diff options
233 files changed, 1497 insertions, 975 deletions
diff --git a/Documentation/arm64/sve.rst b/Documentation/arm64/sve.rst index 5689c74c8082..bfd55f468258 100644 --- a/Documentation/arm64/sve.rst +++ b/Documentation/arm64/sve.rst @@ -186,7 +186,7 @@ prctl(PR_SVE_SET_VL, unsigned long arg) flags: - PR_SVE_SET_VL_INHERIT + PR_SVE_VL_INHERIT Inherit the current vector length across execve(). Otherwise, the vector length is reset to the system default at execve(). (See @@ -247,7 +247,7 @@ prctl(PR_SVE_GET_VL) The following flag may be OR-ed into the result: - PR_SVE_SET_VL_INHERIT + PR_SVE_VL_INHERIT Vector length will be inherited across execve(). @@ -393,7 +393,7 @@ The regset data starts with struct user_sve_header, containing: * At every execve() call, the new vector length of the new process is set to the system default vector length, unless - * PR_SVE_SET_VL_INHERIT (or equivalently SVE_PT_VL_INHERIT) is set for the + * PR_SVE_VL_INHERIT (or equivalently SVE_PT_VL_INHERIT) is set for the calling thread, or * a deferred vector length change is pending, established via the diff --git a/Documentation/filesystems/dax.txt b/Documentation/filesystems/dax.txt index 8e2670781c9b..8fdb78f3c6c9 100644 --- a/Documentation/filesystems/dax.txt +++ b/Documentation/filesystems/dax.txt @@ -25,7 +25,7 @@ size when creating the filesystem. Currently 3 filesystems support DAX: ext2, ext4 and xfs. Enabling DAX on them is different. -Enabling DAX on ext4 and ext2 +Enabling DAX on ext2 ----------------------------- When mounting the filesystem, use the "-o dax" option on the command line or @@ -33,8 +33,8 @@ add 'dax' to the options in /etc/fstab. This works to enable DAX on all files within the filesystem. It is equivalent to the '-o dax=always' behavior below. -Enabling DAX on xfs -------------------- +Enabling DAX on xfs and ext4 +---------------------------- Summary ------- diff --git a/Documentation/filesystems/ext4/verity.rst b/Documentation/filesystems/ext4/verity.rst index 3e4c0ee0e068..e99ff3fd09f7 100644 --- a/Documentation/filesystems/ext4/verity.rst +++ b/Documentation/filesystems/ext4/verity.rst @@ -39,3 +39,6 @@ is encrypted as well as the data itself. Verity files cannot have blocks allocated past the end of the verity metadata. + +Verity and DAX are not compatible and attempts to set both of these flags +on a file will fail. diff --git a/Documentation/sh/index.rst b/Documentation/sh/index.rst index bc8db7ba894a..0bd405acf68f 100644 --- a/Documentation/sh/index.rst +++ b/Documentation/sh/index.rst @@ -16,18 +16,6 @@ Store Queue API .. kernel-doc:: arch/sh/kernel/cpu/sh4/sq.c :export: -SH-5 ----- - -TLB Interfaces -~~~~~~~~~~~~~~ - -.. kernel-doc:: arch/sh/mm/tlb-sh5.c - :internal: - -.. kernel-doc:: arch/sh/include/asm/tlb_64.h - :internal: - Machine Specific Interfaces =========================== diff --git a/MAINTAINERS b/MAINTAINERS index 68f21d46614c..301330e02bca 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11369,14 +11369,6 @@ L: dmaengine@vger.kernel.org S: Supported F: drivers/dma/at_xdmac.c -MICROSEMI ETHERNET SWITCH DRIVER -M: Alexandre Belloni <alexandre.belloni@bootlin.com> -M: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com> -L: netdev@vger.kernel.org -S: Supported -F: drivers/net/ethernet/mscc/ -F: include/soc/mscc/ocelot* - MICROSEMI MIPS SOCS M: Alexandre Belloni <alexandre.belloni@bootlin.com> M: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com> @@ -12335,6 +12327,18 @@ M: Peter Zijlstra <peterz@infradead.org> S: Supported F: tools/objtool/ +OCELOT ETHERNET SWITCH DRIVER +M: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com> +M: Vladimir Oltean <vladimir.oltean@nxp.com> +M: Claudiu Manoil <claudiu.manoil@nxp.com> +M: Alexandre Belloni <alexandre.belloni@bootlin.com> +L: netdev@vger.kernel.org +S: Supported +F: drivers/net/dsa/ocelot/* +F: drivers/net/ethernet/mscc/ +F: include/soc/mscc/ocelot* +F: net/dsa/tag_ocelot.c + OCXL (Open Coherent Accelerator Processor Interface OpenCAPI) DRIVER M: Frederic Barrat <fbarrat@linux.ibm.com> M: Andrew Donnellan <ajd@linux.ibm.com> @@ -14534,7 +14538,7 @@ F: Documentation/devicetree/bindings/i2c/renesas,iic-emev2.txt F: drivers/i2c/busses/i2c-emev2.c RENESAS ETHERNET DRIVERS -R: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> +R: Sergei Shtylyov <sergei.shtylyov@gmail.com> L: netdev@vger.kernel.org L: linux-renesas-soc@vger.kernel.org F: Documentation/devicetree/bindings/net/renesas,*.txt @@ -18254,14 +18258,6 @@ S: Maintained F: drivers/input/serio/userio.c F: include/uapi/linux/userio.h -VITESSE FELIX ETHERNET SWITCH DRIVER -M: Vladimir Oltean <vladimir.oltean@nxp.com> -M: Claudiu Manoil <claudiu.manoil@nxp.com> -L: netdev@vger.kernel.org -S: Maintained -F: drivers/net/dsa/ocelot/* -F: net/dsa/tag_ocelot.c - VIVID VIRTUAL VIDEO DRIVER M: Hans Verkuil <hverkuil@xs4all.nl> L: linux-media@vger.kernel.org diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c index 10499d44964a..9a79ef6b1876 100644 --- a/arch/arm/kernel/ftrace.c +++ b/arch/arm/kernel/ftrace.c @@ -84,7 +84,8 @@ static int ftrace_modify_code(unsigned long pc, unsigned long old, old = __opcode_to_mem_arm(old); if (validate) { - if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(&replaced, (void *)pc, + MCOUNT_INSN_SIZE)) return -EFAULT; if (replaced != old) diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c index 6a95b9296640..7bd30c0a4280 100644 --- a/arch/arm/kernel/kgdb.c +++ b/arch/arm/kernel/kgdb.c @@ -236,7 +236,7 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) /* patch_text() only supports int-sized breakpoints */ BUILD_BUG_ON(sizeof(int) != BREAK_INSTR_SIZE); - err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr, + err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE); if (err) return err; diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 65a3b1e75480..17d5a785df28 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -396,7 +396,7 @@ int is_valid_bugaddr(unsigned long pc) u32 insn = __opcode_to_mem_arm(BUG_INSTR_VALUE); #endif - if (probe_kernel_address((unsigned *)pc, bkpt)) + if (get_kernel_nofault(bkpt, (void *)pc)) return 0; return bkpt == insn; diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 84718eddae60..81a627e6e1c5 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -774,7 +774,7 @@ static int alignment_get_arm(struct pt_regs *regs, u32 *ip, u32 *inst) if (user_mode(regs)) fault = get_user(instr, ip); else - fault = probe_kernel_address(ip, instr); + fault = get_kernel_nofault(instr, ip); *inst = __mem_to_opcode_arm(instr); @@ -789,7 +789,7 @@ static int alignment_get_thumb(struct pt_regs *regs, u16 *ip, u16 *inst) if (user_mode(regs)) fault = get_user(instr, ip); else - fault = probe_kernel_address(ip, instr); + fault = get_kernel_nofault(instr, ip); *inst = __mem_to_opcode_thumb16(instr); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 31380da53689..4ae2419c14a8 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1630,6 +1630,8 @@ config ARM64_BTI_KERNEL depends on CC_HAS_BRANCH_PROT_PAC_RET_BTI # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94697 depends on !CC_IS_GCC || GCC_VERSION >= 100100 + # https://reviews.llvm.org/rGb8ae3fdfa579dbf366b1bb1cbfdbf8c51db7fa55 + depends on !CC_IS_CLANG || CLANG_VERSION >= 100001 depends on !(CC_IS_CLANG && GCOV_KERNEL) depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS) help diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug index cdf7ec0b975e..265c4461031f 100644 --- a/arch/arm64/Kconfig.debug +++ b/arch/arm64/Kconfig.debug @@ -8,21 +8,6 @@ config PID_IN_CONTEXTIDR instructions during context switch. Say Y here only if you are planning to use hardware trace tools with this kernel. -config ARM64_RANDOMIZE_TEXT_OFFSET - bool "Randomize TEXT_OFFSET at build time" - help - Say Y here if you want the image load offset (AKA TEXT_OFFSET) - of the kernel to be randomized at build-time. When selected, - this option will cause TEXT_OFFSET to be randomized upon any - build of the kernel, and the offset will be reflected in the - text_offset field of the resulting Image. This can be used to - fuzz-test bootloaders which respect text_offset. - - This option is intended for bootloader and/or kernel testing - only. Bootloaders must make no assumptions regarding the value - of TEXT_OFFSET and platforms must not require a specific - value. - config DEBUG_EFI depends on EFI && DEBUG_INFO bool "UEFI debugging" diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 76359cfb328a..a0d94d063fa8 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -121,13 +121,7 @@ endif head-y := arch/arm64/kernel/head.o # The byte offset of the kernel image in RAM from the start of RAM. -ifeq ($(CONFIG_ARM64_RANDOMIZE_TEXT_OFFSET), y) -TEXT_OFFSET := $(shell awk "BEGIN {srand(); printf \"0x%06x\n\", \ - int(2 * 1024 * 1024 / (2 ^ $(CONFIG_ARM64_PAGE_SHIFT)) * \ - rand()) * (2 ^ $(CONFIG_ARM64_PAGE_SHIFT))}") -else TEXT_OFFSET := 0x0 -endif ifeq ($(CONFIG_KASAN_SW_TAGS), y) KASAN_SHADOW_SCALE_SHIFT := 4 diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 6dbd267ab931..758e2d1577d0 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -416,7 +416,7 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd) __pgprot((pgprot_val(prot) & ~(mask)) | (bits)) #define pgprot_nx(prot) \ - __pgprot_modify(prot, 0, PTE_PXN) + __pgprot_modify(prot, PTE_MAYBE_GP, PTE_PXN) /* * Mark the prot value as uncacheable and unbufferable. diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 35cb5e66c504..55c8f3ec6705 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -12,6 +12,7 @@ #include <linux/bug.h> #include <linux/cache.h> #include <linux/compat.h> +#include <linux/compiler.h> #include <linux/cpu.h> #include <linux/cpu_pm.h> #include <linux/kernel.h> @@ -119,10 +120,20 @@ struct fpsimd_last_state_struct { static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state); /* Default VL for tasks that don't set it explicitly: */ -static int sve_default_vl = -1; +static int __sve_default_vl = -1; + +static int get_sve_default_vl(void) +{ + return READ_ONCE(__sve_default_vl); +} #ifdef CONFIG_ARM64_SVE +static void set_sve_default_vl(int val) +{ + WRITE_ONCE(__sve_default_vl, val); +} + /* Maximum supported vector length across all CPUs (initially poisoned) */ int __ro_after_init sve_max_vl = SVE_VL_MIN; int __ro_after_init sve_max_virtualisable_vl = SVE_VL_MIN; @@ -338,13 +349,13 @@ static unsigned int find_supported_vector_length(unsigned int vl) return sve_vl_from_vq(__bit_to_vq(bit)); } -#ifdef CONFIG_SYSCTL +#if defined(CONFIG_ARM64_SVE) && defined(CONFIG_SYSCTL) static int sve_proc_do_default_vl(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; - int vl = sve_default_vl; + int vl = get_sve_default_vl(); struct ctl_table tmp_table = { .data = &vl, .maxlen = sizeof(vl), @@ -361,7 +372,7 @@ static int sve_proc_do_default_vl(struct ctl_table *table, int write, if (!sve_vl_valid(vl)) return -EINVAL; - sve_default_vl = find_supported_vector_length(vl); + set_sve_default_vl(find_supported_vector_length(vl)); return 0; } @@ -383,9 +394,9 @@ static int __init sve_sysctl_init(void) return 0; } -#else /* ! CONFIG_SYSCTL */ +#else /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ static int __init sve_sysctl_init(void) { return 0; } -#endif /* ! CONFIG_SYSCTL */ +#endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ #define ZREG(sve_state, vq, n) ((char *)(sve_state) + \ (SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET)) @@ -868,7 +879,7 @@ void __init sve_setup(void) * For the default VL, pick the maximum supported value <= 64. * VL == 64 is guaranteed not to grow the signal frame. */ - sve_default_vl = find_supported_vector_length(64); + set_sve_default_vl(find_supported_vector_length(64)); bitmap_andnot(tmp_map, sve_vq_partial_map, sve_vq_map, SVE_VQ_MAX); @@ -889,7 +900,7 @@ void __init sve_setup(void) pr_info("SVE: maximum available vector length %u bytes per vector\n", sve_max_vl); pr_info("SVE: default vector length %u bytes per vector\n", - sve_default_vl); + get_sve_default_vl()); /* KVM decides whether to support mismatched systems. Just warn here: */ if (sve_max_virtualisable_vl < sve_max_vl) @@ -1029,13 +1040,13 @@ void fpsimd_flush_thread(void) * vector length configured: no kernel task can become a user * task without an exec and hence a call to this function. * By the time the first call to this function is made, all - * early hardware probing is complete, so sve_default_vl + * early hardware probing is complete, so __sve_default_vl * should be valid. * If a bug causes this to go wrong, we make some noise and * try to fudge thread.sve_vl to a safe value here. */ vl = current->thread.sve_vl_onexec ? - current->thread.sve_vl_onexec : sve_default_vl; + current->thread.sve_vl_onexec : get_sve_default_vl(); if (WARN_ON(!sve_vl_valid(vl))) vl = SVE_VL_MIN; diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 0b727edf4104..af234a1e08b7 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -730,6 +730,27 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val, return 0; } +static int watchpoint_report(struct perf_event *wp, unsigned long addr, + struct pt_regs *regs) +{ + int step = is_default_overflow_handler(wp); + struct arch_hw_breakpoint *info = counter_arch_bp(wp); + + info->trigger = addr; + + /* + * If we triggered a user watchpoint from a uaccess routine, then + * handle the stepping ourselves since userspace really can't help + * us with this. + */ + if (!user_mode(regs) && info->ctrl.privilege == AARCH64_BREAKPOINT_EL0) + step = 1; + else + perf_bp_event(wp, regs); + + return step; +} + static int watchpoint_handler(unsigned long addr, unsigned int esr, struct pt_regs *regs) { @@ -739,7 +760,6 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, u64 val; struct perf_event *wp, **slots; struct debug_info *debug_info; - struct arch_hw_breakpoint *info; struct arch_hw_breakpoint_ctrl ctrl; slots = this_cpu_ptr(wp_on_reg); @@ -777,25 +797,13 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, if (dist != 0) continue; - info = counter_arch_bp(wp); - info->trigger = addr; - perf_bp_event(wp, regs); - - /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(wp)) - step = 1; + step = watchpoint_report(wp, addr, regs); } - if (min_dist > 0 && min_dist != -1) { - /* No exact match found. */ - wp = slots[closest_match]; - info = counter_arch_bp(wp); - info->trigger = addr; - perf_bp_event(wp, regs); - /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(wp)) - step = 1; - } + /* No exact match found? */ + if (min_dist > 0 && min_dist != -1) + step = watchpoint_report(slots[closest_match], addr, regs); + rcu_read_unlock(); if (!step) diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 684d871ae38d..a107375005bc 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -135,7 +135,7 @@ int __kprobes aarch64_insn_read(void *addr, u32 *insnp) int ret; __le32 val; - ret = probe_kernel_read(&val, addr, AARCH64_INSN_SIZE); + ret = copy_from_kernel_nofault(&val, addr, AARCH64_INSN_SIZE); if (!ret) *insnp = le32_to_cpu(val); @@ -151,7 +151,7 @@ static int __kprobes __aarch64_insn_write(void *addr, __le32 insn) raw_spin_lock_irqsave(&patch_lock, flags); waddr = patch_map(addr, FIX_TEXT_POKE0); - ret = probe_kernel_write(waddr, &insn, AARCH64_INSN_SIZE); + ret = copy_to_kernel_nofault(waddr, &insn, AARCH64_INSN_SIZE); patch_unmap(FIX_TEXT_POKE0); raw_spin_unlock_irqrestore(&patch_lock, flags); diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index 522e6f517ec0..361a1143e09e 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -219,8 +219,7 @@ static int prepare_elf_headers(void **addr, unsigned long *sz) MEMBLOCK_NONE, &start, &end, NULL) nr_ranges++; - cmem = kmalloc(sizeof(struct crash_mem) + - sizeof(struct crash_mem_range) * nr_ranges, GFP_KERNEL); + cmem = kmalloc(struct_size(cmem, ranges, nr_ranges), GFP_KERNEL); if (!cmem) return -ENOMEM; diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 50cc30acf106..47f651df781c 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -376,7 +376,7 @@ static int call_undef_hook(struct pt_regs *regs) if (!user_mode(regs)) { __le32 instr_le; - if (probe_kernel_address((__force __le32 *)pc, instr_le)) + if (get_kernel_nofault(instr_le, (__force __le32 *)pc)) goto exit; instr = le32_to_cpu(instr_le); } else if (compat_thumb_mode(regs)) { @@ -813,6 +813,7 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr) handler[reason], smp_processor_id(), esr, esr_get_class_string(esr)); + __show_regs(regs); local_daif_mask(); panic("bad mode"); } diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index e631e6425165..1e93cfc7c47a 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -404,11 +404,6 @@ void __init arm64_memblock_init(void) high_memory = __va(memblock_end_of_DRAM() - 1) + 1; dma_contiguous_reserve(arm64_dma32_phys_limit); - -#ifdef CONFIG_ARM64_4K_PAGES - hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT); -#endif - } void __init bootmem_init(void) @@ -424,6 +419,16 @@ void __init bootmem_init(void) min_low_pfn = min; arm64_numa_init(); + + /* + * must be done after arm64_numa_init() which calls numa_init() to + * initialize node_online_map that gets used in hugetlb_cma_reserve() + * while allocating required CMA size across online nodes. + */ +#ifdef CONFIG_ARM64_4K_PAGES + hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT); +#endif + /* * Sparsemem tries to allocate bootmem in memory_present(), so must be * done after the fixed reservations. diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 990929c8837e..1df25f26571d 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -723,6 +723,7 @@ int kern_addr_valid(unsigned long addr) pmd_t *pmdp, pmd; pte_t *ptep, pte; + addr = arch_kasan_reset_tag(addr); if ((((long)addr) >> VA_BITS) != -1UL) return 0; diff --git a/arch/csky/kernel/ftrace.c b/arch/csky/kernel/ftrace.c index 3c425b84e3be..b4a7ec1517ff 100644 --- a/arch/csky/kernel/ftrace.c +++ b/arch/csky/kernel/ftrace.c @@ -72,7 +72,8 @@ static int ftrace_check_current_nop(unsigned long hook) uint16_t olds[7]; unsigned long hook_pos = hook - 2; - if (probe_kernel_read((void *)olds, (void *)hook_pos, sizeof(nops))) + if (copy_from_kernel_nofault((void *)olds, (void *)hook_pos, + sizeof(nops))) return -EFAULT; if (memcmp((void *)nops, (void *)olds, sizeof(nops))) { @@ -97,7 +98,7 @@ static int ftrace_modify_code(unsigned long hook, unsigned long target, make_jbsr(target, hook, call, nolr); - ret = probe_kernel_write((void *)hook_pos, enable ? call : nops, + ret = copy_to_kernel_nofault((void *)hook_pos, enable ? call : nops, sizeof(nops)); if (ret) return -EPERM; diff --git a/arch/ia64/include/asm/sections.h b/arch/ia64/include/asm/sections.h index cea15f2dd38d..3a033d2008b3 100644 --- a/arch/ia64/include/asm/sections.h +++ b/arch/ia64/include/asm/sections.h @@ -35,7 +35,7 @@ static inline void *dereference_function_descriptor(void *ptr) struct fdesc *desc = ptr; void *p; - if (!probe_kernel_address(&desc->ip, p)) + if (!get_kernel_nofault(p, (void *)&desc->ip)) ptr = p; return ptr; } diff --git a/arch/ia64/kernel/ftrace.c b/arch/ia64/kernel/ftrace.c index cee411e647ca..b2ab2d58fb30 100644 --- a/arch/ia64/kernel/ftrace.c +++ b/arch/ia64/kernel/ftrace.c @@ -108,7 +108,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, goto skip_check; /* read the text we want to modify */ - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(replaced, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; /* Make sure it is what we expect it to be */ @@ -117,7 +117,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, skip_check: /* replace the text with the new text */ - if (probe_kernel_write(((void *)ip), new_code, MCOUNT_INSN_SIZE)) + if (copy_to_kernel_nofault(((void *)ip), new_code, MCOUNT_INSN_SIZE)) return -EPERM; flush_icache_range(ip, ip + MCOUNT_INSN_SIZE); @@ -129,7 +129,7 @@ static int ftrace_make_nop_check(struct dyn_ftrace *rec, unsigned long addr) unsigned char __attribute__((aligned(8))) replaced[MCOUNT_INSN_SIZE]; unsigned long ip = rec->ip; - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(replaced, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; if (rec->flags & FTRACE_FL_CONVERTED) { struct ftrace_call_insn *call_insn, *tmp_call; diff --git a/arch/ia64/kernel/unwind_i.h b/arch/ia64/kernel/unwind_i.h index 67994a7e5816..1dd57ba44327 100644 --- a/arch/ia64/kernel/unwind_i.h +++ b/arch/ia64/kernel/unwind_i.h @@ -42,7 +42,7 @@ enum unw_register_index { struct unw_info_block { u64 header; - u64 desc[0]; /* unwind descriptors */ + u64 desc[]; /* unwind descriptors */ /* personality routine and language-specific data follow behind descriptors */ }; diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c index 6cfae2411c04..d043c2f897fc 100644 --- a/arch/mips/kernel/kprobes.c +++ b/arch/mips/kernel/kprobes.c @@ -86,9 +86,9 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) goto out; } - if ((probe_kernel_read(&prev_insn, p->addr - 1, - sizeof(mips_instruction)) == 0) && - insn_has_delayslot(prev_insn)) { + if (copy_from_kernel_nofault(&prev_insn, p->addr - 1, + sizeof(mips_instruction)) == 0 && + insn_has_delayslot(prev_insn)) { pr_notice("Kprobes for branch delayslot are not supported\n"); ret = -EINVAL; goto out; diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c index 22ab77ea27ad..3763b3f8c3db 100644 --- a/arch/nds32/kernel/ftrace.c +++ b/arch/nds32/kernel/ftrace.c @@ -131,13 +131,14 @@ static int __ftrace_modify_code(unsigned long pc, unsigned long *old_insn, unsigned long orig_insn[3]; if (validate) { - if (probe_kernel_read(orig_insn, (void *)pc, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(orig_insn, (void *)pc, + MCOUNT_INSN_SIZE)) return -EFAULT; if (memcmp(orig_insn, old_insn, MCOUNT_INSN_SIZE)) return -EINVAL; } - if (probe_kernel_write((void *)pc, new_insn, MCOUNT_INSN_SIZE)) + if (copy_to_kernel_nofault((void *)pc, new_insn, MCOUNT_INSN_SIZE)) return -EPERM; return 0; diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index b836fc61a24f..1df0f67ed667 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -172,7 +172,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) ip = (void *)(rec->ip + 4 - size); - ret = probe_kernel_read(insn, ip, size); + ret = copy_from_kernel_nofault(insn, ip, size); if (ret) return ret; diff --git a/arch/parisc/kernel/kgdb.c b/arch/parisc/kernel/kgdb.c index 664278db9b97..c4554ac13eac 100644 --- a/arch/parisc/kernel/kgdb.c +++ b/arch/parisc/kernel/kgdb.c @@ -154,8 +154,8 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip) int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) { - int ret = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr, - BREAK_INSTR_SIZE); + int ret = copy_from_kernel_nofault(bpt->saved_instr, + (char *)bpt->bpt_addr, BREAK_INSTR_SIZE); if (ret) return ret; diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 230a6422b99f..b7abb12edd3a 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -293,7 +293,7 @@ void *dereference_function_descriptor(void *ptr) Elf64_Fdesc *desc = ptr; void *p; - if (!probe_kernel_address(&desc->addr, p)) + if (!get_kernel_nofault(p, (void *)&desc->addr)) ptr = p; return ptr; } diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c index 94a9fe2702c2..4b75388190b4 100644 --- a/arch/parisc/lib/memcpy.c +++ b/arch/parisc/lib/memcpy.c @@ -57,7 +57,7 @@ void * memcpy(void * dst,const void *src, size_t count) EXPORT_SYMBOL(raw_copy_in_user); EXPORT_SYMBOL(memcpy); -bool probe_kernel_read_allowed(const void *unsafe_src, size_t size) +bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { if ((unsigned long)unsafe_src < PAGE_SIZE) return false; diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index d19871763ed4..324d7b298ec3 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -85,7 +85,7 @@ static inline void *dereference_function_descriptor(void *ptr) struct ppc64_opd_entry *desc = ptr; void *p; - if (!probe_kernel_address(&desc->funcaddr, p)) + if (!get_kernel_nofault(p, (void *)&desc->funcaddr)) ptr = p; return ptr; } diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 652b2852bea3..409080208a6c 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -421,7 +421,7 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) unsigned int instr; struct ppc_inst *addr = (struct ppc_inst *)bpt->bpt_addr; - err = probe_kernel_address(addr, instr); + err = get_kernel_nofault(instr, (unsigned *) addr); if (err) return err; diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 6f96f65ebfe8..9cc792a3a6a9 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -289,7 +289,7 @@ int kprobe_handler(struct pt_regs *regs) if (!p) { unsigned int instr; - if (probe_kernel_address(addr, instr)) + if (get_kernel_nofault(instr, addr)) goto no_kprobe; if (instr != BREAKPOINT_INSTRUCTION) { diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index f4c2fa190192..ae2b188365b1 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -756,7 +756,8 @@ int module_trampoline_target(struct module *mod, unsigned long addr, stub = (struct ppc64_stub_entry *)addr; - if (probe_kernel_read(&magic, &stub->magic, sizeof(magic))) { + if (copy_from_kernel_nofault(&magic, &stub->magic, + sizeof(magic))) { pr_err("%s: fault reading magic for stub %lx for %s\n", __func__, addr, mod->name); return -EFAULT; } @@ -766,7 +767,8 @@ int module_trampoline_target(struct module *mod, unsigned long addr, return -EFAULT; } - if (probe_kernel_read(&funcdata, &stub->funcdata, sizeof(funcdata))) { + if (copy_from_kernel_nofault(&funcdata, &stub->funcdata, + sizeof(funcdata))) { pr_err("%s: fault reading funcdata for stub %lx for %s\n", __func__, addr, mod->name); return -EFAULT; } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 7bb7faf84490..30955a0c32d0 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1271,7 +1271,7 @@ static void show_instructions(struct pt_regs *regs) #endif if (!__kernel_text_address(pc) || - probe_kernel_address((const void *)pc, instr)) { + get_kernel_nofault(instr, (const void *)pc)) { pr_cont("XXXXXXXX "); } else { if (regs->nip == pc) @@ -1305,7 +1305,8 @@ void show_user_instructions(struct pt_regs *regs) for (i = 0; i < 8 && n; i++, n--, pc += sizeof(int)) { int instr; - if (probe_user_read(&instr, (void __user *)pc, sizeof(instr))) { + if (copy_from_user_nofault(&instr, (void __user *)pc, + sizeof(instr))) { seq_buf_printf(&s, "XXXXXXXX "); continue; } diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 5e399628f51a..c1fede6ec934 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -226,7 +226,7 @@ __ftrace_make_nop(struct module *mod, unsigned long ip = rec->ip; unsigned long tramp; - if (probe_kernel_read(&op, (void *)ip, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(&op, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; /* Make sure that that this is still a 24bit jump */ @@ -249,7 +249,7 @@ __ftrace_make_nop(struct module *mod, pr_devel("ip:%lx jumps to %lx", ip, tramp); /* Find where the trampoline jumps to */ - if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) { + if (copy_from_kernel_nofault(jmp, (void *)tramp, sizeof(jmp))) { pr_err("Failed to read %lx\n", tramp); return -EFAULT; } diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 3cb0c9843d01..e738ea652192 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -64,9 +64,9 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid, isync(); if (is_load) - ret = probe_user_read(to, (const void __user *)from, n); + ret = copy_from_user_nofault(to, (const void __user *)from, n); else - ret = probe_user_write((void __user *)to, from, n); + ret = copy_to_user_nofault((void __user *)to, from, n); /* switch the pid first to avoid running host with unallocated pid */ if (quadrant == 1 && pid != old_pid) diff --git a/arch/powerpc/lib/inst.c b/arch/powerpc/lib/inst.c index aedfd6e31e53..9cc17eb62462 100644 --- a/arch/powerpc/lib/inst.c +++ b/arch/powerpc/lib/inst.c @@ -15,11 +15,11 @@ int probe_user_read_inst(struct ppc_inst *inst, unsigned int val, suffix; int err; - err = probe_user_read(&val, nip, sizeof(val)); + err = copy_from_user_nofault(&val, nip, sizeof(val)); if (err) return err; if (get_op(val) == OP_PREFIX) { - err = probe_user_read(&suffix, (void __user *)nip + 4, 4); + err = copy_from_user_nofault(&suffix, (void __user *)nip + 4, 4); *inst = ppc_inst_prefix(val, suffix); } else { *inst = ppc_inst(val); @@ -33,11 +33,11 @@ int probe_kernel_read_inst(struct ppc_inst *inst, unsigned int val, suffix; int err; - err = probe_kernel_read(&val, src, sizeof(val)); + err = copy_from_kernel_nofault(&val, src, sizeof(val)); if (err) return err; if (get_op(val) == OP_PREFIX) { - err = probe_kernel_read(&suffix, (void *)src + 4, 4); + err = copy_from_kernel_nofault(&suffix, (void *)src + 4, 4); *inst = ppc_inst_prefix(val, suffix); } else { *inst = ppc_inst(val); @@ -51,7 +51,7 @@ int probe_user_read_inst(struct ppc_inst *inst, unsigned int val; int err; - err = probe_user_read(&val, nip, sizeof(val)); + err = copy_from_user_nofault(&val, nip, sizeof(val)); if (!err) *inst = ppc_inst(val); @@ -64,7 +64,7 @@ int probe_kernel_read_inst(struct ppc_inst *inst, unsigned int val; int err; - err = probe_kernel_read(&val, src, sizeof(val)); + err = copy_from_kernel_nofault(&val, src, sizeof(val)); if (!err) *inst = ppc_inst(val); diff --git a/arch/powerpc/oprofile/backtrace.c b/arch/powerpc/oprofile/backtrace.c index 6f347fa29f41..9db7ada79d10 100644 --- a/arch/powerpc/oprofile/backtrace.c +++ b/arch/powerpc/oprofile/backtrace.c @@ -33,7 +33,8 @@ static unsigned int user_getsp32(unsigned int sp, int is_first) * which means that we've done all that we can do from * interrupt context. */ - if (probe_user_read(stack_frame, (void __user *)p, sizeof(stack_frame))) + if (copy_from_user_nofault(stack_frame, (void __user *)p, + sizeof(stack_frame))) return 0; if (!is_first) @@ -51,7 +52,8 @@ static unsigned long user_getsp64(unsigned long sp, int is_first) { unsigned long stack_frame[3]; - if (probe_user_read(stack_frame, (void __user *)sp, sizeof(stack_frame))) + if (copy_from_user_nofault(stack_frame, (void __user *)sp, + sizeof(stack_frame))) return 0; if (!is_first) diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c index f7d888d39cd3..542e68b8eae0 100644 --- a/arch/powerpc/perf/callchain_32.c +++ b/arch/powerpc/perf/callchain_32.c @@ -44,7 +44,7 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret) ((unsigned long)ptr & 3)) return -EFAULT; - rc = probe_user_read(ret, ptr, sizeof(*ret)); + rc = copy_from_user_nofault(ret, ptr, sizeof(*ret)); if (IS_ENABLED(CONFIG_PPC64) && rc) return read_user_stack_slow(ptr, ret, 4); diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c index 814d1c2c2b9c..fa2a1b83b9b0 100644 --- a/arch/powerpc/perf/callchain_64.c +++ b/arch/powerpc/perf/callchain_64.c @@ -50,7 +50,7 @@ static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret) ((unsigned long)ptr & 7)) return -EFAULT; - if (!probe_user_read(ret, ptr, sizeof(*ret))) + if (!copy_from_user_nofault(ret, ptr, sizeof(*ret))) return 0; return read_user_stack_slow(ptr, ret, 8); diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 13b9dd5e4a76..cd6a742ac6ef 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -418,14 +418,16 @@ static __u64 power_pmu_bhrb_to(u64 addr) __u64 target; if (is_kernel_addr(addr)) { - if (probe_kernel_read(&instr, (void *)addr, sizeof(instr))) + if (copy_from_kernel_nofault(&instr, (void *)addr, + sizeof(instr))) return 0; return branch_target((struct ppc_inst *)&instr); } /* Userspace: need copy instruction here then translate it */ - if (probe_user_read(&instr, (unsigned int __user *)addr, sizeof(instr))) + if (copy_from_user_nofault(&instr, (unsigned int __user *)addr, + sizeof(instr))) return 0; target = branch_target((struct ppc_inst *)&instr); diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 4a8874bc1057..040b9d01c079 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -1066,10 +1066,10 @@ int fsl_pci_mcheck_exception(struct pt_regs *regs) if (is_in_pci_mem_space(addr)) { if (user_mode(regs)) - ret = probe_user_read(&inst, (void __user *)regs->nip, - sizeof(inst)); + ret = copy_from_user_nofault(&inst, + (void __user *)regs->nip, sizeof(inst)); else - ret = probe_kernel_address((void *)regs->nip, inst); + ret = get_kernel_nofault(inst, (void *)regs->nip); if (!ret && mcheck_handle_load(regs, inst)) { regs->nip += 4; diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 08396614d6f4..2ff63d0cbb50 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -38,7 +38,8 @@ static int ftrace_check_current_call(unsigned long hook_pos, * Read the text we want to modify; * return must be -EFAULT on read error */ - if (probe_kernel_read(replaced, (void *)hook_pos, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(replaced, (void *)hook_pos, + MCOUNT_INSN_SIZE)) return -EFAULT; /* diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c index f16ade84a11f..c3275f42d1ac 100644 --- a/arch/riscv/kernel/kgdb.c +++ b/arch/riscv/kernel/kgdb.c @@ -62,7 +62,7 @@ int get_step_address(struct pt_regs *regs, unsigned long *next_addr) unsigned int rs1_num, rs2_num; int op_code; - if (probe_kernel_address((void *)pc, op_code)) + if (get_kernel_nofault(op_code, (void *)pc)) return -EINVAL; if ((op_code & __INSN_LENGTH_MASK) != __INSN_LENGTH_GE_32) { if (is_c_jalr_insn(op_code) || is_c_jr_insn(op_code)) { @@ -146,14 +146,14 @@ int do_single_step(struct pt_regs *regs) return error; /* Store the op code in the stepped address */ - error = probe_kernel_address((void *)addr, stepped_opcode); + error = get_kernel_nofault(stepped_opcode, (void *)addr); if (error) return error; stepped_address = addr; /* Replace the op code with the break instruction */ - error = probe_kernel_write((void *)stepped_address, + error = copy_to_kernel_nofault((void *)stepped_address, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE); /* Flush and return */ @@ -173,7 +173,7 @@ int do_single_step(struct pt_regs *regs) static void undo_single_step(struct pt_regs *regs) { if (stepped_opcode != 0) { - probe_kernel_write((void *)stepped_address, + copy_to_kernel_nofault((void *)stepped_address, (void *)&stepped_opcode, BREAK_INSTR_SIZE); flush_icache_range(stepped_address, stepped_address + BREAK_INSTR_SIZE); diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index d4a64dfed342..3fe7a5296aa5 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -63,7 +63,7 @@ static int patch_insn_write(void *addr, const void *insn, size_t len) waddr = patch_map(addr, FIX_TEXT_POKE0); - ret = probe_kernel_write(waddr, insn, len); + ret = copy_to_kernel_nofault(waddr, insn, len); patch_unmap(FIX_TEXT_POKE0); @@ -76,7 +76,7 @@ NOKPROBE_SYMBOL(patch_insn_write); #else static int patch_insn_write(void *addr, const void *insn, size_t len) { - return probe_kernel_write(addr, insn, len); + return copy_to_kernel_nofault(addr, insn, len); } NOKPROBE_SYMBOL(patch_insn_write); #endif /* CONFIG_MMU */ diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index ecec1778e3a4..7d95cce5e47c 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -137,7 +137,7 @@ static inline unsigned long get_break_insn_length(unsigned long pc) { bug_insn_t insn; - if (probe_kernel_address((bug_insn_t *)pc, insn)) + if (get_kernel_nofault(insn, (bug_insn_t *)pc)) return 0; return GET_INSN_LENGTH(insn); @@ -165,7 +165,7 @@ int is_valid_bugaddr(unsigned long pc) if (pc < VMALLOC_START) return 0; - if (probe_kernel_address((bug_insn_t *)pc, insn)) + if (get_kernel_nofault(insn, (bug_insn_t *)pc)) return 0; if ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) return (insn == __BUG_INSN_32); diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 44e01dd1e624..b388e87a08bf 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -83,7 +83,7 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, { struct ftrace_insn orig, new, old; - if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old))) + if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old))) return -EFAULT; if (addr == MCOUNT_ADDR) { /* Initial code replacement */ @@ -105,7 +105,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { struct ftrace_insn orig, new, old; - if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old))) + if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old))) return -EFAULT; /* Replace nop with an ftrace call. */ ftrace_generate_nop_insn(&orig); diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 6a24751557f0..d53c2e2ea1fd 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -105,7 +105,7 @@ static int bad_address(void *p) { unsigned long dummy; - return probe_kernel_address((unsigned long *)p, dummy); + return get_kernel_nofault(dummy, (unsigned long *)p); } static void dump_pagetable(unsigned long asce, unsigned long address) diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c index 1b04270e5460..0646c5961846 100644 --- a/arch/sh/kernel/ftrace.c +++ b/arch/sh/kernel/ftrace.c @@ -119,7 +119,7 @@ static void ftrace_mod_code(void) * But if one were to fail, then they all should, and if one were * to succeed, then they all should. */ - mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode, + mod_code_status = copy_to_kernel_nofault(mod_code_ip, mod_code_newcode, MCOUNT_INSN_SIZE); /* if we fail, then kill any new writers */ @@ -203,7 +203,7 @@ static int ftrace_modify_code(unsigned long ip, unsigned char *old_code, */ /* read the text we want to modify */ - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(replaced, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; /* Make sure it is what we expect it to be */ @@ -268,7 +268,7 @@ static int ftrace_mod(unsigned long ip, unsigned long old_addr, { unsigned char code[MCOUNT_INSN_SIZE]; - if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(code, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; if (old_addr != __raw_readl((unsigned long *)code)) diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c index a33025451fcd..9c3d32b80038 100644 --- a/arch/sh/kernel/traps.c +++ b/arch/sh/kernel/traps.c @@ -118,7 +118,7 @@ int is_valid_bugaddr(unsigned long addr) if (addr < PAGE_OFFSET) return 0; - if (probe_kernel_address((insn_size_t *)addr, opcode)) + if (get_kernel_nofault(opcode, (insn_size_t *)addr)) return 0; if (opcode == TRAPA_BUG_OPCODE) return 1; diff --git a/arch/um/kernel/maccess.c b/arch/um/kernel/maccess.c index e929c0966696..8ccd56813f68 100644 --- a/arch/um/kernel/maccess.c +++ b/arch/um/kernel/maccess.c @@ -7,7 +7,7 @@ #include <linux/kernel.h> #include <os.h> -bool probe_kernel_read_allowed(const void *src, size_t size) +bool copy_from_kernel_nofault_allowed(const void *src, size_t size) { void *psrc = (void *)rounddown((unsigned long)src, PAGE_SIZE); diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index ebedeab48704..255b2dde2c1b 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -278,7 +278,7 @@ static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs } /* To avoid include hell, we can't include uaccess.h */ -extern long probe_kernel_read(void *dst, const void *src, size_t size); +extern long copy_from_kernel_nofault(void *dst, const void *src, size_t size); /** * regs_get_kernel_stack_nth() - get Nth entry of the stack @@ -298,7 +298,7 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, addr = regs_get_kernel_stack_nth_addr(regs, n); if (addr) { - ret = probe_kernel_read(&val, addr, sizeof(val)); + ret = copy_from_kernel_nofault(&val, addr, sizeof(val)); if (!ret) return val; } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 456511b2284e..b037cfa7c0c5 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -106,7 +106,7 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl) bad_ip = user_mode(regs) && __chk_range_not_ok(prologue, OPCODE_BUFSIZE, TASK_SIZE_MAX); - if (bad_ip || probe_kernel_read(opcodes, (u8 *)prologue, + if (bad_ip || copy_from_kernel_nofault(opcodes, (u8 *)prologue, OPCODE_BUFSIZE)) { printk("%sCode: Bad RIP value.\n", loglvl); } else { diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index c84d28e90a58..51504566b3a6 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -86,7 +86,7 @@ static int ftrace_verify_code(unsigned long ip, const char *old_code) * sure what we read is what we expected it to be before modifying it. */ /* read the text we want to modify */ - if (probe_kernel_read(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) { + if (copy_from_kernel_nofault(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) { WARN_ON(1); return -EFAULT; } @@ -355,7 +355,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE); /* Copy ftrace_caller onto the trampoline memory */ - ret = probe_kernel_read(trampoline, (void *)start_offset, size); + ret = copy_from_kernel_nofault(trampoline, (void *)start_offset, size); if (WARN_ON(ret < 0)) goto fail; @@ -363,13 +363,13 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) /* The trampoline ends with ret(q) */ retq = (unsigned long)ftrace_stub; - ret = probe_kernel_read(ip, (void *)retq, RET_SIZE); + ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE); if (WARN_ON(ret < 0)) goto fail; if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { ip = trampoline + (ftrace_regs_caller_ret - ftrace_regs_caller); - ret = probe_kernel_read(ip, (void *)retq, RET_SIZE); + ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE); if (WARN_ON(ret < 0)) goto fail; } @@ -506,7 +506,7 @@ static void *addr_from_call(void *ptr) union text_poke_insn call; int ret; - ret = probe_kernel_read(&call, ptr, CALL_INSN_SIZE); + ret = copy_from_kernel_nofault(&call, ptr, CALL_INSN_SIZE); if (WARN_ON_ONCE(ret < 0)) return NULL; diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index c44fe7d8d9a4..68acd30c6b87 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -732,11 +732,11 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) int err; bpt->type = BP_BREAKPOINT; - err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr, + err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE); if (err) return err; - err = probe_kernel_write((char *)bpt->bpt_addr, + err = copy_to_kernel_nofault((char *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE); if (!err) return err; @@ -768,7 +768,7 @@ int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt) return 0; knl_write: - return probe_kernel_write((char *)bpt->bpt_addr, + return copy_to_kernel_nofault((char *)bpt->bpt_addr, (char *)bpt->saved_instr, BREAK_INSTR_SIZE); } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 3bafe1bd4dc7..f09985c87d73 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -243,7 +243,7 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr) * Fortunately, we know that the original code is the ideal 5-byte * long NOP. */ - if (probe_kernel_read(buf, (void *)addr, + if (copy_from_kernel_nofault(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t))) return 0UL; @@ -346,7 +346,8 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn) return 0; /* This can access kernel text if given address is not recovered */ - if (probe_kernel_read(dest, (void *)recovered_insn, MAX_INSN_SIZE)) + if (copy_from_kernel_nofault(dest, (void *)recovered_insn, + MAX_INSN_SIZE)) return 0; kernel_insn_init(insn, dest, MAX_INSN_SIZE); diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 321c19950285..7af4c61dde52 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -56,7 +56,7 @@ found: * overwritten by jump destination address. In this case, original * bytes must be recovered from op->optinsn.copied_insn buffer. */ - if (probe_kernel_read(buf, (void *)addr, + if (copy_from_kernel_nofault(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t))) return 0UL; diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index ee0286390a4c..9e1def3744f2 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -94,12 +94,12 @@ static bool match_id(struct pci_dev *pdev, unsigned short vendor, unsigned short } static bool probe_list(struct pci_dev *pdev, unsigned short vendor, - const unsigned char *rom_list) + const void *rom_list) { unsigned short device; do { - if (probe_kernel_address(rom_list, device) != 0) + if (get_kernel_nofault(device, rom_list) != 0) device = 0; if (device && match_id(pdev, vendor, device)) @@ -119,19 +119,19 @@ static struct resource *find_oprom(struct pci_dev *pdev) for (i = 0; i < ARRAY_SIZE(adapter_rom_resources); i++) { struct resource *res = &adapter_rom_resources[i]; unsigned short offset, vendor, device, list, rev; - const unsigned char *rom; + const void *rom; if (res->end == 0) break; rom = isa_bus_to_virt(res->start); - if (probe_kernel_address(rom + 0x18, offset) != 0) + if (get_kernel_nofault(offset, rom + 0x18) != 0) continue; - if (probe_kernel_address(rom + offset + 0x4, vendor) != 0) + if (get_kernel_nofault(vendor, rom + offset + 0x4) != 0) continue; - if (probe_kernel_address(rom + offset + 0x6, device) != 0) + if (get_kernel_nofault(device, rom + offset + 0x6) != 0) continue; if (match_id(pdev, vendor, device)) { @@ -139,8 +139,8 @@ static struct resource *find_oprom(struct pci_dev *pdev) break; } - if (probe_kernel_address(rom + offset + 0x8, list) == 0 && - probe_kernel_address(rom + offset + 0xc, rev) == 0 && + if (get_kernel_nofault(list, rom + offset + 0x8) == 0 && + get_kernel_nofault(rev, rom + offset + 0xc) == 0 && rev >= 3 && list && probe_list(pdev, vendor, rom + offset + list)) { oprom = res; @@ -183,14 +183,14 @@ static int __init romsignature(const unsigned char *rom) const unsigned short * const ptr = (const unsigned short *)rom; unsigned short sig; - return probe_kernel_address(ptr, sig) == 0 && sig == ROMSIGNATURE; + return get_kernel_nofault(sig, ptr) == 0 && sig == ROMSIGNATURE; } static int __init romchecksum(const unsigned char *rom, unsigned long length) { unsigned char sum, c; - for (sum = 0; length && probe_kernel_address(rom++, c) == 0; length--) + for (sum = 0; length && get_kernel_nofault(c, rom++) == 0; length--) sum += c; return !length && !sum; } @@ -211,7 +211,7 @@ void __init probe_roms(void) video_rom_resource.start = start; - if (probe_kernel_address(rom + 2, c) != 0) + if (get_kernel_nofault(c, rom + 2) != 0) continue; /* 0 < length <= 0x7f * 512, historically */ @@ -249,7 +249,7 @@ void __init probe_roms(void) if (!romsignature(rom)) continue; - if (probe_kernel_address(rom + 2, c) != 0) + if (get_kernel_nofault(c, rom + 2) != 0) continue; /* 0 < length <= 0x7f * 512, historically */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index af75109485c2..f9727b96961f 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -91,7 +91,7 @@ int is_valid_bugaddr(unsigned long addr) if (addr < TASK_SIZE_MAX) return 0; - if (probe_kernel_address((unsigned short *)addr, ud)) + if (get_kernel_nofault(ud, (unsigned short *)addr)) return 0; return ud == INSN_UD0 || ud == INSN_UD2; @@ -488,7 +488,8 @@ static enum kernel_gp_hint get_kernel_gp_address(struct pt_regs *regs, u8 insn_buf[MAX_INSN_SIZE]; struct insn insn; - if (probe_kernel_read(insn_buf, (void *)regs->ip, MAX_INSN_SIZE)) + if (copy_from_kernel_nofault(insn_buf, (void *)regs->ip, + MAX_INSN_SIZE)) return GP_NO_HINT; kernel_insn_init(&insn, insn_buf, MAX_INSN_SIZE); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 66be9bd60307..1ead568c0101 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -99,7 +99,7 @@ check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr, return !instr_lo || (instr_lo>>1) == 1; case 0x00: /* Prefetch instruction is 0x0F0D or 0x0F18 */ - if (probe_kernel_address(instr, opcode)) + if (get_kernel_nofault(opcode, instr)) return 0; *prefetch = (instr_lo == 0xF) && @@ -133,7 +133,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) while (instr < max_instr) { unsigned char opcode; - if (probe_kernel_address(instr, opcode)) + if (get_kernel_nofault(opcode, instr)) break; instr++; @@ -301,7 +301,7 @@ static int bad_address(void *p) { unsigned long dummy; - return probe_kernel_address((unsigned long *)p, dummy); + return get_kernel_nofault(dummy, (unsigned long *)p); } static void dump_pagetable(unsigned long address) @@ -442,7 +442,7 @@ static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index) return; } - if (probe_kernel_read(&desc, (void *)(gdt->address + offset), + if (copy_from_kernel_nofault(&desc, (void *)(gdt->address + offset), sizeof(struct ldttss_desc))) { pr_alert("%s: 0x%hx -- GDT entry is not readable\n", name, index); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index bda909e3e37e..8b4afad84f4a 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -737,7 +737,7 @@ static void __init test_wp_bit(void) __set_fixmap(FIX_WP_TEST, __pa_symbol(empty_zero_page), PAGE_KERNEL_RO); - if (probe_kernel_write((char *)fix_to_virt(FIX_WP_TEST), &z, 1)) { + if (copy_to_kernel_nofault((char *)fix_to_virt(FIX_WP_TEST), &z, 1)) { clear_fixmap(FIX_WP_TEST); printk(KERN_CONT "Ok.\n"); return; diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c index e1d7d7477c22..92ec176a7293 100644 --- a/arch/x86/mm/maccess.c +++ b/arch/x86/mm/maccess.c @@ -9,7 +9,7 @@ static __always_inline u64 canonical_address(u64 vaddr, u8 vaddr_bits) return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits); } -bool probe_kernel_read_allowed(const void *unsafe_src, size_t size) +bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { unsigned long vaddr = (unsigned long)unsafe_src; @@ -22,7 +22,7 @@ bool probe_kernel_read_allowed(const void *unsafe_src, size_t size) canonical_address(vaddr, boot_cpu_data.x86_virt_bits) == vaddr; } #else -bool probe_kernel_read_allowed(const void *unsafe_src, size_t size) +bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { return (unsigned long)unsafe_src >= TASK_SIZE_MAX; } diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 9c97d814125e..4f15280732ed 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -302,7 +302,7 @@ static const struct pci_raw_ops *__init pci_find_bios(void) check <= (union bios32 *) __va(0xffff0); ++check) { long sig; - if (probe_kernel_address(&check->fields.signature, sig)) + if (get_kernel_nofault(sig, &check->fields.signature)) continue; if (check->fields.signature != BIOS32_SIGNATURE) diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index b04e6e72a592..088bd764e0b7 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -34,6 +34,7 @@ KCOV_INSTRUMENT := n PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING +PURGATORY_CFLAGS += $(call cc-option,-fno-stack-protector) # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That # in turn leaves some undefined symbols like __fentry__ in purgatory and not diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 33b309d65955..acc49fa6a097 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -386,7 +386,7 @@ static void set_aliased_prot(void *v, pgprot_t prot) preempt_disable(); - probe_kernel_read(&dummy, v, 1); + copy_from_kernel_nofault(&dummy, v, 1); if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0)) BUG(); diff --git a/block/partitions/ldm.h b/block/partitions/ldm.h index 841580af7f9b..d8d6beaa72c4 100644 --- a/block/partitions/ldm.h +++ b/block/partitions/ldm.h @@ -93,7 +93,7 @@ struct frag { /* VBLK Fragment handling */ u8 num; /* Total number of records */ u8 rec; /* This is record number n */ u8 map; /* Which portions are in use */ - u8 data[0]; + u8 data[]; }; /* In memory LDM database structures. */ diff --git a/drivers/amba/tegra-ahb.c b/drivers/amba/tegra-ahb.c index 57d3b2e2d007..0b2c20fddb7c 100644 --- a/drivers/amba/tegra-ahb.c +++ b/drivers/amba/tegra-ahb.c @@ -120,7 +120,7 @@ static const u32 tegra_ahb_gizmo[] = { struct tegra_ahb { void __iomem *regs; struct device *dev; - u32 ctx[0]; + u32 ctx[]; }; static inline u32 gizmo_readl(struct tegra_ahb *ahb, u32 offset) diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 14345a87c7cc..33d0831c99b6 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -620,7 +620,7 @@ struct fifo_buffer { unsigned int head_index; unsigned int size; int total; /* sum of all values */ - int values[0]; + int values[]; }; extern struct fifo_buffer *fifo_alloc(unsigned int fifo_size); diff --git a/drivers/block/drbd/drbd_protocol.h b/drivers/block/drbd/drbd_protocol.h index e6fc5ad72501..dea59c92ecc1 100644 --- a/drivers/block/drbd/drbd_protocol.h +++ b/drivers/block/drbd/drbd_protocol.h @@ -271,7 +271,7 @@ struct p_rs_param { u32 resync_rate; /* Since protocol version 88 and higher. */ - char verify_alg[0]; + char verify_alg[]; } __packed; struct p_rs_param_89 { @@ -305,7 +305,7 @@ struct p_protocol { u32 two_primaries; /* Since protocol version 87 and higher. */ - char integrity_alg[0]; + char integrity_alg[]; } __packed; @@ -360,7 +360,7 @@ struct p_sizes { u16 dds_flags; /* use enum dds_flags here. */ /* optional queue_limits if (agreed_features & DRBD_FF_WSAME) */ - struct o_qlim qlim[0]; + struct o_qlim qlim[]; } __packed; struct p_state { @@ -409,7 +409,7 @@ struct p_compressed_bm { */ u8 encoding; - u8 code[0]; + u8 code[]; } __packed; struct p_delay_probe93 { diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 7420648a1de6..4f61e9209461 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -1451,8 +1451,10 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req) static void rbd_osd_format_read(struct ceph_osd_request *osd_req) { struct rbd_obj_request *obj_request = osd_req->r_priv; + struct rbd_device *rbd_dev = obj_request->img_request->rbd_dev; + struct ceph_options *opt = rbd_dev->rbd_client->client->options; - osd_req->r_flags = CEPH_OSD_FLAG_READ; + osd_req->r_flags = CEPH_OSD_FLAG_READ | opt->read_from_replica; osd_req->r_snapid = obj_request->img_request->snap_id; } diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 31cae88a730b..934c92dcb9ab 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -171,7 +171,7 @@ static ssize_t read_mem(struct file *file, char __user *buf, if (!ptr) goto failed; - probe = probe_kernel_read(bounce, ptr, sz); + probe = copy_from_kernel_nofault(bounce, ptr, sz); unxlate_dev_mem_ptr(p, ptr); if (probe) goto failed; diff --git a/drivers/crypto/chelsio/chcr_crypto.h b/drivers/crypto/chelsio/chcr_crypto.h index b3fdbdc25acb..31e427e273f8 100644 --- a/drivers/crypto/chelsio/chcr_crypto.h +++ b/drivers/crypto/chelsio/chcr_crypto.h @@ -223,7 +223,7 @@ struct chcr_authenc_ctx { struct __aead_ctx { struct chcr_gcm_ctx gcm[0]; - struct chcr_authenc_ctx authenc[0]; + struct chcr_authenc_ctx authenc[]; }; struct chcr_aead_ctx { @@ -235,7 +235,7 @@ struct chcr_aead_ctx { u8 nonce[4]; u16 hmac_ctrl; u16 mayverify; - struct __aead_ctx ctx[0]; + struct __aead_ctx ctx[]; }; struct hmac_ctx { @@ -247,7 +247,7 @@ struct hmac_ctx { struct __crypto_ctx { struct hmac_ctx hmacctx[0]; struct ablk_ctx ablkctx[0]; - struct chcr_aead_ctx aeadctx[0]; + struct chcr_aead_ctx aeadctx[]; }; struct chcr_context { @@ -257,7 +257,7 @@ struct chcr_context { unsigned int ntxq; unsigned int nrxq; struct completion cbc_aes_aio_done; - struct __crypto_ctx crypto_ctx[0]; + struct __crypto_ctx crypto_ctx[]; }; struct chcr_hctx_per_wr { diff --git a/drivers/dio/dio.c b/drivers/dio/dio.c index c9aa15fb86a9..193b40e7aec0 100644 --- a/drivers/dio/dio.c +++ b/drivers/dio/dio.c @@ -135,7 +135,8 @@ int __init dio_find(int deviceid) else va = ioremap(pa, PAGE_SIZE); - if (probe_kernel_read(&i, (unsigned char *)va + DIO_IDOFF, 1)) { + if (copy_from_kernel_nofault(&i, + (unsigned char *)va + DIO_IDOFF, 1)) { if (scode >= DIOII_SCBASE) iounmap(va); continue; /* no board present at that select code */ @@ -208,7 +209,8 @@ static int __init dio_init(void) else va = ioremap(pa, PAGE_SIZE); - if (probe_kernel_read(&i, (unsigned char *)va + DIO_IDOFF, 1)) { + if (copy_from_kernel_nofault(&i, + (unsigned char *)va + DIO_IDOFF, 1)) { if (scode >= DIOII_SCBASE) iounmap(va); continue; /* no board present at that select code */ diff --git a/drivers/dma/milbeaut-hdmac.c b/drivers/dma/milbeaut-hdmac.c index 8853d442430b..a8cfb59f6efe 100644 --- a/drivers/dma/milbeaut-hdmac.c +++ b/drivers/dma/milbeaut-hdmac.c @@ -77,7 +77,7 @@ struct milbeaut_hdmac_device { struct dma_device ddev; struct clk *clk; void __iomem *reg_base; - struct milbeaut_hdmac_chan channels[0]; + struct milbeaut_hdmac_chan channels[]; }; static struct milbeaut_hdmac_chan * diff --git a/drivers/dma/milbeaut-xdmac.c b/drivers/dma/milbeaut-xdmac.c index ab3d2f395378..85a597228fb0 100644 --- a/drivers/dma/milbeaut-xdmac.c +++ b/drivers/dma/milbeaut-xdmac.c @@ -74,7 +74,7 @@ struct milbeaut_xdmac_chan { struct milbeaut_xdmac_device { struct dma_device ddev; void __iomem *reg_base; - struct milbeaut_xdmac_chan channels[0]; + struct milbeaut_xdmac_chan channels[]; }; static struct milbeaut_xdmac_chan * diff --git a/drivers/dma/moxart-dma.c b/drivers/dma/moxart-dma.c index 4ab493d46375..347146a6e1d0 100644 --- a/drivers/dma/moxart-dma.c +++ b/drivers/dma/moxart-dma.c @@ -127,7 +127,7 @@ struct moxart_desc { unsigned int dma_cycles; struct virt_dma_desc vd; uint8_t es; - struct moxart_sg sg[0]; + struct moxart_sg sg[]; }; struct moxart_chan { diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c index b9f0d9636620..55fc7400f717 100644 --- a/drivers/dma/tegra20-apb-dma.c +++ b/drivers/dma/tegra20-apb-dma.c @@ -225,7 +225,7 @@ struct tegra_dma { u32 global_pause_count; /* Last member of the structure */ - struct tegra_dma_channel channels[0]; + struct tegra_dma_channel channels[]; }; static inline void tdma_write(struct tegra_dma *tdma, u32 reg, u32 val) diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c index c4a5c170c1f9..35d81bd857f1 100644 --- a/drivers/dma/ti/edma.c +++ b/drivers/dma/ti/edma.c @@ -211,7 +211,7 @@ struct edma_desc { u32 residue; u32 residue_stat; - struct edma_pset pset[0]; + struct edma_pset pset[]; }; struct edma_cc; diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index 945b7c604f91..c91e2dc1bb72 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -170,7 +170,7 @@ struct udma_desc { void *metadata; /* pointer to provided metadata buffer (EPIP, PSdata) */ unsigned int hwdesc_count; - struct udma_hwdesc hwdesc[0]; + struct udma_hwdesc hwdesc[]; }; enum udma_chan_state { diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c index 39382694fdfc..68e48bf54d78 100644 --- a/drivers/dma/timb_dma.c +++ b/drivers/dma/timb_dma.c @@ -88,7 +88,7 @@ struct timb_dma { struct dma_device dma; void __iomem *membase; struct tasklet_struct tasklet; - struct timb_dma_chan channels[0]; + struct timb_dma_chan channels[]; }; static struct device *chan2dev(struct dma_chan *chan) diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index c7ea4f2d5ca6..fb6c651214f3 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -117,7 +117,7 @@ struct inbound_transaction_resource { struct descriptor_resource { struct client_resource resource; struct fw_descriptor descriptor; - u32 data[0]; + u32 data[]; }; struct iso_resource { diff --git a/drivers/firewire/core-transaction.c b/drivers/firewire/core-transaction.c index 404a035f104d..439d918bbaaf 100644 --- a/drivers/firewire/core-transaction.c +++ b/drivers/firewire/core-transaction.c @@ -620,7 +620,7 @@ struct fw_request { u32 request_header[4]; int ack; u32 length; - u32 data[0]; + u32 data[]; }; static void free_response_callback(struct fw_packet *packet, diff --git a/drivers/firewire/core.h b/drivers/firewire/core.h index 4b0e4ee655a1..71d5f16f311c 100644 --- a/drivers/firewire/core.h +++ b/drivers/firewire/core.h @@ -191,7 +191,7 @@ struct fw_node { /* Upper layer specific data. */ void *data; - struct fw_node *ports[0]; + struct fw_node *ports[]; }; static inline struct fw_node *fw_node_get(struct fw_node *node) diff --git a/drivers/firewire/nosy.c b/drivers/firewire/nosy.c index 6ca2f5ab6c57..5fd6a60b6741 100644 --- a/drivers/firewire/nosy.c +++ b/drivers/firewire/nosy.c @@ -52,7 +52,7 @@ struct pcl { struct packet { unsigned int length; - char data[0]; + char data[]; }; struct packet_buffer { diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 33269316f111..54fdc39cd0bc 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -111,7 +111,7 @@ struct descriptor_buffer { dma_addr_t buffer_bus; size_t buffer_size; size_t used; - struct descriptor buffer[0]; + struct descriptor buffer[]; }; struct context { diff --git a/drivers/firmware/dmi-sysfs.c b/drivers/firmware/dmi-sysfs.c index b6180023eba7..8b8127fa8955 100644 --- a/drivers/firmware/dmi-sysfs.c +++ b/drivers/firmware/dmi-sysfs.c @@ -262,7 +262,7 @@ struct dmi_system_event_log { u8 header_format; u8 type_descriptors_supported_count; u8 per_log_type_descriptor_length; - u8 supported_log_type_descriptos[0]; + u8 supported_log_type_descriptos[]; } __packed; #define DMI_SYSFS_SEL_FIELD(_field) \ diff --git a/drivers/firmware/google/memconsole-coreboot.c b/drivers/firmware/google/memconsole-coreboot.c index fd7f0fbec07e..d17e4d6ac9bc 100644 --- a/drivers/firmware/google/memconsole-coreboot.c +++ b/drivers/firmware/google/memconsole-coreboot.c @@ -21,7 +21,7 @@ struct cbmem_cons { u32 size_dont_access_after_boot; u32 cursor; - u8 body[0]; + u8 body[]; } __packed; #define CURSOR_MASK ((1 << 28) - 1) diff --git a/drivers/firmware/google/vpd.c b/drivers/firmware/google/vpd.c index db0812263d46..d23c5c69ab52 100644 --- a/drivers/firmware/google/vpd.c +++ b/drivers/firmware/google/vpd.c @@ -32,7 +32,7 @@ struct vpd_cbmem { u32 version; u32 ro_size; u32 rw_size; - u8 blob[0]; + u8 blob[]; }; struct vpd_section { diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c index 96758b71a8db..7127a04bca19 100644 --- a/drivers/firmware/iscsi_ibft.c +++ b/drivers/firmware/iscsi_ibft.c @@ -104,7 +104,7 @@ struct ibft_control { u16 tgt0_off; u16 nic1_off; u16 tgt1_off; - u16 expansion[0]; + u16 expansion[]; } __attribute__((__packed__)); struct ibft_initiator { diff --git a/drivers/firmware/pcdp.h b/drivers/firmware/pcdp.h index ce75d1da9e84..e02540571c52 100644 --- a/drivers/firmware/pcdp.h +++ b/drivers/firmware/pcdp.h @@ -103,6 +103,6 @@ struct pcdp { u8 creator_id[4]; u32 creator_rev; u32 num_uarts; - struct pcdp_uart uart[0]; /* actual size is num_uarts */ + struct pcdp_uart uart[]; /* actual size is num_uarts */ /* remainder of table is pcdp_device structures */ } __attribute__((packed)); diff --git a/drivers/hwtracing/stm/policy.c b/drivers/hwtracing/stm/policy.c index 4f932a419752..603b4a9969d3 100644 --- a/drivers/hwtracing/stm/policy.c +++ b/drivers/hwtracing/stm/policy.c @@ -34,7 +34,7 @@ struct stp_policy_node { unsigned int first_channel; unsigned int last_channel; /* this is the one that's exposed to the attributes */ - unsigned char priv[0]; + unsigned char priv[]; }; void *stp_policy_node_priv(struct stp_policy_node *pn) diff --git a/drivers/hwtracing/stm/stm.h b/drivers/hwtracing/stm/stm.h index 3569439d53bb..a9be49fc7a6b 100644 --- a/drivers/hwtracing/stm/stm.h +++ b/drivers/hwtracing/stm/stm.h @@ -23,7 +23,7 @@ void *stp_policy_node_priv(struct stp_policy_node *pn); struct stp_master { unsigned int nr_free; - unsigned long chan_map[0]; + unsigned long chan_map[]; }; struct stm_device { @@ -42,7 +42,7 @@ struct stm_device { const struct config_item_type *pdrv_node_type; /* master allocation */ spinlock_t mc_lock; - struct stp_master *masters[0]; + struct stp_master *masters[]; }; #define to_stm_device(_d) \ diff --git a/drivers/input/serio/hp_sdc.c b/drivers/input/serio/hp_sdc.c index 654252361653..13eacf6ab431 100644 --- a/drivers/input/serio/hp_sdc.c +++ b/drivers/input/serio/hp_sdc.c @@ -1021,7 +1021,7 @@ static int __init hp_sdc_register(void) hp_sdc.base_io = (unsigned long) 0xf0428000; hp_sdc.data_io = (unsigned long) hp_sdc.base_io + 1; hp_sdc.status_io = (unsigned long) hp_sdc.base_io + 3; - if (!probe_kernel_read(&i, (unsigned char *)hp_sdc.data_io, 1)) + if (!copy_from_kernel_nofault(&i, (unsigned char *)hp_sdc.data_io, 1)) hp_sdc.dev = (void *)1; hp_sdc.dev_err = hp_sdc_init(); #endif diff --git a/drivers/media/usb/pwc/pwc.h b/drivers/media/usb/pwc/pwc.h index 3362962d0d00..b02a3c7b7742 100644 --- a/drivers/media/usb/pwc/pwc.h +++ b/drivers/media/usb/pwc/pwc.h @@ -193,7 +193,7 @@ struct pwc_raw_frame { decompressor) */ __u8 cmd[4]; /* the four byte of the command (in case of nala, only the first 3 bytes is filled) */ - __u8 rawframe[0]; /* frame_size = H / 4 * vbandlength */ + __u8 rawframe[]; /* frame_size = H / 4 * vbandlength */ } __packed; /* intermediate buffers with raw data from the USB cam */ diff --git a/drivers/mfd/mt6360-core.c b/drivers/mfd/mt6360-core.c index db8cdf5272c1..e9cacc27d980 100644 --- a/drivers/mfd/mt6360-core.c +++ b/drivers/mfd/mt6360-core.c @@ -412,6 +412,7 @@ MODULE_DEVICE_TABLE(of, mt6360_pmu_of_id); static struct i2c_driver mt6360_pmu_driver = { .driver = { + .name = "mt6360_pmu", .pm = &mt6360_pmu_pm_ops, .of_match_table = of_match_ptr(mt6360_pmu_of_id), }, diff --git a/drivers/misc/kgdbts.c b/drivers/misc/kgdbts.c index bccd341e9ae1..d5d2af4d10e6 100644 --- a/drivers/misc/kgdbts.c +++ b/drivers/misc/kgdbts.c @@ -828,7 +828,7 @@ static void run_plant_and_detach_test(int is_early) char before[BREAK_INSTR_SIZE]; char after[BREAK_INSTR_SIZE]; - probe_kernel_read(before, (char *)kgdbts_break_test, + copy_from_kernel_nofault(before, (char *)kgdbts_break_test, BREAK_INSTR_SIZE); init_simple_test(); ts.tst = plant_and_detach_test; @@ -836,8 +836,8 @@ static void run_plant_and_detach_test(int is_early) /* Activate test with initial breakpoint */ if (!is_early) kgdb_breakpoint(); - probe_kernel_read(after, (char *)kgdbts_break_test, - BREAK_INSTR_SIZE); + copy_from_kernel_nofault(after, (char *)kgdbts_break_test, + BREAK_INSTR_SIZE); if (memcmp(before, after, BREAK_INSTR_SIZE)) { printk(KERN_CRIT "kgdbts: ERROR kgdb corrupted memory\n"); panic("kgdb memory corruption"); diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index efd1a1d1f35e..5d3c691a1c66 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -552,6 +552,8 @@ static int bareudp_validate(struct nlattr *tb[], struct nlattr *data[], static int bareudp2info(struct nlattr *data[], struct bareudp_conf *conf, struct netlink_ext_ack *extack) { + memset(conf, 0, sizeof(*conf)); + if (!data[IFLA_BAREUDP_PORT]) { NL_SET_ERR_MSG(extack, "port not specified"); return -EINVAL; diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c index d08a3d559114..6ad83a881039 100644 --- a/drivers/net/can/peak_canfd/peak_pciefd_main.c +++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c @@ -146,7 +146,7 @@ struct pciefd_rx_dma { __le32 irq_status; __le32 sys_time_low; __le32 sys_time_high; - struct pucan_rx_msg msg[0]; + struct pucan_rx_msg msg[]; } __packed __aligned(4); /* Tx Link record */ @@ -194,7 +194,7 @@ struct pciefd_board { struct pci_dev *pci_dev; int can_count; spinlock_t cmd_lock; /* 64-bits cmds must be atomic */ - struct pciefd_can *can[0]; /* array of network devices */ + struct pciefd_can *can[]; /* array of network devices */ }; /* supported device ids. */ diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index bc0e47c1dbb9..177134596458 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -891,16 +891,16 @@ void sja1105_ptp_txtstamp_skb(struct dsa_switch *ds, int port, mutex_lock(&ptp_data->lock); - rc = sja1105_ptpclkval_read(priv, &ticks, NULL); + rc = sja1105_ptpegr_ts_poll(ds, port, &ts); if (rc < 0) { - dev_err(ds->dev, "Failed to read PTP clock: %d\n", rc); + dev_err(ds->dev, "timed out polling for tstamp\n"); kfree_skb(skb); goto out; } - rc = sja1105_ptpegr_ts_poll(ds, port, &ts); + rc = sja1105_ptpclkval_read(priv, &ticks, NULL); if (rc < 0) { - dev_err(ds->dev, "timed out polling for tstamp\n"); + dev_err(ds->dev, "Failed to read PTP clock: %d\n", rc); kfree_skb(skb); goto out; } diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index b9b4edb913c1..9b7f1af5f574 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1249,8 +1249,12 @@ out_disable_adv_intr: static void __alx_stop(struct alx_priv *alx) { - alx_halt(alx); alx_free_irq(alx); + + cancel_work_sync(&alx->link_check_wk); + cancel_work_sync(&alx->reset_wk); + + alx_halt(alx); alx_free_rings(alx); alx_free_napis(alx); } @@ -1855,9 +1859,6 @@ static void alx_remove(struct pci_dev *pdev) struct alx_priv *alx = pci_get_drvdata(pdev); struct alx_hw *hw = &alx->hw; - cancel_work_sync(&alx->link_check_wk); - cancel_work_sync(&alx->reset_wk); - /* restore permanent mac address */ alx_set_macaddr(hw, hw->perm_addr); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index c62589c266b2..b93e05f91d77 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -10037,7 +10037,7 @@ static void bnxt_timer(struct timer_list *t) struct bnxt *bp = from_timer(bp, t, timer); struct net_device *dev = bp->dev; - if (!netif_running(dev)) + if (!netif_running(dev) || !test_bit(BNXT_STATE_OPEN, &bp->state)) return; if (atomic_read(&bp->intr_sem) != 0) @@ -12133,19 +12133,9 @@ static int bnxt_resume(struct device *device) goto resume_exit; } - if (bnxt_hwrm_queue_qportcfg(bp)) { - rc = -ENODEV; + rc = bnxt_hwrm_func_qcaps(bp); + if (rc) goto resume_exit; - } - - if (bp->hwrm_spec_code >= 0x10803) { - if (bnxt_alloc_ctx_mem(bp)) { - rc = -ENODEV; - goto resume_exit; - } - } - if (BNXT_NEW_RM(bp)) - bnxt_hwrm_func_resc_qcaps(bp, false); if (bnxt_hwrm_func_drv_rgtr(bp, NULL, 0, false)) { rc = -ENODEV; @@ -12161,6 +12151,8 @@ static int bnxt_resume(struct device *device) resume_exit: bnxt_ulp_start(bp, rc); + if (!rc) + bnxt_reenable_sriov(bp); rtnl_unlock(); return rc; } @@ -12204,6 +12196,9 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev, bnxt_close(netdev); pci_disable_device(pdev); + bnxt_free_ctx_mem(bp); + kfree(bp->ctx); + bp->ctx = NULL; rtnl_unlock(); /* Request a slot slot reset. */ @@ -12237,12 +12232,16 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) pci_set_master(pdev); err = bnxt_hwrm_func_reset(bp); - if (!err && netif_running(netdev)) - err = bnxt_open(netdev); - - if (!err) - result = PCI_ERS_RESULT_RECOVERED; + if (!err) { + err = bnxt_hwrm_func_qcaps(bp); + if (!err && netif_running(netdev)) + err = bnxt_open(netdev); + } bnxt_ulp_start(bp, err); + if (!err) { + bnxt_reenable_sriov(bp); + result = PCI_ERS_RESULT_RECOVERED; + } } if (result != PCI_ERS_RESULT_RECOVERED) { diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 5b9d7c60eebc..67933079aeea 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -2565,15 +2565,14 @@ static int macb_open(struct net_device *dev) if (bp->ptp_info) bp->ptp_info->ptp_init(dev); + return 0; + napi_exit: for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) napi_disable(&queue->napi); pm_exit: - if (err) { - pm_runtime_put_sync(&bp->pdev->dev); - return err; - } - return 0; + pm_runtime_put_sync(&bp->pdev->dev); + return err; } static int macb_close(struct net_device *dev) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 1b4d04e4474b..2baf7b3ff4cb 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -842,12 +842,13 @@ static int ibmvnic_login(struct net_device *netdev) struct ibmvnic_adapter *adapter = netdev_priv(netdev); unsigned long timeout = msecs_to_jiffies(30000); int retry_count = 0; + int retries = 10; bool retry; int rc; do { retry = false; - if (retry_count > IBMVNIC_MAX_QUEUES) { + if (retry_count > retries) { netdev_warn(netdev, "Login attempts exceeded\n"); return -1; } @@ -862,11 +863,23 @@ static int ibmvnic_login(struct net_device *netdev) if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { - netdev_warn(netdev, "Login timed out\n"); - return -1; + netdev_warn(netdev, "Login timed out, retrying...\n"); + retry = true; + adapter->init_done_rc = 0; + retry_count++; + continue; } - if (adapter->init_done_rc == PARTIALSUCCESS) { + if (adapter->init_done_rc == ABORTED) { + netdev_warn(netdev, "Login aborted, retrying...\n"); + retry = true; + adapter->init_done_rc = 0; + retry_count++; + /* FW or device may be busy, so + * wait a bit before retrying login + */ + msleep(500); + } else if (adapter->init_done_rc == PARTIALSUCCESS) { retry_count++; release_sub_crqs(adapter, 1); diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index d9fa4600f745..4b2de08137be 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -151,10 +151,8 @@ static int e1000_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid); static void e1000_restore_vlan(struct e1000_adapter *adapter); -#ifdef CONFIG_PM -static int e1000_suspend(struct pci_dev *pdev, pm_message_t state); -static int e1000_resume(struct pci_dev *pdev); -#endif +static int __maybe_unused e1000_suspend(struct device *dev); +static int __maybe_unused e1000_resume(struct device *dev); static void e1000_shutdown(struct pci_dev *pdev); #ifdef CONFIG_NET_POLL_CONTROLLER @@ -179,16 +177,16 @@ static const struct pci_error_handlers e1000_err_handler = { .resume = e1000_io_resume, }; +static SIMPLE_DEV_PM_OPS(e1000_pm_ops, e1000_suspend, e1000_resume); + static struct pci_driver e1000_driver = { .name = e1000_driver_name, .id_table = e1000_pci_tbl, .probe = e1000_probe, .remove = e1000_remove, -#ifdef CONFIG_PM - /* Power Management Hooks */ - .suspend = e1000_suspend, - .resume = e1000_resume, -#endif + .driver = { + .pm = &e1000_pm_ops, + }, .shutdown = e1000_shutdown, .err_handler = &e1000_err_handler }; @@ -5060,9 +5058,6 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool *enable_wake) struct e1000_hw *hw = &adapter->hw; u32 ctrl, ctrl_ext, rctl, status; u32 wufc = adapter->wol; -#ifdef CONFIG_PM - int retval = 0; -#endif netif_device_detach(netdev); @@ -5076,12 +5071,6 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool *enable_wake) e1000_down(adapter); } -#ifdef CONFIG_PM - retval = pci_save_state(pdev); - if (retval) - return retval; -#endif - status = er32(STATUS); if (status & E1000_STATUS_LU) wufc &= ~E1000_WUFC_LNKC; @@ -5142,37 +5131,26 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool *enable_wake) return 0; } -#ifdef CONFIG_PM -static int e1000_suspend(struct pci_dev *pdev, pm_message_t state) +static int __maybe_unused e1000_suspend(struct device *dev) { int retval; + struct pci_dev *pdev = to_pci_dev(dev); bool wake; retval = __e1000_shutdown(pdev, &wake); - if (retval) - return retval; - - if (wake) { - pci_prepare_to_sleep(pdev); - } else { - pci_wake_from_d3(pdev, false); - pci_set_power_state(pdev, PCI_D3hot); - } + device_set_wakeup_enable(dev, wake); - return 0; + return retval; } -static int e1000_resume(struct pci_dev *pdev) +static int __maybe_unused e1000_resume(struct device *dev) { + struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; u32 err; - pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); - pci_save_state(pdev); - if (adapter->need_ioport) err = pci_enable_device(pdev); else @@ -5209,7 +5187,6 @@ static int e1000_resume(struct pci_dev *pdev) return 0; } -#endif static void e1000_shutdown(struct pci_dev *pdev) { diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index a279f4fa9962..6f6479ca1267 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6349,7 +6349,6 @@ fl_out: pm_runtime_put_sync(netdev->dev.parent); } -#ifdef CONFIG_PM_SLEEP /* S0ix implementation */ static void e1000e_s0ix_entry_flow(struct e1000_adapter *adapter) { @@ -6571,7 +6570,6 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter) mac_data &= ~E1000_CTRL_EXT_FORCE_SMBUS; ew32(CTRL_EXT, mac_data); } -#endif /* CONFIG_PM_SLEEP */ static int e1000e_pm_freeze(struct device *dev) { @@ -6611,11 +6609,17 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) struct net_device *netdev = pci_get_drvdata(pdev); struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - u32 ctrl, ctrl_ext, rctl, status; - /* Runtime suspend should only enable wakeup for link changes */ - u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol; + u32 ctrl, ctrl_ext, rctl, status, wufc; int retval = 0; + /* Runtime suspend should only enable wakeup for link changes */ + if (runtime) + wufc = E1000_WUFC_LNKC; + else if (device_may_wakeup(&pdev->dev)) + wufc = adapter->wol; + else + wufc = 0; + status = er32(STATUS); if (status & E1000_STATUS_LU) wufc &= ~E1000_WUFC_LNKC; @@ -6672,7 +6676,7 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) if (adapter->hw.phy.type == e1000_phy_igp_3) { e1000e_igp3_phy_powerdown_workaround_ich8lan(&adapter->hw); } else if (hw->mac.type >= e1000_pch_lpt) { - if (!(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC))) + if (wufc && !(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC))) /* ULP does not support wake from unicast, multicast * or broadcast. */ @@ -6869,7 +6873,6 @@ err_irq: return rc; } -#ifdef CONFIG_PM static int __e1000_resume(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); @@ -6935,8 +6938,7 @@ static int __e1000_resume(struct pci_dev *pdev) return 0; } -#ifdef CONFIG_PM_SLEEP -static int e1000e_pm_suspend(struct device *dev) +static __maybe_unused int e1000e_pm_suspend(struct device *dev) { struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); @@ -6960,7 +6962,7 @@ static int e1000e_pm_suspend(struct device *dev) return rc; } -static int e1000e_pm_resume(struct device *dev) +static __maybe_unused int e1000e_pm_resume(struct device *dev) { struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); @@ -6979,9 +6981,8 @@ static int e1000e_pm_resume(struct device *dev) return e1000e_pm_thaw(dev); } -#endif /* CONFIG_PM_SLEEP */ -static int e1000e_pm_runtime_idle(struct device *dev) +static __maybe_unused int e1000e_pm_runtime_idle(struct device *dev) { struct net_device *netdev = dev_get_drvdata(dev); struct e1000_adapter *adapter = netdev_priv(netdev); @@ -6997,7 +6998,7 @@ static int e1000e_pm_runtime_idle(struct device *dev) return -EBUSY; } -static int e1000e_pm_runtime_resume(struct device *dev) +static __maybe_unused int e1000e_pm_runtime_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); @@ -7014,7 +7015,7 @@ static int e1000e_pm_runtime_resume(struct device *dev) return rc; } -static int e1000e_pm_runtime_suspend(struct device *dev) +static __maybe_unused int e1000e_pm_runtime_suspend(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); @@ -7039,7 +7040,6 @@ static int e1000e_pm_runtime_suspend(struct device *dev) return 0; } -#endif /* CONFIG_PM */ static void e1000_shutdown(struct pci_dev *pdev) { diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 2b5dad2ec650..24f4d8e0da98 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -1544,7 +1544,7 @@ static void mvpp2_read_stats(struct mvpp2_port *port) for (q = 0; q < port->ntxqs; q++) for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_txq_regs); i++) *pstats++ += mvpp2_read_index(port->priv, - MVPP22_CTRS_TX_CTR(port->id, i), + MVPP22_CTRS_TX_CTR(port->id, q), mvpp2_ethtool_txq_regs[i].offset); /* Rxqs are numbered from 0 from the user standpoint, but not from the @@ -1553,7 +1553,7 @@ static void mvpp2_read_stats(struct mvpp2_port *port) for (q = 0; q < port->nrxqs; q++) for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_rxq_regs); i++) *pstats++ += mvpp2_read_index(port->priv, - port->first_rxq + i, + port->first_rxq + q, mvpp2_ethtool_rxq_regs[i].offset); } @@ -5983,8 +5983,8 @@ static int mvpp2_remove(struct platform_device *pdev) { struct mvpp2 *priv = platform_get_drvdata(pdev); struct fwnode_handle *fwnode = pdev->dev.fwnode; + int i = 0, poolnum = MVPP2_BM_POOLS_NUM; struct fwnode_handle *port_fwnode; - int i = 0; mvpp2_dbgfs_cleanup(priv); @@ -5998,7 +5998,10 @@ static int mvpp2_remove(struct platform_device *pdev) destroy_workqueue(priv->stats_queue); - for (i = 0; i < MVPP2_BM_POOLS_NUM; i++) { + if (priv->percpu_pools) + poolnum = mvpp2_get_nrxqs(priv) * 2; + + for (i = 0; i < poolnum; i++) { struct mvpp2_bm_pool *bm_pool = &priv->bm_pools[i]; mvpp2_bm_pool_destroy(&pdev->dev, priv, bm_pool); diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c index f1ace4fec19f..3e765bdcf9e1 100644 --- a/drivers/net/ethernet/mediatek/mtk_star_emac.c +++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c @@ -24,7 +24,6 @@ #include <linux/regmap.h> #include <linux/skbuff.h> #include <linux/spinlock.h> -#include <linux/workqueue.h> #define MTK_STAR_DRVNAME "mtk_star_emac" @@ -262,7 +261,6 @@ struct mtk_star_priv { spinlock_t lock; struct rtnl_link_stats64 stats; - struct work_struct stats_work; }; static struct device *mtk_star_get_dev(struct mtk_star_priv *priv) @@ -432,42 +430,6 @@ static void mtk_star_intr_disable(struct mtk_star_priv *priv) regmap_write(priv->regs, MTK_STAR_REG_INT_MASK, ~0); } -static void mtk_star_intr_enable_tx(struct mtk_star_priv *priv) -{ - regmap_clear_bits(priv->regs, MTK_STAR_REG_INT_MASK, - MTK_STAR_BIT_INT_STS_TNTC); -} - -static void mtk_star_intr_enable_rx(struct mtk_star_priv *priv) -{ - regmap_clear_bits(priv->regs, MTK_STAR_REG_INT_MASK, - MTK_STAR_BIT_INT_STS_FNRC); -} - -static void mtk_star_intr_enable_stats(struct mtk_star_priv *priv) -{ - regmap_clear_bits(priv->regs, MTK_STAR_REG_INT_MASK, - MTK_STAR_REG_INT_STS_MIB_CNT_TH); -} - -static void mtk_star_intr_disable_tx(struct mtk_star_priv *priv) -{ - regmap_set_bits(priv->regs, MTK_STAR_REG_INT_MASK, - MTK_STAR_BIT_INT_STS_TNTC); -} - -static void mtk_star_intr_disable_rx(struct mtk_star_priv *priv) -{ - regmap_set_bits(priv->regs, MTK_STAR_REG_INT_MASK, - MTK_STAR_BIT_INT_STS_FNRC); -} - -static void mtk_star_intr_disable_stats(struct mtk_star_priv *priv) -{ - regmap_set_bits(priv->regs, MTK_STAR_REG_INT_MASK, - MTK_STAR_REG_INT_STS_MIB_CNT_TH); -} - static unsigned int mtk_star_intr_read(struct mtk_star_priv *priv) { unsigned int val; @@ -663,20 +625,6 @@ static void mtk_star_update_stats(struct mtk_star_priv *priv) stats->rx_errors += stats->rx_fifo_errors; } -/* This runs in process context and parallel TX and RX paths executing in - * napi context may result in losing some stats data but this should happen - * seldom enough to be acceptable. - */ -static void mtk_star_update_stats_work(struct work_struct *work) -{ - struct mtk_star_priv *priv = container_of(work, struct mtk_star_priv, - stats_work); - - mtk_star_update_stats(priv); - mtk_star_reset_counters(priv); - mtk_star_intr_enable_stats(priv); -} - static struct sk_buff *mtk_star_alloc_skb(struct net_device *ndev) { uintptr_t tail, offset; @@ -767,42 +715,25 @@ static void mtk_star_free_tx_skbs(struct mtk_star_priv *priv) mtk_star_ring_free_skbs(priv, ring, mtk_star_dma_unmap_tx); } -/* All processing for TX and RX happens in the napi poll callback. */ +/* All processing for TX and RX happens in the napi poll callback. + * + * FIXME: The interrupt handling should be more fine-grained with each + * interrupt enabled/disabled independently when needed. Unfortunatly this + * turned out to impact the driver's stability and until we have something + * working properly, we're disabling all interrupts during TX & RX processing + * or when resetting the counter registers. + */ static irqreturn_t mtk_star_handle_irq(int irq, void *data) { struct mtk_star_priv *priv; struct net_device *ndev; - bool need_napi = false; - unsigned int status; ndev = data; priv = netdev_priv(ndev); if (netif_running(ndev)) { - status = mtk_star_intr_read(priv); - - if (status & MTK_STAR_BIT_INT_STS_TNTC) { - mtk_star_intr_disable_tx(priv); - need_napi = true; - } - - if (status & MTK_STAR_BIT_INT_STS_FNRC) { - mtk_star_intr_disable_rx(priv); - need_napi = true; - } - - if (need_napi) - napi_schedule(&priv->napi); - - /* One of the counters reached 0x8000000 - update stats and - * reset all counters. - */ - if (unlikely(status & MTK_STAR_REG_INT_STS_MIB_CNT_TH)) { - mtk_star_intr_disable_stats(priv); - schedule_work(&priv->stats_work); - } - - mtk_star_intr_ack_all(priv); + mtk_star_intr_disable(priv); + napi_schedule(&priv->napi); } return IRQ_HANDLED; @@ -1169,8 +1100,6 @@ static void mtk_star_tx_complete_all(struct mtk_star_priv *priv) if (wake && netif_queue_stopped(ndev)) netif_wake_queue(ndev); - mtk_star_intr_enable_tx(priv); - spin_unlock(&priv->lock); } @@ -1332,20 +1261,32 @@ static int mtk_star_process_rx(struct mtk_star_priv *priv, int budget) static int mtk_star_poll(struct napi_struct *napi, int budget) { struct mtk_star_priv *priv; + unsigned int status; int received = 0; priv = container_of(napi, struct mtk_star_priv, napi); - /* Clean-up all TX descriptors. */ - mtk_star_tx_complete_all(priv); - /* Receive up to $budget packets. */ - received = mtk_star_process_rx(priv, budget); + status = mtk_star_intr_read(priv); + mtk_star_intr_ack_all(priv); - if (received < budget) { - napi_complete_done(napi, received); - mtk_star_intr_enable_rx(priv); + if (status & MTK_STAR_BIT_INT_STS_TNTC) + /* Clean-up all TX descriptors. */ + mtk_star_tx_complete_all(priv); + + if (status & MTK_STAR_BIT_INT_STS_FNRC) + /* Receive up to $budget packets. */ + received = mtk_star_process_rx(priv, budget); + + if (unlikely(status & MTK_STAR_REG_INT_STS_MIB_CNT_TH)) { + mtk_star_update_stats(priv); + mtk_star_reset_counters(priv); } + if (received < budget) + napi_complete_done(napi, received); + + mtk_star_intr_enable(priv); + return received; } @@ -1532,7 +1473,6 @@ static int mtk_star_probe(struct platform_device *pdev) ndev->max_mtu = MTK_STAR_MAX_FRAME_SIZE; spin_lock_init(&priv->lock); - INIT_WORK(&priv->stats_work, mtk_star_update_stats_work); base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(base)) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 5ffa32b75e5f..55af877763ed 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -978,8 +978,10 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu, lossy = !(pfc || pause_en); thres_cells = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu); + mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &thres_cells); delay_cells = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, pfc, pause_en); + mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &delay_cells); total_cells = thres_cells + delay_cells; taken_headroom_cells += total_cells; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 6f96ca50c9ba..6e87457dd635 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -374,6 +374,19 @@ mlxsw_sp_port_vlan_find_by_vid(const struct mlxsw_sp_port *mlxsw_sp_port, return NULL; } +static inline void +mlxsw_sp_port_headroom_8x_adjust(const struct mlxsw_sp_port *mlxsw_sp_port, + u16 *p_size) +{ + /* Ports with eight lanes use two headroom buffers between which the + * configured headroom size is split. Therefore, multiply the calculated + * headroom size by two. + */ + if (mlxsw_sp_port->mapping.width != 8) + return; + *p_size *= 2; +} + enum mlxsw_sp_flood_type { MLXSW_SP_FLOOD_TYPE_UC, MLXSW_SP_FLOOD_TYPE_BC, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 21bfb2f6a6f0..f25a8b084b4b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -312,6 +312,7 @@ static int mlxsw_sp_port_pb_init(struct mlxsw_sp_port *mlxsw_sp_port) if (i == MLXSW_SP_PB_UNUSED) continue; + mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &size); mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, i, size); } mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index 304eb8c3d8bd..f843545d3478 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -782,6 +782,7 @@ mlxsw_sp_span_port_buffer_update(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu) speed = 0; buffsize = mlxsw_sp_span_buffsize_get(mlxsw_sp, speed, mtu); + mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, (u16 *) &buffsize); mlxsw_reg_sbib_pack(sbib_pl, mlxsw_sp_port->local_port, buffsize); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); } diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index c5c5c688b7e2..f1711ac86d0c 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -3091,6 +3091,8 @@ static const struct pci_device_id lan743x_pcidev_tbl[] = { { 0, } }; +MODULE_DEVICE_TABLE(pci, lan743x_pcidev_tbl); + static struct pci_driver lan743x_pcidev_driver = { .name = DRIVER_NAME, .id_table = lan743x_pcidev_tbl, diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c index 8d7b9bb910f2..10037639ac2c 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c @@ -269,7 +269,7 @@ static ssize_t qlcnic_sysfs_read_crb(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); int ret; @@ -286,7 +286,7 @@ static ssize_t qlcnic_sysfs_write_crb(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); int ret; @@ -315,7 +315,7 @@ static ssize_t qlcnic_sysfs_read_mem(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); u64 data; int ret; @@ -337,7 +337,7 @@ static ssize_t qlcnic_sysfs_write_mem(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); u64 data; int ret; @@ -402,7 +402,7 @@ static ssize_t qlcnic_sysfs_write_pm_config(struct file *filp, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); struct qlcnic_pm_func_cfg *pm_cfg; u32 id, action, pci_func; @@ -452,7 +452,7 @@ static ssize_t qlcnic_sysfs_read_pm_config(struct file *filp, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); struct qlcnic_pm_func_cfg *pm_cfg; u8 pci_func; @@ -545,7 +545,7 @@ static ssize_t qlcnic_sysfs_write_esw_config(struct file *file, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); struct qlcnic_esw_func_cfg *esw_cfg; struct qlcnic_npar_info *npar; @@ -629,7 +629,7 @@ static ssize_t qlcnic_sysfs_read_esw_config(struct file *file, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); struct qlcnic_esw_func_cfg *esw_cfg; u8 pci_func; @@ -681,7 +681,7 @@ static ssize_t qlcnic_sysfs_write_npar_config(struct file *file, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); struct qlcnic_info nic_info; struct qlcnic_npar_func_cfg *np_cfg; @@ -728,7 +728,7 @@ static ssize_t qlcnic_sysfs_read_npar_config(struct file *file, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); struct qlcnic_npar_func_cfg *np_cfg; struct qlcnic_info nic_info; @@ -775,7 +775,7 @@ static ssize_t qlcnic_sysfs_get_port_stats(struct file *file, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); struct qlcnic_esw_statistics port_stats; int ret; @@ -810,7 +810,7 @@ static ssize_t qlcnic_sysfs_get_esw_stats(struct file *file, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); struct qlcnic_esw_statistics esw_stats; int ret; @@ -845,7 +845,7 @@ static ssize_t qlcnic_sysfs_clear_esw_stats(struct file *file, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); int ret; @@ -875,7 +875,7 @@ static ssize_t qlcnic_sysfs_clear_port_stats(struct file *file, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); int ret; @@ -904,7 +904,7 @@ static ssize_t qlcnic_sysfs_read_pci_config(struct file *file, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); struct qlcnic_pci_func_cfg *pci_cfg; struct qlcnic_pci_info *pci_info; @@ -946,7 +946,7 @@ static ssize_t qlcnic_83xx_sysfs_flash_read_handler(struct file *filp, { unsigned char *p_read_buf; int ret, count; - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); if (!size) @@ -1124,7 +1124,7 @@ static ssize_t qlcnic_83xx_sysfs_flash_write_handler(struct file *filp, int ret; static int flash_mode; unsigned long data; - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); ret = kstrtoul(buf, 16, &data); diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 7585cd2270ba..fc99e7118e49 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -647,10 +647,10 @@ static int rocker_dma_rings_init(struct rocker *rocker) err_dma_event_ring_bufs_alloc: rocker_dma_ring_destroy(rocker, &rocker->event_ring); err_dma_event_ring_create: + rocker_dma_cmd_ring_waits_free(rocker); +err_dma_cmd_ring_waits_alloc: rocker_dma_ring_bufs_free(rocker, &rocker->cmd_ring, PCI_DMA_BIDIRECTIONAL); -err_dma_cmd_ring_waits_alloc: - rocker_dma_cmd_ring_waits_free(rocker); err_dma_cmd_ring_bufs_alloc: rocker_dma_ring_destroy(rocker, &rocker->cmd_ring); return err; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index fbaf3c987d9c..f34c7903ff52 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -186,7 +186,7 @@ #define XAE_RAF_TXVSTRPMODE_MASK 0x00000180 /* Tx VLAN STRIP mode */ #define XAE_RAF_RXVSTRPMODE_MASK 0x00000600 /* Rx VLAN STRIP mode */ #define XAE_RAF_NEWFNCENBL_MASK 0x00000800 /* New function mode */ -/* Exteneded Multicast Filtering mode */ +/* Extended Multicast Filtering mode */ #define XAE_RAF_EMULTIFLTRENBL_MASK 0x00001000 #define XAE_RAF_STATSRST_MASK 0x00002000 /* Stats. Counter Reset */ #define XAE_RAF_RXBADFRMEN_MASK 0x00004000 /* Recv Bad Frame Enable */ diff --git a/drivers/oprofile/cpu_buffer.h b/drivers/oprofile/cpu_buffer.h index e1d097e250ae..31478c0cff87 100644 --- a/drivers/oprofile/cpu_buffer.h +++ b/drivers/oprofile/cpu_buffer.h @@ -33,7 +33,7 @@ void flush_cpu_work(void); struct op_sample { unsigned long eip; unsigned long event; - unsigned long data[0]; + unsigned long data[]; }; struct op_entry; diff --git a/drivers/phy/samsung/phy-samsung-usb2.h b/drivers/phy/samsung/phy-samsung-usb2.h index 2c1a7d71142b..77fb23bc218f 100644 --- a/drivers/phy/samsung/phy-samsung-usb2.h +++ b/drivers/phy/samsung/phy-samsung-usb2.h @@ -43,7 +43,7 @@ struct samsung_usb2_phy_driver { struct regmap *reg_pmu; struct regmap *reg_sys; spinlock_t lock; - struct samsung_usb2_phy_instance instances[0]; + struct samsung_usb2_phy_instance instances[]; }; struct samsung_usb2_common_phy { diff --git a/drivers/rapidio/rio-scan.c b/drivers/rapidio/rio-scan.c index 0e90c5d4bb2b..eb8ed28533f8 100644 --- a/drivers/rapidio/rio-scan.c +++ b/drivers/rapidio/rio-scan.c @@ -39,7 +39,7 @@ struct rio_id_table { u16 start; /* logical minimal id */ u32 max; /* max number of IDs in table */ spinlock_t lock; - unsigned long table[0]; + unsigned long table[]; }; static int next_destid = 0; diff --git a/drivers/soc/ti/knav_qmss.h b/drivers/soc/ti/knav_qmss.h index 038aec352df7..a01eda720bf6 100644 --- a/drivers/soc/ti/knav_qmss.h +++ b/drivers/soc/ti/knav_qmss.h @@ -67,7 +67,7 @@ struct knav_reg_config { u32 link_ram_size0; u32 link_ram_base1; u32 __pad2[2]; - u32 starvation[0]; + u32 starvation[]; }; struct knav_reg_region { diff --git a/drivers/video/fbdev/hpfb.c b/drivers/video/fbdev/hpfb.c index f02be0db335e..8d418abdd767 100644 --- a/drivers/video/fbdev/hpfb.c +++ b/drivers/video/fbdev/hpfb.c @@ -402,7 +402,7 @@ int __init hpfb_init(void) if (err) return err; - err = probe_kernel_read(&i, (unsigned char *)INTFBVADDR + DIO_IDOFF, 1); + err = copy_from_kernel_nofault(&i, (unsigned char *)INTFBVADDR + DIO_IDOFF, 1); if (!err && (i == DIO_ID_FBUFFER) && topcat_sid_ok(sid = DIO_SECID(INTFBVADDR))) { if (!request_mem_region(INTFBPADDR, DIO_DEVSIZE, "Internal Topcat")) diff --git a/drivers/w1/w1_netlink.h b/drivers/w1/w1_netlink.h index 3041092e84b3..449680a61569 100644 --- a/drivers/w1/w1_netlink.h +++ b/drivers/w1/w1_netlink.h @@ -73,7 +73,7 @@ struct w1_netlink_msg __u32 res; } mst; } id; - __u8 data[0]; + __u8 data[]; }; /** @@ -122,7 +122,7 @@ struct w1_netlink_cmd __u8 cmd; __u8 res; __u16 len; - __u8 data[0]; + __u8 data[]; }; #ifdef __KERNEL__ diff --git a/fs/afs/dir.c b/fs/afs/dir.c index aa1d34141ea3..3e3c2bf0a722 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -648,7 +648,7 @@ static void afs_do_lookup_success(struct afs_operation *op) vp = &op->file[0]; abort_code = vp->scb.status.abort_code; if (abort_code != 0) { - op->abort_code = abort_code; + op->ac.abort_code = abort_code; op->error = afs_abort_to_error(abort_code); } break; @@ -696,10 +696,11 @@ static const struct afs_operation_ops afs_inline_bulk_status_operation = { .success = afs_do_lookup_success, }; -static const struct afs_operation_ops afs_fetch_status_operation = { +static const struct afs_operation_ops afs_lookup_fetch_status_operation = { .issue_afs_rpc = afs_fs_fetch_status, .issue_yfs_rpc = yfs_fs_fetch_status, .success = afs_do_lookup_success, + .aborted = afs_check_for_remote_deletion, }; /* @@ -1236,6 +1237,17 @@ void afs_d_release(struct dentry *dentry) _enter("%pd", dentry); } +void afs_check_for_remote_deletion(struct afs_operation *op) +{ + struct afs_vnode *vnode = op->file[0].vnode; + + switch (op->ac.abort_code) { + case VNOVNODE: + set_bit(AFS_VNODE_DELETED, &vnode->flags); + afs_break_callback(vnode, afs_cb_break_for_deleted); + } +} + /* * Create a new inode for create/mkdir/symlink */ @@ -1268,7 +1280,7 @@ static void afs_vnode_new_inode(struct afs_operation *op) static void afs_create_success(struct afs_operation *op) { _enter("op=%08x", op->debug_id); - afs_check_for_remote_deletion(op, op->file[0].vnode); + op->ctime = op->file[0].scb.status.mtime_client; afs_vnode_commit_status(op, &op->file[0]); afs_update_dentry_version(op, &op->file[0], op->dentry); afs_vnode_new_inode(op); @@ -1302,6 +1314,7 @@ static const struct afs_operation_ops afs_mkdir_operation = { .issue_afs_rpc = afs_fs_make_dir, .issue_yfs_rpc = yfs_fs_make_dir, .success = afs_create_success, + .aborted = afs_check_for_remote_deletion, .edit_dir = afs_create_edit_dir, .put = afs_create_put, }; @@ -1325,6 +1338,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) afs_op_set_vnode(op, 0, dvnode); op->file[0].dv_delta = 1; + op->file[0].update_ctime = true; op->dentry = dentry; op->create.mode = S_IFDIR | mode; op->create.reason = afs_edit_dir_for_mkdir; @@ -1350,7 +1364,7 @@ static void afs_dir_remove_subdir(struct dentry *dentry) static void afs_rmdir_success(struct afs_operation *op) { _enter("op=%08x", op->debug_id); - afs_check_for_remote_deletion(op, op->file[0].vnode); + op->ctime = op->file[0].scb.status.mtime_client; afs_vnode_commit_status(op, &op->file[0]); afs_update_dentry_version(op, &op->file[0], op->dentry); } @@ -1382,6 +1396,7 @@ static const struct afs_operation_ops afs_rmdir_operation = { .issue_afs_rpc = afs_fs_remove_dir, .issue_yfs_rpc = yfs_fs_remove_dir, .success = afs_rmdir_success, + .aborted = afs_check_for_remote_deletion, .edit_dir = afs_rmdir_edit_dir, .put = afs_rmdir_put, }; @@ -1404,6 +1419,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) afs_op_set_vnode(op, 0, dvnode); op->file[0].dv_delta = 1; + op->file[0].update_ctime = true; op->dentry = dentry; op->ops = &afs_rmdir_operation; @@ -1479,7 +1495,8 @@ static void afs_dir_remove_link(struct afs_operation *op) static void afs_unlink_success(struct afs_operation *op) { _enter("op=%08x", op->debug_id); - afs_check_for_remote_deletion(op, op->file[0].vnode); + op->ctime = op->file[0].scb.status.mtime_client; + afs_check_dir_conflict(op, &op->file[0]); afs_vnode_commit_status(op, &op->file[0]); afs_vnode_commit_status(op, &op->file[1]); afs_update_dentry_version(op, &op->file[0], op->dentry); @@ -1511,6 +1528,7 @@ static const struct afs_operation_ops afs_unlink_operation = { .issue_afs_rpc = afs_fs_remove_file, .issue_yfs_rpc = yfs_fs_remove_file, .success = afs_unlink_success, + .aborted = afs_check_for_remote_deletion, .edit_dir = afs_unlink_edit_dir, .put = afs_unlink_put, }; @@ -1537,6 +1555,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) afs_op_set_vnode(op, 0, dvnode); op->file[0].dv_delta = 1; + op->file[0].update_ctime = true; /* Try to make sure we have a callback promise on the victim. */ ret = afs_validate(vnode, op->key); @@ -1561,9 +1580,25 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) spin_unlock(&dentry->d_lock); op->file[1].vnode = vnode; + op->file[1].update_ctime = true; + op->file[1].op_unlinked = true; op->dentry = dentry; op->ops = &afs_unlink_operation; - return afs_do_sync_operation(op); + afs_begin_vnode_operation(op); + afs_wait_for_operation(op); + + /* If there was a conflict with a third party, check the status of the + * unlinked vnode. + */ + if (op->error == 0 && (op->flags & AFS_OPERATION_DIR_CONFLICT)) { + op->file[1].update_ctime = false; + op->fetch_status.which = 1; + op->ops = &afs_fetch_status_operation; + afs_begin_vnode_operation(op); + afs_wait_for_operation(op); + } + + return afs_put_operation(op); error: return afs_put_operation(op); @@ -1573,6 +1608,7 @@ static const struct afs_operation_ops afs_create_operation = { .issue_afs_rpc = afs_fs_create_file, .issue_yfs_rpc = yfs_fs_create_file, .success = afs_create_success, + .aborted = afs_check_for_remote_deletion, .edit_dir = afs_create_edit_dir, .put = afs_create_put, }; @@ -1601,6 +1637,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, afs_op_set_vnode(op, 0, dvnode); op->file[0].dv_delta = 1; + op->file[0].update_ctime = true; op->dentry = dentry; op->create.mode = S_IFREG | mode; @@ -1620,6 +1657,7 @@ static void afs_link_success(struct afs_operation *op) struct afs_vnode_param *vp = &op->file[1]; _enter("op=%08x", op->debug_id); + op->ctime = dvp->scb.status.mtime_client; afs_vnode_commit_status(op, dvp); afs_vnode_commit_status(op, vp); afs_update_dentry_version(op, dvp, op->dentry); @@ -1640,6 +1678,7 @@ static const struct afs_operation_ops afs_link_operation = { .issue_afs_rpc = afs_fs_link, .issue_yfs_rpc = yfs_fs_link, .success = afs_link_success, + .aborted = afs_check_for_remote_deletion, .edit_dir = afs_create_edit_dir, .put = afs_link_put, }; @@ -1672,6 +1711,8 @@ static int afs_link(struct dentry *from, struct inode *dir, afs_op_set_vnode(op, 0, dvnode); afs_op_set_vnode(op, 1, vnode); op->file[0].dv_delta = 1; + op->file[0].update_ctime = true; + op->file[1].update_ctime = true; op->dentry = dentry; op->dentry_2 = from; @@ -1689,6 +1730,7 @@ static const struct afs_operation_ops afs_symlink_operation = { .issue_afs_rpc = afs_fs_symlink, .issue_yfs_rpc = yfs_fs_symlink, .success = afs_create_success, + .aborted = afs_check_for_remote_deletion, .edit_dir = afs_create_edit_dir, .put = afs_create_put, }; @@ -1740,9 +1782,13 @@ static void afs_rename_success(struct afs_operation *op) { _enter("op=%08x", op->debug_id); + op->ctime = op->file[0].scb.status.mtime_client; + afs_check_dir_conflict(op, &op->file[1]); afs_vnode_commit_status(op, &op->file[0]); - if (op->file[1].vnode != op->file[0].vnode) + if (op->file[1].vnode != op->file[0].vnode) { + op->ctime = op->file[1].scb.status.mtime_client; afs_vnode_commit_status(op, &op->file[1]); + } } static void afs_rename_edit_dir(struct afs_operation *op) @@ -1860,6 +1906,8 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, afs_op_set_vnode(op, 1, new_dvnode); /* May be same as orig_dvnode */ op->file[0].dv_delta = 1; op->file[1].dv_delta = 1; + op->file[0].update_ctime = true; + op->file[1].update_ctime = true; op->dentry = old_dentry; op->dentry_2 = new_dentry; diff --git a/fs/afs/dir_silly.c b/fs/afs/dir_silly.c index b14e3d9a25e2..04f75a44f243 100644 --- a/fs/afs/dir_silly.c +++ b/fs/afs/dir_silly.c @@ -16,6 +16,7 @@ static void afs_silly_rename_success(struct afs_operation *op) { _enter("op=%08x", op->debug_id); + afs_check_dir_conflict(op, &op->file[0]); afs_vnode_commit_status(op, &op->file[0]); } @@ -69,6 +70,11 @@ static int afs_do_silly_rename(struct afs_vnode *dvnode, struct afs_vnode *vnode return PTR_ERR(op); afs_op_set_vnode(op, 0, dvnode); + afs_op_set_vnode(op, 1, dvnode); + op->file[0].dv_delta = 1; + op->file[1].dv_delta = 1; + op->file[0].update_ctime = true; + op->file[1].update_ctime = true; op->dentry = old; op->dentry_2 = new; @@ -129,6 +135,7 @@ int afs_sillyrename(struct afs_vnode *dvnode, struct afs_vnode *vnode, switch (ret) { case 0: /* The rename succeeded. */ + set_bit(AFS_VNODE_SILLY_DELETED, &vnode->flags); d_move(dentry, sdentry); break; case -ERESTARTSYS: @@ -148,19 +155,11 @@ out: static void afs_silly_unlink_success(struct afs_operation *op) { - struct afs_vnode *vnode = op->file[1].vnode; - _enter("op=%08x", op->debug_id); - afs_check_for_remote_deletion(op, op->file[0].vnode); + afs_check_dir_conflict(op, &op->file[0]); afs_vnode_commit_status(op, &op->file[0]); afs_vnode_commit_status(op, &op->file[1]); afs_update_dentry_version(op, &op->file[0], op->dentry); - - drop_nlink(&vnode->vfs_inode); - if (vnode->vfs_inode.i_nlink == 0) { - set_bit(AFS_VNODE_DELETED, &vnode->flags); - clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); - } } static void afs_silly_unlink_edit_dir(struct afs_operation *op) @@ -181,6 +180,7 @@ static const struct afs_operation_ops afs_silly_unlink_operation = { .issue_afs_rpc = afs_fs_remove_file, .issue_yfs_rpc = yfs_fs_remove_file, .success = afs_silly_unlink_success, + .aborted = afs_check_for_remote_deletion, .edit_dir = afs_silly_unlink_edit_dir, }; @@ -200,12 +200,30 @@ static int afs_do_silly_unlink(struct afs_vnode *dvnode, struct afs_vnode *vnode afs_op_set_vnode(op, 0, dvnode); afs_op_set_vnode(op, 1, vnode); + op->file[0].dv_delta = 1; + op->file[0].update_ctime = true; + op->file[1].op_unlinked = true; + op->file[1].update_ctime = true; op->dentry = dentry; op->ops = &afs_silly_unlink_operation; trace_afs_silly_rename(vnode, true); - return afs_do_sync_operation(op); + afs_begin_vnode_operation(op); + afs_wait_for_operation(op); + + /* If there was a conflict with a third party, check the status of the + * unlinked vnode. + */ + if (op->error == 0 && (op->flags & AFS_OPERATION_DIR_CONFLICT)) { + op->file[1].update_ctime = false; + op->fetch_status.which = 1; + op->ops = &afs_fetch_status_operation; + afs_begin_vnode_operation(op); + afs_wait_for_operation(op); + } + + return afs_put_operation(op); } /* diff --git a/fs/afs/file.c b/fs/afs/file.c index 506c47471b42..6f6ed1605cfe 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -225,7 +225,6 @@ static void afs_fetch_data_success(struct afs_operation *op) struct afs_vnode *vnode = op->file[0].vnode; _enter("op=%08x", op->debug_id); - afs_check_for_remote_deletion(op, vnode); afs_vnode_commit_status(op, &op->file[0]); afs_stat_v(vnode, n_fetches); atomic_long_add(op->fetch.req->actual_len, &op->net->n_fetch_bytes); @@ -240,6 +239,7 @@ static const struct afs_operation_ops afs_fetch_data_operation = { .issue_afs_rpc = afs_fs_fetch_data, .issue_yfs_rpc = yfs_fs_fetch_data, .success = afs_fetch_data_success, + .aborted = afs_check_for_remote_deletion, .put = afs_fetch_data_put, }; diff --git a/fs/afs/flock.c b/fs/afs/flock.c index 71eea2a908c7..ffb8575345ca 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -175,10 +175,7 @@ static void afs_kill_lockers_enoent(struct afs_vnode *vnode) static void afs_lock_success(struct afs_operation *op) { - struct afs_vnode *vnode = op->file[0].vnode; - _enter("op=%08x", op->debug_id); - afs_check_for_remote_deletion(op, vnode); afs_vnode_commit_status(op, &op->file[0]); } @@ -186,6 +183,7 @@ static const struct afs_operation_ops afs_set_lock_operation = { .issue_afs_rpc = afs_fs_set_lock, .issue_yfs_rpc = yfs_fs_set_lock, .success = afs_lock_success, + .aborted = afs_check_for_remote_deletion, }; /* diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c index 2d2dff5688a4..c264839b2fd0 100644 --- a/fs/afs/fs_operation.c +++ b/fs/afs/fs_operation.c @@ -187,9 +187,17 @@ void afs_wait_for_operation(struct afs_operation *op) op->error = afs_wait_for_call_to_complete(op->call, &op->ac); } - if (op->error == 0) { + switch (op->error) { + case 0: _debug("success"); op->ops->success(op); + break; + case -ECONNABORTED: + if (op->ops->aborted) + op->ops->aborted(op); + break; + default: + break; } afs_end_vnode_operation(op); diff --git a/fs/afs/inode.c b/fs/afs/inode.c index cd0a0060950b..1d13d2e882ad 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -165,9 +165,11 @@ static void afs_apply_status(struct afs_operation *op, { struct afs_file_status *status = &vp->scb.status; struct afs_vnode *vnode = vp->vnode; + struct inode *inode = &vnode->vfs_inode; struct timespec64 t; umode_t mode; bool data_changed = false; + bool change_size = vp->set_size; _enter("{%llx:%llu.%u} %s", vp->fid.vid, vp->fid.vnode, vp->fid.unique, @@ -186,25 +188,25 @@ static void afs_apply_status(struct afs_operation *op, } if (status->nlink != vnode->status.nlink) - set_nlink(&vnode->vfs_inode, status->nlink); + set_nlink(inode, status->nlink); if (status->owner != vnode->status.owner) - vnode->vfs_inode.i_uid = make_kuid(&init_user_ns, status->owner); + inode->i_uid = make_kuid(&init_user_ns, status->owner); if (status->group != vnode->status.group) - vnode->vfs_inode.i_gid = make_kgid(&init_user_ns, status->group); + inode->i_gid = make_kgid(&init_user_ns, status->group); if (status->mode != vnode->status.mode) { - mode = vnode->vfs_inode.i_mode; + mode = inode->i_mode; mode &= ~S_IALLUGO; mode |= status->mode; - WRITE_ONCE(vnode->vfs_inode.i_mode, mode); + WRITE_ONCE(inode->i_mode, mode); } t = status->mtime_client; - vnode->vfs_inode.i_ctime = t; - vnode->vfs_inode.i_mtime = t; - vnode->vfs_inode.i_atime = t; + inode->i_mtime = t; + if (vp->update_ctime) + inode->i_ctime = op->ctime; if (vnode->status.data_version != status->data_version) data_changed = true; @@ -226,6 +228,7 @@ static void afs_apply_status(struct afs_operation *op, } else { set_bit(AFS_VNODE_ZAP_DATA, &vnode->flags); } + change_size = true; } else if (vnode->status.type == AFS_FTYPE_DIR) { /* Expected directory change is handled elsewhere so * that we can locally edit the directory and save on a @@ -233,11 +236,22 @@ static void afs_apply_status(struct afs_operation *op, */ if (test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) data_changed = false; + change_size = true; } if (data_changed) { - inode_set_iversion_raw(&vnode->vfs_inode, status->data_version); - afs_set_i_size(vnode, status->size); + inode_set_iversion_raw(inode, status->data_version); + + /* Only update the size if the data version jumped. If the + * file is being modified locally, then we might have our own + * idea of what the size should be that's not the same as + * what's on the server. + */ + if (change_size) { + afs_set_i_size(vnode, status->size); + inode->i_ctime = t; + inode->i_atime = t; + } } } @@ -267,32 +281,39 @@ void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *v _enter(""); - ASSERTCMP(op->error, ==, 0); - write_seqlock(&vnode->cb_lock); if (vp->scb.have_error) { + /* A YFS server will return this from RemoveFile2 and AFS and + * YFS will return this from InlineBulkStatus. + */ if (vp->scb.status.abort_code == VNOVNODE) { set_bit(AFS_VNODE_DELETED, &vnode->flags); clear_nlink(&vnode->vfs_inode); __afs_break_callback(vnode, afs_cb_break_for_deleted); + op->flags &= ~AFS_OPERATION_DIR_CONFLICT; } - } else { - if (vp->scb.have_status) - afs_apply_status(op, vp); + } else if (vp->scb.have_status) { + afs_apply_status(op, vp); if (vp->scb.have_cb) afs_apply_callback(op, vp); + } else if (vp->op_unlinked && !(op->flags & AFS_OPERATION_DIR_CONFLICT)) { + drop_nlink(&vnode->vfs_inode); + if (vnode->vfs_inode.i_nlink == 0) { + set_bit(AFS_VNODE_DELETED, &vnode->flags); + __afs_break_callback(vnode, afs_cb_break_for_deleted); + } } write_sequnlock(&vnode->cb_lock); - if (op->error == 0 && vp->scb.have_status) + if (vp->scb.have_status) afs_cache_permit(vnode, op->key, vp->cb_break_before, &vp->scb); } static void afs_fetch_status_success(struct afs_operation *op) { - struct afs_vnode_param *vp = &op->file[0]; + struct afs_vnode_param *vp = &op->file[op->fetch_status.which]; struct afs_vnode *vnode = vp->vnode; int ret; @@ -306,10 +327,11 @@ static void afs_fetch_status_success(struct afs_operation *op) } } -static const struct afs_operation_ops afs_fetch_status_operation = { +const struct afs_operation_ops afs_fetch_status_operation = { .issue_afs_rpc = afs_fs_fetch_status, .issue_yfs_rpc = yfs_fs_fetch_status, .success = afs_fetch_status_success, + .aborted = afs_check_for_remote_deletion, }; /* @@ -716,6 +738,9 @@ int afs_getattr(const struct path *path, struct kstat *stat, do { read_seqbegin_or_lock(&vnode->cb_lock, &seq); generic_fillattr(inode, stat); + if (test_bit(AFS_VNODE_SILLY_DELETED, &vnode->flags) && + stat->nlink > 0) + stat->nlink -= 1; } while (need_seqretry(&vnode->cb_lock, seq)); done_seqretry(&vnode->cb_lock, seq); @@ -785,7 +810,15 @@ void afs_evict_inode(struct inode *inode) static void afs_setattr_success(struct afs_operation *op) { + struct inode *inode = &op->file[0].vnode->vfs_inode; + afs_vnode_commit_status(op, &op->file[0]); + if (op->setattr.attr->ia_valid & ATTR_SIZE) { + loff_t i_size = inode->i_size, size = op->setattr.attr->ia_size; + if (size > i_size) + pagecache_isize_extended(inode, i_size, size); + truncate_pagecache(inode, size); + } } static const struct afs_operation_ops afs_setattr_operation = { @@ -801,17 +834,31 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr) { struct afs_operation *op; struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry)); + int ret; _enter("{%llx:%llu},{n=%pd},%x", vnode->fid.vid, vnode->fid.vnode, dentry, attr->ia_valid); if (!(attr->ia_valid & (ATTR_SIZE | ATTR_MODE | ATTR_UID | ATTR_GID | - ATTR_MTIME))) { + ATTR_MTIME | ATTR_MTIME_SET | ATTR_TIMES_SET | + ATTR_TOUCH))) { _leave(" = 0 [unsupported]"); return 0; } + if (attr->ia_valid & ATTR_SIZE) { + if (!S_ISREG(vnode->vfs_inode.i_mode)) + return -EISDIR; + + ret = inode_newsize_ok(&vnode->vfs_inode, attr->ia_size); + if (ret) + return ret; + + if (attr->ia_size == i_size_read(&vnode->vfs_inode)) + attr->ia_valid &= ~ATTR_SIZE; + } + /* flush any dirty data outstanding on a regular file */ if (S_ISREG(vnode->vfs_inode.i_mode)) filemap_write_and_wait(vnode->vfs_inode.i_mapping); @@ -825,8 +872,12 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr) afs_op_set_vnode(op, 0, vnode); op->setattr.attr = attr; - if (attr->ia_valid & ATTR_SIZE) + if (attr->ia_valid & ATTR_SIZE) { op->file[0].dv_delta = 1; + op->file[0].set_size = true; + } + op->ctime = attr->ia_ctime; + op->file[0].update_ctime = 1; op->ops = &afs_setattr_operation; return afs_do_sync_operation(op); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 0c9806ef2a19..573a5922c3bb 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -634,6 +634,7 @@ struct afs_vnode { #define AFS_VNODE_AUTOCELL 6 /* set if Vnode is an auto mount point */ #define AFS_VNODE_PSEUDODIR 7 /* set if Vnode is a pseudo directory */ #define AFS_VNODE_NEW_CONTENT 8 /* Set if file has new content (create/trunc-0) */ +#define AFS_VNODE_SILLY_DELETED 9 /* Set if file has been silly-deleted */ struct list_head wb_keys; /* List of keys available for writeback */ struct list_head pending_locks; /* locks waiting to be granted */ @@ -744,8 +745,11 @@ struct afs_vnode_param { afs_dataversion_t dv_before; /* Data version before the call */ unsigned int cb_break_before; /* cb_break + cb_s_break before the call */ u8 dv_delta; /* Expected change in data version */ - bool put_vnode; /* T if we have a ref on the vnode */ - bool need_io_lock; /* T if we need the I/O lock on this */ + bool put_vnode:1; /* T if we have a ref on the vnode */ + bool need_io_lock:1; /* T if we need the I/O lock on this */ + bool update_ctime:1; /* Need to update the ctime */ + bool set_size:1; /* Must update i_size */ + bool op_unlinked:1; /* True if file was unlinked by op */ }; /* @@ -766,9 +770,9 @@ struct afs_operation { struct dentry *dentry; /* Dentry to be altered */ struct dentry *dentry_2; /* Second dentry to be altered */ struct timespec64 mtime; /* Modification time to record */ + struct timespec64 ctime; /* Change time to set */ short nr_files; /* Number of entries in file[], more_files */ short error; - unsigned int abort_code; unsigned int debug_id; unsigned int cb_v_break; /* Volume break counter before op */ @@ -837,6 +841,7 @@ struct afs_operation { #define AFS_OPERATION_LOCK_1 0x0200 /* Set if have io_lock on file[1] */ #define AFS_OPERATION_TRIED_ALL 0x0400 /* Set if we've tried all the fileservers */ #define AFS_OPERATION_RETRY_SERVER 0x0800 /* Set if we should retry the current server */ +#define AFS_OPERATION_DIR_CONFLICT 0x1000 /* Set if we detected a 3rd-party dir change */ }; /* @@ -932,6 +937,7 @@ extern const struct address_space_operations afs_dir_aops; extern const struct dentry_operations afs_fs_dentry_operations; extern void afs_d_release(struct dentry *); +extern void afs_check_for_remote_deletion(struct afs_operation *); /* * dir_edit.c @@ -1063,6 +1069,8 @@ extern int afs_wait_for_one_fs_probe(struct afs_server *, bool); /* * inode.c */ +extern const struct afs_operation_ops afs_fetch_status_operation; + extern void afs_vnode_commit_status(struct afs_operation *, struct afs_vnode_param *); extern int afs_fetch_status(struct afs_vnode *, struct key *, bool, afs_access_t *); extern int afs_ilookup5_test_by_fid(struct inode *, void *); @@ -1435,7 +1443,6 @@ extern ssize_t afs_listxattr(struct dentry *, char *, size_t); /* * yfsclient.c */ -extern void yfs_fs_fetch_file_status(struct afs_operation *); extern void yfs_fs_fetch_data(struct afs_operation *); extern void yfs_fs_create_file(struct afs_operation *); extern void yfs_fs_make_dir(struct afs_operation *); @@ -1481,15 +1488,6 @@ static inline struct inode *AFS_VNODE_TO_I(struct afs_vnode *vnode) return &vnode->vfs_inode; } -static inline void afs_check_for_remote_deletion(struct afs_operation *op, - struct afs_vnode *vnode) -{ - if (op->error == -ENOENT) { - set_bit(AFS_VNODE_DELETED, &vnode->flags); - afs_break_callback(vnode, afs_cb_break_for_deleted); - } -} - /* * Note that a dentry got changed. We need to set d_fsdata to the data version * number derived from the result of the operation. It doesn't matter if @@ -1504,6 +1502,18 @@ static inline void afs_update_dentry_version(struct afs_operation *op, (void *)(unsigned long)dir_vp->scb.status.data_version; } +/* + * Check for a conflicting operation on a directory that we just unlinked from. + * If someone managed to sneak a link or an unlink in on the file we just + * unlinked, we won't be able to trust nlink on an AFS file (but not YFS). + */ +static inline void afs_check_dir_conflict(struct afs_operation *op, + struct afs_vnode_param *dvp) +{ + if (dvp->dv_before + dvp->dv_delta != dvp->scb.status.data_version) + op->flags |= AFS_OPERATION_DIR_CONFLICT; +} + static inline int afs_io_error(struct afs_call *call, enum afs_io_error where) { trace_afs_io_error(call->debug_id, -EIO, where); diff --git a/fs/afs/misc.c b/fs/afs/misc.c index 52b19e9c1535..5334f1bd2bca 100644 --- a/fs/afs/misc.c +++ b/fs/afs/misc.c @@ -83,6 +83,7 @@ int afs_abort_to_error(u32 abort_code) case UAENOLCK: return -ENOLCK; case UAENOTEMPTY: return -ENOTEMPTY; case UAELOOP: return -ELOOP; + case UAEOVERFLOW: return -EOVERFLOW; case UAENOMEDIUM: return -ENOMEDIUM; case UAEDQUOT: return -EDQUOT; diff --git a/fs/afs/write.c b/fs/afs/write.c index 768497f82aee..7437806332d9 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -194,11 +194,11 @@ int afs_write_end(struct file *file, struct address_space *mapping, i_size = i_size_read(&vnode->vfs_inode); if (maybe_i_size > i_size) { - spin_lock(&vnode->wb_lock); + write_seqlock(&vnode->cb_lock); i_size = i_size_read(&vnode->vfs_inode); if (maybe_i_size > i_size) i_size_write(&vnode->vfs_inode, maybe_i_size); - spin_unlock(&vnode->wb_lock); + write_sequnlock(&vnode->cb_lock); } if (!PageUptodate(page)) { @@ -393,6 +393,7 @@ static void afs_store_data_success(struct afs_operation *op) { struct afs_vnode *vnode = op->file[0].vnode; + op->ctime = op->file[0].scb.status.mtime_client; afs_vnode_commit_status(op, &op->file[0]); if (op->error == 0) { afs_pages_written_back(vnode, op->store.first, op->store.last); @@ -491,6 +492,7 @@ static int afs_write_back_from_locked_page(struct address_space *mapping, unsigned long count, priv; unsigned n, offset, to, f, t; pgoff_t start, first, last; + loff_t i_size, end; int loop, ret; _enter(",%lx", primary_page->index); @@ -591,7 +593,12 @@ no_more: first = primary_page->index; last = first + count - 1; + end = (loff_t)last * PAGE_SIZE + to; + i_size = i_size_read(&vnode->vfs_inode); + _debug("write back %lx[%u..] to %lx[..%u]", first, offset, last, to); + if (end > i_size) + to = i_size & ~PAGE_MASK; ret = afs_store_data(mapping, first, last, offset, to); switch (ret) { @@ -844,6 +851,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) vmf->page->index, priv); SetPagePrivate(vmf->page); set_page_private(vmf->page, priv); + file_update_time(file); sb_end_pagefault(inode->i_sb); return VM_FAULT_LOCKED; diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index 52d5af5fcd44..8c24fdc899e3 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -330,29 +330,6 @@ static void xdr_decode_YFSFetchVolumeStatus(const __be32 **_bp, } /* - * Deliver a reply that's a status, callback and volsync. - */ -static int yfs_deliver_fs_status_cb_and_volsync(struct afs_call *call) -{ - struct afs_operation *op = call->op; - const __be32 *bp; - int ret; - - ret = afs_transfer_reply(call); - if (ret < 0) - return ret; - - /* unmarshall the reply once we've received all of it */ - bp = call->buffer; - xdr_decode_YFSFetchStatus(&bp, call, &op->file[0].scb); - xdr_decode_YFSCallBack(&bp, call, &op->file[0].scb); - xdr_decode_YFSVolSync(&bp, &op->volsync); - - _leave(" = 0 [done]"); - return 0; -} - -/* * Deliver reply data to operations that just return a file status and a volume * sync record. */ @@ -375,48 +352,6 @@ static int yfs_deliver_status_and_volsync(struct afs_call *call) } /* - * YFS.FetchStatus operation type - */ -static const struct afs_call_type yfs_RXYFSFetchStatus_vnode = { - .name = "YFS.FetchStatus(vnode)", - .op = yfs_FS_FetchStatus, - .deliver = yfs_deliver_fs_status_cb_and_volsync, - .destructor = afs_flat_call_destructor, -}; - -/* - * Fetch the status information for a file. - */ -void yfs_fs_fetch_file_status(struct afs_operation *op) -{ - struct afs_vnode_param *vp = &op->file[0]; - struct afs_call *call; - __be32 *bp; - - _enter(",%x,{%llx:%llu},,", - key_serial(op->key), vp->fid.vid, vp->fid.vnode); - - call = afs_alloc_flat_call(op->net, &yfs_RXYFSFetchStatus_vnode, - sizeof(__be32) * 2 + - sizeof(struct yfs_xdr_YFSFid), - sizeof(struct yfs_xdr_YFSFetchStatus) + - sizeof(struct yfs_xdr_YFSCallBack) + - sizeof(struct yfs_xdr_YFSVolSync)); - if (!call) - return afs_op_nomem(op); - - /* marshall the parameters */ - bp = call->request; - bp = xdr_encode_u32(bp, YFSFETCHSTATUS); - bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &vp->fid); - yfs_check_req(call, bp); - - trace_afs_make_fs_call(call, &vp->fid); - afs_make_op_call(op, call, GFP_NOFS); -} - -/* * Deliver reply data to an YFS.FetchData64. */ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) @@ -1605,12 +1540,36 @@ void yfs_fs_release_lock(struct afs_operation *op) } /* + * Deliver a reply to YFS.FetchStatus + */ +static int yfs_deliver_fs_fetch_status(struct afs_call *call) +{ + struct afs_operation *op = call->op; + struct afs_vnode_param *vp = &op->file[op->fetch_status.which]; + const __be32 *bp; + int ret; + + ret = afs_transfer_reply(call); + if (ret < 0) + return ret; + + /* unmarshall the reply once we've received all of it */ + bp = call->buffer; + xdr_decode_YFSFetchStatus(&bp, call, &vp->scb); + xdr_decode_YFSCallBack(&bp, call, &vp->scb); + xdr_decode_YFSVolSync(&bp, &op->volsync); + + _leave(" = 0 [done]"); + return 0; +} + +/* * YFS.FetchStatus operation type */ static const struct afs_call_type yfs_RXYFSFetchStatus = { .name = "YFS.FetchStatus", .op = yfs_FS_FetchStatus, - .deliver = yfs_deliver_fs_status_cb_and_volsync, + .deliver = yfs_deliver_fs_fetch_status, .destructor = afs_flat_call_destructor, }; @@ -1619,7 +1578,7 @@ static const struct afs_call_type yfs_RXYFSFetchStatus = { */ void yfs_fs_fetch_status(struct afs_operation *op) { - struct afs_vnode_param *vp = &op->file[0]; + struct afs_vnode_param *vp = &op->file[op->fetch_status.which]; struct afs_call *call; __be32 *bp; @@ -67,7 +67,7 @@ struct aio_ring { unsigned header_length; /* size of aio_ring */ - struct io_event io_events[0]; + struct io_event io_events[]; }; /* 128 bytes + ring size */ /* diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index 4ccb3c9189d8..2e42f47a7f98 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -9,7 +9,8 @@ ext4-y := balloc.o bitmap.o block_validity.o dir.o ext4_jbd2.o extents.o \ extents_status.o file.o fsmap.o fsync.o hash.o ialloc.o \ indirect.o inline.o inode.o ioctl.o mballoc.o migrate.o \ mmp.o move_extent.o namei.o page-io.o readpage.o resize.o \ - super.o symlink.o sysfs.o xattr.o xattr_trusted.o xattr_user.o + super.o symlink.o sysfs.o xattr.o xattr_hurd.o xattr_trusted.o \ + xattr_user.o ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o ext4-$(CONFIG_EXT4_FS_SECURITY) += xattr_security.o diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index c654205f648d..1d82336b1cd4 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -675,6 +675,7 @@ static int ext4_d_compare(const struct dentry *dentry, unsigned int len, struct qstr qstr = {.name = str, .len = len }; const struct dentry *parent = READ_ONCE(dentry->d_parent); const struct inode *inode = READ_ONCE(parent->d_inode); + char strbuf[DNAME_INLINE_LEN]; if (!inode || !IS_CASEFOLDED(inode) || !EXT4_SB(inode->i_sb)->s_encoding) { @@ -683,6 +684,21 @@ static int ext4_d_compare(const struct dentry *dentry, unsigned int len, return memcmp(str, name->name, len); } + /* + * If the dentry name is stored in-line, then it may be concurrently + * modified by a rename. If this happens, the VFS will eventually retry + * the lookup, so it doesn't matter what ->d_compare() returns. + * However, it's unsafe to call utf8_strncasecmp() with an unstable + * string. Therefore, we have to copy the name into a temporary buffer. + */ + if (len <= DNAME_INLINE_LEN - 1) { + memcpy(strbuf, str, len); + strbuf[len] = 0; + qstr.name = strbuf; + /* prevent compiler from optimizing out the temporary buffer */ + barrier(); + } + return ext4_ci_compare(inode, name, &qstr, false); } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index b08841f70b69..42f5060f3cdf 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -426,13 +426,16 @@ struct flex_groups { #define EXT4_VERITY_FL 0x00100000 /* Verity protected inode */ #define EXT4_EA_INODE_FL 0x00200000 /* Inode used for large EA */ /* 0x00400000 was formerly EXT4_EOFBLOCKS_FL */ + +#define EXT4_DAX_FL 0x02000000 /* Inode is DAX */ + #define EXT4_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */ #define EXT4_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ #define EXT4_CASEFOLD_FL 0x40000000 /* Casefolded directory */ #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ -#define EXT4_FL_USER_VISIBLE 0x705BDFFF /* User visible flags */ -#define EXT4_FL_USER_MODIFIABLE 0x604BC0FF /* User modifiable flags */ +#define EXT4_FL_USER_VISIBLE 0x725BDFFF /* User visible flags */ +#define EXT4_FL_USER_MODIFIABLE 0x624BC0FF /* User modifiable flags */ /* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */ #define EXT4_FL_XFLAG_VISIBLE (EXT4_SYNC_FL | \ @@ -440,14 +443,16 @@ struct flex_groups { EXT4_APPEND_FL | \ EXT4_NODUMP_FL | \ EXT4_NOATIME_FL | \ - EXT4_PROJINHERIT_FL) + EXT4_PROJINHERIT_FL | \ + EXT4_DAX_FL) /* Flags that should be inherited by new inodes from their parent. */ #define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\ EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\ EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\ EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL |\ - EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL) + EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL |\ + EXT4_DAX_FL) /* Flags that are appropriate for regular files (all but dir-specific ones). */ #define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL |\ @@ -459,6 +464,10 @@ struct flex_groups { /* The only flags that should be swapped */ #define EXT4_FL_SHOULD_SWAP (EXT4_HUGE_FILE_FL | EXT4_EXTENTS_FL) +/* Flags which are mutually exclusive to DAX */ +#define EXT4_DAX_MUT_EXCL (EXT4_VERITY_FL | EXT4_ENCRYPT_FL |\ + EXT4_JOURNAL_DATA_FL) + /* Mask out flags that are inappropriate for the given type of inode. */ static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags) { @@ -499,6 +508,7 @@ enum { EXT4_INODE_VERITY = 20, /* Verity protected inode */ EXT4_INODE_EA_INODE = 21, /* Inode used for large EA */ /* 22 was formerly EXT4_INODE_EOFBLOCKS */ + EXT4_INODE_DAX = 25, /* Inode is DAX */ EXT4_INODE_INLINE_DATA = 28, /* Data in inode. */ EXT4_INODE_PROJINHERIT = 29, /* Create with parents projid */ EXT4_INODE_CASEFOLD = 30, /* Casefolded directory */ @@ -1135,9 +1145,9 @@ struct ext4_inode_info { #define EXT4_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */ #define EXT4_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/ #ifdef CONFIG_FS_DAX -#define EXT4_MOUNT_DAX 0x00200 /* Direct Access */ +#define EXT4_MOUNT_DAX_ALWAYS 0x00200 /* Direct Access */ #else -#define EXT4_MOUNT_DAX 0 +#define EXT4_MOUNT_DAX_ALWAYS 0 #endif #define EXT4_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */ #define EXT4_MOUNT_JOURNAL_DATA 0x00400 /* Write data to journal */ @@ -1180,6 +1190,8 @@ struct ext4_inode_info { blocks */ #define EXT4_MOUNT2_HURD_COMPAT 0x00000004 /* Support HURD-castrated file systems */ +#define EXT4_MOUNT2_DAX_NEVER 0x00000008 /* Do not allow Direct Access */ +#define EXT4_MOUNT2_DAX_INODE 0x00000010 /* For printing options only */ #define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM 0x00000008 /* User explicitly specified journal checksum */ @@ -1992,6 +2004,7 @@ static inline bool ext4_has_incompat_features(struct super_block *sb) */ #define EXT4_FLAGS_RESIZING 0 #define EXT4_FLAGS_SHUTDOWN 1 +#define EXT4_FLAGS_BDEV_IS_DAX 2 static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi) { @@ -2705,7 +2718,7 @@ extern int ext4_can_truncate(struct inode *inode); extern int ext4_truncate(struct inode *); extern int ext4_break_layouts(struct inode *); extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length); -extern void ext4_set_inode_flags(struct inode *); +extern void ext4_set_inode_flags(struct inode *, bool init); extern int ext4_alloc_da_blocks(struct inode *inode); extern void ext4_set_aops(struct inode *inode); extern int ext4_writepage_trans_blocks(struct inode *); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 7d088ff1e902..221f240eae60 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2844,7 +2844,7 @@ again: * in use to avoid freeing it when removing blocks. */ if (sbi->s_cluster_ratio > 1) { - pblk = ext4_ext_pblock(ex) + end - ee_block + 2; + pblk = ext4_ext_pblock(ex) + end - ee_block + 1; partial.pclu = EXT4_B2C(sbi, pblk); partial.state = nofree; } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 54d324e80fe5..df25d38d6539 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1116,7 +1116,7 @@ got: ei->i_block_group = group; ei->i_last_alloc_group = ~0; - ext4_set_inode_flags(inode); + ext4_set_inode_flags(inode, true); if (IS_DIRSYNC(inode)) ext4_handle_sync(handle); if (insert_inode_locked(inode) < 0) { diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 40ec5c7ef0d3..10dd470876b3 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4403,9 +4403,11 @@ int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc) !ext4_test_inode_state(inode, EXT4_STATE_XATTR)); } -static bool ext4_should_use_dax(struct inode *inode) +static bool ext4_should_enable_dax(struct inode *inode) { - if (!test_opt(inode->i_sb, DAX)) + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + + if (test_opt2(inode->i_sb, DAX_NEVER)) return false; if (!S_ISREG(inode->i_mode)) return false; @@ -4417,14 +4419,21 @@ static bool ext4_should_use_dax(struct inode *inode) return false; if (ext4_test_inode_flag(inode, EXT4_INODE_VERITY)) return false; - return true; + if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags)) + return false; + if (test_opt(inode->i_sb, DAX_ALWAYS)) + return true; + + return ext4_test_inode_flag(inode, EXT4_INODE_DAX); } -void ext4_set_inode_flags(struct inode *inode) +void ext4_set_inode_flags(struct inode *inode, bool init) { unsigned int flags = EXT4_I(inode)->i_flags; unsigned int new_fl = 0; + WARN_ON_ONCE(IS_DAX(inode) && init); + if (flags & EXT4_SYNC_FL) new_fl |= S_SYNC; if (flags & EXT4_APPEND_FL) @@ -4435,8 +4444,13 @@ void ext4_set_inode_flags(struct inode *inode) new_fl |= S_NOATIME; if (flags & EXT4_DIRSYNC_FL) new_fl |= S_DIRSYNC; - if (ext4_should_use_dax(inode)) + + /* Because of the way inode_set_flags() works we must preserve S_DAX + * here if already set. */ + new_fl |= (inode->i_flags & S_DAX); + if (init && ext4_should_enable_dax(inode)) new_fl |= S_DAX; + if (flags & EXT4_ENCRYPT_FL) new_fl |= S_ENCRYPTED; if (flags & EXT4_CASEFOLD_FL) @@ -4650,7 +4664,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, * not initialized on a new filesystem. */ } ei->i_flags = le32_to_cpu(raw_inode->i_flags); - ext4_set_inode_flags(inode); + ext4_set_inode_flags(inode, true); inode->i_blocks = ext4_inode_blocks(raw_inode, ei); ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo); if (ext4_has_feature_64bit(sb)) diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 2162db0c747d..999cf6add39c 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -292,6 +292,38 @@ static int ext4_ioctl_check_immutable(struct inode *inode, __u32 new_projid, return 0; } +static void ext4_dax_dontcache(struct inode *inode, unsigned int flags) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + + if (S_ISDIR(inode->i_mode)) + return; + + if (test_opt2(inode->i_sb, DAX_NEVER) || + test_opt(inode->i_sb, DAX_ALWAYS)) + return; + + if ((ei->i_flags ^ flags) & EXT4_DAX_FL) + d_mark_dontcache(inode); +} + +static bool dax_compatible(struct inode *inode, unsigned int oldflags, + unsigned int flags) +{ + if (flags & EXT4_DAX_FL) { + if ((oldflags & EXT4_DAX_MUT_EXCL) || + ext4_test_inode_state(inode, + EXT4_STATE_VERITY_IN_PROGRESS)) { + return false; + } + } + + if ((flags & EXT4_DAX_MUT_EXCL) && (oldflags & EXT4_DAX_FL)) + return false; + + return true; +} + static int ext4_ioctl_setflags(struct inode *inode, unsigned int flags) { @@ -300,7 +332,6 @@ static int ext4_ioctl_setflags(struct inode *inode, int err = -EPERM, migrate = 0; struct ext4_iloc iloc; unsigned int oldflags, mask, i; - unsigned int jflag; struct super_block *sb = inode->i_sb; /* Is it quota file? Do not allow user to mess with it */ @@ -309,9 +340,6 @@ static int ext4_ioctl_setflags(struct inode *inode, oldflags = ei->i_flags; - /* The JOURNAL_DATA flag is modifiable only by root */ - jflag = flags & EXT4_JOURNAL_DATA_FL; - err = vfs_ioc_setflags_prepare(inode, oldflags, flags); if (err) goto flags_out; @@ -320,10 +348,16 @@ static int ext4_ioctl_setflags(struct inode *inode, * The JOURNAL_DATA flag can only be changed by * the relevant capability. */ - if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) { + if ((flags ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) { if (!capable(CAP_SYS_RESOURCE)) goto flags_out; } + + if (!dax_compatible(inode, oldflags, flags)) { + err = -EOPNOTSUPP; + goto flags_out; + } + if ((flags ^ oldflags) & EXT4_EXTENTS_FL) migrate = 1; @@ -369,6 +403,8 @@ static int ext4_ioctl_setflags(struct inode *inode, if (err) goto flags_err; + ext4_dax_dontcache(inode, flags); + for (i = 0, mask = 1; i < 32; i++, mask <<= 1) { if (!(mask & EXT4_FL_USER_MODIFIABLE)) continue; @@ -381,7 +417,8 @@ static int ext4_ioctl_setflags(struct inode *inode, ext4_clear_inode_flag(inode, i); } - ext4_set_inode_flags(inode); + ext4_set_inode_flags(inode, false); + inode->i_ctime = current_time(inode); err = ext4_mark_iloc_dirty(handle, inode, &iloc); @@ -390,17 +427,18 @@ flags_err: if (err) goto flags_out; - if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) { + if ((flags ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) { /* * Changes to the journaling mode can cause unsafe changes to - * S_DAX if we are using the DAX mount option. + * S_DAX if the inode is DAX */ - if (test_opt(inode->i_sb, DAX)) { + if (IS_DAX(inode)) { err = -EBUSY; goto flags_out; } - err = ext4_change_inode_journal_flag(inode, jflag); + err = ext4_change_inode_journal_flag(inode, + flags & EXT4_JOURNAL_DATA_FL); if (err) goto flags_out; } @@ -527,12 +565,15 @@ static inline __u32 ext4_iflags_to_xflags(unsigned long iflags) xflags |= FS_XFLAG_NOATIME; if (iflags & EXT4_PROJINHERIT_FL) xflags |= FS_XFLAG_PROJINHERIT; + if (iflags & EXT4_DAX_FL) + xflags |= FS_XFLAG_DAX; return xflags; } #define EXT4_SUPPORTED_FS_XFLAGS (FS_XFLAG_SYNC | FS_XFLAG_IMMUTABLE | \ FS_XFLAG_APPEND | FS_XFLAG_NODUMP | \ - FS_XFLAG_NOATIME | FS_XFLAG_PROJINHERIT) + FS_XFLAG_NOATIME | FS_XFLAG_PROJINHERIT | \ + FS_XFLAG_DAX) /* Transfer xflags flags to internal */ static inline unsigned long ext4_xflags_to_iflags(__u32 xflags) @@ -551,6 +592,8 @@ static inline unsigned long ext4_xflags_to_iflags(__u32 xflags) iflags |= EXT4_NOATIME_FL; if (xflags & FS_XFLAG_PROJINHERIT) iflags |= EXT4_PROJINHERIT_FL; + if (xflags & FS_XFLAG_DAX) + iflags |= EXT4_DAX_FL; return iflags; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index a9083113a8c0..c0a331e2feb0 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4708,7 +4708,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, } ac->ac_op = EXT4_MB_HISTORY_PREALLOC; - seq = *this_cpu_ptr(&discard_pa_seq); + seq = this_cpu_read(discard_pa_seq); if (!ext4_mb_use_preallocated(ac)) { ac->ac_op = EXT4_MB_HISTORY_ALLOC; ext4_mb_normalize_request(ac, ar); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c668f6b42374..330957ed1f05 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -522,9 +522,6 @@ static void ext4_handle_error(struct super_block *sb) smp_wmb(); sb->s_flags |= SB_RDONLY; } else if (test_opt(sb, ERRORS_PANIC)) { - if (EXT4_SB(sb)->s_journal && - !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR)) - return; panic("EXT4-fs (device %s): panic forced after error\n", sb->s_id); } @@ -725,23 +722,20 @@ void __ext4_abort(struct super_block *sb, const char *function, va_end(args); if (sb_rdonly(sb) == 0) { - ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED; + if (EXT4_SB(sb)->s_journal) + jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); + + ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); /* * Make sure updated value of ->s_mount_flags will be visible * before ->s_flags update */ smp_wmb(); sb->s_flags |= SB_RDONLY; - if (EXT4_SB(sb)->s_journal) - jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); } - if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) { - if (EXT4_SB(sb)->s_journal && - !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR)) - return; + if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) panic("EXT4-fs panic from previous error\n"); - } } void __ext4_msg(struct super_block *sb, @@ -1324,6 +1318,9 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len, if (WARN_ON_ONCE(IS_DAX(inode) && i_size_read(inode))) return -EINVAL; + if (ext4_test_inode_flag(inode, EXT4_INODE_DAX)) + return -EOPNOTSUPP; + res = ext4_convert_inline_data(inode); if (res) return res; @@ -1349,7 +1346,7 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len, * Update inode->i_flags - S_ENCRYPTED will be enabled, * S_DAX may be disabled */ - ext4_set_inode_flags(inode); + ext4_set_inode_flags(inode, false); } return res; } @@ -1376,7 +1373,7 @@ retry: * Update inode->i_flags - S_ENCRYPTED will be enabled, * S_DAX may be disabled */ - ext4_set_inode_flags(inode); + ext4_set_inode_flags(inode, false); res = ext4_mark_inode_dirty(handle, inode); if (res) EXT4_ERROR_INODE(inode, "Failed to mark inode dirty"); @@ -1514,7 +1511,8 @@ enum { Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota, Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err, - Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, Opt_dax, + Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, + Opt_dax, Opt_dax_always, Opt_dax_inode, Opt_dax_never, Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error, Opt_nowarn_on_error, Opt_mblk_io_submit, Opt_lazytime, Opt_nolazytime, Opt_debug_want_extra_isize, @@ -1581,6 +1579,9 @@ static const match_table_t tokens = { {Opt_nobarrier, "nobarrier"}, {Opt_i_version, "i_version"}, {Opt_dax, "dax"}, + {Opt_dax_always, "dax=always"}, + {Opt_dax_inode, "dax=inode"}, + {Opt_dax_never, "dax=never"}, {Opt_stripe, "stripe=%u"}, {Opt_delalloc, "delalloc"}, {Opt_warn_on_error, "warn_on_error"}, @@ -1729,6 +1730,7 @@ static int clear_qf_name(struct super_block *sb, int qtype) #define MOPT_NO_EXT3 0x0200 #define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3) #define MOPT_STRING 0x0400 +#define MOPT_SKIP 0x0800 static const struct mount_opts { int token; @@ -1778,7 +1780,13 @@ static const struct mount_opts { {Opt_min_batch_time, 0, MOPT_GTE0}, {Opt_inode_readahead_blks, 0, MOPT_GTE0}, {Opt_init_itable, 0, MOPT_GTE0}, - {Opt_dax, EXT4_MOUNT_DAX, MOPT_SET}, + {Opt_dax, EXT4_MOUNT_DAX_ALWAYS, MOPT_SET | MOPT_SKIP}, + {Opt_dax_always, EXT4_MOUNT_DAX_ALWAYS, + MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP}, + {Opt_dax_inode, EXT4_MOUNT2_DAX_INODE, + MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP}, + {Opt_dax_never, EXT4_MOUNT2_DAX_NEVER, + MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP}, {Opt_stripe, 0, MOPT_GTE0}, {Opt_resuid, 0, MOPT_GTE0}, {Opt_resgid, 0, MOPT_GTE0}, @@ -2123,13 +2131,56 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, } sbi->s_jquota_fmt = m->mount_opt; #endif - } else if (token == Opt_dax) { + } else if (token == Opt_dax || token == Opt_dax_always || + token == Opt_dax_inode || token == Opt_dax_never) { #ifdef CONFIG_FS_DAX - ext4_msg(sb, KERN_WARNING, - "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); - sbi->s_mount_opt |= m->mount_opt; + switch (token) { + case Opt_dax: + case Opt_dax_always: + if (is_remount && + (!(sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) || + (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER))) { + fail_dax_change_remount: + ext4_msg(sb, KERN_ERR, "can't change " + "dax mount option while remounting"); + return -1; + } + if (is_remount && + (test_opt(sb, DATA_FLAGS) == + EXT4_MOUNT_JOURNAL_DATA)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "both data=journal and dax"); + return -1; + } + ext4_msg(sb, KERN_WARNING, + "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); + sbi->s_mount_opt |= EXT4_MOUNT_DAX_ALWAYS; + sbi->s_mount_opt2 &= ~EXT4_MOUNT2_DAX_NEVER; + break; + case Opt_dax_never: + if (is_remount && + (!(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) || + (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS))) + goto fail_dax_change_remount; + sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_NEVER; + sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS; + break; + case Opt_dax_inode: + if (is_remount && + ((sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) || + (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) || + !(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_INODE))) + goto fail_dax_change_remount; + sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS; + sbi->s_mount_opt2 &= ~EXT4_MOUNT2_DAX_NEVER; + /* Strictly for printing options */ + sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_INODE; + break; + } #else ext4_msg(sb, KERN_INFO, "dax option not supported"); + sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_NEVER; + sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS; return -1; #endif } else if (token == Opt_data_err_abort) { @@ -2293,7 +2344,7 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, for (m = ext4_mount_opts; m->token != Opt_err; m++) { int want_set = m->flags & MOPT_SET; if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) || - (m->flags & MOPT_CLEAR_ERR)) + (m->flags & MOPT_CLEAR_ERR) || m->flags & MOPT_SKIP) continue; if (!nodefs && !(m->mount_opt & (sbi->s_mount_opt ^ def_mount_opt))) continue; /* skip if same as the default */ @@ -2353,6 +2404,17 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, fscrypt_show_test_dummy_encryption(seq, sep, sb); + if (test_opt(sb, DAX_ALWAYS)) { + if (IS_EXT2_SB(sb)) + SEQ_OPTS_PUTS("dax"); + else + SEQ_OPTS_PUTS("dax=always"); + } else if (test_opt2(sb, DAX_NEVER)) { + SEQ_OPTS_PUTS("dax=never"); + } else if (test_opt2(sb, DAX_INODE)) { + SEQ_OPTS_PUTS("dax=inode"); + } + ext4_show_quota_options(seq, sb); return 0; } @@ -2383,6 +2445,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, ext4_msg(sb, KERN_ERR, "revision level too high, " "forcing read-only mode"); err = -EROFS; + goto done; } if (read_only) goto done; @@ -4017,7 +4080,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) "both data=journal and delalloc"); goto failed_mount; } - if (test_opt(sb, DAX)) { + if (test_opt(sb, DAX_ALWAYS)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and dax"); goto failed_mount; @@ -4127,13 +4190,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } - if (sbi->s_mount_opt & EXT4_MOUNT_DAX) { + if (bdev_dax_supported(sb->s_bdev, blocksize)) + set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags); + + if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) { if (ext4_has_feature_inline_data(sb)) { ext4_msg(sb, KERN_ERR, "Cannot use DAX on a filesystem" " that may contain inline data"); goto failed_mount; } - if (!bdev_dax_supported(sb->s_bdev, blocksize)) { + if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags)) { ext4_msg(sb, KERN_ERR, "DAX unsupported by block device."); goto failed_mount; @@ -5447,12 +5513,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) err = -EINVAL; goto restore_opts; } - if (test_opt(sb, DAX)) { - ext4_msg(sb, KERN_ERR, "can't mount with " - "both data=journal and dax"); - err = -EINVAL; - goto restore_opts; - } } else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) { if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ext4_msg(sb, KERN_ERR, "can't mount with " @@ -5468,12 +5528,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } - if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX) { - ext4_msg(sb, KERN_WARNING, "warning: refusing change of " - "dax flag with busy inodes while remounting"); - sbi->s_mount_opt ^= EXT4_MOUNT_DAX; - } - if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) ext4_abort(sb, EXT4_ERR_ESHUTDOWN, "Abort forced by user"); diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c index dec1244dd062..bbd5e7e0632b 100644 --- a/fs/ext4/verity.c +++ b/fs/ext4/verity.c @@ -113,6 +113,9 @@ static int ext4_begin_enable_verity(struct file *filp) handle_t *handle; int err; + if (IS_DAX(inode) || ext4_test_inode_flag(inode, EXT4_INODE_DAX)) + return -EINVAL; + if (ext4_verity_in_progress(inode)) return -EBUSY; @@ -241,7 +244,7 @@ static int ext4_end_enable_verity(struct file *filp, const void *desc, if (err) goto out_stop; ext4_set_inode_flag(inode, EXT4_INODE_VERITY); - ext4_set_inode_flags(inode); + ext4_set_inode_flags(inode, false); err = ext4_mark_iloc_dirty(handle, inode, &iloc); } out_stop: diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 9b29a40738ac..7d2f6576d954 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -93,6 +93,7 @@ static const struct xattr_handler * const ext4_xattr_handler_map[] = { #ifdef CONFIG_EXT4_FS_SECURITY [EXT4_XATTR_INDEX_SECURITY] = &ext4_xattr_security_handler, #endif + [EXT4_XATTR_INDEX_HURD] = &ext4_xattr_hurd_handler, }; const struct xattr_handler *ext4_xattr_handlers[] = { @@ -105,6 +106,7 @@ const struct xattr_handler *ext4_xattr_handlers[] = { #ifdef CONFIG_EXT4_FS_SECURITY &ext4_xattr_security_handler, #endif + &ext4_xattr_hurd_handler, NULL }; diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index ffe21ac77f78..730b91fa0dd7 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -124,6 +124,7 @@ struct ext4_xattr_inode_array { extern const struct xattr_handler ext4_xattr_user_handler; extern const struct xattr_handler ext4_xattr_trusted_handler; extern const struct xattr_handler ext4_xattr_security_handler; +extern const struct xattr_handler ext4_xattr_hurd_handler; #define EXT4_XATTR_NAME_ENCRYPTION_CONTEXT "c" diff --git a/fs/ext4/xattr_hurd.c b/fs/ext4/xattr_hurd.c new file mode 100644 index 000000000000..8cfa74a56361 --- /dev/null +++ b/fs/ext4/xattr_hurd.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ext4/xattr_hurd.c + * Handler for extended gnu attributes for the Hurd. + * + * Copyright (C) 2001 by Andreas Gruenbacher, <a.gruenbacher@computer.org> + * Copyright (C) 2020 by Jan (janneke) Nieuwenhuizen, <janneke@gnu.org> + */ + +#include <linux/init.h> +#include <linux/string.h> +#include "ext4.h" +#include "xattr.h" + +static bool +ext4_xattr_hurd_list(struct dentry *dentry) +{ + return test_opt(dentry->d_sb, XATTR_USER); +} + +static int +ext4_xattr_hurd_get(const struct xattr_handler *handler, + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) +{ + if (!test_opt(inode->i_sb, XATTR_USER)) + return -EOPNOTSUPP; + + return ext4_xattr_get(inode, EXT4_XATTR_INDEX_HURD, + name, buffer, size); +} + +static int +ext4_xattr_hurd_set(const struct xattr_handler *handler, + struct dentry *unused, struct inode *inode, + const char *name, const void *value, + size_t size, int flags) +{ + if (!test_opt(inode->i_sb, XATTR_USER)) + return -EOPNOTSUPP; + + return ext4_xattr_set(inode, EXT4_XATTR_INDEX_HURD, + name, value, size, flags); +} + +const struct xattr_handler ext4_xattr_hurd_handler = { + .prefix = XATTR_HURD_PREFIX, + .list = ext4_xattr_hurd_list, + .get = ext4_xattr_hurd_get, + .set = ext4_xattr_hurd_set, +}; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index a49d0e670ddf..e4944436e733 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1140,6 +1140,7 @@ static journal_t *journal_init_common(struct block_device *bdev, init_waitqueue_head(&journal->j_wait_commit); init_waitqueue_head(&journal->j_wait_updates); init_waitqueue_head(&journal->j_wait_reserved); + mutex_init(&journal->j_abort_mutex); mutex_init(&journal->j_barrier); mutex_init(&journal->j_checkpoint_mutex); spin_lock_init(&journal->j_revoke_lock); @@ -1402,7 +1403,8 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags) printk(KERN_ERR "JBD2: Error %d detected when updating " "journal superblock for %s.\n", ret, journal->j_devname); - jbd2_journal_abort(journal, ret); + if (!is_journal_aborted(journal)) + jbd2_journal_abort(journal, ret); } return ret; @@ -2154,6 +2156,13 @@ void jbd2_journal_abort(journal_t *journal, int errno) transaction_t *transaction; /* + * Lock the aborting procedure until everything is done, this avoid + * races between filesystem's error handling flow (e.g. ext4_abort()), + * ensure panic after the error info is written into journal's + * superblock. + */ + mutex_lock(&journal->j_abort_mutex); + /* * ESHUTDOWN always takes precedence because a file system check * caused by any other journal abort error is not required after * a shutdown triggered. @@ -2167,6 +2176,7 @@ void jbd2_journal_abort(journal_t *journal, int errno) journal->j_errno = errno; jbd2_journal_update_sb_errno(journal); } + mutex_unlock(&journal->j_abort_mutex); return; } @@ -2188,10 +2198,7 @@ void jbd2_journal_abort(journal_t *journal, int errno) * layer could realise that a filesystem check is needed. */ jbd2_journal_update_sb_errno(journal); - - write_lock(&journal->j_state_lock); - journal->j_flags |= JBD2_REC_ERR; - write_unlock(&journal->j_state_lock); + mutex_unlock(&journal->j_abort_mutex); } /** diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h index 0637271f3770..8ff4d1a1e774 100644 --- a/fs/jffs2/nodelist.h +++ b/fs/jffs2/nodelist.h @@ -259,7 +259,7 @@ struct jffs2_full_dirent uint32_t ino; /* == zero for unlink */ unsigned int nhash; unsigned char type; - unsigned char name[0]; + unsigned char name[]; }; /* diff --git a/fs/jffs2/summary.h b/fs/jffs2/summary.h index 60207a2ae952..e4131cb1f1d4 100644 --- a/fs/jffs2/summary.h +++ b/fs/jffs2/summary.h @@ -61,7 +61,7 @@ struct jffs2_sum_dirent_flash jint32_t ino; /* == zero for unlink */ uint8_t nsize; /* dirent name size */ uint8_t type; /* dirent type */ - uint8_t name[0]; /* dirent name */ + uint8_t name[]; /* dirent name */ } __attribute__((packed)); struct jffs2_sum_xattr_flash @@ -117,7 +117,7 @@ struct jffs2_sum_dirent_mem jint32_t ino; /* == zero for unlink */ uint8_t nsize; /* dirent name size */ uint8_t type; /* dirent type */ - uint8_t name[0]; /* dirent name */ + uint8_t name[]; /* dirent name */ } __attribute__((packed)); struct jffs2_sum_xattr_mem diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 8ba492d44e68..e502414b3556 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -512,7 +512,8 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) * Using bounce buffer to bypass the * hardened user copy kernel text checks. */ - if (probe_kernel_read(buf, (void *) start, tsz)) { + if (copy_from_kernel_nofault(buf, (void *)start, + tsz)) { if (clear_user(buffer, tsz)) { ret = -EFAULT; goto out; diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index 7187bd1a30ea..8d64edb80ebf 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -262,7 +262,7 @@ struct squashfs_dir_index { __le32 index; __le32 start_block; __le32 size; - unsigned char name[0]; + unsigned char name[]; }; struct squashfs_base_inode { @@ -327,7 +327,7 @@ struct squashfs_symlink_inode { __le32 inode_number; __le32 nlink; __le32 symlink_size; - char symlink[0]; + char symlink[]; }; struct squashfs_reg_inode { @@ -341,7 +341,7 @@ struct squashfs_reg_inode { __le32 fragment; __le32 offset; __le32 file_size; - __le16 block_list[0]; + __le16 block_list[]; }; struct squashfs_lreg_inode { @@ -358,7 +358,7 @@ struct squashfs_lreg_inode { __le32 fragment; __le32 offset; __le32 xattr; - __le16 block_list[0]; + __le16 block_list[]; }; struct squashfs_dir_inode { @@ -389,7 +389,7 @@ struct squashfs_ldir_inode { __le16 i_count; __le16 offset; __le32 xattr; - struct squashfs_dir_index index[0]; + struct squashfs_dir_index index[]; }; union squashfs_inode { @@ -410,7 +410,7 @@ struct squashfs_dir_entry { __le16 inode_number; __le16 type; __le16 size; - char name[0]; + char name[]; }; struct squashfs_dir_header { @@ -428,12 +428,12 @@ struct squashfs_fragment_entry { struct squashfs_xattr_entry { __le16 type; __le16 size; - char data[0]; + char data[]; }; struct squashfs_xattr_val { __le32 vsize; - char value[0]; + char value[]; }; struct squashfs_xattr_id { diff --git a/include/drm/drm_displayid.h b/include/drm/drm_displayid.h index 27bdd273fc4e..77941efb5426 100644 --- a/include/drm/drm_displayid.h +++ b/include/drm/drm_displayid.h @@ -89,7 +89,7 @@ struct displayid_detailed_timings_1 { struct displayid_detailed_timing_block { struct displayid_block base; - struct displayid_detailed_timings_1 timings[0]; + struct displayid_detailed_timings_1 timings[]; }; #define for_each_displayid_db(displayid, block, idx, length) \ diff --git a/include/keys/encrypted-type.h b/include/keys/encrypted-type.h index 9e9ccb20d586..38afb341c3f2 100644 --- a/include/keys/encrypted-type.h +++ b/include/keys/encrypted-type.h @@ -27,7 +27,7 @@ struct encrypted_key_payload { unsigned short payload_datalen; /* payload data length */ unsigned short encrypted_key_format; /* encrypted key format */ u8 *decrypted_data; /* decrypted data */ - u8 payload_data[0]; /* payload data + datablob + hmac */ + u8 payload_data[]; /* payload data + datablob + hmac */ }; extern struct key_type key_type_encrypted; diff --git a/include/keys/rxrpc-type.h b/include/keys/rxrpc-type.h index a183278c3e9e..2b0b15a71228 100644 --- a/include/keys/rxrpc-type.h +++ b/include/keys/rxrpc-type.h @@ -28,7 +28,7 @@ struct rxkad_key { u8 primary_flag; /* T if key for primary cell for this user */ u16 ticket_len; /* length of ticket[] */ u8 session_key[8]; /* DES session key */ - u8 ticket[0]; /* the encrypted ticket */ + u8 ticket[]; /* the encrypted ticket */ }; /* @@ -100,7 +100,7 @@ struct rxrpc_key_data_v1 { u32 expiry; /* time_t */ u32 kvno; u8 session_key[8]; - u8 ticket[0]; + u8 ticket[]; }; /* diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index a954def26c0d..900b9f4e0605 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -34,7 +34,7 @@ struct can_skb_priv { int ifindex; int skbcnt; - struct can_frame cf[0]; + struct can_frame cf[]; }; static inline struct can_skb_priv *can_skb_prv(struct sk_buff *skb) diff --git a/include/linux/cb710.h b/include/linux/cb710.h index 60de3fedd3a7..405657a9a0d5 100644 --- a/include/linux/cb710.h +++ b/include/linux/cb710.h @@ -36,7 +36,7 @@ struct cb710_chip { unsigned slot_mask; unsigned slots; spinlock_t irq_lock; - struct cb710_slot slot[0]; + struct cb710_slot slot[]; }; /* NOTE: cb710_chip.slots is modified only during device init/exit and diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 2247e71beb83..e5ed1c541e7f 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -52,8 +52,7 @@ struct ceph_options { unsigned long osd_idle_ttl; /* jiffies */ unsigned long osd_keepalive_timeout; /* jiffies */ unsigned long osd_request_timeout; /* jiffies */ - - u32 osd_req_flags; /* CEPH_OSD_FLAG_*, applied to each OSD request */ + u32 read_from_replica; /* CEPH_OSD_FLAG_BALANCE/LOCALIZE_READS */ /* * any type that can't be simply compared or doesn't need @@ -76,6 +75,7 @@ struct ceph_options { #define CEPH_OSD_KEEPALIVE_DEFAULT msecs_to_jiffies(5 * 1000) #define CEPH_OSD_IDLE_TTL_DEFAULT msecs_to_jiffies(60 * 1000) #define CEPH_OSD_REQUEST_TIMEOUT_DEFAULT 0 /* no timeout */ +#define CEPH_READ_FROM_REPLICA_DEFAULT 0 /* read from primary */ #define CEPH_MONC_HUNT_INTERVAL msecs_to_jiffies(3 * 1000) #define CEPH_MONC_PING_INTERVAL msecs_to_jiffies(10 * 1000) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 21aed0981edf..e368384445b6 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -5,20 +5,20 @@ #ifndef __ASSEMBLY__ #ifdef __CHECKER__ -# define __user __attribute__((noderef, address_space(1))) # define __kernel __attribute__((address_space(0))) +# define __user __attribute__((noderef, address_space(__user))) # define __safe __attribute__((safe)) # define __force __attribute__((force)) # define __nocast __attribute__((nocast)) -# define __iomem __attribute__((noderef, address_space(2))) +# define __iomem __attribute__((noderef, address_space(__iomem))) # define __must_hold(x) __attribute__((context(x,1,1))) # define __acquires(x) __attribute__((context(x,0,1))) # define __releases(x) __attribute__((context(x,1,0))) # define __acquire(x) __context__(x,1) # define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) -# define __percpu __attribute__((noderef, address_space(3))) -# define __rcu __attribute__((noderef, address_space(4))) +# define __percpu __attribute__((noderef, address_space(__percpu))) +# define __rcu __attribute__((noderef, address_space(__rcu))) # define __private __attribute__((noderef)) extern void __chk_user_ptr(const volatile void __user *); extern void __chk_io_ptr(const volatile void __iomem *); diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index e1c03339918f..6283917edd90 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -153,7 +153,7 @@ struct dma_interleaved_template { bool dst_sgl; size_t numf; size_t frame_size; - struct data_chunk sgl[0]; + struct data_chunk sgl[]; }; /** @@ -535,7 +535,7 @@ struct dmaengine_unmap_data { struct device *dev; struct kref kref; size_t len; - dma_addr_t addr[0]; + dma_addr_t addr[]; }; struct dma_async_tx_descriptor; diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index ce0b5fbf239d..3f0b19dcfae7 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -46,7 +46,7 @@ struct fscache_cache_tag { unsigned long flags; #define FSCACHE_TAG_RESERVED 0 /* T if tag is reserved for a cache */ atomic_t usage; - char name[0]; /* tag name */ + char name[]; /* tag name */ }; /* diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index f613d8529863..d56128df2aff 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -766,6 +766,11 @@ struct journal_s int j_errno; /** + * @j_abort_mutex: Lock the whole aborting procedure. + */ + struct mutex j_abort_mutex; + + /** * @j_sb_buffer: The first part of the superblock buffer. */ struct buffer_head *j_sb_buffer; @@ -1247,7 +1252,6 @@ JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3) #define JBD2_ABORT_ON_SYNCDATA_ERR 0x040 /* Abort the journal on file * data write error in ordered * mode */ -#define JBD2_REC_ERR 0x080 /* The errno in the sb has been recorded */ /* * Function declarations for the journaling transaction and buffer diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 1776eb2e43a4..ea67910ae6b7 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -208,7 +208,7 @@ struct crash_mem_range { struct crash_mem { unsigned int max_nr_ranges; unsigned int nr_ranges; - struct crash_mem_range ranges[0]; + struct crash_mem_range ranges[]; }; extern int crash_exclude_mem_range(struct crash_mem *mem, diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 594265bfd390..e210af75ee38 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -161,7 +161,7 @@ struct kretprobe_instance { kprobe_opcode_t *ret_addr; struct task_struct *task; void *fp; - char data[0]; + char data[]; }; struct kretprobe_blackpoint { diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 62ec926c78a0..d564855243d8 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -409,7 +409,7 @@ struct kvm_irq_routing_table { * Array indexed by gsi. Each entry contains list of irq chips * the gsi is connected to. */ - struct hlist_head map[0]; + struct hlist_head map[]; }; #endif diff --git a/include/linux/libata.h b/include/linux/libata.h index af832852e620..8bf5e59a7859 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -609,7 +609,7 @@ struct ata_host { struct task_struct *eh_owner; struct ata_port *simplex_claimed; /* channel owning the DMA */ - struct ata_port *ports[0]; + struct ata_port *ports[]; }; struct ata_queued_cmd { diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 659045046468..93fcef105061 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -304,16 +304,33 @@ static inline __must_check size_t __ab_c_size(size_t a, size_t b, size_t c) * struct_size() - Calculate size of structure with trailing array. * @p: Pointer to the structure. * @member: Name of the array member. - * @n: Number of elements in the array. + * @count: Number of elements in the array. * * Calculates size of memory needed for structure @p followed by an - * array of @n @member elements. + * array of @count number of @member elements. * * Return: number of bytes needed or SIZE_MAX on overflow. */ -#define struct_size(p, member, n) \ - __ab_c_size(n, \ +#define struct_size(p, member, count) \ + __ab_c_size(count, \ sizeof(*(p)->member) + __must_be_array((p)->member),\ sizeof(*(p))) +/** + * flex_array_size() - Calculate size of a flexible array member + * within an enclosing structure. + * + * @p: Pointer to the structure. + * @member: Name of the flexible array member. + * @count: Number of elements in the array. + * + * Calculates size of a flexible array of @count number of @member + * elements, at the end of structure @p. + * + * Return: number of bytes needed or SIZE_MAX on overflow. + */ +#define flex_array_size(p, member, count) \ + array_size(count, \ + sizeof(*(p)->member) + __must_be_array((p)->member)) + #endif /* __LINUX_OVERFLOW_H */ diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 8ccd82105de8..76731230bbc5 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -221,7 +221,7 @@ struct sctp_datahdr { __be16 stream; __be16 ssn; __u32 ppid; - __u8 payload[0]; + __u8 payload[]; }; struct sctp_data_chunk { @@ -269,7 +269,7 @@ struct sctp_inithdr { __be16 num_outbound_streams; __be16 num_inbound_streams; __be32 initial_tsn; - __u8 params[0]; + __u8 params[]; }; struct sctp_init_chunk { @@ -299,13 +299,13 @@ struct sctp_cookie_preserve_param { /* Section 3.3.2.1 Host Name Address (11) */ struct sctp_hostname_param { struct sctp_paramhdr param_hdr; - uint8_t hostname[0]; + uint8_t hostname[]; }; /* Section 3.3.2.1 Supported Address Types (12) */ struct sctp_supported_addrs_param { struct sctp_paramhdr param_hdr; - __be16 types[0]; + __be16 types[]; }; /* ADDIP Section 3.2.6 Adaptation Layer Indication */ @@ -317,25 +317,25 @@ struct sctp_adaptation_ind_param { /* ADDIP Section 4.2.7 Supported Extensions Parameter */ struct sctp_supported_ext_param { struct sctp_paramhdr param_hdr; - __u8 chunks[0]; + __u8 chunks[]; }; /* AUTH Section 3.1 Random */ struct sctp_random_param { struct sctp_paramhdr param_hdr; - __u8 random_val[0]; + __u8 random_val[]; }; /* AUTH Section 3.2 Chunk List */ struct sctp_chunks_param { struct sctp_paramhdr param_hdr; - __u8 chunks[0]; + __u8 chunks[]; }; /* AUTH Section 3.3 HMAC Algorithm */ struct sctp_hmac_algo_param { struct sctp_paramhdr param_hdr; - __be16 hmac_ids[0]; + __be16 hmac_ids[]; }; /* RFC 2960. Section 3.3.3 Initiation Acknowledgement (INIT ACK) (2): @@ -350,7 +350,7 @@ struct sctp_initack_chunk { /* Section 3.3.3.1 State Cookie (7) */ struct sctp_cookie_param { struct sctp_paramhdr p; - __u8 body[0]; + __u8 body[]; }; /* Section 3.3.3.1 Unrecognized Parameters (8) */ @@ -384,7 +384,7 @@ struct sctp_sackhdr { __be32 a_rwnd; __be16 num_gap_ack_blocks; __be16 num_dup_tsns; - union sctp_sack_variable variable[0]; + union sctp_sack_variable variable[]; }; struct sctp_sack_chunk { @@ -436,7 +436,7 @@ struct sctp_shutdown_chunk { struct sctp_errhdr { __be16 cause; __be16 length; - __u8 variable[0]; + __u8 variable[]; }; struct sctp_operr_chunk { @@ -594,7 +594,7 @@ struct sctp_fwdtsn_skip { struct sctp_fwdtsn_hdr { __be32 new_cum_tsn; - struct sctp_fwdtsn_skip skip[0]; + struct sctp_fwdtsn_skip skip[]; }; struct sctp_fwdtsn_chunk { @@ -611,7 +611,7 @@ struct sctp_ifwdtsn_skip { struct sctp_ifwdtsn_hdr { __be32 new_cum_tsn; - struct sctp_ifwdtsn_skip skip[0]; + struct sctp_ifwdtsn_skip skip[]; }; struct sctp_ifwdtsn_chunk { @@ -658,7 +658,7 @@ struct sctp_addip_param { struct sctp_addiphdr { __be32 serial; - __u8 params[0]; + __u8 params[]; }; struct sctp_addip_chunk { @@ -718,7 +718,7 @@ struct sctp_addip_chunk { struct sctp_authhdr { __be16 shkey_id; __be16 hmac_id; - __u8 hmac[0]; + __u8 hmac[]; }; struct sctp_auth_chunk { @@ -733,7 +733,7 @@ struct sctp_infox { struct sctp_reconf_chunk { struct sctp_chunkhdr chunk_hdr; - __u8 params[0]; + __u8 params[]; }; struct sctp_strreset_outreq { @@ -741,13 +741,13 @@ struct sctp_strreset_outreq { __be32 request_seq; __be32 response_seq; __be32 send_reset_at_tsn; - __be16 list_of_streams[0]; + __be16 list_of_streams[]; }; struct sctp_strreset_inreq { struct sctp_paramhdr param_hdr; __be32 request_seq; - __be16 list_of_streams[0]; + __be16 list_of_streams[]; }; struct sctp_strreset_tsnreq { diff --git a/include/linux/tifm.h b/include/linux/tifm.h index 299cbb8c63bb..44073d06710f 100644 --- a/include/linux/tifm.h +++ b/include/linux/tifm.h @@ -124,7 +124,7 @@ struct tifm_adapter { int (*has_ms_pif)(struct tifm_adapter *fm, struct tifm_dev *sock); - struct tifm_dev *sockets[0]; + struct tifm_dev *sockets[]; }; struct tifm_adapter *tifm_alloc_adapter(unsigned int num_sockets, diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 7bcadca22100..0a76ddc07d59 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -301,13 +301,14 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src, return 0; } -bool probe_kernel_read_allowed(const void *unsafe_src, size_t size); +bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size); -extern long probe_kernel_read(void *dst, const void *src, size_t size); -extern long probe_user_read(void *dst, const void __user *src, size_t size); +long copy_from_kernel_nofault(void *dst, const void *src, size_t size); +long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size); -extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); -extern long notrace probe_user_write(void __user *dst, const void *src, size_t size); +long copy_from_user_nofault(void *dst, const void __user *src, size_t size); +long notrace copy_to_user_nofault(void __user *dst, const void *src, + size_t size); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count); @@ -317,14 +318,16 @@ long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long strnlen_user_nofault(const void __user *unsafe_addr, long count); /** - * probe_kernel_address(): safely attempt to read from a location - * @addr: address to read from - * @retval: read into this variable + * get_kernel_nofault(): safely attempt to read from a location + * @val: read into this variable + * @ptr: address to read from * * Returns 0 on success, or -EFAULT. */ -#define probe_kernel_address(addr, retval) \ - probe_kernel_read(&retval, addr, sizeof(retval)) +#define get_kernel_nofault(val, ptr) ({ \ + const typeof(val) *__gk_ptr = (ptr); \ + copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\ +}) #ifndef user_access_begin #define user_access_begin(ptr,len) access_ok(ptr, len) diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index d7338bfd7b0f..16e8b2f8d006 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -161,10 +161,51 @@ struct nf_flow_route { struct flow_offload *flow_offload_alloc(struct nf_conn *ct); void flow_offload_free(struct flow_offload *flow); -int nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table, - flow_setup_cb_t *cb, void *cb_priv); -void nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, - flow_setup_cb_t *cb, void *cb_priv); +static inline int +nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table, + flow_setup_cb_t *cb, void *cb_priv) +{ + struct flow_block *block = &flow_table->flow_block; + struct flow_block_cb *block_cb; + int err = 0; + + down_write(&flow_table->flow_block_lock); + block_cb = flow_block_cb_lookup(block, cb, cb_priv); + if (block_cb) { + err = -EEXIST; + goto unlock; + } + + block_cb = flow_block_cb_alloc(cb, cb_priv, cb_priv, NULL); + if (IS_ERR(block_cb)) { + err = PTR_ERR(block_cb); + goto unlock; + } + + list_add_tail(&block_cb->list, &block->cb_list); + +unlock: + up_write(&flow_table->flow_block_lock); + return err; +} + +static inline void +nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, + flow_setup_cb_t *cb, void *cb_priv) +{ + struct flow_block *block = &flow_table->flow_block; + struct flow_block_cb *block_cb; + + down_write(&flow_table->flow_block_lock); + block_cb = flow_block_cb_lookup(block, cb, cb_priv); + if (block_cb) { + list_del(&block_cb->list); + flow_block_cb_free(block_cb); + } else { + WARN_ON(true); + } + up_write(&flow_table->flow_block_lock); +} int flow_offload_route_init(struct flow_offload *flow, const struct nf_flow_route *route); diff --git a/include/net/tc_act/tc_ct.h b/include/net/tc_act/tc_ct.h index 79654bcb9a29..8250d6f0a462 100644 --- a/include/net/tc_act/tc_ct.h +++ b/include/net/tc_act/tc_ct.h @@ -66,7 +66,16 @@ static inline struct nf_flowtable *tcf_ct_ft(const struct tc_action *a) #endif /* CONFIG_NF_CONNTRACK */ #if IS_ENABLED(CONFIG_NET_ACT_CT) -void tcf_ct_flow_table_restore_skb(struct sk_buff *skb, unsigned long cookie); +static inline void +tcf_ct_flow_table_restore_skb(struct sk_buff *skb, unsigned long cookie) +{ + enum ip_conntrack_info ctinfo = cookie & NFCT_INFOMASK; + struct nf_conn *ct; + + ct = (struct nf_conn *)(cookie & NFCT_PTRMASK); + nf_conntrack_get(&ct->ct_general); + nf_ct_set(skb, ct, ctinfo); +} #else static inline void tcf_ct_flow_table_restore_skb(struct sk_buff *skb, unsigned long cookie) { } diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 379a612f8f1d..f44eb0a04afd 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -262,6 +262,7 @@ struct fsxattr { #define FS_EA_INODE_FL 0x00200000 /* Inode used for large EA */ #define FS_EOFBLOCKS_FL 0x00400000 /* Reserved for ext4 */ #define FS_NOCOW_FL 0x00800000 /* Do not cow file */ +#define FS_DAX_FL 0x02000000 /* Inode is DAX */ #define FS_INLINE_DATA_FL 0x10000000 /* Reserved for ext4 */ #define FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ #define FS_CASEFOLD_FL 0x40000000 /* Folder is case insensitive */ diff --git a/include/uapi/linux/xattr.h b/include/uapi/linux/xattr.h index c1395b5bd432..9463db2dfa9d 100644 --- a/include/uapi/linux/xattr.h +++ b/include/uapi/linux/xattr.h @@ -7,6 +7,7 @@ Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org> Copyright (c) 2001-2002 Silicon Graphics, Inc. All Rights Reserved. Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> + Copyright (c) 2020 Jan (janneke) Nieuwenhuizen <janneke@gnu.org> */ #include <linux/libc-compat.h> @@ -31,6 +32,9 @@ #define XATTR_BTRFS_PREFIX "btrfs." #define XATTR_BTRFS_PREFIX_LEN (sizeof(XATTR_BTRFS_PREFIX) - 1) +#define XATTR_HURD_PREFIX "gnu." +#define XATTR_HURD_PREFIX_LEN (sizeof(XATTR_HURD_PREFIX) - 1) + #define XATTR_SECURITY_PREFIX "security." #define XATTR_SECURITY_PREFIX_LEN (sizeof(XATTR_SECURITY_PREFIX) - 1) diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index ccc0f98abdd4..bc8d25f2ac8a 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -169,18 +169,18 @@ int __weak kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) { int err; - err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr, + err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE); if (err) return err; - err = probe_kernel_write((char *)bpt->bpt_addr, + err = copy_to_kernel_nofault((char *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE); return err; } int __weak kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt) { - return probe_kernel_write((char *)bpt->bpt_addr, + return copy_to_kernel_nofault((char *)bpt->bpt_addr, (char *)bpt->saved_instr, BREAK_INSTR_SIZE); } diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c index 4b280fc7dd67..61774aec46b4 100644 --- a/kernel/debug/gdbstub.c +++ b/kernel/debug/gdbstub.c @@ -247,7 +247,7 @@ char *kgdb_mem2hex(char *mem, char *buf, int count) */ tmp = buf + count; - err = probe_kernel_read(tmp, mem, count); + err = copy_from_kernel_nofault(tmp, mem, count); if (err) return NULL; while (count > 0) { @@ -283,7 +283,7 @@ int kgdb_hex2mem(char *buf, char *mem, int count) *tmp_raw |= hex_to_bin(*tmp_hex--) << 4; } - return probe_kernel_write(mem, tmp_raw, count); + return copy_to_kernel_nofault(mem, tmp_raw, count); } /* @@ -335,7 +335,7 @@ static int kgdb_ebin2mem(char *buf, char *mem, int count) size++; } - return probe_kernel_write(mem, c, size); + return copy_to_kernel_nofault(mem, c, size); } #if DBG_MAX_REG_NUM > 0 diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index ec190569f690..5c7949061671 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2326,7 +2326,8 @@ void kdb_ps1(const struct task_struct *p) int cpu; unsigned long tmp; - if (!p || probe_kernel_read(&tmp, (char *)p, sizeof(unsigned long))) + if (!p || + copy_from_kernel_nofault(&tmp, (char *)p, sizeof(unsigned long))) return; cpu = kdb_process_cpu(p); diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c index b8e6306e7e13..004c5b6c87f8 100644 --- a/kernel/debug/kdb/kdb_support.c +++ b/kernel/debug/kdb/kdb_support.c @@ -325,7 +325,7 @@ char *kdb_strdup(const char *str, gfp_t type) */ int kdb_getarea_size(void *res, unsigned long addr, size_t size) { - int ret = probe_kernel_read((char *)res, (char *)addr, size); + int ret = copy_from_kernel_nofault((char *)res, (char *)addr, size); if (ret) { if (!KDB_STATE(SUPPRESS)) { kdb_printf("kdb_getarea: Bad address 0x%lx\n", addr); @@ -350,7 +350,7 @@ int kdb_getarea_size(void *res, unsigned long addr, size_t size) */ int kdb_putarea_size(unsigned long addr, void *res, size_t size) { - int ret = probe_kernel_read((char *)addr, (char *)res, size); + int ret = copy_from_kernel_nofault((char *)addr, (char *)res, size); if (ret) { if (!KDB_STATE(SUPPRESS)) { kdb_printf("kdb_putarea: Bad address 0x%lx\n", addr); @@ -624,7 +624,8 @@ char kdb_task_state_char (const struct task_struct *p) char state; unsigned long tmp; - if (!p || probe_kernel_read(&tmp, (char *)p, sizeof(unsigned long))) + if (!p || + copy_from_kernel_nofault(&tmp, (char *)p, sizeof(unsigned long))) return 'E'; cpu = kdb_process_cpu(p); diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index d006668c0027..a0ce3c1494fd 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -73,18 +73,18 @@ config SWIOTLB config DMA_NONCOHERENT_MMAP bool +config DMA_COHERENT_POOL + bool + config DMA_REMAP + bool depends on MMU select GENERIC_ALLOCATOR select DMA_NONCOHERENT_MMAP - bool - -config DMA_COHERENT_POOL - bool - select DMA_REMAP config DMA_DIRECT_REMAP bool + select DMA_REMAP select DMA_COHERENT_POOL config DMA_CMA diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c index 35bb51c31fff..8cfa01243ed2 100644 --- a/kernel/dma/pool.c +++ b/kernel/dma/pool.c @@ -175,10 +175,9 @@ static int __init dma_atomic_pool_init(void) * sizes to 128KB per 1GB of memory, min 128KB, max MAX_ORDER-1. */ if (!atomic_pool_size) { - atomic_pool_size = max(totalram_pages() >> PAGE_SHIFT, 1UL) * - SZ_128K; - atomic_pool_size = min_t(size_t, atomic_pool_size, - 1 << (PAGE_SHIFT + MAX_ORDER-1)); + unsigned long pages = totalram_pages() / (SZ_1G / SZ_128K); + pages = min_t(unsigned long, pages, MAX_ORDER_NR_PAGES); + atomic_pool_size = max_t(size_t, pages << PAGE_SHIFT, SZ_128K); } INIT_WORK(&atomic_pool_work, atomic_pool_work_fn); diff --git a/kernel/kthread.c b/kernel/kthread.c index 8e3d2d7fdf5e..132f84a5fde3 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -201,7 +201,7 @@ void *kthread_probe_data(struct task_struct *task) struct kthread *kthread = to_kthread(task); void *data = NULL; - probe_kernel_read(&data, &kthread->data, sizeof(data)); + copy_from_kernel_nofault(&data, &kthread->data, sizeof(data)); return data; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index e729c9e587a0..dc05626979b8 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -141,7 +141,7 @@ bpf_probe_read_user_common(void *dst, u32 size, const void __user *unsafe_ptr) { int ret; - ret = probe_user_read(dst, unsafe_ptr, size); + ret = copy_from_user_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret; @@ -196,7 +196,7 @@ bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr) if (unlikely(ret < 0)) goto fail; - ret = probe_kernel_read(dst, unsafe_ptr, size); + ret = copy_from_kernel_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) goto fail; return ret; @@ -326,7 +326,7 @@ BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src, if (unlikely(!nmi_uaccess_okay())) return -EPERM; - return probe_user_write(unsafe_ptr, src, size); + return copy_to_user_nofault(unsafe_ptr, src, size); } static const struct bpf_func_proto bpf_probe_write_user_proto = { @@ -661,7 +661,7 @@ BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, copy_size = (fmt[i + 2] == '4') ? 4 : 16; - err = probe_kernel_read(bufs->buf[memcpy_cnt], + err = copy_from_kernel_nofault(bufs->buf[memcpy_cnt], (void *) (long) args[fmt_cnt], copy_size); if (err < 0) diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 6048f1be26d2..aefb6065b508 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1222,7 +1222,7 @@ fetch_store_strlen(unsigned long addr) #endif do { - ret = probe_kernel_read(&c, (u8 *)addr + len, 1); + ret = copy_from_kernel_nofault(&c, (u8 *)addr + len, 1); len++; } while (c && ret == 0 && len < MAX_STRING_SIZE); @@ -1290,7 +1290,7 @@ probe_mem_read_user(void *dest, void *src, size_t size) { const void __user *uaddr = (__force const void __user *)src; - return probe_user_read(dest, uaddr, size); + return copy_from_user_nofault(dest, uaddr, size); } static nokprobe_inline int @@ -1300,7 +1300,7 @@ probe_mem_read(void *dest, void *src, size_t size) if ((unsigned long)src < TASK_SIZE) return probe_mem_read_user(dest, src, size); #endif - return probe_kernel_read(dest, src, size); + return copy_from_kernel_nofault(dest, src, size); } /* Note that we don't verify it, since the code does not come from user space */ diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index a0ff9e200ef6..a22b62813f8c 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -236,7 +236,7 @@ struct trace_probe_event { struct trace_event_call call; struct list_head files; struct list_head probes; - struct trace_uprobe_filter filter[0]; + struct trace_uprobe_filter filter[]; }; struct trace_probe { diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 9fbe1e237563..c41c3c17b86a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4638,11 +4638,11 @@ void print_worker_info(const char *log_lvl, struct task_struct *task) * Carefully copy the associated workqueue's workfn, name and desc. * Keep the original last '\0' in case the original is garbage. */ - probe_kernel_read(&fn, &worker->current_func, sizeof(fn)); - probe_kernel_read(&pwq, &worker->current_pwq, sizeof(pwq)); - probe_kernel_read(&wq, &pwq->wq, sizeof(wq)); - probe_kernel_read(name, wq->name, sizeof(name) - 1); - probe_kernel_read(desc, worker->desc, sizeof(desc) - 1); + copy_from_kernel_nofault(&fn, &worker->current_func, sizeof(fn)); + copy_from_kernel_nofault(&pwq, &worker->current_pwq, sizeof(pwq)); + copy_from_kernel_nofault(&wq, &pwq->wq, sizeof(wq)); + copy_from_kernel_nofault(name, wq->name, sizeof(name) - 1); + copy_from_kernel_nofault(desc, worker->desc, sizeof(desc) - 1); if (fn || name[0] || desc[0]) { printk("%sWorkqueue: %s %ps", log_lvl, name, fn); diff --git a/lib/test_lockup.c b/lib/test_lockup.c index f258743a0d83..bd7c7ff39f6b 100644 --- a/lib/test_lockup.c +++ b/lib/test_lockup.c @@ -419,8 +419,8 @@ static bool test_kernel_ptr(unsigned long addr, int size) /* should be at least readable kernel address */ if (access_ok(ptr, 1) || access_ok(ptr + size - 1, 1) || - probe_kernel_address(ptr, buf) || - probe_kernel_address(ptr + size - 1, buf)) { + get_kernel_nofault(buf, ptr) || + get_kernel_nofault(buf, ptr + size - 1)) { pr_err("invalid kernel ptr: %#lx\n", addr); return true; } @@ -437,7 +437,7 @@ static bool __maybe_unused test_magic(unsigned long addr, int offset, if (!addr) return false; - if (probe_kernel_address(ptr, magic) || magic != expected) { + if (get_kernel_nofault(magic, ptr) || magic != expected) { pr_err("invalid magic at %#lx + %#x = %#x, expected %#x\n", addr, offset, magic, expected); return true; diff --git a/lib/test_objagg.c b/lib/test_objagg.c index 72c1abfa154d..da137939a410 100644 --- a/lib/test_objagg.c +++ b/lib/test_objagg.c @@ -979,10 +979,10 @@ err_check_expect_stats2: err_world2_obj_get: for (i--; i >= 0; i--) world_obj_put(&world2, objagg, hints_case->key_ids[i]); - objagg_hints_put(hints); - objagg_destroy(objagg2); i = hints_case->key_ids_count; + objagg_destroy(objagg2); err_check_expect_hints_stats: + objagg_hints_put(hints); err_hints_get: err_check_expect_stats: err_world_obj_get: diff --git a/mm/debug.c b/mm/debug.c index b5b1de8c71ac..4f376514744d 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -120,9 +120,9 @@ void __dump_page(struct page *page, const char *reason) * mapping can be invalid pointer and we don't want to crash * accessing it, so probe everything depending on it carefully */ - if (probe_kernel_read(&host, &mapping->host, + if (copy_from_kernel_nofault(&host, &mapping->host, sizeof(struct inode *)) || - probe_kernel_read(&a_ops, &mapping->a_ops, + copy_from_kernel_nofault(&a_ops, &mapping->a_ops, sizeof(struct address_space_operations *))) { pr_warn("failed to read mapping->host or a_ops, mapping not a valid kernel address?\n"); goto out_mapping; @@ -133,7 +133,7 @@ void __dump_page(struct page *page, const char *reason) goto out_mapping; } - if (probe_kernel_read(&dentry_first, + if (copy_from_kernel_nofault(&dentry_first, &host->i_dentry.first, sizeof(struct hlist_node *))) { pr_warn("mapping->a_ops:%ps with invalid mapping->host inode address %px\n", a_ops, host); @@ -146,7 +146,7 @@ void __dump_page(struct page *page, const char *reason) } dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias); - if (probe_kernel_read(&dentry, dentry_ptr, + if (copy_from_kernel_nofault(&dentry, dentry_ptr, sizeof(struct dentry))) { pr_warn("mapping->aops:%ps with invalid mapping->host->i_dentry.first %px\n", a_ops, dentry_ptr); diff --git a/mm/maccess.c b/mm/maccess.c index 88845eda5047..f98ff91e32c6 100644 --- a/mm/maccess.c +++ b/mm/maccess.c @@ -6,14 +6,15 @@ #include <linux/mm.h> #include <linux/uaccess.h> -bool __weak probe_kernel_read_allowed(const void *unsafe_src, size_t size) +bool __weak copy_from_kernel_nofault_allowed(const void *unsafe_src, + size_t size) { return true; } #ifdef HAVE_GET_KERNEL_NOFAULT -#define probe_kernel_read_loop(dst, src, len, type, err_label) \ +#define copy_from_kernel_nofault_loop(dst, src, len, type, err_label) \ while (len >= sizeof(type)) { \ __get_kernel_nofault(dst, src, type, err_label); \ dst += sizeof(type); \ @@ -21,25 +22,25 @@ bool __weak probe_kernel_read_allowed(const void *unsafe_src, size_t size) len -= sizeof(type); \ } -long probe_kernel_read(void *dst, const void *src, size_t size) +long copy_from_kernel_nofault(void *dst, const void *src, size_t size) { - if (!probe_kernel_read_allowed(src, size)) + if (!copy_from_kernel_nofault_allowed(src, size)) return -ERANGE; pagefault_disable(); - probe_kernel_read_loop(dst, src, size, u64, Efault); - probe_kernel_read_loop(dst, src, size, u32, Efault); - probe_kernel_read_loop(dst, src, size, u16, Efault); - probe_kernel_read_loop(dst, src, size, u8, Efault); + copy_from_kernel_nofault_loop(dst, src, size, u64, Efault); + copy_from_kernel_nofault_loop(dst, src, size, u32, Efault); + copy_from_kernel_nofault_loop(dst, src, size, u16, Efault); + copy_from_kernel_nofault_loop(dst, src, size, u8, Efault); pagefault_enable(); return 0; Efault: pagefault_enable(); return -EFAULT; } -EXPORT_SYMBOL_GPL(probe_kernel_read); +EXPORT_SYMBOL_GPL(copy_from_kernel_nofault); -#define probe_kernel_write_loop(dst, src, len, type, err_label) \ +#define copy_to_kernel_nofault_loop(dst, src, len, type, err_label) \ while (len >= sizeof(type)) { \ __put_kernel_nofault(dst, src, type, err_label); \ dst += sizeof(type); \ @@ -47,13 +48,13 @@ EXPORT_SYMBOL_GPL(probe_kernel_read); len -= sizeof(type); \ } -long probe_kernel_write(void *dst, const void *src, size_t size) +long copy_to_kernel_nofault(void *dst, const void *src, size_t size) { pagefault_disable(); - probe_kernel_write_loop(dst, src, size, u64, Efault); - probe_kernel_write_loop(dst, src, size, u32, Efault); - probe_kernel_write_loop(dst, src, size, u16, Efault); - probe_kernel_write_loop(dst, src, size, u8, Efault); + copy_to_kernel_nofault_loop(dst, src, size, u64, Efault); + copy_to_kernel_nofault_loop(dst, src, size, u32, Efault); + copy_to_kernel_nofault_loop(dst, src, size, u16, Efault); + copy_to_kernel_nofault_loop(dst, src, size, u8, Efault); pagefault_enable(); return 0; Efault: @@ -67,7 +68,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count) if (unlikely(count <= 0)) return 0; - if (!probe_kernel_read_allowed(unsafe_addr, count)) + if (!copy_from_kernel_nofault_allowed(unsafe_addr, count)) return -ERANGE; pagefault_disable(); @@ -87,7 +88,7 @@ Efault: } #else /* HAVE_GET_KERNEL_NOFAULT */ /** - * probe_kernel_read(): safely attempt to read from kernel-space + * copy_from_kernel_nofault(): safely attempt to read from kernel-space * @dst: pointer to the buffer that shall take the data * @src: address to read from * @size: size of the data chunk @@ -98,15 +99,15 @@ Efault: * * We ensure that the copy_from_user is executed in atomic context so that * do_page_fault() doesn't attempt to take mmap_lock. This makes - * probe_kernel_read() suitable for use within regions where the caller + * copy_from_kernel_nofault() suitable for use within regions where the caller * already holds mmap_lock, or other locks which nest inside mmap_lock. */ -long probe_kernel_read(void *dst, const void *src, size_t size) +long copy_from_kernel_nofault(void *dst, const void *src, size_t size) { long ret; mm_segment_t old_fs = get_fs(); - if (!probe_kernel_read_allowed(src, size)) + if (!copy_from_kernel_nofault_allowed(src, size)) return -ERANGE; set_fs(KERNEL_DS); @@ -120,10 +121,10 @@ long probe_kernel_read(void *dst, const void *src, size_t size) return -EFAULT; return 0; } -EXPORT_SYMBOL_GPL(probe_kernel_read); +EXPORT_SYMBOL_GPL(copy_from_kernel_nofault); /** - * probe_kernel_write(): safely attempt to write to a location + * copy_to_kernel_nofault(): safely attempt to write to a location * @dst: address to write to * @src: pointer to the data that shall be written * @size: size of the data chunk @@ -131,7 +132,7 @@ EXPORT_SYMBOL_GPL(probe_kernel_read); * Safely write to address @dst from the buffer at @src. If a kernel fault * happens, handle that and return -EFAULT. */ -long probe_kernel_write(void *dst, const void *src, size_t size) +long copy_to_kernel_nofault(void *dst, const void *src, size_t size) { long ret; mm_segment_t old_fs = get_fs(); @@ -174,7 +175,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count) if (unlikely(count <= 0)) return 0; - if (!probe_kernel_read_allowed(unsafe_addr, count)) + if (!copy_from_kernel_nofault_allowed(unsafe_addr, count)) return -ERANGE; set_fs(KERNEL_DS); @@ -193,7 +194,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count) #endif /* HAVE_GET_KERNEL_NOFAULT */ /** - * probe_user_read(): safely attempt to read from a user-space location + * copy_from_user_nofault(): safely attempt to read from a user-space location * @dst: pointer to the buffer that shall take the data * @src: address to read from. This must be a user address. * @size: size of the data chunk @@ -201,7 +202,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count) * Safely read from user address @src to the buffer at @dst. If a kernel fault * happens, handle that and return -EFAULT. */ -long probe_user_read(void *dst, const void __user *src, size_t size) +long copy_from_user_nofault(void *dst, const void __user *src, size_t size) { long ret = -EFAULT; mm_segment_t old_fs = get_fs(); @@ -218,10 +219,10 @@ long probe_user_read(void *dst, const void __user *src, size_t size) return -EFAULT; return 0; } -EXPORT_SYMBOL_GPL(probe_user_read); +EXPORT_SYMBOL_GPL(copy_from_user_nofault); /** - * probe_user_write(): safely attempt to write to a user-space location + * copy_to_user_nofault(): safely attempt to write to a user-space location * @dst: address to write to * @src: pointer to the data that shall be written * @size: size of the data chunk @@ -229,7 +230,7 @@ EXPORT_SYMBOL_GPL(probe_user_read); * Safely write to address @dst from the buffer at @src. If a kernel fault * happens, handle that and return -EFAULT. */ -long probe_user_write(void __user *dst, const void *src, size_t size) +long copy_to_user_nofault(void __user *dst, const void *src, size_t size) { long ret = -EFAULT; mm_segment_t old_fs = get_fs(); @@ -246,7 +247,7 @@ long probe_user_write(void __user *dst, const void *src, size_t size) return -EFAULT; return 0; } -EXPORT_SYMBOL_GPL(probe_user_write); +EXPORT_SYMBOL_GPL(copy_to_user_nofault); /** * strncpy_from_user_nofault: - Copy a NUL terminated string from unsafe user diff --git a/mm/rodata_test.c b/mm/rodata_test.c index 5e313fa93276..2a99df7beeb3 100644 --- a/mm/rodata_test.c +++ b/mm/rodata_test.c @@ -25,7 +25,7 @@ void rodata_test(void) } /* test 2: write to the variable; this should fault */ - if (!probe_kernel_write((void *)&rodata_test_data, + if (!copy_to_kernel_nofault((void *)&rodata_test_data, (void *)&zero, sizeof(zero))) { pr_err("test data was not read only\n"); return; diff --git a/mm/slub.c b/mm/slub.c index b8f798b50d44..fe81773fd97e 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -292,7 +292,7 @@ static inline void *get_freepointer_safe(struct kmem_cache *s, void *object) return get_freepointer(s, object); freepointer_addr = (unsigned long)object + s->offset; - probe_kernel_read(&p, (void **)freepointer_addr, sizeof(p)); + copy_from_kernel_nofault(&p, (void **)freepointer_addr, sizeof(p)); return freelist_ptr(s, p, freepointer_addr); } diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index afe0e8184c23..4e7edd707a14 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -332,6 +332,7 @@ struct ceph_options *ceph_alloc_options(void) opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT; opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT; + opt->read_from_replica = CEPH_READ_FROM_REPLICA_DEFAULT; return opt; } EXPORT_SYMBOL(ceph_alloc_options); @@ -490,16 +491,13 @@ int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt, case Opt_read_from_replica: switch (result.uint_32) { case Opt_read_from_replica_no: - opt->osd_req_flags &= ~(CEPH_OSD_FLAG_BALANCE_READS | - CEPH_OSD_FLAG_LOCALIZE_READS); + opt->read_from_replica = 0; break; case Opt_read_from_replica_balance: - opt->osd_req_flags |= CEPH_OSD_FLAG_BALANCE_READS; - opt->osd_req_flags &= ~CEPH_OSD_FLAG_LOCALIZE_READS; + opt->read_from_replica = CEPH_OSD_FLAG_BALANCE_READS; break; case Opt_read_from_replica_localize: - opt->osd_req_flags |= CEPH_OSD_FLAG_LOCALIZE_READS; - opt->osd_req_flags &= ~CEPH_OSD_FLAG_BALANCE_READS; + opt->read_from_replica = CEPH_OSD_FLAG_LOCALIZE_READS; break; default: BUG(); @@ -613,9 +611,9 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client, } seq_putc(m, ','); } - if (opt->osd_req_flags & CEPH_OSD_FLAG_BALANCE_READS) { + if (opt->read_from_replica == CEPH_OSD_FLAG_BALANCE_READS) { seq_puts(m, "read_from_replica=balance,"); - } else if (opt->osd_req_flags & CEPH_OSD_FLAG_LOCALIZE_READS) { + } else if (opt->read_from_replica == CEPH_OSD_FLAG_LOCALIZE_READS) { seq_puts(m, "read_from_replica=localize,"); } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 4fea3c33af2a..2db8b44e70c2 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -445,8 +445,10 @@ static void target_copy(struct ceph_osd_request_target *dest, dest->size = src->size; dest->min_size = src->min_size; dest->sort_bitwise = src->sort_bitwise; + dest->recovery_deletes = src->recovery_deletes; dest->flags = src->flags; + dest->used_replica = src->used_replica; dest->paused = src->paused; dest->epoch = src->epoch; @@ -1117,10 +1119,10 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, truncate_size, truncate_seq); } - req->r_flags = flags; req->r_base_oloc.pool = layout->pool_id; req->r_base_oloc.pool_ns = ceph_try_get_string(layout->pool_ns); ceph_oid_printf(&req->r_base_oid, "%llx.%08llx", vino.ino, objnum); + req->r_flags = flags | osdc->client->options->read_from_replica; req->r_snapid = vino.snap; if (flags & CEPH_OSD_FLAG_WRITE) @@ -2431,14 +2433,11 @@ promote: static void account_request(struct ceph_osd_request *req) { - struct ceph_osd_client *osdc = req->r_osdc; - WARN_ON(req->r_flags & (CEPH_OSD_FLAG_ACK | CEPH_OSD_FLAG_ONDISK)); WARN_ON(!(req->r_flags & (CEPH_OSD_FLAG_READ | CEPH_OSD_FLAG_WRITE))); req->r_flags |= CEPH_OSD_FLAG_ONDISK; - req->r_flags |= osdc->client->options->osd_req_flags; - atomic_inc(&osdc->num_requests); + atomic_inc(&req->r_osdc->num_requests); req->r_start_stamp = jiffies; req->r_start_latency = ktime_get(); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 83330a6cb242..12fda8f27b08 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4605,7 +4605,11 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb, skb, &fragstolen)) { coalesce_done: - tcp_grow_window(sk, skb); + /* For non sack flows, do not grow window to force DUPACK + * and trigger fast retransmit. + */ + if (tcp_is_sack(tp)) + tcp_grow_window(sk, skb); kfree_skb_partial(skb, fragstolen); skb = NULL; goto add_sack; @@ -4689,7 +4693,11 @@ add_sack: tcp_sack_new_ofo_skb(sk, seq, end_seq); end: if (skb) { - tcp_grow_window(sk, skb); + /* For non sack flows, do not grow window to force DUPACK + * and trigger fast retransmit. + */ + if (tcp_is_sack(tp)) + tcp_grow_window(sk, skb); skb_condense(skb); skb_set_owner_r(skb, sk); } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 7e12d2114158..8cd2782a31e4 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2615,6 +2615,7 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev) idev->mc_list = i->next; write_unlock_bh(&idev->lock); + ip6_mc_clear_src(i); ma_put(i); write_lock_bh(&idev->lock); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 809687d3f410..db56535dfc29 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -135,8 +135,6 @@ static inline __be32 mptcp_option(u8 subopt, u8 len, u8 nib, u8 field) ((nib & 0xF) << 8) | field); } -#define MPTCP_PM_MAX_ADDR 4 - struct mptcp_addr_info { sa_family_t family; __be16 port; @@ -234,10 +232,7 @@ static inline struct mptcp_data_frag *mptcp_rtx_head(const struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - if (list_empty(&msk->rtx_queue)) - return NULL; - - return list_first_entry(&msk->rtx_queue, struct mptcp_data_frag, list); + return list_first_entry_or_null(&msk->rtx_queue, struct mptcp_data_frag, list); } struct mptcp_subflow_request_sock { diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index bf132575040d..bbdb74b8bc3c 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1053,8 +1053,10 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock) err = tcp_set_ulp(sf->sk, "mptcp"); release_sock(sf->sk); - if (err) + if (err) { + sock_release(sf); return err; + } /* the newly created socket really belongs to the owning MPTCP master * socket, even if for additional subflows the allocation is performed diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d7bd8b1f27d5..832eabecfbdd 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -939,7 +939,8 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) filter->mark.mask = 0xffffffff; } } else if (cda[CTA_MARK_MASK]) { - return ERR_PTR(-EINVAL); + err = -EINVAL; + goto err_filter; } #endif if (!cda[CTA_FILTER]) @@ -947,15 +948,17 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone); if (err < 0) - return ERR_PTR(err); + goto err_filter; err = ctnetlink_parse_filter(cda[CTA_FILTER], filter); if (err < 0) - return ERR_PTR(err); + goto err_filter; if (filter->orig_flags) { - if (!cda[CTA_TUPLE_ORIG]) - return ERR_PTR(-EINVAL); + if (!cda[CTA_TUPLE_ORIG]) { + err = -EINVAL; + goto err_filter; + } err = ctnetlink_parse_tuple_filter(cda, &filter->orig, CTA_TUPLE_ORIG, @@ -963,23 +966,32 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) &filter->zone, filter->orig_flags); if (err < 0) - return ERR_PTR(err); + goto err_filter; } if (filter->reply_flags) { - if (!cda[CTA_TUPLE_REPLY]) - return ERR_PTR(-EINVAL); + if (!cda[CTA_TUPLE_REPLY]) { + err = -EINVAL; + goto err_filter; + } err = ctnetlink_parse_tuple_filter(cda, &filter->reply, CTA_TUPLE_REPLY, filter->family, &filter->zone, filter->orig_flags); - if (err < 0) - return ERR_PTR(err); + if (err < 0) { + err = -EINVAL; + goto err_filter; + } } return filter; + +err_filter: + kfree(filter); + + return ERR_PTR(err); } static bool ctnetlink_needs_filter(u8 family, const struct nlattr * const *cda) diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 6a3034f84ab6..afa85171df38 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -387,51 +387,6 @@ static void nf_flow_offload_work_gc(struct work_struct *work) queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ); } -int nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table, - flow_setup_cb_t *cb, void *cb_priv) -{ - struct flow_block *block = &flow_table->flow_block; - struct flow_block_cb *block_cb; - int err = 0; - - down_write(&flow_table->flow_block_lock); - block_cb = flow_block_cb_lookup(block, cb, cb_priv); - if (block_cb) { - err = -EEXIST; - goto unlock; - } - - block_cb = flow_block_cb_alloc(cb, cb_priv, cb_priv, NULL); - if (IS_ERR(block_cb)) { - err = PTR_ERR(block_cb); - goto unlock; - } - - list_add_tail(&block_cb->list, &block->cb_list); - -unlock: - up_write(&flow_table->flow_block_lock); - return err; -} -EXPORT_SYMBOL_GPL(nf_flow_table_offload_add_cb); - -void nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, - flow_setup_cb_t *cb, void *cb_priv) -{ - struct flow_block *block = &flow_table->flow_block; - struct flow_block_cb *block_cb; - - down_write(&flow_table->flow_block_lock); - block_cb = flow_block_cb_lookup(block, cb, cb_priv); - if (block_cb) { - list_del(&block_cb->list); - flow_block_cb_free(block_cb); - } else { - WARN_ON(true); - } - up_write(&flow_table->flow_block_lock); -} -EXPORT_SYMBOL_GPL(nf_flow_table_offload_del_cb); static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff, __be16 port, __be16 new_port) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 073aa1051d43..7647ecfa0d40 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -6550,12 +6550,22 @@ err1: return err; } +static void nft_flowtable_hook_release(struct nft_flowtable_hook *flowtable_hook) +{ + struct nft_hook *this, *next; + + list_for_each_entry_safe(this, next, &flowtable_hook->list, list) { + list_del(&this->list); + kfree(this); + } +} + static int nft_delflowtable_hook(struct nft_ctx *ctx, struct nft_flowtable *flowtable) { const struct nlattr * const *nla = ctx->nla; struct nft_flowtable_hook flowtable_hook; - struct nft_hook *this, *next, *hook; + struct nft_hook *this, *hook; struct nft_trans *trans; int err; @@ -6564,33 +6574,40 @@ static int nft_delflowtable_hook(struct nft_ctx *ctx, if (err < 0) return err; - list_for_each_entry_safe(this, next, &flowtable_hook.list, list) { + list_for_each_entry(this, &flowtable_hook.list, list) { hook = nft_hook_list_find(&flowtable->hook_list, this); if (!hook) { err = -ENOENT; goto err_flowtable_del_hook; } hook->inactive = true; - list_del(&this->list); - kfree(this); } trans = nft_trans_alloc(ctx, NFT_MSG_DELFLOWTABLE, sizeof(struct nft_trans_flowtable)); - if (!trans) - return -ENOMEM; + if (!trans) { + err = -ENOMEM; + goto err_flowtable_del_hook; + } nft_trans_flowtable(trans) = flowtable; nft_trans_flowtable_update(trans) = true; INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); + nft_flowtable_hook_release(&flowtable_hook); list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; err_flowtable_del_hook: - list_for_each_entry(hook, &flowtable_hook.list, list) + list_for_each_entry(this, &flowtable_hook.list, list) { + hook = nft_hook_list_find(&flowtable->hook_list, this); + if (!hook) + break; + hook->inactive = false; + } + nft_flowtable_hook_release(&flowtable_hook); return err; } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 8b5acc6910fd..8c04388296b0 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1242,7 +1242,9 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); } - if (!*this_cpu_ptr(m->scratch) || bsize_max > m->bsize_max) { + if (!*get_cpu_ptr(m->scratch) || bsize_max > m->bsize_max) { + put_cpu_ptr(m->scratch); + err = pipapo_realloc_scratch(m, bsize_max); if (err) return err; @@ -1250,6 +1252,8 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, this_cpu_write(nft_pipapo_scratch_index, false); m->bsize_max = bsize_max; + } else { + put_cpu_ptr(m->scratch); } *ext2 = &e->ext; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 62f416bc0579..b6aad3fc46c3 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -271,12 +271,14 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, if (nft_rbtree_interval_start(new)) { if (nft_rbtree_interval_end(rbe) && - nft_set_elem_active(&rbe->ext, genmask)) + nft_set_elem_active(&rbe->ext, genmask) && + !nft_set_elem_expired(&rbe->ext)) overlap = false; } else { overlap = nft_rbtree_interval_end(rbe) && nft_set_elem_active(&rbe->ext, - genmask); + genmask) && + !nft_set_elem_expired(&rbe->ext); } } else if (d > 0) { p = &parent->rb_right; @@ -284,9 +286,11 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, if (nft_rbtree_interval_end(new)) { overlap = nft_rbtree_interval_end(rbe) && nft_set_elem_active(&rbe->ext, - genmask); + genmask) && + !nft_set_elem_expired(&rbe->ext); } else if (nft_rbtree_interval_end(rbe) && - nft_set_elem_active(&rbe->ext, genmask)) { + nft_set_elem_active(&rbe->ext, genmask) && + !nft_set_elem_expired(&rbe->ext)) { overlap = true; } } else { @@ -294,15 +298,18 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, nft_rbtree_interval_start(new)) { p = &parent->rb_left; - if (nft_set_elem_active(&rbe->ext, genmask)) + if (nft_set_elem_active(&rbe->ext, genmask) && + !nft_set_elem_expired(&rbe->ext)) overlap = false; } else if (nft_rbtree_interval_start(rbe) && nft_rbtree_interval_end(new)) { p = &parent->rb_right; - if (nft_set_elem_active(&rbe->ext, genmask)) + if (nft_set_elem_active(&rbe->ext, genmask) && + !nft_set_elem_expired(&rbe->ext)) overlap = false; - } else if (nft_set_elem_active(&rbe->ext, genmask)) { + } else if (nft_set_elem_active(&rbe->ext, genmask) && + !nft_set_elem_expired(&rbe->ext)) { *ext = &rbe->ext; return -EEXIST; } else { diff --git a/net/rds/ib.h b/net/rds/ib.h index 5ae069d39eab..8dfff43cf07f 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -264,7 +264,13 @@ struct rds_ib_device { int *vector_load; }; -#define ibdev_to_node(ibdev) dev_to_node((ibdev)->dev.parent) +static inline int ibdev_to_node(struct ib_device *ibdev) +{ + struct device *parent; + + parent = ibdev->dev.parent; + return parent ? dev_to_node(parent) : NUMA_NO_NODE; +} #define rdsibdev_to_node(rdsibdev) ibdev_to_node(rdsibdev->dev) /* bits for i_ack_flags */ diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index e29f0f45d688..e9f3576cbf71 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1543,17 +1543,6 @@ static void __exit ct_cleanup_module(void) destroy_workqueue(act_ct_wq); } -void tcf_ct_flow_table_restore_skb(struct sk_buff *skb, unsigned long cookie) -{ - enum ip_conntrack_info ctinfo = cookie & NFCT_INFOMASK; - struct nf_conn *ct; - - ct = (struct nf_conn *)(cookie & NFCT_PTRMASK); - nf_conntrack_get(&ct->ct_general); - nf_ct_set(skb, ct, ctinfo); -} -EXPORT_SYMBOL_GPL(tcf_ct_flow_table_restore_skb); - module_init(ct_init_module); module_exit(ct_cleanup_module); MODULE_AUTHOR("Paul Blakey <paulb@mellanox.com>"); diff --git a/samples/mei/mei-amt-version.c b/samples/mei/mei-amt-version.c index 32234481ad7d..ad3e56042f96 100644 --- a/samples/mei/mei-amt-version.c +++ b/samples/mei/mei-amt-version.c @@ -267,7 +267,7 @@ struct amt_host_if_msg_header { struct amt_host_if_resp_header { struct amt_host_if_msg_header header; uint32_t status; - unsigned char data[0]; + unsigned char data[]; } __attribute__((packed)); const uuid_le MEI_IAMTHIF = UUID_LE(0x12f80028, 0xb4b7, 0x4b2d, \ diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh index 13e5fbafdf2f..66a6d511b524 100755 --- a/scripts/decode_stacktrace.sh +++ b/scripts/decode_stacktrace.sh @@ -27,7 +27,10 @@ parse_symbol() { elif [[ "${modcache[$module]+isset}" == "isset" ]]; then local objfile=${modcache[$module]} else - [[ $modpath == "" ]] && return + if [[ $modpath == "" ]]; then + echo "WARNING! Modules path isn't set, but is needed to parse this symbol" >&2 + return + fi local objfile=$(find "$modpath" -name "${module//_/[-_]}.ko*" -print -quit) [[ $objfile == "" ]] && return modcache[$module]=$objfile diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h index 298b73794d8b..16c1894c29bb 100644 --- a/security/integrity/integrity.h +++ b/security/integrity/integrity.h @@ -107,7 +107,7 @@ struct ima_digest_data { } ng; u8 data[2]; } xattr; - u8 digest[0]; + u8 digest[]; } __packed; /* @@ -119,7 +119,7 @@ struct signature_v2_hdr { uint8_t hash_algo; /* Digest algorithm [enum hash_algo] */ __be32 keyid; /* IMA key identifier - not X509/PGP specific */ __be16 sig_size; /* signature size */ - uint8_t sig[0]; /* signature payload */ + uint8_t sig[]; /* signature payload */ } __packed; /* integrity data associated with an inode */ diff --git a/sound/soc/sof/probe.h b/sound/soc/sof/probe.h index b04b728c7224..5e159ab239fa 100644 --- a/sound/soc/sof/probe.h +++ b/sound/soc/sof/probe.h @@ -36,7 +36,7 @@ struct sof_probe_point_desc { struct sof_ipc_probe_dma_add_params { struct sof_ipc_cmd_hdr hdr; unsigned int num_elems; - struct sof_probe_dma dma[0]; + struct sof_probe_dma dma[]; } __packed; struct sof_ipc_probe_info_params { @@ -51,19 +51,19 @@ struct sof_ipc_probe_info_params { struct sof_ipc_probe_dma_remove_params { struct sof_ipc_cmd_hdr hdr; unsigned int num_elems; - unsigned int stream_tag[0]; + unsigned int stream_tag[]; } __packed; struct sof_ipc_probe_point_add_params { struct sof_ipc_cmd_hdr hdr; unsigned int num_elems; - struct sof_probe_point_desc desc[0]; + struct sof_probe_point_desc desc[]; } __packed; struct sof_ipc_probe_point_remove_params { struct sof_ipc_cmd_hdr hdr; unsigned int num_elems; - unsigned int buffer_id[0]; + unsigned int buffer_id[]; } __packed; int sof_ipc_probe_init(struct snd_sof_dev *sdev, diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index db189945e9b0..02dabc9e77b0 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -362,6 +362,7 @@ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ #define X86_FEATURE_FSRM (18*32+ 4) /* Fast Short Rep Mov */ #define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */ +#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* "" SRBDS mitigation MSR available */ #define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ #define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ @@ -407,5 +408,6 @@ #define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ #define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ +#define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index ef452b817f44..e8370e64a155 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -128,6 +128,10 @@ #define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ #define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ +/* SRBDS support */ +#define MSR_IA32_MCU_OPT_CTRL 0x00000123 +#define RNGDS_MITG_DIS BIT(0) + #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 #define MSR_IA32_SYSENTER_EIP 0x00000176 diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 43e24903812c..17c5a038f42d 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -385,33 +385,48 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4) #define KVM_STATE_NESTED_FORMAT_VMX 0 -#define KVM_STATE_NESTED_FORMAT_SVM 1 /* unused */ +#define KVM_STATE_NESTED_FORMAT_SVM 1 #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 #define KVM_STATE_NESTED_EVMCS 0x00000004 #define KVM_STATE_NESTED_MTF_PENDING 0x00000008 +#define KVM_STATE_NESTED_GIF_SET 0x00000100 #define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_SMM_VMXON 0x00000002 #define KVM_STATE_NESTED_VMX_VMCS_SIZE 0x1000 +#define KVM_STATE_NESTED_SVM_VMCB_SIZE 0x1000 + +#define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001 + struct kvm_vmx_nested_state_data { __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; __u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; - __u64 preemption_timer_deadline; }; struct kvm_vmx_nested_state_hdr { + __u32 flags; __u64 vmxon_pa; __u64 vmcs12_pa; + __u64 preemption_timer_deadline; struct { __u16 flags; } smm; }; +struct kvm_svm_nested_state_data { + /* Save area only used if KVM_STATE_NESTED_RUN_PENDING. */ + __u8 vmcb12[KVM_STATE_NESTED_SVM_VMCB_SIZE]; +}; + +struct kvm_svm_nested_state_hdr { + __u64 vmcb_pa; +}; + /* for KVM_CAP_NESTED_STATE */ struct kvm_nested_state { __u16 flags; @@ -420,6 +435,7 @@ struct kvm_nested_state { union { struct kvm_vmx_nested_state_hdr vmx; + struct kvm_svm_nested_state_hdr svm; /* Pad the header to 128 bytes. */ __u8 pad[120]; @@ -432,6 +448,7 @@ struct kvm_nested_state { */ union { struct kvm_vmx_nested_state_data vmx[0]; + struct kvm_svm_nested_state_data svm[0]; } data; }; diff --git a/tools/arch/x86/include/uapi/asm/unistd.h b/tools/arch/x86/include/uapi/asm/unistd.h index 30d7d04d72d6..be5e2e747f50 100644 --- a/tools/arch/x86/include/uapi/asm/unistd.h +++ b/tools/arch/x86/include/uapi/asm/unistd.h @@ -2,7 +2,14 @@ #ifndef _UAPI_ASM_X86_UNISTD_H #define _UAPI_ASM_X86_UNISTD_H -/* x32 syscall flag bit */ +/* + * x32 syscall flag bit. Some user programs expect syscall NR macros + * and __X32_SYSCALL_BIT to have type int, even though syscall numbers + * are, for practical purposes, unsigned long. + * + * Fortunately, expressions like (nr & ~__X32_SYSCALL_BIT) do the right + * thing regardless. + */ #define __X32_SYSCALL_BIT 0x40000000 #ifndef __KERNEL__ diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index e95b72ec19bc..b8ff9e8ac0d5 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -150,6 +150,9 @@ { EXIT_REASON_UMWAIT, "UMWAIT" }, \ { EXIT_REASON_TPAUSE, "TPAUSE" } +#define VMX_EXIT_REASON_FLAGS \ + { VMX_EXIT_REASONS_FAILED_VMENTRY, "FAILED_VMENTRY" } + #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2 #define VMX_ABORT_LOAD_HOST_MSR_FAIL 4 diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 3a3201e4618e..f4a01305d9a6 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -855,9 +855,11 @@ __SYSCALL(__NR_clone3, sys_clone3) __SYSCALL(__NR_openat2, sys_openat2) #define __NR_pidfd_getfd 438 __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) +#define __NR_faccessat2 439 +__SYSCALL(__NR_faccessat2, sys_faccessat2) #undef __NR_syscalls -#define __NR_syscalls 439 +#define __NR_syscalls 440 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 2813e579b480..14b67cd6b54b 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -1969,6 +1969,30 @@ enum drm_i915_perf_property_id { */ DRM_I915_PERF_PROP_HOLD_PREEMPTION, + /** + * Specifying this pins all contexts to the specified SSEU power + * configuration for the duration of the recording. + * + * This parameter's value is a pointer to a struct + * drm_i915_gem_context_param_sseu. + * + * This property is available in perf revision 4. + */ + DRM_I915_PERF_PROP_GLOBAL_SSEU, + + /** + * This optional parameter specifies the timer interval in nanoseconds + * at which the i915 driver will check the OA buffer for available data. + * Minimum allowed value is 100 microseconds. A default value is used by + * the driver if this parameter is not specified. Note that larger timer + * values will reduce cpu consumption during OA perf captures. However, + * excessively large values would potentially result in OA buffer + * overwrites as captures reach end of the OA buffer. + * + * This property is available in perf revision 5. + */ + DRM_I915_PERF_PROP_POLL_OA_PERIOD, + DRM_I915_PERF_PROP_MAX /* non-ABI */ }; diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h index ca88b7bce553..2f86b2ad6d7e 100644 --- a/tools/include/uapi/linux/fcntl.h +++ b/tools/include/uapi/linux/fcntl.h @@ -84,10 +84,20 @@ #define DN_ATTRIB 0x00000020 /* File changed attibutes */ #define DN_MULTISHOT 0x80000000 /* Don't remove notifier */ +/* + * The constants AT_REMOVEDIR and AT_EACCESS have the same value. AT_EACCESS is + * meaningful only to faccessat, while AT_REMOVEDIR is meaningful only to + * unlinkat. The two functions do completely different things and therefore, + * the flags can be allowed to overlap. For example, passing AT_REMOVEDIR to + * faccessat would be undefined behavior and thus treating it equivalent to + * AT_EACCESS is valid undefined behavior. + */ #define AT_FDCWD -100 /* Special value used to indicate openat should use the current working directory. */ #define AT_SYMLINK_NOFOLLOW 0x100 /* Do not follow symbolic links. */ +#define AT_EACCESS 0x200 /* Test access permitted for + effective IDs, not real IDs. */ #define AT_REMOVEDIR 0x200 /* Remove directory instead of unlinking file. */ #define AT_SYMLINK_FOLLOW 0x400 /* Follow symbolic links. */ diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h index 379a612f8f1d..f44eb0a04afd 100644 --- a/tools/include/uapi/linux/fs.h +++ b/tools/include/uapi/linux/fs.h @@ -262,6 +262,7 @@ struct fsxattr { #define FS_EA_INODE_FL 0x00200000 /* Inode used for large EA */ #define FS_EOFBLOCKS_FL 0x00400000 /* Reserved for ext4 */ #define FS_NOCOW_FL 0x00800000 /* Do not cow file */ +#define FS_DAX_FL 0x02000000 /* Inode is DAX */ #define FS_INLINE_DATA_FL 0x10000000 /* Reserved for ext4 */ #define FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ #define FS_CASEFOLD_FL 0x40000000 /* Folder is case insensitive */ diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h index a10e3cdc2839..7875709ccfeb 100644 --- a/tools/include/uapi/linux/fscrypt.h +++ b/tools/include/uapi/linux/fscrypt.h @@ -19,7 +19,8 @@ #define FSCRYPT_POLICY_FLAGS_PAD_MASK 0x03 #define FSCRYPT_POLICY_FLAG_DIRECT_KEY 0x04 #define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 0x08 -#define FSCRYPT_POLICY_FLAGS_VALID 0x0F +#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32 0x10 +#define FSCRYPT_POLICY_FLAGS_VALID 0x1F /* Encryption algorithms */ #define FSCRYPT_MODE_AES_256_XTS 1 diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index fdd632c833b4..4fdf30316582 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -188,10 +188,13 @@ struct kvm_s390_cmma_log { struct kvm_hyperv_exit { #define KVM_EXIT_HYPERV_SYNIC 1 #define KVM_EXIT_HYPERV_HCALL 2 +#define KVM_EXIT_HYPERV_SYNDBG 3 __u32 type; + __u32 pad1; union { struct { __u32 msr; + __u32 pad2; __u64 control; __u64 evt_page; __u64 msg_page; @@ -201,6 +204,15 @@ struct kvm_hyperv_exit { __u64 result; __u64 params[2]; } hcall; + struct { + __u32 msr; + __u32 pad2; + __u64 control; + __u64 status; + __u64 send_page; + __u64 recv_page; + __u64 pending_page; + } syndbg; } u; }; @@ -1017,6 +1029,8 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_VCPU_RESETS 179 #define KVM_CAP_S390_PROTECTED 180 #define KVM_CAP_PPC_SECURE_GUEST 181 +#define KVM_CAP_HALT_POLL 182 +#define KVM_CAP_ASYNC_PF_INT 183 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h index d1192783139a..82cc58fe9368 100644 --- a/tools/include/uapi/linux/stat.h +++ b/tools/include/uapi/linux/stat.h @@ -123,7 +123,10 @@ struct statx { __u32 stx_dev_major; /* ID of device containing file [uncond] */ __u32 stx_dev_minor; /* 0x90 */ - __u64 __spare2[14]; /* Spare space for future expansion */ + __u64 stx_mnt_id; + __u64 __spare2; + /* 0xa0 */ + __u64 __spare3[12]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -148,6 +151,7 @@ struct statx { #define STATX_BLOCKS 0x00000400U /* Want/got stx_blocks */ #define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */ #define STATX_BTIME 0x00000800U /* Want/got stx_btime */ +#define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ @@ -177,7 +181,9 @@ struct statx { #define STATX_ATTR_NODUMP 0x00000040 /* [I] File is not to be dumped */ #define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */ #define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */ +#define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ +#define STATX_ATTR_DAX 0x00002000 /* [I] File is DAX */ #endif /* _UAPI_LINUX_STAT_H */ diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index 9fe72e4b1373..0c2349612e77 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -15,6 +15,8 @@ #include <linux/types.h> #include <linux/ioctl.h> +#define VHOST_FILE_UNBIND -1 + /* ioctls */ #define VHOST_VIRTIO 0xAF @@ -140,4 +142,6 @@ /* Get the max ring size. */ #define VHOST_VDPA_GET_VRING_NUM _IOR(VHOST_VIRTIO, 0x76, __u16) +/* Set event fd for config interrupt*/ +#define VHOST_VDPA_SET_CONFIG_CALL _IOW(VHOST_VIRTIO, 0x77, int) #endif diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index e1bd2a93c6db..5b36c589a029 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -1425,13 +1425,28 @@ static unsigned int type_size(const char *name) return 0; } +static int append(char **buf, const char *delim, const char *str) +{ + char *new_buf; + + new_buf = realloc(*buf, strlen(*buf) + strlen(delim) + strlen(str) + 1); + if (!new_buf) + return -1; + strcat(new_buf, delim); + strcat(new_buf, str); + *buf = new_buf; + return 0; +} + static int event_read_fields(struct tep_event *event, struct tep_format_field **fields) { struct tep_format_field *field = NULL; enum tep_event_type type; char *token; char *last_token; + char *delim = " "; int count = 0; + int ret; do { unsigned int size_dynamic = 0; @@ -1490,24 +1505,51 @@ static int event_read_fields(struct tep_event *event, struct tep_format_field ** field->flags |= TEP_FIELD_IS_POINTER; if (field->type) { - char *new_type; - new_type = realloc(field->type, - strlen(field->type) + - strlen(last_token) + 2); - if (!new_type) { - free(last_token); - goto fail; - } - field->type = new_type; - strcat(field->type, " "); - strcat(field->type, last_token); + ret = append(&field->type, delim, last_token); free(last_token); + if (ret < 0) + goto fail; } else field->type = last_token; last_token = token; + delim = " "; continue; } + /* Handle __attribute__((user)) */ + if ((type == TEP_EVENT_DELIM) && + strcmp("__attribute__", last_token) == 0 && + token[0] == '(') { + int depth = 1; + int ret; + + ret = append(&field->type, " ", last_token); + ret |= append(&field->type, "", "("); + if (ret < 0) + goto fail; + + delim = " "; + while ((type = read_token(&token)) != TEP_EVENT_NONE) { + if (type == TEP_EVENT_DELIM) { + if (token[0] == '(') + depth++; + else if (token[0] == ')') + depth--; + if (!depth) + break; + ret = append(&field->type, "", token); + delim = ""; + } else { + ret = append(&field->type, delim, token); + delim = " "; + } + if (ret < 0) + goto fail; + free(last_token); + last_token = token; + } + continue; + } break; } @@ -1523,8 +1565,6 @@ static int event_read_fields(struct tep_event *event, struct tep_format_field ** if (strcmp(token, "[") == 0) { enum tep_event_type last_type = type; char *brackets = token; - char *new_brackets; - int len; field->flags |= TEP_FIELD_IS_ARRAY; @@ -1536,29 +1576,27 @@ static int event_read_fields(struct tep_event *event, struct tep_format_field ** field->arraylen = 0; while (strcmp(token, "]") != 0) { + const char *delim; + if (last_type == TEP_EVENT_ITEM && type == TEP_EVENT_ITEM) - len = 2; + delim = " "; else - len = 1; + delim = ""; + last_type = type; - new_brackets = realloc(brackets, - strlen(brackets) + - strlen(token) + len); - if (!new_brackets) { + ret = append(&brackets, delim, token); + if (ret < 0) { free(brackets); goto fail; } - brackets = new_brackets; - if (len == 2) - strcat(brackets, " "); - strcat(brackets, token); /* We only care about the last token */ field->arraylen = strtoul(token, NULL, 0); free_token(token); type = read_token(&token); if (type == TEP_EVENT_NONE) { + free(brackets); do_warning_event(event, "failed to find token"); goto fail; } @@ -1566,13 +1604,11 @@ static int event_read_fields(struct tep_event *event, struct tep_format_field ** free_token(token); - new_brackets = realloc(brackets, strlen(brackets) + 2); - if (!new_brackets) { + ret = append(&brackets, "", "]"); + if (ret < 0) { free(brackets); goto fail; } - brackets = new_brackets; - strcat(brackets, "]"); /* add brackets to type */ @@ -1582,34 +1618,23 @@ static int event_read_fields(struct tep_event *event, struct tep_format_field ** * the format: type [] item; */ if (type == TEP_EVENT_ITEM) { - char *new_type; - new_type = realloc(field->type, - strlen(field->type) + - strlen(field->name) + - strlen(brackets) + 2); - if (!new_type) { + ret = append(&field->type, " ", field->name); + if (ret < 0) { free(brackets); goto fail; } - field->type = new_type; - strcat(field->type, " "); - strcat(field->type, field->name); + ret = append(&field->type, "", brackets); + size_dynamic = type_size(field->name); free_token(field->name); - strcat(field->type, brackets); field->name = field->alias = token; type = read_token(&token); } else { - char *new_type; - new_type = realloc(field->type, - strlen(field->type) + - strlen(brackets) + 1); - if (!new_type) { + ret = append(&field->type, "", brackets); + if (ret < 0) { free(brackets); goto fail; } - field->type = new_type; - strcat(field->type, brackets); } free(brackets); } @@ -2046,19 +2071,16 @@ process_op(struct tep_event *event, struct tep_print_arg *arg, char **tok) /* could just be a type pointer */ if ((strcmp(arg->op.op, "*") == 0) && type == TEP_EVENT_DELIM && (strcmp(token, ")") == 0)) { - char *new_atom; + int ret; if (left->type != TEP_PRINT_ATOM) { do_warning_event(event, "bad pointer type"); goto out_free; } - new_atom = realloc(left->atom.atom, - strlen(left->atom.atom) + 3); - if (!new_atom) + ret = append(&left->atom.atom, " ", "*"); + if (ret < 0) goto out_warn_free; - left->atom.atom = new_atom; - strcat(left->atom.atom, " *"); free(arg->op.op); *arg = *left; free(left); @@ -3063,6 +3085,37 @@ err: } static enum tep_event_type +process_builtin_expect(struct tep_event *event, struct tep_print_arg *arg, char **tok) +{ + enum tep_event_type type; + char *token = NULL; + + /* Handle __builtin_expect( cond, #) */ + type = process_arg(event, arg, &token); + + if (type != TEP_EVENT_DELIM || token[0] != ',') + goto out_free; + + free_token(token); + + /* We don't care what the second parameter is of the __builtin_expect() */ + if (read_expect_type(TEP_EVENT_ITEM, &token) < 0) + goto out_free; + + if (read_expected(TEP_EVENT_DELIM, ")") < 0) + goto out_free; + + free_token(token); + type = read_token_item(tok); + return type; + +out_free: + free_token(token); + *tok = NULL; + return TEP_EVENT_ERROR; +} + +static enum tep_event_type process_function(struct tep_event *event, struct tep_print_arg *arg, char *token, char **tok) { @@ -3106,6 +3159,10 @@ process_function(struct tep_event *event, struct tep_print_arg *arg, free_token(token); return process_dynamic_array_len(event, arg, tok); } + if (strcmp(token, "__builtin_expect") == 0) { + free_token(token); + return process_builtin_expect(event, arg, tok); + } func = find_func_handler(event->tep, token); if (func) { @@ -3151,18 +3208,15 @@ process_arg_token(struct tep_event *event, struct tep_print_arg *arg, } /* atoms can be more than one token long */ while (type == TEP_EVENT_ITEM) { - char *new_atom; - new_atom = realloc(atom, - strlen(atom) + strlen(token) + 2); - if (!new_atom) { + int ret; + + ret = append(&atom, " ", token); + if (ret < 0) { free(atom); *tok = NULL; free_token(token); return TEP_EVENT_ERROR; } - atom = new_atom; - strcat(atom, " "); - strcat(atom, token); free_token(token); type = read_token_item(&token); } diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 877ca6be0ed0..513633809c81 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -396,6 +396,18 @@ else NO_LIBBPF := 1 NO_JVMTI := 1 else + ifneq ($(filter s% -fsanitize=address%,$(EXTRA_CFLAGS),),) + ifneq ($(shell ldconfig -p | grep libasan >/dev/null 2>&1; echo $$?), 0) + msg := $(error No libasan found, please install libasan); + endif + endif + + ifneq ($(filter s% -fsanitize=undefined%,$(EXTRA_CFLAGS),),) + ifneq ($(shell ldconfig -p | grep libubsan >/dev/null 2>&1; echo $$?), 0) + msg := $(error No libubsan found, please install libubsan); + endif + endif + ifneq ($(filter s% -static%,$(LDFLAGS),),) msg := $(error No static glibc found, please install glibc-static); else diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 37b844f839bc..78847b32e137 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -359,6 +359,7 @@ 435 common clone3 sys_clone3 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index b63b3fb2de70..5f1d2a878fad 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -478,8 +478,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report if (rep->time_str) ret += fprintf(fp, " (time slices: %s)", rep->time_str); - if (symbol_conf.show_ref_callgraph && - strstr(evname, "call-graph=no")) { + if (symbol_conf.show_ref_callgraph && evname && strstr(evname, "call-graph=no")) { ret += fprintf(fp, ", show reference callgraph"); } diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 5da243676f12..181d65e5a450 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3837,6 +3837,9 @@ int cmd_script(int argc, const char **argv) if (err) goto out_delete; + if (zstd_init(&(session->zstd_data), 0) < 0) + pr_warning("Decompression initialization failed. Reported data may be incomplete.\n"); + err = __cmd_script(&script); flush_scripting(); diff --git a/tools/perf/trace/beauty/statx.c b/tools/perf/trace/beauty/statx.c index 811cc0eeb2d5..110f0c609d84 100644 --- a/tools/perf/trace/beauty/statx.c +++ b/tools/perf/trace/beauty/statx.c @@ -65,6 +65,7 @@ size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_a P_FLAG(SIZE); P_FLAG(BLOCKS); P_FLAG(BTIME); + P_FLAG(MNT_ID); #undef P_FLAG diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c index b020a8678eb9..9887ae09242d 100644 --- a/tools/perf/util/bpf-prologue.c +++ b/tools/perf/util/bpf-prologue.c @@ -142,7 +142,8 @@ static int gen_read_mem(struct bpf_insn_pos *pos, int src_base_addr_reg, int dst_addr_reg, - long offset) + long offset, + int probeid) { /* mov arg3, src_base_addr_reg */ if (src_base_addr_reg != BPF_REG_ARG3) @@ -159,7 +160,7 @@ gen_read_mem(struct bpf_insn_pos *pos, ins(BPF_MOV64_REG(BPF_REG_ARG1, dst_addr_reg), pos); /* Call probe_read */ - ins(BPF_EMIT_CALL(BPF_FUNC_probe_read), pos); + ins(BPF_EMIT_CALL(probeid), pos); /* * Error processing: if read fail, goto error code, * will be relocated. Target should be the start of @@ -241,7 +242,7 @@ static int gen_prologue_slowpath(struct bpf_insn_pos *pos, struct probe_trace_arg *args, int nargs) { - int err, i; + int err, i, probeid; for (i = 0; i < nargs; i++) { struct probe_trace_arg *arg = &args[i]; @@ -276,11 +277,16 @@ gen_prologue_slowpath(struct bpf_insn_pos *pos, stack_offset), pos); ref = arg->ref; + probeid = BPF_FUNC_probe_read_kernel; while (ref) { pr_debug("prologue: arg %d: offset %ld\n", i, ref->offset); + + if (ref->user_access) + probeid = BPF_FUNC_probe_read_user; + err = gen_read_mem(pos, BPF_REG_3, BPF_REG_7, - ref->offset); + ref->offset, probeid); if (err) { pr_err("prologue: failed to generate probe_read function call\n"); goto errout; diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index c4ca932d092d..acef87d9af58 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -26,7 +26,7 @@ do { \ YYABORT; \ } while (0) -static struct list_head* alloc_list() +static struct list_head* alloc_list(void) { struct list_head *list; @@ -349,7 +349,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc struct list_head *list; char pmu_name[128]; - snprintf(&pmu_name, 128, "%s-%s", $1, $3); + snprintf(pmu_name, sizeof(pmu_name), "%s-%s", $1, $3); free($1); free($3); if (parse_events_multi_pmu_add(_parse_state, pmu_name, &list) < 0) diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 85e0c7f2515c..f971d9aa4570 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -86,7 +86,6 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, struct perf_pmu_info *info); struct list_head *perf_pmu__alias(struct perf_pmu *pmu, struct list_head *head_terms); -int perf_pmu_wrap(void); void perf_pmu_error(struct list_head *list, char *name, char const *msg); int perf_pmu__new_format(struct list_head *list, char *name, diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index a08f373d3305..df713a5d1e26 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -1575,7 +1575,7 @@ static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg) } tmp = strchr(str, '@'); - if (tmp && tmp != str && strcmp(tmp + 1, "user")) { /* user attr */ + if (tmp && tmp != str && !strcmp(tmp + 1, "user")) { /* user attr */ if (!user_access_is_supported()) { semantic_error("ftrace does not support user access\n"); return -EINVAL; @@ -1995,7 +1995,10 @@ static int __synthesize_probe_trace_arg_ref(struct probe_trace_arg_ref *ref, if (depth < 0) return depth; } - err = strbuf_addf(buf, "%+ld(", ref->offset); + if (ref->user_access) + err = strbuf_addf(buf, "%s%ld(", "+u", ref->offset); + else + err = strbuf_addf(buf, "%+ld(", ref->offset); return (err < 0) ? err : depth; } diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 8c852948513e..064b63a6a3f3 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -1044,7 +1044,7 @@ static struct { DEFINE_TYPE(FTRACE_README_PROBE_TYPE_X, "*type: * x8/16/32/64,*"), DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"), DEFINE_TYPE(FTRACE_README_UPROBE_REF_CTR, "*ref_ctr_offset*"), - DEFINE_TYPE(FTRACE_README_USER_ACCESS, "*[u]<offset>*"), + DEFINE_TYPE(FTRACE_README_USER_ACCESS, "*u]<offset>*"), DEFINE_TYPE(FTRACE_README_MULTIPROBE_EVENT, "*Create/append/*"), DEFINE_TYPE(FTRACE_README_IMMEDIATE_VALUE, "*\\imm-value,*"), }; diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 3c6976f7574c..57d0706e1330 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -668,7 +668,7 @@ static void print_aggr(struct perf_stat_config *config, int s; bool first; - if (!(config->aggr_map || config->aggr_get_id)) + if (!config->aggr_map || !config->aggr_get_id) return; aggr_update_shadow(config, evlist); @@ -1169,7 +1169,7 @@ static void print_percore(struct perf_stat_config *config, int s; bool first = true; - if (!(config->aggr_map || config->aggr_get_id)) + if (!config->aggr_map || !config->aggr_get_id) return; if (config->percore_show_thread) diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h index db3c07beb9d1..b5f7a996c4d0 100644 --- a/tools/testing/nvdimm/test/nfit_test.h +++ b/tools/testing/nvdimm/test/nfit_test.h @@ -51,7 +51,7 @@ struct nd_cmd_translate_spa { __u32 nfit_device_handle; __u32 _reserved; __u64 dpa; - } __packed devices[0]; + } __packed devices[]; } __packed; @@ -74,7 +74,7 @@ struct nd_cmd_ars_err_inj_stat { struct nd_error_stat_query_record { __u64 err_inj_stat_spa_range_base; __u64 err_inj_stat_spa_range_length; - } __packed record[0]; + } __packed record[]; } __packed; #define ND_INTEL_SMART 1 @@ -180,7 +180,7 @@ struct nd_intel_fw_send_data { __u32 context; __u32 offset; __u32 length; - __u8 data[0]; + __u8 data[]; /* this field is not declared due ot variable data from input */ /* __u32 status; */ } __packed; |