diff --git a/Makefile b/Makefile index fcfef30ca9a6..47a9f9883bdd 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 14 -SUBLEVEL = 113 +SUBLEVEL = 114 EXTRAVERSION = NAME = Petit Gorille

@@ -653,8 +653,7 @@ KBUILD_CFLAGS += $(call cc-disable-warning, int-in-bool-context) KBUILD_CFLAGS += $(call cc-disable-warning, attribute-alias)

ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE -KBUILD_CFLAGS += $(call cc-option,-Oz,-Os) -KBUILD_CFLAGS += $(call cc-disable-warning,maybe-uninitialized,) +KBUILD_CFLAGS += -Os $(call cc-disable-warning,maybe-uninitialized,) else ifdef CONFIG_PROFILE_ALL_BRANCHES KBUILD_CFLAGS += -O2 $(call cc-disable-warning,maybe-uninitialized,) diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h index b447b4db423a..fd1e722f3821 100644 --- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -50,7 +50,7 @@ do { \ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr) { - int oldval, ret, tmp; + int oldval = 0, ret, tmp; u32 __user *uaddr = __uaccess_mask_ptr(_uaddr);

pagefault_disable(); diff --git a/arch/x86/crypto/poly1305-avx2-x86_64.S b/arch/x86/crypto/poly1305-avx2-x86_64.S index 3b6e70d085da..8457cdd47f75 100644 --- a/arch/x86/crypto/poly1305-avx2-x86_64.S +++ b/arch/x86/crypto/poly1305-avx2-x86_64.S @@ -323,6 +323,12 @@ ENTRY(poly1305_4block_avx2) vpaddq t2,t1,t1 vmovq t1x,d4

+ # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 -> + # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small + # amount. Careful: we must not assume the carry bits 'd0 >> 26', + # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit + # integers. It's true in a single-block implementation, but not here. + # d1 += d0 >> 26 mov d0,%rax shr $26,%rax @@ -361,16 +367,16 @@ ENTRY(poly1305_4block_avx2) # h0 += (d4 >> 26) * 5 mov d4,%rax shr $26,%rax - lea (%eax,%eax,4),%eax - add %eax,%ebx + lea (%rax,%rax,4),%rax + add %rax,%rbx # h4 = d4 & 0x3ffffff mov d4,%rax and $0x3ffffff,%eax mov %eax,h4

# h1 += h0 >> 26 - mov %ebx,%eax - shr $26,%eax + mov %rbx,%rax + shr $26,%rax add %eax,h1 # h0 = h0 & 0x3ffffff andl $0x3ffffff,%ebx diff --git a/arch/x86/crypto/poly1305-sse2-x86_64.S b/arch/x86/crypto/poly1305-sse2-x86_64.S index c88c670cb5fc..5851c7418fb7 100644 --- a/arch/x86/crypto/poly1305-sse2-x86_64.S +++ b/arch/x86/crypto/poly1305-sse2-x86_64.S @@ -253,16 +253,16 @@ ENTRY(poly1305_block_sse2) # h0 += (d4 >> 26) * 5 mov d4,%rax shr $26,%rax - lea (%eax,%eax,4),%eax - add %eax,%ebx + lea (%rax,%rax,4),%rax + add %rax,%rbx # h4 = d4 & 0x3ffffff mov d4,%rax and $0x3ffffff,%eax mov %eax,h4

# h1 += h0 >> 26 - mov %ebx,%eax - shr $26,%eax + mov %rbx,%rax + shr $26,%rax add %eax,h1 # h0 = h0 & 0x3ffffff andl $0x3ffffff,%ebx @@ -520,6 +520,12 @@ ENTRY(poly1305_2block_sse2) paddq t2,t1 movq t1,d4

+ # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 -> + # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small + # amount. Careful: we must not assume the carry bits 'd0 >> 26', + # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit + # integers. It's true in a single-block implementation, but not here. + # d1 += d0 >> 26 mov d0,%rax shr $26,%rax @@ -558,16 +564,16 @@ ENTRY(poly1305_2block_sse2) # h0 += (d4 >> 26) * 5 mov d4,%rax shr $26,%rax - lea (%eax,%eax,4),%eax - add %eax,%ebx + lea (%rax,%rax,4),%rax + add %rax,%rbx # h4 = d4 & 0x3ffffff mov d4,%rax and $0x3ffffff,%eax mov %eax,h4

# h1 += h0 >> 26 - mov %ebx,%eax - shr $26,%eax + mov %rbx,%rax + shr $26,%rax add %eax,h1 # h0 = h0 & 0x3ffffff andl $0x3ffffff,%ebx diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 3e5dd85b019a..263af6312329 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -117,22 +117,39 @@ static __initconst const u64 amd_hw_cache_event_ids };

/* - * AMD Performance Monitor K7 and later. + * AMD Performance Monitor K7 and later, up to and including Family 16h: */ static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] = { - [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, - [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, - [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d, - [PERF_COUNT_HW_CACHE_MISSES] = 0x077e, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, - [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, - [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */ - [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */ + [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d, + [PERF_COUNT_HW_CACHE_MISSES] = 0x077e, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */ + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */ +}; + +/* + * AMD Performance Monitor Family 17h and later: + */ +static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] = +{ + [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x0287, + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x0187, };

static u64 amd_pmu_event_map(int hw_event) { + if (boot_cpu_data.x86 >= 0x17) + return amd_f17h_perfmon_event_map[hw_event]; + return amd_perfmon_event_map[hw_event]; }

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index dc8f8b3e6cec..99d45660242e 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3001,7 +3001,7 @@ static unsigned long intel_pmu_free_running_flags(struct perf_event *event) flags &= ~PERF_SAMPLE_TIME; if (!event->attr.exclude_kernel) flags &= ~PERF_SAMPLE_REGS_USER; - if (event->attr.sample_regs_user & ~PEBS_REGS) + if (event->attr.sample_regs_user & ~PEBS_GP_REGS) flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR); return flags; } diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 84b3841c131d..bfe16631fd1d 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -95,25 +95,25 @@ struct amd_nb { PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \ PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER)

-#define PEBS_REGS \ - (PERF_REG_X86_AX | \ - PERF_REG_X86_BX | \ - PERF_REG_X86_CX | \ - PERF_REG_X86_DX | \ - PERF_REG_X86_DI | \ - PERF_REG_X86_SI | \ - PERF_REG_X86_SP | \ - PERF_REG_X86_BP | \ - PERF_REG_X86_IP | \ - PERF_REG_X86_FLAGS | \ - PERF_REG_X86_R8 | \ - PERF_REG_X86_R9 | \ - PERF_REG_X86_R10 | \ - PERF_REG_X86_R11 | \ - PERF_REG_X86_R12 | \ - PERF_REG_X86_R13 | \ - PERF_REG_X86_R14 | \ - PERF_REG_X86_R15) +#define PEBS_GP_REGS \ + ((1ULL << PERF_REG_X86_AX) | \ + (1ULL << PERF_REG_X86_BX) | \ + (1ULL << PERF_REG_X86_CX) | \ + (1ULL << PERF_REG_X86_DX) | \ + (1ULL << PERF_REG_X86_DI) | \ + (1ULL << PERF_REG_X86_SI) | \ + (1ULL << PERF_REG_X86_SP) | \ + (1ULL << PERF_REG_X86_BP) | \ + (1ULL << PERF_REG_X86_IP) | \ + (1ULL << PERF_REG_X86_FLAGS) | \ + (1ULL << PERF_REG_X86_R8) | \ + (1ULL << PERF_REG_X86_R9) | \ + (1ULL << PERF_REG_X86_R10) | \ + (1ULL << PERF_REG_X86_R11) | \ + (1ULL << PERF_REG_X86_R12) | \ + (1ULL << PERF_REG_X86_R13) | \ + (1ULL << PERF_REG_X86_R14) | \ + (1ULL << PERF_REG_X86_R15))

/* * Per register state. diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index ec7aedba3d74..5567705e0601 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -271,7 +271,7 @@ static const struct { const char *option; enum spectre_v2_user_cmd cmd; bool secure; -} v2_user_options[] __initdata = { +} v2_user_options[] __initconst = { { "auto", SPECTRE_V2_USER_CMD_AUTO, false }, { "off", SPECTRE_V2_USER_CMD_NONE, false }, { "on", SPECTRE_V2_USER_CMD_FORCE, true }, @@ -406,7 +406,7 @@ static const struct { const char *option; enum spectre_v2_mitigation_cmd cmd; bool secure; -} mitigation_options[] __initdata = { +} mitigation_options[] __initconst = { { "off", SPECTRE_V2_CMD_NONE, false }, { "on", SPECTRE_V2_CMD_FORCE, true }, { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, @@ -642,7 +642,7 @@ static const char * const ssb_strings[] = { static const struct { const char *option; enum ssb_mitigation_cmd cmd; -} ssb_mitigation_options[] __initdata = { +} ssb_mitigation_options[] __initconst = { { "auto", SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */ { "on", SPEC_STORE_BYPASS_CMD_ON }, /* Disable Speculative Store Bypass */ { "off", SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */ diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 65452d555f05..56cf6c263254 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -553,6 +553,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) unsigned long *sara = stack_addr(regs);

ri->ret_addr = (kprobe_opcode_t *) *sara; + ri->fp = sara;

/* Replace the return addr with trampoline addr */ *sara = (unsigned long) &kretprobe_trampoline; @@ -754,15 +755,21 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; kprobe_opcode_t *correct_ret_addr = NULL; + void *frame_pointer; + bool skipped = false;

INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); /* fixup registers */ #ifdef CONFIG_X86_64 regs->cs = __KERNEL_CS; + /* On x86-64, we use pt_regs->sp for return address holder. */ + frame_pointer = &regs->sp; #else regs->cs = __KERNEL_CS | get_kernel_rpl(); regs->gs = 0; + /* On x86-32, we use pt_regs->flags for return address holder. */ + frame_pointer = &regs->flags; #endif regs->ip = trampoline_address; regs->orig_ax = ~0UL; @@ -784,8 +791,25 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) if (ri->task != current) /* another task is sharing our hash bucket */ continue; + /* + * Return probes must be pushed on this hash list correct + * order (same as return order) so that it can be poped + * correctly. However, if we find it is pushed it incorrect + * order, this means we find a function which should not be + * probed, because the wrong order entry is pushed on the + * path of processing other kretprobe itself. + */ + if (ri->fp != frame_pointer) { + if (!skipped) + pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n"); + skipped = true; + continue; + }

orig_ret_address = (unsigned long)ri->ret_addr; + if (skipped) + pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n", + ri->rp->kp.addr);

if (orig_ret_address != trampoline_address) /* @@ -803,6 +827,8 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) if (ri->task != current) /* another task is sharing our hash bucket */ continue; + if (ri->fp != frame_pointer) + continue;

orig_ret_address = (unsigned long)ri->ret_addr; if (ri->rp && ri->rp->handler) { diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index a98d1cdd6299..d2ef967bfafb 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -465,10 +465,12 @@ static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk)

void speculation_ctrl_update(unsigned long tif) { + unsigned long flags; + /* Forced update. Make sure all relevant TIF flags are different */ - preempt_disable(); + local_irq_save(flags); __speculation_ctrl_update(~tif, tif); - preempt_enable(); + local_irq_restore(flags); }

/* Called from seccomp/prctl update */ diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 5f758568fc44..2bcadfc5b2f0 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2588,15 +2588,13 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) * CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU * supports long mode. */ - cr4 = ctxt->ops->get_cr(ctxt, 4); if (emulator_has_longmode(ctxt)) { struct desc_struct cs_desc;

/* Zero CR4.PCIDE before CR0.PG. */ - if (cr4 & X86_CR4_PCIDE) { + cr4 = ctxt->ops->get_cr(ctxt, 4); + if (cr4 & X86_CR4_PCIDE) ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE); - cr4 &= ~X86_CR4_PCIDE; - }

/* A 32-bit code segment is required to clear EFER.LMA. */ memset(&cs_desc, 0, sizeof(cs_desc)); @@ -2610,13 +2608,16 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) if (cr0 & X86_CR0_PE) ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE));

- /* Now clear CR4.PAE (which must be done before clearing EFER.LME). */ - if (cr4 & X86_CR4_PAE) - ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE); + if (emulator_has_longmode(ctxt)) { + /* Clear CR4.PAE before clearing EFER.LME. */ + cr4 = ctxt->ops->get_cr(ctxt, 4); + if (cr4 & X86_CR4_PAE) + ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);

- /* And finally go back to 32-bit mode. */ - efer = 0; - ctxt->ops->set_msr(ctxt, MSR_EFER, efer); + /* And finally go back to 32-bit mode. */ + efer = 0; + ctxt->ops->set_msr(ctxt, MSR_EFER, efer); + }

smbase = ctxt->ops->get_smbase(ctxt); if (emulator_has_longmode(ctxt)) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index c387047e926a..1296e44fd969 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2211,6 +2211,7 @@ static int pf_interception(struct vcpu_svm *svm) static int db_interception(struct vcpu_svm *svm) { struct kvm_run *kvm_run = svm->vcpu.run; + struct kvm_vcpu *vcpu = &svm->vcpu;

if (!(svm->vcpu.guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) && @@ -2221,6 +2222,8 @@ static int db_interception(struct vcpu_svm *svm)

if (svm->nmi_singlestep) { disable_nmi_singlestep(svm); + /* Make sure we check for pending NMIs upon entry */ + kvm_make_request(KVM_REQ_EVENT, vcpu); }

if (svm->vcpu.guest_debug & @@ -4014,14 +4017,25 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm) kvm_lapic_reg_write(apic, APIC_ICR, icrl); break; case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: { + int i; + struct kvm_vcpu *vcpu; + struct kvm *kvm = svm->vcpu.kvm; struct kvm_lapic *apic = svm->vcpu.arch.apic;

/* - * Update ICR high and low, then emulate sending IPI, - * which is handled when writing APIC_ICR. + * At this point, we expect that the AVIC HW has already + * set the appropriate IRR bits on the valid target + * vcpus. So, we just need to kick the appropriate vcpu. */ - kvm_lapic_reg_write(apic, APIC_ICR2, icrh); - kvm_lapic_reg_write(apic, APIC_ICR, icrl); + kvm_for_each_vcpu(i, vcpu, kvm) { + bool m = kvm_apic_match_dest(vcpu, apic, + icrl & KVM_APIC_SHORT_MASK, + GET_APIC_DEST_FIELD(icrh), + icrl & KVM_APIC_DEST_MASK); + + if (m && !avic_vcpu_is_running(vcpu)) + kvm_vcpu_wake_up(vcpu); + } break; } case AVIC_IPI_FAILURE_INVALID_TARGET: diff --git a/crypto/testmgr.h b/crypto/testmgr.h index fbc0fab5e79e..12835f072614 100644 --- a/crypto/testmgr.h +++ b/crypto/testmgr.h @@ -4660,7 +4660,49 @@ static const struct hash_testvec poly1305_tv_template[] = { .psize = 80, .digest = "\x13\x00\x00\x00\x00\x00\x00\x00" "\x00\x00\x00\x00\x00\x00\x00\x00", - }, + }, { /* Regression test for overflow in AVX2 implementation */ + .plaintext = "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff", + .psize = 300, + .digest = "\xfb\x5e\x96\xd8\x61\xd5\xc7\xc8" + "\x78\xe5\x87\xcc\x2d\x5a\x22\xe1", + } };

/* diff --git a/drivers/char/tpm/tpm_i2c_atmel.c b/drivers/char/tpm/tpm_i2c_atmel.c index 32a8e27c5382..cc4e642d3180 100644 --- a/drivers/char/tpm/tpm_i2c_atmel.c +++ b/drivers/char/tpm/tpm_i2c_atmel.c @@ -69,6 +69,10 @@ static int i2c_atmel_send(struct tpm_chip *chip, u8 *buf, size_t len) if (status < 0) return status;

+ /* The upper layer does not support incomplete sends. */ + if (status != len) + return -E2BIG; + return 0; }

diff --git a/drivers/crypto/amcc/crypto4xx_alg.c b/drivers/crypto/amcc/crypto4xx_alg.c index 4afca3968773..e3b8bebfdd30 100644 --- a/drivers/crypto/amcc/crypto4xx_alg.c +++ b/drivers/crypto/amcc/crypto4xx_alg.c @@ -138,7 +138,8 @@ static int crypto4xx_setkey_aes(struct crypto_ablkcipher *cipher, sa = (struct dynamic_sa_ctl *) ctx->sa_in; ctx->hash_final = 0;

- set_dynamic_sa_command_0(sa, SA_NOT_SAVE_HASH, SA_NOT_SAVE_IV, + set_dynamic_sa_command_0(sa, SA_NOT_SAVE_HASH, (cm == CRYPTO_MODE_CBC ? + SA_SAVE_IV : SA_NOT_SAVE_IV), SA_LOAD_HASH_FROM_SA, SA_LOAD_IV_FROM_STATE, SA_NO_HEADER_PROC, SA_HASH_ALG_NULL, SA_CIPHER_ALG_AES, SA_PAD_TYPE_ZERO, diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c index 3f9eee7e555f..8d4d8db244e9 100644 --- a/drivers/crypto/amcc/crypto4xx_core.c +++ b/drivers/crypto/amcc/crypto4xx_core.c @@ -645,6 +645,15 @@ static u32 crypto4xx_ablkcipher_done(struct crypto4xx_device *dev, addr = dma_map_page(dev->core_dev->device, sg_page(dst), dst->offset, dst->length, DMA_FROM_DEVICE); } + + if (pd_uinfo->sa_va->sa_command_0.bf.save_iv == SA_SAVE_IV) { + struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req); + + crypto4xx_memcpy_from_le32((u32 *)req->iv, + pd_uinfo->sr_va->save_iv, + crypto_skcipher_ivsize(skcipher)); + } + crypto4xx_ret_sg_desc(dev, pd_uinfo); if (ablk_req->base.complete != NULL) ablk_req->base.complete(&ablk_req->base, 0); diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c index 1d645c9ab417..cac262a912c1 100644 --- a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c +++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c @@ -337,7 +337,8 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = { DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "FlexBook edge11 - M-FBE11"), }, .driver_data = (void *)&sipodev_desc - } + }, + { } /* Terminate list */ };

diff --git a/drivers/iio/accel/kxcjk-1013.c b/drivers/iio/accel/kxcjk-1013.c index 784636800361..780f886ccbfe 100644 --- a/drivers/iio/accel/kxcjk-1013.c +++ b/drivers/iio/accel/kxcjk-1013.c @@ -1340,6 +1340,8 @@ static int kxcjk1013_resume(struct device *dev)

mutex_lock(&data->mutex); ret = kxcjk1013_set_mode(data, OPERATION); + if (ret == 0) + ret = kxcjk1013_set_range(data, data->range); mutex_unlock(&data->mutex);

return ret; diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c index 22c4c17cd996..a1d072ecb717 100644 --- a/drivers/iio/adc/ad_sigma_delta.c +++ b/drivers/iio/adc/ad_sigma_delta.c @@ -121,6 +121,7 @@ static int ad_sd_read_reg_raw(struct ad_sigma_delta *sigma_delta, if (sigma_delta->info->has_registers) { data[0] = reg << sigma_delta->info->addr_shift; data[0] |= sigma_delta->info->read_mask; + data[0] |= sigma_delta->comm; spi_message_add_tail(&t[0], &m); } spi_message_add_tail(&t[1], &m); diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c index cd686179aa92..492f6c8ba735 100644 --- a/drivers/iio/adc/at91_adc.c +++ b/drivers/iio/adc/at91_adc.c @@ -705,23 +705,29 @@ static int at91_adc_read_raw(struct iio_dev *idev, ret = wait_event_interruptible_timeout(st->wq_data_avail, st->done, msecs_to_jiffies(1000)); - if (ret == 0) - ret = -ETIMEDOUT; - if (ret < 0) { - mutex_unlock(&st->lock); - return ret; - } - - *val = st->last_value;

+ /* Disable interrupts, regardless if adc conversion was + * successful or not + */ at91_adc_writel(st, AT91_ADC_CHDR, AT91_ADC_CH(chan->channel)); at91_adc_writel(st, AT91_ADC_IDR, BIT(chan->channel));

- st->last_value = 0; - st->done = false; + if (ret > 0) { + /* a valid conversion took place */ + *val = st->last_value; + st->last_value = 0; + st->done = false; + ret = IIO_VAL_INT; + } else if (ret == 0) { + /* conversion timeout */ + dev_err(&idev->dev, "ADC Channel %d timeout.\n", + chan->channel); + ret = -ETIMEDOUT; + } + mutex_unlock(&st->lock); - return IIO_VAL_INT; + return ret;

case IIO_CHAN_INFO_SCALE: *val = st->vref_mv; diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c index 38e8783e4b05..287fbe08264d 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c @@ -104,9 +104,10 @@ static int cros_ec_sensors_read(struct iio_dev *indio_dev, * Do not use IIO_DEGREE_TO_RAD to avoid precision * loss. Round to the nearest integer. */ - *val = div_s64(val64 * 314159 + 9000000ULL, 1000); - *val2 = 18000 << (CROS_EC_SENSOR_BITS - 1); - ret = IIO_VAL_FRACTIONAL; + *val = 0; + *val2 = div_s64(val64 * 3141592653ULL, + 180 << (CROS_EC_SENSOR_BITS - 1)); + ret = IIO_VAL_INT_PLUS_NANO; break; case MOTIONSENSE_TYPE_MAG: /* diff --git a/drivers/iio/dac/mcp4725.c b/drivers/iio/dac/mcp4725.c index 6ab1f23e5a79..fe3e42defb33 100644 --- a/drivers/iio/dac/mcp4725.c +++ b/drivers/iio/dac/mcp4725.c @@ -98,6 +98,7 @@ static ssize_t mcp4725_store_eeprom(struct device *dev,

inoutbuf[0] = 0x60; /* write EEPROM */ inoutbuf[0] |= data->ref_mode << 3; + inoutbuf[0] |= data->powerdown ? ((data->powerdown_mode + 1) << 1) : 0; inoutbuf[1] = data->dac_value >> 4; inoutbuf[2] = (data->dac_value & 0xf) << 4;

diff --git a/drivers/iio/gyro/bmg160_core.c b/drivers/iio/gyro/bmg160_core.c index 821919dd245b..b5a5517e3ce1 100644 --- a/drivers/iio/gyro/bmg160_core.c +++ b/drivers/iio/gyro/bmg160_core.c @@ -583,11 +583,10 @@ static int bmg160_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY: return bmg160_get_filter(data, val); case IIO_CHAN_INFO_SCALE: - *val = 0; switch (chan->type) { case IIO_TEMP: - *val2 = 500000; - return IIO_VAL_INT_PLUS_MICRO; + *val = 500; + return IIO_VAL_INT; case IIO_ANGL_VEL: { int i; @@ -595,6 +594,7 @@ static int bmg160_read_raw(struct iio_dev *indio_dev, for (i = 0; i < ARRAY_SIZE(bmg160_scale_table); ++i) { if (bmg160_scale_table[i].dps_range == data->dps_range) { + *val = 0; *val2 = bmg160_scale_table[i].scale; return IIO_VAL_INT_PLUS_MICRO; } diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c index e0d241a9aa30..a7be4670bf8f 100644 --- a/drivers/iio/gyro/mpu3050-core.c +++ b/drivers/iio/gyro/mpu3050-core.c @@ -29,7 +29,8 @@

#include "mpu3050.h"

-#define MPU3050_CHIP_ID 0x69 +#define MPU3050_CHIP_ID 0x68 +#define MPU3050_CHIP_ID_MASK 0x7E

/* * Register map: anything suffixed *_H is a big-endian high byte and always @@ -1178,8 +1179,9 @@ int mpu3050_common_probe(struct device *dev, goto err_power_down; }

- if (val != MPU3050_CHIP_ID) { - dev_err(dev, "unsupported chip id %02x\n", (u8)val); + if ((val & MPU3050_CHIP_ID_MASK) != MPU3050_CHIP_ID) { + dev_err(dev, "unsupported chip id %02x\n", + (u8)(val & MPU3050_CHIP_ID_MASK)); ret = -ENODEV; goto err_power_down; } diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index 78482d456c3b..d50125766093 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -320,9 +320,8 @@ static int iio_scan_mask_set(struct iio_dev *indio_dev, const unsigned long *mask; unsigned long *trialmask;

- trialmask = kmalloc_array(BITS_TO_LONGS(indio_dev->masklength), - sizeof(*trialmask), - GFP_KERNEL); + trialmask = kcalloc(BITS_TO_LONGS(indio_dev->masklength), + sizeof(*trialmask), GFP_KERNEL); if (trialmask == NULL) return -ENOMEM; if (!indio_dev->masklength) { diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index e565fd4fc414..97b7266ee0ff 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -1741,10 +1741,10 @@ EXPORT_SYMBOL(iio_device_register); **/ void iio_device_unregister(struct iio_dev *indio_dev) { - mutex_lock(&indio_dev->info_exist_lock); - cdev_device_del(&indio_dev->chrdev, &indio_dev->dev);

+ mutex_lock(&indio_dev->info_exist_lock); + iio_device_unregister_debugfs(indio_dev);

iio_disable_all_buffers(indio_dev); diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index ff5c4ad37a3a..8c0b80a54e4d 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -425,7 +425,7 @@ static u16 esdhc_readw_le(struct sdhci_host *host, int reg) val = readl(host->ioaddr + ESDHC_MIX_CTRL); else if (imx_data->socdata->flags & ESDHC_FLAG_STD_TUNING) /* the std tuning bits is in ACMD12_ERR for imx6sl */ - val = readl(host->ioaddr + SDHCI_ACMD12_ERR); + val = readl(host->ioaddr + SDHCI_AUTO_CMD_STATUS); }

if (val & ESDHC_MIX_CTRL_EXE_TUNE) @@ -490,7 +490,7 @@ static void esdhc_writew_le(struct sdhci_host *host, u16 val, int reg) } writel(new_val , host->ioaddr + ESDHC_MIX_CTRL); } else if (imx_data->socdata->flags & ESDHC_FLAG_STD_TUNING) { - u32 v = readl(host->ioaddr + SDHCI_ACMD12_ERR); + u32 v = readl(host->ioaddr + SDHCI_AUTO_CMD_STATUS); u32 m = readl(host->ioaddr + ESDHC_MIX_CTRL); if (val & SDHCI_CTRL_TUNED_CLK) { v |= ESDHC_MIX_CTRL_SMPCLK_SEL; @@ -508,7 +508,7 @@ static void esdhc_writew_le(struct sdhci_host *host, u16 val, int reg) v &= ~ESDHC_MIX_CTRL_EXE_TUNE; }

- writel(v, host->ioaddr + SDHCI_ACMD12_ERR); + writel(v, host->ioaddr + SDHCI_AUTO_CMD_STATUS); writel(m, host->ioaddr + ESDHC_MIX_CTRL); } return; @@ -937,9 +937,9 @@ static void esdhc_reset_tuning(struct sdhci_host *host) writel(ctrl, host->ioaddr + ESDHC_MIX_CTRL); writel(0, host->ioaddr + ESDHC_TUNE_CTRL_STATUS); } else if (imx_data->socdata->flags & ESDHC_FLAG_STD_TUNING) { - ctrl = readl(host->ioaddr + SDHCI_ACMD12_ERR); + ctrl = readl(host->ioaddr + SDHCI_AUTO_CMD_STATUS); ctrl &= ~ESDHC_MIX_CTRL_SMPCLK_SEL; - writel(ctrl, host->ioaddr + SDHCI_ACMD12_ERR); + writel(ctrl, host->ioaddr + SDHCI_AUTO_CMD_STATUS); } } } @@ -1303,7 +1303,7 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)

/* clear tuning bits in case ROM has set it already */ writel(0x0, host->ioaddr + ESDHC_MIX_CTRL); - writel(0x0, host->ioaddr + SDHCI_ACMD12_ERR); + writel(0x0, host->ioaddr + SDHCI_AUTO_CMD_STATUS); writel(0x0, host->ioaddr + ESDHC_TUNE_CTRL_STATUS); }

diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 0edcc2763f3c..9540fda7fc6b 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -82,8 +82,8 @@ void sdhci_dumpregs(struct sdhci_host *host) SDHCI_DUMP("Int enab: 0x%08x | Sig enab: 0x%08x\n", sdhci_readl(host, SDHCI_INT_ENABLE), sdhci_readl(host, SDHCI_SIGNAL_ENABLE)); - SDHCI_DUMP("AC12 err: 0x%08x | Slot int: 0x%08x\n", - sdhci_readw(host, SDHCI_ACMD12_ERR), + SDHCI_DUMP("ACmd stat: 0x%08x | Slot int: 0x%08x\n", + sdhci_readw(host, SDHCI_AUTO_CMD_STATUS), sdhci_readw(host, SDHCI_SLOT_INT_STATUS)); SDHCI_DUMP("Caps: 0x%08x | Caps_1: 0x%08x\n", sdhci_readl(host, SDHCI_CAPABILITIES), @@ -790,6 +790,11 @@ static void sdhci_set_transfer_irqs(struct sdhci_host *host) else host->ier = (host->ier & ~dma_irqs) | pio_irqs;

+ if (host->flags & (SDHCI_AUTO_CMD23 | SDHCI_AUTO_CMD12)) + host->ier |= SDHCI_INT_AUTO_CMD_ERR; + else + host->ier &= ~SDHCI_INT_AUTO_CMD_ERR; + sdhci_writel(host, host->ier, SDHCI_INT_ENABLE); sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE); } @@ -1002,8 +1007,7 @@ static bool sdhci_needs_reset(struct sdhci_host *host, struct mmc_request *mrq) return (!(host->flags & SDHCI_DEVICE_DEAD) && ((mrq->cmd && mrq->cmd->error) || (mrq->sbc && mrq->sbc->error) || - (mrq->data && ((mrq->data->error && !mrq->data->stop) || - (mrq->data->stop && mrq->data->stop->error))) || + (mrq->data && mrq->data->stop && mrq->data->stop->error) || (host->quirks & SDHCI_QUIRK_RESET_AFTER_REQUEST))); }

@@ -1055,6 +1059,16 @@ static void sdhci_finish_data(struct sdhci_host *host) host->data = NULL; host->data_cmd = NULL;

+ /* + * The controller needs a reset of internal state machines upon error + * conditions. + */ + if (data->error) { + if (!host->cmd || host->cmd == data_cmd) + sdhci_do_reset(host, SDHCI_RESET_CMD); + sdhci_do_reset(host, SDHCI_RESET_DATA); + } + if ((host->flags & (SDHCI_REQ_USE_DMA | SDHCI_USE_ADMA)) == (SDHCI_REQ_USE_DMA | SDHCI_USE_ADMA)) sdhci_adma_table_post(host, data); @@ -1079,17 +1093,6 @@ static void sdhci_finish_data(struct sdhci_host *host) if (data->stop && (data->error || !data->mrq->sbc)) { - - /* - * The controller needs a reset of internal state machines - * upon error conditions. - */ - if (data->error) { - if (!host->cmd || host->cmd == data_cmd) - sdhci_do_reset(host, SDHCI_RESET_CMD); - sdhci_do_reset(host, SDHCI_RESET_DATA); - } - /* * 'cap_cmd_during_tfr' request must not use the command line * after mmc_command_done() has been called. It is upper layer's @@ -2560,8 +2563,23 @@ static void sdhci_timeout_data_timer(unsigned long data) * * *****************************************************************************/

-static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask) +static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask, u32 *intmask_p) { + /* Handle auto-CMD12 error */ + if (intmask & SDHCI_INT_AUTO_CMD_ERR && host->data_cmd) { + struct mmc_request *mrq = host->data_cmd->mrq; + u16 auto_cmd_status = sdhci_readw(host, SDHCI_AUTO_CMD_STATUS); + int data_err_bit = (auto_cmd_status & SDHCI_AUTO_CMD_TIMEOUT) ? + SDHCI_INT_DATA_TIMEOUT : + SDHCI_INT_DATA_CRC; + + /* Treat auto-CMD12 error the same as data error */ + if (!mrq->sbc && (host->flags & SDHCI_AUTO_CMD12)) { + *intmask_p |= data_err_bit; + return; + } + } + if (!host->cmd) { /* * SDHCI recovers from errors by resetting the cmd and data @@ -2583,20 +2601,12 @@ static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask) else host->cmd->error = -EILSEQ;

- /* - * If this command initiates a data phase and a response - * CRC error is signalled, the card can start transferring - * data - the card may have received the command without - * error. We must not terminate the mmc_request early. - * - * If the card did not receive the command or returned an - * error which prevented it sending data, the data phase - * will time out. - */ + /* Treat data command CRC error the same as data CRC error */ if (host->cmd->data && (intmask & (SDHCI_INT_CRC | SDHCI_INT_TIMEOUT)) == SDHCI_INT_CRC) { host->cmd = NULL; + *intmask_p |= SDHCI_INT_DATA_CRC; return; }

@@ -2604,6 +2614,21 @@ static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask) return; }

+ /* Handle auto-CMD23 error */ + if (intmask & SDHCI_INT_AUTO_CMD_ERR) { + struct mmc_request *mrq = host->cmd->mrq; + u16 auto_cmd_status = sdhci_readw(host, SDHCI_AUTO_CMD_STATUS); + int err = (auto_cmd_status & SDHCI_AUTO_CMD_TIMEOUT) ? + -ETIMEDOUT : + -EILSEQ; + + if (mrq->sbc && (host->flags & SDHCI_AUTO_CMD23)) { + mrq->sbc->error = err; + sdhci_finish_mrq(host, mrq); + return; + } + } + if (intmask & SDHCI_INT_RESPONSE) sdhci_finish_command(host); } @@ -2824,7 +2849,7 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id) }

if (intmask & SDHCI_INT_CMD_MASK) - sdhci_cmd_irq(host, intmask & SDHCI_INT_CMD_MASK); + sdhci_cmd_irq(host, intmask & SDHCI_INT_CMD_MASK, &intmask);

if (intmask & SDHCI_INT_DATA_MASK) sdhci_data_irq(host, intmask & SDHCI_INT_DATA_MASK); diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h index 1d7d61e25dbf..c0d5458c36d4 100644 --- a/drivers/mmc/host/sdhci.h +++ b/drivers/mmc/host/sdhci.h @@ -144,14 +144,15 @@ #define SDHCI_INT_DATA_CRC 0x00200000 #define SDHCI_INT_DATA_END_BIT 0x00400000 #define SDHCI_INT_BUS_POWER 0x00800000 -#define SDHCI_INT_ACMD12ERR 0x01000000 +#define SDHCI_INT_AUTO_CMD_ERR 0x01000000 #define SDHCI_INT_ADMA_ERROR 0x02000000

#define SDHCI_INT_NORMAL_MASK 0x00007FFF #define SDHCI_INT_ERROR_MASK 0xFFFF8000

#define SDHCI_INT_CMD_MASK (SDHCI_INT_RESPONSE | SDHCI_INT_TIMEOUT | \ - SDHCI_INT_CRC | SDHCI_INT_END_BIT | SDHCI_INT_INDEX) + SDHCI_INT_CRC | SDHCI_INT_END_BIT | SDHCI_INT_INDEX | \ + SDHCI_INT_AUTO_CMD_ERR) #define SDHCI_INT_DATA_MASK (SDHCI_INT_DATA_END | SDHCI_INT_DMA_END | \ SDHCI_INT_DATA_AVAIL | SDHCI_INT_SPACE_AVAIL | \ SDHCI_INT_DATA_TIMEOUT | SDHCI_INT_DATA_CRC | \ @@ -166,7 +167,11 @@

#define SDHCI_CQE_INT_MASK (SDHCI_CQE_INT_ERR_MASK | SDHCI_INT_CQE)

-#define SDHCI_ACMD12_ERR 0x3C +#define SDHCI_AUTO_CMD_STATUS 0x3C +#define SDHCI_AUTO_CMD_TIMEOUT 0x00000002 +#define SDHCI_AUTO_CMD_CRC 0x00000004 +#define SDHCI_AUTO_CMD_END_BIT 0x00000008 +#define SDHCI_AUTO_CMD_INDEX 0x00000010

#define SDHCI_HOST_CONTROL2 0x3E #define SDHCI_CTRL_UHS_MASK 0x0007 diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 99e60bb5fe07..1edd4ff5382c 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3169,8 +3169,12 @@ static int bond_netdev_event(struct notifier_block *this, return NOTIFY_DONE;

if (event_dev->flags & IFF_MASTER) { + int ret; + netdev_dbg(event_dev, "IFF_MASTER\n"); - return bond_master_netdev_event(event, event_dev); + ret = bond_master_netdev_event(event, event_dev); + if (ret != NOTIFY_DONE) + return ret; }

if (event_dev->flags & IFF_SLAVE) { diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 59b62b49ad48..98734a37b6f6 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -29,6 +29,13 @@ #define DRV_NAME "thunder-nicvf" #define DRV_VERSION "1.0"

+/* NOTE: Packets bigger than 1530 are split across multiple pages and XDP needs + * the buffer to be contiguous. Allow XDP to be set up only if we don't exceed + * this value, keeping headroom for the 14 byte Ethernet header and two + * VLAN tags (for QinQ) + */ +#define MAX_XDP_MTU (1530 - ETH_HLEN - VLAN_HLEN * 2) + /* Supported devices */ static const struct pci_device_id nicvf_id_table[] = { { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, @@ -1454,6 +1461,15 @@ static int nicvf_change_mtu(struct net_device *netdev, int new_mtu) struct nicvf *nic = netdev_priv(netdev); int orig_mtu = netdev->mtu;

+ /* For now just support only the usual MTU sized frames, + * plus some headroom for VLAN, QinQ. + */ + if (nic->xdp_prog && new_mtu > MAX_XDP_MTU) { + netdev_warn(netdev, "Jumbo frames not yet supported with XDP, current MTU %d.\n", + netdev->mtu); + return -EINVAL; + } + netdev->mtu = new_mtu;

if (!netif_running(netdev)) @@ -1702,8 +1718,10 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog) bool bpf_attached = false; int ret = 0;

- /* For now just support only the usual MTU sized frames */ - if (prog && (dev->mtu > 1500)) { + /* For now just support only the usual MTU sized frames, + * plus some headroom for VLAN, QinQ. + */ + if (prog && dev->mtu > MAX_XDP_MTU) { netdev_warn(dev, "Jumbo frames not yet supported with XDP, current MTU %d.\n", dev->mtu); return -EOPNOTSUPP; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index bb96153f496e..fea141e71705 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1245,6 +1245,23 @@ static int team_port_add(struct team *team, struct net_device *port_dev) goto err_option_port_add; }

+ /* set promiscuity level to new slave */ + if (dev->flags & IFF_PROMISC) { + err = dev_set_promiscuity(port_dev, 1); + if (err) + goto err_set_slave_promisc; + } + + /* set allmulti level to new slave */ + if (dev->flags & IFF_ALLMULTI) { + err = dev_set_allmulti(port_dev, 1); + if (err) { + if (dev->flags & IFF_PROMISC) + dev_set_promiscuity(port_dev, -1); + goto err_set_slave_promisc; + } + } + netif_addr_lock_bh(dev); dev_uc_sync_multiple(port_dev, dev); dev_mc_sync_multiple(port_dev, dev); @@ -1261,6 +1278,9 @@ static int team_port_add(struct team *team, struct net_device *port_dev)

return 0;

+err_set_slave_promisc: + __team_option_inst_del_port(team, port); + err_option_port_add: team_upper_dev_unlink(team, port);

@@ -1306,6 +1326,12 @@ static int team_port_del(struct team *team, struct net_device *port_dev)

team_port_disable(team, port); list_del_rcu(&port->list); + + if (dev->flags & IFF_PROMISC) + dev_set_promiscuity(port_dev, -1); + if (dev->flags & IFF_ALLMULTI) + dev_set_allmulti(port_dev, -1); + team_upper_dev_unlink(team, port); netdev_rx_handler_unregister(port_dev); team_port_disable_netpoll(port); diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00.h b/drivers/net/wireless/ralink/rt2x00/rt2x00.h index 1f38c338ca7a..2a25996d058d 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00.h +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00.h @@ -672,7 +672,6 @@ enum rt2x00_state_flags { CONFIG_CHANNEL_HT40, CONFIG_POWERSAVING, CONFIG_HT_DISABLED, - CONFIG_QOS_DISABLED, CONFIG_MONITORING,

/* diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c index 6fe0c6abe0d6..84728c281f46 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c @@ -670,18 +670,8 @@ void rt2x00mac_bss_info_changed(struct ieee80211_hw *hw, rt2x00dev->intf_associated--;

rt2x00leds_led_assoc(rt2x00dev, !!rt2x00dev->intf_associated); - - clear_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags); }

- /* - * Check for access point which do not support 802.11e . We have to - * generate data frames sequence number in S/W for such AP, because - * of H/W bug. - */ - if (changes & BSS_CHANGED_QOS && !bss_conf->qos) - set_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags); - /* * When the erp information has changed, we should perform * additional configuration steps. For all other changes we are done. diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c index e1660b92b20c..1b0f2da8a10d 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c @@ -200,15 +200,18 @@ static void rt2x00queue_create_tx_descriptor_seq(struct rt2x00_dev *rt2x00dev, if (!rt2x00_has_cap_flag(rt2x00dev, REQUIRE_SW_SEQNO)) { /* * rt2800 has a H/W (or F/W) bug, device incorrectly increase - * seqno on retransmited data (non-QOS) frames. To workaround - * the problem let's generate seqno in software if QOS is - * disabled. + * seqno on retransmitted data (non-QOS) and management frames. + * To workaround the problem let's generate seqno in software. + * Except for beacons which are transmitted periodically by H/W + * hence hardware has to assign seqno for them. */ - if (test_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags)) - __clear_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags); - else + if (ieee80211_is_beacon(hdr->frame_control)) { + __set_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags); /* H/W will generate sequence number */ return; + } + + __clear_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags); }

/* diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c index 89b1f1af2fd4..31d31aad3de1 100644 --- a/drivers/scsi/libfc/fc_rport.c +++ b/drivers/scsi/libfc/fc_rport.c @@ -2164,7 +2164,6 @@ static void fc_rport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp) FC_RPORT_DBG(rdata, "Received LOGO request while in state %s\n", fc_rport_state(rdata));

- rdata->flags &= ~FC_RP_STARTED; fc_rport_enter_delete(rdata, RPORT_EV_STOP); mutex_unlock(&rdata->rp_mutex); kref_put(&rdata->kref, fc_rport_destroy); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 37d366696d21..c89f0e129f58 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -2050,8 +2050,12 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx, blk_mq_delay_run_hw_queue(hctx, SCSI_QUEUE_DELAY); break; default: + if (unlikely(!scsi_device_online(sdev))) + scsi_req(req)->result = DID_NO_CONNECT << 16; + else + scsi_req(req)->result = DID_ERROR << 16; /* - * Make sure to release all allocated ressources when + * Make sure to release all allocated resources when * we hit an error, as we will never see this command * again. */ diff --git a/drivers/staging/comedi/drivers/ni_usb6501.c b/drivers/staging/comedi/drivers/ni_usb6501.c index 9a0a96329a55..009c5277387b 100644 --- a/drivers/staging/comedi/drivers/ni_usb6501.c +++ b/drivers/staging/comedi/drivers/ni_usb6501.c @@ -472,10 +472,8 @@ static int ni6501_alloc_usb_buffers(struct comedi_device *dev)

size = usb_endpoint_maxp(devpriv->ep_tx); devpriv->usb_tx_buf = kzalloc(size, GFP_KERNEL); - if (!devpriv->usb_tx_buf) { - kfree(devpriv->usb_rx_buf); + if (!devpriv->usb_tx_buf) return -ENOMEM; - }

return 0; } @@ -527,6 +525,9 @@ static int ni6501_auto_attach(struct comedi_device *dev, if (!devpriv) return -ENOMEM;

+ mutex_init(&devpriv->mut); + usb_set_intfdata(intf, devpriv); + ret = ni6501_find_endpoints(dev); if (ret) return ret; @@ -535,9 +536,6 @@ static int ni6501_auto_attach(struct comedi_device *dev, if (ret) return ret;

- mutex_init(&devpriv->mut); - usb_set_intfdata(intf, devpriv); - ret = comedi_alloc_subdevices(dev, 2); if (ret) return ret; diff --git a/drivers/staging/comedi/drivers/vmk80xx.c b/drivers/staging/comedi/drivers/vmk80xx.c index a004aed0147a..1800eb3ae017 100644 --- a/drivers/staging/comedi/drivers/vmk80xx.c +++ b/drivers/staging/comedi/drivers/vmk80xx.c @@ -691,10 +691,8 @@ static int vmk80xx_alloc_usb_buffers(struct comedi_device *dev)

size = usb_endpoint_maxp(devpriv->ep_tx); devpriv->usb_tx_buf = kzalloc(size, GFP_KERNEL); - if (!devpriv->usb_tx_buf) { - kfree(devpriv->usb_rx_buf); + if (!devpriv->usb_tx_buf) return -ENOMEM; - }

return 0; } @@ -809,6 +807,8 @@ static int vmk80xx_auto_attach(struct comedi_device *dev,

devpriv->model = board->model;

+ sema_init(&devpriv->limit_sem, 8); + ret = vmk80xx_find_usb_endpoints(dev); if (ret) return ret; @@ -817,8 +817,6 @@ static int vmk80xx_auto_attach(struct comedi_device *dev, if (ret) return ret;

- sema_init(&devpriv->limit_sem, 8); - usb_set_intfdata(intf, devpriv);

if (devpriv->model == VMK8055_MODEL) diff --git a/drivers/staging/iio/adc/ad7192.c b/drivers/staging/iio/adc/ad7192.c index 31a195d1bf05..f58c80327ba5 100644 --- a/drivers/staging/iio/adc/ad7192.c +++ b/drivers/staging/iio/adc/ad7192.c @@ -109,10 +109,10 @@ #define AD7192_CH_AIN3 BIT(6) /* AIN3 - AINCOM */ #define AD7192_CH_AIN4 BIT(7) /* AIN4 - AINCOM */

-#define AD7193_CH_AIN1P_AIN2M 0x000 /* AIN1(+) - AIN2(-) */ -#define AD7193_CH_AIN3P_AIN4M 0x001 /* AIN3(+) - AIN4(-) */ -#define AD7193_CH_AIN5P_AIN6M 0x002 /* AIN5(+) - AIN6(-) */ -#define AD7193_CH_AIN7P_AIN8M 0x004 /* AIN7(+) - AIN8(-) */ +#define AD7193_CH_AIN1P_AIN2M 0x001 /* AIN1(+) - AIN2(-) */ +#define AD7193_CH_AIN3P_AIN4M 0x002 /* AIN3(+) - AIN4(-) */ +#define AD7193_CH_AIN5P_AIN6M 0x004 /* AIN5(+) - AIN6(-) */ +#define AD7193_CH_AIN7P_AIN8M 0x008 /* AIN7(+) - AIN8(-) */ #define AD7193_CH_TEMP 0x100 /* Temp senseor */ #define AD7193_CH_AIN2P_AIN2M 0x200 /* AIN2(+) - AIN2(-) */ #define AD7193_CH_AIN1 0x401 /* AIN1 - AINCOM */ diff --git a/drivers/staging/iio/meter/ade7854.c b/drivers/staging/iio/meter/ade7854.c index 70612da64a8b..7ae774ef9da3 100644 --- a/drivers/staging/iio/meter/ade7854.c +++ b/drivers/staging/iio/meter/ade7854.c @@ -269,7 +269,7 @@ static IIO_DEV_ATTR_VPEAK(0644, static IIO_DEV_ATTR_IPEAK(0644, ade7854_read_32bit, ade7854_write_32bit, - ADE7854_VPEAK); + ADE7854_IPEAK); static IIO_DEV_ATTR_APHCAL(0644, ade7854_read_16bit, ade7854_write_16bit, diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index d7c22ae5c368..0e93ac888a5f 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -918,8 +918,12 @@ static int vhost_new_umem_range(struct vhost_umem *umem, u64 start, u64 size, u64 end, u64 userspace_addr, int perm) { - struct vhost_umem_node *tmp, *node = kmalloc(sizeof(*node), GFP_ATOMIC); + struct vhost_umem_node *tmp, *node;

+ if (!size) + return -EFAULT; + + node = kmalloc(sizeof(*node), GFP_ATOMIC); if (!node) return -ENOMEM;

diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index f29cdb1cdeb7..7b7ab10a9db1 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1189,6 +1189,7 @@ cifsFileInfo_get_locked(struct cifsFileInfo *cifs_file) }

struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file); +void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_hdlr); void cifsFileInfo_put(struct cifsFileInfo *cifs_file);

#define CIFS_CACHE_READ_FLG 1 @@ -1693,6 +1694,7 @@ GLOBAL_EXTERN spinlock_t gidsidlock; #endif /* CONFIG_CIFS_ACL */

void cifs_oplock_break(struct work_struct *work); +void cifs_queue_oplock_break(struct cifsFileInfo *cfile);

extern const struct slow_work_ops cifs_oplock_break_ops; extern struct workqueue_struct *cifsiod_wq; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index cd69c1e9750f..48ea9dfd5f02 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -358,12 +358,30 @@ cifsFileInfo_get(struct cifsFileInfo *cifs_file) return cifs_file; }

-/* - * Release a reference on the file private data. This may involve closing - * the filehandle out on the server. Must be called without holding - * tcon->open_file_lock and cifs_file->file_info_lock. +/** + * cifsFileInfo_put - release a reference of file priv data + * + * Always potentially wait for oplock handler. See _cifsFileInfo_put(). */ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) +{ + _cifsFileInfo_put(cifs_file, true); +} + +/** + * _cifsFileInfo_put - release a reference of file priv data + * + * This may involve closing the filehandle @cifs_file out on the + * server. Must be called without holding tcon->open_file_lock and + * cifs_file->file_info_lock. + * + * If @wait_for_oplock_handler is true and we are releasing the last + * reference, wait for any running oplock break handler of the file + * and cancel any pending one. If calling this function from the + * oplock break handler, you need to pass false. + * + */ +void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) { struct inode *inode = d_inode(cifs_file->dentry); struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink); @@ -411,7 +429,8 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file)

spin_unlock(&tcon->open_file_lock);

- oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break); + oplock_break_cancelled = wait_oplock_handler ? + cancel_work_sync(&cifs_file->oplock_break) : false;

if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; @@ -4136,6 +4155,7 @@ void cifs_oplock_break(struct work_struct *work) cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } + _cifsFileInfo_put(cfile, false /* do not wait for ourself */); cifs_done_oplock_break(cinode); }

diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index bcab30d4a6c7..76f1649ab444 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -486,8 +486,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &pCifsInode->flags);

- queue_work(cifsoplockd_wq, - &netfile->oplock_break); + cifs_queue_oplock_break(netfile); netfile->oplock_break_cancelled = false;

spin_unlock(&tcon->open_file_lock); @@ -584,6 +583,28 @@ void cifs_put_writer(struct cifsInodeInfo *cinode) spin_unlock(&cinode->writers_lock); }

+/** + * cifs_queue_oplock_break - queue the oplock break handler for cfile + * + * This function is called from the demultiplex thread when it + * receives an oplock break for @cfile. + * + * Assumes the tcon->open_file_lock is held. + * Assumes cfile->file_info_lock is NOT held. + */ +void cifs_queue_oplock_break(struct cifsFileInfo *cfile) +{ + /* + * Bump the handle refcount now while we hold the + * open_file_lock to enforce the validity of it for the oplock + * break handler. The matching put is done at the end of the + * handler. + */ + cifsFileInfo_get(cfile); + + queue_work(cifsoplockd_wq, &cfile->oplock_break); +} + void cifs_done_oplock_break(struct cifsInodeInfo *cinode) { clear_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags); diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index a97a0e0b1a74..31f01f09d25a 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -517,7 +517,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags);

- queue_work(cifsoplockd_wq, &cfile->oplock_break); + cifs_queue_oplock_break(cfile); kfree(lw); return true; } @@ -661,8 +661,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags); spin_unlock(&cfile->file_info_lock); - queue_work(cifsoplockd_wq, - &cfile->oplock_break); + + cifs_queue_oplock_break(cfile);

spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/direct-io.c b/fs/direct-io.c index 2c90d541f527..30bf22c989de 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -219,6 +219,27 @@ static inline struct page *dio_get_page(struct dio *dio, return dio->pages[sdio->head]; }

+/* + * Warn about a page cache invalidation failure during a direct io write. + */ +void dio_warn_stale_pagecache(struct file *filp) +{ + static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST); + char pathname[128]; + struct inode *inode = file_inode(filp); + char *path; + + errseq_set(&inode->i_mapping->wb_err, -EIO); + if (__ratelimit(&_rs)) { + path = file_path(filp, pathname, sizeof(pathname)); + if (IS_ERR(path)) + path = "(unknown)"; + pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n"); + pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid, + current->comm); + } +} + /** * dio_complete() - called when all DIO BIO I/O has been completed * @offset: the byte offset in the file of the completed operation @@ -290,7 +311,8 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags) err = invalidate_inode_pages2_range(dio->inode->i_mapping, offset >> PAGE_SHIFT, (offset + ret - 1) >> PAGE_SHIFT); - WARN_ON_ONCE(err); + if (err) + dio_warn_stale_pagecache(dio->iocb->ki_filp); }

if (!(dio->flags & DIO_SKIP_DIO_COUNT)) diff --git a/fs/iomap.c b/fs/iomap.c index 8f7673a69273..467d98bf7054 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -753,7 +753,8 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio) err = invalidate_inode_pages2_range(inode->i_mapping, offset >> PAGE_SHIFT, (offset + dio->size - 1) >> PAGE_SHIFT); - WARN_ON_ONCE(err); + if (err) + dio_warn_stale_pagecache(iocb->ki_filp); }

inode_dio_end(file_inode(iocb->ki_filp)); @@ -1010,9 +1011,16 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (ret) goto out_free_dio;

+ /* + * Try to invalidate cache pages for the range we're direct + * writing. If this invalidation fails, tough, the write will + * still work, but racing two incompatible write paths is a + * pretty crazy thing to do, so we don't support it 100%. + */ ret = invalidate_inode_pages2_range(mapping, start >> PAGE_SHIFT, end >> PAGE_SHIFT); - WARN_ON_ONCE(ret); + if (ret) + dio_warn_stale_pagecache(iocb->ki_filp); ret = 0;

if (iov_iter_rw(iter) == WRITE && !dio->wait_for_completion && diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 5e63c459dc61..309d24118f9a 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1160,6 +1160,24 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, count = -EINTR; goto out_mm; } + /* + * Avoid to modify vma->vm_flags + * without locked ops while the + * coredump reads the vm_flags. + */ + if (!mmget_still_valid(mm)) { + /* + * Silently return "count" + * like if get_task_mm() + * failed. FIXME: should this + * function have returned + * -ESRCH if get_task_mm() + * failed like if + * get_proc_task() fails? + */ + up_write(&mm->mmap_sem); + goto out_mm; + } for (vma = mm->mmap; vma; vma = vma->vm_next) { vma->vm_flags &= ~VM_SOFTDIRTY; vma_set_page_prot(vma); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 5f10052d2671..7a908d683258 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -627,6 +627,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,

/* the various vma->vm_userfaultfd_ctx still points to it */ down_write(&mm->mmap_sem); + /* no task can run (and in turn coredump) yet */ + VM_WARN_ON(!mmget_still_valid(mm)); for (vma = mm->mmap; vma; vma = vma->vm_next) if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; @@ -867,6 +869,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file) * taking the mmap_sem for writing. */ down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto skip_mm; prev = NULL; for (vma = mm->mmap; vma; vma = vma->vm_next) { cond_resched(); @@ -889,6 +893,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) vma->vm_flags = new_flags; vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } +skip_mm: up_write(&mm->mmap_sem); mmput(mm); wakeup: @@ -1327,6 +1332,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, goto out;

down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; @@ -1514,6 +1521,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, goto out;

down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index ea66f04f46f7..e4265db08e4b 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -212,6 +212,7 @@ xfs_attr_set( int flags) { struct xfs_mount *mp = dp->i_mount; + struct xfs_buf *leaf_bp = NULL; struct xfs_da_args args; struct xfs_defer_ops dfops; struct xfs_trans_res tres; @@ -327,9 +328,16 @@ xfs_attr_set( * GROT: another possible req'mt for a double-split btree op. */ xfs_defer_init(args.dfops, args.firstblock); - error = xfs_attr_shortform_to_leaf(&args); + error = xfs_attr_shortform_to_leaf(&args, &leaf_bp); if (error) goto out_defer_cancel; + /* + * Prevent the leaf buffer from being unlocked so that a + * concurrent AIL push cannot grab the half-baked leaf + * buffer and run into problems with the write verifier. + */ + xfs_trans_bhold(args.trans, leaf_bp); + xfs_defer_bjoin(args.dfops, leaf_bp); xfs_defer_ijoin(args.dfops, dp); error = xfs_defer_finish(&args.trans, args.dfops); if (error) @@ -337,13 +345,14 @@ xfs_attr_set(

/* * Commit the leaf transformation. We'll need another (linked) - * transaction to add the new attribute to the leaf. + * transaction to add the new attribute to the leaf, which + * means that we have to hold & join the leaf buffer here too. */ - error = xfs_trans_roll_inode(&args.trans, dp); if (error) goto out; - + xfs_trans_bjoin(args.trans, leaf_bp); + leaf_bp = NULL; }

if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) @@ -374,8 +383,9 @@ xfs_attr_set(

out_defer_cancel: xfs_defer_cancel(&dfops); - args.trans = NULL; out: + if (leaf_bp) + xfs_trans_brelse(args.trans, leaf_bp); if (args.trans) xfs_trans_cancel(args.trans); xfs_iunlock(dp, XFS_ILOCK_EXCL); diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 40e53a4fc0a6..73a541755d5b 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -739,10 +739,13 @@ xfs_attr_shortform_getvalue(xfs_da_args_t *args) }

/* - * Convert from using the shortform to the leaf. + * Convert from using the shortform to the leaf. On success, return the + * buffer so that we can keep it locked until we're totally done with it. */ int -xfs_attr_shortform_to_leaf(xfs_da_args_t *args) +xfs_attr_shortform_to_leaf( + struct xfs_da_args *args, + struct xfs_buf **leaf_bp) { xfs_inode_t *dp; xfs_attr_shortform_t *sf; @@ -821,7 +824,7 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args) sfe = XFS_ATTR_SF_NEXTENTRY(sfe); } error = 0; - + *leaf_bp = bp; out: kmem_free(tmpbuffer); return error; diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h index f7dda0c237b0..894124efb421 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.h +++ b/fs/xfs/libxfs/xfs_attr_leaf.h @@ -48,7 +48,8 @@ void xfs_attr_shortform_create(struct xfs_da_args *args); void xfs_attr_shortform_add(struct xfs_da_args *args, int forkoff); int xfs_attr_shortform_lookup(struct xfs_da_args *args); int xfs_attr_shortform_getvalue(struct xfs_da_args *args); -int xfs_attr_shortform_to_leaf(struct xfs_da_args *args); +int xfs_attr_shortform_to_leaf(struct xfs_da_args *args, + struct xfs_buf **leaf_bp); int xfs_attr_shortform_remove(struct xfs_da_args *args); int xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp); int xfs_attr_shortform_bytesfit(struct xfs_inode *dp, int bytes); diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 072ebfe1d6ae..087fea02c389 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -249,6 +249,10 @@ xfs_defer_trans_roll( for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++) xfs_trans_log_inode(*tp, dop->dop_inodes[i], XFS_ILOG_CORE);

+ /* Hold the (previously bjoin'd) buffer locked across the roll. */ + for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++) + xfs_trans_dirty_buf(*tp, dop->dop_bufs[i]); + trace_xfs_defer_trans_roll((*tp)->t_mountp, dop);

/* Roll the transaction. */ @@ -264,6 +268,12 @@ xfs_defer_trans_roll( for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++) xfs_trans_ijoin(*tp, dop->dop_inodes[i], 0);

+ /* Rejoin the buffers and dirty them so the log moves forward. */ + for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++) { + xfs_trans_bjoin(*tp, dop->dop_bufs[i]); + xfs_trans_bhold(*tp, dop->dop_bufs[i]); + } + return error; }

@@ -295,6 +305,31 @@ xfs_defer_ijoin( } }

+ ASSERT(0); + return -EFSCORRUPTED; +} + +/* + * Add this buffer to the deferred op. Each joined buffer is relogged + * each time we roll the transaction. + */ +int +xfs_defer_bjoin( + struct xfs_defer_ops *dop, + struct xfs_buf *bp) +{ + int i; + + for (i = 0; i < XFS_DEFER_OPS_NR_BUFS; i++) { + if (dop->dop_bufs[i] == bp) + return 0; + else if (dop->dop_bufs[i] == NULL) { + dop->dop_bufs[i] = bp; + return 0; + } + } + + ASSERT(0); return -EFSCORRUPTED; }

@@ -493,9 +528,7 @@ xfs_defer_init( struct xfs_defer_ops *dop, xfs_fsblock_t *fbp) { - dop->dop_committed = false; - dop->dop_low = false; - memset(&dop->dop_inodes, 0, sizeof(dop->dop_inodes)); + memset(dop, 0, sizeof(struct xfs_defer_ops)); *fbp = NULLFSBLOCK; INIT_LIST_HEAD(&dop->dop_intake); INIT_LIST_HEAD(&dop->dop_pending); diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h index d4f046dd44bd..045beacdd37d 100644 --- a/fs/xfs/libxfs/xfs_defer.h +++ b/fs/xfs/libxfs/xfs_defer.h @@ -59,6 +59,7 @@ enum xfs_defer_ops_type { };

#define XFS_DEFER_OPS_NR_INODES 2 /* join up to two inodes */ +#define XFS_DEFER_OPS_NR_BUFS 2 /* join up to two buffers */

struct xfs_defer_ops { bool dop_committed; /* did any trans commit? */ @@ -66,8 +67,9 @@ struct xfs_defer_ops { struct list_head dop_intake; /* unlogged pending work */ struct list_head dop_pending; /* logged pending work */

- /* relog these inodes with each roll */ + /* relog these with each roll */ struct xfs_inode *dop_inodes[XFS_DEFER_OPS_NR_INODES]; + struct xfs_buf *dop_bufs[XFS_DEFER_OPS_NR_BUFS]; };

void xfs_defer_add(struct xfs_defer_ops *dop, enum xfs_defer_ops_type type, @@ -77,6 +79,7 @@ void xfs_defer_cancel(struct xfs_defer_ops *dop); void xfs_defer_init(struct xfs_defer_ops *dop, xfs_fsblock_t *fbp); bool xfs_defer_has_unfinished_work(struct xfs_defer_ops *dop); int xfs_defer_ijoin(struct xfs_defer_ops *dop, struct xfs_inode *ip); +int xfs_defer_bjoin(struct xfs_defer_ops *dop, struct xfs_buf *bp);

/* Description of a deferred type. */ struct xfs_defer_op_type { diff --git a/include/linux/fs.h b/include/linux/fs.h index f6a577edec67..dafac283b0ff 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2965,6 +2965,7 @@ enum { };

void dio_end_io(struct bio *bio); +void dio_warn_stale_pagecache(struct file *filp);

ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index bd2684700b74..520702b82134 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -198,6 +198,7 @@ struct kretprobe_instance { struct kretprobe *rp; kprobe_opcode_t *ret_addr; struct task_struct *task; + void *fp; char data[0]; };

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 3d49b91b674d..ef4ae0a545fe 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -57,6 +57,27 @@ static inline void mmdrop_async(struct mm_struct *mm) } }

+/* + * This has to be called after a get_task_mm()/mmget_not_zero() + * followed by taking the mmap_sem for writing before modifying the + * vmas or anything the coredump pretends not to change from under it. + * + * NOTE: find_extend_vma() called from GUP context is the only place + * that can modify the "mm" (notably the vm_start/end) under mmap_sem + * for reading and outside the context of the process, so it is also + * the only case that holds the mmap_sem for reading that must call + * this function. Generally if the mmap_sem is hold for reading + * there's no need of this check after get_task_mm()/mmget_not_zero(). + * + * This function can be obsoleted and the check can be removed, after + * the coredump code will hold the mmap_sem for writing before + * invoking the ->core_dump methods. + */ +static inline bool mmget_still_valid(struct mm_struct *mm) +{ + return likely(!mm->core_state); +} + /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 335cf7851f12..008f64823c41 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -77,8 +77,8 @@ struct inet_frag_queue { struct timer_list timer; spinlock_t lock; refcount_t refcnt; - struct sk_buff *fragments; /* Used in IPv6. */ - struct rb_root rb_fragments; /* Used in IPv4. */ + struct sk_buff *fragments; /* used in 6lopwpan IPv6. */ + struct rb_root rb_fragments; /* Used in IPv4/IPv6. */ struct sk_buff *fragments_tail; struct sk_buff *last_run_head; ktime_t stamp; @@ -153,4 +153,16 @@ static inline void add_frag_mem_limit(struct netns_frags *nf, long val)

extern const u8 ip_frag_ecn_table[16];

+/* Return values of inet_frag_queue_insert() */ +#define IPFRAG_OK 0 +#define IPFRAG_DUP 1 +#define IPFRAG_OVERLAP 2 +int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, + int offset, int end); +void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, + struct sk_buff *parent); +void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, + void *reasm_data); +struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q); + #endif diff --git a/include/net/ipv6.h b/include/net/ipv6.h index fa87a62e9bd3..6294d20a5f0e 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -512,35 +512,6 @@ static inline bool ipv6_prefix_equal(const struct in6_addr *addr1, } #endif

-struct inet_frag_queue; - -enum ip6_defrag_users { - IP6_DEFRAG_LOCAL_DELIVER, - IP6_DEFRAG_CONNTRACK_IN, - __IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX, - IP6_DEFRAG_CONNTRACK_OUT, - __IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX, - IP6_DEFRAG_CONNTRACK_BRIDGE_IN, - __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX, -}; - -void ip6_frag_init(struct inet_frag_queue *q, const void *a); -extern const struct rhashtable_params ip6_rhash_params; - -/* - * Equivalent of ipv4 struct ip - */ -struct frag_queue { - struct inet_frag_queue q; - - int iif; - unsigned int csum; - __u16 nhoffset; - u8 ecn; -}; - -void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq); - static inline bool ipv6_addr_any(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h new file mode 100644 index 000000000000..28aa9b30aece --- /dev/null +++ b/include/net/ipv6_frag.h @@ -0,0 +1,111 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _IPV6_FRAG_H +#define _IPV6_FRAG_H +#include <linux/kernel.h> +#include <net/addrconf.h> +#include <net/ipv6.h> +#include <net/inet_frag.h> + +enum ip6_defrag_users { + IP6_DEFRAG_LOCAL_DELIVER, + IP6_DEFRAG_CONNTRACK_IN, + __IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX, + IP6_DEFRAG_CONNTRACK_OUT, + __IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX, + IP6_DEFRAG_CONNTRACK_BRIDGE_IN, + __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX, +}; + +/* + * Equivalent of ipv4 struct ip + */ +struct frag_queue { + struct inet_frag_queue q; + + int iif; + __u16 nhoffset; + u8 ecn; +}; + +#if IS_ENABLED(CONFIG_IPV6) +static inline void ip6frag_init(struct inet_frag_queue *q, const void *a) +{ + struct frag_queue *fq = container_of(q, struct frag_queue, q); + const struct frag_v6_compare_key *key = a; + + q->key.v6 = *key; + fq->ecn = 0; +} + +static inline u32 ip6frag_key_hashfn(const void *data, u32 len, u32 seed) +{ + return jhash2(data, + sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); +} + +static inline u32 ip6frag_obj_hashfn(const void *data, u32 len, u32 seed) +{ + const struct inet_frag_queue *fq = data; + + return jhash2((const u32 *)&fq->key.v6, + sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); +} + +static inline int +ip6frag_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) +{ + const struct frag_v6_compare_key *key = arg->key; + const struct inet_frag_queue *fq = ptr; + + return !!memcmp(&fq->key, key, sizeof(*key)); +} + +static inline void +ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) +{ + struct net_device *dev = NULL; + struct sk_buff *head; + + rcu_read_lock(); + spin_lock(&fq->q.lock); + + if (fq->q.flags & INET_FRAG_COMPLETE) + goto out; + + inet_frag_kill(&fq->q); + + dev = dev_get_by_index_rcu(net, fq->iif); + if (!dev) + goto out; + + __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); + __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); + + /* Don't send error if the first segment did not arrive. */ + if (!(fq->q.flags & INET_FRAG_FIRST_IN)) + goto out; + + /* sk_buff::dev and sk_buff::rbnode are unionized. So we + * pull the head out of the tree in order to be able to + * deal with head->dev. + */ + head = inet_frag_pull_head(&fq->q); + if (!head) + goto out; + + head->dev = dev; + skb_get(head); + spin_unlock(&fq->q.lock); + + icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); + kfree_skb(head); + goto out_rcu_unlock; + +out: + spin_unlock(&fq->q.lock); +out_rcu_unlock: + rcu_read_unlock(); + inet_frag_put(&fq->q); +} +#endif +#endif diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 5cbad4fb9107..ec11bb986a8b 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -703,7 +703,6 @@ static void unoptimize_kprobe(struct kprobe *p, bool force) static int reuse_unused_kprobe(struct kprobe *ap) { struct optimized_kprobe *op; - int ret;

BUG_ON(!kprobe_unused(ap)); /* @@ -717,9 +716,8 @@ static int reuse_unused_kprobe(struct kprobe *ap) /* Enable the probe again */ ap->flags &= ~KPROBE_FLAG_DISABLED; /* Optimize it again (remove from op->list) */ - ret = kprobe_optready(ap); - if (ret) - return ret; + if (!kprobe_optready(ap)) + return -EINVAL;

optimize_kprobe(ap); return 0; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index e57be7031cb3..bf694c709b96 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3650,9 +3650,6 @@ __lock_set_class(struct lockdep_map *lock, const char *name, unsigned int depth; int i;

- if (unlikely(!debug_locks)) - return 0; - depth = curr->lockdep_depth; /* * This function is about (re)setting the class of a held lock, diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 9829ede00498..a5d163903835 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4672,12 +4672,15 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) return HRTIMER_NORESTART; }

+extern const u64 max_cfs_quota_period; + static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) { struct cfs_bandwidth *cfs_b = container_of(timer, struct cfs_bandwidth, period_timer); int overrun; int idle = 0; + int count = 0;

raw_spin_lock(&cfs_b->lock); for (;;) { @@ -4685,6 +4688,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) if (!overrun) break;

+ if (++count > 3) { + u64 new, old = ktime_to_ns(cfs_b->period); + + new = (old * 147) / 128; /* ~115% */ + new = min(new, max_cfs_quota_period); + + cfs_b->period = ns_to_ktime(new); + + /* since max is 1s, this is limited to 1e9^2, which fits in u64 */ + cfs_b->quota *= new; + cfs_b->quota = div64_u64(cfs_b->quota, old); + + pr_warn_ratelimited( + "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n", + smp_processor_id(), + div_u64(new, NSEC_PER_USEC), + div_u64(cfs_b->quota, NSEC_PER_USEC)); + + /* reset count so we don't come right back in here */ + count = 0; + } + idle = do_sched_cfs_period_timer(cfs_b, overrun); } if (idle) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 34a3b8a262a9..f13601a616ad 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -124,6 +124,7 @@ static int zero; static int __maybe_unused one = 1; static int __maybe_unused two = 2; static int __maybe_unused four = 4; +static unsigned long zero_ul; static unsigned long one_ul = 1; static unsigned long long_max = LONG_MAX; static int one_hundred = 100; @@ -1682,7 +1683,7 @@ static struct ctl_table fs_table[] = { .maxlen = sizeof(files_stat.max_files), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra1 = &zero, + .extra1 = &zero_ul, .extra2 = &long_max, }, { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 9937d7cf2a64..3e92852c8b23 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -33,6 +33,7 @@ #include <linux/list.h> #include <linux/hash.h> #include <linux/rcupdate.h> +#include <linux/kprobes.h>

#include <trace/events/sched.h>

@@ -6035,7 +6036,7 @@ void ftrace_reset_array_ops(struct trace_array *tr) tr->ops->func = ftrace_stub; }

-static inline void +static nokprobe_inline void __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ignored, struct pt_regs *regs) { @@ -6098,11 +6099,13 @@ static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, { __ftrace_ops_list_func(ip, parent_ip, NULL, regs); } +NOKPROBE_SYMBOL(ftrace_ops_list_func); #else static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip) { __ftrace_ops_list_func(ip, parent_ip, NULL, NULL); } +NOKPROBE_SYMBOL(ftrace_ops_no_ops); #endif

/* @@ -6132,6 +6135,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip, preempt_enable_notrace(); trace_clear_recursion(bit); } +NOKPROBE_SYMBOL(ftrace_ops_assist_func);

/** * ftrace_ops_get_func - get the function a trampoline should call diff --git a/mm/mmap.c b/mm/mmap.c index 00dab291e61d..59fd53b41c9c 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -45,6 +45,7 @@ #include <linux/moduleparam.h> #include <linux/pkeys.h> #include <linux/oom.h> +#include <linux/sched/mm.h>

#include <linux/uaccess.h> #include <asm/cacheflush.h> @@ -2448,7 +2449,8 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) vma = find_vma_prev(mm, addr, &prev); if (vma && (vma->vm_start <= addr)) return vma; - if (!prev || expand_stack(prev, addr)) + /* don't alter vm_end if the coredump is running */ + if (!prev || !mmget_still_valid(mm) || expand_stack(prev, addr)) return NULL; if (prev->vm_flags & VM_LOCKED) populate_vma_page_range(prev, addr, prev->vm_end, NULL); @@ -2474,6 +2476,9 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) return vma; if (!(vma->vm_flags & VM_GROWSDOWN)) return NULL; + /* don't alter vm_start if the coredump is running */ + if (!mmget_still_valid(mm)) + return NULL; start = vma->vm_start; if (expand_stack(vma, addr)) return NULL; diff --git a/mm/percpu.c b/mm/percpu.c index 3074148b7e0d..0c06e2f549a7 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2507,8 +2507,8 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, ai->groups[group].base_offset = areas[group] - base; }

- pr_info("Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n", - PFN_DOWN(size_sum), base, ai->static_size, ai->reserved_size, + pr_info("Embedded %zu pages/cpu s%zu r%zu d%zu u%zu\n", + PFN_DOWN(size_sum), ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size);

rc = pcpu_setup_first_chunk(ai, base); @@ -2629,8 +2629,8 @@ int __init pcpu_page_first_chunk(size_t reserved_size, }

/* we're ready, commit */ - pr_info("%d %s pages/cpu @%p s%zu r%zu d%zu\n", - unit_pages, psize_str, vm.addr, ai->static_size, + pr_info("%d %s pages/cpu s%zu r%zu d%zu\n", + unit_pages, psize_str, ai->static_size, ai->reserved_size, ai->dyn_size);

rc = pcpu_setup_first_chunk(ai, vm.addr); diff --git a/mm/vmstat.c b/mm/vmstat.c index 6389e876c7a7..28c45c26f901 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1201,13 +1201,8 @@ const char * const vmstat_text[] = { #endif #endif /* CONFIG_MEMORY_BALLOON */ #ifdef CONFIG_DEBUG_TLBFLUSH -#ifdef CONFIG_SMP "nr_tlb_remote_flush", "nr_tlb_remote_flush_received", -#else - "", /* nr_tlb_remote_flush */ - "", /* nr_tlb_remote_flush_received */ -#endif /* CONFIG_SMP */ "nr_tlb_local_flush_all", "nr_tlb_local_flush_one", #endif /* CONFIG_DEBUG_TLBFLUSH */ diff --git a/net/atm/lec.c b/net/atm/lec.c index 9f2365694ad4..85ce89c8a35c 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -710,7 +710,10 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg)

static int lec_mcast_attach(struct atm_vcc *vcc, int arg) { - if (arg < 0 || arg >= MAX_LEC_ITF || !dev_lec[arg]) + if (arg < 0 || arg >= MAX_LEC_ITF) + return -EINVAL; + arg = array_index_nospec(arg, MAX_LEC_ITF); + if (!dev_lec[arg]) return -EINVAL; vcc->proto_data = dev_lec[arg]; return lec_mcast_make(netdev_priv(dev_lec[arg]), vcc); @@ -728,6 +731,7 @@ static int lecd_attach(struct atm_vcc *vcc, int arg) i = arg; if (arg >= MAX_LEC_ITF) return -EINVAL; + i = array_index_nospec(arg, MAX_LEC_ITF); if (!dev_lec[i]) { int size;

diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 7637f58c1226..10fa84056cb5 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -236,13 +236,10 @@ static void __br_handle_local_finish(struct sk_buff *skb) /* note: already called with rcu_read_lock */ static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net_bridge_port *p = br_port_get_rcu(skb->dev); - __br_handle_local_finish(skb);

- BR_INPUT_SKB_CB(skb)->brdev = p->br->dev; - br_pass_frame_up(skb); - return 0; + /* return 1 to signal the okfn() was called so it's ok to use the skb */ + return 1; }

/* @@ -318,10 +315,18 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) goto forward; }

- /* Deliver packet to local host only */ - NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(skb->dev), - NULL, skb, skb->dev, NULL, br_handle_local_finish); - return RX_HANDLER_CONSUMED; + /* The else clause should be hit when nf_hook(): + * - returns < 0 (drop/error) + * - returns = 0 (stolen/nf_queue) + * Thus return 1 from the okfn() to signal the skb is ok to pass + */ + if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, + dev_net(skb->dev), NULL, skb, skb->dev, NULL, + br_handle_local_finish) == 1) { + return RX_HANDLER_PASS; + } else { + return RX_HANDLER_CONSUMED; + } }

forward: diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 8dc5c8d69bcd..e83048cb53ce 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -2119,7 +2119,8 @@ static void br_multicast_start_querier(struct net_bridge *br,

__br_multicast_open(br, query);

- list_for_each_entry(port, &br->port_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(port, &br->port_list, list) { if (port->state == BR_STATE_DISABLED || port->state == BR_STATE_BLOCKING) continue; @@ -2131,6 +2132,7 @@ static void br_multicast_start_querier(struct net_bridge *br, br_multicast_enable(&port->ip6_own_query); #endif } + rcu_read_unlock(); }

int br_multicast_toggle(struct net_bridge *br, unsigned long val) diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index 2cc224106b69..ec7a5da56129 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -25,7 +25,7 @@

#include <net/ieee802154_netdev.h> #include <net/6lowpan.h> -#include <net/ipv6.h> +#include <net/ipv6_frag.h> #include <net/inet_frag.h>

#include "6lowpan_i.h" diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index c9ec1603666b..665f11d7388e 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -120,6 +120,7 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) struct guehdr *guehdr; void *data; u16 doffset = 0; + u8 proto_ctype;

if (!fou) return 1; @@ -211,13 +212,14 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) if (unlikely(guehdr->control)) return gue_control_message(skb, guehdr);

+ proto_ctype = guehdr->proto_ctype; __skb_pull(skb, sizeof(struct udphdr) + hdrlen); skb_reset_transport_header(skb);

if (iptunnel_pull_offloads(skb)) goto drop;

- return -guehdr->proto_ctype; + return -proto_ctype;

drop: kfree_skb(skb); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 6ffee9d2b0e5..481cded81b2d 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -24,6 +24,62 @@ #include <net/sock.h> #include <net/inet_frag.h> #include <net/inet_ecn.h> +#include <net/ip.h> +#include <net/ipv6.h> + +/* Use skb->cb to track consecutive/adjacent fragments coming at + * the end of the queue. Nodes in the rb-tree queue will + * contain "runs" of one or more adjacent fragments. + * + * Invariants: + * - next_frag is NULL at the tail of a "run"; + * - the head of a "run" has the sum of all fragment lengths in frag_run_len. + */ +struct ipfrag_skb_cb { + union { + struct inet_skb_parm h4; + struct inet6_skb_parm h6; + }; + struct sk_buff *next_frag; + int frag_run_len; +}; + +#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) + +static void fragcb_clear(struct sk_buff *skb) +{ + RB_CLEAR_NODE(&skb->rbnode); + FRAG_CB(skb)->next_frag = NULL; + FRAG_CB(skb)->frag_run_len = skb->len; +} + +/* Append skb to the last "run". */ +static void fragrun_append_to_last(struct inet_frag_queue *q, + struct sk_buff *skb) +{ + fragcb_clear(skb); + + FRAG_CB(q->last_run_head)->frag_run_len += skb->len; + FRAG_CB(q->fragments_tail)->next_frag = skb; + q->fragments_tail = skb; +} + +/* Create a new "run" with the skb. */ +static void fragrun_create(struct inet_frag_queue *q, struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); + fragcb_clear(skb); + + if (q->last_run_head) + rb_link_node(&skb->rbnode, &q->last_run_head->rbnode, + &q->last_run_head->rbnode.rb_right); + else + rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node); + rb_insert_color(&skb->rbnode, &q->rb_fragments); + + q->fragments_tail = skb; + q->last_run_head = skb; +}

/* Given the OR values of all fragments, apply RFC 3168 5.3 requirements * Value : 0xff if frame should be dropped. @@ -122,6 +178,28 @@ static void inet_frag_destroy_rcu(struct rcu_head *head) kmem_cache_free(f->frags_cachep, q); }

+unsigned int inet_frag_rbtree_purge(struct rb_root *root) +{ + struct rb_node *p = rb_first(root); + unsigned int sum = 0; + + while (p) { + struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); + + p = rb_next(p); + rb_erase(&skb->rbnode, root); + while (skb) { + struct sk_buff *next = FRAG_CB(skb)->next_frag; + + sum += skb->truesize; + kfree_skb(skb); + skb = next; + } + } + return sum; +} +EXPORT_SYMBOL(inet_frag_rbtree_purge); + void inet_frag_destroy(struct inet_frag_queue *q) { struct sk_buff *fp; @@ -224,3 +302,218 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) return fq; } EXPORT_SYMBOL(inet_frag_find); + +int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, + int offset, int end) +{ + struct sk_buff *last = q->fragments_tail; + + /* RFC5722, Section 4, amended by Errata ID : 3089 + * When reassembling an IPv6 datagram, if + * one or more its constituent fragments is determined to be an + * overlapping fragment, the entire datagram (and any constituent + * fragments) MUST be silently discarded. + * + * Duplicates, however, should be ignored (i.e. skb dropped, but the + * queue/fragments kept for later reassembly). + */ + if (!last) + fragrun_create(q, skb); /* First fragment. */ + else if (last->ip_defrag_offset + last->len < end) { + /* This is the common case: skb goes to the end. */ + /* Detect and discard overlaps. */ + if (offset < last->ip_defrag_offset + last->len) + return IPFRAG_OVERLAP; + if (offset == last->ip_defrag_offset + last->len) + fragrun_append_to_last(q, skb); + else + fragrun_create(q, skb); + } else { + /* Binary search. Note that skb can become the first fragment, + * but not the last (covered above). + */ + struct rb_node **rbn, *parent; + + rbn = &q->rb_fragments.rb_node; + do { + struct sk_buff *curr; + int curr_run_end; + + parent = *rbn; + curr = rb_to_skb(parent); + curr_run_end = curr->ip_defrag_offset + + FRAG_CB(curr)->frag_run_len; + if (end <= curr->ip_defrag_offset) + rbn = &parent->rb_left; + else if (offset >= curr_run_end) + rbn = &parent->rb_right; + else if (offset >= curr->ip_defrag_offset && + end <= curr_run_end) + return IPFRAG_DUP; + else + return IPFRAG_OVERLAP; + } while (*rbn); + /* Here we have parent properly set, and rbn pointing to + * one of its NULL left/right children. Insert skb. + */ + fragcb_clear(skb); + rb_link_node(&skb->rbnode, parent, rbn); + rb_insert_color(&skb->rbnode, &q->rb_fragments); + } + + skb->ip_defrag_offset = offset; + + return IPFRAG_OK; +} +EXPORT_SYMBOL(inet_frag_queue_insert); + +void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, + struct sk_buff *parent) +{ + struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments); + struct sk_buff **nextp; + int delta; + + if (head != skb) { + fp = skb_clone(skb, GFP_ATOMIC); + if (!fp) + return NULL; + FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; + if (RB_EMPTY_NODE(&skb->rbnode)) + FRAG_CB(parent)->next_frag = fp; + else + rb_replace_node(&skb->rbnode, &fp->rbnode, + &q->rb_fragments); + if (q->fragments_tail == skb) + q->fragments_tail = fp; + skb_morph(skb, head); + FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; + rb_replace_node(&head->rbnode, &skb->rbnode, + &q->rb_fragments); + consume_skb(head); + head = skb; + } + WARN_ON(head->ip_defrag_offset != 0); + + delta = -head->truesize; + + /* Head of list must not be cloned. */ + if (skb_unclone(head, GFP_ATOMIC)) + return NULL; + + delta += head->truesize; + if (delta) + add_frag_mem_limit(q->net, delta); + + /* If the first fragment is fragmented itself, we split + * it to two chunks: the first with data and paged part + * and the second, holding only fragments. + */ + if (skb_has_frag_list(head)) { + struct sk_buff *clone; + int i, plen = 0; + + clone = alloc_skb(0, GFP_ATOMIC); + if (!clone) + return NULL; + skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; + skb_frag_list_init(head); + for (i = 0; i < skb_shinfo(head)->nr_frags; i++) + plen += skb_frag_size(&skb_shinfo(head)->frags[i]); + clone->data_len = head->data_len - plen; + clone->len = clone->data_len; + head->truesize += clone->truesize; + clone->csum = 0; + clone->ip_summed = head->ip_summed; + add_frag_mem_limit(q->net, clone->truesize); + skb_shinfo(head)->frag_list = clone; + nextp = &clone->next; + } else { + nextp = &skb_shinfo(head)->frag_list; + } + + return nextp; +} +EXPORT_SYMBOL(inet_frag_reasm_prepare); + +void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, + void *reasm_data) +{ + struct sk_buff **nextp = (struct sk_buff **)reasm_data; + struct rb_node *rbn; + struct sk_buff *fp; + + skb_push(head, head->data - skb_network_header(head)); + + /* Traverse the tree in order, to build frag_list. */ + fp = FRAG_CB(head)->next_frag; + rbn = rb_next(&head->rbnode); + rb_erase(&head->rbnode, &q->rb_fragments); + while (rbn || fp) { + /* fp points to the next sk_buff in the current run; + * rbn points to the next run. + */ + /* Go through the current run. */ + while (fp) { + *nextp = fp; + nextp = &fp->next; + fp->prev = NULL; + memset(&fp->rbnode, 0, sizeof(fp->rbnode)); + fp->sk = NULL; + head->data_len += fp->len; + head->len += fp->len; + if (head->ip_summed != fp->ip_summed) + head->ip_summed = CHECKSUM_NONE; + else if (head->ip_summed == CHECKSUM_COMPLETE) + head->csum = csum_add(head->csum, fp->csum); + head->truesize += fp->truesize; + fp = FRAG_CB(fp)->next_frag; + } + /* Move to the next run. */ + if (rbn) { + struct rb_node *rbnext = rb_next(rbn); + + fp = rb_to_skb(rbn); + rb_erase(rbn, &q->rb_fragments); + rbn = rbnext; + } + } + sub_frag_mem_limit(q->net, head->truesize); + + *nextp = NULL; + head->next = NULL; + head->prev = NULL; + head->tstamp = q->stamp; +} +EXPORT_SYMBOL(inet_frag_reasm_finish); + +struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q) +{ + struct sk_buff *head; + + if (q->fragments) { + head = q->fragments; + q->fragments = head->next; + } else { + struct sk_buff *skb; + + head = skb_rb_first(&q->rb_fragments); + if (!head) + return NULL; + skb = FRAG_CB(head)->next_frag; + if (skb) + rb_replace_node(&head->rbnode, &skb->rbnode, + &q->rb_fragments); + else + rb_erase(&head->rbnode, &q->rb_fragments); + memset(&head->rbnode, 0, sizeof(head->rbnode)); + barrier(); + } + if (head == q->fragments_tail) + q->fragments_tail = NULL; + + sub_frag_mem_limit(q->net, head->truesize); + + return head; +} +EXPORT_SYMBOL(inet_frag_pull_head); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index d95b32af4a0e..5a1d39e32196 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -57,57 +57,6 @@ */ static const char ip_frag_cache_name[] = "ip4-frags";

-/* Use skb->cb to track consecutive/adjacent fragments coming at - * the end of the queue. Nodes in the rb-tree queue will - * contain "runs" of one or more adjacent fragments. - * - * Invariants: - * - next_frag is NULL at the tail of a "run"; - * - the head of a "run" has the sum of all fragment lengths in frag_run_len. - */ -struct ipfrag_skb_cb { - struct inet_skb_parm h; - struct sk_buff *next_frag; - int frag_run_len; -}; - -#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) - -static void ip4_frag_init_run(struct sk_buff *skb) -{ - BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); - - FRAG_CB(skb)->next_frag = NULL; - FRAG_CB(skb)->frag_run_len = skb->len; -} - -/* Append skb to the last "run". */ -static void ip4_frag_append_to_last_run(struct inet_frag_queue *q, - struct sk_buff *skb) -{ - RB_CLEAR_NODE(&skb->rbnode); - FRAG_CB(skb)->next_frag = NULL; - - FRAG_CB(q->last_run_head)->frag_run_len += skb->len; - FRAG_CB(q->fragments_tail)->next_frag = skb; - q->fragments_tail = skb; -} - -/* Create a new "run" with the skb. */ -static void ip4_frag_create_run(struct inet_frag_queue *q, struct sk_buff *skb) -{ - if (q->last_run_head) - rb_link_node(&skb->rbnode, &q->last_run_head->rbnode, - &q->last_run_head->rbnode.rb_right); - else - rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node); - rb_insert_color(&skb->rbnode, &q->rb_fragments); - - ip4_frag_init_run(skb); - q->fragments_tail = skb; - q->last_run_head = skb; -} - /* Describe an entry in the "incomplete datagrams" queue. */ struct ipq { struct inet_frag_queue q; @@ -212,27 +161,9 @@ static void ip_expire(struct timer_list *t) * pull the head out of the tree in order to be able to * deal with head->dev. */ - if (qp->q.fragments) { - head = qp->q.fragments; - qp->q.fragments = head->next; - } else { - head = skb_rb_first(&qp->q.rb_fragments); - if (!head) - goto out; - if (FRAG_CB(head)->next_frag) - rb_replace_node(&head->rbnode, - &FRAG_CB(head)->next_frag->rbnode, - &qp->q.rb_fragments); - else - rb_erase(&head->rbnode, &qp->q.rb_fragments); - memset(&head->rbnode, 0, sizeof(head->rbnode)); - barrier(); - } - if (head == qp->q.fragments_tail) - qp->q.fragments_tail = NULL; - - sub_frag_mem_limit(qp->q.net, head->truesize); - + head = inet_frag_pull_head(&qp->q); + if (!head) + goto out; head->dev = dev_get_by_index_rcu(net, qp->iif); if (!head->dev) goto out; @@ -345,12 +276,10 @@ static int ip_frag_reinit(struct ipq *qp) static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) { struct net *net = container_of(qp->q.net, struct net, ipv4.frags); - struct rb_node **rbn, *parent; - struct sk_buff *skb1, *prev_tail; - int ihl, end, skb1_run_end; + int ihl, end, flags, offset; + struct sk_buff *prev_tail; struct net_device *dev; unsigned int fragsize; - int flags, offset; int err = -ENOENT; u8 ecn;

@@ -382,7 +311,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) */ if (end < qp->q.len || ((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len)) - goto err; + goto discard_qp; qp->q.flags |= INET_FRAG_LAST_IN; qp->q.len = end; } else { @@ -394,82 +323,33 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) if (end > qp->q.len) { /* Some bits beyond end -> corruption. */ if (qp->q.flags & INET_FRAG_LAST_IN) - goto err; + goto discard_qp; qp->q.len = end; } } if (end == offset) - goto err; + goto discard_qp;

err = -ENOMEM; if (!pskb_pull(skb, skb_network_offset(skb) + ihl)) - goto err; + goto discard_qp;

err = pskb_trim_rcsum(skb, end - offset); if (err) - goto err; + goto discard_qp;

/* Note : skb->rbnode and skb->dev share the same location. */ dev = skb->dev; /* Makes sure compiler wont do silly aliasing games */ barrier();

- /* RFC5722, Section 4, amended by Errata ID : 3089 - * When reassembling an IPv6 datagram, if - * one or more its constituent fragments is determined to be an - * overlapping fragment, the entire datagram (and any constituent - * fragments) MUST be silently discarded. - * - * We do the same here for IPv4 (and increment an snmp counter) but - * we do not want to drop the whole queue in response to a duplicate - * fragment. - */ - - err = -EINVAL; - /* Find out where to put this fragment. */ prev_tail = qp->q.fragments_tail; - if (!prev_tail) - ip4_frag_create_run(&qp->q, skb); /* First fragment. */ - else if (prev_tail->ip_defrag_offset + prev_tail->len < end) { - /* This is the common case: skb goes to the end. */ - /* Detect and discard overlaps. */ - if (offset < prev_tail->ip_defrag_offset + prev_tail->len) - goto discard_qp; - if (offset == prev_tail->ip_defrag_offset + prev_tail->len) - ip4_frag_append_to_last_run(&qp->q, skb); - else - ip4_frag_create_run(&qp->q, skb); - } else { - /* Binary search. Note that skb can become the first fragment, - * but not the last (covered above). - */ - rbn = &qp->q.rb_fragments.rb_node; - do { - parent = *rbn; - skb1 = rb_to_skb(parent); - skb1_run_end = skb1->ip_defrag_offset + - FRAG_CB(skb1)->frag_run_len; - if (end <= skb1->ip_defrag_offset) - rbn = &parent->rb_left; - else if (offset >= skb1_run_end) - rbn = &parent->rb_right; - else if (offset >= skb1->ip_defrag_offset && - end <= skb1_run_end) - goto err; /* No new data, potential duplicate */ - else - goto discard_qp; /* Found an overlap */ - } while (*rbn); - /* Here we have parent properly set, and rbn pointing to - * one of its NULL left/right children. Insert skb. - */ - ip4_frag_init_run(skb); - rb_link_node(&skb->rbnode, parent, rbn); - rb_insert_color(&skb->rbnode, &qp->q.rb_fragments); - } + err = inet_frag_queue_insert(&qp->q, skb, offset, end); + if (err) + goto insert_error;

if (dev) qp->iif = dev->ifindex; - skb->ip_defrag_offset = offset;

qp->q.stamp = skb->tstamp; qp->q.meat += skb->len; @@ -494,15 +374,24 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) skb->_skb_refdst = 0UL; err = ip_frag_reasm(qp, skb, prev_tail, dev); skb->_skb_refdst = orefdst; + if (err) + inet_frag_kill(&qp->q); return err; }

skb_dst_drop(skb); return -EINPROGRESS;

+insert_error: + if (err == IPFRAG_DUP) { + kfree_skb(skb); + return -EINVAL; + } + err = -EINVAL; + __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); discard_qp: inet_frag_kill(&qp->q); - __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); + __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); err: kfree_skb(skb); return err; @@ -514,13 +403,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, { struct net *net = container_of(qp->q.net, struct net, ipv4.frags); struct iphdr *iph; - struct sk_buff *fp, *head = skb_rb_first(&qp->q.rb_fragments); - struct sk_buff **nextp; /* To build frag_list. */ - struct rb_node *rbn; - int len; - int ihlen; - int delta; - int err; + void *reasm_data; + int len, err; u8 ecn;

ipq_kill(qp); @@ -530,117 +414,23 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, err = -EINVAL; goto out_fail; } - /* Make the one we just received the head. */ - if (head != skb) { - fp = skb_clone(skb, GFP_ATOMIC); - if (!fp) - goto out_nomem; - FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; - if (RB_EMPTY_NODE(&skb->rbnode)) - FRAG_CB(prev_tail)->next_frag = fp; - else - rb_replace_node(&skb->rbnode, &fp->rbnode, - &qp->q.rb_fragments); - if (qp->q.fragments_tail == skb) - qp->q.fragments_tail = fp; - skb_morph(skb, head); - FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; - rb_replace_node(&head->rbnode, &skb->rbnode, - &qp->q.rb_fragments); - consume_skb(head); - head = skb; - }

- WARN_ON(head->ip_defrag_offset != 0); - - /* Allocate a new buffer for the datagram. */ - ihlen = ip_hdrlen(head); - len = ihlen + qp->q.len; + /* Make the one we just received the head. */ + reasm_data = inet_frag_reasm_prepare(&qp->q, skb, prev_tail); + if (!reasm_data) + goto out_nomem;

+ len = ip_hdrlen(skb) + qp->q.len; err = -E2BIG; if (len > 65535) goto out_oversize;

- delta = - head->truesize; - - /* Head of list must not be cloned. */ - if (skb_unclone(head, GFP_ATOMIC)) - goto out_nomem; - - delta += head->truesize; - if (delta) - add_frag_mem_limit(qp->q.net, delta); - - /* If the first fragment is fragmented itself, we split - * it to two chunks: the first with data and paged part - * and the second, holding only fragments. */ - if (skb_has_frag_list(head)) { - struct sk_buff *clone; - int i, plen = 0; - - clone = alloc_skb(0, GFP_ATOMIC); - if (!clone) - goto out_nomem; - skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; - skb_frag_list_init(head); - for (i = 0; i < skb_shinfo(head)->nr_frags; i++) - plen += skb_frag_size(&skb_shinfo(head)->frags[i]); - clone->len = clone->data_len = head->data_len - plen; - head->truesize += clone->truesize; - clone->csum = 0; - clone->ip_summed = head->ip_summed; - add_frag_mem_limit(qp->q.net, clone->truesize); - skb_shinfo(head)->frag_list = clone; - nextp = &clone->next; - } else { - nextp = &skb_shinfo(head)->frag_list; - } + inet_frag_reasm_finish(&qp->q, skb, reasm_data);

- skb_push(head, head->data - skb_network_header(head)); + skb->dev = dev; + IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size);

- /* Traverse the tree in order, to build frag_list. */ - fp = FRAG_CB(head)->next_frag; - rbn = rb_next(&head->rbnode); - rb_erase(&head->rbnode, &qp->q.rb_fragments); - while (rbn || fp) { - /* fp points to the next sk_buff in the current run; - * rbn points to the next run. - */ - /* Go through the current run. */ - while (fp) { - *nextp = fp; - nextp = &fp->next; - fp->prev = NULL; - memset(&fp->rbnode, 0, sizeof(fp->rbnode)); - fp->sk = NULL; - head->data_len += fp->len; - head->len += fp->len; - if (head->ip_summed != fp->ip_summed) - head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_COMPLETE) - head->csum = csum_add(head->csum, fp->csum); - head->truesize += fp->truesize; - fp = FRAG_CB(fp)->next_frag; - } - /* Move to the next run. */ - if (rbn) { - struct rb_node *rbnext = rb_next(rbn); - - fp = rb_to_skb(rbn); - rb_erase(rbn, &qp->q.rb_fragments); - rbn = rbnext; - } - } - sub_frag_mem_limit(qp->q.net, head->truesize); - - *nextp = NULL; - head->next = NULL; - head->prev = NULL; - head->dev = dev; - head->tstamp = qp->q.stamp; - IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size); - - iph = ip_hdr(head); + iph = ip_hdr(skb); iph->tot_len = htons(len); iph->tos |= ecn;

@@ -653,7 +443,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, * from one very small df-fragment and one large non-df frag. */ if (qp->max_df_size == qp->q.max_size) { - IPCB(head)->flags |= IPSKB_FRAG_PMTU; + IPCB(skb)->flags |= IPSKB_FRAG_PMTU; iph->frag_off = htons(IP_DF); } else { iph->frag_off = 0; @@ -751,28 +541,6 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) } EXPORT_SYMBOL(ip_check_defrag);

-unsigned int inet_frag_rbtree_purge(struct rb_root *root) -{ - struct rb_node *p = rb_first(root); - unsigned int sum = 0; - - while (p) { - struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); - - p = rb_next(p); - rb_erase(&skb->rbnode, root); - while (skb) { - struct sk_buff *next = FRAG_CB(skb)->next_frag; - - sum += skb->truesize; - kfree_skb(skb); - skb = next; - } - } - return sum; -} -EXPORT_SYMBOL(inet_frag_rbtree_purge); - #ifdef CONFIG_SYSCTL static int dist_min;

diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a1bf87711bfa..c64f062d6323 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1194,9 +1194,23 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)

static void ipv4_link_failure(struct sk_buff *skb) { + struct ip_options opt; struct rtable *rt; + int res;

- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); + /* Recompile ip options since IPCB may not be valid anymore. + */ + memset(&opt, 0, sizeof(opt)); + opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); + + rcu_read_lock(); + res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); + rcu_read_unlock(); + + if (res) + return; + + __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt);

rt = skb_rtable(skb); if (rt) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c8227e07d574..657d33e2ff6a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -389,11 +389,12 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb) static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + int room; + + room = min_t(int, tp->window_clamp, tcp_space(sk)) - tp->rcv_ssthresh;

/* Check #1 */ - if (tp->rcv_ssthresh < tp->window_clamp && - (int)tp->rcv_ssthresh < tcp_space(sk) && - !tcp_under_memory_pressure(sk)) { + if (room > 0 && !tcp_under_memory_pressure(sk)) { int incr;

/* Check #2. Increase window, if skb with such overhead @@ -406,8 +407,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)

if (incr) { incr = max_t(int, incr, 2 * skb->len); - tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr, - tp->window_clamp); + tp->rcv_ssthresh += min(room, incr); inet_csk(sk)->icsk_ack.quick |= 1; } } diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 237fb04c6716..cb1b4772dac0 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -33,9 +33,8 @@

#include <net/sock.h> #include <net/snmp.h> -#include <net/inet_frag.h> +#include <net/ipv6_frag.h>

-#include <net/ipv6.h> #include <net/protocol.h> #include <net/transp_v6.h> #include <net/rawv6.h> @@ -52,14 +51,6 @@

static const char nf_frags_cache_name[] = "nf-frags";

-struct nf_ct_frag6_skb_cb -{ - struct inet6_skb_parm h; - int offset; -}; - -#define NFCT_FRAG6_CB(skb) ((struct nf_ct_frag6_skb_cb *)((skb)->cb)) - static struct inet_frags nf_frags;

#ifdef CONFIG_SYSCTL @@ -145,6 +136,9 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) } #endif

+static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *dev); + static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) { return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK); @@ -159,7 +153,7 @@ static void nf_ct_frag6_expire(struct timer_list *t) fq = container_of(frag, struct frag_queue, q); net = container_of(fq->q.net, struct net, nf_frag.frags);

- ip6_expire_frag_queue(net, fq); + ip6frag_expire_frag_queue(net, fq); }

/* Creation primitives. */ @@ -186,9 +180,10 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, const struct frag_hdr *fhdr, int nhoff) { - struct sk_buff *prev, *next; unsigned int payload_len; - int offset, end; + struct net_device *dev; + struct sk_buff *prev; + int offset, end, err; u8 ecn;

if (fq->q.flags & INET_FRAG_COMPLETE) { @@ -263,55 +258,19 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, goto err; }

- /* Find out which fragments are in front and at the back of us - * in the chain of fragments so far. We must know where to put - * this fragment, right? - */ + /* Note : skb->rbnode and skb->dev share the same location. */ + dev = skb->dev; + /* Makes sure compiler wont do silly aliasing games */ + barrier(); + prev = fq->q.fragments_tail; - if (!prev || NFCT_FRAG6_CB(prev)->offset < offset) { - next = NULL; - goto found; - } - prev = NULL; - for (next = fq->q.fragments; next != NULL; next = next->next) { - if (NFCT_FRAG6_CB(next)->offset >= offset) - break; /* bingo! */ - prev = next; - } + err = inet_frag_queue_insert(&fq->q, skb, offset, end); + if (err) + goto insert_error;

-found: - /* RFC5722, Section 4: - * When reassembling an IPv6 datagram, if - * one or more its constituent fragments is determined to be an - * overlapping fragment, the entire datagram (and any constituent - * fragments, including those not yet received) MUST be silently - * discarded. - */ + if (dev) + fq->iif = dev->ifindex;

- /* Check for overlap with preceding fragment. */ - if (prev && - (NFCT_FRAG6_CB(prev)->offset + prev->len) > offset) - goto discard_fq; - - /* Look for overlap with succeeding segment. */ - if (next && NFCT_FRAG6_CB(next)->offset < end) - goto discard_fq; - - NFCT_FRAG6_CB(skb)->offset = offset; - - /* Insert this fragment in the chain of fragments. */ - skb->next = next; - if (!next) - fq->q.fragments_tail = skb; - if (prev) - prev->next = skb; - else - fq->q.fragments = skb; - - if (skb->dev) { - fq->iif = skb->dev->ifindex; - skb->dev = NULL; - } fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; fq->ecn |= ecn; @@ -327,11 +286,25 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, fq->q.flags |= INET_FRAG_FIRST_IN; }

- return 0; + if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + fq->q.meat == fq->q.len) { + unsigned long orefdst = skb->_skb_refdst;

-discard_fq: + skb->_skb_refdst = 0UL; + err = nf_ct_frag6_reasm(fq, skb, prev, dev); + skb->_skb_refdst = orefdst; + return err; + } + + skb_dst_drop(skb); + return -EINPROGRESS; + +insert_error: + if (err == IPFRAG_DUP) + goto err; inet_frag_kill(&fq->q); err: + skb_dst_drop(skb); return -EINVAL; }

@@ -341,147 +314,67 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, * It is called with locked fq, and caller must check that * queue is eligible for reassembly i.e. it is not COMPLETE, * the last and the first frames arrived and all the bits are here. - * - * returns true if *prev skb has been transformed into the reassembled - * skb, false otherwise. */ -static bool -nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_device *dev) +static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *dev) { - struct sk_buff *fp, *head = fq->q.fragments; - int payload_len, delta; + void *reasm_data; + int payload_len; u8 ecn;

inet_frag_kill(&fq->q);

- WARN_ON(head == NULL); - WARN_ON(NFCT_FRAG6_CB(head)->offset != 0); - ecn = ip_frag_ecn_table[fq->ecn]; if (unlikely(ecn == 0xff)) - return false; + goto err;

- /* Unfragmented part is taken from the first segment. */ - payload_len = ((head->data - skb_network_header(head)) - + reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); + if (!reasm_data) + goto err; + + payload_len = ((skb->data - skb_network_header(skb)) - sizeof(struct ipv6hdr) + fq->q.len - sizeof(struct frag_hdr)); if (payload_len > IPV6_MAXPLEN) { net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n", payload_len); - return false; - } - - delta = - head->truesize; - - /* Head of list must not be cloned. */ - if (skb_unclone(head, GFP_ATOMIC)) - return false; - - delta += head->truesize; - if (delta) - add_frag_mem_limit(fq->q.net, delta); - - /* If the first fragment is fragmented itself, we split - * it to two chunks: the first with data and paged part - * and the second, holding only fragments. */ - if (skb_has_frag_list(head)) { - struct sk_buff *clone; - int i, plen = 0; - - clone = alloc_skb(0, GFP_ATOMIC); - if (clone == NULL) - return false; - - clone->next = head->next; - head->next = clone; - skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; - skb_frag_list_init(head); - for (i = 0; i < skb_shinfo(head)->nr_frags; i++) - plen += skb_frag_size(&skb_shinfo(head)->frags[i]); - clone->len = clone->data_len = head->data_len - plen; - head->data_len -= clone->len; - head->len -= clone->len; - clone->csum = 0; - clone->ip_summed = head->ip_summed; - - add_frag_mem_limit(fq->q.net, clone->truesize); - } - - /* morph head into last received skb: prev. - * - * This allows callers of ipv6 conntrack defrag to continue - * to use the last skb(frag) passed into the reasm engine. - * The last skb frag 'silently' turns into the full reassembled skb. - * - * Since prev is also part of q->fragments we have to clone it first. - */ - if (head != prev) { - struct sk_buff *iter; - - fp = skb_clone(prev, GFP_ATOMIC); - if (!fp) - return false; - - fp->next = prev->next; - - iter = head; - while (iter) { - if (iter->next == prev) { - iter->next = fp; - break; - } - iter = iter->next; - } - - skb_morph(prev, head); - prev->next = head->next; - consume_skb(head); - head = prev; + goto err; }

/* We have to remove fragment header from datagram and to relocate * header in order to calculate ICV correctly. */ - skb_network_header(head)[fq->nhoffset] = skb_transport_header(head)[0]; - memmove(head->head + sizeof(struct frag_hdr), head->head, - (head->data - head->head) - sizeof(struct frag_hdr)); - head->mac_header += sizeof(struct frag_hdr); - head->network_header += sizeof(struct frag_hdr); - - skb_shinfo(head)->frag_list = head->next; - skb_reset_transport_header(head); - skb_push(head, head->data - skb_network_header(head)); - - for (fp = head->next; fp; fp = fp->next) { - head->data_len += fp->len; - head->len += fp->len; - if (head->ip_summed != fp->ip_summed) - head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_COMPLETE) - head->csum = csum_add(head->csum, fp->csum); - head->truesize += fp->truesize; - fp->sk = NULL; - } - sub_frag_mem_limit(fq->q.net, head->truesize); + skb_network_header(skb)[fq->nhoffset] = skb_transport_header(skb)[0]; + memmove(skb->head + sizeof(struct frag_hdr), skb->head, + (skb->data - skb->head) - sizeof(struct frag_hdr)); + skb->mac_header += sizeof(struct frag_hdr); + skb->network_header += sizeof(struct frag_hdr); + + skb_reset_transport_header(skb);

- head->ignore_df = 1; - head->next = NULL; - head->dev = dev; - head->tstamp = fq->q.stamp; - ipv6_hdr(head)->payload_len = htons(payload_len); - ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn); - IP6CB(head)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size; + inet_frag_reasm_finish(&fq->q, skb, reasm_data); + + skb->ignore_df = 1; + skb->dev = dev; + ipv6_hdr(skb)->payload_len = htons(payload_len); + ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn); + IP6CB(skb)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size;

/* Yes, and fold redundant checksum back. 8) */ - if (head->ip_summed == CHECKSUM_COMPLETE) - head->csum = csum_partial(skb_network_header(head), - skb_network_header_len(head), - head->csum); + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_partial(skb_network_header(skb), + skb_network_header_len(skb), + skb->csum);

fq->q.fragments = NULL; fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; + fq->q.last_run_head = NULL; + + return 0;

- return true; +err: + inet_frag_kill(&fq->q); + return -EINVAL; }

/* @@ -550,7 +443,6 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) { u16 savethdr = skb->transport_header; - struct net_device *dev = skb->dev; int fhoff, nhoff, ret; struct frag_hdr *fhdr; struct frag_queue *fq; @@ -573,10 +465,6 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) hdr = ipv6_hdr(skb); fhdr = (struct frag_hdr *)skb_transport_header(skb);

- if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU && - fhdr->frag_off & htons(IP6_MF)) - return -EINVAL; - skb_orphan(skb); fq = fq_find(net, fhdr->identification, user, hdr, skb->dev ? skb->dev->ifindex : 0); @@ -588,24 +476,17 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) spin_lock_bh(&fq->q.lock);

ret = nf_ct_frag6_queue(fq, skb, fhdr, nhoff); - if (ret < 0) { - if (ret == -EPROTO) { - skb->transport_header = savethdr; - ret = 0; - } - goto out_unlock; + if (ret == -EPROTO) { + skb->transport_header = savethdr; + ret = 0; }

/* after queue has assumed skb ownership, only 0 or -EINPROGRESS * must be returned. */ - ret = -EINPROGRESS; - if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - fq->q.meat == fq->q.len && - nf_ct_frag6_reasm(fq, skb, dev)) - ret = 0; + if (ret) + ret = -EINPROGRESS;

-out_unlock: spin_unlock_bh(&fq->q.lock); inet_frag_put(&fq->q); return ret; @@ -641,16 +522,24 @@ static struct pernet_operations nf_ct_net_ops = { .exit = nf_ct_net_exit, };

+static const struct rhashtable_params nfct_rhash_params = { + .head_offset = offsetof(struct inet_frag_queue, node), + .hashfn = ip6frag_key_hashfn, + .obj_hashfn = ip6frag_obj_hashfn, + .obj_cmpfn = ip6frag_obj_cmpfn, + .automatic_shrinking = true, +}; + int nf_ct_frag6_init(void) { int ret = 0;

- nf_frags.constructor = ip6_frag_init; + nf_frags.constructor = ip6frag_init; nf_frags.destructor = NULL; nf_frags.qsize = sizeof(struct frag_queue); nf_frags.frag_expire = nf_ct_frag6_expire; nf_frags.frags_cache_name = nf_frags_cache_name; - nf_frags.rhash_params = ip6_rhash_params; + nf_frags.rhash_params = nfct_rhash_params; ret = inet_frags_init(&nf_frags); if (ret) goto out; diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index b326da59257f..123bfb13a5d1 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -14,8 +14,7 @@ #include <linux/skbuff.h> #include <linux/icmp.h> #include <linux/sysctl.h> -#include <net/ipv6.h> -#include <net/inet_frag.h> +#include <net/ipv6_frag.h>

#include <linux/netfilter_ipv6.h> #include <linux/netfilter_bridge.h> diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 2a8c680b67cd..fe797b29ca89 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -57,18 +57,11 @@ #include <net/rawv6.h> #include <net/ndisc.h> #include <net/addrconf.h> -#include <net/inet_frag.h> +#include <net/ipv6_frag.h> #include <net/inet_ecn.h>

static const char ip6_frag_cache_name[] = "ip6-frags";

-struct ip6frag_skb_cb { - struct inet6_skb_parm h; - int offset; -}; - -#define FRAG6_CB(skb) ((struct ip6frag_skb_cb *)((skb)->cb)) - static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) { return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK); @@ -76,63 +69,8 @@ static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)

static struct inet_frags ip6_frags;

-static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, - struct net_device *dev); - -void ip6_frag_init(struct inet_frag_queue *q, const void *a) -{ - struct frag_queue *fq = container_of(q, struct frag_queue, q); - const struct frag_v6_compare_key *key = a; - - q->key.v6 = *key; - fq->ecn = 0; -} -EXPORT_SYMBOL(ip6_frag_init); - -void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq) -{ - struct net_device *dev = NULL; - struct sk_buff *head; - - rcu_read_lock(); - spin_lock(&fq->q.lock); - - if (fq->q.flags & INET_FRAG_COMPLETE) - goto out; - - inet_frag_kill(&fq->q); - - dev = dev_get_by_index_rcu(net, fq->iif); - if (!dev) - goto out; - - __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); - __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); - - /* Don't send error if the first segment did not arrive. */ - head = fq->q.fragments; - if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head) - goto out; - - /* But use as source device on which LAST ARRIVED - * segment was received. And do not use fq->dev - * pointer directly, device might already disappeared. - */ - head->dev = dev; - skb_get(head); - spin_unlock(&fq->q.lock); - - icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); - kfree_skb(head); - goto out_rcu_unlock; - -out: - spin_unlock(&fq->q.lock); -out_rcu_unlock: - rcu_read_unlock(); - inet_frag_put(&fq->q); -} -EXPORT_SYMBOL(ip6_expire_frag_queue); +static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *dev);

static void ip6_frag_expire(struct timer_list *t) { @@ -143,7 +81,7 @@ static void ip6_frag_expire(struct timer_list *t) fq = container_of(frag, struct frag_queue, q); net = container_of(fq->q.net, struct net, ipv6.frags);

- ip6_expire_frag_queue(net, fq); + ip6frag_expire_frag_queue(net, fq); }

static struct frag_queue * @@ -170,27 +108,29 @@ fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif) }

static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, - struct frag_hdr *fhdr, int nhoff) + struct frag_hdr *fhdr, int nhoff, + u32 *prob_offset) { - struct sk_buff *prev, *next; - struct net_device *dev; - int offset, end, fragsize; struct net *net = dev_net(skb_dst(skb)->dev); + int offset, end, fragsize; + struct sk_buff *prev_tail; + struct net_device *dev; + int err = -ENOENT; u8 ecn;

if (fq->q.flags & INET_FRAG_COMPLETE) goto err;

+ err = -EINVAL; offset = ntohs(fhdr->frag_off) & ~0x7; end = offset + (ntohs(ipv6_hdr(skb)->payload_len) - ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));

if ((unsigned int)end > IPV6_MAXPLEN) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INHDRERRORS); - icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, - ((u8 *)&fhdr->frag_off - - skb_network_header(skb))); + *prob_offset = (u8 *)&fhdr->frag_off - skb_network_header(skb); + /* note that if prob_offset is set, the skb is freed elsewhere, + * we do not free it here. + */ return -1; }

@@ -210,7 +150,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, */ if (end < fq->q.len || ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) - goto err; + goto discard_fq; fq->q.flags |= INET_FRAG_LAST_IN; fq->q.len = end; } else { @@ -221,79 +161,42 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, /* RFC2460 says always send parameter problem in * this case. -DaveM */ - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INHDRERRORS); - icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, - offsetof(struct ipv6hdr, payload_len)); + *prob_offset = offsetof(struct ipv6hdr, payload_len); return -1; } if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ if (fq->q.flags & INET_FRAG_LAST_IN) - goto err; + goto discard_fq; fq->q.len = end; } }

if (end == offset) - goto err; + goto discard_fq;

+ err = -ENOMEM; /* Point into the IP datagram 'data' part. */ if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data)) - goto err; - - if (pskb_trim_rcsum(skb, end - offset)) - goto err; - - /* Find out which fragments are in front and at the back of us - * in the chain of fragments so far. We must know where to put - * this fragment, right? - */ - prev = fq->q.fragments_tail; - if (!prev || FRAG6_CB(prev)->offset < offset) { - next = NULL; - goto found; - } - prev = NULL; - for (next = fq->q.fragments; next != NULL; next = next->next) { - if (FRAG6_CB(next)->offset >= offset) - break; /* bingo! */ - prev = next; - } - -found: - /* RFC5722, Section 4, amended by Errata ID : 3089 - * When reassembling an IPv6 datagram, if - * one or more its constituent fragments is determined to be an - * overlapping fragment, the entire datagram (and any constituent - * fragments) MUST be silently discarded. - */ - - /* Check for overlap with preceding fragment. */ - if (prev && - (FRAG6_CB(prev)->offset + prev->len) > offset) goto discard_fq;

- /* Look for overlap with succeeding segment. */ - if (next && FRAG6_CB(next)->offset < end) + err = pskb_trim_rcsum(skb, end - offset); + if (err) goto discard_fq;

- FRAG6_CB(skb)->offset = offset; + /* Note : skb->rbnode and skb->dev share the same location. */ + dev = skb->dev; + /* Makes sure compiler wont do silly aliasing games */ + barrier();

- /* Insert this fragment in the chain of fragments. */ - skb->next = next; - if (!next) - fq->q.fragments_tail = skb; - if (prev) - prev->next = skb; - else - fq->q.fragments = skb; + prev_tail = fq->q.fragments_tail; + err = inet_frag_queue_insert(&fq->q, skb, offset, end); + if (err) + goto insert_error;

- dev = skb->dev; - if (dev) { + if (dev) fq->iif = dev->ifindex; - skb->dev = NULL; - } + fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; fq->ecn |= ecn; @@ -313,44 +216,48 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,

if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { - int res; unsigned long orefdst = skb->_skb_refdst;

skb->_skb_refdst = 0UL; - res = ip6_frag_reasm(fq, prev, dev); + err = ip6_frag_reasm(fq, skb, prev_tail, dev); skb->_skb_refdst = orefdst; - return res; + return err; }

skb_dst_drop(skb); - return -1; + return -EINPROGRESS;

+insert_error: + if (err == IPFRAG_DUP) { + kfree_skb(skb); + return -EINVAL; + } + err = -EINVAL; + __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_REASM_OVERLAPS); discard_fq: inet_frag_kill(&fq->q); -err: __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS); +err: kfree_skb(skb); - return -1; + return err; }

/* * Check if this packet is complete. - * Returns NULL on failure by any reason, and pointer - * to current nexthdr field in reassembled frame. * * It is called with locked fq, and caller must check that * queue is eligible for reassembly i.e. it is not COMPLETE, * the last and the first frames arrived and all the bits are here. */ -static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, - struct net_device *dev) +static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *dev) { struct net *net = container_of(fq->q.net, struct net, ipv6.frags); - struct sk_buff *fp, *head = fq->q.fragments; - int payload_len, delta; unsigned int nhoff; - int sum_truesize; + void *reasm_data; + int payload_len; u8 ecn;

inet_frag_kill(&fq->q); @@ -359,120 +266,40 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, if (unlikely(ecn == 0xff)) goto out_fail;

- /* Make the one we just received the head. */ - if (prev) { - head = prev->next; - fp = skb_clone(head, GFP_ATOMIC); - - if (!fp) - goto out_oom; - - fp->next = head->next; - if (!fp->next) - fq->q.fragments_tail = fp; - prev->next = fp; - - skb_morph(head, fq->q.fragments); - head->next = fq->q.fragments->next; - - consume_skb(fq->q.fragments); - fq->q.fragments = head; - } - - WARN_ON(head == NULL); - WARN_ON(FRAG6_CB(head)->offset != 0); + reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); + if (!reasm_data) + goto out_oom;

- /* Unfragmented part is taken from the first segment. */ - payload_len = ((head->data - skb_network_header(head)) - + payload_len = ((skb->data - skb_network_header(skb)) - sizeof(struct ipv6hdr) + fq->q.len - sizeof(struct frag_hdr)); if (payload_len > IPV6_MAXPLEN) goto out_oversize;

- delta = - head->truesize; - - /* Head of list must not be cloned. */ - if (skb_unclone(head, GFP_ATOMIC)) - goto out_oom; - - delta += head->truesize; - if (delta) - add_frag_mem_limit(fq->q.net, delta); - - /* If the first fragment is fragmented itself, we split - * it to two chunks: the first with data and paged part - * and the second, holding only fragments. */ - if (skb_has_frag_list(head)) { - struct sk_buff *clone; - int i, plen = 0; - - clone = alloc_skb(0, GFP_ATOMIC); - if (!clone) - goto out_oom; - clone->next = head->next; - head->next = clone; - skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; - skb_frag_list_init(head); - for (i = 0; i < skb_shinfo(head)->nr_frags; i++) - plen += skb_frag_size(&skb_shinfo(head)->frags[i]); - clone->len = clone->data_len = head->data_len - plen; - head->data_len -= clone->len; - head->len -= clone->len; - clone->csum = 0; - clone->ip_summed = head->ip_summed; - add_frag_mem_limit(fq->q.net, clone->truesize); - } - /* We have to remove fragment header from datagram and to relocate * header in order to calculate ICV correctly. */ nhoff = fq->nhoffset; - skb_network_header(head)[nhoff] = skb_transport_header(head)[0]; - memmove(head->head + sizeof(struct frag_hdr), head->head, - (head->data - head->head) - sizeof(struct frag_hdr)); - if (skb_mac_header_was_set(head)) - head->mac_header += sizeof(struct frag_hdr); - head->network_header += sizeof(struct frag_hdr); - - skb_reset_transport_header(head); - skb_push(head, head->data - skb_network_header(head)); - - sum_truesize = head->truesize; - for (fp = head->next; fp;) { - bool headstolen; - int delta; - struct sk_buff *next = fp->next; - - sum_truesize += fp->truesize; - if (head->ip_summed != fp->ip_summed) - head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_COMPLETE) - head->csum = csum_add(head->csum, fp->csum); - - if (skb_try_coalesce(head, fp, &headstolen, &delta)) { - kfree_skb_partial(fp, headstolen); - } else { - if (!skb_shinfo(head)->frag_list) - skb_shinfo(head)->frag_list = fp; - head->data_len += fp->len; - head->len += fp->len; - head->truesize += fp->truesize; - } - fp = next; - } - sub_frag_mem_limit(fq->q.net, sum_truesize); + skb_network_header(skb)[nhoff] = skb_transport_header(skb)[0]; + memmove(skb->head + sizeof(struct frag_hdr), skb->head, + (skb->data - skb->head) - sizeof(struct frag_hdr)); + if (skb_mac_header_was_set(skb)) + skb->mac_header += sizeof(struct frag_hdr); + skb->network_header += sizeof(struct frag_hdr); + + skb_reset_transport_header(skb); + + inet_frag_reasm_finish(&fq->q, skb, reasm_data);

- head->next = NULL; - head->dev = dev; - head->tstamp = fq->q.stamp; - ipv6_hdr(head)->payload_len = htons(payload_len); - ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn); - IP6CB(head)->nhoff = nhoff; - IP6CB(head)->flags |= IP6SKB_FRAGMENTED; - IP6CB(head)->frag_max_size = fq->q.max_size; + skb->dev = dev; + ipv6_hdr(skb)->payload_len = htons(payload_len); + ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn); + IP6CB(skb)->nhoff = nhoff; + IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; + IP6CB(skb)->frag_max_size = fq->q.max_size;

/* Yes, and fold redundant checksum back. 8) */ - skb_postpush_rcsum(head, skb_network_header(head), - skb_network_header_len(head)); + skb_postpush_rcsum(skb, skb_network_header(skb), + skb_network_header_len(skb));

rcu_read_lock(); __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS); @@ -480,6 +307,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, fq->q.fragments = NULL; fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; + fq->q.last_run_head = NULL; return 1;

out_oversize: @@ -491,6 +319,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, rcu_read_lock(); __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); rcu_read_unlock(); + inet_frag_kill(&fq->q); return -1; }

@@ -529,22 +358,26 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return 1; }

- if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU && - fhdr->frag_off & htons(IP6_MF)) - goto fail_hdr; - iif = skb->dev ? skb->dev->ifindex : 0; fq = fq_find(net, fhdr->identification, hdr, iif); if (fq) { + u32 prob_offset = 0; int ret;

spin_lock(&fq->q.lock);

fq->iif = iif; - ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff); + ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff, + &prob_offset);

spin_unlock(&fq->q.lock); inet_frag_put(&fq->q); + if (prob_offset) { + __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INHDRERRORS); + /* icmpv6_param_prob() calls kfree_skb(skb) */ + icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, prob_offset); + } return ret; }

@@ -712,42 +545,19 @@ static struct pernet_operations ip6_frags_ops = { .exit = ipv6_frags_exit_net, };

-static u32 ip6_key_hashfn(const void *data, u32 len, u32 seed) -{ - return jhash2(data, - sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); -} - -static u32 ip6_obj_hashfn(const void *data, u32 len, u32 seed) -{ - const struct inet_frag_queue *fq = data; - - return jhash2((const u32 *)&fq->key.v6, - sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); -} - -static int ip6_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) -{ - const struct frag_v6_compare_key *key = arg->key; - const struct inet_frag_queue *fq = ptr; - - return !!memcmp(&fq->key, key, sizeof(*key)); -} - -const struct rhashtable_params ip6_rhash_params = { +static const struct rhashtable_params ip6_rhash_params = { .head_offset = offsetof(struct inet_frag_queue, node), - .hashfn = ip6_key_hashfn, - .obj_hashfn = ip6_obj_hashfn, - .obj_cmpfn = ip6_obj_cmpfn, + .hashfn = ip6frag_key_hashfn, + .obj_hashfn = ip6frag_obj_hashfn, + .obj_cmpfn = ip6frag_obj_cmpfn, .automatic_shrinking = true, }; -EXPORT_SYMBOL(ip6_rhash_params);

int __init ipv6_frag_init(void) { int ret;

- ip6_frags.constructor = ip6_frag_init; + ip6_frags.constructor = ip6frag_init; ip6_frags.destructor = NULL; ip6_frags.qsize = sizeof(struct frag_queue); ip6_frags.frag_expire = ip6_frag_expire; diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 4d82fe7d627c..284276b3e0b4 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1164,6 +1164,9 @@ static inline void drv_wake_tx_queue(struct ieee80211_local *local, { struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->txq.vif);

+ if (local->in_reconfig) + return; + if (!check_sdata_in_driver(sdata)) return;

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 285f8797c26a..0171b27a2b81 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -23,6 +23,7 @@ #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> +#include <net/ipv6_frag.h>

#ifdef CONFIG_NF_NAT_NEEDED #include <linux/netfilter/nf_nat.h> diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 29d6699d5a06..55b4c0dc2b93 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -47,49 +47,9 @@ typedef struct { struct devtable { const char *device_id; /* name of table, __mod_<name>__*_device_table. */ unsigned long id_size; - void *function; + int (*do_entry)(const char *filename, void *symval, char *alias); };

-#define ___cat(a,b) a ## b -#define __cat(a,b) ___cat(a,b) - -/* we need some special handling for this host tool running eventually on - * Darwin. The Mach-O section handling is a bit different than ELF section - * handling. The differnces in detail are: - * a) we have segments which have sections - * b) we need a API call to get the respective section symbols */ -#if defined(__MACH__) -#include <mach-o/getsect.h> - -#define INIT_SECTION(name) do { \ - unsigned long name ## _len; \ - char *__cat(pstart_,name) = getsectdata("__TEXT", \ - #name, &__cat(name,_len)); \ - char *__cat(pstop_,name) = __cat(pstart_,name) + \ - __cat(name, _len); \ - __cat(__start_,name) = (void *)__cat(pstart_,name); \ - __cat(__stop_,name) = (void *)__cat(pstop_,name); \ - } while (0) -#define SECTION(name) __attribute__((section("__TEXT, " #name))) - -struct devtable **__start___devtable, **__stop___devtable; -#else -#define INIT_SECTION(name) /* no-op for ELF */ -#define SECTION(name) __attribute__((section(#name))) - -/* We construct a table of pointers in an ELF section (pointers generally - * go unpadded by gcc). ld creates boundary syms for us. */ -extern struct devtable *__start___devtable[], *__stop___devtable[]; -#endif /* __MACH__ */ - -#if !defined(__used) -# if __GNUC__ == 3 && __GNUC_MINOR__ < 3 -# define __used __attribute__((__unused__)) -# else -# define __used __attribute__((__used__)) -# endif -#endif - /* Define a variable f that holds the value of field f of struct devid * based at address m. */ @@ -102,16 +62,6 @@ extern struct devtable *__start___devtable[], *__stop___devtable[]; #define DEF_FIELD_ADDR(m, devid, f) \ typeof(((struct devid *)0)->f) *f = ((m) + OFF_##devid##_##f)

-/* Add a table entry. We test function type matches while we're here. */ -#define ADD_TO_DEVTABLE(device_id, type, function) \ - static struct devtable __cat(devtable,__LINE__) = { \ - device_id + 0*sizeof((function)((const char *)NULL, \ - (void *)NULL, \ - (char *)NULL)), \ - SIZE_##type, (function) }; \ - static struct devtable *SECTION(__devtable) __used \ - __cat(devtable_ptr,__LINE__) = &__cat(devtable,__LINE__) - #define ADD(str, sep, cond, field) \ do { \ strcat(str, sep); \ @@ -431,7 +381,6 @@ static int do_hid_entry(const char *filename,

return 1; } -ADD_TO_DEVTABLE("hid", hid_device_id, do_hid_entry);

/* Looks like: ieee1394:venNmoNspNverN */ static int do_ieee1394_entry(const char *filename, @@ -456,7 +405,6 @@ static int do_ieee1394_entry(const char *filename, add_wildcard(alias); return 1; } -ADD_TO_DEVTABLE("ieee1394", ieee1394_device_id, do_ieee1394_entry);

/* Looks like: pci:vNdNsvNsdNbcNscNiN. */ static int do_pci_entry(const char *filename, @@ -500,7 +448,6 @@ static int do_pci_entry(const char *filename, add_wildcard(alias); return 1; } -ADD_TO_DEVTABLE("pci", pci_device_id, do_pci_entry);

/* looks like: "ccw:tNmNdtNdmN" */ static int do_ccw_entry(const char *filename, @@ -524,7 +471,6 @@ static int do_ccw_entry(const char *filename, add_wildcard(alias); return 1; } -ADD_TO_DEVTABLE("ccw", ccw_device_id, do_ccw_entry);

/* looks like: "ap:tN" */ static int do_ap_entry(const char *filename, @@ -535,7 +481,6 @@ static int do_ap_entry(const char *filename, sprintf(alias, "ap:t%02X*", dev_type); return 1; } -ADD_TO_DEVTABLE("ap", ap_device_id, do_ap_entry);

/* looks like: "css:tN" */ static int do_css_entry(const char *filename, @@ -546,7 +491,6 @@ static int do_css_entry(const char *filename, sprintf(alias, "css:t%01X", type); return 1; } -ADD_TO_DEVTABLE("css", css_device_id, do_css_entry);

/* Looks like: "serio:tyNprNidNexN" */ static int do_serio_entry(const char *filename, @@ -566,7 +510,6 @@ static int do_serio_entry(const char *filename, add_wildcard(alias); return 1; } -ADD_TO_DEVTABLE("serio", serio_device_id, do_serio_entry);

/* looks like: "acpi:ACPI0003" or "acpi:PNP0C0B" or "acpi:LNXVIDEO" or * "acpi:bbsspp" (bb=base-class, ss=sub-class, pp=prog-if) @@ -604,7 +547,6 @@ static int do_acpi_entry(const char *filename, } return 1; } -ADD_TO_DEVTABLE("acpi", acpi_device_id, do_acpi_entry);

/* looks like: "pnp:dD" */ static void do_pnp_device_entry(void *symval, unsigned long size, @@ -725,7 +667,6 @@ static int do_pcmcia_entry(const char *filename, add_wildcard(alias); return 1; } -ADD_TO_DEVTABLE("pcmcia", pcmcia_device_id, do_pcmcia_entry);

static int do_vio_entry(const char *filename, void *symval, char *alias) @@ -745,7 +686,6 @@ static int do_vio_entry(const char *filename, void *symval, add_wildcard(alias); return 1; } -ADD_TO_DEVTABLE("vio", vio_device_id, do_vio_entry);

#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))

@@ -818,7 +758,6 @@ static int do_input_entry(const char *filename, void *symval, do_input(alias, *swbit, 0, INPUT_DEVICE_ID_SW_MAX); return 1; } -ADD_TO_DEVTABLE("input", input_device_id, do_input_entry);

static int do_eisa_entry(const char *filename, void *symval, char *alias) @@ -830,7 +769,6 @@ static int do_eisa_entry(const char *filename, void *symval, strcat(alias, "*"); return 1; } -ADD_TO_DEVTABLE("eisa", eisa_device_id, do_eisa_entry);

/* Looks like: parisc:tNhvNrevNsvN */ static int do_parisc_entry(const char *filename, void *symval, @@ -850,7 +788,6 @@ static int do_parisc_entry(const char *filename, void *symval, add_wildcard(alias); return 1; } -ADD_TO_DEVTABLE("parisc", parisc_device_id, do_parisc_entry);

/* Looks like: sdio:cNvNdN. */ static int do_sdio_entry(const char *filename, @@ -867,7 +804,6 @@ static int do_sdio_entry(const char *filename, add_wildcard(alias); return 1; } -ADD_TO_DEVTABLE("sdio", sdio_device_id, do_sdio_entry);

/* Looks like: ssb:vNidNrevN. */ static int do_ssb_entry(const char *filename, @@ -884,7 +820,6 @@ static int do_ssb_entry(const char *filename, add_wildcard(alias); return 1; } -ADD_TO_DEVTABLE("ssb", ssb_device_id, do_ssb_entry);

/* Looks like: bcma:mNidNrevNclN. */ static int do_bcma_entry(const char *filename, @@ -903,7 +838,6 @@ static int do_bcma_entry(const char *filename, add_wildcard(alias); return 1; } -ADD_TO_DEVTABLE("bcma", bcma_device_id, do_bcma_entry);

/* Looks like: virtio:dNvN */ static int do_virtio_entry(const char *filename, void *symval, @@ -919,7 +853,6 @@ static int do_virtio_entry(const char *filename, void *symval, add_wildcard(alias); return 1; } -ADD_TO_DEVTABLE("virtio", virtio_device_id, do_virtio_entry);

/* * Looks like: vmbus:guid @@ -942,7 +875,6 @@ static int do_vmbus_entry(const char *filename, void *symval,

return 1; } -ADD_TO_DEVTABLE("vmbus", hv_vmbus_device_id, do_vmbus_entry);

/* Looks like: i2c:S */ static int do_i2c_entry(const char *filename, void *symval, @@ -953,7 +885,6 @@ static int do_i2c_entry(const char *filename, void *symval,

return 1; } -ADD_TO_DEVTABLE("i2c", i2c_device_id, do_i2c_entry);

/* Looks like: spi:S */ static int do_spi_entry(const char *filename, void *symval, @@ -964,7 +895,6 @@ static int do_spi_entry(const char *filename, void *symval,

return 1; } -ADD_TO_DEVTABLE("spi", spi_device_id, do_spi_entry);

static const struct dmifield { const char *prefix; @@ -1019,7 +949,6 @@ static int do_dmi_entry(const char *filename, void *symval, strcat(alias, ":"); return 1; } -ADD_TO_DEVTABLE("dmi", dmi_system_id, do_dmi_entry);

static int do_platform_entry(const char *filename, void *symval, char *alias) @@ -1028,7 +957,6 @@ static int do_platform_entry(const char *filename, sprintf(alias, PLATFORM_MODULE_PREFIX "%s", *name); return 1; } -ADD_TO_DEVTABLE("platform", platform_device_id, do_platform_entry);

static int do_mdio_entry(const char *filename, void *symval, char *alias) @@ -1053,7 +981,6 @@ static int do_mdio_entry(const char *filename,

return 1; } -ADD_TO_DEVTABLE("mdio", mdio_device_id, do_mdio_entry);

/* Looks like: zorro:iN. */ static int do_zorro_entry(const char *filename, void *symval, @@ -1064,7 +991,6 @@ static int do_zorro_entry(const char *filename, void *symval, ADD(alias, "i", id != ZORRO_WILDCARD, id); return 1; } -ADD_TO_DEVTABLE("zorro", zorro_device_id, do_zorro_entry);

/* looks like: "pnp:dD" */ static int do_isapnp_entry(const char *filename, @@ -1080,7 +1006,6 @@ static int do_isapnp_entry(const char *filename, (function >> 12) & 0x0f, (function >> 8) & 0x0f); return 1; } -ADD_TO_DEVTABLE("isapnp", isapnp_device_id, do_isapnp_entry);

/* Looks like: "ipack:fNvNdN". */ static int do_ipack_entry(const char *filename, @@ -1096,7 +1021,6 @@ static int do_ipack_entry(const char *filename, add_wildcard(alias); return 1; } -ADD_TO_DEVTABLE("ipack", ipack_device_id, do_ipack_entry);

/* * Append a match expression for a single masked hex digit. @@ -1167,7 +1091,6 @@ static int do_amba_entry(const char *filename,

return 1; } -ADD_TO_DEVTABLE("amba", amba_id, do_amba_entry);

/* * looks like: "mipscdmm:tN" @@ -1183,7 +1106,6 @@ static int do_mips_cdmm_entry(const char *filename, sprintf(alias, "mipscdmm:t%02X*", type); return 1; } -ADD_TO_DEVTABLE("mipscdmm", mips_cdmm_device_id, do_mips_cdmm_entry);

/* LOOKS like cpu:type:x86,venVVVVfamFFFFmodMMMM:feature:*,FEAT,* * All fields are numbers. It would be nicer to use strings for vendor @@ -1208,7 +1130,6 @@ static int do_x86cpu_entry(const char *filename, void *symval, sprintf(alias + strlen(alias), "%04X*", feature); return 1; } -ADD_TO_DEVTABLE("x86cpu", x86_cpu_id, do_x86cpu_entry);

/* LOOKS like cpu:type:*:feature:*FEAT* */ static int do_cpu_entry(const char *filename, void *symval, char *alias) @@ -1218,7 +1139,6 @@ static int do_cpu_entry(const char *filename, void *symval, char *alias) sprintf(alias, "cpu:type:*:feature:*%04X*", feature); return 1; } -ADD_TO_DEVTABLE("cpu", cpu_feature, do_cpu_entry);

/* Looks like: mei:S:uuid:N:* */ static int do_mei_entry(const char *filename, void *symval, @@ -1237,7 +1157,6 @@ static int do_mei_entry(const char *filename, void *symval,

return 1; } -ADD_TO_DEVTABLE("mei", mei_cl_device_id, do_mei_entry);

/* Looks like: rapidio:vNdNavNadN */ static int do_rio_entry(const char *filename, @@ -1257,7 +1176,6 @@ static int do_rio_entry(const char *filename, add_wildcard(alias); return 1; } -ADD_TO_DEVTABLE("rapidio", rio_device_id, do_rio_entry);

/* Looks like: ulpi:vNpN */ static int do_ulpi_entry(const char *filename, void *symval, @@ -1270,7 +1188,6 @@ static int do_ulpi_entry(const char *filename, void *symval,

return 1; } -ADD_TO_DEVTABLE("ulpi", ulpi_device_id, do_ulpi_entry);

/* Looks like: hdaudio:vNrNaN */ static int do_hda_entry(const char *filename, void *symval, char *alias) @@ -1287,7 +1204,6 @@ static int do_hda_entry(const char *filename, void *symval, char *alias) add_wildcard(alias); return 1; } -ADD_TO_DEVTABLE("hdaudio", hda_device_id, do_hda_entry);

/* Looks like: fsl-mc:vNdN */ static int do_fsl_mc_entry(const char *filename, void *symval, @@ -1299,7 +1215,6 @@ static int do_fsl_mc_entry(const char *filename, void *symval, sprintf(alias, "fsl-mc:v%08Xd%s", vendor, *obj_type); return 1; } -ADD_TO_DEVTABLE("fslmc", fsl_mc_device_id, do_fsl_mc_entry);

/* Does namelen bytes of name exactly match the symbol? */ static bool sym_is(const char *name, unsigned namelen, const char *symbol) @@ -1313,12 +1228,11 @@ static bool sym_is(const char *name, unsigned namelen, const char *symbol) static void do_table(void *symval, unsigned long size, unsigned long id_size, const char *device_id, - void *function, + int (*do_entry)(const char *filename, void *symval, char *alias), struct module *mod) { unsigned int i; char alias[500]; - int (*do_entry)(const char *, void *entry, char *alias) = function;

device_id_check(mod->name, device_id, size, id_size, symval); /* Leave last one: it's the terminator. */ @@ -1332,6 +1246,44 @@ static void do_table(void *symval, unsigned long size, } }

+static const struct devtable devtable[] = { + {"hid", SIZE_hid_device_id, do_hid_entry}, + {"ieee1394", SIZE_ieee1394_device_id, do_ieee1394_entry}, + {"pci", SIZE_pci_device_id, do_pci_entry}, + {"ccw", SIZE_ccw_device_id, do_ccw_entry}, + {"ap", SIZE_ap_device_id, do_ap_entry}, + {"css", SIZE_css_device_id, do_css_entry}, + {"serio", SIZE_serio_device_id, do_serio_entry}, + {"acpi", SIZE_acpi_device_id, do_acpi_entry}, + {"pcmcia", SIZE_pcmcia_device_id, do_pcmcia_entry}, + {"vio", SIZE_vio_device_id, do_vio_entry}, + {"input", SIZE_input_device_id, do_input_entry}, + {"eisa", SIZE_eisa_device_id, do_eisa_entry}, + {"parisc", SIZE_parisc_device_id, do_parisc_entry}, + {"sdio", SIZE_sdio_device_id, do_sdio_entry}, + {"ssb", SIZE_ssb_device_id, do_ssb_entry}, + {"bcma", SIZE_bcma_device_id, do_bcma_entry}, + {"virtio", SIZE_virtio_device_id, do_virtio_entry}, + {"vmbus", SIZE_hv_vmbus_device_id, do_vmbus_entry}, + {"i2c", SIZE_i2c_device_id, do_i2c_entry}, + {"spi", SIZE_spi_device_id, do_spi_entry}, + {"dmi", SIZE_dmi_system_id, do_dmi_entry}, + {"platform", SIZE_platform_device_id, do_platform_entry}, + {"mdio", SIZE_mdio_device_id, do_mdio_entry}, + {"zorro", SIZE_zorro_device_id, do_zorro_entry}, + {"isapnp", SIZE_isapnp_device_id, do_isapnp_entry}, + {"ipack", SIZE_ipack_device_id, do_ipack_entry}, + {"amba", SIZE_amba_id, do_amba_entry}, + {"mipscdmm", SIZE_mips_cdmm_device_id, do_mips_cdmm_entry}, + {"x86cpu", SIZE_x86_cpu_id, do_x86cpu_entry}, + {"cpu", SIZE_cpu_feature, do_cpu_entry}, + {"mei", SIZE_mei_cl_device_id, do_mei_entry}, + {"rapidio", SIZE_rio_device_id, do_rio_entry}, + {"ulpi", SIZE_ulpi_device_id, do_ulpi_entry}, + {"hdaudio", SIZE_hda_device_id, do_hda_entry}, + {"fslmc", SIZE_fsl_mc_device_id, do_fsl_mc_entry}, +}; + /* Create MODULE_ALIAS() statements. * At this time, we cannot write the actual output C source yet, * so we write into the mod->dev_table_buf buffer. */ @@ -1386,13 +1338,14 @@ void handle_moddevtable(struct module *mod, struct elf_info *info, else if (sym_is(name, namelen, "pnp_card")) do_pnp_card_entries(symval, sym->st_size, mod); else { - struct devtable **p; - INIT_SECTION(__devtable); + int i; + + for (i = 0; i < ARRAY_SIZE(devtable); i++) { + const struct devtable *p = &devtable[i];

- for (p = __start___devtable; p < __stop___devtable; p++) { - if (sym_is(name, namelen, (*p)->device_id)) { - do_table(symval, sym->st_size, (*p)->id_size, - (*p)->device_id, (*p)->function, mod); + if (sym_is(name, namelen, p->device_id)) { + do_table(symval, sym->st_size, p->id_size, + p->device_id, p->do_entry, mod); break; } } diff --git a/security/device_cgroup.c b/security/device_cgroup.c index 5ef7e5240563..ea014df89428 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -569,7 +569,7 @@ static int propagate_exception(struct dev_cgroup *devcg_root, devcg->behavior == DEVCG_DEFAULT_ALLOW) { rc = dev_exception_add(devcg, ex); if (rc) - break; + return rc; } else { /* * in the other possible cases: diff --git a/sound/core/info.c b/sound/core/info.c index bcf6a48cc70d..5fb00437507b 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -722,8 +722,11 @@ snd_info_create_entry(const char *name, struct snd_info_entry *parent) INIT_LIST_HEAD(&entry->children); INIT_LIST_HEAD(&entry->list); entry->parent = parent; - if (parent) + if (parent) { + mutex_lock(&parent->access); list_add_tail(&entry->list, &parent->children); + mutex_unlock(&parent->access); + } return entry; }

@@ -805,7 +808,12 @@ void snd_info_free_entry(struct snd_info_entry * entry) list_for_each_entry_safe(p, n, &entry->children, list) snd_info_free_entry(p);

- list_del(&entry->list); + p = entry->parent; + if (p) { + mutex_lock(&p->access); + list_del(&entry->list); + mutex_unlock(&p->access); + } kfree(entry->name); if (entry->private_free) entry->private_free(entry); diff --git a/sound/core/init.c b/sound/core/init.c index 32ebe2f6bc59..dcb9199f5e4f 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -406,14 +406,7 @@ int snd_card_disconnect(struct snd_card *card) card->shutdown = 1; spin_unlock(&card->files_lock);

- /* phase 1: disable fops (user space) operations for ALSA API */ - mutex_lock(&snd_card_mutex); - snd_cards[card->number] = NULL; - clear_bit(card->number, snd_cards_lock); - mutex_unlock(&snd_card_mutex); - - /* phase 2: replace file->f_op with special dummy operations */ - + /* replace file->f_op with special dummy operations */ spin_lock(&card->files_lock); list_for_each_entry(mfile, &card->files_list, list) { /* it's critical part, use endless loop */ @@ -429,7 +422,7 @@ int snd_card_disconnect(struct snd_card *card) } spin_unlock(&card->files_lock);

- /* phase 3: notify all connected devices about disconnection */ + /* notify all connected devices about disconnection */ /* at this point, they cannot respond to any calls except release() */

#if IS_ENABLED(CONFIG_SND_MIXER_OSS) @@ -445,6 +438,13 @@ int snd_card_disconnect(struct snd_card *card) device_del(&card->card_dev); card->registered = false; } + + /* disable fops (user space) operations for ALSA API */ + mutex_lock(&snd_card_mutex); + snd_cards[card->number] = NULL; + clear_bit(card->number, snd_cards_lock); + mutex_unlock(&snd_card_mutex); + #ifdef CONFIG_PM wake_up(&card->power_sleep); #endif diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 9637d0bbdeb5..b9e720cb6f02 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6743,6 +6743,8 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60140}, {0x14, 0x90170150}, {0x21, 0x02211020}), + SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x21, 0x02211020}), SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE, {0x14, 0x90170110}, {0x21, 0x02211020}), @@ -6853,6 +6855,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x21, 0x0221101f}), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, ALC256_STANDARD_PINS), + SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x14, 0x90170110}, + {0x1b, 0x01011020}, + {0x21, 0x0221101f}), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC256_FIXUP_ASUS_MIC, {0x14, 0x90170110}, {0x1b, 0x90a70130}, diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h index acc704bd3998..0b0ef3abc966 100644 --- a/tools/include/linux/bitops.h +++ b/tools/include/linux/bitops.h @@ -3,8 +3,6 @@ #define _TOOLS_LINUX_BITOPS_H_

#include <asm/types.h> -#include <linux/compiler.h> - #ifndef __WORDSIZE #define __WORDSIZE (__SIZEOF_LONG__ * 8) #endif @@ -12,10 +10,9 @@ #ifndef BITS_PER_LONG # define BITS_PER_LONG __WORDSIZE #endif +#include <linux/bits.h> +#include <linux/compiler.h>

-#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) -#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) -#define BITS_PER_BYTE 8 #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) #define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64)) #define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32)) diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h new file mode 100644 index 000000000000..2b7b532c1d51 --- /dev/null +++ b/tools/include/linux/bits.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_BITS_H +#define __LINUX_BITS_H +#include <asm/bitsperlong.h> + +#define BIT(nr) (1UL << (nr)) +#define BIT_ULL(nr) (1ULL << (nr)) +#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) +#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) +#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG)) +#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG) +#define BITS_PER_BYTE 8 + +/* + * Create a contiguous bitmask starting at bit position @l and ending at + * position @h. For example + * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. + */ +#define GENMASK(h, l) \ + (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) + +#define GENMASK_ULL(h, l) \ + (((~0ULL) - (1ULL << (l)) + 1) & \ + (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) + +#endif /* __LINUX_BITS_H */ diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 50cd6228f506..df1dbee8d98d 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -11,6 +11,7 @@ include/uapi/linux/sched.h include/uapi/linux/stat.h include/uapi/linux/vhost.h include/uapi/sound/asound.h +include/linux/bits.h include/linux/hash.h include/uapi/linux/hw_breakpoint.h arch/x86/include/asm/disabled-features.h