diff --git a/Documentation/devicetree/bindings/net/can/tcan4x5x.txt b/Documentation/devicetree/bindings/net/can/tcan4x5x.txt index 0968b40aef1e..e3501bfa22e9 100644 --- a/Documentation/devicetree/bindings/net/can/tcan4x5x.txt +++ b/Documentation/devicetree/bindings/net/can/tcan4x5x.txt @@ -31,7 +31,7 @@ tcan4x5x: tcan4x5x@0 { #address-cells = <1>; #size-cells = <1>; spi-max-frequency = <10000000>; - bosch,mram-cfg = <0x0 0 0 32 0 0 1 1>; + bosch,mram-cfg = <0x0 0 0 16 0 0 1 1>; interrupt-parent = <&gpio1>; interrupts = <14 IRQ_TYPE_LEVEL_LOW>; device-state-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; diff --git a/Makefile b/Makefile index fa98893aae61..c43133c8a5b1 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 95 +SUBLEVEL = 96 EXTRAVERSION = NAME = Dare mighty things

diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 4999caff3281..22275d8518eb 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -511,34 +511,26 @@ static void entry_task_switch(struct task_struct *next)

/* * ARM erratum 1418040 handling, affecting the 32bit view of CNTVCT. - * Assuming the virtual counter is enabled at the beginning of times: - * - * - disable access when switching from a 64bit task to a 32bit task - * - enable access when switching from a 32bit task to a 64bit task + * Ensure access is disabled when switching to a 32bit task, ensure + * access is enabled when switching to a 64bit task. */ -static void erratum_1418040_thread_switch(struct task_struct *prev, - struct task_struct *next) +static void erratum_1418040_thread_switch(struct task_struct *next) { - bool prev32, next32; - u64 val; - - if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040)) - return; - - prev32 = is_compat_thread(task_thread_info(prev)); - next32 = is_compat_thread(task_thread_info(next)); - - if (prev32 == next32 || !this_cpu_has_cap(ARM64_WORKAROUND_1418040)) + if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) || + !this_cpu_has_cap(ARM64_WORKAROUND_1418040)) return;

- val = read_sysreg(cntkctl_el1); - - if (!next32) - val |= ARCH_TIMER_USR_VCT_ACCESS_EN; + if (is_compat_thread(task_thread_info(next))) + sysreg_clear_set(cntkctl_el1, ARCH_TIMER_USR_VCT_ACCESS_EN, 0); else - val &= ~ARCH_TIMER_USR_VCT_ACCESS_EN; + sysreg_clear_set(cntkctl_el1, 0, ARCH_TIMER_USR_VCT_ACCESS_EN); +}

- write_sysreg(val, cntkctl_el1); +static void erratum_1418040_new_exec(void) +{ + preempt_disable(); + erratum_1418040_thread_switch(current); + preempt_enable(); }

/* @@ -556,7 +548,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, entry_task_switch(next); uao_thread_switch(next); ssbs_thread_switch(next); - erratum_1418040_thread_switch(prev, next); + erratum_1418040_thread_switch(next);

/* * Complete any pending TLB or cache maintenance on this CPU in case @@ -622,6 +614,7 @@ void arch_setup_new_exec(void) current->mm->context.flags = is_compat_task() ? MMCF_AARCH32 : 0;

ptrauth_thread_init_user(current); + erratum_1418040_new_exec();

if (task_spec_ssb_noexec(current)) { arch_prctl_spec_ctrl_set(current, PR_SPEC_STORE_BYPASS, diff --git a/arch/powerpc/include/asm/book3s/32/mmu-hash.h b/arch/powerpc/include/asm/book3s/32/mmu-hash.h index a8982d52f6b1..cbde06d0fb38 100644 --- a/arch/powerpc/include/asm/book3s/32/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/32/mmu-hash.h @@ -102,6 +102,8 @@ extern s32 patch__hash_page_B, patch__hash_page_C; extern s32 patch__flush_hash_A0, patch__flush_hash_A1, patch__flush_hash_A2; extern s32 patch__flush_hash_B;

+int __init find_free_bat(void); +unsigned int bat_block_size(unsigned long base, unsigned long top); #endif /* !__ASSEMBLY__ */

/* We happily ignore the smaller BATs on 601, we don't actually use diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index a6e3700c4566..f0c0816f5727 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -449,6 +449,7 @@ #define PPC_RAW_LDX(r, base, b) (0x7c00002a | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_RAW_LHZ(r, base, i) (0xa0000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) #define PPC_RAW_LHBRX(r, base, b) (0x7c00062c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) +#define PPC_RAW_LWBRX(r, base, b) (0x7c00042c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_RAW_LDBRX(r, base, b) (0x7c000428 | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_RAW_STWCX(s, a, b) (0x7c00012d | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_RAW_CMPWI(a, i) (0x2c000000 | ___PPC_RA(a) | IMM_L(i)) diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index fe2ef598e2ea..376104c166fc 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -11,6 +11,7 @@ CFLAGS_prom_init.o += -fPIC CFLAGS_btext.o += -fPIC endif

+CFLAGS_early_32.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_cputable.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_prom_init.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 58991233381e..0697a0e014ae 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -19,6 +19,9 @@ CFLAGS_code-patching.o += -DDISABLE_BRANCH_PROFILING CFLAGS_feature-fixups.o += -DDISABLE_BRANCH_PROFILING endif

+CFLAGS_code-patching.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) +CFLAGS_feature-fixups.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) + obj-y += alloc.o code-patching.o feature-fixups.o pmem.o inst.o test_code-patching.o

ifndef CONFIG_KASAN diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index a59e7ec98180..602ab13127b4 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -72,7 +72,7 @@ unsigned long p_block_mapped(phys_addr_t pa) return 0; }

-static int find_free_bat(void) +int __init find_free_bat(void) { int b; int n = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4; @@ -96,7 +96,7 @@ static int find_free_bat(void) * - block size has to be a power of two. This is calculated by finding the * highest bit set to 1. */ -static unsigned int block_size(unsigned long base, unsigned long top) +unsigned int bat_block_size(unsigned long base, unsigned long top) { unsigned int max_size = SZ_256M; unsigned int base_shift = (ffs(base) - 1) & 31; @@ -141,7 +141,7 @@ static unsigned long __init __mmu_mapin_ram(unsigned long base, unsigned long to int idx;

while ((idx = find_free_bat()) != -1 && base != top) { - unsigned int size = block_size(base, top); + unsigned int size = bat_block_size(base, top);

if (size < 128 << 10) break; @@ -201,18 +201,17 @@ void mmu_mark_initmem_nx(void) int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4; int i; unsigned long base = (unsigned long)_stext - PAGE_OFFSET; - unsigned long top = (unsigned long)_etext - PAGE_OFFSET; + unsigned long top = ALIGN((unsigned long)_etext - PAGE_OFFSET, SZ_128K); unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET; unsigned long size;

- for (i = 0; i < nb - 1 && base < top && top - base > (128 << 10);) { - size = block_size(base, top); + for (i = 0; i < nb - 1 && base < top;) { + size = bat_block_size(base, top); setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT); base += size; } if (base < top) { - size = block_size(base, top); - size = max(size, 128UL << 10); + size = bat_block_size(base, top); if ((top - base) > size) { size <<= 1; if (strict_kernel_rwx_enabled() && base + size > border) diff --git a/arch/powerpc/mm/kasan/book3s_32.c b/arch/powerpc/mm/kasan/book3s_32.c index 35b287b0a8da..450a67ef0bbe 100644 --- a/arch/powerpc/mm/kasan/book3s_32.c +++ b/arch/powerpc/mm/kasan/book3s_32.c @@ -10,48 +10,51 @@ int __init kasan_init_region(void *start, size_t size) { unsigned long k_start = (unsigned long)kasan_mem_to_shadow(start); unsigned long k_end = (unsigned long)kasan_mem_to_shadow(start + size); - unsigned long k_cur = k_start; - int k_size = k_end - k_start; - int k_size_base = 1 << (ffs(k_size) - 1); + unsigned long k_nobat = k_start; + unsigned long k_cur; + phys_addr_t phys; int ret; - void *block;

- block = memblock_alloc(k_size, k_size_base); - - if (block && k_size_base >= SZ_128K && k_start == ALIGN(k_start, k_size_base)) { - int shift = ffs(k_size - k_size_base); - int k_size_more = shift ? 1 << (shift - 1) : 0; - - setbat(-1, k_start, __pa(block), k_size_base, PAGE_KERNEL); - if (k_size_more >= SZ_128K) - setbat(-1, k_start + k_size_base, __pa(block) + k_size_base, - k_size_more, PAGE_KERNEL); - if (v_block_mapped(k_start)) - k_cur = k_start + k_size_base; - if (v_block_mapped(k_start + k_size_base)) - k_cur = k_start + k_size_base + k_size_more; - - update_bats(); + while (k_nobat < k_end) { + unsigned int k_size = bat_block_size(k_nobat, k_end); + int idx = find_free_bat(); + + if (idx == -1) + break; + if (k_size < SZ_128K) + break; + phys = memblock_phys_alloc_range(k_size, k_size, 0, + MEMBLOCK_ALLOC_ANYWHERE); + if (!phys) + break; + + setbat(idx, k_nobat, phys, k_size, PAGE_KERNEL); + k_nobat += k_size; } + if (k_nobat != k_start) + update_bats();

- if (!block) - block = memblock_alloc(k_size, PAGE_SIZE); - if (!block) - return -ENOMEM; + if (k_nobat < k_end) { + phys = memblock_phys_alloc_range(k_end - k_nobat, PAGE_SIZE, 0, + MEMBLOCK_ALLOC_ANYWHERE); + if (!phys) + return -ENOMEM; + }

ret = kasan_init_shadow_page_tables(k_start, k_end); if (ret) return ret;

- kasan_update_early_region(k_start, k_cur, __pte(0)); + kasan_update_early_region(k_start, k_nobat, __pte(0));

- for (; k_cur < k_end; k_cur += PAGE_SIZE) { + for (k_cur = k_nobat; k_cur < k_end; k_cur += PAGE_SIZE) { pmd_t *pmd = pmd_off_k(k_cur); - void *va = block + k_cur - k_start; - pte_t pte = pfn_pte(PHYS_PFN(__pa(va)), PAGE_KERNEL); + pte_t pte = pfn_pte(PHYS_PFN(phys + k_cur - k_nobat), PAGE_KERNEL);

__set_pte_at(&init_mm, k_cur, pte_offset_kernel(pmd, k_cur), pte, 0); } flush_tlb_kernel_range(k_start, k_end); + memset(kasan_mem_to_shadow(start), 0, k_end - k_start); + return 0; } diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 8936090acb57..0d47514e8870 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -651,17 +651,21 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, EMIT(PPC_RAW_MR(dst_reg, b2p[TMP_REG_1])); break; case 64: - /* - * Way easier and faster(?) to store the value - * into stack and then use ldbrx - * - * ctx->seen will be reliable in pass2, but - * the instructions generated will remain the - * same across all passes - */ + /* Store the value to stack and then use byte-reverse loads */ PPC_BPF_STL(dst_reg, 1, bpf_jit_stack_local(ctx)); EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx))); - EMIT(PPC_RAW_LDBRX(dst_reg, 0, b2p[TMP_REG_1])); + if (cpu_has_feature(CPU_FTR_ARCH_206)) { + EMIT(PPC_RAW_LDBRX(dst_reg, 0, b2p[TMP_REG_1])); + } else { + EMIT(PPC_RAW_LWBRX(dst_reg, 0, b2p[TMP_REG_1])); + if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN)) + EMIT(PPC_RAW_SLDI(dst_reg, dst_reg, 32)); + EMIT(PPC_RAW_LI(b2p[TMP_REG_2], 4)); + EMIT(PPC_RAW_LWBRX(b2p[TMP_REG_2], b2p[TMP_REG_2], b2p[TMP_REG_1])); + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) + EMIT(PPC_RAW_SLDI(b2p[TMP_REG_2], b2p[TMP_REG_2], 32)); + EMIT(PPC_RAW_OR(dst_reg, dst_reg, b2p[TMP_REG_2])); + } break; } break; diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index bd34e062bd29..e49aa8fc6a49 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1273,9 +1273,20 @@ static void power_pmu_disable(struct pmu *pmu) * Otherwise provide a warning if there is PMI pending, but * no counter is found overflown. */ - if (any_pmc_overflown(cpuhw)) - clear_pmi_irq_pending(); - else + if (any_pmc_overflown(cpuhw)) { + /* + * Since power_pmu_disable runs under local_irq_save, it + * could happen that code hits a PMC overflow without PMI + * pending in paca. Hence only clear PMI pending if it was + * set. + * + * If a PMI is pending, then MSR[EE] must be disabled (because + * the masked PMI handler disabling EE). So it is safe to + * call clear_pmi_irq_pending(). + */ + if (pmi_irq_pending()) + clear_pmi_irq_pending(); + } else WARN_ON(pmi_irq_pending());

val = mmcra = cpuhw->mmcr.mmcra; diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c index e1fcc03159ef..a927adccb4ba 100644 --- a/arch/s390/hypfs/hypfs_vm.c +++ b/arch/s390/hypfs/hypfs_vm.c @@ -20,6 +20,7 @@

static char local_guest[] = " "; static char all_guests[] = "* "; +static char *all_groups = all_guests; static char *guest_query;

struct diag2fc_data { @@ -62,10 +63,11 @@ static int diag2fc(int size, char* query, void *addr)

memcpy(parm_list.userid, query, NAME_LEN); ASCEBC(parm_list.userid, NAME_LEN); - parm_list.addr = (unsigned long) addr ; + memcpy(parm_list.aci_grp, all_groups, NAME_LEN); + ASCEBC(parm_list.aci_grp, NAME_LEN); + parm_list.addr = (unsigned long)addr; parm_list.size = size; parm_list.fmt = 0x02; - memset(parm_list.aci_grp, 0x40, NAME_LEN); rc = -1;

diag_stat_inc(DIAG_STAT_X2FC); diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index 4055f1c49814..b81bc96216b9 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -30,7 +30,7 @@ #define DEBUGP(fmt , ...) #endif

-#define PLT_ENTRY_SIZE 20 +#define PLT_ENTRY_SIZE 22

void *module_alloc(unsigned long size) { @@ -330,27 +330,26 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_PLTOFF32: /* 32 bit offset from GOT to PLT. */ case R_390_PLTOFF64: /* 16 bit offset from GOT to PLT. */ if (info->plt_initialized == 0) { - unsigned int insn[5]; - unsigned int *ip = me->core_layout.base + - me->arch.plt_offset + - info->plt_offset; - - insn[0] = 0x0d10e310; /* basr 1,0 */ - insn[1] = 0x100a0004; /* lg 1,10(1) */ + unsigned char insn[PLT_ENTRY_SIZE]; + char *plt_base; + char *ip; + + plt_base = me->core_layout.base + me->arch.plt_offset; + ip = plt_base + info->plt_offset; + *(int *)insn = 0x0d10e310; /* basr 1,0 */ + *(int *)&insn[4] = 0x100c0004; /* lg 1,12(1) */ if (IS_ENABLED(CONFIG_EXPOLINE) && !nospec_disable) { - unsigned int *ij; - ij = me->core_layout.base + - me->arch.plt_offset + - me->arch.plt_size - PLT_ENTRY_SIZE; - insn[2] = 0xa7f40000 + /* j __jump_r1 */ - (unsigned int)(u16) - (((unsigned long) ij - 8 - - (unsigned long) ip) / 2); + char *jump_r1; + + jump_r1 = plt_base + me->arch.plt_size - + PLT_ENTRY_SIZE; + /* brcl 0xf,__jump_r1 */ + *(short *)&insn[8] = 0xc0f4; + *(int *)&insn[10] = (jump_r1 - (ip + 8)) / 2; } else { - insn[2] = 0x07f10000; /* br %r1 */ + *(int *)&insn[8] = 0x07f10000; /* br %r1 */ } - insn[3] = (unsigned int) (val >> 32); - insn[4] = (unsigned int) val; + *(long *)&insn[14] = val;

write(ip, insn, sizeof(insn)); info->plt_initialized = 1; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index ba26792d9673..03c8047bebb3 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -5239,7 +5239,7 @@ static struct intel_uncore_type icx_uncore_imc = { .fixed_ctr_bits = 48, .fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR, .fixed_ctl = SNR_IMC_MMIO_PMON_FIXED_CTL, - .event_descs = hswep_uncore_imc_events, + .event_descs = snr_uncore_imc_events, .perf_ctr = SNR_IMC_MMIO_PMON_CTR0, .event_ctl = SNR_IMC_MMIO_PMON_CTL0, .event_mask = SNBEP_PMON_RAW_EVENT_MASK, diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 0c6b02dd744c..f73f1184b1c1 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -387,7 +387,7 @@ static void threshold_restart_bank(void *_tr) u32 hi, lo;

/* sysfs write might race against an offline operation */ - if (this_cpu_read(threshold_banks)) + if (!this_cpu_read(threshold_banks) && !tr->set_lvt_off) return;

rdmsr(tr->b->address, lo, hi); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 5e1d7396a6b8..2e6332af98ab 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4146,13 +4146,6 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, void *insn, int i if (likely(!insn || insn_len)) return true;

- /* - * If RIP is invalid, go ahead with emulation which will cause an - * internal error exit. - */ - if (!kvm_vcpu_gfn_to_memslot(vcpu, kvm_rip_read(vcpu) >> PAGE_SHIFT)) - return true; - cr4 = kvm_read_cr4(vcpu); smep = cr4 & X86_CR4_SMEP; smap = cr4 & X86_CR4_SMAP; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 271669dc8d90..7871b8e84b36 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3171,6 +3171,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & ~supported_xss) return 1; vcpu->arch.ia32_xss = data; + kvm_update_cpuid_runtime(vcpu); break; case MSR_SMI_COUNT: if (!msr_info->host_initiated) diff --git a/block/bio.c b/block/bio.c index 0703a208ca24..f8d26ce7b61b 100644 --- a/block/bio.c +++ b/block/bio.c @@ -575,7 +575,8 @@ void bio_truncate(struct bio *bio, unsigned new_size) offset = new_size - done; else offset = 0; - zero_user(bv.bv_page, offset, bv.bv_len - offset); + zero_user(bv.bv_page, bv.bv_offset + offset, + bv.bv_len - offset); truncated = true; } done += bv.bv_len; diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 847f33ffc4ae..9fa86288b78a 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -719,6 +719,13 @@ void __init efi_systab_report_header(const efi_table_hdr_t *systab_hdr, systab_hdr->revision >> 16, systab_hdr->revision & 0xffff, vendor); + + if (IS_ENABLED(CONFIG_X86_64) && + systab_hdr->revision > EFI_1_10_SYSTEM_TABLE_REVISION && + !strcmp(vendor, "Apple")) { + pr_info("Apple Mac detected, using EFI v1.10 runtime services only\n"); + efi.runtime_version = EFI_1_10_SYSTEM_TABLE_REVISION; + } }

static __initdata char memory_type_name[][13] = { diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c index c1b57dfb1277..415a971e7694 100644 --- a/drivers/firmware/efi/libstub/arm64-stub.c +++ b/drivers/firmware/efi/libstub/arm64-stub.c @@ -119,9 +119,9 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, if (image->image_base != _text) efi_err("FIRMWARE BUG: efi_loaded_image_t::image_base has bogus value\n");

- if (!IS_ALIGNED((u64)_text, EFI_KIMG_ALIGN)) - efi_err("FIRMWARE BUG: kernel image not aligned on %ldk boundary\n", - EFI_KIMG_ALIGN >> 10); + if (!IS_ALIGNED((u64)_text, SEGMENT_ALIGN)) + efi_err("FIRMWARE BUG: kernel image not aligned on %dk boundary\n", + SEGMENT_ALIGN >> 10);

kernel_size = _edata - _text; kernel_memsize = kernel_size + (_end - _edata); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index ed2c50011d44..ddf539f26f2d 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -469,8 +469,8 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data, return -EINVAL; }

- if (args->stream_size > SZ_64K || args->nr_relocs > SZ_64K || - args->nr_bos > SZ_64K || args->nr_pmrs > 128) { + if (args->stream_size > SZ_128K || args->nr_relocs > SZ_128K || + args->nr_bos > SZ_128K || args->nr_pmrs > 128) { DRM_ERROR("submit arguments out of size limits\n"); return -EINVAL; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c index a7a24539921f..a6efc11eba93 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c @@ -26,9 +26,16 @@ static void dpu_setup_dspp_pcc(struct dpu_hw_dspp *ctx, struct dpu_hw_pcc_cfg *cfg) {

- u32 base = ctx->cap->sblk->pcc.base; + u32 base;

- if (!ctx || !base) { + if (!ctx) { + DRM_ERROR("invalid ctx %pK\n", ctx); + return; + } + + base = ctx->cap->sblk->pcc.base; + + if (!base) { DRM_ERROR("invalid ctx %pK pcc base 0x%x\n", ctx, base); return; } diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c index 1adead764fee..f845333593da 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.c +++ b/drivers/gpu/drm/msm/dsi/dsi.c @@ -33,7 +33,12 @@ static int dsi_get_phy(struct msm_dsi *msm_dsi)

of_node_put(phy_node);

- if (!phy_pdev || !msm_dsi->phy) { + if (!phy_pdev) { + DRM_DEV_ERROR(&pdev->dev, "%s: phy driver is not ready\n", __func__); + return -EPROBE_DEFER; + } + if (!msm_dsi->phy) { + put_device(&phy_pdev->dev); DRM_DEV_ERROR(&pdev->dev, "%s: phy driver is not ready\n", __func__); return -EPROBE_DEFER; } diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index e8c1a727179c..e07986ab52c2 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -769,12 +769,14 @@ void __exit msm_dsi_phy_driver_unregister(void) int msm_dsi_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, struct msm_dsi_phy_clk_request *clk_req) { - struct device *dev = &phy->pdev->dev; + struct device *dev; int ret;

if (!phy || !phy->cfg->ops.enable) return -EINVAL;

+ dev = &phy->pdev->dev; + ret = dsi_phy_enable_resource(phy); if (ret) { DRM_DEV_ERROR(dev, "%s: resource enable failed, %d\n", diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c index 737453b6e596..94f948ef279d 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi.c @@ -97,10 +97,15 @@ static int msm_hdmi_get_phy(struct hdmi *hdmi)

of_node_put(phy_node);

- if (!phy_pdev || !hdmi->phy) { + if (!phy_pdev) { DRM_DEV_ERROR(&pdev->dev, "phy driver is not ready\n"); return -EPROBE_DEFER; } + if (!hdmi->phy) { + DRM_DEV_ERROR(&pdev->dev, "phy driver is not ready\n"); + put_device(&phy_pdev->dev); + return -EPROBE_DEFER; + }

hdmi->phy_dev = get_device(&phy_pdev->dev);

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 33e42b2f9cfc..e37e5afc680a 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -350,7 +350,7 @@ static int msm_init_vram(struct drm_device *dev) of_node_put(node); if (ret) return ret; - size = r.end - r.start; + size = r.end - r.start + 1; DRM_INFO("using VRAM carveout: %lx@%pa\n", size, &r.start);

/* if we have no IOMMU, then we need to use carveout allocator. diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c index 959446b0137b..a7142c32889c 100644 --- a/drivers/hwmon/lm90.c +++ b/drivers/hwmon/lm90.c @@ -373,7 +373,7 @@ static const struct lm90_params lm90_params[] = { .flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT | LM90_HAVE_BROKEN_ALERT | LM90_HAVE_CRIT, .alert_alarms = 0x7c, - .max_convrate = 8, + .max_convrate = 7, }, [lm86] = { .flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT @@ -394,12 +394,13 @@ static const struct lm90_params lm90_params[] = { .max_convrate = 9, }, [max6646] = { - .flags = LM90_HAVE_CRIT, + .flags = LM90_HAVE_CRIT | LM90_HAVE_BROKEN_ALERT, .alert_alarms = 0x7c, .max_convrate = 6, .reg_local_ext = MAX6657_REG_R_LOCAL_TEMPL, }, [max6654] = { + .flags = LM90_HAVE_BROKEN_ALERT, .alert_alarms = 0x7c, .max_convrate = 7, .reg_local_ext = MAX6657_REG_R_LOCAL_TEMPL, @@ -418,7 +419,7 @@ static const struct lm90_params lm90_params[] = { }, [max6680] = { .flags = LM90_HAVE_OFFSET | LM90_HAVE_CRIT - | LM90_HAVE_CRIT_ALRM_SWP, + | LM90_HAVE_CRIT_ALRM_SWP | LM90_HAVE_BROKEN_ALERT, .alert_alarms = 0x7c, .max_convrate = 7, }, diff --git a/drivers/media/platform/qcom/venus/core.c b/drivers/media/platform/qcom/venus/core.c index 1d621f776903..62d11c6e41d6 100644 --- a/drivers/media/platform/qcom/venus/core.c +++ b/drivers/media/platform/qcom/venus/core.c @@ -375,8 +375,6 @@ static int venus_remove(struct platform_device *pdev)

hfi_destroy(core);

- v4l2_device_unregister(&core->v4l2_dev); - mutex_destroy(&core->pm_lock); mutex_destroy(&core->lock); venus_dbgfs_deinit(core); diff --git a/drivers/mtd/nand/raw/mpc5121_nfc.c b/drivers/mtd/nand/raw/mpc5121_nfc.c index cb293c50acb8..5b9271b9c326 100644 --- a/drivers/mtd/nand/raw/mpc5121_nfc.c +++ b/drivers/mtd/nand/raw/mpc5121_nfc.c @@ -291,7 +291,6 @@ static int ads5121_chipselect_init(struct mtd_info *mtd) /* Control chips select signal on ADS5121 board */ static void ads5121_select_chip(struct nand_chip *nand, int chip) { - struct mtd_info *mtd = nand_to_mtd(nand); struct mpc5121_nfc_prv *prv = nand_get_controller_data(nand); u8 v;

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 6e7da1dc2e8c..d6580e942724 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -2382,8 +2382,7 @@ static irqreturn_t hclgevf_misc_irq_handle(int irq, void *data) break; }

- if (event_cause != HCLGEVF_VECTOR0_EVENT_OTHER) - hclgevf_enable_vector(&hdev->misc_vector, true); + hclgevf_enable_vector(&hdev->misc_vector, true);

return IRQ_HANDLED; } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 4f99d9763824..c7be7ab131b1 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -3401,11 +3401,25 @@ static void send_request_cap(struct ibmvnic_adapter *adapter, int retry) struct device *dev = &adapter->vdev->dev; union ibmvnic_crq crq; int max_entries; + int cap_reqs; + + /* We send out 6 or 7 REQUEST_CAPABILITY CRQs below (depending on + * the PROMISC flag). Initialize this count upfront. When the tasklet + * receives a response to all of these, it will send the next protocol + * message (QUERY_IP_OFFLOAD). + */ + if (!(adapter->netdev->flags & IFF_PROMISC) || + adapter->promisc_supported) + cap_reqs = 7; + else + cap_reqs = 6;

if (!retry) { /* Sub-CRQ entries are 32 byte long */ int entries_page = 4 * PAGE_SIZE / (sizeof(u64) * 4);

+ atomic_set(&adapter->running_cap_crqs, cap_reqs); + if (adapter->min_tx_entries_per_subcrq > entries_page || adapter->min_rx_add_entries_per_subcrq > entries_page) { dev_err(dev, "Fatal, invalid entries per sub-crq\n"); @@ -3466,44 +3480,45 @@ static void send_request_cap(struct ibmvnic_adapter *adapter, int retry) adapter->opt_rx_comp_queues;

adapter->req_rx_add_queues = adapter->max_rx_add_queues; + } else { + atomic_add(cap_reqs, &adapter->running_cap_crqs); } - memset(&crq, 0, sizeof(crq)); crq.request_capability.first = IBMVNIC_CRQ_CMD; crq.request_capability.cmd = REQUEST_CAPABILITY;

crq.request_capability.capability = cpu_to_be16(REQ_TX_QUEUES); crq.request_capability.number = cpu_to_be64(adapter->req_tx_queues); - atomic_inc(&adapter->running_cap_crqs); + cap_reqs--; ibmvnic_send_crq(adapter, &crq);

crq.request_capability.capability = cpu_to_be16(REQ_RX_QUEUES); crq.request_capability.number = cpu_to_be64(adapter->req_rx_queues); - atomic_inc(&adapter->running_cap_crqs); + cap_reqs--; ibmvnic_send_crq(adapter, &crq);

crq.request_capability.capability = cpu_to_be16(REQ_RX_ADD_QUEUES); crq.request_capability.number = cpu_to_be64(adapter->req_rx_add_queues); - atomic_inc(&adapter->running_cap_crqs); + cap_reqs--; ibmvnic_send_crq(adapter, &crq);

crq.request_capability.capability = cpu_to_be16(REQ_TX_ENTRIES_PER_SUBCRQ); crq.request_capability.number = cpu_to_be64(adapter->req_tx_entries_per_subcrq); - atomic_inc(&adapter->running_cap_crqs); + cap_reqs--; ibmvnic_send_crq(adapter, &crq);

crq.request_capability.capability = cpu_to_be16(REQ_RX_ADD_ENTRIES_PER_SUBCRQ); crq.request_capability.number = cpu_to_be64(adapter->req_rx_add_entries_per_subcrq); - atomic_inc(&adapter->running_cap_crqs); + cap_reqs--; ibmvnic_send_crq(adapter, &crq);

crq.request_capability.capability = cpu_to_be16(REQ_MTU); crq.request_capability.number = cpu_to_be64(adapter->req_mtu); - atomic_inc(&adapter->running_cap_crqs); + cap_reqs--; ibmvnic_send_crq(adapter, &crq);

if (adapter->netdev->flags & IFF_PROMISC) { @@ -3511,16 +3526,21 @@ static void send_request_cap(struct ibmvnic_adapter *adapter, int retry) crq.request_capability.capability = cpu_to_be16(PROMISC_REQUESTED); crq.request_capability.number = cpu_to_be64(1); - atomic_inc(&adapter->running_cap_crqs); + cap_reqs--; ibmvnic_send_crq(adapter, &crq); } } else { crq.request_capability.capability = cpu_to_be16(PROMISC_REQUESTED); crq.request_capability.number = cpu_to_be64(0); - atomic_inc(&adapter->running_cap_crqs); + cap_reqs--; ibmvnic_send_crq(adapter, &crq); } + + /* Keep at end to catch any discrepancy between expected and actual + * CRQs sent. + */ + WARN_ON(cap_reqs != 0); }

static int pending_scrq(struct ibmvnic_adapter *adapter, @@ -3953,118 +3973,132 @@ static void send_query_map(struct ibmvnic_adapter *adapter) static void send_query_cap(struct ibmvnic_adapter *adapter) { union ibmvnic_crq crq; + int cap_reqs; + + /* We send out 25 QUERY_CAPABILITY CRQs below. Initialize this count + * upfront. When the tasklet receives a response to all of these, it + * can send out the next protocol messaage (REQUEST_CAPABILITY). + */ + cap_reqs = 25; + + atomic_set(&adapter->running_cap_crqs, cap_reqs);

- atomic_set(&adapter->running_cap_crqs, 0); memset(&crq, 0, sizeof(crq)); crq.query_capability.first = IBMVNIC_CRQ_CMD; crq.query_capability.cmd = QUERY_CAPABILITY;

crq.query_capability.capability = cpu_to_be16(MIN_TX_QUEUES); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(MIN_RX_QUEUES); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(MIN_RX_ADD_QUEUES); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(MAX_TX_QUEUES); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(MAX_RX_QUEUES); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(MAX_RX_ADD_QUEUES); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(MIN_TX_ENTRIES_PER_SUBCRQ); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(MIN_RX_ADD_ENTRIES_PER_SUBCRQ); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(MAX_TX_ENTRIES_PER_SUBCRQ); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(MAX_RX_ADD_ENTRIES_PER_SUBCRQ); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(TCP_IP_OFFLOAD); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(PROMISC_SUPPORTED); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(MIN_MTU); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(MAX_MTU); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(MAX_MULTICAST_FILTERS); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(VLAN_HEADER_INSERTION); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(RX_VLAN_HEADER_INSERTION); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(MAX_TX_SG_ENTRIES); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(RX_SG_SUPPORTED); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(OPT_TX_COMP_SUB_QUEUES); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(OPT_RX_COMP_QUEUES); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(OPT_RX_BUFADD_Q_PER_RX_COMP_Q); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(OPT_TX_ENTRIES_PER_SUBCRQ); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(OPT_RXBA_ENTRIES_PER_SUBCRQ); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--;

crq.query_capability.capability = cpu_to_be16(TX_RX_DESC_REQ); - atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); + cap_reqs--; + + /* Keep at end to catch any discrepancy between expected and actual + * CRQs sent. + */ + WARN_ON(cap_reqs != 0); }

static void send_query_ip_offload(struct ibmvnic_adapter *adapter) @@ -4369,6 +4403,8 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq, char *name;

atomic_dec(&adapter->running_cap_crqs); + netdev_dbg(adapter->netdev, "Outstanding request-caps: %d\n", + atomic_read(&adapter->running_cap_crqs)); switch (be16_to_cpu(crq->request_capability_rsp.capability)) { case REQ_TX_QUEUES: req_value = &adapter->req_tx_queues; @@ -5039,12 +5075,6 @@ static void ibmvnic_tasklet(struct tasklet_struct *t) ibmvnic_handle_crq(crq, adapter); crq->generic.first = 0; } - - /* remain in tasklet until all - * capabilities responses are received - */ - if (!adapter->wait_capability) - done = true; } /* if capabilities CRQ's were sent in this tasklet, the following * tasklet must wait until all responses are received diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 5b83d1bc0e74..effdc3361266 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -172,7 +172,6 @@ enum i40e_interrupt_policy {

struct i40e_lump_tracking { u16 num_entries; - u16 search_hint; u16 list[0]; #define I40E_PILE_VALID_BIT 0x8000 #define I40E_IWARP_IRQ_PILE_ID (I40E_PILE_VALID_BIT - 2) @@ -755,12 +754,12 @@ struct i40e_vsi { struct rtnl_link_stats64 net_stats_offsets; struct i40e_eth_stats eth_stats; struct i40e_eth_stats eth_stats_offsets; - u32 tx_restart; - u32 tx_busy; + u64 tx_restart; + u64 tx_busy; u64 tx_linearize; u64 tx_force_wb; - u32 rx_buf_failed; - u32 rx_page_failed; + u64 rx_buf_failed; + u64 rx_page_failed;

/* These are containers of ring pointers, allocated at run-time */ struct i40e_ring **rx_rings; diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 714b578b2b49..1114a15a9ce3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -240,7 +240,7 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) (unsigned long int)vsi->net_stats_offsets.rx_compressed, (unsigned long int)vsi->net_stats_offsets.tx_compressed); dev_info(&pf->pdev->dev, - " tx_restart = %d, tx_busy = %d, rx_buf_failed = %d, rx_page_failed = %d\n", + " tx_restart = %llu, tx_busy = %llu, rx_buf_failed = %llu, rx_page_failed = %llu\n", vsi->tx_restart, vsi->tx_busy, vsi->rx_buf_failed, vsi->rx_page_failed); rcu_read_lock(); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index f888a443a067..bd18a780a000 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -195,10 +195,6 @@ int i40e_free_virt_mem_d(struct i40e_hw *hw, struct i40e_virt_mem *mem) * @id: an owner id to stick on the items assigned * * Returns the base item index of the lump, or negative for error - * - * The search_hint trick and lack of advanced fit-finding only work - * because we're highly likely to have all the same size lump requests. - * Linear search time and any fragmentation should be minimal. **/ static int i40e_get_lump(struct i40e_pf *pf, struct i40e_lump_tracking *pile, u16 needed, u16 id) @@ -213,8 +209,21 @@ static int i40e_get_lump(struct i40e_pf *pf, struct i40e_lump_tracking *pile, return -EINVAL; }

- /* start the linear search with an imperfect hint */ - i = pile->search_hint; + /* Allocate last queue in the pile for FDIR VSI queue + * so it doesn't fragment the qp_pile + */ + if (pile == pf->qp_pile && pf->vsi[id]->type == I40E_VSI_FDIR) { + if (pile->list[pile->num_entries - 1] & I40E_PILE_VALID_BIT) { + dev_err(&pf->pdev->dev, + "Cannot allocate queue %d for I40E_VSI_FDIR\n", + pile->num_entries - 1); + return -ENOMEM; + } + pile->list[pile->num_entries - 1] = id | I40E_PILE_VALID_BIT; + return pile->num_entries - 1; + } + + i = 0; while (i < pile->num_entries) { /* skip already allocated entries */ if (pile->list[i] & I40E_PILE_VALID_BIT) { @@ -233,7 +242,6 @@ static int i40e_get_lump(struct i40e_pf *pf, struct i40e_lump_tracking *pile, for (j = 0; j < needed; j++) pile->list[i+j] = id | I40E_PILE_VALID_BIT; ret = i; - pile->search_hint = i + j; break; }

@@ -256,7 +264,7 @@ static int i40e_put_lump(struct i40e_lump_tracking *pile, u16 index, u16 id) { int valid_id = (id | I40E_PILE_VALID_BIT); int count = 0; - int i; + u16 i;

if (!pile || index >= pile->num_entries) return -EINVAL; @@ -268,8 +276,6 @@ static int i40e_put_lump(struct i40e_lump_tracking *pile, u16 index, u16 id) count++; }

- if (count && index < pile->search_hint) - pile->search_hint = index;

return count; } @@ -771,9 +777,9 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) struct rtnl_link_stats64 *ns; /* netdev stats */ struct i40e_eth_stats *oes; struct i40e_eth_stats *es; /* device's eth stats */ - u32 tx_restart, tx_busy; + u64 tx_restart, tx_busy; struct i40e_ring *p; - u32 rx_page, rx_buf; + u64 rx_page, rx_buf; u64 bytes, packets; unsigned int start; u64 tx_linearize; @@ -10130,15 +10136,9 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) } i40e_get_oem_version(&pf->hw);

- if (test_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state) && - ((hw->aq.fw_maj_ver == 4 && hw->aq.fw_min_ver <= 33) || - hw->aq.fw_maj_ver < 4) && hw->mac.type == I40E_MAC_XL710) { - /* The following delay is necessary for 4.33 firmware and older - * to recover after EMP reset. 200 ms should suffice but we - * put here 300 ms to be sure that FW is ready to operate - * after reset. - */ - mdelay(300); + if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state)) { + /* The following delay is necessary for firmware update. */ + mdelay(1000); }

/* re-verify the eeprom if we just had an EMP reset */ @@ -11327,7 +11327,6 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf) return -ENOMEM;

pf->irq_pile->num_entries = vectors; - pf->irq_pile->search_hint = 0;

/* track first vector for misc interrupts, ignore return */ (void)i40e_get_lump(pf, pf->irq_pile, 1, I40E_PILE_VALID_BIT - 1); @@ -12130,7 +12129,6 @@ static int i40e_sw_init(struct i40e_pf *pf) goto sw_init_done; } pf->qp_pile->num_entries = pf->hw.func_caps.num_tx_qp; - pf->qp_pile->search_hint = 0;

pf->tx_timeout_recovery_level = 1;

diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h index 564df22f3f46..8335f151ceef 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_register.h +++ b/drivers/net/ethernet/intel/i40e/i40e_register.h @@ -279,6 +279,9 @@ #define I40E_VFINT_DYN_CTLN(_INTVF) (0x00024800 + ((_INTVF) * 4)) /* _i=0...511 */ /* Reset: VFR */ #define I40E_VFINT_DYN_CTLN_CLEARPBA_SHIFT 1 #define I40E_VFINT_DYN_CTLN_CLEARPBA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN_CLEARPBA_SHIFT) +#define I40E_VFINT_ICR0_ADMINQ_SHIFT 30 +#define I40E_VFINT_ICR0_ADMINQ_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ADMINQ_SHIFT) +#define I40E_VFINT_ICR0_ENA(_VF) (0x0002C000 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: CORER */ #define I40E_VPINT_AEQCTL(_VF) (0x0002B800 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: CORER */ #define I40E_VPINT_AEQCTL_MSIX_INDX_SHIFT 0 #define I40E_VPINT_AEQCTL_ITR_INDX_SHIFT 11 diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 65c4c4fd359f..f71b7334e295 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1323,6 +1323,32 @@ static i40e_status i40e_config_vf_promiscuous_mode(struct i40e_vf *vf, return aq_ret; }

+/** + * i40e_sync_vfr_reset + * @hw: pointer to hw struct + * @vf_id: VF identifier + * + * Before trigger hardware reset, we need to know if no other process has + * reserved the hardware for any reset operations. This check is done by + * examining the status of the RSTAT1 register used to signal the reset. + **/ +static int i40e_sync_vfr_reset(struct i40e_hw *hw, int vf_id) +{ + u32 reg; + int i; + + for (i = 0; i < I40E_VFR_WAIT_COUNT; i++) { + reg = rd32(hw, I40E_VFINT_ICR0_ENA(vf_id)) & + I40E_VFINT_ICR0_ADMINQ_MASK; + if (reg) + return 0; + + usleep_range(100, 200); + } + + return -EAGAIN; +} + /** * i40e_trigger_vf_reset * @vf: pointer to the VF structure @@ -1337,9 +1363,11 @@ static void i40e_trigger_vf_reset(struct i40e_vf *vf, bool flr) struct i40e_pf *pf = vf->pf; struct i40e_hw *hw = &pf->hw; u32 reg, reg_idx, bit_idx; + bool vf_active; + u32 radq;

/* warn the VF */ - clear_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states); + vf_active = test_and_clear_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states);

/* Disable VF's configuration API during reset. The flag is re-enabled * in i40e_alloc_vf_res(), when it's safe again to access VF's VSI. @@ -1353,7 +1381,19 @@ static void i40e_trigger_vf_reset(struct i40e_vf *vf, bool flr) * just need to clean up, so don't hit the VFRTRIG register. */ if (!flr) { - /* reset VF using VPGEN_VFRTRIG reg */ + /* Sync VFR reset before trigger next one */ + radq = rd32(hw, I40E_VFINT_ICR0_ENA(vf->vf_id)) & + I40E_VFINT_ICR0_ADMINQ_MASK; + if (vf_active && !radq) + /* waiting for finish reset by virtual driver */ + if (i40e_sync_vfr_reset(hw, vf->vf_id)) + dev_info(&pf->pdev->dev, + "Reset VF %d never finished\n", + vf->vf_id); + + /* Reset VF using VPGEN_VFRTRIG reg. It is also setting + * in progress state in rstat1 register. + */ reg = rd32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id)); reg |= I40E_VPGEN_VFRTRIG_VFSWR_MASK; wr32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id), reg); @@ -2563,6 +2603,59 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg) aq_ret); }

+/** + * i40e_check_enough_queue - find big enough queue number + * @vf: pointer to the VF info + * @needed: the number of items needed + * + * Returns the base item index of the queue, or negative for error + **/ +static int i40e_check_enough_queue(struct i40e_vf *vf, u16 needed) +{ + unsigned int i, cur_queues, more, pool_size; + struct i40e_lump_tracking *pile; + struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi; + + vsi = pf->vsi[vf->lan_vsi_idx]; + cur_queues = vsi->alloc_queue_pairs; + + /* if current allocated queues are enough for need */ + if (cur_queues >= needed) + return vsi->base_queue; + + pile = pf->qp_pile; + if (cur_queues > 0) { + /* if the allocated queues are not zero + * just check if there are enough queues for more + * behind the allocated queues. + */ + more = needed - cur_queues; + for (i = vsi->base_queue + cur_queues; + i < pile->num_entries; i++) { + if (pile->list[i] & I40E_PILE_VALID_BIT) + break; + + if (more-- == 1) + /* there is enough */ + return vsi->base_queue; + } + } + + pool_size = 0; + for (i = 0; i < pile->num_entries; i++) { + if (pile->list[i] & I40E_PILE_VALID_BIT) { + pool_size = 0; + continue; + } + if (needed <= ++pool_size) + /* there is enough */ + return i; + } + + return -ENOMEM; +} + /** * i40e_vc_request_queues_msg * @vf: pointer to the VF info @@ -2597,6 +2690,12 @@ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg) req_pairs - cur_pairs, pf->queues_left); vfres->num_queue_pairs = pf->queues_left + cur_pairs; + } else if (i40e_check_enough_queue(vf, req_pairs) < 0) { + dev_warn(&pf->pdev->dev, + "VF %d requested %d more queues, but there is not enough for it.\n", + vf->vf_id, + req_pairs - cur_pairs); + vfres->num_queue_pairs = cur_pairs; } else { /* successful request */ vf->num_req_queues = req_pairs; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 49575a640a84..03c42fd0fea1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -19,6 +19,7 @@ #define I40E_MAX_VF_PROMISC_FLAGS 3

#define I40E_VF_STATE_WAIT_COUNT 20 +#define I40E_VFR_WAIT_COUNT 100

/* Various queue ctrls */ enum i40e_queue_ctrl { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 044a5b1196ac..161174be51c3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -386,7 +386,12 @@ static int otx2_forward_vf_mbox_msgs(struct otx2_nic *pf, dst_mdev->msg_size = mbox_hdr->msg_size; dst_mdev->num_msgs = num_msgs; err = otx2_sync_mbox_msg(dst_mbox); - if (err) { + /* Error code -EIO indicate there is a communication failure + * to the AF. Rest of the error codes indicate that AF processed + * VF messages and set the error codes in response messages + * (if any) so simply forward responses to VF. + */ + if (err == -EIO) { dev_warn(pf->dev, "AF not responding to VF%d messages\n", vf); /* restore PF mbase and exit */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index a8c5492cb39b..6d8a839fab22 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -816,8 +816,6 @@ static int stmmac_init_ptp(struct stmmac_priv *priv) priv->hwts_tx_en = 0; priv->hwts_rx_en = 0;

- stmmac_ptp_register(priv); - return 0; }

@@ -2691,7 +2689,7 @@ static void stmmac_safety_feat_configuration(struct stmmac_priv *priv) /** * stmmac_hw_setup - setup mac in a usable state. * @dev : pointer to the device structure. - * @init_ptp: initialize PTP if set + * @ptp_register: register PTP if set * Description: * this is the main function to setup the HW in a usable state because the * dma engine is reset, the core registers are configured (e.g. AXI, @@ -2701,7 +2699,7 @@ static void stmmac_safety_feat_configuration(struct stmmac_priv *priv) * 0 on success and an appropriate (-)ve integer as defined in errno.h * file on failure. */ -static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) +static int stmmac_hw_setup(struct net_device *dev, bool ptp_register) { struct stmmac_priv *priv = netdev_priv(dev); u32 rx_cnt = priv->plat->rx_queues_to_use; @@ -2757,13 +2755,13 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)

stmmac_mmc_setup(priv);

- if (init_ptp) { - ret = stmmac_init_ptp(priv); - if (ret == -EOPNOTSUPP) - netdev_warn(priv->dev, "PTP not supported by HW\n"); - else if (ret) - netdev_warn(priv->dev, "PTP init failed\n"); - } + ret = stmmac_init_ptp(priv); + if (ret == -EOPNOTSUPP) + netdev_warn(priv->dev, "PTP not supported by HW\n"); + else if (ret) + netdev_warn(priv->dev, "PTP init failed\n"); + else if (ptp_register) + stmmac_ptp_register(priv);

priv->eee_tw_timer = STMMAC_DEFAULT_TWT_LS;

diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index 424e644724e4..e74f2e95a46e 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -1144,7 +1144,7 @@ int cpsw_fill_rx_channels(struct cpsw_priv *priv) static struct page_pool *cpsw_create_page_pool(struct cpsw_common *cpsw, int size) { - struct page_pool_params pp_params; + struct page_pool_params pp_params = {}; struct page_pool *pool;

pp_params.order = 0; diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c index 5ab53e9942f3..5d30b3e1806a 100644 --- a/drivers/net/hamradio/yam.c +++ b/drivers/net/hamradio/yam.c @@ -951,9 +951,7 @@ static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) sizeof(struct yamdrv_ioctl_mcs)); if (IS_ERR(ym)) return PTR_ERR(ym); - if (ym->cmd != SIOCYAMSMCS) - return -EINVAL; - if (ym->bitrate > YAM_MAXBITRATE) { + if (ym->cmd != SIOCYAMSMCS || ym->bitrate > YAM_MAXBITRATE) { kfree(ym); return -EINVAL; } diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index dbed15dc0fe7..644861366d54 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -789,6 +789,7 @@ static struct phy_driver broadcom_drivers[] = { .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM54616S", /* PHY_GBIT_FEATURES */ + .soft_reset = genphy_soft_reset, .config_init = bcm54xx_config_init, .config_aneg = bcm54616s_config_aneg, .ack_interrupt = bcm_phy_ack_intr, diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 85f3cde5ffd0..d2f6d8107595 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1682,6 +1682,9 @@ void phy_detach(struct phy_device *phydev) phy_driver_is_genphy_10g(phydev)) device_release_driver(&phydev->mdio.dev);

+ /* Assert the reset signal */ + phy_device_reset(phydev, 1); + /* * The phydev might go away on the put_device() below, so avoid * a use-after-free bug by reading the underlying bus first. @@ -1693,9 +1696,6 @@ void phy_detach(struct phy_device *phydev) ndev_owner = dev->dev.parent->driver->owner; if (ndev_owner != bus->owner) module_put(bus->owner); - - /* Assert the reset signal */ - phy_device_reset(phydev, 1); } EXPORT_SYMBOL(phy_detach);

diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index 4cf874fb5c5b..a05d8372669c 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -609,6 +609,11 @@ struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode) else if (ret < 0) return ERR_PTR(ret);

+ if (!fwnode_device_is_available(ref.fwnode)) { + fwnode_handle_put(ref.fwnode); + return NULL; + } + bus = sfp_bus_get(ref.fwnode); fwnode_handle_put(ref.fwnode); if (!bus) diff --git a/drivers/rpmsg/rpmsg_char.c b/drivers/rpmsg/rpmsg_char.c index 4bbbacdbf3bb..be90d77c5168 100644 --- a/drivers/rpmsg/rpmsg_char.c +++ b/drivers/rpmsg/rpmsg_char.c @@ -92,7 +92,7 @@ static int rpmsg_eptdev_destroy(struct device *dev, void *data) /* wake up any blocked readers */ wake_up_interruptible(&eptdev->readq);

- device_del(&eptdev->dev); + cdev_device_del(&eptdev->cdev, &eptdev->dev); put_device(&eptdev->dev);

return 0; @@ -332,7 +332,6 @@ static void rpmsg_eptdev_release_device(struct device *dev)

ida_simple_remove(&rpmsg_ept_ida, dev->id); ida_simple_remove(&rpmsg_minor_ida, MINOR(eptdev->dev.devt)); - cdev_del(&eptdev->cdev); kfree(eptdev); }

@@ -377,19 +376,13 @@ static int rpmsg_eptdev_create(struct rpmsg_ctrldev *ctrldev, dev->id = ret; dev_set_name(dev, "rpmsg%d", ret);

- ret = cdev_add(&eptdev->cdev, dev->devt, 1); + ret = cdev_device_add(&eptdev->cdev, &eptdev->dev); if (ret) goto free_ept_ida;

/* We can now rely on the release function for cleanup */ dev->release = rpmsg_eptdev_release_device;

- ret = device_add(dev); - if (ret) { - dev_err(dev, "device_add failed: %d\n", ret); - put_device(dev); - } - return ret;

free_ept_ida: @@ -458,7 +451,6 @@ static void rpmsg_ctrldev_release_device(struct device *dev)

ida_simple_remove(&rpmsg_ctrl_ida, dev->id); ida_simple_remove(&rpmsg_minor_ida, MINOR(dev->devt)); - cdev_del(&ctrldev->cdev); kfree(ctrldev); }

@@ -493,19 +485,13 @@ static int rpmsg_chrdev_probe(struct rpmsg_device *rpdev) dev->id = ret; dev_set_name(&ctrldev->dev, "rpmsg_ctrl%d", ret);

- ret = cdev_add(&ctrldev->cdev, dev->devt, 1); + ret = cdev_device_add(&ctrldev->cdev, &ctrldev->dev); if (ret) goto free_ctrl_ida;

/* We can now rely on the release function for cleanup */ dev->release = rpmsg_ctrldev_release_device;

- ret = device_add(dev); - if (ret) { - dev_err(&rpdev->dev, "device_add failed: %d\n", ret); - put_device(dev); - } - dev_set_drvdata(&rpdev->dev, ctrldev);

return ret; @@ -531,7 +517,7 @@ static void rpmsg_chrdev_remove(struct rpmsg_device *rpdev) if (ret) dev_warn(&rpdev->dev, "failed to nuke endpoints: %d\n", ret);

- device_del(&ctrldev->dev); + cdev_device_del(&ctrldev->cdev, &ctrldev->dev); put_device(&ctrldev->dev); }

diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c index d24cafe02708..511bf8e0a436 100644 --- a/drivers/s390/scsi/zfcp_fc.c +++ b/drivers/s390/scsi/zfcp_fc.c @@ -521,6 +521,8 @@ static void zfcp_fc_adisc_handler(void *data) goto out; }

+ /* re-init to undo drop from zfcp_fc_adisc() */ + port->d_id = ntoh24(adisc_resp->adisc_port_id); /* port is good, unblock rport without going through erp */ zfcp_scsi_schedule_rport_register(port); out: @@ -534,6 +536,7 @@ static int zfcp_fc_adisc(struct zfcp_port *port) struct zfcp_fc_req *fc_req; struct zfcp_adapter *adapter = port->adapter; struct Scsi_Host *shost = adapter->scsi_host; + u32 d_id; int ret;

fc_req = kmem_cache_zalloc(zfcp_fc_req_cache, GFP_ATOMIC); @@ -558,7 +561,15 @@ static int zfcp_fc_adisc(struct zfcp_port *port) fc_req->u.adisc.req.adisc_cmd = ELS_ADISC; hton24(fc_req->u.adisc.req.adisc_port_id, fc_host_port_id(shost));

- ret = zfcp_fsf_send_els(adapter, port->d_id, &fc_req->ct_els, + d_id = port->d_id; /* remember as destination for send els below */ + /* + * Force fresh GID_PN lookup on next port recovery. + * Must happen after request setup and before sending request, + * to prevent race with port->d_id re-init in zfcp_fc_adisc_handler(). + */ + port->d_id = 0; + + ret = zfcp_fsf_send_els(adapter, d_id, &fc_req->ct_els, ZFCP_FC_CTELS_TMO); if (ret) kmem_cache_free(zfcp_fc_req_cache, fc_req); diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c index 6890bbe04a8c..052e7879704a 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c @@ -80,7 +80,7 @@ static int bnx2fc_bind_pcidev(struct bnx2fc_hba *hba); static void bnx2fc_unbind_pcidev(struct bnx2fc_hba *hba); static struct fc_lport *bnx2fc_if_create(struct bnx2fc_interface *interface, struct device *parent, int npiv); -static void bnx2fc_destroy_work(struct work_struct *work); +static void bnx2fc_port_destroy(struct fcoe_port *port);

static struct bnx2fc_hba *bnx2fc_hba_lookup(struct net_device *phys_dev); static struct bnx2fc_interface *bnx2fc_interface_lookup(struct net_device @@ -905,9 +905,6 @@ static void bnx2fc_indicate_netevent(void *context, unsigned long event, __bnx2fc_destroy(interface); } mutex_unlock(&bnx2fc_dev_lock); - - /* Ensure ALL destroy work has been completed before return */ - flush_workqueue(bnx2fc_wq); return;

default: @@ -1213,8 +1210,8 @@ static int bnx2fc_vport_destroy(struct fc_vport *vport) mutex_unlock(&n_port->lp_mutex); bnx2fc_free_vport(interface->hba, port->lport); bnx2fc_port_shutdown(port->lport); + bnx2fc_port_destroy(port); bnx2fc_interface_put(interface); - queue_work(bnx2fc_wq, &port->destroy_work); return 0; }

@@ -1523,7 +1520,6 @@ static struct fc_lport *bnx2fc_if_create(struct bnx2fc_interface *interface, port->lport = lport; port->priv = interface; port->get_netdev = bnx2fc_netdev; - INIT_WORK(&port->destroy_work, bnx2fc_destroy_work);

/* Configure fcoe_port */ rc = bnx2fc_lport_config(lport); @@ -1651,8 +1647,8 @@ static void __bnx2fc_destroy(struct bnx2fc_interface *interface) bnx2fc_interface_cleanup(interface); bnx2fc_stop(interface); list_del(&interface->list); + bnx2fc_port_destroy(port); bnx2fc_interface_put(interface); - queue_work(bnx2fc_wq, &port->destroy_work); }

/** @@ -1692,15 +1688,12 @@ static int bnx2fc_destroy(struct net_device *netdev) return rc; }

-static void bnx2fc_destroy_work(struct work_struct *work) +static void bnx2fc_port_destroy(struct fcoe_port *port) { - struct fcoe_port *port; struct fc_lport *lport;

- port = container_of(work, struct fcoe_port, destroy_work); lport = port->lport; - - BNX2FC_HBA_DBG(lport, "Entered bnx2fc_destroy_work\n"); + BNX2FC_HBA_DBG(lport, "Entered %s, destroying lport %p\n", __func__, lport);

bnx2fc_if_destroy(lport); } @@ -2554,9 +2547,6 @@ static void bnx2fc_ulp_exit(struct cnic_dev *dev) __bnx2fc_destroy(interface); mutex_unlock(&bnx2fc_dev_lock);

- /* Ensure ALL destroy work has been completed before return */ - flush_workqueue(bnx2fc_wq); - bnx2fc_ulp_stop(hba); /* unregister cnic device */ if (test_and_clear_bit(BNX2FC_CNIC_REGISTERED, &hba->reg_with_cnic)) diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index d76880ae68c8..b8f862153772 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -317,6 +317,7 @@ static struct tty_driver *gsm_tty_driver; #define GSM1_ESCAPE_BITS 0x20 #define XON 0x11 #define XOFF 0x13 +#define ISO_IEC_646_MASK 0x7F

static const struct tty_port_operations gsm_port_ops;

@@ -526,7 +527,8 @@ static int gsm_stuff_frame(const u8 *input, u8 *output, int len) int olen = 0; while (len--) { if (*input == GSM1_SOF || *input == GSM1_ESCAPE - || *input == XON || *input == XOFF) { + || (*input & ISO_IEC_646_MASK) == XON + || (*input & ISO_IEC_646_MASK) == XOFF) { *output++ = GSM1_ESCAPE; *output++ = *input++ ^ GSM1_ESCAPE_BITS; olen++; diff --git a/drivers/tty/serial/8250/8250_of.c b/drivers/tty/serial/8250/8250_of.c index 65e9045dafe6..5595c63c46ea 100644 --- a/drivers/tty/serial/8250/8250_of.c +++ b/drivers/tty/serial/8250/8250_of.c @@ -83,8 +83,17 @@ static int of_platform_serial_setup(struct platform_device *ofdev, port->mapsize = resource_size(&resource);

/* Check for shifted address mapping */ - if (of_property_read_u32(np, "reg-offset", &prop) == 0) + if (of_property_read_u32(np, "reg-offset", &prop) == 0) { + if (prop >= port->mapsize) { + dev_warn(&ofdev->dev, "reg-offset %u exceeds region size %pa\n", + prop, &port->mapsize); + ret = -EINVAL; + goto err_unprepare; + } + port->mapbase += prop; + port->mapsize -= prop; + }

port->iotype = UPIO_MEM; if (of_property_read_u32(np, "reg-io-width", &prop) == 0) { diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 019328d644d8..3a985e953b8e 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -5171,8 +5171,30 @@ static const struct pci_device_id serial_pci_tbl[] = { { PCI_VENDOR_ID_INTASHIELD, PCI_DEVICE_ID_INTASHIELD_IS400, PCI_ANY_ID, PCI_ANY_ID, 0, 0, /* 135a.0dc0 */ pbn_b2_4_115200 }, + /* Brainboxes Devices */ /* - * BrainBoxes UC-260 + * Brainboxes UC-101 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0BA1, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_2_115200 }, + /* + * Brainboxes UC-235/246 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0AA1, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_1_115200 }, + /* + * Brainboxes UC-257 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0861, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_2_115200 }, + /* + * Brainboxes UC-260/271/701/756 */ { PCI_VENDOR_ID_INTASHIELD, 0x0D21, PCI_ANY_ID, PCI_ANY_ID, @@ -5180,7 +5202,81 @@ static const struct pci_device_id serial_pci_tbl[] = { pbn_b2_4_115200 }, { PCI_VENDOR_ID_INTASHIELD, 0x0E34, PCI_ANY_ID, PCI_ANY_ID, - PCI_CLASS_COMMUNICATION_MULTISERIAL << 8, 0xffff00, + PCI_CLASS_COMMUNICATION_MULTISERIAL << 8, 0xffff00, + pbn_b2_4_115200 }, + /* + * Brainboxes UC-268 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0841, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_4_115200 }, + /* + * Brainboxes UC-275/279 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0881, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_8_115200 }, + /* + * Brainboxes UC-302 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x08E1, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_2_115200 }, + /* + * Brainboxes UC-310 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x08C1, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_2_115200 }, + /* + * Brainboxes UC-313 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x08A3, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_2_115200 }, + /* + * Brainboxes UC-320/324 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0A61, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_1_115200 }, + /* + * Brainboxes UC-346 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0B02, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_4_115200 }, + /* + * Brainboxes UC-357 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0A81, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_2_115200 }, + { PCI_VENDOR_ID_INTASHIELD, 0x0A83, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_2_115200 }, + /* + * Brainboxes UC-368 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0C41, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_4_115200 }, + /* + * Brainboxes UC-420/431 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0921, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, pbn_b2_4_115200 }, /* * Perle PCI-RAS cards diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index 844059861f9e..0eadf0547175 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -574,7 +574,7 @@ static void stm32_usart_start_tx(struct uart_port *port) struct serial_rs485 *rs485conf = &port->rs485; struct circ_buf *xmit = &port->state->xmit;

- if (uart_circ_empty(xmit)) + if (uart_circ_empty(xmit) && !port->x_char) return;

if (rs485conf->flags & SER_RS485_ENABLED) { diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c index a18d7c4222dd..82fe8e00a96a 100644 --- a/drivers/usb/common/ulpi.c +++ b/drivers/usb/common/ulpi.c @@ -39,8 +39,11 @@ static int ulpi_match(struct device *dev, struct device_driver *driver) struct ulpi *ulpi = to_ulpi_dev(dev); const struct ulpi_device_id *id;

- /* Some ULPI devices don't have a vendor id so rely on OF match */ - if (ulpi->id.vendor == 0) + /* + * Some ULPI devices don't have a vendor id + * or provide an id_table so rely on OF match. + */ + if (ulpi->id.vendor == 0 || !drv->id_table) return of_driver_match_device(dev, driver);

for (id = drv->id_table; id->vendor; id++) diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index b2710015493a..ddd1d3eef912 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1562,6 +1562,13 @@ int usb_hcd_submit_urb (struct urb *urb, gfp_t mem_flags) urb->hcpriv = NULL; INIT_LIST_HEAD(&urb->urb_list); atomic_dec(&urb->use_count); + /* + * Order the write of urb->use_count above before the read + * of urb->reject below. Pairs with the memory barriers in + * usb_kill_urb() and usb_poison_urb(). + */ + smp_mb__after_atomic(); + atomic_dec(&urb->dev->urbnum); if (atomic_read(&urb->reject)) wake_up(&usb_kill_urb_queue); @@ -1666,6 +1673,13 @@ static void __usb_hcd_giveback_urb(struct urb *urb)

usb_anchor_resume_wakeups(anchor); atomic_dec(&urb->use_count); + /* + * Order the write of urb->use_count above before the read + * of urb->reject below. Pairs with the memory barriers in + * usb_kill_urb() and usb_poison_urb(). + */ + smp_mb__after_atomic(); + if (unlikely(atomic_read(&urb->reject))) wake_up(&usb_kill_urb_queue); usb_put_urb(urb); diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c index 357b149b20d3..9c285026f827 100644 --- a/drivers/usb/core/urb.c +++ b/drivers/usb/core/urb.c @@ -706,6 +706,12 @@ void usb_kill_urb(struct urb *urb) if (!(urb && urb->dev && urb->ep)) return; atomic_inc(&urb->reject); + /* + * Order the write of urb->reject above before the read + * of urb->use_count below. Pairs with the barriers in + * __usb_hcd_giveback_urb() and usb_hcd_submit_urb(). + */ + smp_mb__after_atomic();

usb_hcd_unlink_urb(urb, -ENOENT); wait_event(usb_kill_urb_queue, atomic_read(&urb->use_count) == 0); @@ -747,6 +753,12 @@ void usb_poison_urb(struct urb *urb) if (!urb) return; atomic_inc(&urb->reject); + /* + * Order the write of urb->reject above before the read + * of urb->use_count below. Pairs with the barriers in + * __usb_hcd_giveback_urb() and usb_hcd_submit_urb(). + */ + smp_mb__after_atomic();

if (!urb->dev || !urb->ep) return; diff --git a/drivers/usb/gadget/function/f_sourcesink.c b/drivers/usb/gadget/function/f_sourcesink.c index 282737e4609c..2c65a9bb3c81 100644 --- a/drivers/usb/gadget/function/f_sourcesink.c +++ b/drivers/usb/gadget/function/f_sourcesink.c @@ -583,6 +583,7 @@ static int source_sink_start_ep(struct f_sourcesink *ss, bool is_in,

if (is_iso) { switch (speed) { + case USB_SPEED_SUPER_PLUS: case USB_SPEED_SUPER: size = ss->isoc_maxpacket * (ss->isoc_mult + 1) * diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index c1edcc9b13ce..dc570ce4e831 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -437,6 +437,9 @@ static int __maybe_unused xhci_plat_suspend(struct device *dev) struct xhci_hcd *xhci = hcd_to_xhci(hcd); int ret;

+ if (pm_runtime_suspended(dev)) + pm_runtime_resume(dev); + ret = xhci_priv_suspend_quirk(hcd); if (ret) return ret; diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 29191d33c0e3..1a05e3dcfec8 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -2301,6 +2301,16 @@ UNUSUAL_DEV( 0x2027, 0xa001, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init, US_FL_SCM_MULT_TARG ),

+/* + * Reported by DocMAX mail@vacharakis.de + * and Thomas Weißschuh linux@weissschuh.net + */ +UNUSUAL_DEV( 0x2109, 0x0715, 0x9999, 0x9999, + "VIA Labs, Inc.", + "VL817 SATA Bridge", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_IGNORE_UAS), + UNUSUAL_DEV( 0x2116, 0x0320, 0x0001, 0x0001, "ST", "2A", diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 721d9c4ddc81..8333c80b5f7c 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -4164,7 +4164,8 @@ static void _tcpm_pd_vbus_off(struct tcpm_port *port) case SNK_TRYWAIT_DEBOUNCE: break; case SNK_ATTACH_WAIT: - tcpm_set_state(port, SNK_UNATTACHED, 0); + case SNK_DEBOUNCED: + /* Do nothing, as TCPM is still waiting for vbus to reaach VSAFE5V to connect */ break;

case SNK_NEGOTIATE_CAPABILITIES: diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c index bff96d64dddf..6db7c8ddd51c 100644 --- a/drivers/usb/typec/ucsi/ucsi_ccg.c +++ b/drivers/usb/typec/ucsi/ucsi_ccg.c @@ -325,7 +325,7 @@ static int ucsi_ccg_init(struct ucsi_ccg *uc) if (status < 0) return status;

- if (!data) + if (!(data & DEV_INT)) return 0;

status = ccg_write(uc, CCGX_RAB_INTR_REG, &data, sizeof(data)); diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index 4dc9077dd2ac..3c309ab20887 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -286,8 +286,6 @@ struct hvfb_par {

static uint screen_width = HVFB_WIDTH; static uint screen_height = HVFB_HEIGHT; -static uint screen_width_max = HVFB_WIDTH; -static uint screen_height_max = HVFB_HEIGHT; static uint screen_depth; static uint screen_fb_size; static uint dio_fb_size; /* FB size for deferred IO */ @@ -581,7 +579,6 @@ static int synthvid_get_supported_resolution(struct hv_device *hdev) int ret = 0; unsigned long t; u8 index; - int i;

memset(msg, 0, sizeof(struct synthvid_msg)); msg->vid_hdr.type = SYNTHVID_RESOLUTION_REQUEST; @@ -612,13 +609,6 @@ static int synthvid_get_supported_resolution(struct hv_device *hdev) goto out; }

- for (i = 0; i < msg->resolution_resp.resolution_count; i++) { - screen_width_max = max_t(unsigned int, screen_width_max, - msg->resolution_resp.supported_resolution[i].width); - screen_height_max = max_t(unsigned int, screen_height_max, - msg->resolution_resp.supported_resolution[i].height); - } - screen_width = msg->resolution_resp.supported_resolution[index].width; screen_height = @@ -940,7 +930,7 @@ static void hvfb_get_option(struct fb_info *info)

if (x < HVFB_WIDTH_MIN || y < HVFB_HEIGHT_MIN || (synthvid_ver_ge(par->synthvid_version, SYNTHVID_VERSION_WIN10) && - (x > screen_width_max || y > screen_height_max)) || + (x * y * screen_depth / 8 > screen_fb_size)) || (par->synthvid_version == SYNTHVID_VERSION_WIN8 && x * y * screen_depth / 8 > SYNTHVID_FB_SIZE_WIN8) || (par->synthvid_version == SYNTHVID_VERSION_WIN7 && @@ -1193,8 +1183,8 @@ static int hvfb_probe(struct hv_device *hdev, }

hvfb_get_option(info); - pr_info("Screen resolution: %dx%d, Color depth: %d\n", - screen_width, screen_height, screen_depth); + pr_info("Screen resolution: %dx%d, Color depth: %d, Frame buffer size: %d\n", + screen_width, screen_height, screen_depth, screen_fb_size);

ret = hvfb_getmem(hdev, info); if (ret) { diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 040db0dfba26..b5e9bfe884c4 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3103,10 +3103,8 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, inode_lock(inode); err = btrfs_delete_subvolume(dir, dentry); inode_unlock(inode); - if (!err) { - fsnotify_rmdir(dir, dentry); - d_delete(dentry); - } + if (!err) + d_delete_notify(dir, dentry);

out_dput: dput(dentry); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 8ed881fd7440..450050801f3b 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -577,6 +577,7 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry, struct ceph_inode_info *ci = ceph_inode(dir); struct inode *inode; struct timespec64 now; + struct ceph_string *pool_ns; struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb); struct ceph_vino vino = { .ino = req->r_deleg_ino, .snap = CEPH_NOSNAP }; @@ -626,6 +627,12 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry, in.max_size = cpu_to_le64(lo->stripe_unit);

ceph_file_layout_to_legacy(lo, &in.layout); + /* lo is private, so pool_ns can't change */ + pool_ns = rcu_dereference_raw(lo->pool_ns); + if (pool_ns) { + iinfo.pool_ns_len = pool_ns->len; + iinfo.pool_ns_data = pool_ns->str; + }

down_read(&mdsc->snap_rwsem); ret = ceph_fill_inode(inode, NULL, &iinfo, NULL, req->r_session, @@ -743,8 +750,10 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, restore_deleg_ino(dir, req->r_deleg_ino); ceph_mdsc_put_request(req); try_async = false; + ceph_put_string(rcu_dereference_raw(lo.pool_ns)); goto retry; } + ceph_put_string(rcu_dereference_raw(lo.pool_ns)); goto out_req; } } diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index b0983e2a4e2c..32ddad3ec5d5 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1805,8 +1805,8 @@ void configfs_unregister_group(struct config_group *group) configfs_detach_group(&group->cg_item); d_inode(dentry)->i_flags |= S_DEAD; dont_mount(dentry); + d_drop(dentry); fsnotify_rmdir(d_inode(parent), dentry); - d_delete(dentry); inode_unlock(d_inode(parent));

dput(dentry); @@ -1947,10 +1947,10 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys) configfs_detach_group(&group->cg_item); d_inode(dentry)->i_flags |= S_DEAD; dont_mount(dentry); - fsnotify_rmdir(d_inode(root), dentry); inode_unlock(d_inode(dentry));

- d_delete(dentry); + d_drop(dentry); + fsnotify_rmdir(d_inode(root), dentry);

inode_unlock(d_inode(root));

diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 42e5a766d33c..4f25015aa534 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -621,8 +621,8 @@ void devpts_pty_kill(struct dentry *dentry)

dentry->d_fsdata = NULL; drop_nlink(dentry->d_inode); - fsnotify_unlink(d_inode(dentry->d_parent), dentry); d_drop(dentry); + fsnotify_unlink(d_inode(dentry->d_parent), dentry); dput(dentry); /* d_alloc_name() in devpts_pty_new() */ }

diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 188f79d76988..b748329bb0ba 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -2795,6 +2795,7 @@ struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh) jbd_unlock_bh_journal_head(bh); return jh; } +EXPORT_SYMBOL(jbd2_journal_grab_journal_head);

static void __journal_remove_journal_head(struct buffer_head *bh) { @@ -2847,6 +2848,7 @@ void jbd2_journal_put_journal_head(struct journal_head *jh) jbd_unlock_bh_journal_head(bh); } } +EXPORT_SYMBOL(jbd2_journal_put_journal_head);

/* * Initialize jbd inode head diff --git a/fs/namei.c b/fs/namei.c index 4c9d0c36545d..72f354b62dd5 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3709,13 +3709,12 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry) dentry->d_inode->i_flags |= S_DEAD; dont_mount(dentry); detach_mounts(dentry); - fsnotify_rmdir(dir, dentry);

out: inode_unlock(dentry->d_inode); dput(dentry); if (!error) - d_delete(dentry); + d_delete_notify(dir, dentry); return error; } EXPORT_SYMBOL(vfs_rmdir); @@ -3825,7 +3824,6 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegate if (!error) { dont_mount(dentry); detach_mounts(dentry); - fsnotify_unlink(dir, dentry); } } } @@ -3833,9 +3831,11 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegate inode_unlock(target);

/* We don't d_delete() NFS sillyrenamed files--they still exist. */ - if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) { + if (!error && dentry->d_flags & DCACHE_NFSFS_RENAMED) { + fsnotify_unlink(dir, dentry); + } else if (!error) { fsnotify_link_count(target); - d_delete(dentry); + d_delete_notify(dir, dentry); }

return error; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 8b963c72dd3b..a23b7a5dec9e 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1777,6 +1777,24 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,

no_open: res = nfs_lookup(dir, dentry, lookup_flags); + if (!res) { + inode = d_inode(dentry); + if ((lookup_flags & LOOKUP_DIRECTORY) && inode && + !S_ISDIR(inode->i_mode)) + res = ERR_PTR(-ENOTDIR); + else if (inode && S_ISREG(inode->i_mode)) + res = ERR_PTR(-EOPENSTALE); + } else if (!IS_ERR(res)) { + inode = d_inode(res); + if ((lookup_flags & LOOKUP_DIRECTORY) && inode && + !S_ISDIR(inode->i_mode)) { + dput(res); + res = ERR_PTR(-ENOTDIR); + } else if (inode && S_ISREG(inode->i_mode)) { + dput(res); + res = ERR_PTR(-EOPENSTALE); + } + } if (switched) { d_lookup_done(dentry); if (!res) @@ -2174,6 +2192,8 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)

trace_nfs_link_enter(inode, dir, dentry); d_drop(dentry); + if (S_ISREG(inode->i_mode)) + nfs_sync_inode(inode); error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name); if (error == 0) { ihold(inode); @@ -2262,6 +2282,8 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, } }

+ if (S_ISREG(old_inode->i_mode)) + nfs_sync_inode(old_inode); task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, NULL); if (IS_ERR(task)) { error = PTR_ERR(task); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index a8f954bbde4f..dedec4771ecc 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1247,7 +1247,8 @@ static void nfsdfs_remove_file(struct inode *dir, struct dentry *dentry) clear_ncl(d_inode(dentry)); dget(dentry); ret = simple_unlink(dir, dentry); - d_delete(dentry); + d_drop(dentry); + fsnotify_unlink(dir, dentry); dput(dentry); WARN_ON_ONCE(ret); } @@ -1336,8 +1337,8 @@ void nfsd_client_rmdir(struct dentry *dentry) dget(dentry); ret = simple_rmdir(dir, dentry); WARN_ON_ONCE(ret); + d_drop(dentry); fsnotify_rmdir(dir, dentry); - d_delete(dentry); dput(dentry); inode_unlock(dir); } diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index e7d04adb6cb8..4f48003e4327 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -1253,26 +1253,23 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh, { struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data; struct journal_head *jh; - int ret = 1; + int ret;

if (ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap)) return 0;

- if (!buffer_jbd(bg_bh)) + jh = jbd2_journal_grab_journal_head(bg_bh); + if (!jh) return 1;

- jbd_lock_bh_journal_head(bg_bh); - if (buffer_jbd(bg_bh)) { - jh = bh2jh(bg_bh); - spin_lock(&jh->b_state_lock); - bg = (struct ocfs2_group_desc *) jh->b_committed_data; - if (bg) - ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap); - else - ret = 1; - spin_unlock(&jh->b_state_lock); - } - jbd_unlock_bh_journal_head(bg_bh); + spin_lock(&jh->b_state_lock); + bg = (struct ocfs2_group_desc *) jh->b_committed_data; + if (bg) + ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap); + else + ret = 1; + spin_unlock(&jh->b_state_lock); + jbd2_journal_put_journal_head(jh);

return ret; } diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 0dd2f93ac048..d32b836f6ca7 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -257,10 +257,6 @@ int udf_expand_file_adinicb(struct inode *inode) char *kaddr; struct udf_inode_info *iinfo = UDF_I(inode); int err; - struct writeback_control udf_wbc = { - .sync_mode = WB_SYNC_NONE, - .nr_to_write = 1, - };

WARN_ON_ONCE(!inode_is_locked(inode)); if (!iinfo->i_lenAlloc) { @@ -304,8 +300,10 @@ int udf_expand_file_adinicb(struct inode *inode) iinfo->i_alloc_type = ICBTAG_FLAG_AD_LONG; /* from now on we have normal address_space methods */ inode->i_data.a_ops = &udf_aops; + set_page_dirty(page); + unlock_page(page); up_write(&iinfo->i_data_sem); - err = inode->i_data.a_ops->writepage(page, &udf_wbc); + err = filemap_fdatawrite(inode->i_mapping); if (err) { /* Restore everything back so that we don't lose data... */ lock_page(page); @@ -316,6 +314,7 @@ int udf_expand_file_adinicb(struct inode *inode) unlock_page(page); iinfo->i_alloc_type = ICBTAG_FLAG_AD_IN_ICB; inode->i_data.a_ops = &udf_adinicb_aops; + iinfo->i_lenAlloc = inode->i_size; up_write(&iinfo->i_data_sem); } put_page(page); diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index f8acddcf54fb..79add91eaa04 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -203,6 +203,42 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, fsnotify_name(dir, FS_CREATE, inode, &new_dentry->d_name, 0); }

+/* + * fsnotify_delete - @dentry was unlinked and unhashed + * + * Caller must make sure that dentry->d_name is stable. + * + * Note: unlike fsnotify_unlink(), we have to pass also the unlinked inode + * as this may be called after d_delete() and old_dentry may be negative. + */ +static inline void fsnotify_delete(struct inode *dir, struct inode *inode, + struct dentry *dentry) +{ + __u32 mask = FS_DELETE; + + if (S_ISDIR(inode->i_mode)) + mask |= FS_ISDIR; + + fsnotify_name(dir, mask, inode, &dentry->d_name, 0); +} + +/** + * d_delete_notify - delete a dentry and call fsnotify_delete() + * @dentry: The dentry to delete + * + * This helper is used to guaranty that the unlinked inode cannot be found + * by lookup of this name after fsnotify_delete() event has been delivered. + */ +static inline void d_delete_notify(struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + + ihold(inode); + d_delete(dentry); + fsnotify_delete(dir, inode, dentry); + iput(inode); +} + /* * fsnotify_unlink - 'name' was unlinked * @@ -210,10 +246,10 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, */ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry) { - /* Expected to be called before d_delete() */ - WARN_ON_ONCE(d_is_negative(dentry)); + if (WARN_ON_ONCE(d_is_negative(dentry))) + return;

- fsnotify_dirent(dir, dentry, FS_DELETE); + fsnotify_delete(dir, d_inode(dentry), dentry); }

/* @@ -233,10 +269,10 @@ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) */ static inline void fsnotify_rmdir(struct inode *dir, struct dentry *dentry) { - /* Expected to be called before d_delete() */ - WARN_ON_ONCE(d_is_negative(dentry)); + if (WARN_ON_ONCE(d_is_negative(dentry))) + return;

- fsnotify_dirent(dir, dentry, FS_DELETE | FS_ISDIR); + fsnotify_delete(dir, d_inode(dentry), dentry); }

/* diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3476d20b75d4..fe3155736d63 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2543,6 +2543,7 @@ struct packet_type { struct net_device *); bool (*id_match)(struct packet_type *ptype, struct sock *sk); + struct net *af_packet_net; void *af_packet_priv; struct list_head list; }; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index c94551091dad..67a50c78232f 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -678,18 +678,6 @@ struct perf_event { u64 total_time_running; u64 tstamp;

- /* - * timestamp shadows the actual context timing but it can - * be safely used in NMI interrupt context. It reflects the - * context time as it was when the event was last scheduled in, - * or when ctx_sched_in failed to schedule the event because we - * run out of PMC. - * - * ctx_time already accounts for ctx->timestamp. Therefore to - * compute ctx_time for a sample, simply add perf_clock(). - */ - u64 shadow_ctx_time; - struct perf_event_attr attr; u16 header_size; u16 id_header_size; @@ -834,6 +822,7 @@ struct perf_event_context { */ u64 time; u64 timestamp; + u64 timeoffset;

/* * These fields let us detect when two contexts have both @@ -916,6 +905,8 @@ struct bpf_perf_event_data_kern { struct perf_cgroup_info { u64 time; u64 timestamp; + u64 timeoffset; + int active; };

struct perf_cgroup { diff --git a/include/linux/usb/role.h b/include/linux/usb/role.h index 0164fed31b06..b9ccaeb8a4ae 100644 --- a/include/linux/usb/role.h +++ b/include/linux/usb/role.h @@ -90,6 +90,12 @@ fwnode_usb_role_switch_get(struct fwnode_handle *node)

static inline void usb_role_switch_put(struct usb_role_switch *sw) { }

+static inline struct usb_role_switch * +usb_role_switch_find_by_fwnode(const struct fwnode_handle *fwnode) +{ + return NULL; +} + static inline struct usb_role_switch * usb_role_switch_register(struct device *parent, const struct usb_role_switch_desc *desc) diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 78ea3e332688..e7ce719838b5 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -6,6 +6,8 @@ #define RTR_SOLICITATION_INTERVAL (4*HZ) #define RTR_SOLICITATION_MAX_INTERVAL (3600*HZ) /* 1 hour */

+#define MIN_VALID_LIFETIME (2*3600) /* 2 hours */ + #define TEMP_VALID_LIFETIME (7*86400) #define TEMP_PREFERRED_LIFETIME (86400) #define REGEN_MAX_RETRY (3) diff --git a/include/net/ip.h b/include/net/ip.h index 5538e54d4620..de2dc22a78f9 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -506,19 +506,18 @@ static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb, { struct iphdr *iph = ip_hdr(skb);

+ /* We had many attacks based on IPID, use the private + * generator as much as we can. + */ + if (sk && inet_sk(sk)->inet_daddr) { + iph->id = htons(inet_sk(sk)->inet_id); + inet_sk(sk)->inet_id += segs; + return; + } if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) { - /* This is only to work around buggy Windows95/2000 - * VJ compression implementations. If the ID field - * does not change, they drop every other packet in - * a TCP stream using header compression. - */ - if (sk && inet_sk(sk)->inet_daddr) { - iph->id = htons(inet_sk(sk)->inet_id); - inet_sk(sk)->inet_id += segs; - } else { - iph->id = 0; - } + iph->id = 0; } else { + /* Unfortunately we need the big hammer to get a suitable IPID */ __ip_select_ident(net, iph, segs); } } diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 88bc66b8d02b..95d93ecf0737 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -280,7 +280,7 @@ static inline bool fib6_get_cookie_safe(const struct fib6_info *f6i, fn = rcu_dereference(f6i->fib6_node);

if (fn) { - *cookie = fn->fn_sernum; + *cookie = READ_ONCE(fn->fn_sernum); /* pairs with smp_wmb() in fib6_update_sernum_upto_root() */ smp_rmb(); status = true; diff --git a/include/net/route.h b/include/net/route.h index ff021cab657e..a07c277cd33e 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -369,7 +369,7 @@ static inline struct neighbour *ip_neigh_gw4(struct net_device *dev, { struct neighbour *neigh;

- neigh = __ipv4_neigh_lookup_noref(dev, daddr); + neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)daddr); if (unlikely(!neigh)) neigh = __neigh_create(&arp_tbl, &daddr, dev, false);

diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 4477873ac3a0..56cd7e6589ff 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -664,13 +664,14 @@ BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf, u32, size, u64, flags) { struct pt_regs *regs; - long res; + long res = -EINVAL;

if (!try_get_task_stack(task)) return -EFAULT;

regs = task_pt_regs(task); - res = __bpf_get_stack(regs, task, NULL, buf, size, flags); + if (regs) + res = __bpf_get_stack(regs, task, NULL, buf, size, flags); put_task_stack(task);

return res; diff --git a/kernel/events/core.c b/kernel/events/core.c index e2d774cc470e..c6493f7e0235 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -266,7 +266,7 @@ static void event_function_call(struct perf_event *event, event_f func, void *da if (!event->parent) { /* * If this is a !child event, we must hold ctx::mutex to - * stabilize the the event->ctx relation. See + * stabilize the event->ctx relation. See * perf_event_ctx_lock(). */ lockdep_assert_held(&ctx->mutex); @@ -673,6 +673,23 @@ perf_event_set_state(struct perf_event *event, enum perf_event_state state) WRITE_ONCE(event->state, state); }

+/* + * UP store-release, load-acquire + */ + +#define __store_release(ptr, val) \ +do { \ + barrier(); \ + WRITE_ONCE(*(ptr), (val)); \ +} while (0) + +#define __load_acquire(ptr) \ +({ \ + __unqual_scalar_typeof(*(ptr)) ___p = READ_ONCE(*(ptr)); \ + barrier(); \ + ___p; \ +}) + #ifdef CONFIG_CGROUP_PERF

static inline bool @@ -718,34 +735,51 @@ static inline u64 perf_cgroup_event_time(struct perf_event *event) return t->time; }

-static inline void __update_cgrp_time(struct perf_cgroup *cgrp) +static inline u64 perf_cgroup_event_time_now(struct perf_event *event, u64 now) { - struct perf_cgroup_info *info; - u64 now; - - now = perf_clock(); + struct perf_cgroup_info *t;

- info = this_cpu_ptr(cgrp->info); + t = per_cpu_ptr(event->cgrp->info, event->cpu); + if (!__load_acquire(&t->active)) + return t->time; + now += READ_ONCE(t->timeoffset); + return now; +}

- info->time += now - info->timestamp; +static inline void __update_cgrp_time(struct perf_cgroup_info *info, u64 now, bool adv) +{ + if (adv) + info->time += now - info->timestamp; info->timestamp = now; + /* + * see update_context_time() + */ + WRITE_ONCE(info->timeoffset, info->time - info->timestamp); }

-static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) +static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, bool final) { struct perf_cgroup *cgrp = cpuctx->cgrp; struct cgroup_subsys_state *css; + struct perf_cgroup_info *info;

if (cgrp) { + u64 now = perf_clock(); + for (css = &cgrp->css; css; css = css->parent) { cgrp = container_of(css, struct perf_cgroup, css); - __update_cgrp_time(cgrp); + info = this_cpu_ptr(cgrp->info); + + __update_cgrp_time(info, now, true); + if (final) + __store_release(&info->active, 0); } } }

static inline void update_cgrp_time_from_event(struct perf_event *event) { + struct perf_cgroup_info *info; struct perf_cgroup *cgrp;

/* @@ -759,8 +793,10 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) /* * Do not update time when cgroup is not active */ - if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) - __update_cgrp_time(event->cgrp); + if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) { + info = this_cpu_ptr(event->cgrp->info); + __update_cgrp_time(info, perf_clock(), true); + } }

static inline void @@ -784,7 +820,8 @@ perf_cgroup_set_timestamp(struct task_struct *task, for (css = &cgrp->css; css; css = css->parent) { cgrp = container_of(css, struct perf_cgroup, css); info = this_cpu_ptr(cgrp->info); - info->timestamp = ctx->timestamp; + __update_cgrp_time(info, ctx->timestamp, false); + __store_release(&info->active, 1); } }

@@ -980,14 +1017,6 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event, return ret; }

-static inline void -perf_cgroup_set_shadow_time(struct perf_event *event, u64 now) -{ - struct perf_cgroup_info *t; - t = per_cpu_ptr(event->cgrp->info, event->cpu); - event->shadow_ctx_time = now - t->timestamp; -} - static inline void perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ctx) { @@ -1065,7 +1094,8 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) { }

-static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) +static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, + bool final) { }

@@ -1097,12 +1127,12 @@ perf_cgroup_switch(struct task_struct *task, struct task_struct *next) { }

-static inline void -perf_cgroup_set_shadow_time(struct perf_event *event, u64 now) +static inline u64 perf_cgroup_event_time(struct perf_event *event) { + return 0; }

-static inline u64 perf_cgroup_event_time(struct perf_event *event) +static inline u64 perf_cgroup_event_time_now(struct perf_event *event, u64 now) { return 0; } @@ -1300,7 +1330,7 @@ static void put_ctx(struct perf_event_context *ctx) * life-time rules separate them. That is an exiting task cannot fork, and a * spawning task cannot (yet) exit. * - * But remember that that these are parent<->child context relations, and + * But remember that these are parent<->child context relations, and * migration does not affect children, therefore these two orderings should not * interact. * @@ -1439,7 +1469,7 @@ static u64 primary_event_id(struct perf_event *event) /* * Get the perf_event_context for a task and lock it. * - * This has to cope with with the fact that until it is locked, + * This has to cope with the fact that until it is locked, * the context could get moved to another task. */ static struct perf_event_context * @@ -1524,22 +1554,59 @@ static void perf_unpin_context(struct perf_event_context *ctx) /* * Update the record of the current time in a context. */ -static void update_context_time(struct perf_event_context *ctx) +static void __update_context_time(struct perf_event_context *ctx, bool adv) { u64 now = perf_clock();

- ctx->time += now - ctx->timestamp; + if (adv) + ctx->time += now - ctx->timestamp; ctx->timestamp = now; + + /* + * The above: time' = time + (now - timestamp), can be re-arranged + * into: time` = now + (time - timestamp), which gives a single value + * offset to compute future time without locks on. + * + * See perf_event_time_now(), which can be used from NMI context where + * it's (obviously) not possible to acquire ctx->lock in order to read + * both the above values in a consistent manner. + */ + WRITE_ONCE(ctx->timeoffset, ctx->time - ctx->timestamp); +} + +static void update_context_time(struct perf_event_context *ctx) +{ + __update_context_time(ctx, true); }

static u64 perf_event_time(struct perf_event *event) { struct perf_event_context *ctx = event->ctx;

+ if (unlikely(!ctx)) + return 0; + if (is_cgroup_event(event)) return perf_cgroup_event_time(event);

- return ctx ? ctx->time : 0; + return ctx->time; +} + +static u64 perf_event_time_now(struct perf_event *event, u64 now) +{ + struct perf_event_context *ctx = event->ctx; + + if (unlikely(!ctx)) + return 0; + + if (is_cgroup_event(event)) + return perf_cgroup_event_time_now(event, now); + + if (!(__load_acquire(&ctx->is_active) & EVENT_TIME)) + return ctx->time; + + now += READ_ONCE(ctx->timeoffset); + return now; }

static enum event_type_t get_event_type(struct perf_event *event) @@ -2333,7 +2400,7 @@ __perf_remove_from_context(struct perf_event *event,

if (ctx->is_active & EVENT_TIME) { update_context_time(ctx); - update_cgrp_time_from_cpuctx(cpuctx); + update_cgrp_time_from_cpuctx(cpuctx, false); }

event_sched_out(event, cpuctx, ctx); @@ -2342,6 +2409,9 @@ __perf_remove_from_context(struct perf_event *event, list_del_event(event, ctx);

if (!ctx->nr_events && ctx->is_active) { + if (ctx == &cpuctx->ctx) + update_cgrp_time_from_cpuctx(cpuctx, true); + ctx->is_active = 0; ctx->rotate_necessary = 0; if (ctx->task) { @@ -2467,40 +2537,6 @@ void perf_event_disable_inatomic(struct perf_event *event) irq_work_queue(&event->pending); }

-static void perf_set_shadow_time(struct perf_event *event, - struct perf_event_context *ctx) -{ - /* - * use the correct time source for the time snapshot - * - * We could get by without this by leveraging the - * fact that to get to this function, the caller - * has most likely already called update_context_time() - * and update_cgrp_time_xx() and thus both timestamp - * are identical (or very close). Given that tstamp is, - * already adjusted for cgroup, we could say that: - * tstamp - ctx->timestamp - * is equivalent to - * tstamp - cgrp->timestamp. - * - * Then, in perf_output_read(), the calculation would - * work with no changes because: - * - event is guaranteed scheduled in - * - no scheduled out in between - * - thus the timestamp would be the same - * - * But this is a bit hairy. - * - * So instead, we have an explicit cgroup call to remain - * within the time time source all along. We believe it - * is cleaner and simpler to understand. - */ - if (is_cgroup_event(event)) - perf_cgroup_set_shadow_time(event, event->tstamp); - else - event->shadow_ctx_time = event->tstamp - ctx->timestamp; -} - #define MAX_INTERRUPTS (~0ULL)

static void perf_log_throttle(struct perf_event *event, int enable); @@ -2541,8 +2577,6 @@ event_sched_in(struct perf_event *event,

perf_pmu_disable(event->pmu);

- perf_set_shadow_time(event, ctx); - perf_log_itrace_start(event);

if (event->pmu->add(event, PERF_EF_START)) { @@ -3216,16 +3250,6 @@ static void ctx_sched_out(struct perf_event_context *ctx, return; }

- ctx->is_active &= ~event_type; - if (!(ctx->is_active & EVENT_ALL)) - ctx->is_active = 0; - - if (ctx->task) { - WARN_ON_ONCE(cpuctx->task_ctx != ctx); - if (!ctx->is_active) - cpuctx->task_ctx = NULL; - } - /* * Always update time if it was set; not only when it changes. * Otherwise we can 'forget' to update time for any but the last @@ -3239,7 +3263,22 @@ static void ctx_sched_out(struct perf_event_context *ctx, if (is_active & EVENT_TIME) { /* update (and stop) ctx time */ update_context_time(ctx); - update_cgrp_time_from_cpuctx(cpuctx); + update_cgrp_time_from_cpuctx(cpuctx, ctx == &cpuctx->ctx); + /* + * CPU-release for the below ->is_active store, + * see __load_acquire() in perf_event_time_now() + */ + barrier(); + } + + ctx->is_active &= ~event_type; + if (!(ctx->is_active & EVENT_ALL)) + ctx->is_active = 0; + + if (ctx->task) { + WARN_ON_ONCE(cpuctx->task_ctx != ctx); + if (!ctx->is_active) + cpuctx->task_ctx = NULL; }

is_active ^= ctx->is_active; /* changed bits */ @@ -3676,13 +3715,19 @@ static noinline int visit_groups_merge(struct perf_cpu_context *cpuctx, return 0; }

+/* + * Because the userpage is strictly per-event (there is no concept of context, + * so there cannot be a context indirection), every userpage must be updated + * when context time starts :-( + * + * IOW, we must not miss EVENT_TIME edges. + */ static inline bool event_update_userpage(struct perf_event *event) { if (likely(!atomic_read(&event->mmap_count))) return false;

perf_event_update_time(event); - perf_set_shadow_time(event, event->ctx); perf_event_update_userpage(event);

return true; @@ -3766,13 +3811,23 @@ ctx_sched_in(struct perf_event_context *ctx, struct task_struct *task) { int is_active = ctx->is_active; - u64 now;

lockdep_assert_held(&ctx->lock);

if (likely(!ctx->nr_events)) return;

+ if (is_active ^ EVENT_TIME) { + /* start ctx time */ + __update_context_time(ctx, false); + perf_cgroup_set_timestamp(task, ctx); + /* + * CPU-release for the below ->is_active store, + * see __load_acquire() in perf_event_time_now() + */ + barrier(); + } + ctx->is_active |= (event_type | EVENT_TIME); if (ctx->task) { if (!is_active) @@ -3783,13 +3838,6 @@ ctx_sched_in(struct perf_event_context *ctx,

is_active ^= ctx->is_active; /* changed bits */

- if (is_active & EVENT_TIME) { - /* start ctx time */ - now = perf_clock(); - ctx->timestamp = now; - perf_cgroup_set_timestamp(task, ctx); - } - /* * First go through the list and put on any pinned groups * in order to give them the best chance of going on. @@ -4325,6 +4373,18 @@ static inline u64 perf_event_count(struct perf_event *event) return local64_read(&event->count) + atomic64_read(&event->child_count); }

+static void calc_timer_values(struct perf_event *event, + u64 *now, + u64 *enabled, + u64 *running) +{ + u64 ctx_time; + + *now = perf_clock(); + ctx_time = perf_event_time_now(event, *now); + __perf_update_times(event, ctx_time, enabled, running); +} + /* * NMI-safe method to read a local event, that is an event that * is: @@ -4384,10 +4444,9 @@ int perf_event_read_local(struct perf_event *event, u64 *value,

*value = local64_read(&event->count); if (enabled || running) { - u64 now = event->shadow_ctx_time + perf_clock(); - u64 __enabled, __running; + u64 __enabled, __running, __now;;

- __perf_update_times(event, now, &__enabled, &__running); + calc_timer_values(event, &__now, &__enabled, &__running); if (enabled) *enabled = __enabled; if (running) @@ -5694,18 +5753,6 @@ static int perf_event_index(struct perf_event *event) return event->pmu->event_idx(event); }

-static void calc_timer_values(struct perf_event *event, - u64 *now, - u64 *enabled, - u64 *running) -{ - u64 ctx_time; - - *now = perf_clock(); - ctx_time = event->shadow_ctx_time + *now; - __perf_update_times(event, ctx_time, enabled, running); -} - static void perf_event_init_userpage(struct perf_event *event) { struct perf_event_mmap_page *userpg; @@ -6245,7 +6292,6 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) ring_buffer_attach(event, rb);

perf_event_update_time(event); - perf_set_shadow_time(event, event->ctx); perf_event_init_userpage(event); perf_event_update_userpage(event); } else { diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 00b0358739ab..e1bbb3b92921 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1735,7 +1735,7 @@ void uprobe_free_utask(struct task_struct *t) }

/* - * Allocate a uprobe_task object for the task if if necessary. + * Allocate a uprobe_task object for the task if necessary. * Called when the thread hits a breakpoint. * * Returns: diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 2f8cd616d3b2..f00dd928fc71 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1438,7 +1438,7 @@ rt_mutex_fasttrylock(struct rt_mutex *lock, }

/* - * Performs the wakeup of the the top-waiter and re-enables preemption. + * Performs the wakeup of the top-waiter and re-enables preemption. */ void rt_mutex_postunlock(struct wake_q_head *wake_q) { @@ -1832,7 +1832,7 @@ struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock) * been started. * @waiter: the pre-initialized rt_mutex_waiter * - * Wait for the the lock acquisition started on our behalf by + * Wait for the lock acquisition started on our behalf by * rt_mutex_start_proxy_lock(). Upon failure, the caller must call * rt_mutex_cleanup_proxy_lock(). * diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index a163542d178e..cc5cc889b5b7 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -1177,7 +1177,7 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)

/* * If there were already threads queued before us and: - * 1) there are no no active locks, wake the front + * 1) there are no active locks, wake the front * queued process(es) as the handoff bit might be set. * 2) there are no active writers and some readers, the lock * must be read owned; so we try to wake any read lock diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c index d9dd94defc0a..9aa855a96c4a 100644 --- a/kernel/locking/semaphore.c +++ b/kernel/locking/semaphore.c @@ -119,7 +119,7 @@ EXPORT_SYMBOL(down_killable); * @sem: the semaphore to be acquired * * Try to acquire the semaphore atomically. Returns 0 if the semaphore has - * been acquired successfully or 1 if it it cannot be acquired. + * been acquired successfully or 1 if it cannot be acquired. * * NOTE: This return value is inverted from both spin_trylock and * mutex_trylock! Be careful about this when converting code. diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c index 105df4dfc783..52571dcad768 100644 --- a/kernel/power/wakelock.c +++ b/kernel/power/wakelock.c @@ -39,23 +39,20 @@ ssize_t pm_show_wakelocks(char *buf, bool show_active) { struct rb_node *node; struct wakelock *wl; - char *str = buf; - char *end = buf + PAGE_SIZE; + int len = 0;

mutex_lock(&wakelocks_lock);

for (node = rb_first(&wakelocks_tree); node; node = rb_next(node)) { wl = rb_entry(node, struct wakelock, node); if (wl->ws->active == show_active) - str += scnprintf(str, end - str, "%s ", wl->name); + len += sysfs_emit_at(buf, len, "%s ", wl->name); } - if (str > buf) - str--;

- str += scnprintf(str, end - str, "\n"); + len += sysfs_emit_at(buf, len, "\n");

mutex_unlock(&wakelocks_lock); - return (str - buf); + return len; }

#if CONFIG_PM_WAKELOCKS_LIMIT > 0 diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 2a33cb5a10e5..acd9833b8ec2 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3379,7 +3379,6 @@ void set_task_rq_fair(struct sched_entity *se, se->avg.last_update_time = n_last_update_time; }

- /* * When on migration a sched_entity joins/leaves the PELT hierarchy, we need to * propagate its contribution. The key to this propagation is the invariant @@ -3447,7 +3446,6 @@ void set_task_rq_fair(struct sched_entity *se, * XXX: only do this for the part of runnable > running ? * */ - static inline void update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { @@ -3676,7 +3674,19 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)

r = removed_util; sub_positive(&sa->util_avg, r); - sa->util_sum = sa->util_avg * divider; + sub_positive(&sa->util_sum, r * divider); + /* + * Because of rounding, se->util_sum might ends up being +1 more than + * cfs->util_sum. Although this is not a problem by itself, detaching + * a lot of tasks with the rounding problem between 2 updates of + * util_avg (~1ms) can make cfs->util_sum becoming null whereas + * cfs_util_avg is not. + * Check that util_sum is still above its lower bound for the new + * util_avg. Given that period_contrib might have moved since the last + * sync, we are only sure that util_sum must be above or equal to + * util_avg * minimum possible divider + */ + sa->util_sum = max_t(u32, sa->util_sum, sa->util_avg * PELT_MIN_DIVIDER);

r = removed_runnable; sub_positive(&sa->runnable_avg, r); @@ -5149,7 +5159,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) /* * When a group wakes up we want to make sure that its quota is not already * expired/exceeded, otherwise it may be allowed to steal additional ticks of - * runtime as update_curr() throttling can not not trigger until it's on-rq. + * runtime as update_curr() throttling can not trigger until it's on-rq. */ static void check_enqueue_throttle(struct cfs_rq *cfs_rq) { diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 16f57e71f9c4..cc7cd512e4e3 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -19,11 +19,11 @@ #endif

#ifdef CONFIG_RSEQ -#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK \ +#define MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK \ (MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ \ - | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ_BITMASK) + | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ) #else -#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK 0 +#define MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK 0 #endif

#define MEMBARRIER_CMD_BITMASK \ @@ -31,7 +31,8 @@ | MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED \ | MEMBARRIER_CMD_PRIVATE_EXPEDITED \ | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED \ - | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK) + | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK \ + | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK)

static void ipi_mb(void *info) { @@ -315,7 +316,7 @@ static int sync_runqueues_membarrier_state(struct mm_struct *mm)

/* * For each cpu runqueue, if the task's mm match @mm, ensure that all - * @mm's membarrier state set bits are also set in in the runqueue's + * @mm's membarrier state set bits are also set in the runqueue's * membarrier state. This ensures that a runqueue scheduling * between threads which are users of @mm has its membarrier state * updated. diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index 0b9aeebb9c32..45bf08e22207 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -37,9 +37,11 @@ update_irq_load_avg(struct rq *rq, u64 running) } #endif

+#define PELT_MIN_DIVIDER (LOAD_AVG_MAX - 1024) + static inline u32 get_pelt_divider(struct sched_avg *avg) { - return LOAD_AVG_MAX - 1024 + avg->period_contrib; + return PELT_MIN_DIVIDER + avg->period_contrib; }

static inline void cfs_se_util_change(struct sched_avg *avg) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index cd2d094b9f82..a0729213f37b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7257,7 +7257,8 @@ static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr) err = kzalloc(sizeof(*err), GFP_KERNEL); if (!err) err = ERR_PTR(-ENOMEM); - tr->n_err_log_entries++; + else + tr->n_err_log_entries++;

return err; } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 003e5f37861e..1557a20b6500 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -3506,6 +3506,7 @@ static int trace_action_create(struct hist_trigger_data *hist_data,

var_ref_idx = find_var_ref_idx(hist_data, var_ref); if (WARN_ON(var_ref_idx < 0)) { + kfree(p); ret = var_ref_idx; goto err; } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 7ffcca9ae82a..72b4127360c7 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -5661,6 +5661,11 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) struct hci_ev_le_advertising_info *ev = ptr; s8 rssi;

+ if (ptr > (void *)skb_tail_pointer(skb) - sizeof(*ev)) { + bt_dev_err(hdev, "Malicious advertising data."); + break; + } + if (ev->length <= HCI_MAX_AD_LENGTH && ev->data + ev->length <= skb_tail_pointer(skb)) { rssi = ev->data[ev->length]; @@ -5672,11 +5677,6 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) }

ptr += sizeof(*ev) + ev->length + 1; - - if (ptr > (void *) skb_tail_pointer(skb) - sizeof(*ev)) { - bt_dev_err(hdev, "Malicious advertising data. Stopping processing"); - break; - } }

hci_dev_unlock(hdev); diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 08c77418c687..852f4b54e881 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -543,10 +543,10 @@ static bool __allowed_ingress(const struct net_bridge *br, if (!br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { if (*state == BR_STATE_FORWARDING) { *state = br_vlan_get_pvid_state(vg); - return br_vlan_state_allowed(*state, true); - } else { - return true; + if (!br_vlan_state_allowed(*state, true)) + goto drop; } + return true; } } v = br_vlan_find(vg, *vid); @@ -1873,7 +1873,8 @@ static int br_vlan_rtm_dump(struct sk_buff *skb, struct netlink_callback *cb) goto out_err; } err = br_vlan_dump_dev(dev, skb, cb, dump_flags); - if (err && err != -EMSGSIZE) + /* if the dump completed without an error we return 0 here */ + if (err != -EMSGSIZE) goto out_err; } else { for_each_netdev_rcu(net, dev) { diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index c714e6a9dad4..eadb696360b4 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -193,12 +193,23 @@ static const struct seq_operations softnet_seq_ops = { .show = softnet_seq_show, };

-static void *ptype_get_idx(loff_t pos) +static void *ptype_get_idx(struct seq_file *seq, loff_t pos) { + struct list_head *ptype_list = NULL; struct packet_type *pt = NULL; + struct net_device *dev; loff_t i = 0; int t;

+ for_each_netdev_rcu(seq_file_net(seq), dev) { + ptype_list = &dev->ptype_all; + list_for_each_entry_rcu(pt, ptype_list, list) { + if (i == pos) + return pt; + ++i; + } + } + list_for_each_entry_rcu(pt, &ptype_all, list) { if (i == pos) return pt; @@ -219,22 +230,40 @@ static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); - return *pos ? ptype_get_idx(*pos - 1) : SEQ_START_TOKEN; + return *pos ? ptype_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; }

static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) { + struct net_device *dev; struct packet_type *pt; struct list_head *nxt; int hash;

++*pos; if (v == SEQ_START_TOKEN) - return ptype_get_idx(0); + return ptype_get_idx(seq, 0);

pt = v; nxt = pt->list.next; + if (pt->dev) { + if (nxt != &pt->dev->ptype_all) + goto found; + + dev = pt->dev; + for_each_netdev_continue_rcu(seq_file_net(seq), dev) { + if (!list_empty(&dev->ptype_all)) { + nxt = dev->ptype_all.next; + goto found; + } + } + + nxt = ptype_all.next; + goto ptype_all; + } + if (pt->type == htons(ETH_P_ALL)) { +ptype_all: if (nxt != &ptype_all) goto found; hash = 0; @@ -263,7 +292,8 @@ static int ptype_seq_show(struct seq_file *seq, void *v)

if (v == SEQ_START_TOKEN) seq_puts(seq, "Type Device Function\n"); - else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) { + else if ((!pt->af_packet_net || net_eq(pt->af_packet_net, seq_file_net(seq))) && + (!pt->dev || net_eq(dev_net(pt->dev), seq_file_net(seq)))) { if (pt->type == htons(ETH_P_ALL)) seq_puts(seq, "ALL "); else diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 10d4cde31c6b..5e48b3d3a00d 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -162,12 +162,19 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; - if (ip_dont_fragment(sk, &rt->dst)) { + /* Do not bother generating IPID for small packets (eg SYNACK) */ + if (skb->len <= IPV4_MIN_MTU || ip_dont_fragment(sk, &rt->dst)) { iph->frag_off = htons(IP_DF); iph->id = 0; } else { iph->frag_off = 0; - __ip_select_ident(net, iph, 1); + /* TCP packets here are SYNACK with fat IPv4/TCP options. + * Avoid using the hashed IP ident generator. + */ + if (sk->sk_protocol == IPPROTO_TCP) + iph->id = (__force __be16)prandom_u32(); + else + __ip_select_ident(net, iph, 1); }

if (opt && opt->opt.optlen) { @@ -614,18 +621,6 @@ void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph, } EXPORT_SYMBOL(ip_fraglist_init);

-static void ip_fraglist_ipcb_prepare(struct sk_buff *skb, - struct ip_fraglist_iter *iter) -{ - struct sk_buff *to = iter->frag; - - /* Copy the flags to each fragment. */ - IPCB(to)->flags = IPCB(skb)->flags; - - if (iter->offset == 0) - ip_options_fragment(to); -} - void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter) { unsigned int hlen = iter->hlen; @@ -671,7 +666,7 @@ void ip_frag_init(struct sk_buff *skb, unsigned int hlen, EXPORT_SYMBOL(ip_frag_init);

static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to, - bool first_frag, struct ip_frag_state *state) + bool first_frag) { /* Copy the flags to each fragment. */ IPCB(to)->flags = IPCB(from)->flags; @@ -850,8 +845,20 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, /* Prepare header of the next frame, * before previous one went down. */ if (iter.frag) { - ip_fraglist_ipcb_prepare(skb, &iter); + bool first_frag = (iter.offset == 0); + + IPCB(iter.frag)->flags = IPCB(skb)->flags; ip_fraglist_prepare(skb, &iter); + if (first_frag && IPCB(skb)->opt.optlen) { + /* ipcb->opt is not populated for frags + * coming from __ip_make_skb(), + * ip_options_fragment() needs optlen + */ + IPCB(iter.frag)->opt.optlen = + IPCB(skb)->opt.optlen; + ip_options_fragment(iter.frag); + ip_send_check(iter.iph); + } }

skb->tstamp = tstamp; @@ -905,7 +912,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, err = PTR_ERR(skb2); goto fail; } - ip_frag_ipcb(skb, skb2, first_frag, &state); + ip_frag_ipcb(skb, skb2, first_frag);

/* * Put this fragment into the sending queue. diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 8ce8b7300b9d..a5722905456c 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -220,7 +220,8 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) continue; }

- if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) + if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif && + sk->sk_bound_dev_if != inet_sdif(skb)) continue;

sock_hold(sk); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 7d26e0f8bdae..5d95f80314f9 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -721,6 +721,7 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) int ret = -EINVAL; int chk_addr_ret;

+ lock_sock(sk); if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_in)) goto out;

@@ -740,7 +741,9 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_saddr = 0; /* Use device */ sk_dst_reset(sk); ret = 0; -out: return ret; +out: + release_sock(sk); + return ret; }

/* diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 29526937077b..4dde49e628fa 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2577,7 +2577,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, __u32 valid_lft, u32 prefered_lft) { struct inet6_ifaddr *ifp = ipv6_get_ifaddr(net, addr, dev, 1); - int create = 0; + int create = 0, update_lft = 0;

if (!ifp && valid_lft) { int max_addresses = in6_dev->cnf.max_addresses; @@ -2621,19 +2621,32 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, unsigned long now; u32 stored_lft;

- /* Update lifetime (RFC4862 5.5.3 e) - * We deviate from RFC4862 by honoring all Valid Lifetimes to - * improve the reaction of SLAAC to renumbering events - * (draft-gont-6man-slaac-renum-06, Section 4.2) - */ + /* update lifetime (RFC2462 5.5.3 e) */ spin_lock_bh(&ifp->lock); now = jiffies; if (ifp->valid_lft > (now - ifp->tstamp) / HZ) stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ; else stored_lft = 0; - if (!create && stored_lft) { + const u32 minimum_lft = min_t(u32, + stored_lft, MIN_VALID_LIFETIME); + valid_lft = max(valid_lft, minimum_lft); + + /* RFC4862 Section 5.5.3e: + * "Note that the preferred lifetime of the + * corresponding address is always reset to + * the Preferred Lifetime in the received + * Prefix Information option, regardless of + * whether the valid lifetime is also reset or + * ignored." + * + * So we should always update prefered_lft here. + */ + update_lft = 1; + } + + if (update_lft) { ifp->valid_lft = valid_lft; ifp->prefered_lft = prefered_lft; ifp->tstamp = now; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index e43f1fbac28b..c783b9123132 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -110,7 +110,7 @@ void fib6_update_sernum(struct net *net, struct fib6_info *f6i) fn = rcu_dereference_protected(f6i->fib6_node, lockdep_is_held(&f6i->fib6_table->tb6_lock)); if (fn) - fn->fn_sernum = fib6_new_sernum(net); + WRITE_ONCE(fn->fn_sernum, fib6_new_sernum(net)); }

/* @@ -587,12 +587,13 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, spin_unlock_bh(&table->tb6_lock); if (res > 0) { cb->args[4] = 1; - cb->args[5] = w->root->fn_sernum; + cb->args[5] = READ_ONCE(w->root->fn_sernum); } } else { - if (cb->args[5] != w->root->fn_sernum) { + int sernum = READ_ONCE(w->root->fn_sernum); + if (cb->args[5] != sernum) { /* Begin at the root if the tree changed */ - cb->args[5] = w->root->fn_sernum; + cb->args[5] = sernum; w->state = FWS_INIT; w->node = w->root; w->skip = w->count; @@ -1342,7 +1343,7 @@ static void __fib6_update_sernum_upto_root(struct fib6_info *rt, /* paired with smp_rmb() in rt6_get_cookie_safe() */ smp_wmb(); while (fn) { - fn->fn_sernum = sernum; + WRITE_ONCE(fn->fn_sernum, sernum); fn = rcu_dereference_protected(fn->parent, lockdep_is_held(&rt->fib6_table->tb6_lock)); } @@ -2171,8 +2172,8 @@ static int fib6_clean_node(struct fib6_walker *w) };

if (c->sernum != FIB6_NO_SERNUM_CHANGE && - w->node->fn_sernum != c->sernum) - w->node->fn_sernum = c->sernum; + READ_ONCE(w->node->fn_sernum) != c->sernum) + WRITE_ONCE(w->node->fn_sernum, c->sernum);

if (!c->func) { WARN_ON_ONCE(c->sernum == FIB6_NO_SERNUM_CHANGE); @@ -2536,7 +2537,7 @@ static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter, iter->w.state = FWS_INIT; iter->w.node = iter->w.root; iter->w.args = iter; - iter->sernum = iter->w.root->fn_sernum; + iter->sernum = READ_ONCE(iter->w.root->fn_sernum); INIT_LIST_HEAD(&iter->w.lh); fib6_walker_link(net, &iter->w); } @@ -2564,8 +2565,10 @@ static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl,

static void ipv6_route_check_sernum(struct ipv6_route_iter *iter) { - if (iter->sernum != iter->w.root->fn_sernum) { - iter->sernum = iter->w.root->fn_sernum; + int sernum = READ_ONCE(iter->w.root->fn_sernum); + + if (iter->sernum != sernum) { + iter->sernum = sernum; iter->w.state = FWS_INIT; iter->w.node = iter->w.root; WARN_ON(iter->w.skip); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 08441f06afd4..3a2741569b84 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1066,14 +1066,14 @@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t,

if (unlikely(!ipv6_chk_addr_and_flags(net, laddr, ldev, false, 0, IFA_F_TENTATIVE))) - pr_warn("%s xmit: Local address not yet configured!\n", - p->name); + pr_warn_ratelimited("%s xmit: Local address not yet configured!\n", + p->name); else if (!(p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) && !ipv6_addr_is_multicast(raddr) && unlikely(ipv6_chk_addr_and_flags(net, raddr, ldev, true, 0, IFA_F_TENTATIVE))) - pr_warn("%s xmit: Routing loop! Remote address found on this node!\n", - p->name); + pr_warn_ratelimited("%s xmit: Routing loop! Remote address found on this node!\n", + p->name); else ret = 1; rcu_read_unlock(); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 654bf4ca6126..352e645c546e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2674,7 +2674,7 @@ static void ip6_link_failure(struct sk_buff *skb) if (from) { fn = rcu_dereference(from->fib6_node); if (fn && (rt->rt6i_flags & RTF_DEFAULT)) - fn->fn_sernum = -1; + WRITE_ONCE(fn->fn_sernum, -1); } } rcu_read_unlock(); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index f4cf26b606f9..8369af0c50ea 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1832,15 +1832,17 @@ nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state) pr_debug("nf_conntrack_in: Can't track with proto module\n"); nf_conntrack_put(&ct->ct_general); skb->_nfct = 0; - NF_CT_STAT_INC_ATOMIC(state->net, invalid); - if (ret == -NF_DROP) - NF_CT_STAT_INC_ATOMIC(state->net, drop); /* Special case: TCP tracker reports an attempt to reopen a * closed/aborted connection. We have to go back and create a * fresh conntrack. */ if (ret == -NF_REPEAT) goto repeat; + + NF_CT_STAT_INC_ATOMIC(state->net, invalid); + if (ret == -NF_DROP) + NF_CT_STAT_INC_ATOMIC(state->net, drop); + ret = -ret; goto out; } diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 1ebee25de677..6a8495bd08bb 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -502,6 +502,9 @@ static int nft_payload_l4csum_offset(const struct nft_pktinfo *pkt, struct sk_buff *skb, unsigned int *l4csum_offset) { + if (pkt->xt.fragoff) + return -1; + switch (pkt->tprot) { case IPPROTO_TCP: *l4csum_offset = offsetof(struct tcphdr, check); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index f78097aa403a..6ef035494f30 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1735,6 +1735,7 @@ static int fanout_add(struct sock *sk, struct fanout_args *args) match->prot_hook.dev = po->prot_hook.dev; match->prot_hook.func = packet_rcv_fanout; match->prot_hook.af_packet_priv = match; + match->prot_hook.af_packet_net = read_pnet(&match->net); match->prot_hook.id_match = match_fanout_group; match->max_num_members = args->max_num_members; list_add(&match->list, &fanout_list); @@ -3323,6 +3324,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, po->prot_hook.func = packet_rcv_spkt;

po->prot_hook.af_packet_priv = sk; + po->prot_hook.af_packet_net = sock_net(sk);

if (proto) { po->prot_hook.type = proto; diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 6be2672a65ea..df864e692267 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -157,7 +157,7 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call) static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) { struct sk_buff *skb; - unsigned long resend_at, rto_j; + unsigned long resend_at; rxrpc_seq_t cursor, seq, top; ktime_t now, max_age, oldest, ack_ts; int ix; @@ -165,10 +165,8 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)

_enter("{%d,%d}", call->tx_hard_ack, call->tx_top);

- rto_j = call->peer->rto_j; - now = ktime_get_real(); - max_age = ktime_sub(now, jiffies_to_usecs(rto_j)); + max_age = ktime_sub(now, jiffies_to_usecs(call->peer->rto_j));

spin_lock_bh(&call->lock);

@@ -213,7 +211,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) }

resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest))); - resend_at += jiffies + rto_j; + resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, retrans); WRITE_ONCE(call->resend_at, resend_at);

if (unacked) diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 10f2bf2e9068..a45c83f22236 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -468,7 +468,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, if (call->peer->rtt_count > 1) { unsigned long nowj = jiffies, ack_lost_at;

- ack_lost_at = rxrpc_get_rto_backoff(call->peer, retrans); + ack_lost_at = rxrpc_get_rto_backoff(call->peer, false); ack_lost_at += nowj; WRITE_ONCE(call->ack_lost_at, ack_lost_at); rxrpc_reduce_call_timer(call, ack_lost_at, nowj, diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index eadc0ede928c..5f854ffbab92 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -599,9 +599,9 @@ static int __rpc_rmdir(struct inode *dir, struct dentry *dentry)

dget(dentry); ret = simple_rmdir(dir, dentry); + d_drop(dentry); if (!ret) fsnotify_rmdir(dir, dentry); - d_delete(dentry); dput(dentry); return ret; } @@ -612,9 +612,9 @@ static int __rpc_unlink(struct inode *dir, struct dentry *dentry)

dget(dentry); ret = simple_unlink(dir, dentry); + d_drop(dentry); if (!ret) fsnotify_unlink(dir, dentry); - d_delete(dentry); dput(dentry); return ret; } diff --git a/usr/include/Makefile b/usr/include/Makefile index f6b3c85d900e..703a255cddc6 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -34,7 +34,6 @@ no-header-test += linux/hdlc/ioctl.h no-header-test += linux/ivtv.h no-header-test += linux/kexec.h no-header-test += linux/matroxfb.h -no-header-test += linux/nfc.h no-header-test += linux/omap3isp.h no-header-test += linux/omapfb.h no-header-test += linux/patchkey.h diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 4a7d377b3a50..d22de4392507 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1691,7 +1691,6 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn { return __gfn_to_memslot(kvm_vcpu_memslots(vcpu), gfn); } -EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_memslot);

bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) {