diff options
155 files changed, 1549 insertions, 914 deletions
diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 495e35fcfb21..ea21fe135b97 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -1753,6 +1753,7 @@ operations: request: attributes: - header + - context reply: attributes: - header @@ -1761,7 +1762,6 @@ operations: - indir - hkey - input_xfrm - dump: *rss-get-op - name: plca-get-cfg doc: Get PLCA params. diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 3ab423b80e91..d5f246aceb9f 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1875,6 +1875,7 @@ Kernel response contents: ===================================== ====== ========================== ``ETHTOOL_A_RSS_HEADER`` nested reply header + ``ETHTOOL_A_RSS_CONTEXT`` u32 context number ``ETHTOOL_A_RSS_HFUNC`` u32 RSS hash func ``ETHTOOL_A_RSS_INDIR`` binary Indir table bytes ``ETHTOOL_A_RSS_HKEY`` binary Hash key bytes diff --git a/MAINTAINERS b/MAINTAINERS index 42decde38320..8766f3e5e87e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15936,6 +15936,7 @@ F: include/linux/in.h F: include/linux/indirect_call_wrapper.h F: include/linux/net.h F: include/linux/netdevice.h +F: include/linux/skbuff.h F: include/net/ F: include/uapi/linux/in.h F: include/uapi/linux/net.h @@ -18556,7 +18557,7 @@ F: drivers/usb/misc/qcom_eud.c QCOM IPA DRIVER M: Alex Elder <[email protected]> -S: Supported +S: Maintained F: drivers/net/ipa/ QEMU MACHINE EMULATOR AND VIRTUALIZER SUPPORT diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 954a1916a500..54b2bb817a7f 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -87,6 +87,7 @@ config ARM select HAVE_ARCH_PFN_VALID select HAVE_ARCH_SECCOMP select HAVE_ARCH_SECCOMP_FILTER if AEABI && !OABI_COMPAT + select HAVE_ARCH_STACKLEAK select HAVE_ARCH_THREAD_STRUCT_WHITELIST select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE if ARM_LPAE @@ -116,6 +117,7 @@ config ARM select HAVE_KERNEL_XZ select HAVE_KPROBES if !XIP_KERNEL && !CPU_ENDIAN_BE32 && !CPU_V7M select HAVE_KRETPROBES if HAVE_KPROBES + select HAVE_LD_DEAD_CODE_DATA_ELIMINATION select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI select HAVE_OPTPROBES if !THUMB2_KERNEL @@ -736,7 +738,7 @@ config ARM_ERRATA_764319 bool "ARM errata: Read to DBGPRSR and DBGOSLSR may generate Undefined instruction" depends on CPU_V7 help - This option enables the workaround for the 764319 Cortex A-9 erratum. + This option enables the workaround for the 764319 Cortex-A9 erratum. CP14 read accesses to the DBGPRSR and DBGOSLSR registers generate an unexpected Undefined Instruction exception when the DBGSWENABLE external pin is set to 0, even when the CP14 accesses are performed diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 6bca03c0c7f0..945b5975fce2 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -9,6 +9,7 @@ OBJS = HEAD = head.o OBJS += misc.o decompress.o +CFLAGS_decompress.o += $(DISABLE_STACKLEAK_PLUGIN) ifeq ($(CONFIG_DEBUG_UNCOMPRESS),y) OBJS += debug.o AFLAGS_head.o += -DDEBUG diff --git a/arch/arm/boot/compressed/vmlinux.lds.S b/arch/arm/boot/compressed/vmlinux.lds.S index 3fcb3e62dc56..d411abd4310e 100644 --- a/arch/arm/boot/compressed/vmlinux.lds.S +++ b/arch/arm/boot/compressed/vmlinux.lds.S @@ -125,7 +125,7 @@ SECTIONS . = BSS_START; __bss_start = .; - .bss : { *(.bss) } + .bss : { *(.bss .bss.*) } _end = .; . = ALIGN(8); /* the stack must be 64-bit aligned */ diff --git a/arch/arm/include/asm/stacktrace.h b/arch/arm/include/asm/stacktrace.h index 360f0d2406bf..f80a85b091d6 100644 --- a/arch/arm/include/asm/stacktrace.h +++ b/arch/arm/include/asm/stacktrace.h @@ -26,6 +26,13 @@ struct stackframe { #endif }; +static inline bool on_thread_stack(void) +{ + unsigned long delta = current_stack_pointer ^ (unsigned long)current->stack; + + return delta < THREAD_SIZE; +} + static __always_inline void arm_get_current_stackframe(struct pt_regs *regs, struct stackframe *frame) { diff --git a/arch/arm/include/asm/vmlinux.lds.h b/arch/arm/include/asm/vmlinux.lds.h index 4c8632d5c432..d60f6e83a9f7 100644 --- a/arch/arm/include/asm/vmlinux.lds.h +++ b/arch/arm/include/asm/vmlinux.lds.h @@ -42,7 +42,7 @@ #define PROC_INFO \ . = ALIGN(4); \ __proc_info_begin = .; \ - *(.proc.info.init) \ + KEEP(*(.proc.info.init)) \ __proc_info_end = .; #define IDMAP_TEXT \ diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 6150a716828c..f01d23a220e6 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -1065,6 +1065,7 @@ vector_addrexcptn: .globl vector_fiq .section .vectors, "ax", %progbits + .reloc .text, R_ARM_NONE, . W(b) vector_rst W(b) vector_und ARM( .reloc ., R_ARM_LDR_PC_G0, .L__vector_swi ) @@ -1078,6 +1079,7 @@ THUMB( .reloc ., R_ARM_THM_PC12, .L__vector_swi ) #ifdef CONFIG_HARDEN_BRANCH_HISTORY .section .vectors.bhb.loop8, "ax", %progbits + .reloc .text, R_ARM_NONE, . W(b) vector_rst W(b) vector_bhb_loop8_und ARM( .reloc ., R_ARM_LDR_PC_G0, .L__vector_bhb_loop8_swi ) @@ -1090,6 +1092,7 @@ THUMB( .reloc ., R_ARM_THM_PC12, .L__vector_bhb_loop8_swi ) W(b) vector_bhb_loop8_fiq .section .vectors.bhb.bpiall, "ax", %progbits + .reloc .text, R_ARM_NONE, . W(b) vector_rst W(b) vector_bhb_bpiall_und ARM( .reloc ., R_ARM_LDR_PC_G0, .L__vector_bhb_bpiall_swi ) diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 5c31e9de7a60..f379c852dcb7 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -119,6 +119,9 @@ no_work_pending: ct_user_enter save = 0 +#ifdef CONFIG_GCC_PLUGIN_STACKLEAK + bl stackleak_erase_on_task_stack +#endif restore_user_regs fast = 0, offset = 0 ENDPROC(ret_to_user_from_irq) ENDPROC(ret_to_user) diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index 677f218f7e84..da488d92e7a0 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -395,11 +395,6 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, return 0; } -struct mod_unwind_map { - const Elf_Shdr *unw_sec; - const Elf_Shdr *txt_sec; -}; - static const Elf_Shdr *find_mod_section(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs, const char *name) { diff --git a/arch/arm/kernel/perf_callchain.c b/arch/arm/kernel/perf_callchain.c index 7147edbe56c6..1d230ac9d0eb 100644 --- a/arch/arm/kernel/perf_callchain.c +++ b/arch/arm/kernel/perf_callchain.c @@ -85,8 +85,7 @@ static bool callchain_trace(void *data, unsigned long pc) { struct perf_callchain_entry_ctx *entry = data; - perf_callchain_store(entry, pc); - return true; + return perf_callchain_store(entry, pc) == 0; } void diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S index c16d196b5aad..5eddb75a7174 100644 --- a/arch/arm/kernel/vmlinux-xip.lds.S +++ b/arch/arm/kernel/vmlinux-xip.lds.S @@ -63,7 +63,7 @@ SECTIONS . = ALIGN(4); __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) { __start___ex_table = .; - ARM_MMU_KEEP(*(__ex_table)) + ARM_MMU_KEEP(KEEP(*(__ex_table))) __stop___ex_table = .; } @@ -83,7 +83,7 @@ SECTIONS } .init.arch.info : { __arch_info_begin = .; - *(.arch.info.init) + KEEP(*(.arch.info.init)) __arch_info_end = .; } .init.tagtable : { diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index bd9127c4b451..de373c6c2ae8 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -74,7 +74,7 @@ SECTIONS . = ALIGN(4); __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) { __start___ex_table = .; - ARM_MMU_KEEP(*(__ex_table)) + ARM_MMU_KEEP(KEEP(*(__ex_table))) __stop___ex_table = .; } @@ -99,7 +99,7 @@ SECTIONS } .init.arch.info : { __arch_info_begin = .; - *(.arch.info.init) + KEEP(*(.arch.info.init)) __arch_info_end = .; } .init.tagtable : { @@ -116,7 +116,7 @@ SECTIONS #endif .init.pv_table : { __pv_table_begin = .; - *(.pv_table) + KEEP(*(.pv_table)) __pv_table_end = .; } diff --git a/arch/arm/mach-alpine/alpine_cpu_pm.c b/arch/arm/mach-alpine/alpine_cpu_pm.c index 13ae8412e9ce..b48da6f12b6c 100644 --- a/arch/arm/mach-alpine/alpine_cpu_pm.c +++ b/arch/arm/mach-alpine/alpine_cpu_pm.c @@ -29,7 +29,7 @@ int alpine_cpu_wakeup(unsigned int phys_cpu, uint32_t phys_resume_addr) /* * Set CPU resume address - * secure firmware running on boot will jump to this address - * after setting proper CPU mode, and initialiing e.g. secure + * after setting proper CPU mode, and initializing e.g. secure * regs (the same mode all CPUs are booted to - usually HYP) */ writel(phys_resume_addr, diff --git a/arch/arm/mm/proc.c b/arch/arm/mm/proc.c index bdbbf65d1b36..2027845efefb 100644 --- a/arch/arm/mm/proc.c +++ b/arch/arm/mm/proc.c @@ -17,7 +17,7 @@ void cpu_arm7tdmi_proc_init(void); __ADDRESSABLE(cpu_arm7tdmi_proc_init); void cpu_arm7tdmi_proc_fin(void); __ADDRESSABLE(cpu_arm7tdmi_proc_fin); -void cpu_arm7tdmi_reset(void); +void cpu_arm7tdmi_reset(unsigned long addr, bool hvc); __ADDRESSABLE(cpu_arm7tdmi_reset); int cpu_arm7tdmi_do_idle(void); __ADDRESSABLE(cpu_arm7tdmi_do_idle); @@ -32,7 +32,7 @@ void cpu_arm720_proc_init(void); __ADDRESSABLE(cpu_arm720_proc_init); void cpu_arm720_proc_fin(void); __ADDRESSABLE(cpu_arm720_proc_fin); -void cpu_arm720_reset(void); +void cpu_arm720_reset(unsigned long addr, bool hvc); __ADDRESSABLE(cpu_arm720_reset); int cpu_arm720_do_idle(void); __ADDRESSABLE(cpu_arm720_do_idle); @@ -49,7 +49,7 @@ void cpu_arm740_proc_init(void); __ADDRESSABLE(cpu_arm740_proc_init); void cpu_arm740_proc_fin(void); __ADDRESSABLE(cpu_arm740_proc_fin); -void cpu_arm740_reset(void); +void cpu_arm740_reset(unsigned long addr, bool hvc); __ADDRESSABLE(cpu_arm740_reset); int cpu_arm740_do_idle(void); __ADDRESSABLE(cpu_arm740_do_idle); @@ -64,7 +64,7 @@ void cpu_arm9tdmi_proc_init(void); __ADDRESSABLE(cpu_arm9tdmi_proc_init); void cpu_arm9tdmi_proc_fin(void); __ADDRESSABLE(cpu_arm9tdmi_proc_fin); -void cpu_arm9tdmi_reset(void); +void cpu_arm9tdmi_reset(unsigned long addr, bool hvc); __ADDRESSABLE(cpu_arm9tdmi_reset); int cpu_arm9tdmi_do_idle(void); __ADDRESSABLE(cpu_arm9tdmi_do_idle); @@ -79,7 +79,7 @@ void cpu_arm920_proc_init(void); __ADDRESSABLE(cpu_arm920_proc_init); void cpu_arm920_proc_fin(void); __ADDRESSABLE(cpu_arm920_proc_fin); -void cpu_arm920_reset(void); +void cpu_arm920_reset(unsigned long addr, bool hvc); __ADDRESSABLE(cpu_arm920_reset); int cpu_arm920_do_idle(void); __ADDRESSABLE(cpu_arm920_do_idle); @@ -102,7 +102,7 @@ void cpu_arm922_proc_init(void); __ADDRESSABLE(cpu_arm922_proc_init); void cpu_arm922_proc_fin(void); __ADDRESSABLE(cpu_arm922_proc_fin); -void cpu_arm922_reset(void); +void cpu_arm922_reset(unsigned long addr, bool hvc); __ADDRESSABLE(cpu_arm922_reset); int cpu_arm922_do_idle(void); __ADDRESSABLE(cpu_arm922_do_idle); @@ -119,7 +119,7 @@ void cpu_arm925_proc_init(void); __ADDRESSABLE(cpu_arm925_proc_init); void cpu_arm925_proc_fin(void); __ADDRESSABLE(cpu_arm925_proc_fin); -void cpu_arm925_reset(void); +void cpu_arm925_reset(unsigned long addr, bool hvc); __ADDRESSABLE(cpu_arm925_reset); int cpu_arm925_do_idle(void); __ADDRESSABLE(cpu_arm925_do_idle); @@ -159,7 +159,7 @@ void cpu_arm940_proc_init(void); __ADDRESSABLE(cpu_arm940_proc_init); void cpu_arm940_proc_fin(void); __ADDRESSABLE(cpu_arm940_proc_fin); -void cpu_arm940_reset(void); +void cpu_arm940_reset(unsigned long addr, bool hvc); __ADDRESSABLE(cpu_arm940_reset); int cpu_arm940_do_idle(void); __ADDRESSABLE(cpu_arm940_do_idle); @@ -174,7 +174,7 @@ void cpu_arm946_proc_init(void); __ADDRESSABLE(cpu_arm946_proc_init); void cpu_arm946_proc_fin(void); __ADDRESSABLE(cpu_arm946_proc_fin); -void cpu_arm946_reset(void); +void cpu_arm946_reset(unsigned long addr, bool hvc); __ADDRESSABLE(cpu_arm946_reset); int cpu_arm946_do_idle(void); __ADDRESSABLE(cpu_arm946_do_idle); @@ -429,7 +429,7 @@ void cpu_v7_proc_init(void); __ADDRESSABLE(cpu_v7_proc_init); void cpu_v7_proc_fin(void); __ADDRESSABLE(cpu_v7_proc_fin); -void cpu_v7_reset(void); +void cpu_v7_reset(unsigned long addr, bool hvc); __ADDRESSABLE(cpu_v7_reset); int cpu_v7_do_idle(void); __ADDRESSABLE(cpu_v7_do_idle); diff --git a/arch/um/drivers/mconsole_user.c b/arch/um/drivers/mconsole_user.c index e24298a734be..a04cd13c6315 100644 --- a/arch/um/drivers/mconsole_user.c +++ b/arch/um/drivers/mconsole_user.c @@ -71,7 +71,9 @@ static struct mconsole_command *mconsole_parse(struct mc_request *req) return NULL; } +#ifndef MIN #define MIN(a,b) ((a)<(b) ? (a):(b)) +#endif #define STRINGX(x) #x #define STRING(x) STRINGX(x) diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig index 90a94a111e67..769fa288179d 100644 --- a/drivers/bluetooth/Kconfig +++ b/drivers/bluetooth/Kconfig @@ -413,6 +413,7 @@ config BT_ATH3K config BT_MTKSDIO tristate "MediaTek HCI SDIO driver" depends on MMC + depends on USB || !BT_HCIBTUSB_MTK select BT_MTK help MediaTek Bluetooth HCI SDIO driver. @@ -425,6 +426,7 @@ config BT_MTKSDIO config BT_MTKUART tristate "MediaTek HCI UART driver" depends on SERIAL_DEV_BUS + depends on USB || !BT_HCIBTUSB_MTK select BT_MTK help MediaTek Bluetooth HCI UART driver. diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index e7a612504ab1..2ebc970e6573 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -3085,6 +3085,9 @@ static int btintel_setup_combined(struct hci_dev *hdev) btintel_set_dsm_reset_method(hdev, &ver_tlv); err = btintel_bootloader_setup_tlv(hdev, &ver_tlv); + if (err) + goto exit_error; + btintel_register_devcoredump_support(hdev); btintel_print_fseq_info(hdev); break; diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index b7c348687a77..2b7c80043aa2 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -437,6 +437,7 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb) } EXPORT_SYMBOL_GPL(btmtk_process_coredump); +#if IS_ENABLED(CONFIG_BT_HCIBTUSB_MTK) static void btmtk_usb_wmt_recv(struct urb *urb) { struct hci_dev *hdev = urb->context; @@ -1262,7 +1263,8 @@ int btmtk_usb_suspend(struct hci_dev *hdev) struct btmtk_data *btmtk_data = hci_get_priv(hdev); /* Stop urb anchor for iso data transmission */ - usb_kill_anchored_urbs(&btmtk_data->isopkt_anchor); + if (test_bit(BTMTK_ISOPKT_RUNNING, &btmtk_data->flags)) + usb_kill_anchored_urbs(&btmtk_data->isopkt_anchor); return 0; } @@ -1487,6 +1489,7 @@ int btmtk_usb_shutdown(struct hci_dev *hdev) return 0; } EXPORT_SYMBOL_GPL(btmtk_usb_shutdown); +#endif MODULE_AUTHOR("Sean Wang <[email protected]>"); MODULE_AUTHOR("Mark Chen <[email protected]>"); diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h index 11faf1db4fa4..473421ba7a18 100644 --- a/drivers/edac/skx_common.h +++ b/drivers/edac/skx_common.h @@ -45,7 +45,6 @@ #define I10NM_NUM_CHANNELS MAX(I10NM_NUM_DDR_CHANNELS, I10NM_NUM_HBM_CHANNELS) #define I10NM_NUM_DIMMS MAX(I10NM_NUM_DDR_DIMMS, I10NM_NUM_HBM_DIMMS) -#define MAX(a, b) ((a) > (b) ? (a) : (b)) #define NUM_IMC MAX(SKX_NUM_IMC, I10NM_NUM_IMC) #define NUM_CHANNELS MAX(SKX_NUM_CHANNELS, I10NM_NUM_CHANNELS) #define NUM_DIMMS MAX(SKX_NUM_DIMMS, I10NM_NUM_DIMMS) diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index f23ba62ce127..ed4e8ddbe76a 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -27,7 +27,8 @@ cflags-$(CONFIG_ARM64) += -fpie $(DISABLE_STACKLEAK_PLUGIN) \ cflags-$(CONFIG_ARM) += -DEFI_HAVE_STRLEN -DEFI_HAVE_STRNLEN \ -DEFI_HAVE_MEMCHR -DEFI_HAVE_STRRCHR \ -DEFI_HAVE_STRCMP -fno-builtin -fpic \ - $(call cc-option,-mno-single-pic-base) + $(call cc-option,-mno-single-pic-base) \ + $(DISABLE_STACKLEAK_PLUGIN) cflags-$(CONFIG_RISCV) += -fpic -DNO_ALTERNATIVE -mno-relax \ $(DISABLE_STACKLEAK_PLUGIN) cflags-$(CONFIG_LOONGARCH) += -fpie @@ -57,6 +58,10 @@ KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_CFI), $(KBUILD_CFLAGS)) # disable LTO KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO), $(KBUILD_CFLAGS)) +# The .data section would be renamed to .data.efistub, therefore, remove +# `-fdata-sections` flag from KBUILD_CFLAGS_KERNEL +KBUILD_CFLAGS_KERNEL := $(filter-out -fdata-sections, $(KBUILD_CFLAGS_KERNEL)) + lib-y := efi-stub-helper.o gop.o secureboot.o tpm.o \ file.o mem.o random.o randomalloc.o pci.o \ skip_spaces.o lib-cmdline.o lib-ctype.o \ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index be2638c763d7..9a406d74c0dd 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -35,8 +35,10 @@ #include "dc_stream_priv.h" #define DC_LOGGER dc->ctx->logger +#ifndef MIN #define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) #define MAX(x, y) ((x > y) ? x : y) +#endif /******************************************************************************* * Private functions diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c index 7ecf76aea950..6e064e6ae949 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c @@ -25,7 +25,9 @@ #include "hdcp.h" +#ifndef MIN #define MIN(a, b) ((a) < (b) ? (a) : (b)) +#endif #define HDCP_I2C_ADDR 0x3a /* 0x74 >> 1*/ #define KSV_READ_SIZE 0xf /* 0x6803b - 0x6802c */ #define HDCP_MAX_AUX_TRANSACTION_SIZE 16 diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h index 6f54c410c2f9..409aeec6baa9 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h @@ -22,12 +22,18 @@ */ #include <asm/div64.h> -#define SHIFT_AMOUNT 16 /* We multiply all original integers with 2^SHIFT_AMOUNT to get the fInt representation */ +enum ppevvmath_constants { + /* We multiply all original integers with 2^SHIFT_AMOUNT to get the fInt representation */ + SHIFT_AMOUNT = 16, -#define PRECISION 5 /* Change this value to change the number of decimal places in the final output - 5 is a good default */ + /* Change this value to change the number of decimal places in the final output - 5 is a good default */ + PRECISION = 5, -#define SHIFTED_2 (2 << SHIFT_AMOUNT) -#define MAX (1 << (SHIFT_AMOUNT - 1)) - 1 /* 32767 - Might change in the future */ + SHIFTED_2 = (2 << SHIFT_AMOUNT), + + /* 32767 - Might change in the future */ + MAX = (1 << (SHIFT_AMOUNT - 1)) - 1, +}; /* ------------------------------------------------------------------------------- * NEW TYPE - fINT diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c index 88eefef05fae..91ad434bcdae 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c @@ -794,7 +794,7 @@ static const char *smu_get_feature_name(struct smu_context *smu, size_t smu_cmn_get_pp_feature_mask(struct smu_context *smu, char *buf) { - int8_t sort_feature[max(SMU_FEATURE_COUNT, SMU_FEATURE_MAX)]; + int8_t sort_feature[MAX(SMU_FEATURE_COUNT, SMU_FEATURE_MAX)]; uint64_t feature_mask; int i, feature_index; uint32_t count = 0; diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c index 1fe6e0d883c7..e5577d2a19ef 100644 --- a/drivers/gpu/drm/radeon/evergreen_cs.c +++ b/drivers/gpu/drm/radeon/evergreen_cs.c @@ -33,8 +33,10 @@ #include "evergreen_reg_safe.h" #include "cayman_reg_safe.h" +#ifndef MIN #define MAX(a, b) (((a) > (b)) ? (a) : (b)) #define MIN(a, b) (((a) < (b)) ? (a) : (b)) +#endif #define REG_SAFE_BM_SIZE ARRAY_SIZE(evergreen_reg_safe_bm) diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_client.c b/drivers/hid/amd-sfh-hid/amd_sfh_client.c index bdb578e0899f..4b59687ff5d8 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_client.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_client.c @@ -288,12 +288,22 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) mp2_ops->start(privdata, info); cl_data->sensor_sts[i] = amd_sfh_wait_for_response (privdata, cl_data->sensor_idx[i], SENSOR_ENABLED); + + if (cl_data->sensor_sts[i] == SENSOR_ENABLED) + cl_data->is_any_sensor_enabled = true; + } + + if (!cl_data->is_any_sensor_enabled || + (mp2_ops->discovery_status && mp2_ops->discovery_status(privdata) == 0)) { + dev_warn(dev, "Failed to discover, sensors not enabled is %d\n", + cl_data->is_any_sensor_enabled); + rc = -EOPNOTSUPP; + goto cleanup; } for (i = 0; i < cl_data->num_hid_devices; i++) { cl_data->cur_hid_dev = i; if (cl_data->sensor_sts[i] == SENSOR_ENABLED) { - cl_data->is_any_sensor_enabled = true; rc = amdtp_hid_probe(i, cl_data); if (rc) goto cleanup; @@ -305,12 +315,6 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) cl_data->sensor_sts[i]); } - if (!cl_data->is_any_sensor_enabled || - (mp2_ops->discovery_status && mp2_ops->discovery_status(privdata) == 0)) { - dev_warn(dev, "Failed to discover, sensors not enabled is %d\n", cl_data->is_any_sensor_enabled); - rc = -EOPNOTSUPP; - goto cleanup; - } schedule_delayed_work(&cl_data->work_buffer, msecs_to_jiffies(AMD_SFH_IDLE_LOOP)); return 0; diff --git a/drivers/hid/bpf/Kconfig b/drivers/hid/bpf/Kconfig index 83214bae6768..d65482e02a6c 100644 --- a/drivers/hid/bpf/Kconfig +++ b/drivers/hid/bpf/Kconfig @@ -3,7 +3,7 @@ menu "HID-BPF support" config HID_BPF bool "HID-BPF support" - depends on BPF + depends on BPF_JIT depends on BPF_SYSCALL depends on DYNAMIC_FTRACE_WITH_DIRECT_CALLS help diff --git a/drivers/hid/bpf/hid_bpf_struct_ops.c b/drivers/hid/bpf/hid_bpf_struct_ops.c index f59cce6e437f..cd696c59ba0f 100644 --- a/drivers/hid/bpf/hid_bpf_struct_ops.c +++ b/drivers/hid/bpf/hid_bpf_struct_ops.c @@ -183,6 +183,10 @@ static int hid_bpf_reg(void *kdata, struct bpf_link *link) struct hid_device *hdev; int count, err = 0; + /* prevent multiple attach of the same struct_ops */ + if (ops->hdev) + return -EINVAL; + hdev = hid_get_device(ops->hid_id); if (IS_ERR(hdev)) return PTR_ERR(hdev); @@ -248,6 +252,7 @@ static void hid_bpf_unreg(void *kdata, struct bpf_link *link) list_del_rcu(&ops->list); synchronize_srcu(&hdev->bpf.srcu); + ops->hdev = NULL; reconnect = hdev->bpf.rdesc_ops == ops; if (reconnect) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index a44367aef621..1f4564982b95 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -692,78 +692,28 @@ static bool wacom_is_art_pen(int tool_id) static int wacom_intuos_get_tool_type(int tool_id) { - int tool_type = BTN_TOOL_PEN; - - if (wacom_is_art_pen(tool_id)) - return tool_type; - switch (tool_id) { case 0x812: /* Inking pen */ case 0x801: /* Intuos3 Inking pen */ case 0x12802: /* Intuos4/5 Inking Pen */ case 0x012: - tool_type = BTN_TOOL_PENCIL; - break; - - case 0x822: /* Pen */ - case 0x842: - case 0x852: - case 0x823: /* Intuos3 Grip Pen */ - case 0x813: /* Intuos3 Classic Pen */ - case 0x802: /* Intuos4/5 13HD/24HD General Pen */ - case 0x8e2: /* IntuosHT2 pen */ - case 0x022: - case 0x200: /* Pro Pen 3 */ - case 0x04200: /* Pro Pen 3 */ - case 0x10842: /* MobileStudio Pro Pro Pen slim */ - case 0x14802: /* Intuos4/5 13HD/24HD Classic Pen */ - case 0x16802: /* Cintiq 13HD Pro Pen */ - case 0x18802: /* DTH2242 Pen */ - case 0x10802: /* Intuos4/5 13HD/24HD General Pen */ - case 0x80842: /* Intuos Pro and Cintiq Pro 3D Pen */ - tool_type = BTN_TOOL_PEN; - break; + return BTN_TOOL_PENCIL; case 0x832: /* Stroke pen */ case 0x032: - tool_type = BTN_TOOL_BRUSH; - break; + return BTN_TOOL_BRUSH; case 0x007: /* Mouse 4D and 2D */ case 0x09c: case 0x094: case 0x017: /* Intuos3 2D Mouse */ case 0x806: /* Intuos4 Mouse */ - tool_type = BTN_TOOL_MOUSE; - break; + return BTN_TOOL_MOUSE; case 0x096: /* Lens cursor */ case 0x097: /* Intuos3 Lens cursor */ case 0x006: /* Intuos4 Lens cursor */ - tool_type = BTN_TOOL_LENS; - break; - - case 0x82a: /* Eraser */ - case 0x84a: - case 0x85a: - case 0x91a: - case 0xd1a: - case 0x0fa: - case 0x82b: /* Intuos3 Grip Pen Eraser */ - case 0x81b: /* Intuos3 Classic Pen Eraser */ - case 0x91b: /* Intuos3 Airbrush Eraser */ - case 0x80c: /* Intuos4/5 13HD/24HD Marker Pen Eraser */ - case 0x80a: /* Intuos4/5 13HD/24HD General Pen Eraser */ - case 0x90a: /* Intuos4/5 13HD/24HD Airbrush Eraser */ - case 0x1480a: /* Intuos4/5 13HD/24HD Classic Pen Eraser */ - case 0x1090a: /* Intuos4/5 13HD/24HD Airbrush Eraser */ - case 0x1080c: /* Intuos4/5 13HD/24HD Art Pen Eraser */ - case 0x1084a: /* MobileStudio Pro Pro Pen slim Eraser */ - case 0x1680a: /* Cintiq 13HD Pro Pen Eraser */ - case 0x1880a: /* DTH2242 Eraser */ - case 0x1080a: /* Intuos4/5 13HD/24HD General Pen Eraser */ - tool_type = BTN_TOOL_RUBBER; - break; + return BTN_TOOL_LENS; case 0xd12: case 0x912: @@ -771,10 +721,13 @@ static int wacom_intuos_get_tool_type(int tool_id) case 0x913: /* Intuos3 Airbrush */ case 0x902: /* Intuos4/5 13HD/24HD Airbrush */ case 0x10902: /* Intuos4/5 13HD/24HD Airbrush */ - tool_type = BTN_TOOL_AIRBRUSH; - break; + return BTN_TOOL_AIRBRUSH; + + default: + if (tool_id & 0x0008) + return BTN_TOOL_RUBBER; + return BTN_TOOL_PEN; } - return tool_type; } static void wacom_exit_report(struct wacom_wac *wacom) diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c index bc186c61a2c0..382a2bb9168a 100644 --- a/drivers/hwmon/adt7475.c +++ b/drivers/hwmon/adt7475.c @@ -22,23 +22,23 @@ #include <linux/util_macros.h> /* Indexes for the sysfs hooks */ - -#define INPUT 0 -#define MIN 1 -#define MAX 2 -#define CONTROL 3 -#define OFFSET 3 -#define AUTOMIN 4 -#define THERM 5 -#define HYSTERSIS 6 - +enum adt_sysfs_id { + INPUT = 0, + MIN = 1, + MAX = 2, + CONTROL = 3, + OFFSET = 3, // Dup + AUTOMIN = 4, + THERM = 5, + HYSTERSIS = 6, /* * These are unique identifiers for the sysfs functions - unlike the * numbers above, these are not also indexes into an array */ + ALARM = 9, + FAULT = 10, +}; -#define ALARM 9 -#define FAULT 10 /* 7475 Common Registers */ diff --git a/drivers/input/input-mt.c b/drivers/input/input-mt.c index 14b53dac1253..6b04a674f832 100644 --- a/drivers/input/input-mt.c +++ b/drivers/input/input-mt.c @@ -46,6 +46,9 @@ int input_mt_init_slots(struct input_dev *dev, unsigned int num_slots, return 0; if (mt) return mt->num_slots != num_slots ? -EINVAL : 0; + /* Arbitrary limit for avoiding too large memory allocation. */ + if (num_slots > 1024) + return -EINVAL; mt = kzalloc(struct_size(mt, slots, num_slots), GFP_KERNEL); if (!mt) diff --git a/drivers/input/touchscreen/cyttsp4_core.c b/drivers/input/touchscreen/cyttsp4_core.c index 7cb26929dc73..9dc25eb2be44 100644 --- a/drivers/input/touchscreen/cyttsp4_core.c +++ b/drivers/input/touchscreen/cyttsp4_core.c @@ -871,7 +871,7 @@ static void cyttsp4_get_mt_touches(struct cyttsp4_mt_data *md, int num_cur_tch) struct cyttsp4_touch tch; int sig; int i, j, t = 0; - int ids[max(CY_TMA1036_MAX_TCH, CY_TMA4XX_MAX_TCH)]; + int ids[MAX(CY_TMA1036_MAX_TCH, CY_TMA4XX_MAX_TCH)]; memset(ids, 0, si->si_ofs.tch_abs[CY_TCH_T].max * sizeof(int)); for (i = 0; i < num_cur_tch; i++) { diff --git a/drivers/irqchip/irq-sun6i-r.c b/drivers/irqchip/irq-sun6i-r.c index a01e44049415..99958d470d62 100644 --- a/drivers/irqchip/irq-sun6i-r.c +++ b/drivers/irqchip/irq-sun6i-r.c @@ -270,7 +270,7 @@ static const struct irq_domain_ops sun6i_r_intc_domain_ops = { static int sun6i_r_intc_suspend(void) { - u32 buf[BITS_TO_U32(max(SUN6I_NR_TOP_LEVEL_IRQS, SUN6I_NR_MUX_BITS))]; + u32 buf[BITS_TO_U32(MAX(SUN6I_NR_TOP_LEVEL_IRQS, SUN6I_NR_MUX_BITS))]; int i; /* Wake IRQs are enabled during system sleep and shutdown. */ diff --git a/drivers/media/dvb-frontends/stv0367_priv.h b/drivers/media/dvb-frontends/stv0367_priv.h index 617f605947b2..7f056d1cce82 100644 --- a/drivers/media/dvb-frontends/stv0367_priv.h +++ b/drivers/media/dvb-frontends/stv0367_priv.h @@ -25,8 +25,11 @@ #endif /* MACRO definitions */ +#ifndef MIN #define MAX(X, Y) ((X) >= (Y) ? (X) : (Y)) #define MIN(X, Y) ((X) <= (Y) ? (X) : (Y)) +#endif + #define INRANGE(X, Y, Z) \ ((((X) <= (Y)) && ((Y) <= (Z))) || \ (((Z) <= (Y)) && ((Y) <= (X))) ? 1 : 0) diff --git a/drivers/net/can/usb/etas_es58x/es58x_devlink.c b/drivers/net/can/usb/etas_es58x/es58x_devlink.c index 635edeb8f68c..eee20839d96f 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_devlink.c +++ b/drivers/net/can/usb/etas_es58x/es58x_devlink.c @@ -215,7 +215,7 @@ static int es58x_devlink_info_get(struct devlink *devlink, struct es58x_sw_version *fw_ver = &es58x_dev->firmware_version; struct es58x_sw_version *bl_ver = &es58x_dev->bootloader_version; struct es58x_hw_revision *hw_rev = &es58x_dev->hardware_revision; - char buf[max(sizeof("xx.xx.xx"), sizeof("axxx/xxx"))]; + char buf[MAX(sizeof("xx.xx.xx"), sizeof("axxx/xxx"))]; int ret = 0; if (es58x_sw_version_is_valid(fw_ver)) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index ffa74c26ee53..23f74c6c88b9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -7649,8 +7649,8 @@ static int bnxt_get_avail_msix(struct bnxt *bp, int num); static int __bnxt_reserve_rings(struct bnxt *bp) { struct bnxt_hw_rings hwr = {0}; + int rx_rings, old_rx_rings, rc; int cp = bp->cp_nr_rings; - int rx_rings, rc; int ulp_msix = 0; bool sh = false; int tx_cp; @@ -7684,6 +7684,7 @@ static int __bnxt_reserve_rings(struct bnxt *bp) hwr.grp = bp->rx_nr_rings; hwr.rss_ctx = bnxt_get_total_rss_ctxs(bp, &hwr); hwr.stat = bnxt_get_func_stat_ctxs(bp); + old_rx_rings = bp->hw_resc.resv_rx_rings; rc = bnxt_hwrm_reserve_rings(bp, &hwr); if (rc) @@ -7738,7 +7739,8 @@ static int __bnxt_reserve_rings(struct bnxt *bp) if (!bnxt_rings_ok(bp, &hwr)) return -ENOMEM; - if (!netif_is_rxfh_configured(bp->dev)) + if (old_rx_rings != bp->hw_resc.resv_rx_rings && + !netif_is_rxfh_configured(bp->dev)) bnxt_set_dflt_rss_indir_tbl(bp, NULL); if (!bnxt_ulp_registered(bp->edev) && BNXT_NEW_RM(bp)) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index d00ef0063820..ab8e3f197e7b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -1863,8 +1863,14 @@ static void bnxt_modify_rss(struct bnxt *bp, struct ethtool_rxfh_context *ctx, } static int bnxt_rxfh_context_check(struct bnxt *bp, + const struct ethtool_rxfh_param *rxfh, struct netlink_ext_ack *extack) { + if (rxfh->hfunc && rxfh->hfunc != ETH_RSS_HASH_TOP) { + NL_SET_ERR_MSG_MOD(extack, "RSS hash function not supported"); + return -EOPNOTSUPP; + } + if (!BNXT_SUPPORTS_MULTI_RSS_CTX(bp)) { NL_SET_ERR_MSG_MOD(extack, "RSS contexts not supported"); return -EOPNOTSUPP; @@ -1888,7 +1894,7 @@ static int bnxt_create_rxfh_context(struct net_device *dev, struct bnxt_vnic_info *vnic; int rc; - rc = bnxt_rxfh_context_check(bp, extack); + rc = bnxt_rxfh_context_check(bp, rxfh, extack); if (rc) return rc; @@ -1915,8 +1921,12 @@ static int bnxt_create_rxfh_context(struct net_device *dev, if (rc) goto out; + /* Populate defaults in the context */ bnxt_set_dflt_rss_indir_tbl(bp, ctx); + ctx->hfunc = ETH_RSS_HASH_TOP; memcpy(vnic->rss_hash_key, bp->rss_hash_key, HW_HASH_KEY_SIZE); + memcpy(ethtool_rxfh_context_key(ctx), + bp->rss_hash_key, HW_HASH_KEY_SIZE); rc = bnxt_hwrm_vnic_alloc(bp, vnic, 0, bp->rx_nr_rings); if (rc) { @@ -1953,7 +1963,7 @@ static int bnxt_modify_rxfh_context(struct net_device *dev, struct bnxt_rss_ctx *rss_ctx; int rc; - rc = bnxt_rxfh_context_check(bp, extack); + rc = bnxt_rxfh_context_check(bp, rxfh, extack); if (rc) return rc; diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 99a75a59078e..caaa10157909 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -765,18 +765,17 @@ static inline struct xsk_buff_pool *ice_get_xp_from_qid(struct ice_vsi *vsi, } /** - * ice_xsk_pool - get XSK buffer pool bound to a ring + * ice_rx_xsk_pool - assign XSK buff pool to Rx ring * @ring: Rx ring to use * - * Returns a pointer to xsk_buff_pool structure if there is a buffer pool - * present, NULL otherwise. + * Sets XSK buff pool pointer on Rx ring. */ -static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring) +static inline void ice_rx_xsk_pool(struct ice_rx_ring *ring) { struct ice_vsi *vsi = ring->vsi; u16 qid = ring->q_index; - return ice_get_xp_from_qid(vsi, qid); + WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid)); } /** @@ -801,7 +800,7 @@ static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid) if (!ring) return; - ring->xsk_pool = ice_get_xp_from_qid(vsi, qid); + WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid)); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 5d396c1a7731..1facf179a96f 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -536,7 +536,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) return err; } - ring->xsk_pool = ice_xsk_pool(ring); + ice_rx_xsk_pool(ring); if (ring->xsk_pool) { xdp_rxq_info_unreg(&ring->xdp_rxq); @@ -597,7 +597,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) return 0; } - ok = ice_alloc_rx_bufs_zc(ring, num_bufs); + ok = ice_alloc_rx_bufs_zc(ring, ring->xsk_pool, num_bufs); if (!ok) { u16 pf_q = ring->vsi->rxq_map[ring->q_index]; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index ec636be4d17d..3de020020bc4 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2948,7 +2948,7 @@ static void ice_vsi_rx_napi_schedule(struct ice_vsi *vsi) ice_for_each_rxq(vsi, i) { struct ice_rx_ring *rx_ring = vsi->rx_rings[i]; - if (rx_ring->xsk_pool) + if (READ_ONCE(rx_ring->xsk_pool)) napi_schedule(&rx_ring->q_vector->napi); } } diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 8bb743f78fcb..8d25b6981269 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -456,7 +456,7 @@ void ice_free_rx_ring(struct ice_rx_ring *rx_ring) if (rx_ring->vsi->type == ICE_VSI_PF) if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) xdp_rxq_info_unreg(&rx_ring->xdp_rxq); - rx_ring->xdp_prog = NULL; + WRITE_ONCE(rx_ring->xdp_prog, NULL); if (rx_ring->xsk_pool) { kfree(rx_ring->xdp_buf); rx_ring->xdp_buf = NULL; @@ -1521,10 +1521,11 @@ int ice_napi_poll(struct napi_struct *napi, int budget) * budget and be more aggressive about cleaning up the Tx descriptors. */ ice_for_each_tx_ring(tx_ring, q_vector->tx) { + struct xsk_buff_pool *xsk_pool = READ_ONCE(tx_ring->xsk_pool); bool wd; - if (tx_ring->xsk_pool) - wd = ice_xmit_zc(tx_ring); + if (xsk_pool) + wd = ice_xmit_zc(tx_ring, xsk_pool); else if (ice_ring_is_xdp(tx_ring)) wd = true; else @@ -1550,6 +1551,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) budget_per_ring = budget; ice_for_each_rx_ring(rx_ring, q_vector->rx) { + struct xsk_buff_pool *xsk_pool = READ_ONCE(rx_ring->xsk_pool); int cleaned; /* A dedicated path for zero-copy allows making a single @@ -1557,7 +1559,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) * ice_clean_rx_irq function and makes the codebase cleaner. */ cleaned = rx_ring->xsk_pool ? - ice_clean_rx_irq_zc(rx_ring, budget_per_ring) : + ice_clean_rx_irq_zc(rx_ring, xsk_pool, budget_per_ring) : ice_clean_rx_irq(rx_ring, budget_per_ring); work_done += cleaned; /* if we clean as many as budgeted, we must not be done */ diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index a65955eb23c0..240a7bec242b 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -52,10 +52,8 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx) static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx) { ice_clean_tx_ring(vsi->tx_rings[q_idx]); - if (ice_is_xdp_ena_vsi(vsi)) { - synchronize_rcu(); + if (ice_is_xdp_ena_vsi(vsi)) ice_clean_tx_ring(vsi->xdp_rings[q_idx]); - } ice_clean_rx_ring(vsi->rx_rings[q_idx]); } @@ -112,25 +110,29 @@ ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_rx_ring *rx_ring, * ice_qvec_cfg_msix - Enable IRQ for given queue vector * @vsi: the VSI that contains queue vector * @q_vector: queue vector + * @qid: queue index */ static void -ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector) +ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector, u16 qid) { u16 reg_idx = q_vector->reg_idx; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; - struct ice_tx_ring *tx_ring; - struct ice_rx_ring *rx_ring; + int q, _qid = qid; ice_cfg_itr(hw, q_vector); - ice_for_each_tx_ring(tx_ring, q_vector->tx) - ice_cfg_txq_interrupt(vsi, tx_ring->reg_idx, reg_idx, - q_vector->tx.itr_idx); + for (q = 0; q < q_vector->num_ring_tx; q++) { + ice_cfg_txq_interrupt(vsi, _qid, reg_idx, q_vector->tx.itr_idx); + _qid++; + } + + _qid = qid; - ice_for_each_rx_ring(rx_ring, q_vector->rx) - ice_cfg_rxq_interrupt(vsi, rx_ring->reg_idx, reg_idx, - q_vector->rx.itr_idx); + for (q = 0; q < q_vector->num_ring_rx; q++) { + ice_cfg_rxq_interrupt(vsi, _qid, reg_idx, q_vector->rx.itr_idx); + _qid++; + } ice_flush(hw); } @@ -164,6 +166,7 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) struct ice_tx_ring *tx_ring; struct ice_rx_ring *rx_ring; int timeout = 50; + int fail = 0; int err; if (q_idx >= vsi->num_rxq || q_idx >= vsi->num_txq) @@ -180,15 +183,17 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) usleep_range(1000, 2000); } + synchronize_net(); + netif_carrier_off(vsi->netdev); + netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); + ice_qvec_dis_irq(vsi, rx_ring, q_vector); ice_qvec_toggle_napi(vsi, q_vector, false); - netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); - ice_fill_txq_meta(vsi, tx_ring, &txq_meta); err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, tx_ring, &txq_meta); - if (err) - return err; + if (!fail) + fail = err; if (ice_is_xdp_ena_vsi(vsi)) { struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx]; @@ -196,17 +201,15 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) ice_fill_txq_meta(vsi, xdp_ring, &txq_meta); err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, xdp_ring, &txq_meta); - if (err) - return err; + if (!fail) + fail = err; } - err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true); - if (err) - return err; + ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, false); ice_qp_clean_rings(vsi, q_idx); ice_qp_reset_stats(vsi, q_idx); - return 0; + return fail; } /** @@ -219,40 +222,48 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) { struct ice_q_vector *q_vector; + int fail = 0; + bool link_up; int err; err = ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx); - if (err) - return err; + if (!fail) + fail = err; if (ice_is_xdp_ena_vsi(vsi)) { struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx]; err = ice_vsi_cfg_single_txq(vsi, vsi->xdp_rings, q_idx); - if (err) - return err; + if (!fail) + fail = err; ice_set_ring_xdp(xdp_ring); ice_tx_xsk_pool(vsi, q_idx); } err = ice_vsi_cfg_single_rxq(vsi, q_idx); - if (err) - return err; + if (!fail) + fail = err; q_vector = vsi->rx_rings[q_idx]->q_vector; - ice_qvec_cfg_msix(vsi, q_vector); + ice_qvec_cfg_msix(vsi, q_vector, q_idx); err = ice_vsi_ctrl_one_rx_ring(vsi, true, q_idx, true); - if (err) - return err; + if (!fail) + fail = err; ice_qvec_toggle_napi(vsi, q_vector, true); ice_qvec_ena_irq(vsi, q_vector); - netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); + /* make sure NAPI sees updated ice_{t,x}_ring::xsk_pool */ + synchronize_net(); + ice_get_link_status(vsi->port_info, &link_up); + if (link_up) { + netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); + netif_carrier_on(vsi->netdev); + } clear_bit(ICE_CFG_BUSY, vsi->state); - return 0; + return fail; } /** @@ -459,6 +470,7 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, /** * __ice_alloc_rx_bufs_zc - allocate a number of Rx buffers * @rx_ring: Rx ring + * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW * @count: The number of buffers to allocate * * Place the @count of descriptors onto Rx ring. Handle the ring wrap @@ -467,7 +479,8 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, * * Returns true if all allocations were successful, false if any fail. */ -static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) +static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, u16 count) { u32 nb_buffs_extra = 0, nb_buffs = 0; union ice_32b_rx_flex_desc *rx_desc; @@ -479,8 +492,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) xdp = ice_xdp_buf(rx_ring, ntu); if (ntu + count >= rx_ring->count) { - nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, - rx_desc, + nb_buffs_extra = ice_fill_rx_descs(xsk_pool, xdp, rx_desc, rx_ring->count - ntu); if (nb_buffs_extra != rx_ring->count - ntu) { ntu += nb_buffs_extra; @@ -493,7 +505,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) ice_release_rx_desc(rx_ring, 0); } - nb_buffs = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, count); + nb_buffs = ice_fill_rx_descs(xsk_pool, xdp, rx_desc, count); ntu += nb_buffs; if (ntu == rx_ring->count) @@ -509,6 +521,7 @@ exit: /** * ice_alloc_rx_bufs_zc - allocate a number of Rx buffers * @rx_ring: Rx ring + * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW * @count: The number of buffers to allocate * * Wrapper for internal allocation routine; figure out how many tail @@ -516,7 +529,8 @@ exit: * * Returns true if all calls to internal alloc routine succeeded */ -bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) +bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, u16 count) { u16 rx_thresh = ICE_RING_QUARTER(rx_ring); u16 leftover, i, tail_bumps; @@ -525,9 +539,9 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) leftover = count - (tail_bumps * rx_thresh); for (i = 0; i < tail_bumps; i++) - if (!__ice_alloc_rx_bufs_zc(rx_ring, rx_thresh)) + if (!__ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, rx_thresh)) return false; - return __ice_alloc_rx_bufs_zc(rx_ring, leftover); + return __ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, leftover); } /** @@ -596,8 +610,10 @@ out: /** * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ * @xdp_ring: XDP Tx ring + * @xsk_pool: AF_XDP buffer pool pointer */ -static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) +static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring, + struct xsk_buff_pool *xsk_pool) { u16 ntc = xdp_ring->next_to_clean; struct ice_tx_desc *tx_desc; @@ -648,7 +664,7 @@ skip: if (xdp_ring->next_to_clean >= cnt) xdp_ring->next_to_clean -= cnt; if (xsk_frames) - xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); + xsk_tx_completed(xsk_pool, xsk_frames); return completed_frames; } @@ -657,6 +673,7 @@ skip: * ice_xmit_xdp_tx_zc - AF_XDP ZC handler for XDP_TX * @xdp: XDP buffer to xmit * @xdp_ring: XDP ring to produce descriptor onto + * @xsk_pool: AF_XDP buffer pool pointer * * note that this function works directly on xdp_buff, no need to convert * it to xdp_frame. xdp_buff pointer is stored to ice_tx_buf so that cleaning @@ -666,7 +683,8 @@ skip: * was not enough space on XDP ring */ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp, - struct ice_tx_ring *xdp_ring) + struct ice_tx_ring *xdp_ring, + struct xsk_buff_pool *xsk_pool) { struct skb_shared_info *sinfo = NULL; u32 size = xdp->data_end - xdp->data; @@ -680,7 +698,7 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp, free_space = ICE_DESC_UNUSED(xdp_ring); if (free_space < ICE_RING_QUARTER(xdp_ring)) - free_space += ice_clean_xdp_irq_zc(xdp_ring); + free_space += ice_clean_xdp_irq_zc(xdp_ring, xsk_pool); if (unlikely(!free_space)) goto busy; @@ -700,7 +718,7 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp, dma_addr_t dma; dma = xsk_buff_xdp_get_dma(xdp); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size); + xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, size); tx_buf->xdp = xdp; tx_buf->type = ICE_TX_BUF_XSK_TX; @@ -742,12 +760,14 @@ busy: * @xdp: xdp_buff used as input to the XDP program * @xdp_prog: XDP program to run * @xdp_ring: ring to be used for XDP_TX action + * @xsk_pool: AF_XDP buffer pool pointer * * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR} */ static int ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring) + struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring, + struct xsk_buff_pool *xsk_pool) { int err, result = ICE_XDP_PASS; u32 act; @@ -758,7 +778,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); if (!err) return ICE_XDP_REDIR; - if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS) + if (xsk_uses_need_wakeup(xsk_pool) && err == -ENOBUFS) result = ICE_XDP_EXIT; else result = ICE_XDP_CONSUMED; @@ -769,7 +789,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, case XDP_PASS: break; case XDP_TX: - result = ice_xmit_xdp_tx_zc(xdp, xdp_ring); + result = ice_xmit_xdp_tx_zc(xdp, xdp_ring, xsk_pool); if (result == ICE_XDP_CONSUMED) goto out_failure; break; @@ -821,14 +841,16 @@ ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first, /** * ice_clean_rx_irq_zc - consumes packets from the hardware ring * @rx_ring: AF_XDP Rx ring + * @xsk_pool: AF_XDP buffer pool pointer * @budget: NAPI budget * * Returns number of processed packets on success, remaining budget on failure. */ -int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) +int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, + int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; - struct xsk_buff_pool *xsk_pool = rx_ring->xsk_pool; u32 ntc = rx_ring->next_to_clean; u32 ntu = rx_ring->next_to_use; struct xdp_buff *first = NULL; @@ -891,7 +913,8 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) if (ice_is_non_eop(rx_ring, rx_desc)) continue; - xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring); + xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring, + xsk_pool); if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) { xdp_xmit |= xdp_res; } else if (xdp_res == ICE_XDP_EXIT) { @@ -940,7 +963,8 @@ construct_skb: rx_ring->next_to_clean = ntc; entries_to_alloc = ICE_RX_DESC_UNUSED(rx_ring); if (entries_to_alloc > ICE_RING_QUARTER(rx_ring)) - failure |= !ice_alloc_rx_bufs_zc(rx_ring, entries_to_alloc); + failure |= !ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, + entries_to_alloc); ice_finalize_xdp_rx(xdp_ring, xdp_xmit, 0); ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes); @@ -963,17 +987,19 @@ construct_skb: /** * ice_xmit_pkt - produce a single HW Tx descriptor out of AF_XDP descriptor * @xdp_ring: XDP ring to produce the HW Tx descriptor on + * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW * @desc: AF_XDP descriptor to pull the DMA address and length from * @total_bytes: bytes accumulator that will be used for stats update */ -static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc, +static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, + struct xsk_buff_pool *xsk_pool, struct xdp_desc *desc, unsigned int *total_bytes) { struct ice_tx_desc *tx_desc; dma_addr_t dma; - dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc->addr); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc->len); + dma = xsk_buff_raw_get_dma(xsk_pool, desc->addr); + xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, desc->len); tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use++); tx_desc->buf_addr = cpu_to_le64(dma); @@ -986,10 +1012,13 @@ static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc, /** * ice_xmit_pkt_batch - produce a batch of HW Tx descriptors out of AF_XDP descriptors * @xdp_ring: XDP ring to produce the HW Tx descriptors on + * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from * @total_bytes: bytes accumulator that will be used for stats update */ -static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs, +static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, + struct xsk_buff_pool *xsk_pool, + struct xdp_desc *descs, unsigned int *total_bytes) { u16 ntu = xdp_ring->next_to_use; @@ -999,8 +1028,8 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) { dma_addr_t dma; - dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, descs[i].addr); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, descs[i].len); + dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr); + xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, descs[i].len); tx_desc = ICE_TX_DESC(xdp_ring, ntu++); tx_desc->buf_addr = cpu_to_le64(dma); @@ -1016,60 +1045,69 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de /** * ice_fill_tx_hw_ring - produce the number of Tx descriptors onto ring * @xdp_ring: XDP ring to produce the HW Tx descriptors on + * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from * @nb_pkts: count of packets to be send * @total_bytes: bytes accumulator that will be used for stats update */ -static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs, - u32 nb_pkts, unsigned int *total_bytes) +static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, + struct xsk_buff_pool *xsk_pool, + struct xdp_desc *descs, u32 nb_pkts, + unsigned int *total_bytes) { u32 batched, leftover, i; batched = ALIGN_DOWN(nb_pkts, PKTS_PER_BATCH); leftover = nb_pkts & (PKTS_PER_BATCH - 1); for (i = 0; i < batched; i += PKTS_PER_BATCH) - ice_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes); + ice_xmit_pkt_batch(xdp_ring, xsk_pool, &descs[i], total_bytes); for (; i < batched + leftover; i++) - ice_xmit_pkt(xdp_ring, &descs[i], total_bytes); + ice_xmit_pkt(xdp_ring, xsk_pool, &descs[i], total_bytes); } /** * ice_xmit_zc - take entries from XSK Tx ring and place them onto HW Tx ring * @xdp_ring: XDP ring to produce the HW Tx descriptors on + * @xsk_pool: AF_XDP buffer pool pointer * * Returns true if there is no more work that needs to be done, false otherwise */ -bool ice_xmit_zc(struct ice_tx_ring *xdp_ring) +bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool) { - struct xdp_desc *descs = xdp_ring->xsk_pool->tx_descs; + struct xdp_desc *descs = xsk_pool->tx_descs; u32 nb_pkts, nb_processed = 0; unsigned int total_bytes = 0; int budget; - ice_clean_xdp_irq_zc(xdp_ring); + ice_clean_xdp_irq_zc(xdp_ring, xsk_pool); + + if (!netif_carrier_ok(xdp_ring->vsi->netdev) || + !netif_running(xdp_ring->vsi->netdev)) + return true; budget = ICE_DESC_UNUSED(xdp_ring); budget = min_t(u16, budget, ICE_RING_QUARTER(xdp_ring)); - nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, budget); + nb_pkts = xsk_tx_peek_release_desc_batch(xsk_pool, budget); if (!nb_pkts) return true; if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) { nb_processed = xdp_ring->count - xdp_ring->next_to_use; - ice_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes); + ice_fill_tx_hw_ring(xdp_ring, xsk_pool, descs, nb_processed, + &total_bytes); xdp_ring->next_to_use = 0; } - ice_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed, - &total_bytes); + ice_fill_tx_hw_ring(xdp_ring, xsk_pool, &descs[nb_processed], + nb_pkts - nb_processed, &total_bytes); ice_set_rs_bit(xdp_ring); ice_xdp_ring_update_tail(xdp_ring); ice_update_tx_ring_stats(xdp_ring, nb_pkts, total_bytes); - if (xsk_uses_need_wakeup(xdp_ring->xsk_pool)) - xsk_set_tx_need_wakeup(xdp_ring->xsk_pool); + if (xsk_uses_need_wakeup(xsk_pool)) + xsk_set_tx_need_wakeup(xsk_pool); return nb_pkts < budget; } @@ -1091,7 +1129,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, struct ice_vsi *vsi = np->vsi; struct ice_tx_ring *ring; - if (test_bit(ICE_VSI_DOWN, vsi->state)) + if (test_bit(ICE_VSI_DOWN, vsi->state) || !netif_carrier_ok(netdev)) return -ENETDOWN; if (!ice_is_xdp_ena_vsi(vsi)) @@ -1102,7 +1140,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, ring = vsi->rx_rings[queue_id]->xdp_ring; - if (!ring->xsk_pool) + if (!READ_ONCE(ring->xsk_pool)) return -EINVAL; /* The idea here is that if NAPI is running, mark a miss, so diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h index 6fa181f080ef..45adeb513253 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.h +++ b/drivers/net/ethernet/intel/ice/ice_xsk.h @@ -20,16 +20,20 @@ struct ice_vsi; #ifdef CONFIG_XDP_SOCKETS int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid); -int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget); +int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, + int budget); int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags); -bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count); +bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, u16 count); bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi); void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring); void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring); -bool ice_xmit_zc(struct ice_tx_ring *xdp_ring); +bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool); int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc); #else -static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring) +static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring, + struct xsk_buff_pool __always_unused *xsk_pool) { return false; } @@ -44,6 +48,7 @@ ice_xsk_pool_setup(struct ice_vsi __always_unused *vsi, static inline int ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring, + struct xsk_buff_pool __always_unused *xsk_pool, int __always_unused budget) { return 0; @@ -51,6 +56,7 @@ ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring, static inline bool ice_alloc_rx_bufs_zc(struct ice_rx_ring __always_unused *rx_ring, + struct xsk_buff_pool __always_unused *xsk_pool, u16 __always_unused count) { return false; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index cb5c7b09e8a0..8daf938afc36 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6306,21 +6306,6 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, size_t n; int i; - switch (qopt->cmd) { - case TAPRIO_CMD_REPLACE: - break; - case TAPRIO_CMD_DESTROY: - return igc_tsn_clear_schedule(adapter); - case TAPRIO_CMD_STATS: - igc_taprio_stats(adapter->netdev, &qopt->stats); - return 0; - case TAPRIO_CMD_QUEUE_STATS: - igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats); - return 0; - default: - return -EOPNOTSUPP; - } - if (qopt->base_time < 0) return -ERANGE; @@ -6429,7 +6414,23 @@ static int igc_tsn_enable_qbv_scheduling(struct igc_adapter *adapter, if (hw->mac.type != igc_i225) return -EOPNOTSUPP; - err = igc_save_qbv_schedule(adapter, qopt); + switch (qopt->cmd) { + case TAPRIO_CMD_REPLACE: + err = igc_save_qbv_schedule(adapter, qopt); + break; + case TAPRIO_CMD_DESTROY: + err = igc_tsn_clear_schedule(adapter); + break; + case TAPRIO_CMD_STATS: + igc_taprio_stats(adapter->netdev, &qopt->stats); + return 0; + case TAPRIO_CMD_QUEUE_STATS: + igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats); + return 0; + default: + return -EOPNOTSUPP; + } + if (err) return err; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 8c45ad983abc..0d62a33afa80 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -953,13 +953,13 @@ static void mvpp2_bm_pool_update_fc(struct mvpp2_port *port, static void mvpp2_bm_pool_update_priv_fc(struct mvpp2 *priv, bool en) { struct mvpp2_port *port; - int i; + int i, j; for (i = 0; i < priv->port_count; i++) { port = priv->port_list[i]; if (port->priv->percpu_pools) { - for (i = 0; i < port->nrxqs; i++) - mvpp2_bm_pool_update_fc(port, &port->priv->bm_pools[i], + for (j = 0; j < port->nrxqs; j++) + mvpp2_bm_pool_update_fc(port, &port->priv->bm_pools[j], port->tx_fc & en); } else { mvpp2_bm_pool_update_fc(port, port->pool_long, port->tx_fc & en); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index 8cf8ba2622f2..71a168746ebe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -932,6 +932,7 @@ err_rule: mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, zone_rule->attr, mh); mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id); err_mod_hdr: + *attr = *old_attr; kfree(old_attr); err_attr: kvfree(spec); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index 6e00afe4671b..797db853de36 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -51,9 +51,10 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev) MLX5_CAP_FLOWTABLE_NIC_RX(mdev, decap)) caps |= MLX5_IPSEC_CAP_PACKET_OFFLOAD; - if ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) && - MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) || - MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level)) + if (IS_ENABLED(CONFIG_MLX5_CLS_ACT) && + ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) && + MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) || + MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level))) caps |= MLX5_IPSEC_CAP_PRIO; if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 00d5661dc62e..36845872ae94 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1409,7 +1409,12 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, if (!an_changes && link_modes == eproto.admin) goto out; - mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext); + err = mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext); + if (err) { + netdev_err(priv->netdev, "%s: failed to set ptys reg: %d\n", __func__, err); + goto out; + } + mlx5_toggle_port_link(mdev); out: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 979c49ae6b5c..b43ca0b762c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -207,6 +207,7 @@ int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev) static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unloaded) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + struct devlink *devlink = priv_to_devlink(dev); /* if this is the driver that initiated the fw reset, devlink completed the reload */ if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) { @@ -218,9 +219,11 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unload mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n"); else mlx5_load_one(dev, true); - devlink_remote_reload_actions_performed(priv_to_devlink(dev), 0, + devl_lock(devlink); + devlink_remote_reload_actions_performed(devlink, 0, BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) | BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE)); + devl_unlock(devlink); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c index f7b01b3f0cba..1477db7f5307 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c @@ -48,6 +48,7 @@ static struct mlx5_irq * irq_pool_request_irq(struct mlx5_irq_pool *pool, struct irq_affinity_desc *af_desc) { struct irq_affinity_desc auto_desc = {}; + struct mlx5_irq *irq; u32 irq_index; int err; @@ -64,9 +65,12 @@ irq_pool_request_irq(struct mlx5_irq_pool *pool, struct irq_affinity_desc *af_de else cpu_get(pool, cpumask_first(&af_desc->mask)); } - return mlx5_irq_alloc(pool, irq_index, - cpumask_empty(&auto_desc.mask) ? af_desc : &auto_desc, - NULL); + irq = mlx5_irq_alloc(pool, irq_index, + cpumask_empty(&auto_desc.mask) ? af_desc : &auto_desc, + NULL); + if (IS_ERR(irq)) + xa_erase(&pool->irqs, irq_index); + return irq; } /* Looking for the IRQ with the smallest refcount that fits req_mask. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index d0871c46b8c5..cf8045b92689 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -1538,7 +1538,7 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev, goto unlock; for (i = 0; i < ldev->ports; i++) { - if (ldev->pf[MLX5_LAG_P1].netdev == slave) { + if (ldev->pf[i].netdev == slave) { port = i; break; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 527da58c7953..5b7e6f4b5c7e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -2142,7 +2142,6 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) /* Panic tear down fw command will stop the PCI bus communication * with the HCA, so the health poll is no longer needed. */ - mlx5_drain_health_wq(dev); mlx5_stop_health_poll(dev, false); ret = mlx5_cmd_fast_teardown_hca(dev); @@ -2177,6 +2176,7 @@ static void shutdown(struct pci_dev *pdev) mlx5_core_info(dev, "Shutdown was called\n"); set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state); + mlx5_drain_health_wq(dev); err = mlx5_try_fast_unload(dev); if (err) mlx5_unload_one(dev, false); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index b2986175d9af..b706f1486504 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -112,6 +112,7 @@ static void mlx5_sf_dev_shutdown(struct auxiliary_device *adev) struct mlx5_core_dev *mdev = sf_dev->mdev; set_bit(MLX5_BREAK_FW_WAIT, &mdev->intf_state); + mlx5_drain_health_wq(mdev); mlx5_unload_one(mdev, false); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index 042ca0349124..d1db04baa1fa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -7,7 +7,7 @@ /* don't try to optimize STE allocation if the stack is too constaraining */ #define DR_RULE_MAX_STES_OPTIMIZED 0 #else -#define DR_RULE_MAX_STES_OPTIMIZED 5 +#define DR_RULE_MAX_STES_OPTIMIZED 2 #endif #define DR_RULE_MAX_STE_CHAIN_OPTIMIZED (DR_RULE_MAX_STES_OPTIMIZED + DR_ACTION_MAX_STES) diff --git a/drivers/net/ethernet/meta/Kconfig b/drivers/net/ethernet/meta/Kconfig index 86034ea4ba5b..c002ede36402 100644 --- a/drivers/net/ethernet/meta/Kconfig +++ b/drivers/net/ethernet/meta/Kconfig @@ -20,7 +20,7 @@ if NET_VENDOR_META config FBNIC tristate "Meta Platforms Host Network Interface" depends on X86_64 || COMPILE_TEST - depends on S390=n + depends on !S390 depends on MAX_SKB_FRAGS < 22 depends on PCI_MSI select PHYLINK diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 714d2e804694..3507c2e28110 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -4349,7 +4349,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, if (unlikely(!rtl_tx_slots_avail(tp))) { if (net_ratelimit()) netdev_err(dev, "BUG! Tx Ring full when queue awake!\n"); - goto err_stop_0; + netif_stop_queue(dev); + return NETDEV_TX_BUSY; } opts[1] = rtl8169_tx_vlan_tag(skb); @@ -4405,11 +4406,6 @@ err_dma_0: dev_kfree_skb_any(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; - -err_stop_0: - netif_stop_queue(dev); - dev->stats.tx_dropped++; - return NETDEV_TX_BUSY; } static unsigned int rtl_last_frag_len(struct sk_buff *skb) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index e342f387c3dd..02fdf66e07fa 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -2219,9 +2219,9 @@ static void axienet_dma_err_handler(struct work_struct *work) ~(XAE_OPTION_TXEN | XAE_OPTION_RXEN)); axienet_set_mac_address(ndev, NULL); axienet_set_multicast_list(ndev); - axienet_setoptions(ndev, lp->options); napi_enable(&lp->napi_rx); napi_enable(&lp->napi_tx); + axienet_setoptions(ndev, lp->options); } /** diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c index b3ddc9a629d9..fad5b6564464 100644 --- a/drivers/net/fjes/fjes_main.c +++ b/drivers/net/fjes/fjes_main.c @@ -14,9 +14,7 @@ #include "fjes.h" #include "fjes_trace.h" -#define MAJ 1 -#define MIN 2 -#define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) +#define DRV_VERSION "1.2" #define DRV_NAME "fjes" char fjes_driver_name[] = DRV_NAME; char fjes_driver_version[] = DRV_VERSION; diff --git a/drivers/net/phy/aquantia/aquantia_main.c b/drivers/net/phy/aquantia/aquantia_main.c index d12e35374231..e982e9ce44a5 100644 --- a/drivers/net/phy/aquantia/aquantia_main.c +++ b/drivers/net/phy/aquantia/aquantia_main.c @@ -653,13 +653,7 @@ static int aqr107_fill_interface_modes(struct phy_device *phydev) unsigned long *possible = phydev->possible_interfaces; unsigned int serdes_mode, rate_adapt; phy_interface_t interface; - int i, val, ret; - - ret = phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1, - VEND1_GLOBAL_CFG_10M, val, val != 0, - 1000, 100000, false); - if (ret) - return ret; + int i, val; /* Walk the media-speed configuration registers to determine which * host-side serdes modes may be used by the PHY depending on the @@ -708,6 +702,25 @@ static int aqr107_fill_interface_modes(struct phy_device *phydev) return 0; } +static int aqr113c_fill_interface_modes(struct phy_device *phydev) +{ + int val, ret; + + /* It's been observed on some models that - when coming out of suspend + * - the FW signals that the PHY is ready but the GLOBAL_CFG registers + * continue on returning zeroes for some time. Let's poll the 100M + * register until it returns a real value as both 113c and 115c support + * this mode. + */ + ret = phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1, + VEND1_GLOBAL_CFG_100M, val, val != 0, + 1000, 100000, false); + if (ret) + return ret; + + return aqr107_fill_interface_modes(phydev); +} + static int aqr113c_config_init(struct phy_device *phydev) { int ret; @@ -725,7 +738,7 @@ static int aqr113c_config_init(struct phy_device *phydev) if (ret) return ret; - return aqr107_fill_interface_modes(phydev); + return aqr113c_fill_interface_modes(phydev); } static int aqr107_probe(struct phy_device *phydev) diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index dd519805deee..65b0a3115e14 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -1389,6 +1389,8 @@ static int ksz9131_config_init(struct phy_device *phydev) const struct device *dev_walker; int ret; + phydev->mdix_ctrl = ETH_TP_MDI_AUTO; + dev_walker = &phydev->mdio.dev; do { of_node = dev_walker->of_node; @@ -1438,28 +1440,30 @@ static int ksz9131_config_init(struct phy_device *phydev) #define MII_KSZ9131_AUTO_MDIX 0x1C #define MII_KSZ9131_AUTO_MDI_SET BIT(7) #define MII_KSZ9131_AUTO_MDIX_SWAP_OFF BIT(6) +#define MII_KSZ9131_DIG_AXAN_STS 0x14 +#define MII_KSZ9131_DIG_AXAN_STS_LINK_DET BIT(14) +#define MII_KSZ9131_DIG_AXAN_STS_A_SELECT BIT(12) static int ksz9131_mdix_update(struct phy_device *phydev) { int ret; - ret = phy_read(phydev, MII_KSZ9131_AUTO_MDIX); - if (ret < 0) - return ret; - - if (ret & MII_KSZ9131_AUTO_MDIX_SWAP_OFF) { - if (ret & MII_KSZ9131_AUTO_MDI_SET) - phydev->mdix_ctrl = ETH_TP_MDI; - else - phydev->mdix_ctrl = ETH_TP_MDI_X; + if (phydev->mdix_ctrl != ETH_TP_MDI_AUTO) { + phydev->mdix = phydev->mdix_ctrl; } else { - phydev->mdix_ctrl = ETH_TP_MDI_AUTO; - } + ret = phy_read(phydev, MII_KSZ9131_DIG_AXAN_STS); + if (ret < 0) + return ret; - if (ret & MII_KSZ9131_AUTO_MDI_SET) - phydev->mdix = ETH_TP_MDI; - else - phydev->mdix = ETH_TP_MDI_X; + if (ret & MII_KSZ9131_DIG_AXAN_STS_LINK_DET) { + if (ret & MII_KSZ9131_DIG_AXAN_STS_A_SELECT) + phydev->mdix = ETH_TP_MDI; + else + phydev->mdix = ETH_TP_MDI_X; + } else { + phydev->mdix = ETH_TP_MDI_INVALID; + } + } return 0; } diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index bed839237fb5..87865918dab6 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -1465,6 +1465,13 @@ static struct phy_driver realtek_drvs[] = { .handle_interrupt = genphy_handle_interrupt_no_ack, .suspend = genphy_suspend, .resume = genphy_resume, + }, { + PHY_ID_MATCH_EXACT(0x001cc960), + .name = "RTL8366S Gigabit Ethernet", + .suspend = genphy_suspend, + .resume = genphy_resume, + .read_mmd = genphy_read_mmd_unsupported, + .write_mmd = genphy_write_mmd_unsupported, }, }; diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index 0a662e42ed96..cb7d2f798fb4 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -179,6 +179,7 @@ static int sr_mdio_read(struct net_device *netdev, int phy_id, int loc) struct usbnet *dev = netdev_priv(netdev); __le16 res; int rc = 0; + int err; if (phy_id) { netdev_dbg(netdev, "Only internal phy supported\n"); @@ -189,11 +190,17 @@ static int sr_mdio_read(struct net_device *netdev, int phy_id, int loc) if (loc == MII_BMSR) { u8 value; - sr_read_reg(dev, SR_NSR, &value); + err = sr_read_reg(dev, SR_NSR, &value); + if (err < 0) + return err; + if (value & NSR_LINKST) rc = 1; } - sr_share_read_word(dev, 1, loc, &res); + err = sr_share_read_word(dev, 1, loc, &res); + if (err < 0) + return err; + if (rc == 1) res = le16_to_cpu(res) | BMSR_LSTATUS; else diff --git a/drivers/net/wan/fsl_qmc_hdlc.c b/drivers/net/wan/fsl_qmc_hdlc.c index c5e7ca793c43..8fcfbde31a1c 100644 --- a/drivers/net/wan/fsl_qmc_hdlc.c +++ b/drivers/net/wan/fsl_qmc_hdlc.c @@ -18,6 +18,7 @@ #include <linux/hdlc.h> #include <linux/mod_devicetable.h> #include <linux/module.h> +#include <linux/mutex.h> #include <linux/platform_device.h> #include <linux/slab.h> #include <linux/spinlock.h> @@ -37,7 +38,7 @@ struct qmc_hdlc { struct qmc_chan *qmc_chan; struct net_device *netdev; struct framer *framer; - spinlock_t carrier_lock; /* Protect carrier detection */ + struct mutex carrier_lock; /* Protect carrier detection */ struct notifier_block nb; bool is_crc32; spinlock_t tx_lock; /* Protect tx descriptors */ @@ -60,7 +61,7 @@ static int qmc_hdlc_framer_set_carrier(struct qmc_hdlc *qmc_hdlc) if (!qmc_hdlc->framer) return 0; - guard(spinlock_irqsave)(&qmc_hdlc->carrier_lock); + guard(mutex)(&qmc_hdlc->carrier_lock); ret = framer_get_status(qmc_hdlc->framer, &framer_status); if (ret) { @@ -249,6 +250,7 @@ static void qmc_hcld_recv_complete(void *context, size_t length, unsigned int fl struct qmc_hdlc_desc *desc = context; struct net_device *netdev; struct qmc_hdlc *qmc_hdlc; + size_t crc_size; int ret; netdev = desc->netdev; @@ -267,15 +269,26 @@ static void qmc_hcld_recv_complete(void *context, size_t length, unsigned int fl if (flags & QMC_RX_FLAG_HDLC_CRC) /* CRC error */ netdev->stats.rx_crc_errors++; kfree_skb(desc->skb); - } else { - netdev->stats.rx_packets++; - netdev->stats.rx_bytes += length; + goto re_queue; + } - skb_put(desc->skb, length); - desc->skb->protocol = hdlc_type_trans(desc->skb, netdev); - netif_rx(desc->skb); + /* Discard the CRC */ + crc_size = qmc_hdlc->is_crc32 ? 4 : 2; + if (length < crc_size) { + netdev->stats.rx_length_errors++; + kfree_skb(desc->skb); + goto re_queue; } + length -= crc_size; + + netdev->stats.rx_packets++; + netdev->stats.rx_bytes += length; + + skb_put(desc->skb, length); + desc->skb->protocol = hdlc_type_trans(desc->skb, netdev); + netif_rx(desc->skb); +re_queue: /* Re-queue a transfer using the same descriptor */ ret = qmc_hdlc_recv_queue(qmc_hdlc, desc, desc->dma_size); if (ret) { @@ -706,7 +719,7 @@ static int qmc_hdlc_probe(struct platform_device *pdev) qmc_hdlc->dev = dev; spin_lock_init(&qmc_hdlc->tx_lock); - spin_lock_init(&qmc_hdlc->carrier_lock); + mutex_init(&qmc_hdlc->carrier_lock); qmc_hdlc->qmc_chan = devm_qmc_chan_get_bychild(dev, dev->of_node); if (IS_ERR(qmc_hdlc->qmc_chan)) diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c index 876c029f58f6..9e0b9e329bda 100644 --- a/drivers/net/wireless/ath/ath12k/pci.c +++ b/drivers/net/wireless/ath/ath12k/pci.c @@ -473,7 +473,8 @@ static void __ath12k_pci_ext_irq_disable(struct ath12k_base *ab) { int i; - clear_bit(ATH12K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags); + if (!test_and_clear_bit(ATH12K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags)) + return; for (i = 0; i < ATH12K_EXT_IRQ_GRP_NUM_MAX; i++) { struct ath12k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i]; diff --git a/drivers/net/wireless/ath/ath12k/wow.c b/drivers/net/wireless/ath/ath12k/wow.c index bead19db2c9a..9b8684abbe40 100644 --- a/drivers/net/wireless/ath/ath12k/wow.c +++ b/drivers/net/wireless/ath/ath12k/wow.c @@ -361,7 +361,7 @@ static int ath12k_wow_vif_set_wakeups(struct ath12k_vif *arvif, struct ath12k *ar = arvif->ar; unsigned long wow_mask = 0; int pattern_id = 0; - int ret, i; + int ret, i, j; /* Setup requested WOW features */ switch (arvif->vdev_type) { @@ -431,9 +431,9 @@ static int ath12k_wow_vif_set_wakeups(struct ath12k_vif *arvif, eth_pattern->pattern_len); /* convert bitmask to bytemask */ - for (i = 0; i < eth_pattern->pattern_len; i++) - if (eth_pattern->mask[i / 8] & BIT(i % 8)) - new_pattern.bytemask[i] = 0xff; + for (j = 0; j < eth_pattern->pattern_len; j++) + if (eth_pattern->mask[j / 8] & BIT(j % 8)) + new_pattern.bytemask[j] = 0xff; new_pattern.pattern_len = eth_pattern->pattern_len; new_pattern.pkt_offset = eth_pattern->pkt_offset; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index 2e6268cb06c0..1bab93d049df 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -303,6 +303,7 @@ mt7921_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) mvif->bss_conf.mt76.omac_idx = mvif->bss_conf.mt76.idx; mvif->phy = phy; + mvif->bss_conf.vif = mvif; mvif->bss_conf.mt76.band_idx = 0; mvif->bss_conf.mt76.wmm_idx = mvif->bss_conf.mt76.idx % MT76_CONNAC_MAX_WMM_SETS; diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c index 9fe664960b38..e2a6575b9ff7 100644 --- a/drivers/nfc/pn544/i2c.c +++ b/drivers/nfc/pn544/i2c.c @@ -126,8 +126,6 @@ struct pn544_i2c_fw_secure_blob { #define PN544_FW_CMD_RESULT_COMMAND_REJECTED 0xE0 #define PN544_FW_CMD_RESULT_CHUNK_ERROR 0xE6 -#define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) - #define PN544_FW_WRITE_BUFFER_MAX_LEN 0x9f7 #define PN544_FW_I2C_MAX_PAYLOAD PN544_HCI_I2C_LLC_MAX_SIZE #define PN544_FW_I2C_WRITE_FRAME_HEADER_LEN 8 diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index 061f01f60db4..736ad8baa2a5 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -485,7 +485,9 @@ int pciehp_set_raw_indicator_status(struct hotplug_slot *hotplug_slot, struct pci_dev *pdev = ctrl_dev(ctrl); pci_config_pm_runtime_get(pdev); - pcie_write_cmd_nowait(ctrl, FIELD_PREP(PCI_EXP_SLTCTL_AIC, status), + + /* Attention and Power Indicator Control bits are supported */ + pcie_write_cmd_nowait(ctrl, FIELD_PREP(PCI_EXP_SLTCTL_AIC | PCI_EXP_SLTCTL_PIC, status), PCI_EXP_SLTCTL_AIC | PCI_EXP_SLTCTL_PIC); pci_config_pm_runtime_put(pdev); return 0; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e3a49f66982d..ffaaca0978cb 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4477,12 +4477,6 @@ void pci_intx(struct pci_dev *pdev, int enable) { u16 pci_command, new; - /* Preserve the "hybrid" behavior for backwards compatibility */ - if (pci_is_managed(pdev)) { - WARN_ON_ONCE(pcim_intx(pdev, enable) != 0); - return; - } - pci_read_config_word(pdev, PCI_COMMAND, &pci_command); if (enable) @@ -4490,8 +4484,15 @@ void pci_intx(struct pci_dev *pdev, int enable) else new = pci_command | PCI_COMMAND_INTX_DISABLE; - if (new != pci_command) + if (new != pci_command) { + /* Preserve the "hybrid" behavior for backwards compatibility */ + if (pci_is_managed(pdev)) { + WARN_ON_ONCE(pcim_intx(pdev, enable) != 0); + return; + } + pci_write_config_word(pdev, PCI_COMMAND, new); + } } EXPORT_SYMBOL_GPL(pci_intx); diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index f776fd42244f..73f75958e15c 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -813,9 +813,11 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, if (ret == -ENOPROTOOPT) { dev_dbg(ec_dev->dev, "GET_NEXT_EVENT returned invalid version error.\n"); + mutex_lock(&ec_dev->lock); ret = cros_ec_get_host_command_version_mask(ec_dev, EC_CMD_GET_NEXT_EVENT, &ver_mask); + mutex_unlock(&ec_dev->lock); if (ret < 0 || ver_mask == 0) /* * Do not change the MKBP supported version if we can't diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c index 3e94fdd1ea52..3197aaa69da7 100644 --- a/drivers/platform/x86/sony-laptop.c +++ b/drivers/platform/x86/sony-laptop.c @@ -757,7 +757,6 @@ static union acpi_object *__call_snc_method(acpi_handle handle, char *method, return result; } -#define MIN(a, b) (a > b ? b : a) static int sony_nc_buffer_call(acpi_handle handle, char *name, u64 *value, void *buffer, size_t buflen) { diff --git a/drivers/scsi/isci/init.c b/drivers/scsi/isci/init.c index d31884f82f2a..73085d2f5c43 100644 --- a/drivers/scsi/isci/init.c +++ b/drivers/scsi/isci/init.c @@ -65,11 +65,7 @@ #include "task.h" #include "probe_roms.h" -#define MAJ 1 -#define MIN 2 -#define BUILD 0 -#define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \ - __stringify(BUILD) +#define DRV_VERSION "1.2.0" MODULE_VERSION(DRV_VERSION); diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c index a0d2556a27bb..089653018d32 100644 --- a/drivers/scsi/sr_ioctl.c +++ b/drivers/scsi/sr_ioctl.c @@ -431,7 +431,7 @@ int sr_select_speed(struct cdrom_device_info *cdi, unsigned long speed) struct packet_command cgc; /* avoid exceeding the max speed or overflowing integer bounds */ - speed = clamp(0, speed, 0xffff / 177); + speed = clamp(speed, 0, 0xffff / 177); if (speed == 0) speed = 0xffff; /* set to max */ diff --git a/drivers/staging/media/atomisp/pci/hive_isp_css_include/math_support.h b/drivers/staging/media/atomisp/pci/hive_isp_css_include/math_support.h index 7349943bba2b..160c496784b7 100644 --- a/drivers/staging/media/atomisp/pci/hive_isp_css_include/math_support.h +++ b/drivers/staging/media/atomisp/pci/hive_isp_css_include/math_support.h @@ -22,11 +22,6 @@ /* force a value to a lower even value */ #define EVEN_FLOOR(x) ((x) & ~1) -/* for preprocessor and array sizing use MIN and MAX - otherwise use min and max */ -#define MAX(a, b) (((a) > (b)) ? (a) : (b)) -#define MIN(a, b) (((a) < (b)) ? (a) : (b)) - #define CEIL_DIV(a, b) (((b) != 0) ? ((a) + (b) - 1) / (b) : 0) #define CEIL_MUL(a, b) (CEIL_DIV(a, b) * (b)) #define CEIL_MUL2(a, b) (((a) + (b) - 1) & ~((b) - 1)) diff --git a/drivers/vdpa/octeon_ep/octep_vdpa_hw.c b/drivers/vdpa/octeon_ep/octep_vdpa_hw.c index 7fa0491bb201..11bd76ae18cf 100644 --- a/drivers/vdpa/octeon_ep/octep_vdpa_hw.c +++ b/drivers/vdpa/octeon_ep/octep_vdpa_hw.c @@ -140,7 +140,7 @@ static int octep_process_mbox(struct octep_hw *oct_hw, u16 id, u16 qid, void *bu val = octep_read_sig(mbox); if ((val & 0xFFFF) != MBOX_RSP_SIG) { dev_warn(&pdev->dev, "Invalid Signature from mbox : %d response\n", id); - return ret; + return -EINVAL; } val = octep_read_sts(mbox); diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index a9b93e99c23a..bc1f962e483b 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -305,15 +305,9 @@ 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_probe; + goto err; /* If probe didn't do it, mark device DRIVER_OK ourselves. */ if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK)) @@ -326,9 +320,6 @@ static int virtio_dev_probe(struct device *_d) 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; @@ -344,9 +335,6 @@ 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)); @@ -524,9 +512,6 @@ int virtio_device_freeze(struct virtio_device *dev) } } - if (dev->config->destroy_avq) - dev->config->destroy_avq(dev); - return 0; } EXPORT_SYMBOL_GPL(virtio_device_freeze); @@ -562,16 +547,10 @@ 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_restore; + goto err; } /* If restore didn't do it, mark device DRIVER_OK ourselves. */ @@ -582,9 +561,6 @@ 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 7d82facafd75..c44d8ba00c02 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -46,12 +46,26 @@ bool vp_notify(struct virtqueue *vq) return true; } +/* Notify all slow path virtqueues on an interrupt. */ +static void vp_vring_slow_path_interrupt(int irq, + struct virtio_pci_device *vp_dev) +{ + struct virtio_pci_vq_info *info; + unsigned long flags; + + spin_lock_irqsave(&vp_dev->lock, flags); + list_for_each_entry(info, &vp_dev->slow_virtqueues, node) + vring_interrupt(irq, info->vq); + spin_unlock_irqrestore(&vp_dev->lock, flags); +} + /* Handle a configuration change: Tell driver if it wants to know. */ static irqreturn_t vp_config_changed(int irq, void *opaque) { struct virtio_pci_device *vp_dev = opaque; virtio_config_changed(&vp_dev->vdev); + vp_vring_slow_path_interrupt(irq, vp_dev); return IRQ_HANDLED; } @@ -125,6 +139,9 @@ static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors, GFP_KERNEL)) goto error; + if (!per_vq_vectors) + desc = NULL; + if (desc) { flags |= PCI_IRQ_AFFINITY; desc->pre_vectors++; /* virtio config vector */ @@ -171,11 +188,17 @@ error: return err; } +static bool vp_is_slow_path_vector(u16 msix_vec) +{ + return msix_vec == VP_MSIX_CONFIG_VECTOR; +} + static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned int index, void (*callback)(struct virtqueue *vq), const char *name, bool ctx, - u16 msix_vec) + u16 msix_vec, + struct virtio_pci_vq_info **p_info) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); struct virtio_pci_vq_info *info = kmalloc(sizeof *info, GFP_KERNEL); @@ -194,13 +217,16 @@ static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned int in info->vq = vq; if (callback) { spin_lock_irqsave(&vp_dev->lock, flags); - list_add(&info->node, &vp_dev->virtqueues); + if (!vp_is_slow_path_vector(msix_vec)) + list_add(&info->node, &vp_dev->virtqueues); + else + list_add(&info->node, &vp_dev->slow_virtqueues); spin_unlock_irqrestore(&vp_dev->lock, flags); } else { INIT_LIST_HEAD(&info->node); } - vp_dev->vqs[index] = info; + *p_info = info; return vq; out_info: @@ -236,13 +262,11 @@ 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 && vp_dev->is_avq(vdev, vq->index)) - continue; - if (vp_dev->per_vq_vectors) { int v = vp_dev->vqs[vq->index]->msix_vector; - if (v != VIRTIO_MSI_NO_VECTOR) { + if (v != VIRTIO_MSI_NO_VECTOR && + !vp_is_slow_path_vector(v)) { int irq = pci_irq_vector(vp_dev->pci_dev, v); irq_update_affinity_hint(irq, NULL); @@ -284,21 +308,85 @@ void vp_del_vqs(struct virtio_device *vdev) vp_dev->vqs = NULL; } +enum vp_vq_vector_policy { + VP_VQ_VECTOR_POLICY_EACH, + VP_VQ_VECTOR_POLICY_SHARED_SLOW, + VP_VQ_VECTOR_POLICY_SHARED, +}; + +static struct virtqueue * +vp_find_one_vq_msix(struct virtio_device *vdev, int queue_idx, + vq_callback_t *callback, const char *name, bool ctx, + bool slow_path, int *allocated_vectors, + enum vp_vq_vector_policy vector_policy, + struct virtio_pci_vq_info **p_info) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtqueue *vq; + u16 msix_vec; + int err; + + if (!callback) + msix_vec = VIRTIO_MSI_NO_VECTOR; + else if (vector_policy == VP_VQ_VECTOR_POLICY_EACH || + (vector_policy == VP_VQ_VECTOR_POLICY_SHARED_SLOW && + !slow_path)) + msix_vec = (*allocated_vectors)++; + else if (vector_policy != VP_VQ_VECTOR_POLICY_EACH && + slow_path) + msix_vec = VP_MSIX_CONFIG_VECTOR; + else + msix_vec = VP_MSIX_VQ_VECTOR; + vq = vp_setup_vq(vdev, queue_idx, callback, name, ctx, msix_vec, + p_info); + if (IS_ERR(vq)) + return vq; + + if (vector_policy == VP_VQ_VECTOR_POLICY_SHARED || + msix_vec == VIRTIO_MSI_NO_VECTOR || + vp_is_slow_path_vector(msix_vec)) + return vq; + + /* allocate per-vq irq if available and necessary */ + snprintf(vp_dev->msix_names[msix_vec], sizeof(*vp_dev->msix_names), + "%s-%s", dev_name(&vp_dev->vdev.dev), name); + err = request_irq(pci_irq_vector(vp_dev->pci_dev, msix_vec), + vring_interrupt, 0, + vp_dev->msix_names[msix_vec], vq); + if (err) { + vp_del_vq(vq); + return ERR_PTR(err); + } + + return vq; +} + static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs, struct virtqueue *vqs[], struct virtqueue_info vqs_info[], - bool per_vq_vectors, + enum vp_vq_vector_policy vector_policy, struct irq_affinity *desc) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_pci_admin_vq *avq = &vp_dev->admin_vq; struct virtqueue_info *vqi; - u16 msix_vec; int i, err, nvectors, allocated_vectors, queue_idx = 0; + struct virtqueue *vq; + bool per_vq_vectors; + u16 avq_num = 0; vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL); if (!vp_dev->vqs) return -ENOMEM; + if (vp_dev->avq_index) { + err = vp_dev->avq_index(vdev, &avq->vq_index, &avq_num); + if (err) + goto error_find; + } + + per_vq_vectors = vector_policy != VP_VQ_VECTOR_POLICY_SHARED; + if (per_vq_vectors) { /* Best option: one for change interrupt, one per vq. */ nvectors = 1; @@ -307,13 +395,14 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs, if (vqi->name && vqi->callback) ++nvectors; } + if (avq_num && vector_policy == VP_VQ_VECTOR_POLICY_EACH) + ++nvectors; } else { /* Second best: one for change, shared for all vqs. */ nvectors = 2; } - err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors, - per_vq_vectors ? desc : NULL); + err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors, desc); if (err) goto error_find; @@ -325,37 +414,27 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs, vqs[i] = NULL; continue; } - - if (!vqi->callback) - msix_vec = VIRTIO_MSI_NO_VECTOR; - else if (vp_dev->per_vq_vectors) - msix_vec = allocated_vectors++; - else - msix_vec = VP_MSIX_VQ_VECTOR; - vqs[i] = vp_setup_vq(vdev, queue_idx++, vqi->callback, - vqi->name, vqi->ctx, msix_vec); + vqs[i] = vp_find_one_vq_msix(vdev, queue_idx++, vqi->callback, + vqi->name, vqi->ctx, false, + &allocated_vectors, vector_policy, + &vp_dev->vqs[i]); if (IS_ERR(vqs[i])) { err = PTR_ERR(vqs[i]); goto error_find; } + } - if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR) - continue; - - /* allocate per-vq irq if available and necessary */ - snprintf(vp_dev->msix_names[msix_vec], - sizeof *vp_dev->msix_names, - "%s-%s", - dev_name(&vp_dev->vdev.dev), vqi->name); - err = request_irq(pci_irq_vector(vp_dev->pci_dev, msix_vec), - vring_interrupt, 0, - vp_dev->msix_names[msix_vec], - vqs[i]); - if (err) { - vp_del_vq(vqs[i]); - goto error_find; - } + if (!avq_num) + return 0; + sprintf(avq->name, "avq.%u", avq->vq_index); + vq = vp_find_one_vq_msix(vdev, avq->vq_index, vp_modern_avq_done, + avq->name, false, true, &allocated_vectors, + vector_policy, &vp_dev->admin_vq.info); + if (IS_ERR(vq)) { + err = PTR_ERR(vq); + goto error_find; } + return 0; error_find: @@ -368,12 +447,21 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs, struct virtqueue_info vqs_info[]) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_pci_admin_vq *avq = &vp_dev->admin_vq; int i, err, queue_idx = 0; + struct virtqueue *vq; + u16 avq_num = 0; vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL); if (!vp_dev->vqs) return -ENOMEM; + if (vp_dev->avq_index) { + err = vp_dev->avq_index(vdev, &avq->vq_index, &avq_num); + if (err) + goto out_del_vqs; + } + err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED, dev_name(&vdev->dev), vp_dev); if (err) @@ -390,13 +478,24 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs, } vqs[i] = vp_setup_vq(vdev, queue_idx++, vqi->callback, vqi->name, vqi->ctx, - VIRTIO_MSI_NO_VECTOR); + VIRTIO_MSI_NO_VECTOR, &vp_dev->vqs[i]); if (IS_ERR(vqs[i])) { err = PTR_ERR(vqs[i]); goto out_del_vqs; } } + if (!avq_num) + return 0; + sprintf(avq->name, "avq.%u", avq->vq_index); + vq = vp_setup_vq(vdev, queue_idx++, vp_modern_avq_done, avq->name, + false, VIRTIO_MSI_NO_VECTOR, + &vp_dev->admin_vq.info); + if (IS_ERR(vq)) { + err = PTR_ERR(vq); + goto out_del_vqs; + } + return 0; out_del_vqs: vp_del_vqs(vdev); @@ -411,11 +510,20 @@ int vp_find_vqs(struct virtio_device *vdev, unsigned int nvqs, int err; /* Try MSI-X with one vector per queue. */ - err = vp_find_vqs_msix(vdev, nvqs, vqs, vqs_info, true, desc); + err = vp_find_vqs_msix(vdev, nvqs, vqs, vqs_info, + VP_VQ_VECTOR_POLICY_EACH, desc); + if (!err) + return 0; + /* Fallback: MSI-X with one shared vector for config and + * slow path queues, one vector per queue for the rest. + */ + err = vp_find_vqs_msix(vdev, nvqs, vqs, vqs_info, + VP_VQ_VECTOR_POLICY_SHARED_SLOW, desc); if (!err) return 0; /* Fallback: MSI-X with one vector for config, one shared for queues. */ - err = vp_find_vqs_msix(vdev, nvqs, vqs, vqs_info, false, desc); + err = vp_find_vqs_msix(vdev, nvqs, vqs, vqs_info, + VP_VQ_VECTOR_POLICY_SHARED, desc); if (!err) return 0; /* Is there an interrupt? If not give up. */ @@ -466,7 +574,8 @@ const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index) struct virtio_pci_device *vp_dev = to_vp_device(vdev); if (!vp_dev->per_vq_vectors || - vp_dev->vqs[index]->msix_vector == VIRTIO_MSI_NO_VECTOR) + vp_dev->vqs[index]->msix_vector == VIRTIO_MSI_NO_VECTOR || + vp_is_slow_path_vector(vp_dev->vqs[index]->msix_vector)) return NULL; return pci_irq_get_affinity(vp_dev->pci_dev, @@ -574,6 +683,7 @@ static int virtio_pci_probe(struct pci_dev *pci_dev, vp_dev->vdev.dev.release = virtio_pci_release_dev; vp_dev->pci_dev = pci_dev; INIT_LIST_HEAD(&vp_dev->virtqueues); + INIT_LIST_HEAD(&vp_dev->slow_virtqueues); spin_lock_init(&vp_dev->lock); /* enable the device */ diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index 3c4bb2d6163a..1d9c49947f52 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -35,7 +35,7 @@ struct virtio_pci_vq_info { /* the actual virtqueue */ struct virtqueue *vq; - /* the list node for the virtqueues list */ + /* the list node for the virtqueues or slow_virtqueues list */ struct list_head node; /* MSI-X vector (or none) */ @@ -44,9 +44,9 @@ 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; + struct virtio_pci_vq_info *info; + /* Protects virtqueue access. */ + spinlock_t lock; u64 supported_cmds; /* Name of the admin queue: avq.$vq_index. */ char name[10]; @@ -66,9 +66,12 @@ struct virtio_pci_device { /* Where to read and clear interrupt */ u8 __iomem *isr; - /* a list of queues so we can dispatch IRQs */ + /* Lists of queues and potentially slow path queues + * so we can dispatch IRQs. + */ spinlock_t lock; struct list_head virtqueues; + struct list_head slow_virtqueues; /* Array of all virtqueues reported in the * PCI common config num_queues field @@ -102,7 +105,7 @@ 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); + int (*avq_index)(struct virtio_device *vdev, u16 *index, u16 *num); }; /* Constants for MSI-X */ @@ -175,6 +178,7 @@ struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev); #define VIRTIO_ADMIN_CMD_BITMAP 0 #endif +void vp_modern_avq_done(struct virtqueue *vq); int vp_modern_admin_cmd_exec(struct virtio_device *vdev, struct virtio_admin_cmd *cmd); diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index 3b5b9499a53a..9193c30d640a 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -28,6 +28,21 @@ static u64 vp_get_features(struct virtio_device *vdev) return vp_modern_get_features(&vp_dev->mdev); } +static int vp_avq_index(struct virtio_device *vdev, u16 *index, u16 *num) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + + *num = 0; + if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) + return 0; + + *num = vp_modern_avq_num(&vp_dev->mdev); + if (!(*num)) + return -EINVAL; + *index = vp_modern_avq_index(&vp_dev->mdev); + return 0; +} + static bool vp_is_avq(struct virtio_device *vdev, unsigned int index) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); @@ -38,17 +53,35 @@ static bool vp_is_avq(struct virtio_device *vdev, unsigned int index) return index == vp_dev->admin_vq.vq_index; } +void vp_modern_avq_done(struct virtqueue *vq) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); + struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq; + struct virtio_admin_cmd *cmd; + unsigned long flags; + unsigned int len; + + spin_lock_irqsave(&admin_vq->lock, flags); + do { + virtqueue_disable_cb(vq); + while ((cmd = virtqueue_get_buf(vq, &len))) + complete(&cmd->completion); + } while (!virtqueue_enable_cb(vq)); + spin_unlock_irqrestore(&admin_vq->lock, flags); +} + static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq, u16 opcode, struct scatterlist **sgs, unsigned int out_num, unsigned int in_num, - void *data) + struct virtio_admin_cmd *cmd) { struct virtqueue *vq; - int ret, len; + unsigned long flags; + int ret; - vq = admin_vq->info.vq; + vq = admin_vq->info->vq; if (!vq) return -EIO; @@ -57,21 +90,33 @@ static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq, !((1ULL << opcode) & admin_vq->supported_cmds)) return -EOPNOTSUPP; - ret = virtqueue_add_sgs(vq, sgs, out_num, in_num, data, GFP_KERNEL); - if (ret < 0) - return -EIO; + init_completion(&cmd->completion); - if (unlikely(!virtqueue_kick(vq))) +again: + if (virtqueue_is_broken(vq)) return -EIO; - while (!virtqueue_get_buf(vq, &len) && - !virtqueue_is_broken(vq)) - cpu_relax(); + spin_lock_irqsave(&admin_vq->lock, flags); + ret = virtqueue_add_sgs(vq, sgs, out_num, in_num, cmd, GFP_KERNEL); + if (ret < 0) { + if (ret == -ENOSPC) { + spin_unlock_irqrestore(&admin_vq->lock, flags); + cpu_relax(); + goto again; + } + goto unlock_err; + } + if (!virtqueue_kick(vq)) + goto unlock_err; + spin_unlock_irqrestore(&admin_vq->lock, flags); - if (virtqueue_is_broken(vq)) - return -EIO; + wait_for_completion(&cmd->completion); - return 0; + return cmd->ret; + +unlock_err: + spin_unlock_irqrestore(&admin_vq->lock, flags); + return -EIO; } int vp_modern_admin_cmd_exec(struct virtio_device *vdev, @@ -122,12 +167,9 @@ int vp_modern_admin_cmd_exec(struct virtio_device *vdev, in_num++; } - mutex_lock(&vp_dev->admin_vq.cmd_lock); ret = virtqueue_exec_admin_cmd(&vp_dev->admin_vq, le16_to_cpu(cmd->opcode), - sgs, out_num, in_num, sgs); - mutex_unlock(&vp_dev->admin_vq.cmd_lock); - + sgs, out_num, in_num, cmd); if (ret) { dev_err(&vdev->dev, "Failed to execute command on admin vq: %d\n.", ret); @@ -188,25 +230,29 @@ end: 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); virtio_pci_admin_cmd_list_init(vdev); } -static void vp_modern_avq_deactivate(struct virtio_device *vdev) +static void vp_modern_avq_cleanup(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; + struct virtio_admin_cmd *cmd; + struct virtqueue *vq; if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) return; - __virtqueue_break(admin_vq->info.vq); + vq = vp_dev->vqs[vp_dev->admin_vq.vq_index]->vq; + if (!vq) + return; + + while ((cmd = virtqueue_detach_unused_buf(vq))) { + cmd->ret = -EIO; + complete(&cmd->completion); + } } static void vp_transport_features(struct virtio_device *vdev, u64 features) @@ -403,7 +449,7 @@ static void vp_reset(struct virtio_device *vdev) while (vp_modern_get_status(mdev)) msleep(1); - vp_modern_avq_deactivate(vdev); + vp_modern_avq_cleanup(vdev); /* Flush pending VQ/configuration callbacks. */ vp_synchronize_vectors(vdev); @@ -552,8 +598,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, 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); + num = vp_modern_get_queue_size(mdev, index); /* Check if queue is either not available or already active. */ if (!num || vp_modern_get_queue_enable(mdev, index)) return ERR_PTR(-ENOENT); @@ -580,12 +625,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, goto err; } - 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; err: @@ -620,12 +659,6 @@ 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)) { - 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, VIRTIO_MSI_NO_VECTOR); @@ -735,45 +768,6 @@ 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, @@ -792,8 +786,6 @@ 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 = { @@ -814,8 +806,6 @@ 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 */ @@ -839,11 +829,11 @@ 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->avq_index = vp_avq_index; vp_dev->isr = mdev->isr; vp_dev->vdev.id = mdev->id; - mutex_init(&vp_dev->admin_vq.cmd_lock); + spin_lock_init(&vp_dev->admin_vq.lock); return 0; } @@ -851,6 +841,5 @@ 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/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 498442d0c216..2e49d978f504 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1223,8 +1223,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, block_group->space_info->total_bytes -= block_group->length; block_group->space_info->bytes_readonly -= (block_group->length - block_group->zone_unusable); - block_group->space_info->bytes_zone_unusable -= - block_group->zone_unusable; + btrfs_space_info_update_bytes_zone_unusable(fs_info, block_group->space_info, + -block_group->zone_unusable); block_group->space_info->disk_total -= block_group->length * factor; spin_unlock(&block_group->space_info->lock); @@ -1396,7 +1396,8 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force) if (btrfs_is_zoned(cache->fs_info)) { /* Migrate zone_unusable bytes to readonly */ sinfo->bytes_readonly += cache->zone_unusable; - sinfo->bytes_zone_unusable -= cache->zone_unusable; + btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo, + -cache->zone_unusable); cache->zone_unusable = 0; } cache->ro++; @@ -3056,9 +3057,11 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group *cache) if (btrfs_is_zoned(cache->fs_info)) { /* Migrate zone_unusable bytes back */ cache->zone_unusable = - (cache->alloc_offset - cache->used) + + (cache->alloc_offset - cache->used - cache->pinned - + cache->reserved) + (cache->length - cache->zone_capacity); - sinfo->bytes_zone_unusable += cache->zone_unusable; + btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo, + cache->zone_unusable); sinfo->bytes_readonly -= cache->zone_unusable; } num_bytes = cache->length - cache->reserved - diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index c8568b1a61c4..75fa563e4cac 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -459,6 +459,7 @@ struct btrfs_file_private { void *filldir_buf; u64 last_index; struct extent_state *llseek_cached_state; + bool fsync_skip_inode_lock; }; static inline u32 BTRFS_LEAF_DATA_SIZE(const struct btrfs_fs_info *info) diff --git a/fs/btrfs/direct-io.c b/fs/btrfs/direct-io.c index f9fb2db6a1e4..67adbe9d294a 100644 --- a/fs/btrfs/direct-io.c +++ b/fs/btrfs/direct-io.c @@ -856,21 +856,37 @@ relock: * So here we disable page faults in the iov_iter and then retry if we * got -EFAULT, faulting in the pages before the retry. */ +again: from->nofault = true; dio = btrfs_dio_write(iocb, from, written); from->nofault = false; - /* - * iomap_dio_complete() will call btrfs_sync_file() if we have a dsync - * iocb, and that needs to lock the inode. So unlock it before calling - * iomap_dio_complete() to avoid a deadlock. - */ - btrfs_inode_unlock(BTRFS_I(inode), ilock_flags); - - if (IS_ERR_OR_NULL(dio)) + if (IS_ERR_OR_NULL(dio)) { ret = PTR_ERR_OR_ZERO(dio); - else + } else { + struct btrfs_file_private stack_private = { 0 }; + struct btrfs_file_private *private; + const bool have_private = (file->private_data != NULL); + + if (!have_private) + file->private_data = &stack_private; + + /* + * If we have a synchronous write, we must make sure the fsync + * triggered by the iomap_dio_complete() call below doesn't + * deadlock on the inode lock - we are already holding it and we + * can't call it after unlocking because we may need to complete + * partial writes due to the input buffer (or parts of it) not + * being already faulted in. + */ + private = file->private_data; + private->fsync_skip_inode_lock = true; ret = iomap_dio_complete(dio); + private->fsync_skip_inode_lock = false; + + if (!have_private) + file->private_data = NULL; + } /* No increment (+=) because iomap returns a cumulative value. */ if (ret > 0) @@ -897,10 +913,12 @@ relock: } else { fault_in_iov_iter_readable(from, left); prev_left = left; - goto relock; + goto again; } } + btrfs_inode_unlock(BTRFS_I(inode), ilock_flags); + /* * If 'ret' is -ENOTBLK or we have not written all data, then it means * we must fallback to buffered IO. diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index d77498e7671c..ff9f0d41987e 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2793,7 +2793,8 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info, readonly = true; } else if (btrfs_is_zoned(fs_info)) { /* Need reset before reusing in a zoned block group */ - space_info->bytes_zone_unusable += len; + btrfs_space_info_update_bytes_zone_unusable(fs_info, space_info, + len); readonly = true; } spin_unlock(&cache->lock); diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 81558f90ee80..23b65dc73c00 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -664,7 +664,7 @@ static noinline int merge_extent_mapping(struct btrfs_inode *inode, start_diff = start - em->start; em->start = start; em->len = end - start; - if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE && !extent_map_is_compressed(em)) + if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE) em->offset += start_diff; return add_extent_mapping(inode, em, 0); } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 21381de906f6..9f10a9f23fcc 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1603,6 +1603,7 @@ static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx) */ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) { + struct btrfs_file_private *private = file->private_data; struct dentry *dentry = file_dentry(file); struct btrfs_inode *inode = BTRFS_I(d_inode(dentry)); struct btrfs_root *root = inode->root; @@ -1612,6 +1613,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) int ret = 0, err; u64 len; bool full_sync; + const bool skip_ilock = (private ? private->fsync_skip_inode_lock : false); trace_btrfs_sync_file(file, datasync); @@ -1639,7 +1641,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) if (ret) goto out; - btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP); + if (skip_ilock) + down_write(&inode->i_mmap_lock); + else + btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP); atomic_inc(&root->log_batch); @@ -1663,7 +1668,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) */ ret = start_ordered_ops(inode, start, end); if (ret) { - btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP); + if (skip_ilock) + up_write(&inode->i_mmap_lock); + else + btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP); goto out; } @@ -1788,7 +1796,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) * file again, but that will end up using the synchronization * inside btrfs_sync_log to keep things safe. */ - btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP); + if (skip_ilock) + up_write(&inode->i_mmap_lock); + else + btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP); if (ret == BTRFS_NO_LOG_SYNC) { ret = btrfs_end_transaction(trans); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 3f9b7507543a..f5996a43db24 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -2723,8 +2723,10 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, * If the block group is read-only, we should account freed space into * bytes_readonly. */ - if (!block_group->ro) + if (!block_group->ro) { block_group->zone_unusable += to_unusable; + WARN_ON(block_group->zone_unusable > block_group->length); + } spin_unlock(&ctl->tree_lock); if (!used) { spin_lock(&block_group->lock); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 01eab6955647..19d05a4c5c33 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -714,8 +714,9 @@ out: return ret; } -static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 offset, - u64 end, +static noinline int cow_file_range_inline(struct btrfs_inode *inode, + struct page *locked_page, + u64 offset, u64 end, size_t compressed_size, int compress_type, struct folio *compressed_folio, @@ -739,7 +740,10 @@ static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 offset, return ret; } - extent_clear_unlock_delalloc(inode, offset, end, NULL, &cached, + if (ret == 0) + locked_page = NULL; + + extent_clear_unlock_delalloc(inode, offset, end, locked_page, &cached, clear_flags, PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK); @@ -1043,10 +1047,10 @@ again: * extent for the subpage case. */ if (total_in < actual_end) - ret = cow_file_range_inline(inode, start, end, 0, + ret = cow_file_range_inline(inode, NULL, start, end, 0, BTRFS_COMPRESS_NONE, NULL, false); else - ret = cow_file_range_inline(inode, start, end, total_compressed, + ret = cow_file_range_inline(inode, NULL, start, end, total_compressed, compress_type, folios[0], false); if (ret <= 0) { if (ret < 0) @@ -1359,7 +1363,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode, if (!no_inline) { /* lets try to make an inline extent */ - ret = cow_file_range_inline(inode, start, end, 0, + ret = cow_file_range_inline(inode, locked_page, start, end, 0, BTRFS_COMPRESS_NONE, NULL, false); if (ret <= 0) { /* @@ -5660,7 +5664,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry) struct inode *inode; struct btrfs_root *root = BTRFS_I(dir)->root; struct btrfs_root *sub_root = root; - struct btrfs_key location; + struct btrfs_key location = { 0 }; u8 di_type = 0; int ret = 0; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 9ac94d3119e8..68e14fd48638 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -316,7 +316,7 @@ void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info, found->bytes_used += block_group->used; found->disk_used += block_group->used * factor; found->bytes_readonly += block_group->bytes_super; - found->bytes_zone_unusable += block_group->zone_unusable; + btrfs_space_info_update_bytes_zone_unusable(info, found, block_group->zone_unusable); if (block_group->length > 0) found->full = 0; btrfs_try_granting_tickets(info, found); @@ -583,8 +583,7 @@ again: spin_lock(&cache->lock); avail = cache->length - cache->used - cache->pinned - - cache->reserved - cache->delalloc_bytes - - cache->bytes_super - cache->zone_unusable; + cache->reserved - cache->bytes_super - cache->zone_unusable; btrfs_info(fs_info, "block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %llu delalloc %llu super %llu zone_unusable (%llu bytes available) %s", cache->start, cache->length, cache->used, cache->pinned, diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index 4db8a0267c16..88b44221ce97 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -249,6 +249,7 @@ btrfs_space_info_update_##name(struct btrfs_fs_info *fs_info, \ DECLARE_SPACE_INFO_UPDATE(bytes_may_use, "space_info"); DECLARE_SPACE_INFO_UPDATE(bytes_pinned, "pinned"); +DECLARE_SPACE_INFO_UPDATE(bytes_zone_unusable, "zone_unusable"); int btrfs_init_space_info(struct btrfs_fs_info *fs_info); void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info, diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c index ebec4ab361b8..56e61ac1cc64 100644 --- a/fs/btrfs/tests/extent-map-tests.c +++ b/fs/btrfs/tests/extent-map-tests.c @@ -900,6 +900,102 @@ out: return ret; } +/* + * Test a regression for compressed extent map adjustment when we attempt to + * add an extent map that is partially overlapped by another existing extent + * map. The resulting extent map offset was left unchanged despite having + * incremented its start offset. + */ +static int test_case_8(struct btrfs_fs_info *fs_info, struct btrfs_inode *inode) +{ + struct extent_map_tree *em_tree = &inode->extent_tree; + struct extent_map *em; + int ret; + int ret2; + + em = alloc_extent_map(); + if (!em) { + test_std_err(TEST_ALLOC_EXTENT_MAP); + return -ENOMEM; + } + + /* Compressed extent for the file range [120K, 128K). */ + em->start = SZ_1K * 120; + em->len = SZ_8K; + em->disk_num_bytes = SZ_4K; + em->ram_bytes = SZ_8K; + em->flags |= EXTENT_FLAG_COMPRESS_ZLIB; + write_lock(&em_tree->lock); + ret = btrfs_add_extent_mapping(inode, &em, em->start, em->len); + write_unlock(&em_tree->lock); + free_extent_map(em); + if (ret < 0) { + test_err("couldn't add extent map for range [120K, 128K)"); + goto out; + } + + em = alloc_extent_map(); + if (!em) { + test_std_err(TEST_ALLOC_EXTENT_MAP); + ret = -ENOMEM; + goto out; + } + + /* + * Compressed extent for the file range [108K, 144K), which overlaps + * with the [120K, 128K) we previously inserted. + */ + em->start = SZ_1K * 108; + em->len = SZ_1K * 36; + em->disk_num_bytes = SZ_4K; + em->ram_bytes = SZ_1K * 36; + em->flags |= EXTENT_FLAG_COMPRESS_ZLIB; + + /* + * Try to add the extent map but with a search range of [140K, 144K), + * this should succeed and adjust the extent map to the range + * [128K, 144K), with a length of 16K and an offset of 20K. + * + * This simulates a scenario where in the subvolume tree of an inode we + * have a compressed file extent item for the range [108K, 144K) and we + * have an overlapping compressed extent map for the range [120K, 128K), + * which was created by an encoded write, but its ordered extent was not + * yet completed, so the subvolume tree doesn't have yet the file extent + * item for that range - we only have the extent map in the inode's + * extent map tree. + */ + write_lock(&em_tree->lock); + ret = btrfs_add_extent_mapping(inode, &em, SZ_1K * 140, SZ_4K); + write_unlock(&em_tree->lock); + free_extent_map(em); + if (ret < 0) { + test_err("couldn't add extent map for range [108K, 144K)"); + goto out; + } + + if (em->start != SZ_128K) { + test_err("unexpected extent map start %llu (should be 128K)", em->start); + ret = -EINVAL; + goto out; + } + if (em->len != SZ_16K) { + test_err("unexpected extent map length %llu (should be 16K)", em->len); + ret = -EINVAL; + goto out; + } + if (em->offset != SZ_1K * 20) { + test_err("unexpected extent map offset %llu (should be 20K)", em->offset); + ret = -EINVAL; + goto out; + } +out: + ret2 = free_extent_map_tree(inode); + if (ret == 0) + ret = ret2; + + return ret; +} + struct rmap_test_vector { u64 raid_type; u64 physical_start; @@ -1078,6 +1174,9 @@ int btrfs_test_extent_map(void) ret = test_case_7(fs_info, BTRFS_I(inode)); if (ret) goto out; + ret = test_case_8(fs_info, BTRFS_I(inode)); + if (ret) + goto out; test_msg("running rmap tests"); for (i = 0; i < ARRAY_SIZE(rmap_tests); i++) { diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 6388786fd8b5..a825fa598e3c 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -634,7 +634,7 @@ static int check_dir_item(struct extent_buffer *leaf, */ if (key->type == BTRFS_DIR_ITEM_KEY || key->type == BTRFS_XATTR_ITEM_KEY) { - char namebuf[max(BTRFS_NAME_LEN, XATTR_NAME_MAX)]; + char namebuf[MAX(BTRFS_NAME_LEN, XATTR_NAME_MAX)]; read_extent_buffer(leaf, namebuf, (unsigned long)(di + 1), name_len); @@ -1289,6 +1289,19 @@ static void extent_err(const struct extent_buffer *eb, int slot, va_end(args); } +static bool is_valid_dref_root(u64 rootid) +{ + /* + * The following tree root objectids are allowed to have a data backref: + * - subvolume trees + * - data reloc tree + * - tree root + * For v1 space cache + */ + return is_fstree(rootid) || rootid == BTRFS_DATA_RELOC_TREE_OBJECTID || + rootid == BTRFS_ROOT_TREE_OBJECTID; +} + static int check_extent_item(struct extent_buffer *leaf, struct btrfs_key *key, int slot, struct btrfs_key *prev_key) @@ -1441,6 +1454,8 @@ static int check_extent_item(struct extent_buffer *leaf, struct btrfs_extent_data_ref *dref; struct btrfs_shared_data_ref *sref; u64 seq; + u64 dref_root; + u64 dref_objectid; u64 dref_offset; u64 inline_offset; u8 inline_type; @@ -1484,11 +1499,26 @@ static int check_extent_item(struct extent_buffer *leaf, */ case BTRFS_EXTENT_DATA_REF_KEY: dref = (struct btrfs_extent_data_ref *)(&iref->offset); + dref_root = btrfs_extent_data_ref_root(leaf, dref); + dref_objectid = btrfs_extent_data_ref_objectid(leaf, dref); dref_offset = btrfs_extent_data_ref_offset(leaf, dref); seq = hash_extent_data_ref( btrfs_extent_data_ref_root(leaf, dref), btrfs_extent_data_ref_objectid(leaf, dref), btrfs_extent_data_ref_offset(leaf, dref)); + if (unlikely(!is_valid_dref_root(dref_root))) { + extent_err(leaf, slot, + "invalid data ref root value %llu", + dref_root); + return -EUCLEAN; + } + if (unlikely(dref_objectid < BTRFS_FIRST_FREE_OBJECTID || + dref_objectid > BTRFS_LAST_FREE_OBJECTID)) { + extent_err(leaf, slot, + "invalid data ref objectid value %llu", + dref_root); + return -EUCLEAN; + } if (unlikely(!IS_ALIGNED(dref_offset, fs_info->sectorsize))) { extent_err(leaf, slot, @@ -1627,6 +1657,8 @@ static int check_extent_data_ref(struct extent_buffer *leaf, return -EUCLEAN; } for (; ptr < end; ptr += sizeof(*dref)) { + u64 root; + u64 objectid; u64 offset; /* @@ -1634,7 +1666,22 @@ static int check_extent_data_ref(struct extent_buffer *leaf, * overflow from the leaf due to hash collisions. */ dref = (struct btrfs_extent_data_ref *)ptr; + root = btrfs_extent_data_ref_root(leaf, dref); + objectid = btrfs_extent_data_ref_objectid(leaf, dref); offset = btrfs_extent_data_ref_offset(leaf, dref); + if (unlikely(!is_valid_dref_root(root))) { + extent_err(leaf, slot, + "invalid extent data backref root value %llu", + root); + return -EUCLEAN; + } + if (unlikely(objectid < BTRFS_FIRST_FREE_OBJECTID || + objectid > BTRFS_LAST_FREE_OBJECTID)) { + extent_err(leaf, slot, + "invalid extent data backref objectid value %llu", + root); + return -EUCLEAN; + } if (unlikely(!IS_ALIGNED(offset, leaf->fs_info->sectorsize))) { extent_err(leaf, slot, "invalid extent data backref offset, have %llu expect aligned to %u", diff --git a/fs/file.c b/fs/file.c index a3b72aa64f11..a11e59b5d602 100644 --- a/fs/file.c +++ b/fs/file.c @@ -1248,6 +1248,7 @@ __releases(&files->file_lock) * tables and this condition does not arise without those. */ fdt = files_fdtable(files); + fd = array_index_nospec(fd, fdt->max_fds); tofree = fdt->fd[fd]; if (!tofree && fd_is_open(fd, fdt)) goto Ebusy; diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 2594553bb30b..2df665fa2964 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -297,6 +297,15 @@ static inline void *offset_to_ptr(const int *off) #define is_unsigned_type(type) (!is_signed_type(type)) /* + * Useful shorthand for "is this condition known at compile-time?" + * + * Note that the condition may involve non-constant values, + * but the compiler may know enough about the details of the + * values to determine that the condition is statically true. + */ +#define statically_true(x) (__builtin_constant_p(x) && (x)) + +/* * This is needed in functions which generate the stack canary, see * arch/x86/kernel/smpboot.c::start_secondary() for an example. */ diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 51ba681b915a..affdd890899e 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -100,7 +100,6 @@ enum cpuhp_state { CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, - CPUHP_PROFILE_PREPARE, CPUHP_X2APIC_PREPARE, CPUHP_SMPCFD_PREPARE, CPUHP_RELAY_PREPARE, diff --git a/include/linux/minmax.h b/include/linux/minmax.h index 9c2848abc804..98008dd92153 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -26,19 +26,63 @@ #define __typecheck(x, y) \ (!!(sizeof((typeof(x) *)1 == (typeof(y) *)1))) -/* is_signed_type() isn't a constexpr for pointer types */ -#define __is_signed(x) \ - __builtin_choose_expr(__is_constexpr(is_signed_type(typeof(x))), \ - is_signed_type(typeof(x)), 0) +/* + * __sign_use for integer expressions: + * bit #0 set if ok for unsigned comparisons + * bit #1 set if ok for signed comparisons + * + * In particular, statically non-negative signed integer + * expressions are ok for both. + * + * NOTE! Unsigned types smaller than 'int' are implicitly + * converted to 'int' in expressions, and are accepted for + * signed conversions for now. This is debatable. + * + * Note that 'x' is the original expression, and 'ux' is + * the unique variable that contains the value. + * + * We use 'ux' for pure type checking, and 'x' for when + * we need to look at the value (but without evaluating + * it for side effects! Careful to only ever evaluate it + * with sizeof() or __builtin_constant_p() etc). + * + * Pointers end up being checked by the normal C type + * rules at the actual comparison, and these expressions + * only need to be careful to not cause warnings for + * pointer use. + */ +#define __signed_type_use(x,ux) (2+__is_nonneg(x,ux)) +#define __unsigned_type_use(x,ux) (1+2*(sizeof(ux)<4)) +#define __sign_use(x,ux) (is_signed_type(typeof(ux))? \ + __signed_type_use(x,ux):__unsigned_type_use(x,ux)) -/* True for a non-negative signed int constant */ -#define __is_noneg_int(x) \ - (__builtin_choose_expr(__is_constexpr(x) && __is_signed(x), x, -1) >= 0) +/* + * To avoid warnings about casting pointers to integers + * of different sizes, we need that special sign type. + * + * On 64-bit we can just always use 'long', since any + * integer or pointer type can just be cast to that. + * + * This does not work for 128-bit signed integers since + * the cast would truncate them, but we do not use s128 + * types in the kernel (we do use 'u128', but they will + * be handled by the !is_signed_type() case). + * + * NOTE! The cast is there only to avoid any warnings + * from when values that aren't signed integer types. + */ +#ifdef CONFIG_64BIT + #define __signed_type(ux) long +#else + #define __signed_type(ux) typeof(__builtin_choose_expr(sizeof(ux)>4,1LL,1L)) +#endif +#define __is_nonneg(x,ux) statically_true((__signed_type(ux))(x)>=0) + +#define __types_ok(x,y,ux,uy) \ + (__sign_use(x,ux) & __sign_use(y,uy)) -#define __types_ok(x, y) \ - (__is_signed(x) == __is_signed(y) || \ - __is_signed((x) + 0) == __is_signed((y) + 0) || \ - __is_noneg_int(x) || __is_noneg_int(y)) +#define __types_ok3(x,y,z,ux,uy,uz) \ + (__sign_use(x,ux) & __sign_use(y,uy) & __sign_use(z,uz)) #define __cmp_op_min < #define __cmp_op_max > @@ -51,34 +95,31 @@ #define __cmp_once(op, type, x, y) \ __cmp_once_unique(op, type, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_)) -#define __careful_cmp_once(op, x, y) ({ \ - static_assert(__types_ok(x, y), \ - #op "(" #x ", " #y ") signedness error, fix types or consider u" #op "() before " #op "_t()"); \ - __cmp_once(op, __auto_type, x, y); }) +#define __careful_cmp_once(op, x, y, ux, uy) ({ \ + __auto_type ux = (x); __auto_type uy = (y); \ + BUILD_BUG_ON_MSG(!__types_ok(x,y,ux,uy), \ + #op"("#x", "#y") signedness error"); \ + __cmp(op, ux, uy); }) -#define __careful_cmp(op, x, y) \ - __builtin_choose_expr(__is_constexpr((x) - (y)), \ - __cmp(op, x, y), __careful_cmp_once(op, x, y)) +#define __careful_cmp(op, x, y) \ + __careful_cmp_once(op, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_)) #define __clamp(val, lo, hi) \ ((val) >= (hi) ? (hi) : ((val) <= (lo) ? (lo) : (val))) -#define __clamp_once(val, lo, hi, unique_val, unique_lo, unique_hi) ({ \ - typeof(val) unique_val = (val); \ - typeof(lo) unique_lo = (lo); \ - typeof(hi) unique_hi = (hi); \ +#define __clamp_once(val, lo, hi, uval, ulo, uhi) ({ \ + __auto_type uval = (val); \ + __auto_type ulo = (lo); \ + __auto_type uhi = (hi); \ static_assert(__builtin_choose_expr(__is_constexpr((lo) > (hi)), \ (lo) <= (hi), true), \ "clamp() low limit " #lo " greater than high limit " #hi); \ - static_assert(__types_ok(val, lo), "clamp() 'lo' signedness error"); \ - static_assert(__types_ok(val, hi), "clamp() 'hi' signedness error"); \ - __clamp(unique_val, unique_lo, unique_hi); }) + BUILD_BUG_ON_MSG(!__types_ok3(val,lo,hi,uval,ulo,uhi), \ + "clamp("#val", "#lo", "#hi") signedness error"); \ + __clamp(uval, ulo, uhi); }) -#define __careful_clamp(val, lo, hi) ({ \ - __builtin_choose_expr(__is_constexpr((val) - (lo) + (hi)), \ - __clamp(val, lo, hi), \ - __clamp_once(val, lo, hi, __UNIQUE_ID(__val), \ - __UNIQUE_ID(__lo), __UNIQUE_ID(__hi))); }) +#define __careful_clamp(val, lo, hi) \ + __clamp_once(val, lo, hi, __UNIQUE_ID(v_), __UNIQUE_ID(l_), __UNIQUE_ID(h_)) /** * min - return minimum of two values of the same or compatible types @@ -111,13 +152,20 @@ #define umax(x, y) \ __careful_cmp(max, (x) + 0u + 0ul + 0ull, (y) + 0u + 0ul + 0ull) +#define __careful_op3(op, x, y, z, ux, uy, uz) ({ \ + __auto_type ux = (x); __auto_type uy = (y);__auto_type uz = (z);\ + BUILD_BUG_ON_MSG(!__types_ok3(x,y,z,ux,uy,uz), \ + #op"3("#x", "#y", "#z") signedness error"); \ + __cmp(op, ux, __cmp(op, uy, uz)); }) + /** * min3 - return minimum of three values * @x: first value * @y: second value * @z: third value */ -#define min3(x, y, z) min((typeof(x))min(x, y), z) +#define min3(x, y, z) \ + __careful_op3(min, x, y, z, __UNIQUE_ID(x_), __UNIQUE_ID(y_), __UNIQUE_ID(z_)) /** * max3 - return maximum of three values @@ -125,7 +173,8 @@ * @y: second value * @z: third value */ -#define max3(x, y, z) max((typeof(x))max(x, y), z) +#define max3(x, y, z) \ + __careful_op3(max, x, y, z, __UNIQUE_ID(x_), __UNIQUE_ID(y_), __UNIQUE_ID(z_)) /** * min_not_zero - return the minimum that is _not_ zero, unless both are zero @@ -277,6 +326,8 @@ static inline bool in_range32(u32 val, u32 start, u32 len) * Use these carefully: no type checking, and uses the arguments * multiple times. Use for obvious constants only. */ +#define MIN(a,b) __cmp(min,a,b) +#define MAX(a,b) __cmp(max,a,b) #define MIN_T(type,a,b) __cmp(min,(type)(a),(type)(b)) #define MAX_T(type,a,b) __cmp(max,(type)(a),(type)(b)) diff --git a/include/linux/virtio.h b/include/linux/virtio.h index ecc5cb7b8c91..4b16844c6bc2 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -10,6 +10,7 @@ #include <linux/mod_devicetable.h> #include <linux/gfp.h> #include <linux/dma-mapping.h> +#include <linux/completion.h> /** * struct virtqueue - a queue to register buffers for sending or receiving. @@ -109,6 +110,8 @@ struct virtio_admin_cmd { __le64 group_member_id; struct scatterlist *data_sg; struct scatterlist *result_sg; + struct completion completion; + int ret; }; /** diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index ab4b9a3fef6b..169c7d367fac 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -104,8 +104,6 @@ struct virtqueue_info { * 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, @@ -133,8 +131,6 @@ 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_net.h b/include/linux/virtio_net.h index d1d7825318c3..6c395a2600e8 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -56,7 +56,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, unsigned int thlen = 0; unsigned int p_off = 0; unsigned int ip_proto; - u64 ret, remainder, gso_size; if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { @@ -99,16 +98,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset); u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16)); - if (hdr->gso_size) { - gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); - ret = div64_u64_rem(skb->len, gso_size, &remainder); - if (!(ret && (hdr->gso_size > needed) && - ((remainder > needed) || (remainder == 0)))) { - return -EINVAL; - } - skb_shinfo(skb)->tx_flags |= SKBFL_SHARED_FRAG; - } - if (!pskb_may_pull(skb, needed)) return -EINVAL; @@ -182,6 +171,11 @@ retry: if (gso_type != SKB_GSO_UDP_L4) return -EINVAL; break; + case SKB_GSO_TCPV4: + case SKB_GSO_TCPV6: + if (skb->csum_offset != offsetof(struct tcphdr, check)) + return -EINVAL; + break; } /* Kernel has a special handling for GSO_BY_FRAGS. */ diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 246c0fbd582e..0a523023bdcc 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -2383,6 +2383,14 @@ DEFINE_EVENT(btrfs__space_info_update, update_bytes_pinned, TP_ARGS(fs_info, sinfo, old, diff) ); +DEFINE_EVENT(btrfs__space_info_update, update_bytes_zone_unusable, + + TP_PROTO(const struct btrfs_fs_info *fs_info, + const struct btrfs_space_info *sinfo, u64 old, s64 diff), + + TP_ARGS(fs_info, sinfo, old, diff) +); + DECLARE_EVENT_CLASS(btrfs_raid56_bio, TP_PROTO(const struct btrfs_raid_bio *rbio, diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h index 09e72215b9f9..085b749cdd97 100644 --- a/include/trace/events/mptcp.h +++ b/include/trace/events/mptcp.h @@ -34,7 +34,7 @@ TRACE_EVENT(mptcp_subflow_get_send, struct sock *ssk; __entry->active = mptcp_subflow_active(subflow); - __entry->backup = subflow->backup; + __entry->backup = subflow->backup || subflow->request_bkup; if (subflow->tcp_sock && sk_fullsock(subflow->tcp_sock)) __entry->free = sk_stream_memory_free(subflow->tcp_sock); diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 07fb5987b42b..1bab21b4718f 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -92,7 +92,14 @@ static ssize_t profiling_store(struct kobject *kobj, const char *buf, size_t count) { int ret; + static DEFINE_MUTEX(lock); + /* + * We need serialization, for profile_setup() initializes prof_on + * value and profile_init() must not reallocate prof_buffer after + * once allocated. + */ + guard(mutex)(&lock); if (prof_on) return -EEXIST; /* diff --git a/kernel/profile.c b/kernel/profile.c index 2b775cc5c28f..ff68d3816182 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -47,13 +47,6 @@ static unsigned short int prof_shift; int prof_on __read_mostly; EXPORT_SYMBOL_GPL(prof_on); -static cpumask_var_t prof_cpu_mask; -#if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS) -static DEFINE_PER_CPU(struct profile_hit *[2], cpu_profile_hits); -static DEFINE_PER_CPU(int, cpu_profile_flip); -static DEFINE_MUTEX(profile_flip_mutex); -#endif /* CONFIG_SMP */ - int profile_setup(char *str) { static const char schedstr[] = "schedule"; @@ -114,11 +107,6 @@ int __ref profile_init(void) buffer_bytes = prof_len*sizeof(atomic_t); - if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL)) - return -ENOMEM; - - cpumask_copy(prof_cpu_mask, cpu_possible_mask); - prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL|__GFP_NOWARN); if (prof_buffer) return 0; @@ -132,195 +120,16 @@ int __ref profile_init(void) if (prof_buffer) return 0; - free_cpumask_var(prof_cpu_mask); return -ENOMEM; } -#if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS) -/* - * Each cpu has a pair of open-addressed hashtables for pending - * profile hits. read_profile() IPI's all cpus to request them - * to flip buffers and flushes their contents to prof_buffer itself. - * Flip requests are serialized by the profile_flip_mutex. The sole - * use of having a second hashtable is for avoiding cacheline - * contention that would otherwise happen during flushes of pending - * profile hits required for the accuracy of reported profile hits - * and so resurrect the interrupt livelock issue. - * - * The open-addressed hashtables are indexed by profile buffer slot - * and hold the number of pending hits to that profile buffer slot on - * a cpu in an entry. When the hashtable overflows, all pending hits - * are accounted to their corresponding profile buffer slots with - * atomic_add() and the hashtable emptied. As numerous pending hits - * may be accounted to a profile buffer slot in a hashtable entry, - * this amortizes a number of atomic profile buffer increments likely - * to be far larger than the number of entries in the hashtable, - * particularly given that the number of distinct profile buffer - * positions to which hits are accounted during short intervals (e.g. - * several seconds) is usually very small. Exclusion from buffer - * flipping is provided by interrupt disablement (note that for - * SCHED_PROFILING or SLEEP_PROFILING profile_hit() may be called from - * process context). - * The hash function is meant to be lightweight as opposed to strong, - * and was vaguely inspired by ppc64 firmware-supported inverted - * pagetable hash functions, but uses a full hashtable full of finite - * collision chains, not just pairs of them. - * - * -- nyc - */ -static void __profile_flip_buffers(void *unused) -{ - int cpu = smp_processor_id(); - - per_cpu(cpu_profile_flip, cpu) = !per_cpu(cpu_profile_flip, cpu); -} - -static void profile_flip_buffers(void) -{ - int i, j, cpu; - - mutex_lock(&profile_flip_mutex); - j = per_cpu(cpu_profile_flip, get_cpu()); - put_cpu(); - on_each_cpu(__profile_flip_buffers, NULL, 1); - for_each_online_cpu(cpu) { - struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[j]; - for (i = 0; i < NR_PROFILE_HIT; ++i) { - if (!hits[i].hits) { - if (hits[i].pc) - hits[i].pc = 0; - continue; - } - atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]); - hits[i].hits = hits[i].pc = 0; - } - } - mutex_unlock(&profile_flip_mutex); -} - -static void profile_discard_flip_buffers(void) -{ - int i, cpu; - - mutex_lock(&profile_flip_mutex); - i = per_cpu(cpu_profile_flip, get_cpu()); - put_cpu(); - on_each_cpu(__profile_flip_buffers, NULL, 1); - for_each_online_cpu(cpu) { - struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[i]; - memset(hits, 0, NR_PROFILE_HIT*sizeof(struct profile_hit)); - } - mutex_unlock(&profile_flip_mutex); -} - -static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) -{ - unsigned long primary, secondary, flags, pc = (unsigned long)__pc; - int i, j, cpu; - struct profile_hit *hits; - - pc = min((pc - (unsigned long)_stext) >> prof_shift, prof_len - 1); - i = primary = (pc & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT; - secondary = (~(pc << 1) & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT; - cpu = get_cpu(); - hits = per_cpu(cpu_profile_hits, cpu)[per_cpu(cpu_profile_flip, cpu)]; - if (!hits) { - put_cpu(); - return; - } - /* - * We buffer the global profiler buffer into a per-CPU - * queue and thus reduce the number of global (and possibly - * NUMA-alien) accesses. The write-queue is self-coalescing: - */ - local_irq_save(flags); - do { - for (j = 0; j < PROFILE_GRPSZ; ++j) { - if (hits[i + j].pc == pc) { - hits[i + j].hits += nr_hits; - goto out; - } else if (!hits[i + j].hits) { - hits[i + j].pc = pc; - hits[i + j].hits = nr_hits; - goto out; - } - } - i = (i + secondary) & (NR_PROFILE_HIT - 1); - } while (i != primary); - - /* - * Add the current hit(s) and flush the write-queue out - * to the global buffer: - */ - atomic_add(nr_hits, &prof_buffer[pc]); - for (i = 0; i < NR_PROFILE_HIT; ++i) { - atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]); - hits[i].pc = hits[i].hits = 0; - } -out: - local_irq_restore(flags); - put_cpu(); -} - -static int profile_dead_cpu(unsigned int cpu) -{ - struct page *page; - int i; - - if (cpumask_available(prof_cpu_mask)) - cpumask_clear_cpu(cpu, prof_cpu_mask); - - for (i = 0; i < 2; i++) { - if (per_cpu(cpu_profile_hits, cpu)[i]) { - page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[i]); - per_cpu(cpu_profile_hits, cpu)[i] = NULL; - __free_page(page); - } - } - return 0; -} - -static int profile_prepare_cpu(unsigned int cpu) -{ - int i, node = cpu_to_mem(cpu); - struct page *page; - - per_cpu(cpu_profile_flip, cpu) = 0; - - for (i = 0; i < 2; i++) { - if (per_cpu(cpu_profile_hits, cpu)[i]) - continue; - - page = __alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); - if (!page) { - profile_dead_cpu(cpu); - return -ENOMEM; - } - per_cpu(cpu_profile_hits, cpu)[i] = page_address(page); - - } - return 0; -} - -static int profile_online_cpu(unsigned int cpu) -{ - if (cpumask_available(prof_cpu_mask)) - cpumask_set_cpu(cpu, prof_cpu_mask); - - return 0; -} - -#else /* !CONFIG_SMP */ -#define profile_flip_buffers() do { } while (0) -#define profile_discard_flip_buffers() do { } while (0) - static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) { unsigned long pc; pc = ((unsigned long)__pc - (unsigned long)_stext) >> prof_shift; - atomic_add(nr_hits, &prof_buffer[min(pc, prof_len - 1)]); + if (pc < prof_len) + atomic_add(nr_hits, &prof_buffer[pc]); } -#endif /* !CONFIG_SMP */ void profile_hits(int type, void *__pc, unsigned int nr_hits) { @@ -334,8 +143,8 @@ void profile_tick(int type) { struct pt_regs *regs = get_irq_regs(); - if (!user_mode(regs) && cpumask_available(prof_cpu_mask) && - cpumask_test_cpu(smp_processor_id(), prof_cpu_mask)) + /* This is the old kernel-only legacy profiling */ + if (!user_mode(regs)) profile_hit(type, (void *)profile_pc(regs)); } @@ -358,7 +167,6 @@ read_profile(struct file *file, char __user *buf, size_t count, loff_t *ppos) char *pnt; unsigned long sample_step = 1UL << prof_shift; - profile_flip_buffers(); if (p >= (prof_len+1)*sizeof(unsigned int)) return 0; if (count > (prof_len+1)*sizeof(unsigned int) - p) @@ -404,7 +212,6 @@ static ssize_t write_profile(struct file *file, const char __user *buf, return -EINVAL; } #endif - profile_discard_flip_buffers(); memset(prof_buffer, 0, prof_len * sizeof(atomic_t)); return count; } @@ -418,40 +225,14 @@ static const struct proc_ops profile_proc_ops = { int __ref create_proc_profile(void) { struct proc_dir_entry *entry; -#ifdef CONFIG_SMP - enum cpuhp_state online_state; -#endif - int err = 0; if (!prof_on) return 0; -#ifdef CONFIG_SMP - err = cpuhp_setup_state(CPUHP_PROFILE_PREPARE, "PROFILE_PREPARE", - profile_prepare_cpu, profile_dead_cpu); - if (err) - return err; - - err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_PROFILE_ONLINE", - profile_online_cpu, NULL); - if (err < 0) - goto err_state_prep; - online_state = err; - err = 0; -#endif entry = proc_create("profile", S_IWUSR | S_IRUGO, NULL, &profile_proc_ops); - if (!entry) - goto err_state_onl; - proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t)); - - return err; -err_state_onl: -#ifdef CONFIG_SMP - cpuhp_remove_state(online_state); -err_state_prep: - cpuhp_remove_state(CPUHP_PROFILE_PREPARE); -#endif + if (entry) + proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t)); return err; } subsys_initcall(create_proc_profile); diff --git a/kernel/task_work.c b/kernel/task_work.c index 5c2daa7ad3f9..5d14d639ac71 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -6,12 +6,14 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */ +#ifdef CONFIG_IRQ_WORK static void task_work_set_notify_irq(struct irq_work *entry) { test_and_set_tsk_thread_flag(current, TIF_NOTIFY_RESUME); } static DEFINE_PER_CPU(struct irq_work, irq_work_NMI_resume) = IRQ_WORK_INIT_HARD(task_work_set_notify_irq); +#endif /** * task_work_add - ask the @task to execute @work->func() @@ -57,6 +59,8 @@ int task_work_add(struct task_struct *task, struct callback_head *work, if (notify == TWA_NMI_CURRENT) { if (WARN_ON_ONCE(task != current)) return -EINVAL; + if (!IS_ENABLED(CONFIG_IRQ_WORK)) + return -EINVAL; } else { /* record the work call stack in order to print it in KASAN reports */ kasan_record_aux_stack(work); @@ -81,9 +85,11 @@ int task_work_add(struct task_struct *task, struct callback_head *work, case TWA_SIGNAL_NO_IPI: __set_notify_signal(task); break; +#ifdef CONFIG_IRQ_WORK case TWA_NMI_CURRENT: irq_work_queue(this_cpu_ptr(&irq_work_NMI_resume)); break; +#endif default: WARN_ON_ONCE(1); break; diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c index cb0871fbdb07..314ffc143039 100644 --- a/kernel/trace/preemptirq_delay_test.c +++ b/kernel/trace/preemptirq_delay_test.c @@ -34,8 +34,6 @@ MODULE_PARM_DESC(cpu_affinity, "Cpu num test is running on"); static struct completion done; -#define MIN(x, y) ((x) < (y) ? (x) : (y)) - static void busy_wait(ulong time) { u64 start, end; diff --git a/lib/btree.c b/lib/btree.c index 49420cae3a83..bb81d3393ac5 100644 --- a/lib/btree.c +++ b/lib/btree.c @@ -43,7 +43,6 @@ #include <linux/slab.h> #include <linux/module.h> -#define MAX(a, b) ((a) > (b) ? (a) : (b)) #define NODESIZE MAX(L1_CACHE_BYTES, 128) struct btree_geo { diff --git a/lib/decompress_unlzma.c b/lib/decompress_unlzma.c index 20a858031f12..9d34d35908da 100644 --- a/lib/decompress_unlzma.c +++ b/lib/decompress_unlzma.c @@ -37,7 +37,9 @@ #include <linux/decompress/mm.h> +#ifndef MIN #define MIN(a, b) (((a) < (b)) ? (a) : (b)) +#endif static long long INIT read_int(unsigned char *ptr, int size) { diff --git a/lib/vsprintf.c b/lib/vsprintf.c index cdd4e2314bfc..2d71b1115916 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -1080,7 +1080,7 @@ char *resource_string(char *buf, char *end, struct resource *res, #define FLAG_BUF_SIZE (2 * sizeof(res->flags)) #define DECODED_BUF_SIZE sizeof("[mem - 64bit pref window disabled]") #define RAW_BUF_SIZE sizeof("[mem - flags 0x]") - char sym[max(2*RSRC_BUF_SIZE + DECODED_BUF_SIZE, + char sym[MAX(2*RSRC_BUF_SIZE + DECODED_BUF_SIZE, 2*RSRC_BUF_SIZE + FLAG_BUF_SIZE + RAW_BUF_SIZE)]; char *p = sym, *pend = sym + sizeof(sym); diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 5d6581ab7c07..2d3163e4da96 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -120,8 +120,6 @@ #define CLASS_BITS 8 #define MAGIC_VAL_BITS 8 -#define MAX(a, b) ((a) >= (b) ? (a) : (b)) - #define ZS_MAX_PAGES_PER_ZSPAGE (_AC(CONFIG_ZSMALLOC_CHAIN_SIZE, UL)) /* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */ diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 8a4ebd93adfc..06da8ac13dca 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -119,13 +119,6 @@ void hci_discovery_set_state(struct hci_dev *hdev, int state) case DISCOVERY_STARTING: break; case DISCOVERY_FINDING: - /* If discovery was not started then it was initiated by the - * MGMT interface so no MGMT event shall be generated either - */ - if (old_state != DISCOVERY_STARTING) { - hdev->discovery.state = old_state; - return; - } mgmt_discovering(hdev, 1); break; case DISCOVERY_RESOLVING: diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index dce8035ca799..d0c118c47f6c 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1721,9 +1721,10 @@ static void le_set_scan_enable_complete(struct hci_dev *hdev, u8 enable) switch (enable) { case LE_SCAN_ENABLE: hci_dev_set_flag(hdev, HCI_LE_SCAN); - if (hdev->le_scan_type == LE_SCAN_ACTIVE) + if (hdev->le_scan_type == LE_SCAN_ACTIVE) { clear_pending_adv_report(hdev); - hci_discovery_set_state(hdev, DISCOVERY_FINDING); + hci_discovery_set_state(hdev, DISCOVERY_FINDING); + } break; case LE_SCAN_DISABLE: diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index cd2ed16da8a4..a31d39a821f4 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -2976,6 +2976,27 @@ static int hci_passive_scan_sync(struct hci_dev *hdev) */ filter_policy = hci_update_accept_list_sync(hdev); + /* If suspended and filter_policy set to 0x00 (no acceptlist) then + * passive scanning cannot be started since that would require the host + * to be woken up to process the reports. + */ + if (hdev->suspended && !filter_policy) { + /* Check if accept list is empty then there is no need to scan + * while suspended. + */ + if (list_empty(&hdev->le_accept_list)) + return 0; + + /* If there are devices is the accept_list that means some + * devices could not be programmed which in non-suspended case + * means filter_policy needs to be set to 0x00 so the host needs + * to filter, but since this is treating suspended case we + * can ignore device needing host to filter to allow devices in + * the acceptlist to be able to wakeup the system. + */ + filter_policy = 0x01; + } + /* When the controller is using random resolvable addresses and * with that having LE privacy enabled, then controllers with * Extended Scanner Filter Policies support can now enable support diff --git a/net/core/dev.c b/net/core/dev.c index 6ea1d20676fb..751d9b70e6ad 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5150,6 +5150,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb) bpf_net_ctx_clear(bpf_net_ctx); return XDP_DROP; } + bpf_net_ctx_clear(bpf_net_ctx); } return XDP_PASS; out_redir: diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 87e67194f240..73fd7f543fd0 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3288,7 +3288,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, if (ifm->ifi_index > 0) dev = __dev_get_by_index(tgt_net, ifm->ifi_index); else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) - dev = rtnl_dev_get(net, tb); + dev = rtnl_dev_get(tgt_net, tb); else if (tb[IFLA_GROUP]) err = rtnl_group_dellink(tgt_net, nla_get_u32(tb[IFLA_GROUP])); else diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 983fee76f5cf..8ca13208d240 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1331,13 +1331,13 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]); const struct ethtool_ops *ops = dev->ethtool_ops; u32 dev_indir_size = 0, dev_key_size = 0, i; + u32 user_indir_len = 0, indir_bytes = 0; struct ethtool_rxfh_param rxfh_dev = {}; struct ethtool_rxfh_context *ctx = NULL; struct netlink_ext_ack *extack = NULL; struct ethtool_rxnfc rx_rings; struct ethtool_rxfh rxfh; bool locked = false; /* dev->ethtool->rss_lock taken */ - u32 indir_bytes = 0; bool create = false; u8 *rss_config; int ret; @@ -1382,10 +1382,9 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, rxfh.input_xfrm == RXH_XFRM_NO_CHANGE)) return -EINVAL; - if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) - indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]); + indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]); - rss_config = kzalloc(indir_bytes + rxfh.key_size, GFP_USER); + rss_config = kzalloc(indir_bytes + dev_key_size, GFP_USER); if (!rss_config) return -ENOMEM; @@ -1400,6 +1399,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, */ if (rxfh.indir_size && rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) { + user_indir_len = indir_bytes; rxfh_dev.indir = (u32 *)rss_config; rxfh_dev.indir_size = dev_indir_size; ret = ethtool_copy_validate_indir(rxfh_dev.indir, @@ -1426,7 +1426,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, rxfh_dev.key_size = dev_key_size; rxfh_dev.key = rss_config + indir_bytes; if (copy_from_user(rxfh_dev.key, - useraddr + rss_cfg_offset + indir_bytes, + useraddr + rss_cfg_offset + user_indir_len, rxfh.key_size)) { ret = -EFAULT; goto out; @@ -1474,16 +1474,21 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, rxfh_dev.input_xfrm = rxfh.input_xfrm; if (rxfh.rss_context && ops->create_rxfh_context) { - if (create) + if (create) { ret = ops->create_rxfh_context(dev, ctx, &rxfh_dev, extack); - else if (rxfh_dev.rss_delete) + /* Make sure driver populates defaults */ + WARN_ON_ONCE(!ret && !rxfh_dev.key && + !memchr_inv(ethtool_rxfh_context_key(ctx), + 0, ctx->key_size)); + } else if (rxfh_dev.rss_delete) { ret = ops->remove_rxfh_context(dev, ctx, rxfh.rss_context, extack); - else + } else { ret = ops->modify_rxfh_context(dev, ctx, &rxfh_dev, extack); + } } else { ret = ops->set_rxfh(dev, &rxfh_dev, extack); } @@ -1522,6 +1527,22 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, kfree(ctx); goto out; } + + /* Fetch the defaults for the old API, in the new API drivers + * should write defaults into ctx themselves. + */ + rxfh_dev.indir = (u32 *)rss_config; + rxfh_dev.indir_size = dev_indir_size; + + rxfh_dev.key = rss_config + indir_bytes; + rxfh_dev.key_size = dev_key_size; + + ret = ops->get_rxfh(dev, &rxfh_dev); + if (WARN_ON(ret)) { + xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context); + kfree(ctx); + goto out; + } } if (rxfh_dev.rss_delete) { WARN_ON(xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context) != ctx); @@ -1530,12 +1551,14 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, if (rxfh_dev.indir) { for (i = 0; i < dev_indir_size; i++) ethtool_rxfh_context_indir(ctx)[i] = rxfh_dev.indir[i]; - ctx->indir_configured = 1; + ctx->indir_configured = + rxfh.indir_size && + rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE; } if (rxfh_dev.key) { memcpy(ethtool_rxfh_context_key(ctx), rxfh_dev.key, dev_key_size); - ctx->key_configured = 1; + ctx->key_configured = !!rxfh.key_size; } if (rxfh_dev.hfunc != ETH_RSS_HASH_NO_CHANGE) ctx->hfunc = rxfh_dev.hfunc; diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 71679137eff2..5c4c4505ab9a 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -111,7 +111,8 @@ rss_reply_size(const struct ethnl_req_info *req_base, const struct rss_reply_data *data = RSS_REPDATA(reply_base); int len; - len = nla_total_size(sizeof(u32)) + /* _RSS_HFUNC */ + len = nla_total_size(sizeof(u32)) + /* _RSS_CONTEXT */ + 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 +125,11 @@ rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct rss_reply_data *data = RSS_REPDATA(reply_base); + struct rss_req_info *request = RSS_REQINFO(req_base); + + if (request->rss_context && + nla_put_u32(skb, ETHTOOL_A_RSS_CONTEXT, request->rss_context)) + return -EMSGSIZE; if ((data->hfunc && nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) || diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 4d42d0756fd7..a5db7c67d61b 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -145,25 +145,27 @@ static struct pernet_operations iptable_nat_net_ops = { static int __init iptable_nat_init(void) { - int ret = xt_register_template(&nf_nat_ipv4_table, - iptable_nat_table_init); + int ret; + /* net->gen->ptr[iptable_nat_net_id] must be allocated + * before calling iptable_nat_table_init(). + */ + ret = register_pernet_subsys(&iptable_nat_net_ops); if (ret < 0) return ret; - ret = register_pernet_subsys(&iptable_nat_net_ops); - if (ret < 0) { - xt_unregister_template(&nf_nat_ipv4_table); - return ret; - } + ret = xt_register_template(&nf_nat_ipv4_table, + iptable_nat_table_init); + if (ret < 0) + unregister_pernet_subsys(&iptable_nat_net_ops); return ret; } static void __exit iptable_nat_exit(void) { - unregister_pernet_subsys(&iptable_nat_net_ops); xt_unregister_template(&nf_nat_ipv4_table); + unregister_pernet_subsys(&iptable_nat_net_ops); } module_init(iptable_nat_init); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 454362e359da..e2b9583ed96a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -754,8 +754,7 @@ void tcp_rcv_space_adjust(struct sock *sk) * <prev RTT . ><current RTT .. ><next RTT .... > */ - if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) && - !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)) { u64 rcvwin, grow; int rcvbuf; @@ -771,12 +770,22 @@ void tcp_rcv_space_adjust(struct sock *sk) rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin), READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); - if (rcvbuf > sk->sk_rcvbuf) { - WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); + if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { + if (rcvbuf > sk->sk_rcvbuf) { + WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); - /* Make the window clamp follow along. */ - WRITE_ONCE(tp->window_clamp, - tcp_win_from_space(sk, rcvbuf)); + /* Make the window clamp follow along. */ + WRITE_ONCE(tp->window_clamp, + tcp_win_from_space(sk, rcvbuf)); + } + } else { + /* Make the window clamp follow along while being bounded + * by SO_RCVBUF. + */ + int clamp = tcp_win_from_space(sk, min(rcvbuf, sk->sk_rcvbuf)); + + if (clamp > tp->window_clamp) + WRITE_ONCE(tp->window_clamp, clamp); } } tp->rcvq_space.space = copied; diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 4b791e74529e..e4ad3311e148 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -140,6 +140,9 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, if (thlen < sizeof(*th)) goto out; + if (unlikely(skb_checksum_start(skb) != skb_transport_header(skb))) + goto out; + if (!pskb_may_pull(skb, thlen)) goto out; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index aa2e0a28ca61..bc8a9da750fe 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -278,6 +278,10 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); + if (unlikely(skb_checksum_start(gso_skb) != + skb_transport_header(gso_skb))) + return ERR_PTR(-EINVAL); + if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 70a0b2ad6bd7..b8eec1b6cc2c 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -227,6 +227,7 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev, return NULL; memset(ndopts, 0, sizeof(*ndopts)); while (opt_len) { + bool unknown = false; int l; if (opt_len < sizeof(struct nd_opt_hdr)) return NULL; @@ -262,22 +263,23 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev, break; #endif default: - if (ndisc_is_useropt(dev, nd_opt)) { - ndopts->nd_useropts_end = nd_opt; - if (!ndopts->nd_useropts) - ndopts->nd_useropts = nd_opt; - } else { - /* - * Unknown options must be silently ignored, - * to accommodate future extension to the - * protocol. - */ - ND_PRINTK(2, notice, - "%s: ignored unsupported option; type=%d, len=%d\n", - __func__, - nd_opt->nd_opt_type, - nd_opt->nd_opt_len); - } + unknown = true; + } + if (ndisc_is_useropt(dev, nd_opt)) { + ndopts->nd_useropts_end = nd_opt; + if (!ndopts->nd_useropts) + ndopts->nd_useropts = nd_opt; + } else if (unknown) { + /* + * Unknown options must be silently ignored, + * to accommodate future extension to the + * protocol. + */ + ND_PRINTK(2, notice, + "%s: ignored unsupported option; type=%d, len=%d\n", + __func__, + nd_opt->nd_opt_type, + nd_opt->nd_opt_len); } next_opt: opt_len -= l; diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 52cf104e3478..e119d4f090cc 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -147,23 +147,27 @@ static struct pernet_operations ip6table_nat_net_ops = { static int __init ip6table_nat_init(void) { - int ret = xt_register_template(&nf_nat_ipv6_table, - ip6table_nat_table_init); + int ret; + /* net->gen->ptr[ip6table_nat_net_id] must be allocated + * before calling ip6t_nat_register_lookups(). + */ + ret = register_pernet_subsys(&ip6table_nat_net_ops); if (ret < 0) return ret; - ret = register_pernet_subsys(&ip6table_nat_net_ops); + ret = xt_register_template(&nf_nat_ipv6_table, + ip6table_nat_table_init); if (ret) - xt_unregister_template(&nf_nat_ipv6_table); + unregister_pernet_subsys(&ip6table_nat_net_ops); return ret; } static void __exit ip6table_nat_exit(void) { - unregister_pernet_subsys(&ip6table_nat_net_ops); xt_unregister_template(&nf_nat_ipv6_table); + unregister_pernet_subsys(&ip6table_nat_net_ops); } module_init(ip6table_nat_init); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index c3b0b610b0aa..c00323fa9eb6 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -335,8 +335,8 @@ static void iucv_sever_path(struct sock *sk, int with_user_data) struct iucv_sock *iucv = iucv_sk(sk); struct iucv_path *path = iucv->path; - if (iucv->path) { - iucv->path = NULL; + /* Whoever resets the path pointer, must sever and free it. */ + if (xchg(&iucv->path, NULL)) { if (with_user_data) { low_nmcpy(user_data, iucv->src_name); high_nmcpy(user_data, iucv->dst_name); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 85cb71de370f..b02b84ce2130 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -114,7 +114,7 @@ static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata, /* apply all changes now - no failures allowed */ - if (monitor_sdata) + if (monitor_sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) ieee80211_set_mu_mimo_follow(monitor_sdata, params); if (params->flags) { @@ -3053,6 +3053,9 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { + if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) + return -EOPNOTSUPP; + sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (!sdata) @@ -3115,7 +3118,7 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, if (has_monitor) { sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); - if (sdata) { + if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { sdata->deflink.user_power_level = local->user_power_level; if (txp_type != sdata->vif.bss_conf.txpower_type) update_txp_type = true; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 72a9ba8bc5fd..edba4a31844f 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1768,7 +1768,7 @@ static bool __ieee80211_tx(struct ieee80211_local *local, break; } sdata = rcu_dereference(local->monitor_sdata); - if (sdata) { + if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { vif = &sdata->vif; info->hw_queue = vif->hw_queue[skb_get_queue_mapping(skb)]; @@ -3957,7 +3957,8 @@ begin: break; } tx.sdata = rcu_dereference(local->monitor_sdata); - if (tx.sdata) { + if (tx.sdata && + ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { vif = &tx.sdata->vif; info->hw_queue = vif->hw_queue[skb_get_queue_mapping(skb)]; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index ced19ce7c51a..c7ad9bc5973a 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -776,7 +776,7 @@ static void __iterate_interfaces(struct ieee80211_local *local, sdata = rcu_dereference_check(local->monitor_sdata, lockdep_is_held(&local->iflist_mtx) || lockdep_is_held(&local->hw.wiphy->mtx)); - if (sdata && + if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) && (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || !active_only || sdata->flags & IEEE80211_SDATA_IN_DRIVER)) iterator(data, sdata->vif.addr, &sdata->vif); diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index c30405e76833..7884217f33eb 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -19,7 +19,9 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS), SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN), SNMP_MIB_ITEM("MPJoinSynRx", MPTCP_MIB_JOINSYNRX), + SNMP_MIB_ITEM("MPJoinSynBackupRx", MPTCP_MIB_JOINSYNBACKUPRX), SNMP_MIB_ITEM("MPJoinSynAckRx", MPTCP_MIB_JOINSYNACKRX), + SNMP_MIB_ITEM("MPJoinSynAckBackupRx", MPTCP_MIB_JOINSYNACKBACKUPRX), SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC), SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX), SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 2704afd0dfe4..66aa67f49d03 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -14,7 +14,9 @@ enum linux_mptcp_mib_field { MPTCP_MIB_RETRANSSEGS, /* Segments retransmitted at the MPTCP-level */ MPTCP_MIB_JOINNOTOKEN, /* Received MP_JOIN but the token was not found */ MPTCP_MIB_JOINSYNRX, /* Received a SYN + MP_JOIN */ + MPTCP_MIB_JOINSYNBACKUPRX, /* Received a SYN + MP_JOIN + backup flag */ MPTCP_MIB_JOINSYNACKRX, /* Received a SYN/ACK + MP_JOIN */ + MPTCP_MIB_JOINSYNACKBACKUPRX, /* Received a SYN/ACK + MP_JOIN + backup flag */ MPTCP_MIB_JOINSYNACKMAC, /* HMAC was wrong on SYN/ACK + MP_JOIN */ MPTCP_MIB_JOINACKRX, /* Received an ACK + MP_JOIN */ MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */ diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 8e8dcfbc2993..8a68382a4fe9 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -909,7 +909,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, return true; } else if (subflow_req->mp_join) { opts->suboptions = OPTION_MPTCP_MPJ_SYNACK; - opts->backup = subflow_req->backup; + opts->backup = subflow_req->request_bkup; opts->join_id = subflow_req->local_id; opts->thmac = subflow_req->thmac; opts->nonce = subflow_req->local_nonce; diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 55406720c607..23bb89c94e90 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -426,6 +426,18 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) return mptcp_pm_nl_get_local_id(msk, &skc_local); } +bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc) +{ + struct mptcp_addr_info skc_local; + + mptcp_local_address((struct sock_common *)skc, &skc_local); + + if (mptcp_pm_is_userspace(msk)) + return mptcp_userspace_pm_is_backup(msk, &skc_local); + + return mptcp_pm_nl_is_backup(msk, &skc_local); +} + int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, u8 *flags, int *ifindex) { diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index ea9e5817b9e9..37954a0b087d 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -471,7 +471,6 @@ static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_con slow = lock_sock_fast(ssk); if (prio) { subflow->send_mp_prio = 1; - subflow->backup = backup; subflow->request_bkup = backup; } @@ -1102,6 +1101,24 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc return ret; } +bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc) +{ + struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); + struct mptcp_pm_addr_entry *entry; + bool backup = false; + + rcu_read_lock(); + list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { + if (mptcp_addresses_equal(&entry->addr, skc, entry->addr.port)) { + backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP); + break; + } + } + rcu_read_unlock(); + + return backup; +} + #define MPTCP_PM_CMD_GRP_OFFSET 0 #define MPTCP_PM_EV_GRP_OFFSET 1 @@ -1401,6 +1418,7 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, ret = remove_anno_list_by_saddr(msk, addr); if (ret || force) { spin_lock_bh(&msk->pm.lock); + msk->pm.add_addr_signaled -= ret; mptcp_pm_remove_addr(msk, &list); spin_unlock_bh(&msk->pm.lock); } @@ -1534,16 +1552,25 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list) { struct mptcp_rm_list alist = { .nr = 0 }; struct mptcp_pm_addr_entry *entry; + int anno_nr = 0; list_for_each_entry(entry, rm_list, list) { - if ((remove_anno_list_by_saddr(msk, &entry->addr) || - lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) && - alist.nr < MPTCP_RM_IDS_MAX) - alist.ids[alist.nr++] = entry->addr.id; + if (alist.nr >= MPTCP_RM_IDS_MAX) + break; + + /* only delete if either announced or matching a subflow */ + if (remove_anno_list_by_saddr(msk, &entry->addr)) + anno_nr++; + else if (!lookup_subflow_by_saddr(&msk->conn_list, + &entry->addr)) + continue; + + alist.ids[alist.nr++] = entry->addr.id; } if (alist.nr) { spin_lock_bh(&msk->pm.lock); + msk->pm.add_addr_signaled -= anno_nr; mptcp_pm_remove_addr(msk, &alist); spin_unlock_bh(&msk->pm.lock); } @@ -1556,17 +1583,18 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, struct mptcp_pm_addr_entry *entry; list_for_each_entry(entry, rm_list, list) { - if (lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) && - slist.nr < MPTCP_RM_IDS_MAX) + if (slist.nr < MPTCP_RM_IDS_MAX && + lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) slist.ids[slist.nr++] = entry->addr.id; - if (remove_anno_list_by_saddr(msk, &entry->addr) && - alist.nr < MPTCP_RM_IDS_MAX) + if (alist.nr < MPTCP_RM_IDS_MAX && + remove_anno_list_by_saddr(msk, &entry->addr)) alist.ids[alist.nr++] = entry->addr.id; } if (alist.nr) { spin_lock_bh(&msk->pm.lock); + msk->pm.add_addr_signaled -= alist.nr; mptcp_pm_remove_addr(msk, &alist); spin_unlock_bh(&msk->pm.lock); } diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index f0a4590506c6..8eaa9fbe3e34 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -165,6 +165,24 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true); } +bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, + struct mptcp_addr_info *skc) +{ + struct mptcp_pm_addr_entry *entry; + bool backup = false; + + spin_lock_bh(&msk->pm.lock); + list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { + if (mptcp_addresses_equal(&entry->addr, skc, false)) { + backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP); + break; + } + } + spin_unlock_bh(&msk->pm.lock); + + return backup; +} + int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a26c2c840fd9..0d536b183a6c 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -350,8 +350,10 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, skb_orphan(skb); /* try to fetch required memory from subflow */ - if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) + if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); goto drop; + } has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; @@ -844,10 +846,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) sk_rbuf = ssk_rbuf; /* over limit? can't append more skbs to msk, Also, no need to wake-up*/ - if (__mptcp_rmem(sk) > sk_rbuf) { - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); + if (__mptcp_rmem(sk) > sk_rbuf) return; - } /* Wake-up the reader only for in-sequence data */ mptcp_data_lock(sk); @@ -1422,13 +1422,15 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) } mptcp_for_each_subflow(msk, subflow) { + bool backup = subflow->backup || subflow->request_bkup; + trace_mptcp_subflow_get_send(subflow); ssk = mptcp_subflow_tcp_sock(subflow); if (!mptcp_subflow_active(subflow)) continue; tout = max(tout, mptcp_timeout_from_subflow(subflow)); - nr_active += !subflow->backup; + nr_active += !backup; pace = subflow->avg_pacing_rate; if (unlikely(!pace)) { /* init pacing rate from socket */ @@ -1439,9 +1441,9 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) } linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace); - if (linger_time < send_info[subflow->backup].linger_time) { - send_info[subflow->backup].ssk = ssk; - send_info[subflow->backup].linger_time = linger_time; + if (linger_time < send_info[backup].linger_time) { + send_info[backup].ssk = ssk; + send_info[backup].linger_time = linger_time; } } __mptcp_set_timeout(sk, tout); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index b11a4e50d52b..60c6b073d65f 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -448,6 +448,7 @@ struct mptcp_subflow_request_sock { u16 mp_capable : 1, mp_join : 1, backup : 1, + request_bkup : 1, csum_reqd : 1, allow_join_id0 : 1; u8 local_id; @@ -1108,6 +1109,9 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); +bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc); +bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc); +bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc); int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb); int mptcp_pm_nl_dump_addr(struct sk_buff *msg, struct netlink_callback *cb); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 39e2cbdf3801..a21c712350c3 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -100,6 +100,7 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req) return NULL; } subflow_req->local_id = local_id; + subflow_req->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)req); return msk; } @@ -168,6 +169,9 @@ static int subflow_check_req(struct request_sock *req, return 0; } else if (opt_mp_join) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX); + + if (mp_opt.backup) + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX); } if (opt_mp_capable && listener->request_mptcp) { @@ -577,6 +581,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->mp_join = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX); + if (subflow->backup) + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKBACKUPRX); + if (subflow_use_different_dport(msk, sk)) { pr_debug("synack inet_dport=%d %d", ntohs(inet_sk(sk)->inet_dport), @@ -614,6 +621,8 @@ static int subflow_chk_local_id(struct sock *sk) return err; subflow_set_local_id(subflow, err); + subflow->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)sk); + return 0; } @@ -1221,14 +1230,22 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; - u32 incr; + struct tcp_sock *tp = tcp_sk(ssk); + u32 offset, incr, avail_len; - incr = limit >= skb->len ? skb->len + fin : limit; + offset = tp->copied_seq - TCP_SKB_CB(skb)->seq; + if (WARN_ON_ONCE(offset > skb->len)) + goto out; - pr_debug("discarding=%d len=%d seq=%d", incr, skb->len, - subflow->map_subflow_seq); + avail_len = skb->len - offset; + incr = limit >= avail_len ? avail_len + fin : limit; + + pr_debug("discarding=%d len=%d offset=%d seq=%d", incr, skb->len, + offset, subflow->map_subflow_seq); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA); tcp_sk(ssk)->copied_seq += incr; + +out: if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq)) sk_eat_skb(ssk, skb); if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) @@ -2005,6 +2022,7 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->fully_established = 1; new_ctx->remote_key_valid = 1; new_ctx->backup = subflow_req->backup; + new_ctx->request_bkup = subflow_req->request_bkup; WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id); new_ctx->token = subflow_req->token; new_ctx->thmac = subflow_req->thmac; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 113b907da0f7..3ba8e7e739b5 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -44,6 +44,8 @@ static DEFINE_MUTEX(zones_mutex); struct zones_ht_key { struct net *net; u16 zone; + /* Note : pad[] must be the last field. */ + u8 pad[]; }; struct tcf_ct_flow_table { @@ -60,7 +62,7 @@ struct tcf_ct_flow_table { static const struct rhashtable_params zones_params = { .head_offset = offsetof(struct tcf_ct_flow_table, node), .key_offset = offsetof(struct tcf_ct_flow_table, key), - .key_len = sizeof_field(struct tcf_ct_flow_table, key), + .key_len = offsetof(struct zones_ht_key, pad), .automatic_shrinking = true, }; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 73a875573e7a..8e3093938cd2 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -3319,10 +3319,8 @@ int smc_create_clcsk(struct net *net, struct sock *sk, int family) rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, &smc->clcsock); - if (rc) { - sk_common_release(sk); + if (rc) return rc; - } /* smc_clcsock_release() does not wait smc->clcsock->sk's * destruction; its sk_state might not be TCP_CLOSE after @@ -3368,6 +3366,9 @@ static int __smc_create(struct net *net, struct socket *sock, int protocol, smc->clcsock = clcsock; else rc = smc_create_clcsk(net, sk, family); + + if (rc) + sk_common_release(sk); out: return rc; } diff --git a/net/wireless/scan.c b/net/wireless/scan.c index d99319d82205..64eeed82d43d 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -3178,8 +3178,7 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, struct ieee80211_mgmt *mgmt, size_t len, gfp_t gfp) { - size_t min_hdr_len = offsetof(struct ieee80211_mgmt, - u.probe_resp.variable); + size_t min_hdr_len; struct ieee80211_ext *ext = NULL; enum cfg80211_bss_frame_type ftype; u16 beacon_interval; @@ -3202,10 +3201,16 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { ext = (void *) mgmt; - min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_beacon); if (ieee80211_is_s1g_short_beacon(mgmt->frame_control)) min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_short_beacon.variable); + else + min_hdr_len = offsetof(struct ieee80211_ext, + u.s1g_beacon.variable); + } else { + /* same for beacons */ + min_hdr_len = offsetof(struct ieee80211_mgmt, + u.probe_resp.variable); } if (WARN_ON(len < min_hdr_len)) diff --git a/net/wireless/sme.c b/net/wireless/sme.c index e419aa8c4a5a..d9d7bf8bb5c1 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1045,6 +1045,7 @@ void cfg80211_connect_done(struct net_device *dev, cfg80211_hold_bss( bss_from_pub(params->links[link].bss)); ev->cr.links[link].bss = params->links[link].bss; + ev->cr.links[link].status = params->links[link].status; if (params->links[link].addr) { ev->cr.links[link].addr = next; diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 489cbed7e82a..12796808f07a 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -82,7 +82,30 @@ FILES= \ FILES := $(addprefix $(OUTPUT),$(FILES)) -PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config +# Some distros provide the command $(CROSS_COMPILE)pkg-config for +# searching packges installed with Multiarch. Use it for cross +# compilation if it is existed. +ifneq (, $(shell which $(CROSS_COMPILE)pkg-config)) + PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config +else + PKG_CONFIG ?= pkg-config + + # PKG_CONFIG_PATH or PKG_CONFIG_LIBDIR, alongside PKG_CONFIG_SYSROOT_DIR + # for modified system root, are required for the cross compilation. + # If these PKG_CONFIG environment variables are not set, Multiarch library + # paths are used instead. + ifdef CROSS_COMPILE + ifeq ($(PKG_CONFIG_LIBDIR)$(PKG_CONFIG_PATH)$(PKG_CONFIG_SYSROOT_DIR),) + CROSS_ARCH = $(shell $(CC) -dumpmachine) + PKG_CONFIG_LIBDIR := /usr/local/$(CROSS_ARCH)/lib/pkgconfig/ + PKG_CONFIG_LIBDIR := $(PKG_CONFIG_LIBDIR):/usr/local/lib/$(CROSS_ARCH)/pkgconfig/ + PKG_CONFIG_LIBDIR := $(PKG_CONFIG_LIBDIR):/usr/lib/$(CROSS_ARCH)/pkgconfig/ + PKG_CONFIG_LIBDIR := $(PKG_CONFIG_LIBDIR):/usr/local/share/pkgconfig/ + PKG_CONFIG_LIBDIR := $(PKG_CONFIG_LIBDIR):/usr/share/pkgconfig/ + export PKG_CONFIG_LIBDIR + endif + endif +endif all: $(FILES) @@ -147,7 +170,17 @@ $(OUTPUT)test-libopencsd.bin: DWARFLIBS := -ldw ifeq ($(findstring -static,${LDFLAGS}),-static) -DWARFLIBS += -lelf -lebl -lz -llzma -lbz2 + DWARFLIBS += -lelf -lz -llzma -lbz2 -lzstd + + LIBDW_VERSION := $(shell $(PKG_CONFIG) --modversion libdw) + LIBDW_VERSION_1 := $(word 1, $(subst ., ,$(LIBDW_VERSION))) + LIBDW_VERSION_2 := $(word 2, $(subst ., ,$(LIBDW_VERSION))) + + # Elfutils merged libebl.a into libdw.a starting from version 0.177, + # Link libebl.a only if libdw is older than this version. + ifeq ($(shell test $(LIBDW_VERSION_2) -lt 177; echo $$?),0) + DWARFLIBS += -lebl + endif endif $(OUTPUT)test-dwarf.bin: @@ -178,27 +211,27 @@ $(OUTPUT)test-numa_num_possible_cpus.bin: $(BUILD) -lnuma $(OUTPUT)test-libunwind.bin: - $(BUILD) -lelf + $(BUILD) -lelf -llzma $(OUTPUT)test-libunwind-debug-frame.bin: - $(BUILD) -lelf + $(BUILD) -lelf -llzma $(OUTPUT)test-libunwind-x86.bin: - $(BUILD) -lelf -lunwind-x86 + $(BUILD) -lelf -llzma -lunwind-x86 $(OUTPUT)test-libunwind-x86_64.bin: - $(BUILD) -lelf -lunwind-x86_64 + $(BUILD) -lelf -llzma -lunwind-x86_64 $(OUTPUT)test-libunwind-arm.bin: - $(BUILD) -lelf -lunwind-arm + $(BUILD) -lelf -llzma -lunwind-arm $(OUTPUT)test-libunwind-aarch64.bin: - $(BUILD) -lelf -lunwind-aarch64 + $(BUILD) -lelf -llzma -lunwind-aarch64 $(OUTPUT)test-libunwind-debug-frame-arm.bin: - $(BUILD) -lelf -lunwind-arm + $(BUILD) -lelf -llzma -lunwind-arm $(OUTPUT)test-libunwind-debug-frame-aarch64.bin: - $(BUILD) -lelf -lunwind-aarch64 + $(BUILD) -lelf -llzma -lunwind-aarch64 $(OUTPUT)test-libaudit.bin: $(BUILD) -laudit diff --git a/tools/perf/Documentation/Build.txt b/tools/perf/Documentation/Build.txt index 3766886c4bca..83dc87c662b6 100644 --- a/tools/perf/Documentation/Build.txt +++ b/tools/perf/Documentation/Build.txt @@ -71,3 +71,31 @@ supported by GCC. UBSan detects undefined behaviors of programs at runtime. $ UBSAN_OPTIONS=print_stacktrace=1 ./perf record -a If UBSan detects any problem at runtime, it outputs a “runtime error:” message. + +4) Cross compilation +==================== +As Multiarch is commonly supported in Linux distributions, we can install +libraries for multiple architectures on the same system and then cross-compile +Linux perf. For example, Aarch64 libraries and toolchains can be installed on +an x86_64 machine, allowing us to compile perf for an Aarch64 target. + +Below is the command for building the perf with dynamic linking. + + $ cd /path/to/Linux + $ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- -C tools/perf + +For static linking, the option `LDFLAGS="-static"` is required. + + $ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- \ + LDFLAGS="-static" -C tools/perf + +In the embedded system world, a use case is to explicitly specify the package +configuration paths for cross building: + + $ PKG_CONFIG_SYSROOT_DIR="/path/to/cross/build/sysroot" \ + PKG_CONFIG_LIBDIR="/usr/lib/:/usr/local/lib" \ + make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- -C tools/perf + +In this case, the variable PKG_CONFIG_SYSROOT_DIR can be used alongside the +variable PKG_CONFIG_LIBDIR or PKG_CONFIG_PATH to prepend the sysroot path to +the library paths for cross compilation. diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index c896babf7a74..fa679db61f62 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -152,7 +152,17 @@ ifdef LIBDW_DIR endif DWARFLIBS := -ldw ifeq ($(findstring -static,${LDFLAGS}),-static) - DWARFLIBS += -lelf -lebl -ldl -lz -llzma -lbz2 + DWARFLIBS += -lelf -ldl -lz -llzma -lbz2 -lzstd + + LIBDW_VERSION := $(shell $(PKG_CONFIG) --modversion libdw) + LIBDW_VERSION_1 := $(word 1, $(subst ., ,$(LIBDW_VERSION))) + LIBDW_VERSION_2 := $(word 2, $(subst ., ,$(LIBDW_VERSION))) + + # Elfutils merged libebl.a into libdw.a starting from version 0.177, + # Link libebl.a only if libdw is older than this version. + ifeq ($(shell test $(LIBDW_VERSION_2) -lt 177; echo $$?),0) + DWARFLIBS += -lebl + endif endif FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS) FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) $(DWARFLIBS) @@ -296,6 +306,11 @@ endif ifdef PYTHON_CONFIG PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) $(PYTHON_CONFIG_LDFLAGS) 2>/dev/null) + # Update the python flags for cross compilation + ifdef CROSS_COMPILE + PYTHON_NATIVE := $(shell echo $(PYTHON_EMBED_LDOPTS) | sed 's/\(-L.*\/\)\(.*-linux-gnu\).*/\2/') + PYTHON_EMBED_LDOPTS := $(subst $(PYTHON_NATIVE),$(shell $(CC) -dumpmachine),$(PYTHON_EMBED_LDOPTS)) + endif PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS)) PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null) @@ -897,6 +912,9 @@ else PYTHON_SETUPTOOLS_INSTALLED := $(shell $(PYTHON) -c 'import setuptools;' 2> /dev/null && echo "yes" || echo "no") ifeq ($(PYTHON_SETUPTOOLS_INSTALLED), yes) PYTHON_EXTENSION_SUFFIX := $(shell $(PYTHON) -c 'from importlib import machinery; print(machinery.EXTENSION_SUFFIXES[0])') + ifdef CROSS_COMPILE + PYTHON_EXTENSION_SUFFIX := $(subst $(PYTHON_NATIVE),$(shell $(CC) -dumpmachine),$(PYTHON_EXTENSION_SUFFIX)) + endif LANG_BINDINGS += $(obj-perf)python/perf$(PYTHON_EXTENSION_SUFFIX) else $(warning Missing python setuptools, the python binding won't be built, please install python3-setuptools or equivalent) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 175e4c7898f0..f8148db5fc38 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -193,7 +193,32 @@ HOSTLD ?= ld HOSTAR ?= ar CLANG ?= clang -PKG_CONFIG = $(CROSS_COMPILE)pkg-config +# Some distros provide the command $(CROSS_COMPILE)pkg-config for +# searching packges installed with Multiarch. Use it for cross +# compilation if it is existed. +ifneq (, $(shell which $(CROSS_COMPILE)pkg-config)) + PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config +else + PKG_CONFIG ?= pkg-config + + # PKG_CONFIG_PATH or PKG_CONFIG_LIBDIR, alongside PKG_CONFIG_SYSROOT_DIR + # for modified system root, is required for the cross compilation. + # If these PKG_CONFIG environment variables are not set, Multiarch library + # paths are used instead. + ifdef CROSS_COMPILE + ifeq ($(PKG_CONFIG_LIBDIR)$(PKG_CONFIG_PATH)$(PKG_CONFIG_SYSROOT_DIR),) + CROSS_ARCH = $(shell $(CC) -dumpmachine) + PKG_CONFIG_LIBDIR := /usr/local/$(CROSS_ARCH)/lib/pkgconfig/ + PKG_CONFIG_LIBDIR := $(PKG_CONFIG_LIBDIR):/usr/local/lib/$(CROSS_ARCH)/pkgconfig/ + PKG_CONFIG_LIBDIR := $(PKG_CONFIG_LIBDIR):/usr/lib/$(CROSS_ARCH)/pkgconfig/ + PKG_CONFIG_LIBDIR := $(PKG_CONFIG_LIBDIR):/usr/local/share/pkgconfig/ + PKG_CONFIG_LIBDIR := $(PKG_CONFIG_LIBDIR):/usr/share/pkgconfig/ + export PKG_CONFIG_LIBDIR + $(warning Missing PKG_CONFIG_LIBDIR, PKG_CONFIG_PATH and PKG_CONFIG_SYSROOT_DIR for cross compilation,) + $(warning set PKG_CONFIG_LIBDIR for using Multiarch libs.) + endif + endif +endif RM = rm -f LN = ln -f diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 1730b852a947..6d075648d2cc 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -1141,7 +1141,7 @@ int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *samp int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node, bool hide_unresolved) { - struct machine *machine = maps__machine(node->ms.maps); + struct machine *machine = node->ms.maps ? maps__machine(node->ms.maps) : NULL; maps__put(al->maps); al->maps = maps__get(node->ms.maps); diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index dd49c1d23a60..81d4757ecd4c 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -713,7 +713,7 @@ $(OUTPUT)/xdp_features: xdp_features.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xdp # Make sure we are able to include and link libbpf against c++. $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ) $(call msg,CXX,,$@) - $(Q)$(CXX) $(CFLAGS) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@ + $(Q)$(CXX) $(subst -D_GNU_SOURCE=,,$(CFLAGS)) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@ # Benchmark runner $(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h $(BPFOBJ) diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c index bd8c75b620c2..797de47f8197 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c @@ -253,7 +253,7 @@ static void test_uretprobe_syscall_call(void) struct uprobe_syscall_executed *skel; int pid, status, err, go[2], c; - if (ASSERT_OK(pipe(go), "pipe")) + if (!ASSERT_OK(pipe(go), "pipe")) return; skel = uprobe_syscall_executed__open_and_load(); diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py index 931dbc36ca43..011508ca604b 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -19,6 +19,15 @@ def _rss_key_rand(length): return [random.randint(0, 255) for _ in range(length)] +def _rss_key_check(cfg, data=None, context=0): + if data is None: + data = get_rss(cfg, context=context) + if 'rss-hash-key' not in data: + return + non_zero = [x for x in data['rss-hash-key'] if x != 0] + ksft_eq(bool(non_zero), True, comment=f"RSS key is all zero {data['rss-hash-key']}") + + def get_rss(cfg, context=0): return ethtool(f"-x {cfg.ifname} context {context}", json=True)[0] @@ -90,8 +99,9 @@ def _send_traffic_check(cfg, port, name, params): def test_rss_key_indir(cfg): """Test basics like updating the main RSS key and indirection table.""" - if len(_get_rx_cnts(cfg)) < 2: - KsftSkipEx("Device has only one queue (or doesn't support queue stats)") + qcnt = len(_get_rx_cnts(cfg)) + if qcnt < 3: + KsftSkipEx("Device has fewer than 3 queues (or doesn't support queue stats)") data = get_rss(cfg) want_keys = ['rss-hash-key', 'rss-hash-function', 'rss-indirection-table'] @@ -101,6 +111,7 @@ def test_rss_key_indir(cfg): if not data[k]: raise KsftFailEx(f"ethtool results empty for '{k}': {data[k]}") + _rss_key_check(cfg, data=data) key_len = len(data['rss-hash-key']) # Set the key @@ -110,9 +121,26 @@ def test_rss_key_indir(cfg): data = get_rss(cfg) ksft_eq(key, data['rss-hash-key']) + # Set the indirection table and the key together + key = _rss_key_rand(key_len) + ethtool(f"-X {cfg.ifname} equal 3 hkey " + _rss_key_str(key)) + reset_indir = defer(ethtool, f"-X {cfg.ifname} default") + + data = get_rss(cfg) + _rss_key_check(cfg, data=data) + ksft_eq(0, min(data['rss-indirection-table'])) + ksft_eq(2, max(data['rss-indirection-table'])) + + # Reset indirection table and set the key + key = _rss_key_rand(key_len) + ethtool(f"-X {cfg.ifname} default hkey " + _rss_key_str(key)) + data = get_rss(cfg) + _rss_key_check(cfg, data=data) + ksft_eq(0, min(data['rss-indirection-table'])) + ksft_eq(qcnt - 1, max(data['rss-indirection-table'])) + # Set the indirection table ethtool(f"-X {cfg.ifname} equal 2") - reset_indir = defer(ethtool, f"-X {cfg.ifname} default") data = get_rss(cfg) ksft_eq(0, min(data['rss-indirection-table'])) ksft_eq(1, max(data['rss-indirection-table'])) @@ -317,8 +345,11 @@ def test_rss_context(cfg, ctx_cnt=1, create_with_cfg=None): ctx_cnt = i break + _rss_key_check(cfg, context=ctx_id) + if not create_with_cfg: ethtool(f"-X {cfg.ifname} context {ctx_id} {want_cfg}") + _rss_key_check(cfg, context=ctx_id) # Sanity check the context we just created data = get_rss(cfg, ctx_id) diff --git a/tools/testing/selftests/hid/hid_bpf.c b/tools/testing/selftests/hid/hid_bpf.c index dc0408a831d0..75b7b4ef6cfa 100644 --- a/tools/testing/selftests/hid/hid_bpf.c +++ b/tools/testing/selftests/hid/hid_bpf.c @@ -532,6 +532,7 @@ static void load_programs(const struct test_program programs[], FIXTURE_DATA(hid_bpf) * self, const FIXTURE_VARIANT(hid_bpf) * variant) { + struct bpf_map *iter_map; int err = -EINVAL; ASSERT_LE(progs_count, ARRAY_SIZE(self->hid_links)) @@ -564,6 +565,13 @@ static void load_programs(const struct test_program programs[], *ops_hid_id = self->hid_id; } + /* we disable the auto-attach feature of all maps because we + * only want the tested one to be manually attached in the next + * call to bpf_map__attach_struct_ops() + */ + bpf_object__for_each_map(iter_map, *self->skel->skeleton->obj) + bpf_map__set_autoattach(iter_map, false); + err = hid__load(self->skel); ASSERT_OK(err) TH_LOG("hid_skel_load failed: %d", err); @@ -687,6 +695,24 @@ TEST_F(hid_bpf, subprog_raw_event) } /* + * Attach hid_first_event to the given uhid device, + * attempt at re-attaching it, we should not lock and + * return an invalid struct bpf_link + */ +TEST_F(hid_bpf, multiple_attach) +{ + const struct test_program progs[] = { + { .name = "hid_first_event" }, + }; + struct bpf_link *link; + + LOAD_PROGRAMS(progs); + + link = bpf_map__attach_struct_ops(self->skel->maps.first_event); + ASSERT_NULL(link) TH_LOG("unexpected return value when re-attaching the struct_ops"); +} + +/* * Ensures that we can attach/detach programs */ TEST_F(hid_bpf, test_attach_detach) diff --git a/tools/testing/selftests/hid/progs/hid.c b/tools/testing/selftests/hid/progs/hid.c index ee9bbbcf751b..5ecc845ef792 100644 --- a/tools/testing/selftests/hid/progs/hid.c +++ b/tools/testing/selftests/hid/progs/hid.c @@ -455,7 +455,7 @@ struct { __type(value, struct elem); } hmap SEC(".maps"); -static int wq_cb_sleepable(void *map, int *key, struct bpf_wq *work) +static int wq_cb_sleepable(void *map, int *key, void *work) { __u8 buf[9] = {2, 3, 4, 5, 6, 7, 8, 9, 10}; struct hid_bpf_ctx *hid_ctx; diff --git a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h index cfe37f491906..e5db897586bb 100644 --- a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h +++ b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h @@ -114,7 +114,7 @@ extern int hid_bpf_try_input_report(struct hid_bpf_ctx *ctx, extern int bpf_wq_init(struct bpf_wq *wq, void *p__map, unsigned int flags) __weak __ksym; extern int bpf_wq_start(struct bpf_wq *wq, unsigned int flags) __weak __ksym; extern int bpf_wq_set_callback_impl(struct bpf_wq *wq, - int (callback_fn)(void *map, int *key, struct bpf_wq *wq), + int (callback_fn)(void *map, int *key, void *wq), unsigned int flags__k, void *aux__ign) __ksym; #define bpf_wq_set_callback(timer, cb, flags) \ bpf_wq_set_callback_impl(timer, cb, flags, NULL) diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c index 1b03bcfaefdf..5a3a9bcba640 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -22,8 +22,10 @@ #define VALIDATION_DEFAULT_THRESHOLD 4 /* 4MB */ #define VALIDATION_NO_THRESHOLD 0 /* Verify the entire region */ +#ifndef MIN #define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) #define MAX(X, Y) ((X) > (Y) ? (X) : (Y)) +#endif #define SIZE_MB(m) ((size_t)m * (1024 * 1024)) #define SIZE_KB(k) ((size_t)k * 1024) diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index d2043ec3bf6d..4209b9569039 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -1115,11 +1115,11 @@ again: return 1; } - if (--cfg_repeat > 0) { - if (cfg_input) - close(fd); + if (cfg_input) + close(fd); + + if (--cfg_repeat > 0) goto again; - } return 0; } diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 108aeeb84ef1..4df48f1f14ab 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -661,7 +661,7 @@ pm_nl_check_endpoint() done if [ -z "${id}" ]; then - test_fail "bad test - missing endpoint id" + fail_test "bad test - missing endpoint id" return fi @@ -1634,6 +1634,8 @@ chk_prio_nr() { local mp_prio_nr_tx=$1 local mp_prio_nr_rx=$2 + local mpj_syn=$3 + local mpj_syn_ack=$4 local count print_check "ptx" @@ -1655,6 +1657,26 @@ chk_prio_nr() else print_ok fi + + print_check "syn backup" + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinSynBackupRx") + if [ -z "$count" ]; then + print_skip + elif [ "$count" != "$mpj_syn" ]; then + fail_test "got $count JOIN[s] syn with Backup expected $mpj_syn" + else + print_ok + fi + + print_check "synack backup" + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinSynAckBackupRx") + if [ -z "$count" ]; then + print_skip + elif [ "$count" != "$mpj_syn_ack" ]; then + fail_test "got $count JOIN[s] synack with Backup expected $mpj_syn_ack" + else + print_ok + fi } chk_subflow_nr() @@ -2612,33 +2634,46 @@ backup_tests() sflags=nobackup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 - chk_prio_nr 0 1 + chk_prio_nr 0 1 1 0 fi # single address, backup if reset "single address, backup" && continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,backup + pm_nl_set_limits $ns2 1 1 + sflags=nobackup speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_prio_nr 1 0 0 1 + fi + + # single address, switch to backup + if reset "single address, switch to backup" && + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_set_limits $ns2 1 1 sflags=backup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_add_nr 1 1 - chk_prio_nr 1 1 + chk_prio_nr 1 1 0 0 fi # single address with port, backup if reset "single address with port, backup" && continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 1 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,backup port 10100 pm_nl_set_limits $ns2 1 1 - sflags=backup speed=slow \ + sflags=nobackup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_add_nr 1 1 - chk_prio_nr 1 1 + chk_prio_nr 1 0 0 1 fi if reset "mpc backup" && @@ -2647,17 +2682,26 @@ backup_tests() speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 - chk_prio_nr 0 1 + chk_prio_nr 0 1 0 0 fi if reset "mpc backup both sides" && continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then - pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns1 10.0.1.1 flags signal,backup pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup + + # 10.0.2.2 (non-backup) -> 10.0.1.1 (backup) + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + # 10.0.1.2 (backup) -> 10.0.2.1 (non-backup) + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + ip -net "$ns2" route add 10.0.2.1 via 10.0.1.1 dev ns2eth1 # force this path + speed=slow \ run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr 0 0 0 - chk_prio_nr 1 1 + chk_join_nr 2 2 2 + chk_prio_nr 1 1 1 1 fi if reset "mpc switch to backup" && @@ -2666,7 +2710,7 @@ backup_tests() sflags=backup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 - chk_prio_nr 0 1 + chk_prio_nr 0 1 0 0 fi if reset "mpc switch to backup both sides" && @@ -2676,7 +2720,7 @@ backup_tests() sflags=backup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 - chk_prio_nr 1 1 + chk_prio_nr 1 1 0 0 fi } @@ -3053,7 +3097,7 @@ fullmesh_tests() addr_nr_ns2=1 sflags=backup,fullmesh speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 - chk_prio_nr 0 1 + chk_prio_nr 0 1 1 0 chk_rm_nr 0 1 fi @@ -3066,7 +3110,7 @@ fullmesh_tests() sflags=nobackup,nofullmesh speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 - chk_prio_nr 0 1 + chk_prio_nr 0 1 1 0 chk_rm_nr 0 1 fi } @@ -3318,7 +3362,7 @@ userspace_tests() sflags=backup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 0 - chk_prio_nr 0 0 + chk_prio_nr 0 0 0 0 fi # userspace pm type prevents rm_addr @@ -3526,6 +3570,35 @@ endpoint_tests() chk_mptcp_info subflows 1 subflows 1 mptcp_lib_kill_wait $tests_pid fi + + # remove and re-add + if reset "delete re-add signal" && + mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal + test_linkfail=4 speed=20 \ + run_tests $ns1 $ns2 10.0.1.1 & + local tests_pid=$! + + wait_mpj $ns2 + pm_nl_check_endpoint "creation" \ + $ns1 10.0.2.1 id 1 flags signal + chk_subflow_nr "before delete" 2 + chk_mptcp_info subflows 1 subflows 1 + + pm_nl_del_endpoint $ns1 1 10.0.2.1 + sleep 0.5 + chk_subflow_nr "after delete" 1 + chk_mptcp_info subflows 0 subflows 0 + + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + wait_mpj $ns2 + chk_subflow_nr "after re-add" 2 + chk_mptcp_info subflows 1 subflows 1 + mptcp_lib_kill_wait $tests_pid + fi + } # [$1: error message] diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index e3f97f90d8db..8c3a73461475 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -60,7 +60,9 @@ #define SKIP(s, ...) XFAIL(s, ##__VA_ARGS__) #endif +#ifndef MIN #define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) +#endif #ifndef PR_SET_PTRACER # define PR_SET_PTRACER 0x59616d61 |