last = ctx; + if (submitter) + tctx->last = ctx; return 0; } @@ -241,7 +262,7 @@ int io_ringfd_register(struct io_ring_ctx *ctx, void __user *__arg, return -EINVAL; mutex_unlock(&ctx->uring_lock); - ret = io_uring_add_tctx_node(ctx); + ret = __io_uring_add_tctx_node(ctx, false); mutex_lock(&ctx->uring_lock); if (ret) return ret; diff --git a/io_uring/tctx.h b/io_uring/tctx.h index 7684713e950f..dde82ce4d8e2 100644 --- a/io_uring/tctx.h +++ b/io_uring/tctx.h @@ -34,7 +34,7 @@ struct io_tctx_node { int io_uring_alloc_task_context(struct task_struct *task, struct io_ring_ctx *ctx); void io_uring_del_tctx_node(unsigned long index); -int __io_uring_add_tctx_node(struct io_ring_ctx *ctx); +int __io_uring_add_tctx_node(struct io_ring_ctx *ctx, bool submitter); void io_uring_clean_tctx(struct io_uring_task *tctx); void io_uring_unreg_ringfd(void); @@ -52,5 +52,5 @@ static inline int io_uring_add_tctx_node(struct io_ring_ctx *ctx) if (likely(tctx && tctx->last == ctx)) return 0; - return __io_uring_add_tctx_node(ctx); + return __io_uring_add_tctx_node(ctx, true); } -- cgit From 7d8ca7250197096bfa9f432c1d99b0555504bbba Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 18 Jun 2022 09:47:04 -0600 Subject: io_uring: add IORING_ASYNC_CANCEL_FD_FIXED cancel flag In preparation for not having a request to pass in that carries this state, add a separate cancelation flag that allows the caller to ask for a fixed file for cancelation. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 ++ io_uring/cancel.c | 9 ++++++--- 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index d7ae81b10893..a09a78bd7556 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -247,10 +247,12 @@ enum io_uring_op { * IORING_ASYNC_CANCEL_FD Key off 'fd' for cancelation rather than the * request 'user_data' * IORING_ASYNC_CANCEL_ANY Match any request + * IORING_ASYNC_CANCEL_FD_FIXED 'fd' passed in is a fixed descriptor */ #define IORING_ASYNC_CANCEL_ALL (1U << 0) #define IORING_ASYNC_CANCEL_FD (1U << 1) #define IORING_ASYNC_CANCEL_ANY (1U << 2) +#define IORING_ASYNC_CANCEL_FD_FIXED (1U << 3) /* * send/sendmsg and recv/recvmsg flags (sqe->ioprio) diff --git a/io_uring/cancel.c b/io_uring/cancel.c index 500ee5f5fd23..da486de07029 100644 --- a/io_uring/cancel.c +++ b/io_uring/cancel.c @@ -24,7 +24,7 @@ struct io_cancel { }; #define CANCEL_FLAGS (IORING_ASYNC_CANCEL_ALL | IORING_ASYNC_CANCEL_FD | \ - IORING_ASYNC_CANCEL_ANY) + IORING_ASYNC_CANCEL_ANY | IORING_ASYNC_CANCEL_FD_FIXED) static bool io_cancel_cb(struct io_wq_work *work, void *data) { @@ -174,11 +174,14 @@ int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) int ret; if (cd.flags & IORING_ASYNC_CANCEL_FD) { - if (req->flags & REQ_F_FIXED_FILE) + if (req->flags & REQ_F_FIXED_FILE || + cd.flags & IORING_ASYNC_CANCEL_FD_FIXED) { + req->flags |= REQ_F_FIXED_FILE; req->file = io_file_get_fixed(req, cancel->fd, issue_flags); - else + } else { req->file = io_file_get_normal(req, cancel->fd); + } if (!req->file) { ret = -EBADF; goto done; -- cgit From 78a861b9495920f8609dee5b670dacbff09d359f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 18 Jun 2022 10:00:50 -0600 Subject: io_uring: add sync cancelation API through io_uring_register() The io_uring cancelation API is async, like any other API that we expose there. For the case of finding a request to cancel, or not finding one, it is fully sync in that when submission returns, the CQE for both the cancelation request and the targeted request have been posted to the CQ ring. However, if the targeted work is being executed by io-wq, the API can only start the act of canceling it. This makes it difficult to use in some circumstances, as the caller then has to wait for the CQEs to come in and match on the same cancelation data there. Provide a IORING_REGISTER_SYNC_CANCEL command for io_uring_register() that does sync cancelations, always. For the io-wq case, it'll wait for the cancelation to come in before returning. The only expected returns from this API is: 0 Request found and canceled fine. > 0 Requests found and canceled. Only happens if asked to cancel multiple requests, and if the work wasn't in progress. -ENOENT Request not found. -ETIME A timeout on the operation was requested, but the timeout expired before we could cancel. and we won't get -EALREADY via this API. If the timeout value passed in is -1 (tv_sec and tv_nsec), then that means that no timeout is requested. Otherwise, the timespec passed in is the amount of time the sync cancel will wait for a successful cancelation. Link: https://github.com/axboe/liburing/discussions/608 Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 15 ++++++ io_uring/cancel.c | 107 ++++++++++++++++++++++++++++++++++++++++++ io_uring/cancel.h | 2 + io_uring/io_uring.c | 6 +++ 4 files changed, 130 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index a09a78bd7556..094f706c93e0 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -10,6 +10,7 @@ #include #include +#include /* * IO submission data structure (Submission Queue Entry) @@ -428,6 +429,9 @@ enum { IORING_REGISTER_PBUF_RING = 22, IORING_UNREGISTER_PBUF_RING = 23, + /* sync cancelation API */ + IORING_REGISTER_SYNC_CANCEL = 24, + /* this goes last */ IORING_REGISTER_LAST }; @@ -563,4 +567,15 @@ struct io_uring_getevents_arg { __u64 ts; }; +/* + * Argument for IORING_REGISTER_SYNC_CANCEL + */ +struct io_uring_sync_cancel_reg { + __u64 addr; + __s32 fd; + __u32 flags; + struct __kernel_timespec timeout; + __u64 pad[4]; +}; + #endif diff --git a/io_uring/cancel.c b/io_uring/cancel.c index da486de07029..8435a1eba59a 100644 --- a/io_uring/cancel.c +++ b/io_uring/cancel.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include @@ -206,3 +207,109 @@ void init_hash_table(struct io_hash_table *table, unsigned size) INIT_HLIST_HEAD(&table->hbs[i].list); } } + +static int __io_sync_cancel(struct io_uring_task *tctx, + struct io_cancel_data *cd, int fd) +{ + struct io_ring_ctx *ctx = cd->ctx; + + /* fixed must be grabbed every time since we drop the uring_lock */ + if ((cd->flags & IORING_ASYNC_CANCEL_FD) && + (cd->flags & IORING_ASYNC_CANCEL_FD_FIXED)) { + unsigned long file_ptr; + + if (unlikely(fd > ctx->nr_user_files)) + return -EBADF; + fd = array_index_nospec(fd, ctx->nr_user_files); + file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; + cd->file = (struct file *) (file_ptr & FFS_MASK); + if (!cd->file) + return -EBADF; + } + + return __io_async_cancel(cd, tctx, 0); +} + +int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg) + __must_hold(&ctx->uring_lock) +{ + struct io_cancel_data cd = { + .ctx = ctx, + .seq = atomic_inc_return(&ctx->cancel_seq), + }; + ktime_t timeout = KTIME_MAX; + struct io_uring_sync_cancel_reg sc; + struct fd f = { }; + DEFINE_WAIT(wait); + int ret; + + if (copy_from_user(&sc, arg, sizeof(sc))) + return -EFAULT; + if (sc.flags & ~CANCEL_FLAGS) + return -EINVAL; + if (sc.pad[0] || sc.pad[1] || sc.pad[2] || sc.pad[3]) + return -EINVAL; + + cd.data = sc.addr; + cd.flags = sc.flags; + + /* we can grab a normal file descriptor upfront */ + if ((cd.flags & IORING_ASYNC_CANCEL_FD) && + !(cd.flags & IORING_ASYNC_CANCEL_FD_FIXED)) { + f = fdget(sc.fd); + if (!f.file) + return -EBADF; + cd.file = f.file; + } + + ret = __io_sync_cancel(current->io_uring, &cd, sc.fd); + + /* found something, done! */ + if (ret != -EALREADY) + goto out; + + if (sc.timeout.tv_sec != -1UL || sc.timeout.tv_nsec != -1UL) { + struct timespec64 ts = { + .tv_sec = sc.timeout.tv_sec, + .tv_nsec = sc.timeout.tv_nsec + }; + + timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); + } + + /* + * Keep looking until we get -ENOENT. we'll get woken everytime + * every time a request completes and will retry the cancelation. + */ + do { + cd.seq = atomic_inc_return(&ctx->cancel_seq); + + prepare_to_wait(&ctx->cq_wait, &wait, TASK_INTERRUPTIBLE); + + ret = __io_sync_cancel(current->io_uring, &cd, sc.fd); + + if (ret != -EALREADY) + break; + + mutex_unlock(&ctx->uring_lock); + ret = io_run_task_work_sig(); + if (ret < 0) { + mutex_lock(&ctx->uring_lock); + break; + } + ret = schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS); + mutex_lock(&ctx->uring_lock); + if (!ret) { + ret = -ETIME; + break; + } + } while (1); + + finish_wait(&ctx->cq_wait, &wait); + + if (ret == -ENOENT || ret > 0) + ret = 0; +out: + fdput(f); + return ret; +} diff --git a/io_uring/cancel.h b/io_uring/cancel.h index 1bc7e917ce94..6a59ee484d0c 100644 --- a/io_uring/cancel.h +++ b/io_uring/cancel.h @@ -19,3 +19,5 @@ int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags); int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd, unsigned int issue_flags); void init_hash_table(struct io_hash_table *table, unsigned size); + +int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 997b915a1ff7..45538b3c3a76 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3871,6 +3871,12 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_unregister_pbuf_ring(ctx, arg); break; + case IORING_REGISTER_SYNC_CANCEL: + ret = -EINVAL; + if (!arg || nr_args != 1) + break; + ret = io_sync_cancel(ctx, arg); + break; default: ret = -EINVAL; break; -- cgit From 8fcf4c48f44bd7b1b75db139f56ff1ad6477379e Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 28 Jun 2022 21:33:20 +0200 Subject: io_uring: replace zero-length array with flexible-array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://www.kernel.org/doc/html/v5.16/process/deprecated.html#zero-length-and-one-element-arrays Link: https://github.com/KSPP/linux/issues/78 Signed-off-by: Gustavo A. R. Silva Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 094f706c93e0..8fe0275cdaf3 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -495,7 +495,7 @@ struct io_uring_probe { __u8 ops_len; /* length of ops[] array below */ __u16 resv; __u32 resv2[3]; - struct io_uring_probe_op ops[0]; + struct io_uring_probe_op ops[]; }; struct io_uring_restriction { -- cgit From e6130eba8a848a7a6ba6c534bd8f6d60749ae1a9 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 13 Jun 2022 04:47:02 -0600 Subject: io_uring: add support for passing fixed file descriptors With IORING_OP_MSG_RING, one ring can send a message to another ring. Extend that support to also allow sending a fixed file descriptor to that ring, enabling one ring to pass a registered descriptor to another one. Arguments are extended to pass in: sqe->addr3 fixed file slot in source ring sqe->file_index fixed file slot in destination ring IORING_OP_MSG_RING is extended to take a command argument in sqe->addr. If set to zero (or IORING_MSG_DATA), it sends just a message like before. If set to IORING_MSG_SEND_FD, a fixed file descriptor is sent according to the above arguments. Two common use cases for this are: 1) Server needs to be shutdown or restarted, pass file descriptors to another onei 2) Backend is split, and one accepts connections, while others then get the fd passed and handle the actual connection. Both of those are classic SCM_RIGHTS use cases, and it's not possible to support them with direct descriptors today. By default, this will post a CQE to the target ring, similarly to how IORING_MSG_DATA does it. If IORING_MSG_RING_CQE_SKIP is set, no message is posted to the target ring. The issuer is expected to notify the receiver side separately. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 17 ++++++ io_uring/msg_ring.c | 130 +++++++++++++++++++++++++++++++++++++++--- 2 files changed, 140 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 8fe0275cdaf3..f378eabbff21 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -51,6 +51,7 @@ struct io_uring_sqe { __u32 unlink_flags; __u32 hardlink_flags; __u32 xattr_flags; + __u32 msg_ring_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -270,6 +271,22 @@ enum io_uring_op { */ #define IORING_ACCEPT_MULTISHOT (1U << 0) +/* + * IORING_OP_MSG_RING command types, stored in sqe->addr + */ +enum { + IORING_MSG_DATA, /* pass sqe->len as 'res' and off as user_data */ + IORING_MSG_SEND_FD, /* send a registered fd to another ring */ +}; + +/* + * IORING_OP_MSG_RING flags (sqe->msg_ring_flags) + * + * IORING_MSG_RING_CQE_SKIP Don't post a CQE to the target ring. Not + * applicable for IORING_MSG_DATA, obviously. + */ +#define IORING_MSG_RING_CQE_SKIP (1U << 0) + /* * IO completion data structure (Completion Queue Entry) */ diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index b02be2349652..939205b30c8b 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -3,46 +3,162 @@ #include #include #include +#include #include #include #include "io_uring.h" +#include "rsrc.h" +#include "filetable.h" #include "msg_ring.h" struct io_msg { struct file *file; u64 user_data; u32 len; + u32 cmd; + u32 src_fd; + u32 dst_fd; + u32 flags; }; +static int io_msg_ring_data(struct io_kiocb *req) +{ + struct io_ring_ctx *target_ctx = req->file->private_data; + struct io_msg *msg = io_kiocb_to_cmd(req); + + if (msg->src_fd || msg->dst_fd || msg->flags) + return -EINVAL; + + if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0)) + return 0; + + return -EOVERFLOW; +} + +static void io_double_unlock_ctx(struct io_ring_ctx *ctx, + struct io_ring_ctx *octx, + unsigned int issue_flags) +{ + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_unlock(&ctx->uring_lock); + mutex_unlock(&octx->uring_lock); +} + +static int io_double_lock_ctx(struct io_ring_ctx *ctx, + struct io_ring_ctx *octx, + unsigned int issue_flags) +{ + /* + * To ensure proper ordering between the two ctxs, we can only + * attempt a trylock on the target. If that fails and we already have + * the source ctx lock, punt to io-wq. + */ + if (!(issue_flags & IO_URING_F_UNLOCKED)) { + if (!mutex_trylock(&octx->uring_lock)) + return -EAGAIN; + return 0; + } + + /* Always grab smallest value ctx first. We know ctx != octx. */ + if (ctx < octx) { + mutex_lock(&ctx->uring_lock); + mutex_lock(&octx->uring_lock); + } else { + mutex_lock(&octx->uring_lock); + mutex_lock(&ctx->uring_lock); + } + + return 0; +} + +static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *target_ctx = req->file->private_data; + struct io_msg *msg = io_kiocb_to_cmd(req); + struct io_ring_ctx *ctx = req->ctx; + unsigned long file_ptr; + struct file *src_file; + int ret; + + if (target_ctx == ctx) + return -EINVAL; + + ret = io_double_lock_ctx(ctx, target_ctx, issue_flags); + if (unlikely(ret)) + return ret; + + ret = -EBADF; + if (unlikely(msg->src_fd >= ctx->nr_user_files)) + goto out_unlock; + + msg->src_fd = array_index_nospec(msg->src_fd, ctx->nr_user_files); + file_ptr = io_fixed_file_slot(&ctx->file_table, msg->src_fd)->file_ptr; + src_file = (struct file *) (file_ptr & FFS_MASK); + get_file(src_file); + + ret = __io_fixed_fd_install(target_ctx, src_file, msg->dst_fd); + if (ret < 0) { + fput(src_file); + goto out_unlock; + } + + if (msg->flags & IORING_MSG_RING_CQE_SKIP) + goto out_unlock; + + /* + * If this fails, the target still received the file descriptor but + * wasn't notified of the fact. This means that if this request + * completes with -EOVERFLOW, then the sender must ensure that a + * later IORING_OP_MSG_RING delivers the message. + */ + if (!io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0)) + ret = -EOVERFLOW; +out_unlock: + io_double_unlock_ctx(ctx, target_ctx, issue_flags); + return ret; +} + int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_msg *msg = io_kiocb_to_cmd(req); - if (unlikely(sqe->addr || sqe->rw_flags || sqe->splice_fd_in || - sqe->buf_index || sqe->personality)) + if (unlikely(sqe->buf_index || sqe->personality)) return -EINVAL; msg->user_data = READ_ONCE(sqe->off); msg->len = READ_ONCE(sqe->len); + msg->cmd = READ_ONCE(sqe->addr); + msg->src_fd = READ_ONCE(sqe->addr3); + msg->dst_fd = READ_ONCE(sqe->file_index); + msg->flags = READ_ONCE(sqe->msg_ring_flags); + if (msg->flags & ~IORING_MSG_RING_CQE_SKIP) + return -EINVAL; + return 0; } int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags) { struct io_msg *msg = io_kiocb_to_cmd(req); - struct io_ring_ctx *target_ctx; int ret; ret = -EBADFD; if (!io_is_uring_fops(req->file)) goto done; - ret = -EOVERFLOW; - target_ctx = req->file->private_data; - if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0)) - ret = 0; + switch (msg->cmd) { + case IORING_MSG_DATA: + ret = io_msg_ring_data(req); + break; + case IORING_MSG_SEND_FD: + ret = io_msg_send_fd(req, issue_flags); + break; + default: + ret = -EINVAL; + break; + } done: if (ret < 0) -- cgit From 6e73dffbb93cb8797cd4e42e98d837edf0f1a967 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 25 Jun 2022 11:55:38 +0100 Subject: io_uring: let to set a range for file slot allocation From recently io_uring provides an option to allocate a file index for operation registering fixed files. However, it's utterly unusable with mixed approaches when for a part of files the userspace knows better where to place it, as it may race and users don't have any sane way to pick a slot and hoping it will not be taken. Let the userspace to register a range of fixed file slots in which the auto-allocation happens. The use case is splittting the fixed table in two parts, where on of them is used for auto-allocation and another for slot-specified operations. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/66ab0394e436f38437cf7c44676e1920d09687ad.1656154403.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 3 +++ include/uapi/linux/io_uring.h | 13 +++++++++++++ io_uring/filetable.c | 24 ++++++++++++++++++++---- io_uring/filetable.h | 20 +++++++++++++++++--- io_uring/io_uring.c | 6 ++++++ io_uring/rsrc.c | 2 ++ 6 files changed, 61 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 3ca8f363f504..26ef11e978d4 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -233,6 +233,9 @@ struct io_ring_ctx { unsigned long check_cq; + unsigned int file_alloc_start; + unsigned int file_alloc_end; + struct { /* * We cache a range of free CQEs we can use, once exhausted it diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index f378eabbff21..cf95354198a3 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -449,6 +449,9 @@ enum { /* sync cancelation API */ IORING_REGISTER_SYNC_CANCEL = 24, + /* register a range of fixed file slots for automatic slot allocation */ + IORING_REGISTER_FILE_ALLOC_RANGE = 25, + /* this goes last */ IORING_REGISTER_LAST }; @@ -595,4 +598,14 @@ struct io_uring_sync_cancel_reg { __u64 pad[4]; }; +/* + * Argument for IORING_REGISTER_FILE_ALLOC_RANGE + * The range is specified as [off, off + len) + */ +struct io_uring_file_index_range { + __u32 off; + __u32 len; + __u64 resv; +}; + #endif diff --git a/io_uring/filetable.c b/io_uring/filetable.c index abaa5ba7f655..7b473259f3f4 100644 --- a/io_uring/filetable.c +++ b/io_uring/filetable.c @@ -16,7 +16,7 @@ static int io_file_bitmap_get(struct io_ring_ctx *ctx) { struct io_file_table *table = &ctx->file_table; - unsigned long nr = ctx->nr_user_files; + unsigned long nr = ctx->file_alloc_end; int ret; do { @@ -24,11 +24,10 @@ static int io_file_bitmap_get(struct io_ring_ctx *ctx) if (ret != nr) return ret; - if (!table->alloc_hint) + if (table->alloc_hint == ctx->file_alloc_start) break; - nr = table->alloc_hint; - table->alloc_hint = 0; + table->alloc_hint = ctx->file_alloc_start; } while (1); return -ENFILE; @@ -175,3 +174,20 @@ int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset) io_rsrc_node_switch(ctx, ctx->file_data); return 0; } + +int io_register_file_alloc_range(struct io_ring_ctx *ctx, + struct io_uring_file_index_range __user *arg) +{ + struct io_uring_file_index_range range; + u32 end; + + if (copy_from_user(&range, arg, sizeof(range))) + return -EFAULT; + if (check_add_overflow(range.off, range.len, &end)) + return -EOVERFLOW; + if (range.resv || end > ctx->nr_user_files) + return -EINVAL; + + io_file_table_set_alloc_range(ctx, range.off, range.len); + return 0; +} diff --git a/io_uring/filetable.h b/io_uring/filetable.h index 79eb50c1980e..ff3a712e11bf 100644 --- a/io_uring/filetable.h +++ b/io_uring/filetable.h @@ -3,9 +3,7 @@ #define IOU_FILE_TABLE_H #include - -struct io_ring_ctx; -struct io_kiocb; +#include /* * FFS_SCM is only available on 64-bit archs, for 32-bit we just define it as 0 @@ -33,6 +31,9 @@ int __io_fixed_fd_install(struct io_ring_ctx *ctx, struct file *file, unsigned int file_slot); int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset); +int io_register_file_alloc_range(struct io_ring_ctx *ctx, + struct io_uring_file_index_range __user *arg); + unsigned int io_file_get_flags(struct file *file); static inline void io_file_bitmap_clear(struct io_file_table *table, int bit) @@ -71,4 +72,17 @@ static inline void io_fixed_file_set(struct io_fixed_file *file_slot, file_slot->file_ptr = file_ptr; } +static inline void io_reset_alloc_hint(struct io_ring_ctx *ctx) +{ + ctx->file_table.alloc_hint = ctx->file_alloc_start; +} + +static inline void io_file_table_set_alloc_range(struct io_ring_ctx *ctx, + unsigned off, unsigned len) +{ + ctx->file_alloc_start = off; + ctx->file_alloc_end = off + len; + io_reset_alloc_hint(ctx); +} + #endif diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 070ee9ec9ee7..745264938a48 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3866,6 +3866,12 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_sync_cancel(ctx, arg); break; + case IORING_REGISTER_FILE_ALLOC_RANGE: + ret = -EINVAL; + if (!arg || nr_args) + break; + ret = io_register_file_alloc_range(ctx, arg); + break; default: ret = -EINVAL; break; diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 706fa020505b..d2e589c703d0 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -1012,6 +1012,8 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, io_file_bitmap_set(&ctx->file_table, i); } + /* default it to the whole table */ + io_file_table_set_alloc_range(ctx, 0, ctx->nr_user_files); io_rsrc_node_switch(ctx, NULL); return 0; fail: -- cgit From b3fdea6ecb55c3ceea866ff66486927e51a982b3 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Thu, 30 Jun 2022 02:12:29 -0700 Subject: io_uring: multishot recv Support multishot receive for io_uring. Typical server applications will run a loop where for each recv CQE it requeues another recv/recvmsg. This can be simplified by using the existing multishot functionality combined with io_uring's provided buffers. The API is to add the IORING_RECV_MULTISHOT flag to the SQE. CQEs will then be posted (with IORING_CQE_F_MORE flag set) when data is available and is read. Once an error occurs or the socket ends, the multishot will be removed and a completion without IORING_CQE_F_MORE will be posted. The benefit to this is that the recv is much more performant. * Subsequent receives are queued up straight away without requiring the application to finish a processing loop. * If there are more data in the socket (sat the provided buffer size is smaller than the socket buffer) then the data is immediately returned, improving batching. * Poll is only armed once and reused, saving CPU cycles Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220630091231.1456789-11-dylany@fb.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 5 +++ io_uring/net.c | 102 ++++++++++++++++++++++++++++++++++++------ 2 files changed, 94 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index cf95354198a3..499679134961 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -263,8 +263,13 @@ enum io_uring_op { * or receive and arm poll if that yields an * -EAGAIN result, arm poll upfront and skip * the initial transfer attempt. + * + * IORING_RECV_MULTISHOT Multishot recv. Sets IORING_CQE_F_MORE if + * the handler will continue to report + * CQEs on behalf of the same SQE. */ #define IORING_RECVSEND_POLL_FIRST (1U << 0) +#define IORING_RECV_MULTISHOT (1U << 1) /* * accept flags stored in sqe->ioprio diff --git a/io_uring/net.c b/io_uring/net.c index e1eaf902f3b2..cb08a4b62840 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -389,6 +389,8 @@ int io_recvmsg_prep_async(struct io_kiocb *req) return ret; } +#define RECVMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECV_MULTISHOT) + int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sr_msg *sr = io_kiocb_to_cmd(req); @@ -399,13 +401,22 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); sr->flags = READ_ONCE(sqe->ioprio); - if (sr->flags & ~IORING_RECVSEND_POLL_FIRST) + if (sr->flags & ~(RECVMSG_FLAGS)) return -EINVAL; sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; if (sr->msg_flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; if (sr->msg_flags & MSG_ERRQUEUE) req->flags |= REQ_F_CLEAR_POLLIN; + if (sr->flags & IORING_RECV_MULTISHOT) { + if (!(req->flags & REQ_F_BUFFER_SELECT)) + return -EINVAL; + if (sr->msg_flags & MSG_WAITALL) + return -EINVAL; + if (req->opcode == IORING_OP_RECV && sr->len) + return -EINVAL; + req->flags |= REQ_F_APOLL_MULTISHOT; + } #ifdef CONFIG_COMPAT if (req->ctx->compat) @@ -415,6 +426,48 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } +static inline void io_recv_prep_retry(struct io_kiocb *req) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req); + + sr->done_io = 0; + sr->len = 0; /* get from the provided buffer */ +} + +/* + * Finishes io_recv and io_recvmsg. + * + * Returns true if it is actually finished, or false if it should run + * again (for multishot). + */ +static inline bool io_recv_finish(struct io_kiocb *req, int *ret, unsigned int cflags) +{ + if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { + io_req_set_res(req, *ret, cflags); + *ret = IOU_OK; + return true; + } + + if (*ret > 0) { + if (io_post_aux_cqe(req->ctx, req->cqe.user_data, *ret, + cflags | IORING_CQE_F_MORE, false)) { + io_recv_prep_retry(req); + return false; + } + /* + * Otherwise stop multishot but use the current result. + * Probably will end up going into overflow, but this means + * we cannot trust the ordering anymore + */ + } + + io_req_set_res(req, *ret, cflags); + + if (req->flags & REQ_F_POLLED) + *ret = IOU_STOP_MULTISHOT; + return true; +} + int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_sr_msg *sr = io_kiocb_to_cmd(req); @@ -424,6 +477,7 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) unsigned flags; int ret, min_ret = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + size_t len = sr->len; sock = sock_from_file(req->file); if (unlikely(!sock)) @@ -442,16 +496,17 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) (sr->flags & IORING_RECVSEND_POLL_FIRST)) return io_setup_async_msg(req, kmsg); +retry_multishot: if (io_do_buffer_select(req)) { void __user *buf; - buf = io_buffer_select(req, &sr->len, issue_flags); + buf = io_buffer_select(req, &len, issue_flags); if (!buf) return -ENOBUFS; kmsg->fast_iov[0].iov_base = buf; - kmsg->fast_iov[0].iov_len = sr->len; + kmsg->fast_iov[0].iov_len = len; iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, 1, - sr->len); + len); } flags = sr->msg_flags; @@ -463,8 +518,15 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) kmsg->msg.msg_get_inq = 1; ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, kmsg->uaddr, flags); if (ret < min_ret) { - if (ret == -EAGAIN && force_nonblock) - return io_setup_async_msg(req, kmsg); + if (ret == -EAGAIN && force_nonblock) { + ret = io_setup_async_msg(req, kmsg); + if (ret == -EAGAIN && (req->flags & IO_APOLL_MULTI_POLLED) == + IO_APOLL_MULTI_POLLED) { + io_kbuf_recycle(req, issue_flags); + return IOU_ISSUE_SKIP_COMPLETE; + } + return ret; + } if (ret == -ERESTARTSYS) ret = -EINTR; if (ret > 0 && io_net_retry(sock, flags)) { @@ -491,8 +553,11 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) cflags = io_put_kbuf(req, issue_flags); if (kmsg->msg.msg_inq) cflags |= IORING_CQE_F_SOCK_NONEMPTY; - io_req_set_res(req, ret, cflags); - return IOU_OK; + + if (!io_recv_finish(req, &ret, cflags)) + goto retry_multishot; + + return ret; } int io_recv(struct io_kiocb *req, unsigned int issue_flags) @@ -505,6 +570,7 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags) unsigned flags; int ret, min_ret = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + size_t len = sr->len; if (!(req->flags & REQ_F_POLLED) && (sr->flags & IORING_RECVSEND_POLL_FIRST)) @@ -514,16 +580,17 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags) if (unlikely(!sock)) return -ENOTSOCK; +retry_multishot: if (io_do_buffer_select(req)) { void __user *buf; - buf = io_buffer_select(req, &sr->len, issue_flags); + buf = io_buffer_select(req, &len, issue_flags); if (!buf) return -ENOBUFS; sr->buf = buf; } - ret = import_single_range(READ, sr->buf, sr->len, &iov, &msg.msg_iter); + ret = import_single_range(READ, sr->buf, len, &iov, &msg.msg_iter); if (unlikely(ret)) goto out_free; @@ -543,8 +610,14 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags) ret = sock_recvmsg(sock, &msg, flags); if (ret < min_ret) { - if (ret == -EAGAIN && force_nonblock) + if (ret == -EAGAIN && force_nonblock) { + if ((req->flags & IO_APOLL_MULTI_POLLED) == IO_APOLL_MULTI_POLLED) { + io_kbuf_recycle(req, issue_flags); + return IOU_ISSUE_SKIP_COMPLETE; + } + return -EAGAIN; + } if (ret == -ERESTARTSYS) ret = -EINTR; if (ret > 0 && io_net_retry(sock, flags)) { @@ -570,8 +643,11 @@ out_free: cflags = io_put_kbuf(req, issue_flags); if (msg.msg_inq) cflags |= IORING_CQE_F_SOCK_NONEMPTY; - io_req_set_res(req, ret, cflags); - return IOU_OK; + + if (!io_recv_finish(req, &ret, cflags)) + goto retry_multishot; + + return ret; } int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -- cgit From 9bb66906f23e50d6db1e11f7498b72dfca1982a2 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Thu, 14 Jul 2022 04:02:58 -0700 Subject: io_uring: support multishot in recvmsg Similar to multishot recv, this will require provided buffers to be used. However recvmsg is much more complex than recv as it has multiple outputs. Specifically flags, name, and control messages. Support this by introducing a new struct io_uring_recvmsg_out with 4 fields. namelen, controllen and flags match the similar out fields in msghdr from standard recvmsg(2), payloadlen is the length of the payload following the header. This struct is placed at the start of the returned buffer. Based on what the user specifies in struct msghdr, the next bytes of the buffer will be name (the next msg_namelen bytes), and then control (the next msg_controllen bytes). The payload will come at the end. The return value in the CQE is the total used size of the provided buffer. Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220714110258.1336200-4-dylany@fb.com [axboe: style fixups, see link] Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 7 ++ io_uring/net.c | 180 +++++++++++++++++++++++++++++++++++++----- io_uring/net.h | 6 ++ 3 files changed, 174 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 499679134961..4c9b11e2e991 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -613,4 +613,11 @@ struct io_uring_file_index_range { __u64 resv; }; +struct io_uring_recvmsg_out { + __u32 namelen; + __u32 controllen; + __u32 payloadlen; + __u32 flags; +}; + #endif diff --git a/io_uring/net.c b/io_uring/net.c index 5bc3440a8290..616d5f04cc74 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -325,6 +325,21 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags) return IOU_OK; } +static bool io_recvmsg_multishot_overflow(struct io_async_msghdr *iomsg) +{ + unsigned long hdr; + + if (check_add_overflow(sizeof(struct io_uring_recvmsg_out), + (unsigned long)iomsg->namelen, &hdr)) + return true; + if (check_add_overflow(hdr, iomsg->controllen, &hdr)) + return true; + if (hdr > INT_MAX) + return true; + + return false; +} + static int __io_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { @@ -352,6 +367,13 @@ static int __io_recvmsg_copy_hdr(struct io_kiocb *req, sr->len = iomsg->fast_iov[0].iov_len; iomsg->free_iov = NULL; } + + if (req->flags & REQ_F_APOLL_MULTISHOT) { + iomsg->namelen = msg.msg_namelen; + iomsg->controllen = msg.msg_controllen; + if (io_recvmsg_multishot_overflow(iomsg)) + return -EOVERFLOW; + } } else { iomsg->free_iov = iomsg->fast_iov; ret = __import_iovec(READ, msg.msg_iov, msg.msg_iovlen, UIO_FASTIOV, @@ -399,6 +421,13 @@ static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req, sr->len = clen; iomsg->free_iov = NULL; } + + if (req->flags & REQ_F_APOLL_MULTISHOT) { + iomsg->namelen = msg.msg_namelen; + iomsg->controllen = msg.msg_controllen; + if (io_recvmsg_multishot_overflow(iomsg)) + return -EOVERFLOW; + } } else { iomsg->free_iov = iomsg->fast_iov; ret = __import_iovec(READ, (struct iovec __user *)uiov, msg.msg_iovlen, @@ -455,8 +484,6 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (sr->msg_flags & MSG_ERRQUEUE) req->flags |= REQ_F_CLEAR_POLLIN; if (sr->flags & IORING_RECV_MULTISHOT) { - if (req->opcode == IORING_OP_RECVMSG) - return -EINVAL; if (!(req->flags & REQ_F_BUFFER_SELECT)) return -EINVAL; if (sr->msg_flags & MSG_WAITALL) @@ -483,12 +510,13 @@ static inline void io_recv_prep_retry(struct io_kiocb *req) } /* - * Finishes io_recv + * Finishes io_recv and io_recvmsg. * * Returns true if it is actually finished, or false if it should run * again (for multishot). */ -static inline bool io_recv_finish(struct io_kiocb *req, int *ret, unsigned int cflags) +static inline bool io_recv_finish(struct io_kiocb *req, int *ret, + unsigned int cflags, bool mshot_finished) { if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { io_req_set_res(req, *ret, cflags); @@ -496,7 +524,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, unsigned int c return true; } - if (*ret > 0) { + if (!mshot_finished) { if (io_post_aux_cqe(req->ctx, req->cqe.user_data, *ret, cflags | IORING_CQE_F_MORE, false)) { io_recv_prep_retry(req); @@ -518,6 +546,90 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, unsigned int c return true; } +static int io_recvmsg_prep_multishot(struct io_async_msghdr *kmsg, + struct io_sr_msg *sr, void __user **buf, + size_t *len) +{ + unsigned long ubuf = (unsigned long) *buf; + unsigned long hdr; + + hdr = sizeof(struct io_uring_recvmsg_out) + kmsg->namelen + + kmsg->controllen; + if (*len < hdr) + return -EFAULT; + + if (kmsg->controllen) { + unsigned long control = ubuf + hdr - kmsg->controllen; + + kmsg->msg.msg_control_user = (void *) control; + kmsg->msg.msg_controllen = kmsg->controllen; + } + + sr->buf = *buf; /* stash for later copy */ + *buf = (void *) (ubuf + hdr); + kmsg->payloadlen = *len = *len - hdr; + return 0; +} + +struct io_recvmsg_multishot_hdr { + struct io_uring_recvmsg_out msg; + struct sockaddr_storage addr; +}; + +static int io_recvmsg_multishot(struct socket *sock, struct io_sr_msg *io, + struct io_async_msghdr *kmsg, + unsigned int flags, bool *finished) +{ + int err; + int copy_len; + struct io_recvmsg_multishot_hdr hdr; + + if (kmsg->namelen) + kmsg->msg.msg_name = &hdr.addr; + kmsg->msg.msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT); + kmsg->msg.msg_namelen = 0; + + if (sock->file->f_flags & O_NONBLOCK) + flags |= MSG_DONTWAIT; + + err = sock_recvmsg(sock, &kmsg->msg, flags); + *finished = err <= 0; + if (err < 0) + return err; + + hdr.msg = (struct io_uring_recvmsg_out) { + .controllen = kmsg->controllen - kmsg->msg.msg_controllen, + .flags = kmsg->msg.msg_flags & ~MSG_CMSG_COMPAT + }; + + hdr.msg.payloadlen = err; + if (err > kmsg->payloadlen) + err = kmsg->payloadlen; + + copy_len = sizeof(struct io_uring_recvmsg_out); + if (kmsg->msg.msg_namelen > kmsg->namelen) + copy_len += kmsg->namelen; + else + copy_len += kmsg->msg.msg_namelen; + + /* + * "fromlen shall refer to the value before truncation.." + * 1003.1g + */ + hdr.msg.namelen = kmsg->msg.msg_namelen; + + /* ensure that there is no gap between hdr and sockaddr_storage */ + BUILD_BUG_ON(offsetof(struct io_recvmsg_multishot_hdr, addr) != + sizeof(struct io_uring_recvmsg_out)); + if (copy_to_user(io->buf, &hdr, copy_len)) { + *finished = true; + return -EFAULT; + } + + return sizeof(struct io_uring_recvmsg_out) + kmsg->namelen + + kmsg->controllen + err; +} + int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_sr_msg *sr = io_kiocb_to_cmd(req); @@ -527,6 +639,7 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) unsigned flags; int ret, min_ret = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + bool mshot_finished = true; sock = sock_from_file(req->file); if (unlikely(!sock)) @@ -545,16 +658,27 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) (sr->flags & IORING_RECVSEND_POLL_FIRST)) return io_setup_async_msg(req, kmsg, issue_flags); +retry_multishot: if (io_do_buffer_select(req)) { void __user *buf; + size_t len = sr->len; - buf = io_buffer_select(req, &sr->len, issue_flags); + buf = io_buffer_select(req, &len, issue_flags); if (!buf) return -ENOBUFS; + + if (req->flags & REQ_F_APOLL_MULTISHOT) { + ret = io_recvmsg_prep_multishot(kmsg, sr, &buf, &len); + if (ret) { + io_kbuf_recycle(req, issue_flags); + return ret; + } + } + kmsg->fast_iov[0].iov_base = buf; - kmsg->fast_iov[0].iov_len = sr->len; + kmsg->fast_iov[0].iov_len = len; iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, 1, - sr->len); + len); } flags = sr->msg_flags; @@ -564,10 +688,23 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) min_ret = iov_iter_count(&kmsg->msg.msg_iter); kmsg->msg.msg_get_inq = 1; - ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, kmsg->uaddr, flags); + if (req->flags & REQ_F_APOLL_MULTISHOT) + ret = io_recvmsg_multishot(sock, sr, kmsg, flags, + &mshot_finished); + else + ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, + kmsg->uaddr, flags); + if (ret < min_ret) { - if (ret == -EAGAIN && force_nonblock) - return io_setup_async_msg(req, kmsg, issue_flags); + if (ret == -EAGAIN && force_nonblock) { + ret = io_setup_async_msg(req, kmsg, issue_flags); + if (ret == -EAGAIN && (req->flags & IO_APOLL_MULTI_POLLED) == + IO_APOLL_MULTI_POLLED) { + io_kbuf_recycle(req, issue_flags); + return IOU_ISSUE_SKIP_COMPLETE; + } + return ret; + } if (ret == -ERESTARTSYS) ret = -EINTR; if (ret > 0 && io_net_retry(sock, flags)) { @@ -580,11 +717,6 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) req_set_fail(req); } - /* fast path, check for non-NULL to avoid function call */ - if (kmsg->free_iov) - kfree(kmsg->free_iov); - io_netmsg_recycle(req, issue_flags); - req->flags &= ~REQ_F_NEED_CLEANUP; if (ret > 0) ret += sr->done_io; else if (sr->done_io) @@ -596,8 +728,18 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) if (kmsg->msg.msg_inq) cflags |= IORING_CQE_F_SOCK_NONEMPTY; - io_req_set_res(req, ret, cflags); - return IOU_OK; + if (!io_recv_finish(req, &ret, cflags, mshot_finished)) + goto retry_multishot; + + if (mshot_finished) { + io_netmsg_recycle(req, issue_flags); + /* fast path, check for non-NULL to avoid function call */ + if (kmsg->free_iov) + kfree(kmsg->free_iov); + req->flags &= ~REQ_F_NEED_CLEANUP; + } + + return ret; } int io_recv(struct io_kiocb *req, unsigned int issue_flags) @@ -684,7 +826,7 @@ out_free: if (msg.msg_inq) cflags |= IORING_CQE_F_SOCK_NONEMPTY; - if (!io_recv_finish(req, &ret, cflags)) + if (!io_recv_finish(req, &ret, cflags, ret <= 0)) goto retry_multishot; return ret; diff --git a/io_uring/net.h b/io_uring/net.h index 178a6d8b76e0..db20ce9d6546 100644 --- a/io_uring/net.h +++ b/io_uring/net.h @@ -9,6 +9,12 @@ struct io_async_msghdr { union { struct iovec fast_iov[UIO_FASTIOV]; + struct { + struct iovec fast_iov_one; + __kernel_size_t controllen; + int namelen; + __kernel_size_t payloadlen; + }; struct io_cache_entry cache; }; /* points to an allocated iov, if NULL we use fast_iov instead */ -- cgit