diff --git a/Makefile b/Makefile index 6d4fca82529a..a8c772b299aa 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 4 -SUBLEVEL = 40 +SUBLEVEL = 41 EXTRAVERSION = NAME = Kleptomaniac Octopus diff --git a/arch/arm/crypto/nhpoly1305-neon-glue.c b/arch/arm/crypto/nhpoly1305-neon-glue.c index ae5aefc44a4d..ffa8d73fe722 100644 --- a/arch/arm/crypto/nhpoly1305-neon-glue.c +++ b/arch/arm/crypto/nhpoly1305-neon-glue.c @@ -30,7 +30,7 @@ static int nhpoly1305_neon_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_neon_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_neon); diff --git a/arch/arm64/crypto/nhpoly1305-neon-glue.c b/arch/arm64/crypto/nhpoly1305-neon-glue.c index 895d3727c1fb..c5405e6a6db7 100644 --- a/arch/arm64/crypto/nhpoly1305-neon-glue.c +++ b/arch/arm64/crypto/nhpoly1305-neon-glue.c @@ -30,7 +30,7 @@ static int nhpoly1305_neon_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_neon_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_neon); diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index dfd626447482..5271ab366bee 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -202,6 +202,13 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) } memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id)); + + if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) { + int i; + + for (i = 0; i < 16; i++) + *vcpu_reg32(vcpu, i) = (u32)*vcpu_reg32(vcpu, i); + } out: return err; } diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index bbeb6a5a6ba6..0be3355e3499 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -230,6 +230,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, ptep = (pte_t *)pudp; } else if (sz == (CONT_PTE_SIZE)) { pmdp = pmd_alloc(mm, pudp, addr); + if (!pmdp) + return NULL; WARN_ON(addr & (sz - 1)); /* diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index f5d813c1304d..319812923012 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -116,7 +116,8 @@ void __init setup_bootmem(void) memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); set_max_mapnr(PFN_DOWN(mem_size)); - max_low_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_low_pfn = max_pfn; #ifdef CONFIG_BLK_DEV_INITRD setup_initrd(); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index ed52ffa8d5d4..560310e29e27 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -626,10 +626,12 @@ static int handle_pqap(struct kvm_vcpu *vcpu) * available for the guest are AQIC and TAPQ with the t bit set * since we do not set IC.3 (FIII) we currently will only intercept * the AQIC function code. + * Note: running nested under z/VM can result in intercepts for other + * function codes, e.g. PQAP(QCI). We do not support this and bail out. */ reg0 = vcpu->run->s.regs.gprs[0]; fc = (reg0 >> 24) & 0xff; - if (WARN_ON_ONCE(fc != 0x03)) + if (fc != 0x03) return -EOPNOTSUPP; /* PQAP instruction is allowed for guest kernel only */ diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c index f7567cbd35b6..80fcb85736e1 100644 --- a/arch/x86/crypto/nhpoly1305-avx2-glue.c +++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c @@ -29,7 +29,7 @@ static int nhpoly1305_avx2_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_fpu_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_avx2); diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c index a661ede3b5cf..cc6b7c1a2705 100644 --- a/arch/x86/crypto/nhpoly1305-sse2-glue.c +++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c @@ -29,7 +29,7 @@ static int nhpoly1305_sse2_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_fpu_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_sse2); diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 515c0ceeb4a3..b3f121478738 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -98,13 +98,6 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 .macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0 - /* - * Push registers and sanitize registers of values that a - * speculation attack might otherwise want to exploit. The - * lower registers are likely clobbered well before they - * could be put to use in a speculative execution gadget. - * Interleave XOR with PUSH for better uop scheduling: - */ .if \save_ret pushq %rsi /* pt_regs->si */ movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */ @@ -114,34 +107,43 @@ For 32-bit we have the following conventions - kernel is built with pushq %rsi /* pt_regs->si */ .endif pushq \rdx /* pt_regs->dx */ - xorl %edx, %edx /* nospec dx */ pushq %rcx /* pt_regs->cx */ - xorl %ecx, %ecx /* nospec cx */ pushq \rax /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 */ - xorl %r8d, %r8d /* nospec r8 */ pushq %r9 /* pt_regs->r9 */ - xorl %r9d, %r9d /* nospec r9 */ pushq %r10 /* pt_regs->r10 */ - xorl %r10d, %r10d /* nospec r10 */ pushq %r11 /* pt_regs->r11 */ - xorl %r11d, %r11d /* nospec r11*/ pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx*/ pushq %rbp /* pt_regs->rbp */ - xorl %ebp, %ebp /* nospec rbp*/ pushq %r12 /* pt_regs->r12 */ - xorl %r12d, %r12d /* nospec r12*/ pushq %r13 /* pt_regs->r13 */ - xorl %r13d, %r13d /* nospec r13*/ pushq %r14 /* pt_regs->r14 */ - xorl %r14d, %r14d /* nospec r14*/ pushq %r15 /* pt_regs->r15 */ - xorl %r15d, %r15d /* nospec r15*/ UNWIND_HINT_REGS + .if \save_ret pushq %rsi /* return address on top of stack */ .endif + + /* + * Sanitize registers of values that a speculation attack might + * otherwise want to exploit. The lower registers are likely clobbered + * well before they could be put to use in a speculative execution + * gadget. + */ + xorl %edx, %edx /* nospec dx */ + xorl %ecx, %ecx /* nospec cx */ + xorl %r8d, %r8d /* nospec r8 */ + xorl %r9d, %r9d /* nospec r9 */ + xorl %r10d, %r10d /* nospec r10 */ + xorl %r11d, %r11d /* nospec r11 */ + xorl %ebx, %ebx /* nospec rbx */ + xorl %ebp, %ebp /* nospec rbp */ + xorl %r12d, %r12d /* nospec r12 */ + xorl %r13d, %r13d /* nospec r13 */ + xorl %r14d, %r14d /* nospec r14 */ + xorl %r15d, %r15d /* nospec r15 */ + .endm .macro POP_REGS pop_rdi=1 skip_r11rcx=0 diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index b7c3ea4cb19d..2ba3d53ac5b1 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -249,7 +249,6 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) */ syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ - UNWIND_HINT_EMPTY POP_REGS pop_rdi=0 skip_r11rcx=1 /* @@ -258,6 +257,7 @@ syscall_return_via_sysret: */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + UNWIND_HINT_EMPTY pushq RSP-RDI(%rdi) /* RSP */ pushq (%rdi) /* RDI */ @@ -512,7 +512,7 @@ END(spurious_entries_start) * +----------------------------------------------------+ */ ENTRY(interrupt_entry) - UNWIND_HINT_FUNC + UNWIND_HINT_IRET_REGS offset=16 ASM_CLAC cld @@ -544,9 +544,9 @@ ENTRY(interrupt_entry) pushq 5*8(%rdi) /* regs->eflags */ pushq 4*8(%rdi) /* regs->cs */ pushq 3*8(%rdi) /* regs->ip */ + UNWIND_HINT_IRET_REGS pushq 2*8(%rdi) /* regs->orig_ax */ pushq 8(%rdi) /* return address */ - UNWIND_HINT_FUNC movq (%rdi), %rdi jmp 2f @@ -637,6 +637,7 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + UNWIND_HINT_EMPTY /* Copy the IRET frame to the trampoline stack. */ pushq 6*8(%rdi) /* SS */ @@ -1739,7 +1740,7 @@ ENTRY(rewind_stack_do_exit) movq PER_CPU_VAR(cpu_current_top_of_stack), %rax leaq -PTREGS_SIZE(%rax), %rsp - UNWIND_HINT_FUNC sp_offset=PTREGS_SIZE + UNWIND_HINT_REGS call do_exit END(rewind_stack_do_exit) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 380cee9bc175..f5341edbfa16 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1608,8 +1608,8 @@ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq) { /* We can only post Fixed and LowPrio IRQs */ - return (irq->delivery_mode == dest_Fixed || - irq->delivery_mode == dest_LowestPrio); + return (irq->delivery_mode == APIC_DM_FIXED || + irq->delivery_mode == APIC_DM_LOWEST); } static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index 499578f7e6d7..70fc159ebe69 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -19,7 +19,7 @@ struct unwind_state { #if defined(CONFIG_UNWINDER_ORC) bool signal, full_regs; unsigned long sp, bp, ip; - struct pt_regs *regs; + struct pt_regs *regs, *prev_regs; #elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 332ae6530fa8..fb37221a1532 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -142,9 +142,6 @@ static struct orc_entry *orc_find(unsigned long ip) { static struct orc_entry *orc; - if (!orc_init) - return NULL; - if (ip == 0) return &null_orc_entry; @@ -378,9 +375,38 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr return true; } +/* + * If state->regs is non-NULL, and points to a full pt_regs, just get the reg + * value from state->regs. + * + * Otherwise, if state->regs just points to IRET regs, and the previous frame + * had full regs, it's safe to get the value from the previous regs. This can + * happen when early/late IRQ entry code gets interrupted by an NMI. + */ +static bool get_reg(struct unwind_state *state, unsigned int reg_off, + unsigned long *val) +{ + unsigned int reg = reg_off/8; + + if (!state->regs) + return false; + + if (state->full_regs) { + *val = ((unsigned long *)state->regs)[reg]; + return true; + } + + if (state->prev_regs) { + *val = ((unsigned long *)state->prev_regs)[reg]; + return true; + } + + return false; +} + bool unwind_next_frame(struct unwind_state *state) { - unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp; + unsigned long ip_p, sp, tmp, orig_ip = state->ip, prev_sp = state->sp; enum stack_type prev_type = state->stack_info.type; struct orc_entry *orc; bool indirect = false; @@ -442,39 +468,35 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_REG_R10: - if (!state->regs || !state->full_regs) { + if (!get_reg(state, offsetof(struct pt_regs, r10), &sp)) { orc_warn("missing regs for base reg R10 at ip %pB\n", (void *)state->ip); goto err; } - sp = state->regs->r10; break; case ORC_REG_R13: - if (!state->regs || !state->full_regs) { + if (!get_reg(state, offsetof(struct pt_regs, r13), &sp)) { orc_warn("missing regs for base reg R13 at ip %pB\n", (void *)state->ip); goto err; } - sp = state->regs->r13; break; case ORC_REG_DI: - if (!state->regs || !state->full_regs) { + if (!get_reg(state, offsetof(struct pt_regs, di), &sp)) { orc_warn("missing regs for base reg DI at ip %pB\n", (void *)state->ip); goto err; } - sp = state->regs->di; break; case ORC_REG_DX: - if (!state->regs || !state->full_regs) { + if (!get_reg(state, offsetof(struct pt_regs, dx), &sp)) { orc_warn("missing regs for base reg DX at ip %pB\n", (void *)state->ip); goto err; } - sp = state->regs->dx; break; default: @@ -501,6 +523,7 @@ bool unwind_next_frame(struct unwind_state *state) state->sp = sp; state->regs = NULL; + state->prev_regs = NULL; state->signal = false; break; @@ -512,6 +535,7 @@ bool unwind_next_frame(struct unwind_state *state) } state->regs = (struct pt_regs *)sp; + state->prev_regs = NULL; state->full_regs = true; state->signal = true; break; @@ -523,6 +547,8 @@ bool unwind_next_frame(struct unwind_state *state) goto err; } + if (state->full_regs) + state->prev_regs = state->regs; state->regs = (void *)sp - IRET_FRAME_OFFSET; state->full_regs = false; state->signal = true; @@ -531,14 +557,14 @@ bool unwind_next_frame(struct unwind_state *state) default: orc_warn("unknown .orc_unwind entry type %d for ip %pB\n", orc->type, (void *)orig_ip); - break; + goto err; } /* Find BP: */ switch (orc->bp_reg) { case ORC_REG_UNDEFINED: - if (state->regs && state->full_regs) - state->bp = state->regs->bp; + if (get_reg(state, offsetof(struct pt_regs, bp), &tmp)) + state->bp = tmp; break; case ORC_REG_PREV_SP: @@ -582,6 +608,9 @@ EXPORT_SYMBOL_GPL(unwind_next_frame); void __unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs, unsigned long *first_frame) { + if (!orc_init) + goto done; + memset(state, 0, sizeof(*state)); state->task = task; @@ -648,7 +677,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, /* Otherwise, skip ahead to the user-specified starting frame: */ while (!unwind_done(state) && (!on_stack(&state->stack_info, first_frame, sizeof(long)) || - state->sp <= (unsigned long)first_frame)) + state->sp < (unsigned long)first_frame)) unwind_next_frame(state); return; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 51ff6b342279..fda2126f9a97 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1861,7 +1861,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, return NULL; /* Pin the user virtual address. */ - npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages); + npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages); if (npinned != npages) { pr_err("SEV: Failure locking %lu pages.\n", npages); goto err; diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index c7012f6c971c..ca4252f81bf8 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -86,6 +86,9 @@ ENTRY(vmx_vmexit) /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + /* Clear RFLAGS.CF and RFLAGS.ZF to preserve VM-Exit, i.e. !VM-Fail. */ + or $1, %_ASM_AX + pop %_ASM_AX .Lvmexit_skip_rsb: #endif diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 2dc5dc54e257..d083f7704082 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -469,7 +469,7 @@ struct ioc_gq { */ atomic64_t vtime; atomic64_t done_vtime; - atomic64_t abs_vdebt; + u64 abs_vdebt; u64 last_vtime; /* @@ -1145,7 +1145,7 @@ static void iocg_kick_waitq(struct ioc_gq *iocg, struct ioc_now *now) struct iocg_wake_ctx ctx = { .iocg = iocg }; u64 margin_ns = (u64)(ioc->period_us * WAITQ_TIMER_MARGIN_PCT / 100) * NSEC_PER_USEC; - u64 abs_vdebt, vdebt, vshortage, expires, oexpires; + u64 vdebt, vshortage, expires, oexpires; s64 vbudget; u32 hw_inuse; @@ -1155,18 +1155,15 @@ static void iocg_kick_waitq(struct ioc_gq *iocg, struct ioc_now *now) vbudget = now->vnow - atomic64_read(&iocg->vtime); /* pay off debt */ - abs_vdebt = atomic64_read(&iocg->abs_vdebt); - vdebt = abs_cost_to_cost(abs_vdebt, hw_inuse); + vdebt = abs_cost_to_cost(iocg->abs_vdebt, hw_inuse); if (vdebt && vbudget > 0) { u64 delta = min_t(u64, vbudget, vdebt); u64 abs_delta = min(cost_to_abs_cost(delta, hw_inuse), - abs_vdebt); + iocg->abs_vdebt); atomic64_add(delta, &iocg->vtime); atomic64_add(delta, &iocg->done_vtime); - atomic64_sub(abs_delta, &iocg->abs_vdebt); - if (WARN_ON_ONCE(atomic64_read(&iocg->abs_vdebt) < 0)) - atomic64_set(&iocg->abs_vdebt, 0); + iocg->abs_vdebt -= abs_delta; } /* @@ -1222,12 +1219,18 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost) u64 expires, oexpires; u32 hw_inuse; + lockdep_assert_held(&iocg->waitq.lock); + /* debt-adjust vtime */ current_hweight(iocg, NULL, &hw_inuse); - vtime += abs_cost_to_cost(atomic64_read(&iocg->abs_vdebt), hw_inuse); + vtime += abs_cost_to_cost(iocg->abs_vdebt, hw_inuse); - /* clear or maintain depending on the overage */ - if (time_before_eq64(vtime, now->vnow)) { + /* + * Clear or maintain depending on the overage. Non-zero vdebt is what + * guarantees that @iocg is online and future iocg_kick_delay() will + * clear use_delay. Don't leave it on when there's no vdebt. + */ + if (!iocg->abs_vdebt || time_before_eq64(vtime, now->vnow)) { blkcg_clear_delay(blkg); return false; } @@ -1261,9 +1264,12 @@ static enum hrtimer_restart iocg_delay_timer_fn(struct hrtimer *timer) { struct ioc_gq *iocg = container_of(timer, struct ioc_gq, delay_timer); struct ioc_now now; + unsigned long flags; + spin_lock_irqsave(&iocg->waitq.lock, flags); ioc_now(iocg->ioc, &now); iocg_kick_delay(iocg, &now, 0); + spin_unlock_irqrestore(&iocg->waitq.lock, flags); return HRTIMER_NORESTART; } @@ -1371,14 +1377,13 @@ static void ioc_timer_fn(struct timer_list *timer) * should have woken up in the last period and expire idle iocgs. */ list_for_each_entry_safe(iocg, tiocg, &ioc->active_iocgs, active_list) { - if (!waitqueue_active(&iocg->waitq) && - !atomic64_read(&iocg->abs_vdebt) && !iocg_is_idle(iocg)) + if (!waitqueue_active(&iocg->waitq) && iocg->abs_vdebt && + !iocg_is_idle(iocg)) continue; spin_lock(&iocg->waitq.lock); - if (waitqueue_active(&iocg->waitq) || - atomic64_read(&iocg->abs_vdebt)) { + if (waitqueue_active(&iocg->waitq) || iocg->abs_vdebt) { /* might be oversleeping vtime / hweight changes, kick */ iocg_kick_waitq(iocg, &now); iocg_kick_delay(iocg, &now, 0); @@ -1721,28 +1726,49 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio) * tests are racy but the races aren't systemic - we only miss once * in a while which is fine. */ - if (!waitqueue_active(&iocg->waitq) && - !atomic64_read(&iocg->abs_vdebt) && + if (!waitqueue_active(&iocg->waitq) && !iocg->abs_vdebt && time_before_eq64(vtime + cost, now.vnow)) { iocg_commit_bio(iocg, bio, cost); return; } /* - * We're over budget. If @bio has to be issued regardless, - * remember the abs_cost instead of advancing vtime. - * iocg_kick_waitq() will pay off the debt before waking more IOs. + * We activated above but w/o any synchronization. Deactivation is + * synchronized with waitq.lock and we won't get deactivated as long + * as we're waiting or has debt, so we're good if we're activated + * here. In the unlikely case that we aren't, just issue the IO. + */ + spin_lock_irq(&iocg->waitq.lock); + + if (unlikely(list_empty(&iocg->active_list))) { + spin_unlock_irq(&iocg->waitq.lock); + iocg_commit_bio(iocg, bio, cost); + return; + } + + /* + * We're over budget. If @bio has to be issued regardless, remember + * the abs_cost instead of advancing vtime. iocg_kick_waitq() will pay + * off the debt before waking more IOs. + * * This way, the debt is continuously paid off each period with the - * actual budget available to the cgroup. If we just wound vtime, - * we would incorrectly use the current hw_inuse for the entire - * amount which, for example, can lead to the cgroup staying - * blocked for a long time even with substantially raised hw_inuse. + * actual budget available to the cgroup. If we just wound vtime, we + * would incorrectly use the current hw_inuse for the entire amount + * which, for example, can lead to the cgroup staying blocked for a + * long time even with substantially raised hw_inuse. + * + * An iocg with vdebt should stay online so that the timer can keep + * deducting its vdebt and [de]activate use_delay mechanism + * accordingly. We don't want to race against the timer trying to + * clear them and leave @iocg inactive w/ dangling use_delay heavily + * penalizing the cgroup and its descendants. */ if (bio_issue_as_root_blkg(bio) || fatal_signal_pending(current)) { - atomic64_add(abs_cost, &iocg->abs_vdebt); + iocg->abs_vdebt += abs_cost; if (iocg_kick_delay(iocg, &now, cost)) blkcg_schedule_throttle(rqos->q, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); + spin_unlock_irq(&iocg->waitq.lock); return; } @@ -1759,20 +1785,6 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio) * All waiters are on iocg->waitq and the wait states are * synchronized using waitq.lock. */ - spin_lock_irq(&iocg->waitq.lock); - - /* - * We activated above but w/o any synchronization. Deactivation is - * synchronized with waitq.lock and we won't get deactivated as - * long as we're waiting, so we're good if we're activated here. - * In the unlikely case that we are deactivated, just issue the IO. - */ - if (unlikely(list_empty(&iocg->active_list))) { - spin_unlock_irq(&iocg->waitq.lock); - iocg_commit_bio(iocg, bio, cost); - return; - } - init_waitqueue_func_entry(&wait.wait, iocg_wake_fn); wait.wait.private = current; wait.bio = bio; @@ -1804,6 +1816,7 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq, struct ioc_now now; u32 hw_inuse; u64 abs_cost, cost; + unsigned long flags; /* bypass if disabled or for root cgroup */ if (!ioc->enabled || !iocg->level) @@ -1823,15 +1836,28 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq, iocg->cursor = bio_end; /* - * Charge if there's enough vtime budget and the existing request - * has cost assigned. Otherwise, account it as debt. See debt - * handling in ioc_rqos_throttle() for details. + * Charge if there's enough vtime budget and the existing request has + * cost assigned. */ if (rq->bio && rq->bio->bi_iocost_cost && - time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow)) + time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow)) { iocg_commit_bio(iocg, bio, cost); - else - atomic64_add(abs_cost, &iocg->abs_vdebt); + return; + } + + /* + * Otherwise, account it as debt if @iocg is online, which it should + * be for the vast majority of cases. See debt handling in + * ioc_rqos_throttle() for details. + */ + spin_lock_irqsave(&iocg->waitq.lock, flags); + if (likely(!list_empty(&iocg->active_list))) { + iocg->abs_vdebt += abs_cost; + iocg_kick_delay(iocg, &now, cost); + } else { + iocg_commit_bio(iocg, bio, cost); + } + spin_unlock_irqrestore(&iocg->waitq.lock, flags); } static void ioc_rqos_done_bio(struct rq_qos *rqos, struct bio *bio) @@ -2001,7 +2027,6 @@ static void ioc_pd_init(struct blkg_policy_data *pd) iocg->ioc = ioc; atomic64_set(&iocg->vtime, now.vnow); atomic64_set(&iocg->done_vtime, now.vnow); - atomic64_set(&iocg->abs_vdebt, 0); atomic64_set(&iocg->active_period, atomic64_read(&ioc->cur_period)); INIT_LIST_HEAD(&iocg->active_list); iocg->hweight_active = HWEIGHT_WHOLE; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 630e8342d162..5e1dce424154 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3070,15 +3070,12 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon) } } - amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); - amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); - - amdgpu_amdkfd_suspend(adev); - amdgpu_ras_suspend(adev); r = amdgpu_device_ip_suspend_phase1(adev); + amdgpu_amdkfd_suspend(adev); + /* evict vram memory */ amdgpu_bo_evict_vram(adev); diff --git a/drivers/gpu/drm/ingenic/ingenic-drm.c b/drivers/gpu/drm/ingenic/ingenic-drm.c index f156f245fdec..9e95f6fd5406 100644 --- a/drivers/gpu/drm/ingenic/ingenic-drm.c +++ b/drivers/gpu/drm/ingenic/ingenic-drm.c @@ -824,6 +824,7 @@ static const struct of_device_id ingenic_drm_of_match[] = { { .compatible = "ingenic,jz4725b-lcd", .data = &jz4725b_soc_info }, { /* sentinel */ }, }; +MODULE_DEVICE_TABLE(of, ingenic_drm_of_match); static struct platform_driver ingenic_drm_driver = { .driver = { diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index c7bc9db5b192..17a638f15082 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -682,16 +682,21 @@ static int usbhid_open(struct hid_device *hid) struct usbhid_device *usbhid = hid->driver_data; int res; + mutex_lock(&usbhid->mutex); + set_bit(HID_OPENED, &usbhid->iofl); - if (hid->quirks & HID_QUIRK_ALWAYS_POLL) - return 0; + if (hid->quirks & HID_QUIRK_ALWAYS_POLL) { + res = 0; + goto Done; + } res = usb_autopm_get_interface(usbhid->intf); /* the device must be awake to reliably request remote wakeup */ if (res < 0) { clear_bit(HID_OPENED, &usbhid->iofl); - return -EIO; + res = -EIO; + goto Done; } usbhid->intf->needs_remote_wakeup = 1; @@ -725,6 +730,9 @@ static int usbhid_open(struct hid_device *hid) msleep(50); clear_bit(HID_RESUME_RUNNING, &usbhid->iofl); + + Done: + mutex_unlock(&usbhid->mutex); return res; } @@ -732,6 +740,8 @@ static void usbhid_close(struct hid_device *hid) { struct usbhid_device *usbhid = hid->driver_data; + mutex_lock(&usbhid->mutex); + /* * Make sure we don't restart data acquisition due to * a resumption we no longer care about by avoiding racing @@ -743,12 +753,13 @@ static void usbhid_close(struct hid_device *hid) clear_bit(HID_IN_POLLING, &usbhid->iofl); spin_unlock_irq(&usbhid->lock); - if (hid->quirks & HID_QUIRK_ALWAYS_POLL) - return; + if (!(hid->quirks & HID_QUIRK_ALWAYS_POLL)) { + hid_cancel_delayed_stuff(usbhid); + usb_kill_urb(usbhid->urbin); + usbhid->intf->needs_remote_wakeup = 0; + } - hid_cancel_delayed_stuff(usbhid); - usb_kill_urb(usbhid->urbin); - usbhid->intf->needs_remote_wakeup = 0; + mutex_unlock(&usbhid->mutex); } /* @@ -1057,6 +1068,8 @@ static int usbhid_start(struct hid_device *hid) unsigned int n, insize = 0; int ret; + mutex_lock(&usbhid->mutex); + clear_bit(HID_DISCONNECTED, &usbhid->iofl); usbhid->bufsize = HID_MIN_BUFFER_SIZE; @@ -1177,6 +1190,8 @@ static int usbhid_start(struct hid_device *hid) usbhid_set_leds(hid); device_set_wakeup_enable(&dev->dev, 1); } + + mutex_unlock(&usbhid->mutex); return 0; fail: @@ -1187,6 +1202,7 @@ fail: usbhid->urbout = NULL; usbhid->urbctrl = NULL; hid_free_buffers(dev, hid); + mutex_unlock(&usbhid->mutex); return ret; } @@ -1202,6 +1218,8 @@ static void usbhid_stop(struct hid_device *hid) usbhid->intf->needs_remote_wakeup = 0; } + mutex_lock(&usbhid->mutex); + clear_bit(HID_STARTED, &usbhid->iofl); spin_lock_irq(&usbhid->lock); /* Sync with error and led handlers */ set_bit(HID_DISCONNECTED, &usbhid->iofl); @@ -1222,6 +1240,8 @@ static void usbhid_stop(struct hid_device *hid) usbhid->urbout = NULL; hid_free_buffers(hid_to_usb_dev(hid), hid); + + mutex_unlock(&usbhid->mutex); } static int usbhid_power(struct hid_device *hid, int lvl) @@ -1382,6 +1402,7 @@ static int usbhid_probe(struct usb_interface *intf, const struct usb_device_id * INIT_WORK(&usbhid->reset_work, hid_reset); timer_setup(&usbhid->io_retry, hid_retry_timeout, 0); spin_lock_init(&usbhid->lock); + mutex_init(&usbhid->mutex); ret = hid_add_device(hid); if (ret) { diff --git a/drivers/hid/usbhid/usbhid.h b/drivers/hid/usbhid/usbhid.h index 8620408bd7af..75fe85d3d27a 100644 --- a/drivers/hid/usbhid/usbhid.h +++ b/drivers/hid/usbhid/usbhid.h @@ -80,6 +80,7 @@ struct usbhid_device { dma_addr_t outbuf_dma; /* Output buffer dma */ unsigned long last_out; /* record of last output for timeouts */ + struct mutex mutex; /* start/stop/open/close */ spinlock_t lock; /* fifo spinlock */ unsigned long iofl; /* I/O flags (CTRL_RUNNING, OUT_RUNNING) */ struct timer_list io_retry; /* Retry timer */ diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 5ded94b7bf68..cd71e7133944 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -319,9 +319,11 @@ static void wacom_feature_mapping(struct hid_device *hdev, data[0] = field->report->id; ret = wacom_get_report(hdev, HID_FEATURE_REPORT, data, n, WAC_CMD_RETRIES); - if (ret == n) { + if (ret == n && features->type == HID_GENERIC) { ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, data, n, 0); + } else if (ret == 2 && features->type != HID_GENERIC) { + features->touch_max = data[1]; } else { features->touch_max = 16; hid_warn(hdev, "wacom_feature_mapping: " diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index d99a9d407671..1c96809b51c9 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1427,11 +1427,13 @@ static void wacom_intuos_pro2_bt_pad(struct wacom_wac *wacom) { struct input_dev *pad_input = wacom->pad_input; unsigned char *data = wacom->data; + int nbuttons = wacom->features.numbered_buttons; - int buttons = data[282] | ((data[281] & 0x40) << 2); + int expresskeys = data[282]; + int center = (data[281] & 0x40) >> 6; int ring = data[285] & 0x7F; bool ringstatus = data[285] & 0x80; - bool prox = buttons || ringstatus; + bool prox = expresskeys || center || ringstatus; /* Fix touchring data: userspace expects 0 at left and increasing clockwise */ ring = 71 - ring; @@ -1439,7 +1441,8 @@ static void wacom_intuos_pro2_bt_pad(struct wacom_wac *wacom) if (ring > 71) ring -= 72; - wacom_report_numbered_buttons(pad_input, 9, buttons); + wacom_report_numbered_buttons(pad_input, nbuttons, + expresskeys | (center << (nbuttons - 1))); input_report_abs(pad_input, ABS_WHEEL, ringstatus ? ring : 0); @@ -2637,9 +2640,25 @@ static void wacom_wac_finger_pre_report(struct hid_device *hdev, case HID_DG_TIPSWITCH: hid_data->last_slot_field = equivalent_usage; break; + case HID_DG_CONTACTCOUNT: + hid_data->cc_report = report->id; + hid_data->cc_index = i; + hid_data->cc_value_index = j; + break; } } } + + if (hid_data->cc_report != 0 && + hid_data->cc_index >= 0) { + struct hid_field *field = report->field[hid_data->cc_index]; + int value = field->value[hid_data->cc_value_index]; + if (value) + hid_data->num_expected = value; + } + else { + hid_data->num_expected = wacom_wac->features.touch_max; + } } static void wacom_wac_finger_report(struct hid_device *hdev, @@ -2649,7 +2668,6 @@ static void wacom_wac_finger_report(struct hid_device *hdev, struct wacom_wac *wacom_wac = &wacom->wacom_wac; struct input_dev *input = wacom_wac->touch_input; unsigned touch_max = wacom_wac->features.touch_max; - struct hid_data *hid_data = &wacom_wac->hid_data; /* If more packets of data are expected, give us a chance to * process them rather than immediately syncing a partial @@ -2663,7 +2681,6 @@ static void wacom_wac_finger_report(struct hid_device *hdev, input_sync(input); wacom_wac->hid_data.num_received = 0; - hid_data->num_expected = 0; /* keep touch state for pen event */ wacom_wac->shared->touch_down = wacom_wac_finger_count_touches(wacom_wac); @@ -2738,73 +2755,12 @@ static void wacom_report_events(struct hid_device *hdev, } } -static void wacom_set_num_expected(struct hid_device *hdev, - struct hid_report *report, - int collection_index, - struct hid_field *field, - int field_index) -{ - struct wacom *wacom = hid_get_drvdata(hdev); - struct wacom_wac *wacom_wac = &wacom->wacom_wac; - struct hid_data *hid_data = &wacom_wac->hid_data; - unsigned int original_collection_level = - hdev->collection[collection_index].level; - bool end_collection = false; - int i; - - if (hid_data->num_expected) - return; - - // find the contact count value for this segment - for (i = field_index; i < report->maxfield && !end_collection; i++) { - struct hid_field *field = report->field[i]; - unsigned int field_level = - hdev->collection[field->usage[0].collection_index].level; - unsigned int j; - - if (field_level != original_collection_level) - continue; - - for (j = 0; j < field->maxusage; j++) { - struct hid_usage *usage = &field->usage[j]; - - if (usage->collection_index != collection_index) { - end_collection = true; - break; - } - if (wacom_equivalent_usage(usage->hid) == HID_DG_CONTACTCOUNT) { - hid_data->cc_report = report->id; - hid_data->cc_index = i; - hid_data->cc_value_index = j; - - if (hid_data->cc_report != 0 && - hid_data->cc_index >= 0) { - - struct hid_field *field = - report->field[hid_data->cc_index]; - int value = - field->value[hid_data->cc_value_index]; - - if (value) - hid_data->num_expected = value; - } - } - } - } - - if (hid_data->cc_report == 0 || hid_data->cc_index < 0) - hid_data->num_expected = wacom_wac->features.touch_max; -} - static int wacom_wac_collection(struct hid_device *hdev, struct hid_report *report, int collection_index, struct hid_field *field, int field_index) { struct wacom *wacom = hid_get_drvdata(hdev); - if (WACOM_FINGER_FIELD(field)) - wacom_set_num_expected(hdev, report, collection_index, field, - field_index); wacom_report_events(hdev, report, collection_index, field_index); /* diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 6c340a4f4fd2..60e659a24f90 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -454,7 +454,7 @@ static int viommu_add_resv_mem(struct viommu_endpoint *vdev, if (!region) return -ENOMEM; - list_add(&vdev->resv_regions, ®ion->list); + list_add(®ion->list, &vdev->resv_regions); return 0; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 6862594b49ab..edf8452a2574 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -6649,7 +6649,7 @@ static int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp, int rc; if (!mem_size) - return 0; + return -EINVAL; ctx_pg->nr_pages = DIV_ROUND_UP(mem_size, BNXT_PAGE_SIZE); if (ctx_pg->nr_pages > MAX_CTX_TOTAL_PAGES) { @@ -9755,6 +9755,7 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev, netdev_features_t features) { struct bnxt *bp = netdev_priv(dev); + netdev_features_t vlan_features; if ((features & NETIF_F_NTUPLE) && !bnxt_rfs_capable(bp)) features &= ~NETIF_F_NTUPLE; @@ -9771,12 +9772,14 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev, /* Both CTAG and STAG VLAN accelaration on the RX side have to be * turned on or off together. */ - if ((features & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) != - (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) { + vlan_features = features & (NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_STAG_RX); + if (vlan_features != (NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_STAG_RX)) { if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) features &= ~(NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX); - else + else if (vlan_features) features |= NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX; } @@ -12066,12 +12069,15 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) } } - if (result != PCI_ERS_RESULT_RECOVERED && netif_running(netdev)) - dev_close(netdev); + if (result != PCI_ERS_RESULT_RECOVERED) { + if (netif_running(netdev)) + dev_close(netdev); + pci_disable_device(pdev); + } rtnl_unlock(); - return PCI_ERS_RESULT_RECOVERED; + return result; } /** diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index cda7ba31095a..a61a5873ab0a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1058,7 +1058,6 @@ struct bnxt_vf_info { #define BNXT_VF_LINK_FORCED 0x4 #define BNXT_VF_LINK_UP 0x8 #define BNXT_VF_TRUST 0x10 - u32 func_flags; /* func cfg flags */ u32 min_tx_rate; u32 max_tx_rate; void *hwrm_cmd_req_addr; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h index 689c47ab2155..ba94edec9fb8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h @@ -39,7 +39,7 @@ static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl) #define NVM_OFF_DIS_GRE_VER_CHECK 171 #define NVM_OFF_ENABLE_SRIOV 401 -#define BNXT_MSIX_VEC_MAX 1280 +#define BNXT_MSIX_VEC_MAX 512 #define BNXT_MSIX_VEC_MIN_MAX 128 enum bnxt_nvm_dir_type { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index f6f3454d6059..1046b22220a3 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -85,11 +85,10 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting) if (old_setting == setting) return 0; - func_flags = vf->func_flags; if (setting) - func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE; + func_flags = FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE; else - func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE; + func_flags = FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE; /*TODO: if the driver supports VLAN filter on guest VLAN, * the spoof check should also include vlan anti-spoofing */ @@ -98,7 +97,6 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting) req.flags = cpu_to_le32(func_flags); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (!rc) { - vf->func_flags = func_flags; if (setting) vf->flags |= BNXT_VF_SPOOFCHK; else @@ -230,7 +228,6 @@ int bnxt_set_vf_mac(struct net_device *dev, int vf_id, u8 *mac) memcpy(vf->mac_addr, mac, ETH_ALEN); bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR); memcpy(req.dflt_mac_addr, mac, ETH_ALEN); return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); @@ -268,7 +265,6 @@ int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos, bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); req.dflt_vlan = cpu_to_le16(vlan_tag); req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_VLAN); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); @@ -307,7 +303,6 @@ int bnxt_set_vf_bw(struct net_device *dev, int vf_id, int min_tx_rate, return 0; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_MAX_BW); req.max_bw = cpu_to_le32(max_tx_rate); req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_MIN_BW); @@ -479,7 +474,6 @@ static void __bnxt_set_vf_params(struct bnxt *bp, int vf_id) vf = &bp->pf.vf[vf_id]; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); if (is_valid_ether_addr(vf->mac_addr)) { req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR); diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 234c13ebbc41..1ec19d9fab00 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -334,8 +334,10 @@ static int macb_mdio_read(struct mii_bus *bus, int mii_id, int regnum) int status; status = pm_runtime_get_sync(&bp->pdev->dev); - if (status < 0) + if (status < 0) { + pm_runtime_put_noidle(&bp->pdev->dev); goto mdio_pm_exit; + } status = macb_mdio_wait_for_idle(bp); if (status < 0) @@ -367,8 +369,10 @@ static int macb_mdio_write(struct mii_bus *bus, int mii_id, int regnum, int status; status = pm_runtime_get_sync(&bp->pdev->dev); - if (status < 0) + if (status < 0) { + pm_runtime_put_noidle(&bp->pdev->dev); goto mdio_pm_exit; + } status = macb_mdio_wait_for_idle(bp); if (status < 0) @@ -3691,8 +3695,10 @@ static int at91ether_open(struct net_device *dev) int ret; ret = pm_runtime_get_sync(&lp->pdev->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_noidle(&lp->pdev->dev); return ret; + } /* Clear internal statistics */ ctl = macb_readl(lp, NCR); @@ -4048,15 +4054,9 @@ static int fu540_c000_clk_init(struct platform_device *pdev, struct clk **pclk, static int fu540_c000_init(struct platform_device *pdev) { - struct resource *res; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - if (!res) - return -ENODEV; - - mgmt->reg = ioremap(res->start, resource_size(res)); - if (!mgmt->reg) - return -ENOMEM; + mgmt->reg = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(mgmt->reg)) + return PTR_ERR(mgmt->reg); return macb_init(pdev); } diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c index 35478cba2aa5..4344a59c823f 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c @@ -1422,6 +1422,9 @@ int mvpp2_ethtool_cls_rule_del(struct mvpp2_port *port, struct mvpp2_ethtool_fs *efs; int ret; + if (info->fs.location >= MVPP2_N_RFS_ENTRIES_PER_FLOW) + return -EINVAL; + efs = port->rfs_rules[info->fs.location]; if (!efs) return -EINVAL; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index ef44c6979a31..373b8c832850 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -4319,6 +4319,8 @@ static int mvpp2_ethtool_get_rxfh_context(struct net_device *dev, u32 *indir, if (!mvpp22_rss_is_supported()) return -EOPNOTSUPP; + if (rss_context >= MVPP22_N_RSS_TABLES) + return -EINVAL; if (hfunc) *hfunc = ETH_RSS_HASH_CRC32; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index d44ac666e730..87c2e8de6102 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2550,6 +2550,7 @@ static int mlx4_allocate_default_counters(struct mlx4_dev *dev) if (!err || err == -ENOSPC) { priv->def_counter[port] = idx; + err = 0; } else if (err == -ENOENT) { err = 0; continue; @@ -2600,7 +2601,8 @@ int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx, u8 usage) MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED); if (!err) *idx = get_param_l(&out_param); - + if (WARN_ON(err == -ENOSPC)) + err = -EINVAL; return err; } return __mlx4_counter_alloc(dev, idx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index ea934cd02448..08048a2d7259 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -888,7 +888,6 @@ static void cmd_work_handler(struct work_struct *work) } cmd->ent_arr[ent->idx] = ent; - set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state); lay = get_inst(cmd, ent->idx); ent->lay = lay; memset(lay, 0, sizeof(*lay)); @@ -910,6 +909,7 @@ static void cmd_work_handler(struct work_struct *work) if (ent->callback) schedule_delayed_work(&ent->cb_timeout_work, cb_timeout); + set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state); /* Skip sending command to fw if internal error */ if (pci_channel_offline(dev->pdev) || @@ -922,6 +922,10 @@ static void cmd_work_handler(struct work_struct *work) MLX5_SET(mbox_out, ent->out, syndrome, drv_synd); mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); + /* no doorbell, no need to keep the entry */ + free_ent(cmd, ent->idx); + if (ent->callback) + free_cmd(ent); return; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index 095ec7b1399d..7c77378accf0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -689,6 +689,12 @@ static void dr_cq_event(struct mlx5_core_cq *mcq, pr_info("CQ event %u on CQ #%u\n", event, mcq->cqn); } +static void dr_cq_complete(struct mlx5_core_cq *mcq, + struct mlx5_eqe *eqe) +{ + pr_err("CQ completion CQ: #%u\n", mcq->cqn); +} + static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, struct mlx5_uars_page *uar, size_t ncqe) @@ -750,6 +756,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, pas); cq->mcq.event = dr_cq_event; + cq->mcq.comp = dr_cq_complete; err = mlx5_core_create_cq(mdev, &cq->mcq, in, inlen, out, sizeof(out)); kvfree(in); @@ -761,7 +768,12 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, cq->mcq.set_ci_db = cq->wq_ctrl.db.db; cq->mcq.arm_db = cq->wq_ctrl.db.db + 1; *cq->mcq.set_ci_db = 0; - *cq->mcq.arm_db = 0; + + /* set no-zero value, in order to avoid the HW to run db-recovery on + * CQ that used in polling mode. + */ + *cq->mcq.arm_db = cpu_to_be32(2 << 28); + cq->mcq.vector = 0; cq->mcq.irqn = irqn; cq->mcq.uar = uar; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index e993159e8e4c..295b27112d36 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -986,8 +986,9 @@ mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp, unsigned int priority, struct mlxsw_afk_element_usage *elusage) { + struct mlxsw_sp_acl_tcam_vchunk *vchunk, *vchunk2; struct mlxsw_sp_acl_tcam_vregion *vregion; - struct mlxsw_sp_acl_tcam_vchunk *vchunk; + struct list_head *pos; int err; if (priority == MLXSW_SP_ACL_TCAM_CATCHALL_PRIO) @@ -1025,7 +1026,14 @@ mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp, } mlxsw_sp_acl_tcam_rehash_ctx_vregion_changed(vregion); - list_add_tail(&vchunk->list, &vregion->vchunk_list); + + /* Position the vchunk inside the list according to priority */ + list_for_each(pos, &vregion->vchunk_list) { + vchunk2 = list_entry(pos, typeof(*vchunk2), list); + if (vchunk2->priority > priority) + break; + } + list_add_tail(&vchunk->list, pos); mutex_unlock(&vregion->lock); return vchunk; diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c index 9183b3e85d21..354efffac0f9 100644 --- a/drivers/net/ethernet/netronome/nfp/abm/main.c +++ b/drivers/net/ethernet/netronome/nfp/abm/main.c @@ -283,6 +283,7 @@ nfp_abm_vnic_set_mac(struct nfp_pf *pf, struct nfp_abm *abm, struct nfp_net *nn, if (!nfp_nsp_has_hwinfo_lookup(nsp)) { nfp_warn(pf->cpp, "NSP doesn't support PF MAC generation\n"); eth_hw_addr_random(nn->dp.netdev); + nfp_nsp_close(nsp); return; } diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c index 12466a72cefc..aab0cf57c654 100644 --- a/drivers/net/ethernet/toshiba/tc35815.c +++ b/drivers/net/ethernet/toshiba/tc35815.c @@ -644,7 +644,7 @@ static int tc_mii_probe(struct net_device *dev) linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, mask); linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, mask); } - linkmode_and(phydev->supported, phydev->supported, mask); + linkmode_andnot(phydev->supported, phydev->supported, mask); linkmode_copy(phydev->advertising, phydev->supported); lp->link = 0; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index a0abc729f0ca..4c86a73db475 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1309,7 +1309,8 @@ static struct crypto_aead *macsec_alloc_tfm(char *key, int key_len, int icv_len) struct crypto_aead *tfm; int ret; - tfm = crypto_alloc_aead("gcm(aes)", 0, 0); + /* Pick a sync gcm(aes) cipher to ensure order is preserved. */ + tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(tfm)) return tfm; diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 8f241b57fcf6..1c75b2627ca8 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -1119,7 +1119,7 @@ static struct dp83640_clock *dp83640_clock_get_bus(struct mii_bus *bus) goto out; } dp83640_clock_init(clock, bus); - list_add_tail(&phyter_clocks, &clock->list); + list_add_tail(&clock->list, &phyter_clocks); out: mutex_unlock(&phyter_clocks_lock); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 6c738a271257..4bb8552a00d3 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1359,6 +1359,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */ + {QMI_FIXED_INTF(0x413c, 0x81cc, 8)}, /* Dell Wireless 5816e */ {QMI_FIXED_INTF(0x413c, 0x81d7, 0)}, /* Dell Wireless 5821e */ {QMI_FIXED_INTF(0x413c, 0x81d7, 1)}, /* Dell Wireless 5821e preproduction config */ {QMI_FIXED_INTF(0x413c, 0x81e0, 0)}, /* Dell Wireless 5821e with eSIM support*/ diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 31b7dcd791c2..f0e0af3aa714 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1071,8 +1071,17 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, status = nvme_submit_sync_cmd(ctrl->admin_q, &c, data, NVME_IDENTIFY_DATA_SIZE); - if (status) + if (status) { + dev_warn(ctrl->device, + "Identify Descriptors failed (%d)\n", status); + /* + * Don't treat an error as fatal, as we potentially already + * have a NGUID or EUI-64. + */ + if (status > 0 && !(status & NVME_SC_DNR)) + status = 0; goto free_data; + } for (pos = 0; pos < NVME_IDENTIFY_DATA_SIZE; pos += len) { struct nvme_ns_id_desc *cur = data + pos; @@ -1730,26 +1739,15 @@ static void nvme_config_write_zeroes(struct gendisk *disk, struct nvme_ns *ns) static int nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid, struct nvme_id_ns *id, struct nvme_ns_ids *ids) { - int ret = 0; - memset(ids, 0, sizeof(*ids)); if (ctrl->vs >= NVME_VS(1, 1, 0)) memcpy(ids->eui64, id->eui64, sizeof(id->eui64)); if (ctrl->vs >= NVME_VS(1, 2, 0)) memcpy(ids->nguid, id->nguid, sizeof(id->nguid)); - if (ctrl->vs >= NVME_VS(1, 3, 0)) { - /* Don't treat error as fatal we potentially - * already have a NGUID or EUI-64 - */ - ret = nvme_identify_ns_descs(ctrl, nsid, ids); - if (ret) - dev_warn(ctrl->device, - "Identify Descriptors failed (%d)\n", ret); - if (ret > 0) - ret = 0; - } - return ret; + if (ctrl->vs >= NVME_VS(1, 3, 0)) + return nvme_identify_ns_descs(ctrl, nsid, ids); + return 0; } static bool nvme_ns_ids_valid(struct nvme_ns_ids *ids) diff --git a/drivers/staging/gasket/gasket_core.c b/drivers/staging/gasket/gasket_core.c index 13179f063a61..6f9c0d18d9ce 100644 --- a/drivers/staging/gasket/gasket_core.c +++ b/drivers/staging/gasket/gasket_core.c @@ -926,6 +926,10 @@ do_map_region(const struct gasket_dev *gasket_dev, struct vm_area_struct *vma, gasket_get_bar_index(gasket_dev, (vma->vm_pgoff << PAGE_SHIFT) + driver_desc->legacy_mmap_address_offset); + + if (bar_index < 0) + return DO_MAP_REGION_INVALID; + phys_base = gasket_dev->bar_data[bar_index].phys_base + phys_offset; while (mapped_bytes < map_length) { /* diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index fe098cf14e6a..3cb9aacfe0b2 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -1445,6 +1445,7 @@ static int cdns_uart_probe(struct platform_device *pdev) cdns_uart_uart_driver.nr = CDNS_UART_NR_PORTS; #ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE cdns_uart_uart_driver.cons = &cdns_uart_console; + cdns_uart_console.index = id; #endif rc = uart_register_driver(&cdns_uart_uart_driver); diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 8b3ecef50394..fd0361d72738 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -365,9 +365,14 @@ static struct uni_screen *vc_uniscr_alloc(unsigned int cols, unsigned int rows) return uniscr; } +static void vc_uniscr_free(struct uni_screen *uniscr) +{ + vfree(uniscr); +} + static void vc_uniscr_set(struct vc_data *vc, struct uni_screen *new_uniscr) { - vfree(vc->vc_uni_screen); + vc_uniscr_free(vc->vc_uni_screen); vc->vc_uni_screen = new_uniscr; } @@ -1230,7 +1235,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, err = resize_screen(vc, new_cols, new_rows, user); if (err) { kfree(newscreen); - kfree(new_uniscr); + vc_uniscr_free(new_uniscr); return err; } diff --git a/drivers/usb/chipidea/ci_hdrc_msm.c b/drivers/usb/chipidea/ci_hdrc_msm.c index af648ba6544d..46105457e1ca 100644 --- a/drivers/usb/chipidea/ci_hdrc_msm.c +++ b/drivers/usb/chipidea/ci_hdrc_msm.c @@ -114,7 +114,7 @@ static int ci_hdrc_msm_notify_event(struct ci_hdrc *ci, unsigned event) hw_write_id_reg(ci, HS_PHY_GENCONFIG_2, HS_PHY_ULPI_TX_PKT_EN_CLR_FIX, 0); - if (!IS_ERR(ci->platdata->vbus_extcon.edev)) { + if (!IS_ERR(ci->platdata->vbus_extcon.edev) || ci->role_switch) { hw_write_id_reg(ci, HS_PHY_GENCONFIG_2, HS_PHY_SESS_VLD_CTRL_EN, HS_PHY_SESS_VLD_CTRL_EN); diff --git a/drivers/usb/serial/garmin_gps.c b/drivers/usb/serial/garmin_gps.c index 633550ec3025..f29c3a936a08 100644 --- a/drivers/usb/serial/garmin_gps.c +++ b/drivers/usb/serial/garmin_gps.c @@ -1138,8 +1138,8 @@ static void garmin_read_process(struct garmin_data *garmin_data_p, send it directly to the tty port */ if (garmin_data_p->flags & FLAGS_QUEUING) { pkt_add(garmin_data_p, data, data_length); - } else if (bulk_data || - getLayerId(data) == GARMIN_LAYERID_APPL) { + } else if (bulk_data || (data_length >= sizeof(u32) && + getLayerId(data) == GARMIN_LAYERID_APPL)) { spin_lock_irqsave(&garmin_data_p->lock, flags); garmin_data_p->flags |= APP_RESP_SEEN; diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 613f91add03d..ce0401d3137f 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -173,6 +173,7 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x413c, 0x81b3)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {DEVICE_SWI(0x413c, 0x81b5)}, /* Dell Wireless 5811e QDL */ {DEVICE_SWI(0x413c, 0x81b6)}, /* Dell Wireless 5811e QDL */ + {DEVICE_SWI(0x413c, 0x81cc)}, /* Dell Wireless 5816e */ {DEVICE_SWI(0x413c, 0x81cf)}, /* Dell Wireless 5819 */ {DEVICE_SWI(0x413c, 0x81d0)}, /* Dell Wireless 5819 */ {DEVICE_SWI(0x413c, 0x81d1)}, /* Dell Wireless 5818 */ diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index 1b23741036ee..37157ed9a881 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -28,6 +28,13 @@ * and don't forget to CC: the USB development list */ +/* Reported-by: Julian Groß */ +UNUSUAL_DEV(0x059f, 0x105f, 0x0000, 0x9999, + "LaCie", + "2Big Quadra USB3", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_REPORT_OPCODES), + /* * Apricorn USB3 dongle sometimes returns "USBSUSBSUSBS" in response to SCSI * commands in UAS mode. Observed with the 1.28 firmware; are there others? diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 8c1f04c3a684..b79fe6549df6 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3072,8 +3072,7 @@ static void handle_session(struct ceph_mds_session *session, void *end = p + msg->front.iov_len; struct ceph_mds_session_head *h; u32 op; - u64 seq; - unsigned long features = 0; + u64 seq, features = 0; int wake = 0; bool blacklisted = false; @@ -3092,9 +3091,8 @@ static void handle_session(struct ceph_mds_session *session, goto bad; /* version >= 3, feature bits */ ceph_decode_32_safe(&p, end, len, bad); - ceph_decode_need(&p, end, len, bad); - memcpy(&features, p, min_t(size_t, len, sizeof(features))); - p += len; + ceph_decode_64_safe(&p, end, features, bad); + p += len - sizeof(features); } mutex_lock(&mdsc->mutex); diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index de56dee60540..19507e2fdb57 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -159,8 +159,8 @@ static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc, } if (IS_ERR(in)) { - pr_warn("Can't lookup inode %llx (err: %ld)\n", - realm->ino, PTR_ERR(in)); + dout("Can't lookup inode %llx (err: %ld)\n", + realm->ino, PTR_ERR(in)); qri->timeout = jiffies + msecs_to_jiffies(60 * 1000); /* XXX */ } else { qri->timeout = 0; diff --git a/fs/coredump.c b/fs/coredump.c index d25bad2ed061..5c0375e7440f 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -788,6 +788,14 @@ void do_coredump(const kernel_siginfo_t *siginfo) if (displaced) put_files_struct(displaced); if (!dump_interrupted()) { + /* + * umh disabled with CONFIG_STATIC_USERMODEHELPER_PATH="" would + * have this set to NULL. + */ + if (!cprm.file) { + pr_info("Core dump to |%s disabled\n", cn.corename); + goto close_fail; + } file_start_write(cprm.file); core_dumped = binfmt->core_dump(&cprm); file_end_write(cprm.file); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 33cff49769cc..6307c1d883e0 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1176,6 +1176,10 @@ static inline bool chain_epi_lockless(struct epitem *epi) { struct eventpoll *ep = epi->ep; + /* Fast preliminary check */ + if (epi->next != EP_UNACTIVE_PTR) + return false; + /* Check that the same epi has not been just chained from another CPU */ if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR) return false; @@ -1242,16 +1246,12 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v * chained in ep->ovflist and requeued later on. */ if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) { - if (epi->next == EP_UNACTIVE_PTR && - chain_epi_lockless(epi)) + if (chain_epi_lockless(epi)) + ep_pm_stay_awake_rcu(epi); + } else if (!ep_is_linked(epi)) { + /* In the usual case, add event to ready list. */ + if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) ep_pm_stay_awake_rcu(epi); - goto out_unlock; - } - - /* If this file is already in the ready list we exit soon */ - if (!ep_is_linked(epi) && - list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) { - ep_pm_stay_awake_rcu(epi); } /* @@ -1827,7 +1827,6 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, { int res = 0, eavail, timed_out = 0; u64 slack = 0; - bool waiter = false; wait_queue_entry_t wait; ktime_t expires, *to = NULL; @@ -1872,21 +1871,23 @@ fetch_events: */ ep_reset_busy_poll_napi_id(ep); - /* - * We don't have any available event to return to the caller. We need - * to sleep here, and we will be woken by ep_poll_callback() when events - * become available. - */ - if (!waiter) { - waiter = true; - init_waitqueue_entry(&wait, current); - + do { + /* + * Internally init_wait() uses autoremove_wake_function(), + * thus wait entry is removed from the wait queue on each + * wakeup. Why it is important? In case of several waiters + * each new wakeup will hit the next waiter, giving it the + * chance to harvest new event. Otherwise wakeup can be + * lost. This is also good performance-wise, because on + * normal wakeup path no need to call __remove_wait_queue() + * explicitly, thus ep->lock is not taken, which halts the + * event delivery. + */ + init_wait(&wait); write_lock_irq(&ep->lock); __add_wait_queue_exclusive(&ep->wq, &wait); write_unlock_irq(&ep->lock); - } - for (;;) { /* * We don't want to sleep if the ep_poll_callback() sends us * a wakeup in between. That's why we set the task state @@ -1916,10 +1917,20 @@ fetch_events: timed_out = 1; break; } - } + + /* We were woken up, thus go and try to harvest some events */ + eavail = 1; + + } while (0); __set_current_state(TASK_RUNNING); + if (!list_empty_careful(&wait.entry)) { + write_lock_irq(&ep->lock); + __remove_wait_queue(&ep->wq, &wait); + write_unlock_irq(&ep->lock); + } + send_events: /* * Try to transfer events to user space. In case we get 0 events and @@ -1930,12 +1941,6 @@ send_events: !(res = ep_send_events(ep, events, maxevents)) && !timed_out) goto fetch_events; - if (waiter) { - write_lock_irq(&ep->lock); - __remove_wait_queue(&ep->wq, &wait); - write_unlock_irq(&ep->lock); - } - return res; } diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 5778d1347b35..f5d30573f4a9 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -26,7 +26,7 @@ static bool should_merge(struct fsnotify_event *old_fsn, old = FANOTIFY_E(old_fsn); new = FANOTIFY_E(new_fsn); - if (old_fsn->inode != new_fsn->inode || old->pid != new->pid || + if (old_fsn->objectid != new_fsn->objectid || old->pid != new->pid || old->fh_type != new->fh_type || old->fh_len != new->fh_len) return false; @@ -314,7 +314,12 @@ struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, if (!event) goto out; init: __maybe_unused - fsnotify_init_event(&event->fse, inode); + /* + * Use the victim inode instead of the watching inode as the id for + * event queue, so event reported on parent is merged with event + * reported on child when both directory and child watches exist. + */ + fsnotify_init_event(&event->fse, (unsigned long)id); event->mask = mask; if (FAN_GROUP_FLAG(group, FAN_REPORT_TID)) event->pid = get_pid(task_pid(current)); diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index d510223d302c..589dee962993 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -39,7 +39,7 @@ static bool event_compare(struct fsnotify_event *old_fsn, if (old->mask & FS_IN_IGNORED) return false; if ((old->mask == new->mask) && - (old_fsn->inode == new_fsn->inode) && + (old_fsn->objectid == new_fsn->objectid) && (old->name_len == new->name_len) && (!old->name_len || !strcmp(old->name, new->name))) return true; @@ -118,7 +118,7 @@ int inotify_handle_event(struct fsnotify_group *group, mask &= ~IN_ISDIR; fsn_event = &event->fse; - fsnotify_init_event(fsn_event, inode); + fsnotify_init_event(fsn_event, (unsigned long)inode); event->mask = mask; event->wd = i_mark->wd; event->sync_cookie = cookie; diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 107537a543fd..81ffc8629fc4 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -635,7 +635,7 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events) return ERR_PTR(-ENOMEM); } group->overflow_event = &oevent->fse; - fsnotify_init_event(group->overflow_event, NULL); + fsnotify_init_event(group->overflow_event, 0); oevent->mask = FS_Q_OVERFLOW; oevent->wd = -1; oevent->sync_cookie = 0; diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 4fc87dee005a..2849bdbb3acb 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -220,6 +220,7 @@ struct backing_dev_info { wait_queue_head_t wb_waitq; struct device *dev; + char dev_name[64]; struct device *owner; struct timer_list laptop_mode_wb_timer; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f88197c1ffc2..c9ad5c3b7b4b 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -505,13 +505,6 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi) (1 << WB_async_congested)); } -extern const char *bdi_unknown_name; - -static inline const char *bdi_dev_name(struct backing_dev_info *bdi) -{ - if (!bdi || !bdi->dev) - return bdi_unknown_name; - return dev_name(bdi->dev); -} +const char *bdi_dev_name(struct backing_dev_info *bdi); #endif /* _LINUX_BACKING_DEV_H */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 1915bdba2fad..64cfb5446f4d 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -133,8 +133,7 @@ struct fsnotify_ops { */ struct fsnotify_event { struct list_head list; - /* inode may ONLY be dereferenced during handle_event(). */ - struct inode *inode; /* either the inode the event happened to or its parent */ + unsigned long objectid; /* identifier for queue merges */ }; /* @@ -500,10 +499,10 @@ extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info); extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info); static inline void fsnotify_init_event(struct fsnotify_event *event, - struct inode *inode) + unsigned long objectid) { INIT_LIST_HEAD(&event->list); - event->inode = inode; + event->objectid = objectid; } #else diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 0d1fe9297ac6..6f6ade63b04c 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -3,6 +3,8 @@ #define _LINUX_VIRTIO_NET_H #include +#include +#include #include static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, @@ -28,17 +30,25 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, bool little_endian) { unsigned int gso_type = 0; + unsigned int thlen = 0; + unsigned int ip_proto; if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: gso_type = SKB_GSO_TCPV4; + ip_proto = IPPROTO_TCP; + thlen = sizeof(struct tcphdr); break; case VIRTIO_NET_HDR_GSO_TCPV6: gso_type = SKB_GSO_TCPV6; + ip_proto = IPPROTO_TCP; + thlen = sizeof(struct tcphdr); break; case VIRTIO_NET_HDR_GSO_UDP: gso_type = SKB_GSO_UDP; + ip_proto = IPPROTO_UDP; + thlen = sizeof(struct udphdr); break; default: return -EINVAL; @@ -57,16 +67,22 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; + + if (skb_transport_offset(skb) + thlen > skb_headlen(skb)) + return -EINVAL; } else { /* gso packets without NEEDS_CSUM do not set transport_offset. * probe and drop if does not match one of the above types. */ if (gso_type && skb->network_header) { + struct flow_keys_basic keys; + if (!skb->protocol) virtio_net_hdr_set_proto(skb, hdr); retry: - skb_probe_transport_header(skb); - if (!skb_transport_header_was_set(skb)) { + if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, + NULL, 0, 0, 0, + 0)) { /* UFO does not specify ipv4 or 6: try both */ if (gso_type & SKB_GSO_UDP && skb->protocol == htons(ETH_P_IP)) { @@ -75,6 +91,12 @@ retry: } return -EINVAL; } + + if (keys.control.thoff + thlen > skb_headlen(skb) || + keys.basic.ip_proto != ip_proto) + return -EINVAL; + + skb_set_transport_header(skb, keys.control.thoff); } } diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index c8e2bebd8d93..0f0d1efe06dd 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -99,6 +99,20 @@ static inline int IP_ECN_set_ce(struct iphdr *iph) return 1; } +static inline int IP_ECN_set_ect1(struct iphdr *iph) +{ + u32 check = (__force u32)iph->check; + + if ((iph->tos & INET_ECN_MASK) != INET_ECN_ECT_0) + return 0; + + check += (__force u16)htons(0x100); + + iph->check = (__force __sum16)(check + (check>=0xFFFF)); + iph->tos ^= INET_ECN_MASK; + return 1; +} + static inline void IP_ECN_clear(struct iphdr *iph) { iph->tos &= ~INET_ECN_MASK; @@ -134,6 +148,22 @@ static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph) return 1; } +static inline int IP6_ECN_set_ect1(struct sk_buff *skb, struct ipv6hdr *iph) +{ + __be32 from, to; + + if ((ipv6_get_dsfield(iph) & INET_ECN_MASK) != INET_ECN_ECT_0) + return 0; + + from = *(__be32 *)iph; + to = from ^ htonl(INET_ECN_MASK << 20); + *(__be32 *)iph = to; + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_add(csum_sub(skb->csum, (__force __wsum)from), + (__force __wsum)to); + return 1; +} + static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner) { dscp &= ~INET_ECN_MASK; @@ -159,6 +189,25 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb) return 0; } +static inline int INET_ECN_set_ect1(struct sk_buff *skb) +{ + switch (skb->protocol) { + case cpu_to_be16(ETH_P_IP): + if (skb_network_header(skb) + sizeof(struct iphdr) <= + skb_tail_pointer(skb)) + return IP_ECN_set_ect1(ip_hdr(skb)); + break; + + case cpu_to_be16(ETH_P_IPV6): + if (skb_network_header(skb) + sizeof(struct ipv6hdr) <= + skb_tail_pointer(skb)) + return IP6_ECN_set_ect1(skb, ipv6_hdr(skb)); + break; + } + + return 0; +} + /* * RFC 6040 4.2 * To decapsulate the inner header at the tunnel egress, a compliant @@ -208,8 +257,12 @@ static inline int INET_ECN_decapsulate(struct sk_buff *skb, int rc; rc = __INET_ECN_decapsulate(outer, inner, &set_ce); - if (!rc && set_ce) - INET_ECN_set_ce(skb); + if (!rc) { + if (set_ce) + INET_ECN_set_ce(skb); + else if ((outer & INET_ECN_MASK) == INET_ECN_ECT_1) + INET_ECN_set_ect1(skb); + } return rc; } diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 4b5656c71abc..bd0f1595bdc7 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -177,6 +177,7 @@ struct fib6_info { struct rt6_info { struct dst_entry dst; struct fib6_info __rcu *from; + int sernum; struct rt6key rt6i_dst; struct rt6key rt6i_src; @@ -260,6 +261,9 @@ static inline u32 rt6_get_cookie(const struct rt6_info *rt) struct fib6_info *from; u32 cookie = 0; + if (rt->sernum) + return rt->sernum; + rcu_read_lock(); from = rcu_dereference(rt->from); diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index c7e15a213ef2..0fca98a3d2d3 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -428,6 +428,13 @@ static inline int rt_genid_ipv4(struct net *net) return atomic_read(&net->ipv4.rt_genid); } +#if IS_ENABLED(CONFIG_IPV6) +static inline int rt_genid_ipv6(const struct net *net) +{ + return atomic_read(&net->ipv6.fib6_sernum); +} +#endif + static inline void rt_genid_bump_ipv4(struct net *net) { atomic_inc(&net->ipv4.rt_genid); diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 3d920ff15c80..2ea0c08188e6 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -82,6 +82,7 @@ struct mqueue_inode_info { struct sigevent notify; struct pid *notify_owner; + u32 notify_self_exec_id; struct user_namespace *notify_user_ns; struct user_struct *user; /* user who created, for accounting */ struct sock *notify_sock; @@ -709,28 +710,44 @@ static void __do_notify(struct mqueue_inode_info *info) * synchronously. */ if (info->notify_owner && info->attr.mq_curmsgs == 1) { - struct kernel_siginfo sig_i; switch (info->notify.sigev_notify) { case SIGEV_NONE: break; - case SIGEV_SIGNAL: - /* sends signal */ + case SIGEV_SIGNAL: { + struct kernel_siginfo sig_i; + struct task_struct *task; + + /* do_mq_notify() accepts sigev_signo == 0, why?? */ + if (!info->notify.sigev_signo) + break; clear_siginfo(&sig_i); sig_i.si_signo = info->notify.sigev_signo; sig_i.si_errno = 0; sig_i.si_code = SI_MESGQ; sig_i.si_value = info->notify.sigev_value; - /* map current pid/uid into info->owner's namespaces */ rcu_read_lock(); + /* map current pid/uid into info->owner's namespaces */ sig_i.si_pid = task_tgid_nr_ns(current, ns_of_pid(info->notify_owner)); - sig_i.si_uid = from_kuid_munged(info->notify_user_ns, current_uid()); + sig_i.si_uid = from_kuid_munged(info->notify_user_ns, + current_uid()); + /* + * We can't use kill_pid_info(), this signal should + * bypass check_kill_permission(). It is from kernel + * but si_fromuser() can't know this. + * We do check the self_exec_id, to avoid sending + * signals to programs that don't expect them. + */ + task = pid_task(info->notify_owner, PIDTYPE_TGID); + if (task && task->self_exec_id == + info->notify_self_exec_id) { + do_send_sig_info(info->notify.sigev_signo, + &sig_i, task, PIDTYPE_TGID); + } rcu_read_unlock(); - - kill_pid_info(info->notify.sigev_signo, - &sig_i, info->notify_owner); break; + } case SIGEV_THREAD: set_cookie(info->notify_cookie, NOTIFY_WOKENUP); netlink_sendskb(info->notify_sock, info->notify_cookie); @@ -1315,6 +1332,7 @@ retry: info->notify.sigev_signo = notification->sigev_signo; info->notify.sigev_value = notification->sigev_value; info->notify.sigev_notify = SIGEV_SIGNAL; + info->notify_self_exec_id = current->self_exec_id; break; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c6ccaf6c62f7..721947b9962d 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8318,6 +8318,19 @@ static int allocate_trace_buffers(struct trace_array *tr, int size) */ allocate_snapshot = false; #endif + + /* + * Because of some magic with the way alloc_percpu() works on + * x86_64, we need to synchronize the pgd of all the tables, + * otherwise the trace events that happen in x86_64 page fault + * handlers can't cope with accessing the chance that a + * alloc_percpu()'d memory might be touched in the page fault trace + * event. Oh, and we need to audit all other alloc_percpu() and vmalloc() + * calls in tracing, because something might get triggered within a + * page fault trace event! + */ + vmalloc_sync_mappings(); + return 0; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 2f0f7fcee73e..fba4b48451f6 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -454,7 +454,7 @@ static bool __within_notrace_func(unsigned long addr) static bool within_notrace_func(struct trace_kprobe *tk) { - unsigned long addr = addr = trace_kprobe_address(tk); + unsigned long addr = trace_kprobe_address(tk); char symname[KSYM_NAME_LEN], *p; if (!__within_notrace_func(addr)) diff --git a/kernel/umh.c b/kernel/umh.c index 7f255b5a8845..11bf5eea474c 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -544,6 +544,11 @@ EXPORT_SYMBOL_GPL(fork_usermode_blob); * Runs a user-space application. The application is started * asynchronously if wait is not set, and runs as a child of system workqueues. * (ie. it runs with full root capabilities and optimized affinity). + * + * Note: successful return value does not guarantee the helper was called at + * all. You can't rely on sub_info->{init,cleanup} being called even for + * UMH_WAIT_* wait modes as STATIC_USERMODEHELPER_PATH="" turns all helpers + * into a successful no-op. */ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) { diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 62f05f605fb5..3f2480e4c5af 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -21,7 +21,7 @@ struct backing_dev_info noop_backing_dev_info = { EXPORT_SYMBOL_GPL(noop_backing_dev_info); static struct class *bdi_class; -const char *bdi_unknown_name = "(unknown)"; +static const char *bdi_unknown_name = "(unknown)"; /* * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU @@ -938,7 +938,8 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) if (bdi->dev) /* The driver needs to use separate queues per device */ return 0; - dev = device_create_vargs(bdi_class, NULL, MKDEV(0, 0), bdi, fmt, args); + vsnprintf(bdi->dev_name, sizeof(bdi->dev_name), fmt, args); + dev = device_create(bdi_class, NULL, MKDEV(0, 0), bdi, bdi->dev_name); if (IS_ERR(dev)) return PTR_ERR(dev); @@ -1043,6 +1044,14 @@ void bdi_put(struct backing_dev_info *bdi) } EXPORT_SYMBOL(bdi_put); +const char *bdi_dev_name(struct backing_dev_info *bdi) +{ + if (!bdi || !bdi->dev) + return bdi_unknown_name; + return bdi->dev_name; +} +EXPORT_SYMBOL_GPL(bdi_dev_name); + static wait_queue_head_t congestion_wqh[2] = { __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]), __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1]) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8159000781be..0d6f3ea86738 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5101,19 +5101,22 @@ static struct mem_cgroup *mem_cgroup_alloc(void) unsigned int size; int node; int __maybe_unused i; + long error = -ENOMEM; size = sizeof(struct mem_cgroup); size += nr_node_ids * sizeof(struct mem_cgroup_per_node *); memcg = kzalloc(size, GFP_KERNEL); if (!memcg) - return NULL; + return ERR_PTR(error); memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL, 1, MEM_CGROUP_ID_MAX, GFP_KERNEL); - if (memcg->id.id < 0) + if (memcg->id.id < 0) { + error = memcg->id.id; goto fail; + } memcg->vmstats_local = alloc_percpu(struct memcg_vmstats_percpu); if (!memcg->vmstats_local) @@ -5158,7 +5161,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void) fail: mem_cgroup_id_remove(memcg); __mem_cgroup_free(memcg); - return NULL; + return ERR_PTR(error); } static struct cgroup_subsys_state * __ref @@ -5169,8 +5172,8 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) long error = -ENOMEM; memcg = mem_cgroup_alloc(); - if (!memcg) - return ERR_PTR(error); + if (IS_ERR(memcg)) + return ERR_CAST(memcg); memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; @@ -5220,7 +5223,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) fail: mem_cgroup_id_remove(memcg); mem_cgroup_free(memcg); - return ERR_PTR(-ENOMEM); + return ERR_PTR(error); } static int mem_cgroup_css_online(struct cgroup_subsys_state *css) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d387ca74cb5a..98d5c940facd 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1555,6 +1555,7 @@ void set_zone_contiguous(struct zone *zone) if (!__pageblock_pfn_to_page(block_start_pfn, block_end_pfn, zone)) return; + cond_resched(); } /* We confirm that there is no hole */ @@ -2350,6 +2351,14 @@ static inline void boost_watermark(struct zone *zone) if (!watermark_boost_factor) return; + /* + * Don't bother in zones that are unlikely to produce results. + * On small machines, including kdump capture kernels running + * in a small area, boosting the watermark can cause an out of + * memory situation immediately. + */ + if ((pageblock_nr_pages * 4) > zone_managed_pages(zone)) + return; max_boost = mult_frac(zone->_watermark[WMARK_HIGH], watermark_boost_factor, 10000); diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 8033f24f506c..a9e7540c5691 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -897,7 +897,7 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset, orig_node = batadv_v_ogm_orig_get(bat_priv, ogm_packet->orig); if (!orig_node) - return; + goto out; neigh_node = batadv_neigh_node_get_or_create(orig_node, if_incoming, ethhdr->h_source); diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 580609389f0f..70e3b161c663 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1009,15 +1009,8 @@ static struct batadv_nc_path *batadv_nc_get_path(struct batadv_priv *bat_priv, */ static u8 batadv_nc_random_weight_tq(u8 tq) { - u8 rand_val, rand_tq; - - get_random_bytes(&rand_val, sizeof(rand_val)); - /* randomize the estimated packet loss (max TQ - estimated TQ) */ - rand_tq = rand_val * (BATADV_TQ_MAX_VALUE - tq); - - /* normalize the randomized packet loss */ - rand_tq /= BATADV_TQ_MAX_VALUE; + u8 rand_tq = prandom_u32_max(BATADV_TQ_MAX_VALUE + 1 - tq); /* convert to (randomized) estimated tq again */ return BATADV_TQ_MAX_VALUE - rand_tq; diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index e5bbc28ed12c..079a13493880 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1150,7 +1150,7 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj, ret = batadv_parse_throughput(net_dev, buff, "throughput_override", &tp_override); if (!ret) - return count; + goto out; old_tp_override = atomic_read(&hard_iface->bat_v.throughput_override); if (old_tp_override == tp_override) @@ -1190,6 +1190,7 @@ static ssize_t batadv_show_throughput_override(struct kobject *kobj, tp_override = atomic_read(&hard_iface->bat_v.throughput_override); + batadv_hardif_put(hard_iface); return sprintf(buff, "%u.%u MBit\n", tp_override / 10, tp_override % 10); } diff --git a/net/core/devlink.c b/net/core/devlink.c index 4c25f1aa2d37..5667cae57072 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3907,6 +3907,11 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]); dump = false; + + if (start_offset == end_offset) { + err = 0; + goto nla_put_failure; + } } err = devlink_nl_region_read_snapshot_fill(skb, devlink, diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 920784a9b7ff..7b40d12f0c22 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1954,6 +1954,9 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, NEIGH_UPDATE_F_OVERRIDE_ISROUTER); } + if (protocol) + neigh->protocol = protocol; + if (ndm->ndm_flags & NTF_EXT_LEARNED) flags |= NEIGH_UPDATE_F_EXT_LEARNED; @@ -1967,9 +1970,6 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags, NETLINK_CB(skb).portid, extack); - if (protocol) - neigh->protocol = protocol; - neigh_release(neigh); out: diff --git a/net/dsa/master.c b/net/dsa/master.c index 3255dfc97f86..be0b4ed3b7d8 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -259,7 +259,8 @@ static void dsa_master_ndo_teardown(struct net_device *dev) { struct dsa_port *cpu_dp = dev->dsa_ptr; - dev->netdev_ops = cpu_dp->orig_ndo_ops; + if (cpu_dp->orig_ndo_ops) + dev->netdev_ops = cpu_dp->orig_ndo_ops; cpu_dp->orig_ndo_ops = NULL; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 894c7370c1bd..c81d8e9e5169 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1388,9 +1388,18 @@ static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res) } ip6_rt_copy_init(pcpu_rt, res); pcpu_rt->rt6i_flags |= RTF_PCPU; + + if (f6i->nh) + pcpu_rt->sernum = rt_genid_ipv6(dev_net(dev)); + return pcpu_rt; } +static bool rt6_is_valid(const struct rt6_info *rt6) +{ + return rt6->sernum == rt_genid_ipv6(dev_net(rt6->dst.dev)); +} + /* It should be called with rcu_read_lock() acquired */ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res) { @@ -1398,6 +1407,19 @@ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res) pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu); + if (pcpu_rt && pcpu_rt->sernum && !rt6_is_valid(pcpu_rt)) { + struct rt6_info *prev, **p; + + p = this_cpu_ptr(res->nh->rt6i_pcpu); + prev = xchg(p, NULL); + if (prev) { + dst_dev_put(&prev->dst); + dst_release(&prev->dst); + } + + pcpu_rt = NULL; + } + return pcpu_rt; } @@ -2599,6 +2621,9 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) rt = container_of(dst, struct rt6_info, dst); + if (rt->sernum) + return rt6_is_valid(rt) ? dst : NULL; + rcu_read_lock(); /* All IPV6 dsts are created with ->obsolete set to the value diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index 3d816a1e5442..59151dc07fdc 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -68,15 +68,13 @@ static bool udp_manip_pkt(struct sk_buff *skb, enum nf_nat_manip_type maniptype) { struct udphdr *hdr; - bool do_csum; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct udphdr *)(skb->data + hdroff); - do_csum = hdr->check || skb->ip_summed == CHECKSUM_PARTIAL; + __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, !!hdr->check); - __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, do_csum); return true; } diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 9f5dea0064ea..916a3c7f9eaf 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -165,12 +165,12 @@ static bool nf_osf_match_one(const struct sk_buff *skb, static const struct tcphdr *nf_osf_hdr_ctx_init(struct nf_osf_hdr_ctx *ctx, const struct sk_buff *skb, const struct iphdr *ip, - unsigned char *opts) + unsigned char *opts, + struct tcphdr *_tcph) { const struct tcphdr *tcp; - struct tcphdr _tcph; - tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph); + tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), _tcph); if (!tcp) return NULL; @@ -205,10 +205,11 @@ nf_osf_match(const struct sk_buff *skb, u_int8_t family, int fmatch = FMATCH_WRONG; struct nf_osf_hdr_ctx ctx; const struct tcphdr *tcp; + struct tcphdr _tcph; memset(&ctx, 0, sizeof(ctx)); - tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts); + tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts, &_tcph); if (!tcp) return false; @@ -265,10 +266,11 @@ bool nf_osf_find(const struct sk_buff *skb, const struct nf_osf_finger *kf; struct nf_osf_hdr_ctx ctx; const struct tcphdr *tcp; + struct tcphdr _tcph; memset(&ctx, 0, sizeof(ctx)); - tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts); + tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts, &_tcph); if (!tcp) return false; diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index dba70377bbd9..4021f726b58f 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -323,7 +323,8 @@ static void choke_reset(struct Qdisc *sch) sch->q.qlen = 0; sch->qstats.backlog = 0; - memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); + if (q->tab) + memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); q->head = q->tail = 0; red_restart(&q->vars); } diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index c261c0a18868..76d72c3f52ed 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -417,7 +417,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, q->quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM])); if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]) - q->drop_batch_size = min(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])); + q->drop_batch_size = max(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])); if (tb[TCA_FQ_CODEL_MEMORY_LIMIT]) q->memory_limit = min(1U << 31, nla_get_u32(tb[TCA_FQ_CODEL_MEMORY_LIMIT])); diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index c787d4d46017..5a6def5e4e6d 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -637,6 +637,15 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) if (ctl->divisor && (!is_power_of_2(ctl->divisor) || ctl->divisor > 65536)) return -EINVAL; + + /* slot->allot is a short, make sure quantum is not too big. */ + if (ctl->quantum) { + unsigned int scaled = SFQ_ALLOT_SIZE(ctl->quantum); + + if (scaled <= 0 || scaled > SHRT_MAX) + return -EINVAL; + } + if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max, ctl_v1->Wlog)) return -EINVAL; diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c index 0fb10abf7579..7a5e4c454715 100644 --- a/net/sched/sch_skbprio.c +++ b/net/sched/sch_skbprio.c @@ -169,6 +169,9 @@ static int skbprio_change(struct Qdisc *sch, struct nlattr *opt, { struct tc_skbprio_qopt *ctl = nla_data(opt); + if (opt->nla_len != nla_attr_size(sizeof(*ctl))) + return -EINVAL; + sch->limit = ctl->limit; return 0; } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index c6d83a64eac3..5625a9500f21 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1865,7 +1865,7 @@ static enum sctp_disposition sctp_sf_do_dupcook_a( */ sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); return sctp_sf_do_9_2_start_shutdown(net, ep, asoc, - SCTP_ST_CHUNK(0), NULL, + SCTP_ST_CHUNK(0), repl, commands); } else { sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, @@ -5470,7 +5470,7 @@ enum sctp_disposition sctp_sf_do_9_2_start_shutdown( * in the Cumulative TSN Ack field the last sequential TSN it * has received from the peer. */ - reply = sctp_make_shutdown(asoc, NULL); + reply = sctp_make_shutdown(asoc, arg); if (!reply) goto nomem; @@ -6068,7 +6068,7 @@ enum sctp_disposition sctp_sf_autoclose_timer_expire( disposition = SCTP_DISPOSITION_CONSUME; if (sctp_outq_is_empty(&asoc->outqueue)) { disposition = sctp_sf_do_9_2_start_shutdown(net, ep, asoc, type, - arg, commands); + NULL, commands); } return disposition; diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 3a12fc18239b..73dbed0c4b6b 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -402,10 +402,11 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con) read_lock_bh(&sk->sk_callback_lock); ret = tipc_conn_rcv_sub(srv, con, &s); read_unlock_bh(&sk->sk_callback_lock); + if (!ret) + return 0; } - if (ret < 0) - tipc_conn_close(con); + tipc_conn_close(con); return ret; } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 41e9c2932b34..5513a08a4308 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -797,6 +797,8 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk, *copied -= sk_msg_free(sk, msg); tls_free_open_rec(sk); } + if (psock) + sk_psock_put(sk, psock); return err; } more_data: @@ -2076,8 +2078,9 @@ static void tls_data_ready(struct sock *sk) strp_data_ready(&ctx->strp); psock = sk_psock_get(sk); - if (psock && !list_empty(&psock->ingress_msg)) { - ctx->saved_data_ready(sk); + if (psock) { + if (!list_empty(&psock->ingress_msg)) + ctx->saved_data_ready(sk); sk_psock_put(sk, psock); } } diff --git a/scripts/decodecode b/scripts/decodecode index ba8b8d5834e6..fbdb325cdf4f 100755 --- a/scripts/decodecode +++ b/scripts/decodecode @@ -126,7 +126,7 @@ faultlinenum=$(( $(wc -l $T.oo | cut -d" " -f1) - \ faultline=`cat $T.dis | head -1 | cut -d":" -f2-` faultline=`echo "$faultline" | sed -e 's/\[/\\\[/g; s/\]/\\\]/g'` -cat $T.oo | sed -e "${faultlinenum}s/^\(.*:\)\(.*\)/\1\*\2\t\t<-- trapping instruction/" +cat $T.oo | sed -e "${faultlinenum}s/^\([^:]*:\)\(.*\)/\1\*\2\t\t<-- trapping instruction/" echo cat $T.aa cleanup diff --git a/tools/cgroup/iocost_monitor.py b/tools/cgroup/iocost_monitor.py index f79b23582a1d..7e344a78a627 100644 --- a/tools/cgroup/iocost_monitor.py +++ b/tools/cgroup/iocost_monitor.py @@ -159,7 +159,12 @@ class IocgStat: else: self.inflight_pct = 0 - self.debt_ms = iocg.abs_vdebt.counter.value_() / VTIME_PER_USEC / 1000 + # vdebt used to be an atomic64_t and is now u64, support both + try: + self.debt_ms = iocg.abs_vdebt.counter.value_() / VTIME_PER_USEC / 1000 + except: + self.debt_ms = iocg.abs_vdebt.value_() / VTIME_PER_USEC / 1000 + self.use_delay = blkg.use_delay.counter.value_() self.delay_ms = blkg.delay_nsec.counter.value_() / 1_000_000 diff --git a/tools/objtool/check.c b/tools/objtool/check.c index d6a971326f87..fcc6cd404f56 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1402,7 +1402,7 @@ static int update_insn_state_regs(struct instruction *insn, struct insn_state *s struct cfi_reg *cfa = &state->cfa; struct stack_op *op = &insn->stack_op; - if (cfa->base != CFI_SP) + if (cfa->base != CFI_SP && cfa->base != CFI_SP_INDIRECT) return 0; /* push */ diff --git a/virt/kvm/arm/hyp/aarch32.c b/virt/kvm/arm/hyp/aarch32.c index d31f267961e7..25c0e47d57cb 100644 --- a/virt/kvm/arm/hyp/aarch32.c +++ b/virt/kvm/arm/hyp/aarch32.c @@ -125,12 +125,16 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu) */ void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr) { + u32 pc = *vcpu_pc(vcpu); bool is_thumb; is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT); if (is_thumb && !is_wide_instr) - *vcpu_pc(vcpu) += 2; + pc += 2; else - *vcpu_pc(vcpu) += 4; + pc += 4; + + *vcpu_pc(vcpu) = pc; + kvm_adjust_itstate(vcpu); } diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index 0d090482720d..7eacf00e5abe 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -389,7 +389,7 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, static void vgic_change_active_prepare(struct kvm_vcpu *vcpu, u32 intid) { if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || - intid > VGIC_NR_PRIVATE_IRQS) + intid >= VGIC_NR_PRIVATE_IRQS) kvm_arm_halt_guest(vcpu->kvm); } @@ -397,7 +397,7 @@ static void vgic_change_active_prepare(struct kvm_vcpu *vcpu, u32 intid) static void vgic_change_active_finish(struct kvm_vcpu *vcpu, u32 intid) { if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || - intid > VGIC_NR_PRIVATE_IRQS) + intid >= VGIC_NR_PRIVATE_IRQS) kvm_arm_resume_guest(vcpu->kvm); }