diff --git a/kernel/Documentation/ABI/testing/sysfs-kernel-mm-swap b/kernel/Documentation/ABI/testing/sysfs-kernel-mm-swap index 587db5208..94672016c 100644 --- a/kernel/Documentation/ABI/testing/sysfs-kernel-mm-swap +++ b/kernel/Documentation/ABI/testing/sysfs-kernel-mm-swap @@ -14,13 +14,3 @@ Description: Enable/disable VMA based swap readahead. still used for tmpfs etc. other users. If set to false, the global swap readahead algorithm will be used for all swappable pages. - -What: /sys/kernel/mm/swap/vma_ra_max_order -Date: August 2017 -Contact: Linux memory management mailing list -Description: The max readahead size in order for VMA based swap readahead - - VMA based swap readahead algorithm will readahead at - most 1 << max_order pages for each readahead. The - real readahead size for each readahead will be scaled - according to the estimation algorithm. diff --git a/kernel/Documentation/networking/bonding.txt b/kernel/Documentation/networking/bonding.txt index 57f52cdce..9ba04c0ba 100644 --- a/kernel/Documentation/networking/bonding.txt +++ b/kernel/Documentation/networking/bonding.txt @@ -2387,7 +2387,7 @@ broadcast: Like active-backup, there is not much advantage to this and packet type ID), so in a "gatewayed" configuration, all outgoing traffic will generally use the same device. Incoming traffic may also end up on a single device, but that is - dependent upon the balancing policy of the peer's 8023.ad + dependent upon the balancing policy of the peer's 802.3ad implementation. In a "local" configuration, traffic will be distributed across the devices in the bond. diff --git a/kernel/MAINTAINERS b/kernel/MAINTAINERS index 2d3d750b1..a74227ad0 100644 --- a/kernel/MAINTAINERS +++ b/kernel/MAINTAINERS @@ -5346,9 +5346,7 @@ M: "J. Bruce Fields" L: linux-fsdevel@vger.kernel.org S: Maintained F: include/linux/fcntl.h -F: include/linux/fs.h F: include/uapi/linux/fcntl.h -F: include/uapi/linux/fs.h F: fs/fcntl.c F: fs/locks.c @@ -5357,6 +5355,8 @@ M: Alexander Viro L: linux-fsdevel@vger.kernel.org S: Maintained F: fs/* +F: include/linux/fs.h +F: include/uapi/linux/fs.h FINTEK F75375S HARDWARE MONITOR AND FAN CONTROLLER DRIVER M: Riku Voipio @@ -7571,7 +7571,7 @@ F: arch/mips/include/asm/kvm* F: arch/mips/kvm/ KERNEL VIRTUAL MACHINE FOR POWERPC (KVM/powerpc) -M: Alexander Graf +M: Paul Mackerras L: kvm-ppc@vger.kernel.org W: http://www.linux-kvm.org/ T: git git://github.com/agraf/linux-2.6.git diff --git a/kernel/Makefile b/kernel/Makefile index 2835863bd..46bfb0ed2 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Fearless Coyote # *DOCUMENTATION* @@ -933,7 +933,11 @@ ifdef CONFIG_STACK_VALIDATION ifeq ($(has_libelf),1) objtool_target := tools/objtool FORCE else - $(warning "Cannot use CONFIG_STACK_VALIDATION, please install libelf-dev, libelf-devel or elfutils-libelf-devel") + ifdef CONFIG_ORC_UNWINDER + $(error "Cannot generate ORC metadata for CONFIG_ORC_UNWINDER=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel") + else + $(warning "Cannot use CONFIG_STACK_VALIDATION=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel") + endif SKIP_STACK_VALIDATION := 1 export SKIP_STACK_VALIDATION endif diff --git a/kernel/arch/Kconfig b/kernel/arch/Kconfig index 1aafb4efb..d789a89cb 100644 --- a/kernel/arch/Kconfig +++ b/kernel/arch/Kconfig @@ -937,9 +937,6 @@ config STRICT_MODULE_RWX and non-text memory will be made non-executable. This provides protection against certain security exploits (e.g. writing to text) -config ARCH_WANT_RELAX_ORDER - bool - config ARCH_HAS_REFCOUNT bool help diff --git a/kernel/arch/mips/include/asm/cmpxchg.h b/kernel/arch/mips/include/asm/cmpxchg.h index 903f3bf48..7e25c5cc3 100644 --- a/kernel/arch/mips/include/asm/cmpxchg.h +++ b/kernel/arch/mips/include/asm/cmpxchg.h @@ -155,14 +155,16 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, return __cmpxchg_small(ptr, old, new, size); case 4: - return __cmpxchg_asm("ll", "sc", (volatile u32 *)ptr, old, new); + return __cmpxchg_asm("ll", "sc", (volatile u32 *)ptr, + (u32)old, new); case 8: /* lld/scd are only available for MIPS64 */ if (!IS_ENABLED(CONFIG_64BIT)) return __cmpxchg_called_with_bad_pointer(); - return __cmpxchg_asm("lld", "scd", (volatile u64 *)ptr, old, new); + return __cmpxchg_asm("lld", "scd", (volatile u64 *)ptr, + (u64)old, new); default: return __cmpxchg_called_with_bad_pointer(); diff --git a/kernel/arch/mips/loongson32/common/platform.c b/kernel/arch/mips/loongson32/common/platform.c index 100f23dfa..ac584c582 100644 --- a/kernel/arch/mips/loongson32/common/platform.c +++ b/kernel/arch/mips/loongson32/common/platform.c @@ -183,18 +183,20 @@ int ls1x_eth_mux_init(struct platform_device *pdev, void *priv) } static struct plat_stmmacenet_data ls1x_eth0_pdata = { - .bus_id = 0, - .phy_addr = -1, + .bus_id = 0, + .phy_addr = -1, #if defined(CONFIG_LOONGSON1_LS1B) - .interface = PHY_INTERFACE_MODE_MII, + .interface = PHY_INTERFACE_MODE_MII, #elif defined(CONFIG_LOONGSON1_LS1C) - .interface = PHY_INTERFACE_MODE_RMII, + .interface = PHY_INTERFACE_MODE_RMII, #endif - .mdio_bus_data = &ls1x_mdio_bus_data, - .dma_cfg = &ls1x_eth_dma_cfg, - .has_gmac = 1, - .tx_coe = 1, - .init = ls1x_eth_mux_init, + .mdio_bus_data = &ls1x_mdio_bus_data, + .dma_cfg = &ls1x_eth_dma_cfg, + .has_gmac = 1, + .tx_coe = 1, + .rx_queues_to_use = 1, + .tx_queues_to_use = 1, + .init = ls1x_eth_mux_init, }; static struct resource ls1x_eth0_resources[] = { @@ -222,14 +224,16 @@ struct platform_device ls1x_eth0_pdev = { #ifdef CONFIG_LOONGSON1_LS1B static struct plat_stmmacenet_data ls1x_eth1_pdata = { - .bus_id = 1, - .phy_addr = -1, - .interface = PHY_INTERFACE_MODE_MII, - .mdio_bus_data = &ls1x_mdio_bus_data, - .dma_cfg = &ls1x_eth_dma_cfg, - .has_gmac = 1, - .tx_coe = 1, - .init = ls1x_eth_mux_init, + .bus_id = 1, + .phy_addr = -1, + .interface = PHY_INTERFACE_MODE_MII, + .mdio_bus_data = &ls1x_mdio_bus_data, + .dma_cfg = &ls1x_eth_dma_cfg, + .has_gmac = 1, + .tx_coe = 1, + .rx_queues_to_use = 1, + .tx_queues_to_use = 1, + .init = ls1x_eth_mux_init, }; static struct resource ls1x_eth1_resources[] = { diff --git a/kernel/arch/mips/math-emu/cp1emu.c b/kernel/arch/mips/math-emu/cp1emu.c index 192542dbd..16d9ef5a7 100644 --- a/kernel/arch/mips/math-emu/cp1emu.c +++ b/kernel/arch/mips/math-emu/cp1emu.c @@ -2558,7 +2558,6 @@ dcopuop: break; default: /* Reserved R6 ops */ - pr_err("Reserved MIPS R6 CMP.condn.S operation\n"); return SIGILL; } } @@ -2719,7 +2718,6 @@ dcopuop: break; default: /* Reserved R6 ops */ - pr_err("Reserved MIPS R6 CMP.condn.D operation\n"); return SIGILL; } } diff --git a/kernel/arch/mips/net/ebpf_jit.c b/kernel/arch/mips/net/ebpf_jit.c index 7646891c4..01b7a87ea 100644 --- a/kernel/arch/mips/net/ebpf_jit.c +++ b/kernel/arch/mips/net/ebpf_jit.c @@ -667,7 +667,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, { int src, dst, r, td, ts, mem_off, b_off; bool need_swap, did_move, cmp_eq; - unsigned int target; + unsigned int target = 0; u64 t64; s64 t64s; int bpf_op = BPF_OP(insn->code); diff --git a/kernel/arch/mips/tools/generic-board-config.sh b/kernel/arch/mips/tools/generic-board-config.sh index 5c4f93687..654d652d7 100755 --- a/kernel/arch/mips/tools/generic-board-config.sh +++ b/kernel/arch/mips/tools/generic-board-config.sh @@ -30,8 +30,6 @@ cfg="$4" boards_origin="$5" shift 5 -cd "${srctree}" - # Only print Skipping... lines if the user explicitly specified BOARDS=. In the # general case it only serves to obscure the useful output about what actually # was included. @@ -48,7 +46,7 @@ environment*) esac for board in $@; do - board_cfg="arch/mips/configs/generic/board-${board}.config" + board_cfg="${srctree}/arch/mips/configs/generic/board-${board}.config" if [ ! -f "${board_cfg}" ]; then echo "WARNING: Board config '${board_cfg}' not found" continue @@ -84,7 +82,7 @@ for board in $@; do done || continue # Merge this board config fragment into our final config file - ./scripts/kconfig/merge_config.sh \ + ${srctree}/scripts/kconfig/merge_config.sh \ -m -O ${objtree} ${cfg} ${board_cfg} \ | grep -Ev '^(#|Using)' done diff --git a/kernel/arch/powerpc/kernel/exceptions-64s.S b/kernel/arch/powerpc/kernel/exceptions-64s.S index 48da0f5d2..b82586c53 100644 --- a/kernel/arch/powerpc/kernel/exceptions-64s.S +++ b/kernel/arch/powerpc/kernel/exceptions-64s.S @@ -734,7 +734,29 @@ EXC_REAL(program_check, 0x700, 0x100) EXC_VIRT(program_check, 0x4700, 0x100, 0x700) TRAMP_KVM(PACA_EXGEN, 0x700) EXC_COMMON_BEGIN(program_check_common) - EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) + /* + * It's possible to receive a TM Bad Thing type program check with + * userspace register values (in particular r1), but with SRR1 reporting + * that we came from the kernel. Normally that would confuse the bad + * stack logic, and we would report a bad kernel stack pointer. Instead + * we switch to the emergency stack if we're taking a TM Bad Thing from + * the kernel. + */ + li r10,MSR_PR /* Build a mask of MSR_PR .. */ + oris r10,r10,0x200000@h /* .. and SRR1_PROGTM */ + and r10,r10,r12 /* Mask SRR1 with that. */ + srdi r10,r10,8 /* Shift it so we can compare */ + cmpldi r10,(0x200000 >> 8) /* .. with an immediate. */ + bne 1f /* If != go to normal path. */ + + /* SRR1 had PR=0 and SRR1_PROGTM=1, so use the emergency stack */ + andi. r10,r12,MSR_PR; /* Set CR0 correctly for label */ + /* 3 in EXCEPTION_PROLOG_COMMON */ + mr r10,r1 /* Save r1 */ + ld r1,PACAEMERGSP(r13) /* Use emergency stack */ + subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ + b 3f /* Jump into the macro !! */ +1: EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) bl save_nvgprs RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD diff --git a/kernel/arch/powerpc/kernel/signal_64.c b/kernel/arch/powerpc/kernel/signal_64.c index c83c11585..b2c002993 100644 --- a/kernel/arch/powerpc/kernel/signal_64.c +++ b/kernel/arch/powerpc/kernel/signal_64.c @@ -452,9 +452,20 @@ static long restore_tm_sigcontexts(struct task_struct *tsk, if (MSR_TM_RESV(msr)) return -EINVAL; - /* pull in MSR TM from user context */ + /* pull in MSR TS bits from user context */ regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK); + /* + * Ensure that TM is enabled in regs->msr before we leave the signal + * handler. It could be the case that (a) user disabled the TM bit + * through the manipulation of the MSR bits in uc_mcontext or (b) the + * TM bit was disabled because a sufficient number of context switches + * happened whilst in the signal handler and load_tm overflowed, + * disabling the TM bit. In either case we can end up with an illegal + * TM state leading to a TM Bad Thing when we return to userspace. + */ + regs->msr |= MSR_TM; + /* pull in MSR LE from user context */ regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE); diff --git a/kernel/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/kernel/arch/powerpc/kernel/trace/ftrace_64_mprofile.S index c98e90b4e..b4e2b7165 100644 --- a/kernel/arch/powerpc/kernel/trace/ftrace_64_mprofile.S +++ b/kernel/arch/powerpc/kernel/trace/ftrace_64_mprofile.S @@ -181,34 +181,25 @@ _GLOBAL(ftrace_stub) * - we have no stack frame and can not allocate one * - LR points back to the original caller (in A) * - CTR holds the new NIP in C - * - r0 & r12 are free - * - * r0 can't be used as the base register for a DS-form load or store, so - * we temporarily shuffle r1 (stack pointer) into r0 and then put it back. + * - r0, r11 & r12 are free */ livepatch_handler: CURRENT_THREAD_INFO(r12, r1) - /* Save stack pointer into r0 */ - mr r0, r1 - /* Allocate 3 x 8 bytes */ - ld r1, TI_livepatch_sp(r12) - addi r1, r1, 24 - std r1, TI_livepatch_sp(r12) + ld r11, TI_livepatch_sp(r12) + addi r11, r11, 24 + std r11, TI_livepatch_sp(r12) /* Save toc & real LR on livepatch stack */ - std r2, -24(r1) + std r2, -24(r11) mflr r12 - std r12, -16(r1) + std r12, -16(r11) /* Store stack end marker */ lis r12, STACK_END_MAGIC@h ori r12, r12, STACK_END_MAGIC@l - std r12, -8(r1) - - /* Restore real stack pointer */ - mr r1, r0 + std r12, -8(r11) /* Put ctr in r12 for global entry and branch there */ mfctr r12 @@ -216,36 +207,30 @@ livepatch_handler: /* * Now we are returning from the patched function to the original - * caller A. We are free to use r0 and r12, and we can use r2 until we + * caller A. We are free to use r11, r12 and we can use r2 until we * restore it. */ CURRENT_THREAD_INFO(r12, r1) - /* Save stack pointer into r0 */ - mr r0, r1 - - ld r1, TI_livepatch_sp(r12) + ld r11, TI_livepatch_sp(r12) /* Check stack marker hasn't been trashed */ lis r2, STACK_END_MAGIC@h ori r2, r2, STACK_END_MAGIC@l - ld r12, -8(r1) + ld r12, -8(r11) 1: tdne r12, r2 EMIT_BUG_ENTRY 1b, __FILE__, __LINE__ - 1, 0 /* Restore LR & toc from livepatch stack */ - ld r12, -16(r1) + ld r12, -16(r11) mtlr r12 - ld r2, -24(r1) + ld r2, -24(r11) /* Pop livepatch stack frame */ - CURRENT_THREAD_INFO(r12, r0) - subi r1, r1, 24 - std r1, TI_livepatch_sp(r12) - - /* Restore real stack pointer */ - mr r1, r0 + CURRENT_THREAD_INFO(r12, r1) + subi r11, r11, 24 + std r11, TI_livepatch_sp(r12) /* Return to original caller of live patched function */ blr diff --git a/kernel/arch/powerpc/lib/sstep.c b/kernel/arch/powerpc/lib/sstep.c index 5e8418c28..f208f560a 100644 --- a/kernel/arch/powerpc/lib/sstep.c +++ b/kernel/arch/powerpc/lib/sstep.c @@ -1684,11 +1684,13 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, * Logical instructions */ case 26: /* cntlzw */ - op->val = __builtin_clz((unsigned int) regs->gpr[rd]); + val = (unsigned int) regs->gpr[rd]; + op->val = ( val ? __builtin_clz(val) : 32 ); goto logical_done; #ifdef __powerpc64__ case 58: /* cntlzd */ - op->val = __builtin_clzl(regs->gpr[rd]); + val = regs->gpr[rd]; + op->val = ( val ? __builtin_clzl(val) : 64 ); goto logical_done; #endif case 28: /* and */ diff --git a/kernel/arch/powerpc/mm/numa.c b/kernel/arch/powerpc/mm/numa.c index b95c584ce..a51df9ef5 100644 --- a/kernel/arch/powerpc/mm/numa.c +++ b/kernel/arch/powerpc/mm/numa.c @@ -1438,7 +1438,6 @@ out: int arch_update_cpu_topology(void) { - lockdep_assert_cpus_held(); return numa_update_cpu_topology(true); } diff --git a/kernel/arch/powerpc/perf/imc-pmu.c b/kernel/arch/powerpc/perf/imc-pmu.c index 9ccac86f3..881262458 100644 --- a/kernel/arch/powerpc/perf/imc-pmu.c +++ b/kernel/arch/powerpc/perf/imc-pmu.c @@ -399,6 +399,20 @@ static void nest_imc_counters_release(struct perf_event *event) /* Take the mutex lock for this node and then decrement the reference count */ mutex_lock(&ref->lock); + if (ref->refc == 0) { + /* + * The scenario where this is true is, when perf session is + * started, followed by offlining of all cpus in a given node. + * + * In the cpuhotplug offline path, ppc_nest_imc_cpu_offline() + * function set the ref->count to zero, if the cpu which is + * about to offline is the last cpu in a given node and make + * an OPAL call to disable the engine in that node. + * + */ + mutex_unlock(&ref->lock); + return; + } ref->refc--; if (ref->refc == 0) { rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST, @@ -523,8 +537,8 @@ static int core_imc_mem_init(int cpu, int size) /* We need only vbase for core counters */ mem_info->vbase = page_address(alloc_pages_node(phys_id, - GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, - get_order(size))); + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE | + __GFP_NOWARN, get_order(size))); if (!mem_info->vbase) return -ENOMEM; @@ -646,6 +660,20 @@ static void core_imc_counters_release(struct perf_event *event) return; mutex_lock(&ref->lock); + if (ref->refc == 0) { + /* + * The scenario where this is true is, when perf session is + * started, followed by offlining of all cpus in a given core. + * + * In the cpuhotplug offline path, ppc_core_imc_cpu_offline() + * function set the ref->count to zero, if the cpu which is + * about to offline is the last cpu in a given core and make + * an OPAL call to disable the engine in that core. + * + */ + mutex_unlock(&ref->lock); + return; + } ref->refc--; if (ref->refc == 0) { rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, @@ -763,8 +791,8 @@ static int thread_imc_mem_alloc(int cpu_id, int size) * free the memory in cpu offline path. */ local_mem = page_address(alloc_pages_node(phys_id, - GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, - get_order(size))); + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE | + __GFP_NOWARN, get_order(size))); if (!local_mem) return -ENOMEM; @@ -1148,7 +1176,8 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) } /* Only free the attr_groups which are dynamically allocated */ - kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs); + if (pmu_ptr->attr_groups[IMC_EVENT_ATTR]) + kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs); kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]); kfree(pmu_ptr); return; diff --git a/kernel/arch/sparc/Kconfig b/kernel/arch/sparc/Kconfig index 0be382875..4e83f9507 100644 --- a/kernel/arch/sparc/Kconfig +++ b/kernel/arch/sparc/Kconfig @@ -44,7 +44,6 @@ config SPARC select ARCH_HAS_SG_CHAIN select CPU_NO_EFFICIENT_FFS select LOCKDEP_SMALL if LOCKDEP - select ARCH_WANT_RELAX_ORDER config SPARC32 def_bool !64BIT diff --git a/kernel/arch/x86/entry/entry_32.S b/kernel/arch/x86/entry/entry_32.S index 8a13d4686..50e0d2bc4 100644 --- a/kernel/arch/x86/entry/entry_32.S +++ b/kernel/arch/x86/entry/entry_32.S @@ -176,7 +176,7 @@ /* * This is a sneaky trick to help the unwinder find pt_regs on the stack. The * frame pointer is replaced with an encoded pointer to pt_regs. The encoding - * is just setting the LSB, which makes it an invalid stack address and is also + * is just clearing the MSB, which makes it an invalid stack address and is also * a signal to the unwinder that it's a pt_regs pointer in disguise. * * NOTE: This macro must be used *after* SAVE_ALL because it corrupts the @@ -185,7 +185,7 @@ .macro ENCODE_FRAME_POINTER #ifdef CONFIG_FRAME_POINTER mov %esp, %ebp - orl $0x1, %ebp + andl $0x7fffffff, %ebp #endif .endm diff --git a/kernel/arch/x86/events/intel/uncore.c b/kernel/arch/x86/events/intel/uncore.c index 1c5390f1c..d45e06346 100644 --- a/kernel/arch/x86/events/intel/uncore.c +++ b/kernel/arch/x86/events/intel/uncore.c @@ -822,7 +822,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) pmus[i].type = type; pmus[i].boxes = kzalloc(size, GFP_KERNEL); if (!pmus[i].boxes) - return -ENOMEM; + goto err; } type->pmus = pmus; @@ -836,7 +836,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) attr_group = kzalloc(sizeof(struct attribute *) * (i + 1) + sizeof(*attr_group), GFP_KERNEL); if (!attr_group) - return -ENOMEM; + goto err; attrs = (struct attribute **)(attr_group + 1); attr_group->name = "events"; @@ -849,7 +849,15 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) } type->pmu_group = &uncore_pmu_attr_group; + return 0; + +err: + for (i = 0; i < type->num_boxes; i++) + kfree(pmus[i].boxes); + kfree(pmus); + + return -ENOMEM; } static int __init diff --git a/kernel/arch/x86/hyperv/hv_init.c b/kernel/arch/x86/hyperv/hv_init.c index 1a8eb550c..a5db63f72 100644 --- a/kernel/arch/x86/hyperv/hv_init.c +++ b/kernel/arch/x86/hyperv/hv_init.c @@ -85,6 +85,8 @@ EXPORT_SYMBOL_GPL(hyperv_cs); u32 *hv_vp_index; EXPORT_SYMBOL_GPL(hv_vp_index); +u32 hv_max_vp_index; + static int hv_cpu_init(unsigned int cpu) { u64 msr_vp_index; @@ -93,6 +95,9 @@ static int hv_cpu_init(unsigned int cpu) hv_vp_index[smp_processor_id()] = msr_vp_index; + if (msr_vp_index > hv_max_vp_index) + hv_max_vp_index = msr_vp_index; + return 0; } diff --git a/kernel/arch/x86/hyperv/mmu.c b/kernel/arch/x86/hyperv/mmu.c index 39e7f6e50..9cc9e1c1e 100644 --- a/kernel/arch/x86/hyperv/mmu.c +++ b/kernel/arch/x86/hyperv/mmu.c @@ -36,9 +36,9 @@ struct hv_flush_pcpu_ex { /* Each gva in gva_list encodes up to 4096 pages to flush */ #define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE) -static struct hv_flush_pcpu __percpu *pcpu_flush; +static struct hv_flush_pcpu __percpu **pcpu_flush; -static struct hv_flush_pcpu_ex __percpu *pcpu_flush_ex; +static struct hv_flush_pcpu_ex __percpu **pcpu_flush_ex; /* * Fills in gva_list starting from offset. Returns the number of items added. @@ -76,6 +76,18 @@ static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush, { int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1; + /* valid_bank_mask can represent up to 64 banks */ + if (hv_max_vp_index / 64 >= 64) + return 0; + + /* + * Clear all banks up to the maximum possible bank as hv_flush_pcpu_ex + * structs are not cleared between calls, we risk flushing unneeded + * vCPUs otherwise. + */ + for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++) + flush->hv_vp_set.bank_contents[vcpu_bank] = 0; + /* * Some banks may end up being empty but this is acceptable. */ @@ -83,11 +95,6 @@ static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush, vcpu = hv_cpu_number_to_vp_number(cpu); vcpu_bank = vcpu / 64; vcpu_offset = vcpu % 64; - - /* valid_bank_mask can represent up to 64 banks */ - if (vcpu_bank >= 64) - return 0; - __set_bit(vcpu_offset, (unsigned long *) &flush->hv_vp_set.bank_contents[vcpu_bank]); if (vcpu_bank >= nr_bank) @@ -102,6 +109,7 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, const struct flush_tlb_info *info) { int cpu, vcpu, gva_n, max_gvas; + struct hv_flush_pcpu **flush_pcpu; struct hv_flush_pcpu *flush; u64 status = U64_MAX; unsigned long flags; @@ -116,7 +124,17 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, local_irq_save(flags); - flush = this_cpu_ptr(pcpu_flush); + flush_pcpu = this_cpu_ptr(pcpu_flush); + + if (unlikely(!*flush_pcpu)) + *flush_pcpu = page_address(alloc_page(GFP_ATOMIC)); + + flush = *flush_pcpu; + + if (unlikely(!flush)) { + local_irq_restore(flags); + goto do_native; + } if (info->mm) { flush->address_space = virt_to_phys(info->mm->pgd); @@ -173,6 +191,7 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, const struct flush_tlb_info *info) { int nr_bank = 0, max_gvas, gva_n; + struct hv_flush_pcpu_ex **flush_pcpu; struct hv_flush_pcpu_ex *flush; u64 status = U64_MAX; unsigned long flags; @@ -187,7 +206,17 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, local_irq_save(flags); - flush = this_cpu_ptr(pcpu_flush_ex); + flush_pcpu = this_cpu_ptr(pcpu_flush_ex); + + if (unlikely(!*flush_pcpu)) + *flush_pcpu = page_address(alloc_page(GFP_ATOMIC)); + + flush = *flush_pcpu; + + if (unlikely(!flush)) { + local_irq_restore(flags); + goto do_native; + } if (info->mm) { flush->address_space = virt_to_phys(info->mm->pgd); @@ -222,18 +251,18 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY; status = hv_do_rep_hypercall( HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX, - 0, nr_bank + 2, flush, NULL); + 0, nr_bank, flush, NULL); } else if (info->end && ((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) { status = hv_do_rep_hypercall( HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX, - 0, nr_bank + 2, flush, NULL); + 0, nr_bank, flush, NULL); } else { gva_n = fill_gva_list(flush->gva_list, nr_bank, info->start, info->end); status = hv_do_rep_hypercall( HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX, - gva_n, nr_bank + 2, flush, NULL); + gva_n, nr_bank, flush, NULL); } local_irq_restore(flags); @@ -266,7 +295,7 @@ void hyper_alloc_mmu(void) return; if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) - pcpu_flush = __alloc_percpu(PAGE_SIZE, PAGE_SIZE); + pcpu_flush = alloc_percpu(struct hv_flush_pcpu *); else - pcpu_flush_ex = __alloc_percpu(PAGE_SIZE, PAGE_SIZE); + pcpu_flush_ex = alloc_percpu(struct hv_flush_pcpu_ex *); } diff --git a/kernel/arch/x86/include/asm/alternative-asm.h b/kernel/arch/x86/include/asm/alternative-asm.h index e7636bac7..6c98821fe 100644 --- a/kernel/arch/x86/include/asm/alternative-asm.h +++ b/kernel/arch/x86/include/asm/alternative-asm.h @@ -62,8 +62,10 @@ #define new_len2 145f-144f /* - * max without conditionals. Idea adapted from: + * gas compatible max based on the idea from: * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax + * + * The additional "-" is needed because gas uses a "true" value of -1. */ #define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b))))) diff --git a/kernel/arch/x86/include/asm/alternative.h b/kernel/arch/x86/include/asm/alternative.h index c09662413..ccbe24e69 100644 --- a/kernel/arch/x86/include/asm/alternative.h +++ b/kernel/arch/x86/include/asm/alternative.h @@ -103,12 +103,12 @@ static inline int alternatives_text_reserved(void *start, void *end) alt_end_marker ":\n" /* - * max without conditionals. Idea adapted from: + * gas compatible max based on the idea from: * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax * - * The additional "-" is needed because gas works with s32s. + * The additional "-" is needed because gas uses a "true" value of -1. */ -#define alt_max_short(a, b) "((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") - (" b ")))))" +#define alt_max_short(a, b) "((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") < (" b ")))))" /* * Pad the second replacement alternative with additional NOPs if it is diff --git a/kernel/arch/x86/include/asm/mce.h b/kernel/arch/x86/include/asm/mce.h index 181264989..8edac1de2 100644 --- a/kernel/arch/x86/include/asm/mce.h +++ b/kernel/arch/x86/include/asm/mce.h @@ -187,7 +187,6 @@ struct mca_msr_regs { extern struct mce_vendor_flags mce_flags; -extern struct mca_config mca_cfg; extern struct mca_msr_regs msr_ops; enum mce_notifier_prios { diff --git a/kernel/arch/x86/include/asm/mmu_context.h b/kernel/arch/x86/include/asm/mmu_context.h index c120b5db1..3c856a15b 100644 --- a/kernel/arch/x86/include/asm/mmu_context.h +++ b/kernel/arch/x86/include/asm/mmu_context.h @@ -126,13 +126,7 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) DEBUG_LOCKS_WARN_ON(preemptible()); } -static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) -{ - int cpu = smp_processor_id(); - - if (cpumask_test_cpu(cpu, mm_cpumask(mm))) - cpumask_clear_cpu(cpu, mm_cpumask(mm)); -} +void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) diff --git a/kernel/arch/x86/include/asm/mshyperv.h b/kernel/arch/x86/include/asm/mshyperv.h index 738503e1f..530f448fd 100644 --- a/kernel/arch/x86/include/asm/mshyperv.h +++ b/kernel/arch/x86/include/asm/mshyperv.h @@ -289,6 +289,7 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size, * to this information. */ extern u32 *hv_vp_index; +extern u32 hv_max_vp_index; /** * hv_cpu_number_to_vp_number() - Map CPU to VP. diff --git a/kernel/arch/x86/include/asm/tlbflush.h b/kernel/arch/x86/include/asm/tlbflush.h index 4893abf7f..d362161d3 100644 --- a/kernel/arch/x86/include/asm/tlbflush.h +++ b/kernel/arch/x86/include/asm/tlbflush.h @@ -82,6 +82,13 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm) #define __flush_tlb_single(addr) __native_flush_tlb_single(addr) #endif +/* + * If tlb_use_lazy_mode is true, then we try to avoid switching CR3 to point + * to init_mm when we switch to a kernel thread (e.g. the idle thread). If + * it's false, then we immediately switch CR3 when entering a kernel thread. + */ +DECLARE_STATIC_KEY_TRUE(tlb_use_lazy_mode); + /* * 6 because 6 should be plenty and struct tlb_state will fit in * two cache lines. @@ -104,6 +111,23 @@ struct tlb_state { u16 loaded_mm_asid; u16 next_asid; + /* + * We can be in one of several states: + * + * - Actively using an mm. Our CPU's bit will be set in + * mm_cpumask(loaded_mm) and is_lazy == false; + * + * - Not using a real mm. loaded_mm == &init_mm. Our CPU's bit + * will not be set in mm_cpumask(&init_mm) and is_lazy == false. + * + * - Lazily using a real mm. loaded_mm != &init_mm, our bit + * is set in mm_cpumask(loaded_mm), but is_lazy == true. + * We're heuristically guessing that the CR3 load we + * skipped more than makes up for the overhead added by + * lazy mode. + */ + bool is_lazy; + /* * Access to this CR4 shadow and to H/W CR4 is protected by * disabling interrupts when modifying either one. diff --git a/kernel/arch/x86/kernel/apic/apic.c b/kernel/arch/x86/kernel/apic/apic.c index d705c769f..ff891772c 100644 --- a/kernel/arch/x86/kernel/apic/apic.c +++ b/kernel/arch/x86/kernel/apic/apic.c @@ -573,11 +573,21 @@ static u32 bdx_deadline_rev(void) return ~0U; } +static u32 skx_deadline_rev(void) +{ + switch (boot_cpu_data.x86_mask) { + case 0x03: return 0x01000136; + case 0x04: return 0x02000014; + } + + return ~0U; +} + static const struct x86_cpu_id deadline_match[] = { DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X, hsx_deadline_rev), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X, 0x0b000020), DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_XEON_D, bdx_deadline_rev), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_X, 0x02000014), + DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_SKYLAKE_X, skx_deadline_rev), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_CORE, 0x22), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_ULT, 0x20), @@ -600,7 +610,8 @@ static void apic_check_deadline_errata(void) const struct x86_cpu_id *m; u32 rev; - if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) || + boot_cpu_has(X86_FEATURE_HYPERVISOR)) return; m = x86_match_cpu(deadline_match); diff --git a/kernel/arch/x86/kernel/cpu/mcheck/mce-internal.h b/kernel/arch/x86/kernel/cpu/mcheck/mce-internal.h index 098530a93..debb974fd 100644 --- a/kernel/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/kernel/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -1,3 +1,6 @@ +#ifndef __X86_MCE_INTERNAL_H__ +#define __X86_MCE_INTERNAL_H__ + #include #include @@ -108,3 +111,7 @@ static inline void mce_work_trigger(void) { } static inline void mce_register_injector_chain(struct notifier_block *nb) { } static inline void mce_unregister_injector_chain(struct notifier_block *nb) { } #endif + +extern struct mca_config mca_cfg; + +#endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/kernel/arch/x86/kernel/cpu/mcheck/mce_amd.c b/kernel/arch/x86/kernel/cpu/mcheck/mce_amd.c index 40e28ed77..486f640b0 100644 --- a/kernel/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/kernel/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -28,6 +28,8 @@ #include #include +#include "mce-internal.h" + #define NR_BLOCKS 5 #define THRESHOLD_MAX 0xFFF #define INT_TYPE_APIC 0x00020000 diff --git a/kernel/arch/x86/kernel/cpu/microcode/core.c b/kernel/arch/x86/kernel/cpu/microcode/core.c index 86e8f0b25..c4fa4a85d 100644 --- a/kernel/arch/x86/kernel/cpu/microcode/core.c +++ b/kernel/arch/x86/kernel/cpu/microcode/core.c @@ -122,9 +122,6 @@ static bool __init check_loader_disabled_bsp(void) bool *res = &dis_ucode_ldr; #endif - if (!have_cpuid_p()) - return *res; - /* * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not * completely accurate as xen pv guests don't see that CPUID bit set but @@ -166,24 +163,36 @@ bool get_builtin_firmware(struct cpio_data *cd, const char *name) void __init load_ucode_bsp(void) { unsigned int cpuid_1_eax; + bool intel = true; - if (check_loader_disabled_bsp()) + if (!have_cpuid_p()) return; cpuid_1_eax = native_cpuid_eax(1); switch (x86_cpuid_vendor()) { case X86_VENDOR_INTEL: - if (x86_family(cpuid_1_eax) >= 6) - load_ucode_intel_bsp(); + if (x86_family(cpuid_1_eax) < 6) + return; break; + case X86_VENDOR_AMD: - if (x86_family(cpuid_1_eax) >= 0x10) - load_ucode_amd_bsp(cpuid_1_eax); + if (x86_family(cpuid_1_eax) < 0x10) + return; + intel = false; break; + default: - break; + return; } + + if (check_loader_disabled_bsp()) + return; + + if (intel) + load_ucode_intel_bsp(); + else + load_ucode_amd_bsp(cpuid_1_eax); } static bool check_loader_disabled_ap(void) diff --git a/kernel/arch/x86/kernel/kprobes/common.h b/kernel/arch/x86/kernel/kprobes/common.h index db2182d63..3fc0f9a79 100644 --- a/kernel/arch/x86/kernel/kprobes/common.h +++ b/kernel/arch/x86/kernel/kprobes/common.h @@ -3,6 +3,15 @@ /* Kprobes and Optprobes common header */ +#include + +#ifdef CONFIG_FRAME_POINTER +# define SAVE_RBP_STRING " push %" _ASM_BP "\n" \ + " mov %" _ASM_SP ", %" _ASM_BP "\n" +#else +# define SAVE_RBP_STRING " push %" _ASM_BP "\n" +#endif + #ifdef CONFIG_X86_64 #define SAVE_REGS_STRING \ /* Skip cs, ip, orig_ax. */ \ @@ -17,7 +26,7 @@ " pushq %r10\n" \ " pushq %r11\n" \ " pushq %rbx\n" \ - " pushq %rbp\n" \ + SAVE_RBP_STRING \ " pushq %r12\n" \ " pushq %r13\n" \ " pushq %r14\n" \ @@ -48,7 +57,7 @@ " pushl %es\n" \ " pushl %ds\n" \ " pushl %eax\n" \ - " pushl %ebp\n" \ + SAVE_RBP_STRING \ " pushl %edi\n" \ " pushl %esi\n" \ " pushl %edx\n" \ diff --git a/kernel/arch/x86/kernel/kprobes/core.c b/kernel/arch/x86/kernel/kprobes/core.c index f0153714d..0742491cb 100644 --- a/kernel/arch/x86/kernel/kprobes/core.c +++ b/kernel/arch/x86/kernel/kprobes/core.c @@ -1080,8 +1080,6 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) * raw stack chunk with redzones: */ __memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr)); - regs->flags &= ~X86_EFLAGS_IF; - trace_hardirqs_off(); regs->ip = (unsigned long)(jp->entry); /* diff --git a/kernel/arch/x86/kernel/reboot.c b/kernel/arch/x86/kernel/reboot.c index 54180fa6f..add33f600 100644 --- a/kernel/arch/x86/kernel/reboot.c +++ b/kernel/arch/x86/kernel/reboot.c @@ -105,6 +105,10 @@ void __noreturn machine_real_restart(unsigned int type) load_cr3(initial_page_table); #else write_cr3(real_mode_header->trampoline_pgd); + + /* Exiting long mode will fail if CR4.PCIDE is set. */ + if (static_cpu_has(X86_FEATURE_PCID)) + cr4_clear_bits(X86_CR4_PCIDE); #endif /* Jump to the identity-mapped low memory code */ diff --git a/kernel/arch/x86/kernel/unwind_frame.c b/kernel/arch/x86/kernel/unwind_frame.c index d145a0b1f..3dc26f95d 100644 --- a/kernel/arch/x86/kernel/unwind_frame.c +++ b/kernel/arch/x86/kernel/unwind_frame.c @@ -44,7 +44,8 @@ static void unwind_dump(struct unwind_state *state) state->stack_info.type, state->stack_info.next_sp, state->stack_mask, state->graph_idx); - for (sp = state->orig_sp; sp; sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { + for (sp = PTR_ALIGN(state->orig_sp, sizeof(long)); sp; + sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { if (get_stack_info(sp, state->task, &stack_info, &visit_mask)) break; @@ -174,6 +175,7 @@ static bool is_last_task_frame(struct unwind_state *state) * This determines if the frame pointer actually contains an encoded pointer to * pt_regs on the stack. See ENCODE_FRAME_POINTER. */ +#ifdef CONFIG_X86_64 static struct pt_regs *decode_frame_pointer(unsigned long *bp) { unsigned long regs = (unsigned long)bp; @@ -183,6 +185,23 @@ static struct pt_regs *decode_frame_pointer(unsigned long *bp) return (struct pt_regs *)(regs & ~0x1); } +#else +static struct pt_regs *decode_frame_pointer(unsigned long *bp) +{ + unsigned long regs = (unsigned long)bp; + + if (regs & 0x80000000) + return NULL; + + return (struct pt_regs *)(regs | 0x80000000); +} +#endif + +#ifdef CONFIG_X86_32 +#define KERNEL_REGS_SIZE (sizeof(struct pt_regs) - 2*sizeof(long)) +#else +#define KERNEL_REGS_SIZE (sizeof(struct pt_regs)) +#endif static bool update_stack_state(struct unwind_state *state, unsigned long *next_bp) @@ -202,7 +221,7 @@ static bool update_stack_state(struct unwind_state *state, regs = decode_frame_pointer(next_bp); if (regs) { frame = (unsigned long *)regs; - len = regs_size(regs); + len = KERNEL_REGS_SIZE; state->got_irq = true; } else { frame = next_bp; @@ -226,6 +245,14 @@ static bool update_stack_state(struct unwind_state *state, frame < prev_frame_end) return false; + /* + * On 32-bit with user mode regs, make sure the last two regs are safe + * to access: + */ + if (IS_ENABLED(CONFIG_X86_32) && regs && user_mode(regs) && + !on_stack(info, frame, len + 2*sizeof(long))) + return false; + /* Move state to the next frame: */ if (regs) { state->regs = regs; @@ -328,6 +355,13 @@ bad_address: state->regs->sp < (unsigned long)task_pt_regs(state->task)) goto the_end; + /* + * There are some known frame pointer issues on 32-bit. Disable + * unwinder warnings on 32-bit until it gets objtool support. + */ + if (IS_ENABLED(CONFIG_X86_32)) + goto the_end; + if (state->regs) { printk_deferred_once(KERN_WARNING "WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n", diff --git a/kernel/arch/x86/kvm/mmu.c b/kernel/arch/x86/kvm/mmu.c index 106d4a029..7a69cf053 100644 --- a/kernel/arch/x86/kvm/mmu.c +++ b/kernel/arch/x86/kvm/mmu.c @@ -3973,13 +3973,6 @@ static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gpte) { - /* - * PT_PAGE_TABLE_LEVEL always terminates. The RHS has bit 7 set - * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means - * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then. - */ - gpte |= level - PT_PAGE_TABLE_LEVEL - 1; - /* * The RHS has bit 7 set iff level < mmu->last_nonleaf_level. * If it is clear, there are no large pages at this level, so clear @@ -3987,6 +3980,13 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu, */ gpte &= level - mmu->last_nonleaf_level; + /* + * PT_PAGE_TABLE_LEVEL always terminates. The RHS has bit 7 set + * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means + * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then. + */ + gpte |= level - PT_PAGE_TABLE_LEVEL - 1; + return gpte & PT_PAGE_SIZE_MASK; } @@ -4555,6 +4555,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, update_permission_bitmask(vcpu, context, true); update_pkru_bitmask(vcpu, context, true); + update_last_nonleaf_level(vcpu, context); reset_rsvds_bits_mask_ept(vcpu, context, execonly); reset_ept_shadow_zero_bits_mask(vcpu, context, execonly); } diff --git a/kernel/arch/x86/kvm/paging_tmpl.h b/kernel/arch/x86/kvm/paging_tmpl.h index 86b68dc5a..f18d1f8d3 100644 --- a/kernel/arch/x86/kvm/paging_tmpl.h +++ b/kernel/arch/x86/kvm/paging_tmpl.h @@ -334,10 +334,11 @@ retry_walk: --walker->level; index = PT_INDEX(addr, walker->level); - table_gfn = gpte_to_gfn(pte); offset = index * sizeof(pt_element_t); pte_gpa = gfn_to_gpa(table_gfn) + offset; + + BUG_ON(walker->level < 1); walker->table_gfn[walker->level - 1] = table_gfn; walker->pte_gpa[walker->level - 1] = pte_gpa; diff --git a/kernel/arch/x86/kvm/vmx.c b/kernel/arch/x86/kvm/vmx.c index a2b804e10..95a01609d 100644 --- a/kernel/arch/x86/kvm/vmx.c +++ b/kernel/arch/x86/kvm/vmx.c @@ -11297,7 +11297,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, /* Same as above - no reason to call set_cr4_guest_host_mask(). */ vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); - kvm_set_cr4(vcpu, vmcs12->host_cr4); + vmx_set_cr4(vcpu, vmcs12->host_cr4); nested_ept_uninit_mmu_context(vcpu); diff --git a/kernel/arch/x86/mm/Makefile b/kernel/arch/x86/mm/Makefile index 72bf8c01c..e1f095884 100644 --- a/kernel/arch/x86/mm/Makefile +++ b/kernel/arch/x86/mm/Makefile @@ -1,5 +1,12 @@ -# Kernel does not boot with instrumentation of tlb.c. -KCOV_INSTRUMENT_tlb.o := n +# Kernel does not boot with instrumentation of tlb.c and mem_encrypt.c +KCOV_INSTRUMENT_tlb.o := n +KCOV_INSTRUMENT_mem_encrypt.o := n + +KASAN_SANITIZE_mem_encrypt.o := n + +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_mem_encrypt.o = -pg +endif obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ pat.o pgtable.o physaddr.o setup_nx.o tlb.o diff --git a/kernel/arch/x86/mm/tlb.c b/kernel/arch/x86/mm/tlb.c index 49d977837..658bf0090 100644 --- a/kernel/arch/x86/mm/tlb.c +++ b/kernel/arch/x86/mm/tlb.c @@ -30,6 +30,8 @@ atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1); +DEFINE_STATIC_KEY_TRUE(tlb_use_lazy_mode); + static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen, u16 *new_asid, bool *need_flush) { @@ -80,7 +82,7 @@ void leave_mm(int cpu) return; /* Warn if we're not lazy. */ - WARN_ON(cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm))); + WARN_ON(!this_cpu_read(cpu_tlbstate.is_lazy)); switch_mm(NULL, &init_mm, NULL); } @@ -142,45 +144,24 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, __flush_tlb_all(); } #endif + this_cpu_write(cpu_tlbstate.is_lazy, false); if (real_prev == next) { VM_BUG_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != next->context.ctx_id); - if (cpumask_test_cpu(cpu, mm_cpumask(next))) { - /* - * There's nothing to do: we weren't lazy, and we - * aren't changing our mm. We don't need to flush - * anything, nor do we need to update CR3, CR4, or - * LDTR. - */ - return; - } - - /* Resume remote flushes and then read tlb_gen. */ - cpumask_set_cpu(cpu, mm_cpumask(next)); - next_tlb_gen = atomic64_read(&next->context.tlb_gen); - - if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) < - next_tlb_gen) { - /* - * Ideally, we'd have a flush_tlb() variant that - * takes the known CR3 value as input. This would - * be faster on Xen PV and on hypothetical CPUs - * on which INVPCID is fast. - */ - this_cpu_write(cpu_tlbstate.ctxs[prev_asid].tlb_gen, - next_tlb_gen); - write_cr3(build_cr3(next, prev_asid)); - trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, - TLB_FLUSH_ALL); - } - /* - * We just exited lazy mode, which means that CR4 and/or LDTR - * may be stale. (Changes to the required CR4 and LDTR states - * are not reflected in tlb_gen.) + * We don't currently support having a real mm loaded without + * our cpu set in mm_cpumask(). We have all the bookkeeping + * in place to figure out whether we would need to flush + * if our cpu were cleared in mm_cpumask(), but we don't + * currently use it. */ + if (WARN_ON_ONCE(real_prev != &init_mm && + !cpumask_test_cpu(cpu, mm_cpumask(next)))) + cpumask_set_cpu(cpu, mm_cpumask(next)); + + return; } else { u16 new_asid; bool need_flush; @@ -199,10 +180,9 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, } /* Stop remote flushes for the previous mm */ - if (cpumask_test_cpu(cpu, mm_cpumask(real_prev))) - cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); - - VM_WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next))); + VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) && + real_prev != &init_mm); + cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); /* * Start remote flushes and then read tlb_gen. @@ -232,6 +212,37 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, switch_ldt(real_prev, next); } +/* + * enter_lazy_tlb() is a hint from the scheduler that we are entering a + * kernel thread or other context without an mm. Acceptable implementations + * include doing nothing whatsoever, switching to init_mm, or various clever + * lazy tricks to try to minimize TLB flushes. + * + * The scheduler reserves the right to call enter_lazy_tlb() several times + * in a row. It will notify us that we're going back to a real mm by + * calling switch_mm_irqs_off(). + */ +void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) +{ + if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm) + return; + + if (static_branch_unlikely(&tlb_use_lazy_mode)) { + /* + * There's a significant optimization that may be possible + * here. We have accurate enough TLB flush tracking that we + * don't need to maintain coherence of TLB per se when we're + * lazy. We do, however, need to maintain coherence of + * paging-structure caches. We could, in principle, leave our + * old mm loaded and only switch to init_mm when + * tlb_remove_page() happens. + */ + this_cpu_write(cpu_tlbstate.is_lazy, true); + } else { + switch_mm(NULL, &init_mm, NULL); + } +} + /* * Call this when reinitializing a CPU. It fixes the following potential * problems: @@ -303,16 +314,20 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, /* This code cannot presently handle being reentered. */ VM_WARN_ON(!irqs_disabled()); + if (unlikely(loaded_mm == &init_mm)) + return; + VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) != loaded_mm->context.ctx_id); - if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm))) { + if (this_cpu_read(cpu_tlbstate.is_lazy)) { /* - * We're in lazy mode -- don't flush. We can get here on - * remote flushes due to races and on local flushes if a - * kernel thread coincidentally flushes the mm it's lazily - * still using. + * We're in lazy mode. We need to at least flush our + * paging-structure cache to avoid speculatively reading + * garbage into our TLB. Since switching to init_mm is barely + * slower than a minimal flush, just switch to init_mm. */ + switch_mm_irqs_off(NULL, &init_mm, NULL); return; } @@ -611,3 +626,57 @@ static int __init create_tlb_single_page_flush_ceiling(void) return 0; } late_initcall(create_tlb_single_page_flush_ceiling); + +static ssize_t tlblazy_read_file(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + char buf[2]; + + buf[0] = static_branch_likely(&tlb_use_lazy_mode) ? '1' : '0'; + buf[1] = '\n'; + + return simple_read_from_buffer(user_buf, count, ppos, buf, 2); +} + +static ssize_t tlblazy_write_file(struct file *file, + const char __user *user_buf, size_t count, loff_t *ppos) +{ + bool val; + + if (kstrtobool_from_user(user_buf, count, &val)) + return -EINVAL; + + if (val) + static_branch_enable(&tlb_use_lazy_mode); + else + static_branch_disable(&tlb_use_lazy_mode); + + return count; +} + +static const struct file_operations fops_tlblazy = { + .read = tlblazy_read_file, + .write = tlblazy_write_file, + .llseek = default_llseek, +}; + +static int __init init_tlb_use_lazy_mode(void) +{ + if (boot_cpu_has(X86_FEATURE_PCID)) { + /* + * Heuristic: with PCID on, switching to and from + * init_mm is reasonably fast, but remote flush IPIs + * as expensive as ever, so turn off lazy TLB mode. + * + * We can't do this in setup_pcid() because static keys + * haven't been initialized yet, and it would blow up + * badly. + */ + static_branch_disable(&tlb_use_lazy_mode); + } + + debugfs_create_file("tlb_use_lazy_mode", S_IRUSR | S_IWUSR, + arch_debugfs_dir, NULL, &fops_tlblazy); + return 0; +} +late_initcall(init_tlb_use_lazy_mode); diff --git a/kernel/arch/x86/xen/enlighten.c b/kernel/arch/x86/xen/enlighten.c index 0e7ef69e8..d669e9d89 100644 --- a/kernel/arch/x86/xen/enlighten.c +++ b/kernel/arch/x86/xen/enlighten.c @@ -93,11 +93,11 @@ int xen_cpuhp_setup(int (*cpu_up_prepare_cb)(unsigned int), int rc; rc = cpuhp_setup_state_nocalls(CPUHP_XEN_PREPARE, - "x86/xen/hvm_guest:prepare", + "x86/xen/guest:prepare", cpu_up_prepare_cb, cpu_dead_cb); if (rc >= 0) { rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, - "x86/xen/hvm_guest:online", + "x86/xen/guest:online", xen_cpu_up_online, NULL); if (rc < 0) cpuhp_remove_state_nocalls(CPUHP_XEN_PREPARE); diff --git a/kernel/block/bio.c b/kernel/block/bio.c index b38e962fa..101c2a9b5 100644 --- a/kernel/block/bio.c +++ b/kernel/block/bio.c @@ -1239,8 +1239,8 @@ struct bio *bio_copy_user_iov(struct request_queue *q, */ bmd->is_our_pages = map_data ? 0 : 1; memcpy(bmd->iov, iter->iov, sizeof(struct iovec) * iter->nr_segs); - iov_iter_init(&bmd->iter, iter->type, bmd->iov, - iter->nr_segs, iter->count); + bmd->iter = *iter; + bmd->iter.iov = bmd->iov; ret = -ENOMEM; bio = bio_kmalloc(gfp_mask, nr_pages); @@ -1331,6 +1331,7 @@ struct bio *bio_map_user_iov(struct request_queue *q, int ret, offset; struct iov_iter i; struct iovec iov; + struct bio_vec *bvec; iov_for_each(iov, i, *iter) { unsigned long uaddr = (unsigned long) iov.iov_base; @@ -1375,7 +1376,12 @@ struct bio *bio_map_user_iov(struct request_queue *q, ret = get_user_pages_fast(uaddr, local_nr_pages, (iter->type & WRITE) != WRITE, &pages[cur_page]); - if (ret < local_nr_pages) { + if (unlikely(ret < local_nr_pages)) { + for (j = cur_page; j < page_limit; j++) { + if (!pages[j]) + break; + put_page(pages[j]); + } ret = -EFAULT; goto out_unmap; } @@ -1383,6 +1389,7 @@ struct bio *bio_map_user_iov(struct request_queue *q, offset = offset_in_page(uaddr); for (j = cur_page; j < page_limit; j++) { unsigned int bytes = PAGE_SIZE - offset; + unsigned short prev_bi_vcnt = bio->bi_vcnt; if (len <= 0) break; @@ -1397,6 +1404,13 @@ struct bio *bio_map_user_iov(struct request_queue *q, bytes) break; + /* + * check if vector was merged with previous + * drop page reference if needed + */ + if (bio->bi_vcnt == prev_bi_vcnt) + put_page(pages[j]); + len -= bytes; offset = 0; } @@ -1423,10 +1437,8 @@ struct bio *bio_map_user_iov(struct request_queue *q, return bio; out_unmap: - for (j = 0; j < nr_pages; j++) { - if (!pages[j]) - break; - put_page(pages[j]); + bio_for_each_segment_all(bvec, bio, j) { + put_page(bvec->bv_page); } out: kfree(pages); diff --git a/kernel/crypto/shash.c b/kernel/crypto/shash.c index 5e31c8d77..325a14da5 100644 --- a/kernel/crypto/shash.c +++ b/kernel/crypto/shash.c @@ -41,7 +41,7 @@ static int shash_setkey_unaligned(struct crypto_shash *tfm, const u8 *key, int err; absize = keylen + (alignmask & ~(crypto_tfm_ctx_alignment() - 1)); - buffer = kmalloc(absize, GFP_KERNEL); + buffer = kmalloc(absize, GFP_ATOMIC); if (!buffer) return -ENOMEM; @@ -275,12 +275,14 @@ static int shash_async_finup(struct ahash_request *req) int shash_ahash_digest(struct ahash_request *req, struct shash_desc *desc) { - struct scatterlist *sg = req->src; - unsigned int offset = sg->offset; unsigned int nbytes = req->nbytes; + struct scatterlist *sg; + unsigned int offset; int err; - if (nbytes < min(sg->length, ((unsigned int)(PAGE_SIZE)) - offset)) { + if (nbytes && + (sg = req->src, offset = sg->offset, + nbytes < min(sg->length, ((unsigned int)(PAGE_SIZE)) - offset))) { void *data; data = kmap_atomic(sg_page(sg)); diff --git a/kernel/crypto/skcipher.c b/kernel/crypto/skcipher.c index 4faa0fd53..d5692e35f 100644 --- a/kernel/crypto/skcipher.c +++ b/kernel/crypto/skcipher.c @@ -426,14 +426,9 @@ static int skcipher_copy_iv(struct skcipher_walk *walk) static int skcipher_walk_first(struct skcipher_walk *walk) { - walk->nbytes = 0; - if (WARN_ON_ONCE(in_irq())) return -EDEADLK; - if (unlikely(!walk->total)) - return 0; - walk->buffer = NULL; if (unlikely(((unsigned long)walk->iv & walk->alignmask))) { int err = skcipher_copy_iv(walk); @@ -452,10 +447,15 @@ static int skcipher_walk_skcipher(struct skcipher_walk *walk, { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + walk->total = req->cryptlen; + walk->nbytes = 0; + + if (unlikely(!walk->total)) + return 0; + scatterwalk_start(&walk->in, req->src); scatterwalk_start(&walk->out, req->dst); - walk->total = req->cryptlen; walk->iv = req->iv; walk->oiv = req->iv; @@ -509,6 +509,11 @@ static int skcipher_walk_aead_common(struct skcipher_walk *walk, struct crypto_aead *tfm = crypto_aead_reqtfm(req); int err; + walk->nbytes = 0; + + if (unlikely(!walk->total)) + return 0; + walk->flags &= ~SKCIPHER_WALK_PHYS; scatterwalk_start(&walk->in, req->src); diff --git a/kernel/crypto/xts.c b/kernel/crypto/xts.c index d86c11a8c..e31828ed0 100644 --- a/kernel/crypto/xts.c +++ b/kernel/crypto/xts.c @@ -554,8 +554,10 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb) ctx->name[len - 1] = 0; if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME, - "xts(%s)", ctx->name) >= CRYPTO_MAX_ALG_NAME) - return -ENAMETOOLONG; + "xts(%s)", ctx->name) >= CRYPTO_MAX_ALG_NAME) { + err = -ENAMETOOLONG; + goto err_drop_spawn; + } } else goto err_drop_spawn; diff --git a/kernel/drivers/acpi/property.c b/kernel/drivers/acpi/property.c index 3fb8ff513..e26ea209b 100644 --- a/kernel/drivers/acpi/property.c +++ b/kernel/drivers/acpi/property.c @@ -571,10 +571,9 @@ static int acpi_data_get_property_array(const struct acpi_device_data *data, * } * } * - * Calling this function with index %2 return %-ENOENT and with index %3 - * returns the last entry. If the property does not contain any more values - * %-ENODATA is returned. The NULL entry must be single integer and - * preferably contain value %0. + * Calling this function with index %2 or index %3 return %-ENOENT. If the + * property does not contain any more values %-ENOENT is returned. The NULL + * entry must be single integer and preferably contain value %0. * * Return: %0 on success, negative error code on failure. */ @@ -590,11 +589,11 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, data = acpi_device_data_of_node(fwnode); if (!data) - return -EINVAL; + return -ENOENT; ret = acpi_data_get_property(data, propname, ACPI_TYPE_ANY, &obj); if (ret) - return ret; + return ret == -EINVAL ? -ENOENT : -EINVAL; /* * The simplest case is when the value is a single reference. Just @@ -606,7 +605,7 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, ret = acpi_bus_get_device(obj->reference.handle, &device); if (ret) - return ret; + return ret == -ENODEV ? -EINVAL : ret; args->adev = device; args->nargs = 0; @@ -622,8 +621,10 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, * The index argument is then used to determine which reference * the caller wants (along with the arguments). */ - if (obj->type != ACPI_TYPE_PACKAGE || index >= obj->package.count) - return -EPROTO; + if (obj->type != ACPI_TYPE_PACKAGE) + return -EINVAL; + if (index >= obj->package.count) + return -ENOENT; element = obj->package.elements; end = element + obj->package.count; @@ -635,7 +636,7 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, ret = acpi_bus_get_device(element->reference.handle, &device); if (ret) - return -ENODEV; + return -EINVAL; nargs = 0; element++; @@ -649,11 +650,11 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, else if (type == ACPI_TYPE_LOCAL_REFERENCE) break; else - return -EPROTO; + return -EINVAL; } if (nargs > MAX_ACPI_REFERENCE_ARGS) - return -EPROTO; + return -EINVAL; if (idx == index) { args->adev = device; @@ -670,13 +671,13 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, return -ENOENT; element++; } else { - return -EPROTO; + return -EINVAL; } idx++; } - return -ENODATA; + return -ENOENT; } EXPORT_SYMBOL_GPL(__acpi_node_get_property_reference); diff --git a/kernel/drivers/android/binder.c b/kernel/drivers/android/binder.c index ab34239a7..0621a95b8 100644 --- a/kernel/drivers/android/binder.c +++ b/kernel/drivers/android/binder.c @@ -2582,6 +2582,48 @@ static bool binder_proc_transaction(struct binder_transaction *t, return true; } +/** + * binder_get_node_refs_for_txn() - Get required refs on node for txn + * @node: struct binder_node for which to get refs + * @proc: returns @node->proc if valid + * @error: if no @proc then returns BR_DEAD_REPLY + * + * User-space normally keeps the node alive when creating a transaction + * since it has a reference to the target. The local strong ref keeps it + * alive if the sending process dies before the target process processes + * the transaction. If the source process is malicious or has a reference + * counting bug, relying on the local strong ref can fail. + * + * Since user-space can cause the local strong ref to go away, we also take + * a tmpref on the node to ensure it survives while we are constructing + * the transaction. We also need a tmpref on the proc while we are + * constructing the transaction, so we take that here as well. + * + * Return: The target_node with refs taken or NULL if no @node->proc is NULL. + * Also sets @proc if valid. If the @node->proc is NULL indicating that the + * target proc has died, @error is set to BR_DEAD_REPLY + */ +static struct binder_node *binder_get_node_refs_for_txn( + struct binder_node *node, + struct binder_proc **procp, + uint32_t *error) +{ + struct binder_node *target_node = NULL; + + binder_node_inner_lock(node); + if (node->proc) { + target_node = node; + binder_inc_node_nilocked(node, 1, 0, NULL); + binder_inc_node_tmpref_ilocked(node); + node->proc->tmp_ref++; + *procp = node->proc; + } else + *error = BR_DEAD_REPLY; + binder_node_inner_unlock(node); + + return target_node; +} + static void binder_transaction(struct binder_proc *proc, struct binder_thread *thread, struct binder_transaction_data *tr, int reply, @@ -2685,43 +2727,35 @@ static void binder_transaction(struct binder_proc *proc, ref = binder_get_ref_olocked(proc, tr->target.handle, true); if (ref) { - binder_inc_node(ref->node, 1, 0, NULL); - target_node = ref->node; + target_node = binder_get_node_refs_for_txn( + ref->node, &target_proc, + &return_error); + } else { + binder_user_error("%d:%d got transaction to invalid handle\n", + proc->pid, thread->pid); + return_error = BR_FAILED_REPLY; } binder_proc_unlock(proc); - if (target_node == NULL) { - binder_user_error("%d:%d got transaction to invalid handle\n", - proc->pid, thread->pid); - return_error = BR_FAILED_REPLY; - return_error_param = -EINVAL; - return_error_line = __LINE__; - goto err_invalid_target_handle; - } } else { mutex_lock(&context->context_mgr_node_lock); target_node = context->binder_context_mgr_node; - if (target_node == NULL) { + if (target_node) + target_node = binder_get_node_refs_for_txn( + target_node, &target_proc, + &return_error); + else return_error = BR_DEAD_REPLY; - mutex_unlock(&context->context_mgr_node_lock); - return_error_line = __LINE__; - goto err_no_context_mgr_node; - } - binder_inc_node(target_node, 1, 0, NULL); mutex_unlock(&context->context_mgr_node_lock); } - e->to_node = target_node->debug_id; - binder_node_lock(target_node); - target_proc = target_node->proc; - if (target_proc == NULL) { - binder_node_unlock(target_node); - return_error = BR_DEAD_REPLY; + if (!target_node) { + /* + * return_error is set above + */ + return_error_param = -EINVAL; return_error_line = __LINE__; goto err_dead_binder; } - binder_inner_proc_lock(target_proc); - target_proc->tmp_ref++; - binder_inner_proc_unlock(target_proc); - binder_node_unlock(target_node); + e->to_node = target_node->debug_id; if (security_binder_transaction(proc->tsk, target_proc->tsk) < 0) { return_error = BR_FAILED_REPLY; @@ -3071,6 +3105,8 @@ static void binder_transaction(struct binder_proc *proc, if (target_thread) binder_thread_dec_tmpref(target_thread); binder_proc_dec_tmpref(target_proc); + if (target_node) + binder_dec_node_tmpref(target_node); /* * write barrier to synchronize with initialization * of log entry @@ -3090,6 +3126,8 @@ err_bad_parent: err_copy_data_failed: trace_binder_transaction_failed_buffer_release(t->buffer); binder_transaction_buffer_release(target_proc, t->buffer, offp); + if (target_node) + binder_dec_node_tmpref(target_node); target_node = NULL; t->buffer->transaction = NULL; binder_alloc_free_buf(&target_proc->alloc, t->buffer); @@ -3104,13 +3142,14 @@ err_bad_call_stack: err_empty_call_stack: err_dead_binder: err_invalid_target_handle: -err_no_context_mgr_node: if (target_thread) binder_thread_dec_tmpref(target_thread); if (target_proc) binder_proc_dec_tmpref(target_proc); - if (target_node) + if (target_node) { binder_dec_node(target_node, 1, 0); + binder_dec_node_tmpref(target_node); + } binder_debug(BINDER_DEBUG_FAILED_TRANSACTION, "%d:%d transaction failed %d/%d, size %lld-%lld line %d\n", diff --git a/kernel/drivers/base/node.c b/kernel/drivers/base/node.c index 3855902f2..aae2402f3 100644 --- a/kernel/drivers/base/node.c +++ b/kernel/drivers/base/node.c @@ -27,13 +27,21 @@ static struct bus_type node_subsys = { static ssize_t node_read_cpumap(struct device *dev, bool list, char *buf) { + ssize_t n; + cpumask_var_t mask; struct node *node_dev = to_node(dev); - const struct cpumask *mask = cpumask_of_node(node_dev->dev.id); /* 2008/04/07: buf currently PAGE_SIZE, need 9 chars per 32 bits. */ BUILD_BUG_ON((NR_CPUS/32 * 9) > (PAGE_SIZE-1)); - return cpumap_print_to_pagebuf(list, buf, mask); + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return 0; + + cpumask_and(mask, cpumask_of_node(node_dev->dev.id), cpu_online_mask); + n = cpumap_print_to_pagebuf(list, buf, mask); + free_cpumask_var(mask); + + return n; } static inline ssize_t node_read_cpumask(struct device *dev, diff --git a/kernel/drivers/base/property.c b/kernel/drivers/base/property.c index d0b65bbe7..7ed99c1b2 100644 --- a/kernel/drivers/base/property.c +++ b/kernel/drivers/base/property.c @@ -21,6 +21,7 @@ #include struct property_set { + struct device *dev; struct fwnode_handle fwnode; const struct property_entry *properties; }; @@ -682,6 +683,10 @@ EXPORT_SYMBOL_GPL(fwnode_property_match_string); * Caller is responsible to call fwnode_handle_put() on the returned * args->fwnode pointer. * + * Returns: %0 on success + * %-ENOENT when the index is out of bounds, the index has an empty + * reference or the property was not found + * %-EINVAL on parse error */ int fwnode_property_get_reference_args(const struct fwnode_handle *fwnode, const char *prop, const char *nargs_prop, @@ -891,6 +896,7 @@ static struct property_set *pset_copy_set(const struct property_set *pset) void device_remove_properties(struct device *dev) { struct fwnode_handle *fwnode; + struct property_set *pset; fwnode = dev_fwnode(dev); if (!fwnode) @@ -900,16 +906,16 @@ void device_remove_properties(struct device *dev) * the pset. If there is no real firmware node (ACPI/DT) primary * will hold the pset. */ - if (is_pset_node(fwnode)) { + pset = to_pset_node(fwnode); + if (pset) { set_primary_fwnode(dev, NULL); - pset_free_set(to_pset_node(fwnode)); } else { - fwnode = fwnode->secondary; - if (!IS_ERR(fwnode) && is_pset_node(fwnode)) { + pset = to_pset_node(fwnode->secondary); + if (pset && dev == pset->dev) set_secondary_fwnode(dev, NULL); - pset_free_set(to_pset_node(fwnode)); - } } + if (pset && dev == pset->dev) + pset_free_set(pset); } EXPORT_SYMBOL_GPL(device_remove_properties); @@ -938,6 +944,7 @@ int device_add_properties(struct device *dev, p->fwnode.ops = &pset_fwnode_ops; set_secondary_fwnode(dev, &p->fwnode); + p->dev = dev; return 0; } EXPORT_SYMBOL_GPL(device_add_properties); diff --git a/kernel/drivers/crypto/axis/artpec6_crypto.c b/kernel/drivers/crypto/axis/artpec6_crypto.c index d9fbbf010..0f9754e07 100644 --- a/kernel/drivers/crypto/axis/artpec6_crypto.c +++ b/kernel/drivers/crypto/axis/artpec6_crypto.c @@ -349,8 +349,6 @@ struct artpec6_crypto_aead_req_ctx { /* The crypto framework makes it hard to avoid this global. */ static struct device *artpec6_crypto_dev; -static struct dentry *dbgfs_root; - #ifdef CONFIG_FAULT_INJECTION static DECLARE_FAULT_ATTR(artpec6_crypto_fail_status_read); static DECLARE_FAULT_ATTR(artpec6_crypto_fail_dma_array_full); @@ -2984,6 +2982,8 @@ struct dbgfs_u32 { char *desc; }; +static struct dentry *dbgfs_root; + static void artpec6_crypto_init_debugfs(void) { dbgfs_root = debugfs_create_dir("artpec6_crypto", NULL); diff --git a/kernel/drivers/crypto/stm32/stm32-hash.c b/kernel/drivers/crypto/stm32/stm32-hash.c index b585ce54a..4835dd4a9 100644 --- a/kernel/drivers/crypto/stm32/stm32-hash.c +++ b/kernel/drivers/crypto/stm32/stm32-hash.c @@ -553,9 +553,9 @@ static int stm32_hash_dma_send(struct stm32_hash_dev *hdev) { struct stm32_hash_request_ctx *rctx = ahash_request_ctx(hdev->req); struct scatterlist sg[1], *tsg; - int err = 0, len = 0, reg, ncp; + int err = 0, len = 0, reg, ncp = 0; unsigned int i; - const u32 *buffer = (const u32 *)rctx->buffer; + u32 *buffer = (void *)rctx->buffer; rctx->sg = hdev->req->src; rctx->total = hdev->req->nbytes; @@ -620,10 +620,13 @@ static int stm32_hash_dma_send(struct stm32_hash_dev *hdev) reg |= HASH_CR_DMAA; stm32_hash_write(hdev, HASH_CR, reg); - for (i = 0; i < DIV_ROUND_UP(ncp, sizeof(u32)); i++) - stm32_hash_write(hdev, HASH_DIN, buffer[i]); - - stm32_hash_set_nblw(hdev, ncp); + if (ncp) { + memset(buffer + ncp, 0, + DIV_ROUND_UP(ncp, sizeof(u32)) - ncp); + writesl(hdev->io_base + HASH_DIN, buffer, + DIV_ROUND_UP(ncp, sizeof(u32))); + } + stm32_hash_set_nblw(hdev, DIV_ROUND_UP(ncp, sizeof(u32))); reg = stm32_hash_read(hdev, HASH_STR); reg |= HASH_STR_DCAL; stm32_hash_write(hdev, HASH_STR, reg); diff --git a/kernel/drivers/dma-buf/sync_file.c b/kernel/drivers/dma-buf/sync_file.c index 66fb40d0e..03830634e 100644 --- a/kernel/drivers/dma-buf/sync_file.c +++ b/kernel/drivers/dma-buf/sync_file.c @@ -383,7 +383,7 @@ err_put_fd: return err; } -static void sync_fill_fence_info(struct dma_fence *fence, +static int sync_fill_fence_info(struct dma_fence *fence, struct sync_fence_info *info) { strlcpy(info->obj_name, fence->ops->get_timeline_name(fence), @@ -399,6 +399,8 @@ static void sync_fill_fence_info(struct dma_fence *fence, test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags) ? ktime_to_ns(fence->timestamp) : ktime_set(0, 0); + + return info->status; } static long sync_file_ioctl_fence_info(struct sync_file *sync_file, @@ -424,8 +426,12 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, * sync_fence_info and return the actual number of fences on * info->num_fences. */ - if (!info.num_fences) + if (!info.num_fences) { + info.status = dma_fence_is_signaled(sync_file->fence); goto no_fences; + } else { + info.status = 1; + } if (info.num_fences < num_fences) return -EINVAL; @@ -435,8 +441,10 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, if (!fence_info) return -ENOMEM; - for (i = 0; i < num_fences; i++) - sync_fill_fence_info(fences[i], &fence_info[i]); + for (i = 0; i < num_fences; i++) { + int status = sync_fill_fence_info(fences[i], &fence_info[i]); + info.status = info.status <= 0 ? info.status : status; + } if (copy_to_user(u64_to_user_ptr(info.sync_fence_info), fence_info, size)) { @@ -446,7 +454,6 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, no_fences: sync_file_get_name(sync_file, info.name, sizeof(info.name)); - info.status = dma_fence_is_signaled(sync_file->fence); info.num_fences = num_fences; if (copy_to_user((void __user *)arg, &info, sizeof(info))) diff --git a/kernel/drivers/dma/altera-msgdma.c b/kernel/drivers/dma/altera-msgdma.c index 32905d560..339186f25 100644 --- a/kernel/drivers/dma/altera-msgdma.c +++ b/kernel/drivers/dma/altera-msgdma.c @@ -212,11 +212,12 @@ struct msgdma_device { static struct msgdma_sw_desc *msgdma_get_descriptor(struct msgdma_device *mdev) { struct msgdma_sw_desc *desc; + unsigned long flags; - spin_lock_bh(&mdev->lock); + spin_lock_irqsave(&mdev->lock, flags); desc = list_first_entry(&mdev->free_list, struct msgdma_sw_desc, node); list_del(&desc->node); - spin_unlock_bh(&mdev->lock); + spin_unlock_irqrestore(&mdev->lock, flags); INIT_LIST_HEAD(&desc->tx_list); @@ -306,13 +307,14 @@ static dma_cookie_t msgdma_tx_submit(struct dma_async_tx_descriptor *tx) struct msgdma_device *mdev = to_mdev(tx->chan); struct msgdma_sw_desc *new; dma_cookie_t cookie; + unsigned long flags; new = tx_to_desc(tx); - spin_lock_bh(&mdev->lock); + spin_lock_irqsave(&mdev->lock, flags); cookie = dma_cookie_assign(tx); list_add_tail(&new->node, &mdev->pending_list); - spin_unlock_bh(&mdev->lock); + spin_unlock_irqrestore(&mdev->lock, flags); return cookie; } @@ -336,17 +338,18 @@ msgdma_prep_memcpy(struct dma_chan *dchan, dma_addr_t dma_dst, struct msgdma_extended_desc *desc; size_t copy; u32 desc_cnt; + unsigned long irqflags; desc_cnt = DIV_ROUND_UP(len, MSGDMA_MAX_TRANS_LEN); - spin_lock_bh(&mdev->lock); + spin_lock_irqsave(&mdev->lock, irqflags); if (desc_cnt > mdev->desc_free_cnt) { spin_unlock_bh(&mdev->lock); dev_dbg(mdev->dev, "mdev %p descs are not available\n", mdev); return NULL; } mdev->desc_free_cnt -= desc_cnt; - spin_unlock_bh(&mdev->lock); + spin_unlock_irqrestore(&mdev->lock, irqflags); do { /* Allocate and populate the descriptor */ @@ -397,18 +400,19 @@ msgdma_prep_slave_sg(struct dma_chan *dchan, struct scatterlist *sgl, u32 desc_cnt = 0, i; struct scatterlist *sg; u32 stride; + unsigned long irqflags; for_each_sg(sgl, sg, sg_len, i) desc_cnt += DIV_ROUND_UP(sg_dma_len(sg), MSGDMA_MAX_TRANS_LEN); - spin_lock_bh(&mdev->lock); + spin_lock_irqsave(&mdev->lock, irqflags); if (desc_cnt > mdev->desc_free_cnt) { spin_unlock_bh(&mdev->lock); dev_dbg(mdev->dev, "mdev %p descs are not available\n", mdev); return NULL; } mdev->desc_free_cnt -= desc_cnt; - spin_unlock_bh(&mdev->lock); + spin_unlock_irqrestore(&mdev->lock, irqflags); avail = sg_dma_len(sgl); @@ -566,10 +570,11 @@ static void msgdma_start_transfer(struct msgdma_device *mdev) static void msgdma_issue_pending(struct dma_chan *chan) { struct msgdma_device *mdev = to_mdev(chan); + unsigned long flags; - spin_lock_bh(&mdev->lock); + spin_lock_irqsave(&mdev->lock, flags); msgdma_start_transfer(mdev); - spin_unlock_bh(&mdev->lock); + spin_unlock_irqrestore(&mdev->lock, flags); } /** @@ -634,10 +639,11 @@ static void msgdma_free_descriptors(struct msgdma_device *mdev) static void msgdma_free_chan_resources(struct dma_chan *dchan) { struct msgdma_device *mdev = to_mdev(dchan); + unsigned long flags; - spin_lock_bh(&mdev->lock); + spin_lock_irqsave(&mdev->lock, flags); msgdma_free_descriptors(mdev); - spin_unlock_bh(&mdev->lock); + spin_unlock_irqrestore(&mdev->lock, flags); kfree(mdev->sw_desq); } @@ -682,8 +688,9 @@ static void msgdma_tasklet(unsigned long data) u32 count; u32 __maybe_unused size; u32 __maybe_unused status; + unsigned long flags; - spin_lock(&mdev->lock); + spin_lock_irqsave(&mdev->lock, flags); /* Read number of responses that are available */ count = ioread32(mdev->csr + MSGDMA_CSR_RESP_FILL_LEVEL); @@ -698,13 +705,13 @@ static void msgdma_tasklet(unsigned long data) * bits. So we need to just drop these values. */ size = ioread32(mdev->resp + MSGDMA_RESP_BYTES_TRANSFERRED); - status = ioread32(mdev->resp - MSGDMA_RESP_STATUS); + status = ioread32(mdev->resp + MSGDMA_RESP_STATUS); msgdma_complete_descriptor(mdev); msgdma_chan_desc_cleanup(mdev); } - spin_unlock(&mdev->lock); + spin_unlock_irqrestore(&mdev->lock, flags); } /** diff --git a/kernel/drivers/dma/edma.c b/kernel/drivers/dma/edma.c index 3879f80a4..a7ea20e7b 100644 --- a/kernel/drivers/dma/edma.c +++ b/kernel/drivers/dma/edma.c @@ -1143,11 +1143,24 @@ static struct dma_async_tx_descriptor *edma_prep_dma_memcpy( struct edma_desc *edesc; struct device *dev = chan->device->dev; struct edma_chan *echan = to_edma_chan(chan); - unsigned int width, pset_len; + unsigned int width, pset_len, array_size; if (unlikely(!echan || !len)) return NULL; + /* Align the array size (acnt block) with the transfer properties */ + switch (__ffs((src | dest | len))) { + case 0: + array_size = SZ_32K - 1; + break; + case 1: + array_size = SZ_32K - 2; + break; + default: + array_size = SZ_32K - 4; + break; + } + if (len < SZ_64K) { /* * Transfer size less than 64K can be handled with one paRAM @@ -1169,7 +1182,7 @@ static struct dma_async_tx_descriptor *edma_prep_dma_memcpy( * When the full_length is multibple of 32767 one slot can be * used to complete the transfer. */ - width = SZ_32K - 1; + width = array_size; pset_len = rounddown(len, width); /* One slot is enough for lengths multiple of (SZ_32K -1) */ if (unlikely(pset_len == len)) @@ -1217,7 +1230,7 @@ static struct dma_async_tx_descriptor *edma_prep_dma_memcpy( } dest += pset_len; src += pset_len; - pset_len = width = len % (SZ_32K - 1); + pset_len = width = len % array_size; ret = edma_config_pset(chan, &edesc->pset[1], src, dest, 1, width, pset_len, DMA_MEM_TO_MEM); diff --git a/kernel/drivers/dma/ti-dma-crossbar.c b/kernel/drivers/dma/ti-dma-crossbar.c index 2f65a8fde..f1d04b70e 100644 --- a/kernel/drivers/dma/ti-dma-crossbar.c +++ b/kernel/drivers/dma/ti-dma-crossbar.c @@ -262,13 +262,14 @@ static void *ti_dra7_xbar_route_allocate(struct of_phandle_args *dma_spec, mutex_lock(&xbar->mutex); map->xbar_out = find_first_zero_bit(xbar->dma_inuse, xbar->dma_requests); - mutex_unlock(&xbar->mutex); if (map->xbar_out == xbar->dma_requests) { + mutex_unlock(&xbar->mutex); dev_err(&pdev->dev, "Run out of free DMA requests\n"); kfree(map); return ERR_PTR(-ENOMEM); } set_bit(map->xbar_out, xbar->dma_inuse); + mutex_unlock(&xbar->mutex); map->xbar_in = (u16)dma_spec->args[0]; diff --git a/kernel/drivers/gpio/Kconfig b/kernel/drivers/gpio/Kconfig index 3388d54ba..3f80f167e 100644 --- a/kernel/drivers/gpio/Kconfig +++ b/kernel/drivers/gpio/Kconfig @@ -453,7 +453,8 @@ config GPIO_TS4800 config GPIO_THUNDERX tristate "Cavium ThunderX/OCTEON-TX GPIO" depends on ARCH_THUNDER || (64BIT && COMPILE_TEST) - depends on PCI_MSI && IRQ_DOMAIN_HIERARCHY + depends on PCI_MSI + select IRQ_DOMAIN_HIERARCHY select IRQ_FASTEOI_HIERARCHY_HANDLERS help Say yes here to support the on-chip GPIO lines on the ThunderX diff --git a/kernel/drivers/gpio/gpio-omap.c b/kernel/drivers/gpio/gpio-omap.c index dbf869fb6..3233b72b6 100644 --- a/kernel/drivers/gpio/gpio-omap.c +++ b/kernel/drivers/gpio/gpio-omap.c @@ -518,7 +518,13 @@ static int omap_gpio_irq_type(struct irq_data *d, unsigned type) if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH)) irq_set_handler_locked(d, handle_level_irq); else if (type & (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING)) - irq_set_handler_locked(d, handle_edge_irq); + /* + * Edge IRQs are already cleared/acked in irq_handler and + * not need to be masked, as result handle_edge_irq() + * logic is excessed here and may cause lose of interrupts. + * So just use handle_simple_irq. + */ + irq_set_handler_locked(d, handle_simple_irq); return 0; @@ -678,7 +684,7 @@ static void omap_gpio_free(struct gpio_chip *chip, unsigned offset) static irqreturn_t omap_gpio_irq_handler(int irq, void *gpiobank) { void __iomem *isr_reg = NULL; - u32 isr; + u32 enabled, isr, level_mask; unsigned int bit; struct gpio_bank *bank = gpiobank; unsigned long wa_lock_flags; @@ -691,23 +697,21 @@ static irqreturn_t omap_gpio_irq_handler(int irq, void *gpiobank) pm_runtime_get_sync(bank->chip.parent); while (1) { - u32 isr_saved, level_mask = 0; - u32 enabled; - raw_spin_lock_irqsave(&bank->lock, lock_flags); enabled = omap_get_gpio_irqbank_mask(bank); - isr_saved = isr = readl_relaxed(isr_reg) & enabled; + isr = readl_relaxed(isr_reg) & enabled; if (bank->level_mask) level_mask = bank->level_mask & enabled; + else + level_mask = 0; /* clear edge sensitive interrupts before handler(s) are called so that we don't miss any interrupt occurred while executing them */ - omap_disable_gpio_irqbank(bank, isr_saved & ~level_mask); - omap_clear_gpio_irqbank(bank, isr_saved & ~level_mask); - omap_enable_gpio_irqbank(bank, isr_saved & ~level_mask); + if (isr & ~level_mask) + omap_clear_gpio_irqbank(bank, isr & ~level_mask); raw_spin_unlock_irqrestore(&bank->lock, lock_flags); @@ -1010,7 +1014,7 @@ static void omap_gpio_set(struct gpio_chip *chip, unsigned offset, int value) /*---------------------------------------------------------------------*/ -static void __init omap_gpio_show_rev(struct gpio_bank *bank) +static void omap_gpio_show_rev(struct gpio_bank *bank) { static bool called; u32 rev; diff --git a/kernel/drivers/gpio/gpiolib-acpi.c b/kernel/drivers/gpio/gpiolib-acpi.c index 4d2113530..eb4528c87 100644 --- a/kernel/drivers/gpio/gpiolib-acpi.c +++ b/kernel/drivers/gpio/gpiolib-acpi.c @@ -203,7 +203,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, if (pin <= 255) { char ev_name[5]; - sprintf(ev_name, "_%c%02X", + sprintf(ev_name, "_%c%02hhX", agpio->triggering == ACPI_EDGE_SENSITIVE ? 'E' : 'L', pin); if (ACPI_SUCCESS(acpi_get_handle(handle, ev_name, &evt_handle))) diff --git a/kernel/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/kernel/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 7ef6c28a3..bc7461319 100644 --- a/kernel/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/kernel/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -834,7 +834,7 @@ int amdgpu_ttm_bind(struct ttm_buffer_object *bo, struct ttm_mem_reg *bo_mem) placement.busy_placement = &placements; placements.fpfn = 0; placements.lpfn = adev->mc.gart_size >> PAGE_SHIFT; - placements.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT; + placements.flags = bo->mem.placement | TTM_PL_FLAG_TT; r = ttm_bo_mem_space(bo, &placement, &tmp, true, false); if (unlikely(r)) diff --git a/kernel/drivers/gpu/drm/drm_atomic_helper.c b/kernel/drivers/gpu/drm/drm_atomic_helper.c index 4e53aae9a..0028591f3 100644 --- a/kernel/drivers/gpu/drm/drm_atomic_helper.c +++ b/kernel/drivers/gpu/drm/drm_atomic_helper.c @@ -2960,6 +2960,7 @@ out: drm_modeset_backoff(&ctx); } + drm_atomic_state_put(state); drm_modeset_drop_locks(&ctx); drm_modeset_acquire_fini(&ctx); diff --git a/kernel/drivers/gpu/drm/i915/i915_gem.c b/kernel/drivers/gpu/drm/i915/i915_gem.c index 19404c96e..af289d35b 100644 --- a/kernel/drivers/gpu/drm/i915/i915_gem.c +++ b/kernel/drivers/gpu/drm/i915/i915_gem.c @@ -3013,10 +3013,15 @@ void i915_gem_reset_finish(struct drm_i915_private *dev_priv) static void nop_submit_request(struct drm_i915_gem_request *request) { + unsigned long flags; + GEM_BUG_ON(!i915_terminally_wedged(&request->i915->gpu_error)); dma_fence_set_error(&request->fence, -EIO); - i915_gem_request_submit(request); + + spin_lock_irqsave(&request->engine->timeline->lock, flags); + __i915_gem_request_submit(request); intel_engine_init_global_seqno(request->engine, request->global_seqno); + spin_unlock_irqrestore(&request->engine->timeline->lock, flags); } static void engine_set_wedged(struct intel_engine_cs *engine) diff --git a/kernel/drivers/gpu/drm/i915/intel_bios.c b/kernel/drivers/gpu/drm/i915/intel_bios.c index 00c6aee0a..5d4cd3d00 100644 --- a/kernel/drivers/gpu/drm/i915/intel_bios.c +++ b/kernel/drivers/gpu/drm/i915/intel_bios.c @@ -1240,7 +1240,7 @@ static void parse_ddi_ports(struct drm_i915_private *dev_priv, { enum port port; - if (!HAS_DDI(dev_priv)) + if (!HAS_DDI(dev_priv) && !IS_CHERRYVIEW(dev_priv)) return; if (!dev_priv->vbt.child_dev_num) diff --git a/kernel/drivers/gpu/drm/i915/intel_color.c b/kernel/drivers/gpu/drm/i915/intel_color.c index ff9ecd211..b8315bca8 100644 --- a/kernel/drivers/gpu/drm/i915/intel_color.c +++ b/kernel/drivers/gpu/drm/i915/intel_color.c @@ -74,7 +74,7 @@ #define I9XX_CSC_COEFF_1_0 \ ((7 << 12) | I9XX_CSC_COEFF_FP(CTM_COEFF_1_0, 8)) -static bool crtc_state_is_legacy(struct drm_crtc_state *state) +static bool crtc_state_is_legacy_gamma(struct drm_crtc_state *state) { return !state->degamma_lut && !state->ctm && @@ -288,7 +288,7 @@ static void cherryview_load_csc_matrix(struct drm_crtc_state *state) } mode = (state->ctm ? CGM_PIPE_MODE_CSC : 0); - if (!crtc_state_is_legacy(state)) { + if (!crtc_state_is_legacy_gamma(state)) { mode |= (state->degamma_lut ? CGM_PIPE_MODE_DEGAMMA : 0) | (state->gamma_lut ? CGM_PIPE_MODE_GAMMA : 0); } @@ -469,7 +469,7 @@ static void broadwell_load_luts(struct drm_crtc_state *state) struct intel_crtc_state *intel_state = to_intel_crtc_state(state); enum pipe pipe = to_intel_crtc(state->crtc)->pipe; - if (crtc_state_is_legacy(state)) { + if (crtc_state_is_legacy_gamma(state)) { haswell_load_luts(state); return; } @@ -529,7 +529,7 @@ static void glk_load_luts(struct drm_crtc_state *state) glk_load_degamma_lut(state); - if (crtc_state_is_legacy(state)) { + if (crtc_state_is_legacy_gamma(state)) { haswell_load_luts(state); return; } @@ -551,7 +551,7 @@ static void cherryview_load_luts(struct drm_crtc_state *state) uint32_t i, lut_size; uint32_t word0, word1; - if (crtc_state_is_legacy(state)) { + if (crtc_state_is_legacy_gamma(state)) { /* Turn off degamma/gamma on CGM block. */ I915_WRITE(CGM_PIPE_MODE(pipe), (state->ctm ? CGM_PIPE_MODE_CSC : 0)); @@ -632,12 +632,10 @@ int intel_color_check(struct drm_crtc *crtc, return 0; /* - * We also allow no degamma lut and a gamma lut at the legacy + * We also allow no degamma lut/ctm and a gamma lut at the legacy * size (256 entries). */ - if (!crtc_state->degamma_lut && - crtc_state->gamma_lut && - crtc_state->gamma_lut->length == LEGACY_LUT_LENGTH) + if (crtc_state_is_legacy_gamma(crtc_state)) return 0; return -EINVAL; diff --git a/kernel/drivers/gpu/drm/i915/intel_display.c b/kernel/drivers/gpu/drm/i915/intel_display.c index 64f7b51ed..5c7828c52 100644 --- a/kernel/drivers/gpu/drm/i915/intel_display.c +++ b/kernel/drivers/gpu/drm/i915/intel_display.c @@ -10245,13 +10245,10 @@ struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev, { struct drm_i915_private *dev_priv = to_i915(dev); struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder; + enum transcoder cpu_transcoder; struct drm_display_mode *mode; struct intel_crtc_state *pipe_config; - int htot = I915_READ(HTOTAL(cpu_transcoder)); - int hsync = I915_READ(HSYNC(cpu_transcoder)); - int vtot = I915_READ(VTOTAL(cpu_transcoder)); - int vsync = I915_READ(VSYNC(cpu_transcoder)); + u32 htot, hsync, vtot, vsync; enum pipe pipe = intel_crtc->pipe; mode = kzalloc(sizeof(*mode), GFP_KERNEL); @@ -10279,6 +10276,13 @@ struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev, i9xx_crtc_clock_get(intel_crtc, pipe_config); mode->clock = pipe_config->port_clock / pipe_config->pixel_multiplier; + + cpu_transcoder = pipe_config->cpu_transcoder; + htot = I915_READ(HTOTAL(cpu_transcoder)); + hsync = I915_READ(HSYNC(cpu_transcoder)); + vtot = I915_READ(VTOTAL(cpu_transcoder)); + vsync = I915_READ(VSYNC(cpu_transcoder)); + mode->hdisplay = (htot & 0xffff) + 1; mode->htotal = ((htot & 0xffff0000) >> 16) + 1; mode->hsync_start = (hsync & 0xffff) + 1; diff --git a/kernel/drivers/gpu/drm/i915/intel_dp.c b/kernel/drivers/gpu/drm/i915/intel_dp.c index 64134947c..203198659 100644 --- a/kernel/drivers/gpu/drm/i915/intel_dp.c +++ b/kernel/drivers/gpu/drm/i915/intel_dp.c @@ -2307,8 +2307,8 @@ static void edp_panel_off(struct intel_dp *intel_dp) I915_WRITE(pp_ctrl_reg, pp); POSTING_READ(pp_ctrl_reg); - intel_dp->panel_power_off_time = ktime_get_boottime(); wait_panel_off(intel_dp); + intel_dp->panel_power_off_time = ktime_get_boottime(); /* We got a reference when we enabled the VDD. */ intel_display_power_put(dev_priv, intel_dp->aux_power_domain); @@ -5273,7 +5273,7 @@ intel_dp_init_panel_power_sequencer(struct drm_device *dev, * seems sufficient to avoid this problem. */ if (dev_priv->quirks & QUIRK_INCREASE_T12_DELAY) { - vbt.t11_t12 = max_t(u16, vbt.t11_t12, 900 * 10); + vbt.t11_t12 = max_t(u16, vbt.t11_t12, 1300 * 10); DRM_DEBUG_KMS("Increasing T12 panel delay as per the quirk to %d\n", vbt.t11_t12); } diff --git a/kernel/drivers/gpu/drm/i915/intel_runtime_pm.c b/kernel/drivers/gpu/drm/i915/intel_runtime_pm.c index b3a087cb0..49577eba8 100644 --- a/kernel/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/kernel/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -368,7 +368,7 @@ static void hsw_power_well_enable(struct drm_i915_private *dev_priv, { enum i915_power_well_id id = power_well->id; bool wait_fuses = power_well->hsw.has_fuses; - enum skl_power_gate pg; + enum skl_power_gate uninitialized_var(pg); u32 val; if (wait_fuses) { diff --git a/kernel/drivers/gpu/drm/msm/dsi/dsi_host.c b/kernel/drivers/gpu/drm/msm/dsi/dsi_host.c index dbb31a014..deaf86937 100644 --- a/kernel/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/kernel/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -248,7 +248,7 @@ disable_clks: clk_disable_unprepare(ahb_clk); disable_gdsc: regulator_disable(gdsc_reg); - pm_runtime_put_autosuspend(dev); + pm_runtime_put_sync(dev); put_clk: clk_put(ahb_clk); put_gdsc: diff --git a/kernel/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c b/kernel/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c index c2bdad884..824067d2d 100644 --- a/kernel/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c +++ b/kernel/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c @@ -83,6 +83,8 @@ const struct mdp5_cfg_hw msm8x74v1_config = { .caps = MDP_LM_CAP_WB }, }, .nb_stages = 5, + .max_width = 2048, + .max_height = 0xFFFF, }, .dspp = { .count = 3, diff --git a/kernel/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c b/kernel/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c index 6fcb58ab7..440977677 100644 --- a/kernel/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c +++ b/kernel/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c @@ -804,8 +804,6 @@ static int mdp5_crtc_cursor_set(struct drm_crtc *crtc, spin_unlock_irqrestore(&mdp5_crtc->cursor.lock, flags); - pm_runtime_put_autosuspend(&pdev->dev); - set_cursor: ret = mdp5_ctl_set_cursor(ctl, pipeline, 0, cursor_enable); if (ret) { diff --git a/kernel/drivers/gpu/drm/msm/msm_gem.c b/kernel/drivers/gpu/drm/msm/msm_gem.c index f15821a0d..ea5bb0e16 100644 --- a/kernel/drivers/gpu/drm/msm/msm_gem.c +++ b/kernel/drivers/gpu/drm/msm/msm_gem.c @@ -610,17 +610,6 @@ int msm_gem_sync_object(struct drm_gem_object *obj, struct dma_fence *fence; int i, ret; - if (!exclusive) { - /* NOTE: _reserve_shared() must happen before _add_shared_fence(), - * which makes this a slightly strange place to call it. OTOH this - * is a convenient can-fail point to hook it in. (And similar to - * how etnaviv and nouveau handle this.) - */ - ret = reservation_object_reserve_shared(msm_obj->resv); - if (ret) - return ret; - } - fobj = reservation_object_get_list(msm_obj->resv); if (!fobj || (fobj->shared_count == 0)) { fence = reservation_object_get_excl(msm_obj->resv); @@ -1045,10 +1034,10 @@ static void *_msm_gem_kernel_new(struct drm_device *dev, uint32_t size, } vaddr = msm_gem_get_vaddr(obj); - if (!vaddr) { + if (IS_ERR(vaddr)) { msm_gem_put_iova(obj, aspace); drm_gem_object_unreference(obj); - return ERR_PTR(-ENOMEM); + return ERR_CAST(vaddr); } if (bo) diff --git a/kernel/drivers/gpu/drm/msm/msm_gem_submit.c b/kernel/drivers/gpu/drm/msm/msm_gem_submit.c index 5d0a75d4b..93535cac0 100644 --- a/kernel/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/kernel/drivers/gpu/drm/msm/msm_gem_submit.c @@ -221,7 +221,7 @@ fail: return ret; } -static int submit_fence_sync(struct msm_gem_submit *submit) +static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit) { int i, ret = 0; @@ -229,6 +229,20 @@ static int submit_fence_sync(struct msm_gem_submit *submit) struct msm_gem_object *msm_obj = submit->bos[i].obj; bool write = submit->bos[i].flags & MSM_SUBMIT_BO_WRITE; + if (!write) { + /* NOTE: _reserve_shared() must happen before + * _add_shared_fence(), which makes this a slightly + * strange place to call it. OTOH this is a + * convenient can-fail point to hook it in. + */ + ret = reservation_object_reserve_shared(msm_obj->resv); + if (ret) + return ret; + } + + if (no_implicit) + continue; + ret = msm_gem_sync_object(&msm_obj->base, submit->gpu->fctx, write); if (ret) break; @@ -451,11 +465,9 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (ret) goto out; - if (!(args->flags & MSM_SUBMIT_NO_IMPLICIT)) { - ret = submit_fence_sync(submit); - if (ret) - goto out; - } + ret = submit_fence_sync(submit, !!(args->flags & MSM_SUBMIT_NO_IMPLICIT)); + if (ret) + goto out; ret = submit_pin_objects(submit); if (ret) diff --git a/kernel/drivers/gpu/drm/msm/msm_gpu.c b/kernel/drivers/gpu/drm/msm/msm_gpu.c index ffbff2760..6a887032c 100644 --- a/kernel/drivers/gpu/drm/msm/msm_gpu.c +++ b/kernel/drivers/gpu/drm/msm/msm_gpu.c @@ -718,7 +718,8 @@ void msm_gpu_cleanup(struct msm_gpu *gpu) msm_gem_put_iova(gpu->rb->bo, gpu->aspace); msm_ringbuffer_destroy(gpu->rb); } - if (gpu->aspace) { + + if (!IS_ERR_OR_NULL(gpu->aspace)) { gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu, NULL, 0); msm_gem_address_space_put(gpu->aspace); diff --git a/kernel/drivers/gpu/drm/msm/msm_rd.c b/kernel/drivers/gpu/drm/msm/msm_rd.c index 0366b8092..ec56794ad 100644 --- a/kernel/drivers/gpu/drm/msm/msm_rd.c +++ b/kernel/drivers/gpu/drm/msm/msm_rd.c @@ -111,10 +111,14 @@ static void rd_write(struct msm_rd_state *rd, const void *buf, int sz) wait_event(rd->fifo_event, circ_space(&rd->fifo) > 0); + /* Note that smp_load_acquire() is not strictly required + * as CIRC_SPACE_TO_END() does not access the tail more + * than once. + */ n = min(sz, circ_space_to_end(&rd->fifo)); memcpy(fptr, ptr, n); - fifo->head = (fifo->head + n) & (BUF_SZ - 1); + smp_store_release(&fifo->head, (fifo->head + n) & (BUF_SZ - 1)); sz -= n; ptr += n; @@ -145,13 +149,17 @@ static ssize_t rd_read(struct file *file, char __user *buf, if (ret) goto out; + /* Note that smp_load_acquire() is not strictly required + * as CIRC_CNT_TO_END() does not access the head more than + * once. + */ n = min_t(int, sz, circ_count_to_end(&rd->fifo)); if (copy_to_user(buf, fptr, n)) { ret = -EFAULT; goto out; } - fifo->tail = (fifo->tail + n) & (BUF_SZ - 1); + smp_store_release(&fifo->tail, (fifo->tail + n) & (BUF_SZ - 1)); *ppos += n; wake_up_all(&rd->fifo_event); diff --git a/kernel/drivers/gpu/ipu-v3/ipu-common.c b/kernel/drivers/gpu/ipu-v3/ipu-common.c index 6a573d21d..658fa2d3e 100644 --- a/kernel/drivers/gpu/ipu-v3/ipu-common.c +++ b/kernel/drivers/gpu/ipu-v3/ipu-common.c @@ -405,6 +405,14 @@ int ipu_idmac_lock_enable(struct ipuv3_channel *channel, int num_bursts) return -EINVAL; } + /* + * IPUv3EX / i.MX51 has a different register layout, and on IPUv3M / + * i.MX53 channel arbitration locking doesn't seem to work properly. + * Allow enabling the lock feature on IPUv3H / i.MX6 only. + */ + if (bursts && ipu->ipu_type != IPUV3H) + return -EINVAL; + for (i = 0; i < ARRAY_SIZE(idmac_lock_en_info); i++) { if (channel->num == idmac_lock_en_info[i].chnum) break; diff --git a/kernel/drivers/gpu/ipu-v3/ipu-pre.c b/kernel/drivers/gpu/ipu-v3/ipu-pre.c index c35f74c83..c860a7997 100644 --- a/kernel/drivers/gpu/ipu-v3/ipu-pre.c +++ b/kernel/drivers/gpu/ipu-v3/ipu-pre.c @@ -73,6 +73,14 @@ #define IPU_PRE_STORE_ENG_CTRL_WR_NUM_BYTES(v) ((v & 0x7) << 1) #define IPU_PRE_STORE_ENG_CTRL_OUTPUT_ACTIVE_BPP(v) ((v & 0x3) << 4) +#define IPU_PRE_STORE_ENG_STATUS 0x120 +#define IPU_PRE_STORE_ENG_STATUS_STORE_BLOCK_X_MASK 0xffff +#define IPU_PRE_STORE_ENG_STATUS_STORE_BLOCK_X_SHIFT 0 +#define IPU_PRE_STORE_ENG_STATUS_STORE_BLOCK_Y_MASK 0x3fff +#define IPU_PRE_STORE_ENG_STATUS_STORE_BLOCK_Y_SHIFT 16 +#define IPU_PRE_STORE_ENG_STATUS_STORE_FIFO_FULL (1 << 30) +#define IPU_PRE_STORE_ENG_STATUS_STORE_FIELD (1 << 31) + #define IPU_PRE_STORE_ENG_SIZE 0x130 #define IPU_PRE_STORE_ENG_SIZE_INPUT_WIDTH(v) ((v & 0xffff) << 0) #define IPU_PRE_STORE_ENG_SIZE_INPUT_HEIGHT(v) ((v & 0xffff) << 16) @@ -93,6 +101,7 @@ struct ipu_pre { dma_addr_t buffer_paddr; void *buffer_virt; bool in_use; + unsigned int safe_window_end; }; static DEFINE_MUTEX(ipu_pre_list_mutex); @@ -160,6 +169,9 @@ void ipu_pre_configure(struct ipu_pre *pre, unsigned int width, u32 active_bpp = info->cpp[0] >> 1; u32 val; + /* calculate safe window for ctrl register updates */ + pre->safe_window_end = height - 2; + writel(bufaddr, pre->regs + IPU_PRE_CUR_BUF); writel(bufaddr, pre->regs + IPU_PRE_NEXT_BUF); @@ -199,7 +211,24 @@ void ipu_pre_configure(struct ipu_pre *pre, unsigned int width, void ipu_pre_update(struct ipu_pre *pre, unsigned int bufaddr) { + unsigned long timeout = jiffies + msecs_to_jiffies(5); + unsigned short current_yblock; + u32 val; + writel(bufaddr, pre->regs + IPU_PRE_NEXT_BUF); + + do { + if (time_after(jiffies, timeout)) { + dev_warn(pre->dev, "timeout waiting for PRE safe window\n"); + return; + } + + val = readl(pre->regs + IPU_PRE_STORE_ENG_STATUS); + current_yblock = + (val >> IPU_PRE_STORE_ENG_STATUS_STORE_BLOCK_Y_SHIFT) & + IPU_PRE_STORE_ENG_STATUS_STORE_BLOCK_Y_MASK; + } while (current_yblock == 0 || current_yblock >= pre->safe_window_end); + writel(IPU_PRE_CTRL_SDW_UPDATE, pre->regs + IPU_PRE_CTRL_SET); } diff --git a/kernel/drivers/gpu/ipu-v3/ipu-prg.c b/kernel/drivers/gpu/ipu-v3/ipu-prg.c index ecc9ea44d..0013ca9f7 100644 --- a/kernel/drivers/gpu/ipu-v3/ipu-prg.c +++ b/kernel/drivers/gpu/ipu-v3/ipu-prg.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -329,6 +330,12 @@ int ipu_prg_channel_configure(struct ipuv3_channel *ipu_chan, val = IPU_PRG_REG_UPDATE_REG_UPDATE; writel(val, prg->regs + IPU_PRG_REG_UPDATE); + /* wait for both double buffers to be filled */ + readl_poll_timeout(prg->regs + IPU_PRG_STATUS, val, + (val & IPU_PRG_STATUS_BUFFER0_READY(prg_chan)) && + (val & IPU_PRG_STATUS_BUFFER1_READY(prg_chan)), + 5, 1000); + clk_disable_unprepare(prg->clk_ipg); chan->enabled = true; diff --git a/kernel/drivers/hid/Kconfig b/kernel/drivers/hid/Kconfig index 0a3117cc2..374301fcb 100644 --- a/kernel/drivers/hid/Kconfig +++ b/kernel/drivers/hid/Kconfig @@ -281,6 +281,7 @@ config HID_ELECOM Support for ELECOM devices: - BM084 Bluetooth Mouse - DEFT Trackball (Wired and wireless) + - HUGE Trackball (Wired and wireless) config HID_ELO tristate "ELO USB 4000/4500 touchscreen" diff --git a/kernel/drivers/hid/hid-core.c b/kernel/drivers/hid/hid-core.c index 9bc911608..330ca9838 100644 --- a/kernel/drivers/hid/hid-core.c +++ b/kernel/drivers/hid/hid-core.c @@ -2032,6 +2032,8 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_BM084) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_DEFT_WIRED) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_DEFT_WIRELESS) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_HUGE_WIRED) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_HUGE_WIRELESS) }, #endif #if IS_ENABLED(CONFIG_HID_ELO) { HID_USB_DEVICE(USB_VENDOR_ID_ELO, 0x0009) }, diff --git a/kernel/drivers/hid/hid-elecom.c b/kernel/drivers/hid/hid-elecom.c index e2c7465df..54aeea57d 100644 --- a/kernel/drivers/hid/hid-elecom.c +++ b/kernel/drivers/hid/hid-elecom.c @@ -3,6 +3,7 @@ * Copyright (c) 2010 Richard Nauber * Copyright (c) 2016 Yuxuan Shui * Copyright (c) 2017 Diego Elio Pettenò + * Copyright (c) 2017 Alex Manoussakis */ /* @@ -32,9 +33,11 @@ static __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc, break; case USB_DEVICE_ID_ELECOM_DEFT_WIRED: case USB_DEVICE_ID_ELECOM_DEFT_WIRELESS: - /* The DEFT trackball has eight buttons, but its descriptor only - * reports five, disabling the three Fn buttons on the top of - * the mouse. + case USB_DEVICE_ID_ELECOM_HUGE_WIRED: + case USB_DEVICE_ID_ELECOM_HUGE_WIRELESS: + /* The DEFT/HUGE trackball has eight buttons, but its descriptor + * only reports five, disabling the three Fn buttons on the top + * of the mouse. * * Apply the following diff to the descriptor: * @@ -62,7 +65,7 @@ static __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc, * End Collection, End Collection, */ if (*rsize == 213 && rdesc[13] == 5 && rdesc[21] == 5) { - hid_info(hdev, "Fixing up Elecom DEFT Fn buttons\n"); + hid_info(hdev, "Fixing up Elecom DEFT/HUGE Fn buttons\n"); rdesc[13] = 8; /* Button/Variable Report Count */ rdesc[21] = 8; /* Button/Variable Usage Maximum */ rdesc[29] = 0; /* Button/Constant Report Count */ @@ -76,6 +79,8 @@ static const struct hid_device_id elecom_devices[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_BM084) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_DEFT_WIRED) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_DEFT_WIRELESS) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_HUGE_WIRED) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_HUGE_WIRELESS) }, { } }; MODULE_DEVICE_TABLE(hid, elecom_devices); diff --git a/kernel/drivers/hid/hid-ids.h b/kernel/drivers/hid/hid-ids.h index 5b94d89c1..e011419cc 100644 --- a/kernel/drivers/hid/hid-ids.h +++ b/kernel/drivers/hid/hid-ids.h @@ -368,6 +368,8 @@ #define USB_DEVICE_ID_ELECOM_BM084 0x0061 #define USB_DEVICE_ID_ELECOM_DEFT_WIRED 0x00fe #define USB_DEVICE_ID_ELECOM_DEFT_WIRELESS 0x00ff +#define USB_DEVICE_ID_ELECOM_HUGE_WIRED 0x010c +#define USB_DEVICE_ID_ELECOM_HUGE_WIRELESS 0x010d #define USB_VENDOR_ID_DREAM_CHEEKY 0x1d34 #define USB_DEVICE_ID_DREAM_CHEEKY_WN 0x0004 diff --git a/kernel/drivers/hid/usbhid/hid-core.c b/kernel/drivers/hid/usbhid/hid-core.c index 089bad8a9..045b5da9b 100644 --- a/kernel/drivers/hid/usbhid/hid-core.c +++ b/kernel/drivers/hid/usbhid/hid-core.c @@ -975,6 +975,8 @@ static int usbhid_parse(struct hid_device *hid) unsigned int rsize = 0; char *rdesc; int ret, n; + int num_descriptors; + size_t offset = offsetof(struct hid_descriptor, desc); quirks = usbhid_lookup_quirk(le16_to_cpu(dev->descriptor.idVendor), le16_to_cpu(dev->descriptor.idProduct)); @@ -997,10 +999,18 @@ static int usbhid_parse(struct hid_device *hid) return -ENODEV; } + if (hdesc->bLength < sizeof(struct hid_descriptor)) { + dbg_hid("hid descriptor is too short\n"); + return -EINVAL; + } + hid->version = le16_to_cpu(hdesc->bcdHID); hid->country = hdesc->bCountryCode; - for (n = 0; n < hdesc->bNumDescriptors; n++) + num_descriptors = min_t(int, hdesc->bNumDescriptors, + (hdesc->bLength - offset) / sizeof(struct hid_class_descriptor)); + + for (n = 0; n < num_descriptors; n++) if (hdesc->desc[n].bDescriptorType == HID_DT_REPORT) rsize = le16_to_cpu(hdesc->desc[n].wDescriptorLength); diff --git a/kernel/drivers/hv/channel.c b/kernel/drivers/hv/channel.c index efd5db743..894b67ac2 100644 --- a/kernel/drivers/hv/channel.c +++ b/kernel/drivers/hv/channel.c @@ -640,6 +640,7 @@ void vmbus_close(struct vmbus_channel *channel) */ return; } + mutex_lock(&vmbus_connection.channel_mutex); /* * Close all the sub-channels first and then close the * primary channel. @@ -648,16 +649,15 @@ void vmbus_close(struct vmbus_channel *channel) cur_channel = list_entry(cur, struct vmbus_channel, sc_list); vmbus_close_internal(cur_channel); if (cur_channel->rescind) { - mutex_lock(&vmbus_connection.channel_mutex); - hv_process_channel_removal(cur_channel, + hv_process_channel_removal( cur_channel->offermsg.child_relid); - mutex_unlock(&vmbus_connection.channel_mutex); } } /* * Now close the primary. */ vmbus_close_internal(channel); + mutex_unlock(&vmbus_connection.channel_mutex); } EXPORT_SYMBOL_GPL(vmbus_close); diff --git a/kernel/drivers/hv/channel_mgmt.c b/kernel/drivers/hv/channel_mgmt.c index bcbb031f7..018d2e0f8 100644 --- a/kernel/drivers/hv/channel_mgmt.c +++ b/kernel/drivers/hv/channel_mgmt.c @@ -159,7 +159,7 @@ static void vmbus_rescind_cleanup(struct vmbus_channel *channel) spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags); - + channel->rescind = true; list_for_each_entry(msginfo, &vmbus_connection.chn_msg_list, msglistentry) { @@ -381,14 +381,21 @@ static void vmbus_release_relid(u32 relid) true); } -void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid) +void hv_process_channel_removal(u32 relid) { unsigned long flags; - struct vmbus_channel *primary_channel; + struct vmbus_channel *primary_channel, *channel; - BUG_ON(!channel->rescind); BUG_ON(!mutex_is_locked(&vmbus_connection.channel_mutex)); + /* + * Make sure channel is valid as we may have raced. + */ + channel = relid2channel(relid); + if (!channel) + return; + + BUG_ON(!channel->rescind); if (channel->target_cpu != get_cpu()) { put_cpu(); smp_call_function_single(channel->target_cpu, @@ -515,6 +522,7 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) if (!fnew) { if (channel->sc_creation_callback != NULL) channel->sc_creation_callback(newchannel); + newchannel->probe_done = true; return; } @@ -834,7 +842,6 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) { struct vmbus_channel_rescind_offer *rescind; struct vmbus_channel *channel; - unsigned long flags; struct device *dev; rescind = (struct vmbus_channel_rescind_offer *)hdr; @@ -873,16 +880,6 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) return; } - spin_lock_irqsave(&channel->lock, flags); - channel->rescind = true; - spin_unlock_irqrestore(&channel->lock, flags); - - /* - * Now that we have posted the rescind state, perform - * rescind related cleanup. - */ - vmbus_rescind_cleanup(channel); - /* * Now wait for offer handling to complete. */ @@ -901,6 +898,7 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) if (channel->device_obj) { if (channel->chn_rescind_callback) { channel->chn_rescind_callback(channel); + vmbus_rescind_cleanup(channel); return; } /* @@ -909,6 +907,7 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) */ dev = get_device(&channel->device_obj->device); if (dev) { + vmbus_rescind_cleanup(channel); vmbus_device_unregister(channel->device_obj); put_device(dev); } @@ -921,16 +920,16 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) * 1. Close all sub-channels first * 2. Then close the primary channel. */ + mutex_lock(&vmbus_connection.channel_mutex); + vmbus_rescind_cleanup(channel); if (channel->state == CHANNEL_OPEN_STATE) { /* * The channel is currently not open; * it is safe for us to cleanup the channel. */ - mutex_lock(&vmbus_connection.channel_mutex); - hv_process_channel_removal(channel, - channel->offermsg.child_relid); - mutex_unlock(&vmbus_connection.channel_mutex); + hv_process_channel_removal(rescind->child_relid); } + mutex_unlock(&vmbus_connection.channel_mutex); } } diff --git a/kernel/drivers/hv/vmbus_drv.c b/kernel/drivers/hv/vmbus_drv.c index a9d49f6f6..937801ac2 100644 --- a/kernel/drivers/hv/vmbus_drv.c +++ b/kernel/drivers/hv/vmbus_drv.c @@ -768,8 +768,7 @@ static void vmbus_device_release(struct device *device) struct vmbus_channel *channel = hv_dev->channel; mutex_lock(&vmbus_connection.channel_mutex); - hv_process_channel_removal(channel, - channel->offermsg.child_relid); + hv_process_channel_removal(channel->offermsg.child_relid); mutex_unlock(&vmbus_connection.channel_mutex); kfree(hv_dev); diff --git a/kernel/drivers/iommu/amd_iommu.c b/kernel/drivers/iommu/amd_iommu.c index 51f821587..8e8874d23 100644 --- a/kernel/drivers/iommu/amd_iommu.c +++ b/kernel/drivers/iommu/amd_iommu.c @@ -2773,14 +2773,16 @@ int __init amd_iommu_init_api(void) int __init amd_iommu_init_dma_ops(void) { - swiotlb = iommu_pass_through ? 1 : 0; + swiotlb = (iommu_pass_through || sme_me_mask) ? 1 : 0; iommu_detected = 1; /* * In case we don't initialize SWIOTLB (actually the common case - * when AMD IOMMU is enabled), make sure there are global - * dma_ops set as a fall-back for devices not handled by this - * driver (for example non-PCI devices). + * when AMD IOMMU is enabled and SME is not active), make sure there + * are global dma_ops set as a fall-back for devices not handled by + * this driver (for example non-PCI devices). When SME is active, + * make sure that swiotlb variable remains set so the global dma_ops + * continue to be SWIOTLB. */ if (!swiotlb) dma_ops = &nommu_dma_ops; @@ -3046,6 +3048,7 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova, mutex_unlock(&domain->api_lock); domain_flush_tlb_pde(domain); + domain_flush_complete(domain); return unmap_size; } diff --git a/kernel/drivers/iommu/exynos-iommu.c b/kernel/drivers/iommu/exynos-iommu.c index f596fcc32..25c2c75f5 100644 --- a/kernel/drivers/iommu/exynos-iommu.c +++ b/kernel/drivers/iommu/exynos-iommu.c @@ -709,7 +709,7 @@ static const struct dev_pm_ops sysmmu_pm_ops = { pm_runtime_force_resume) }; -static const struct of_device_id sysmmu_of_match[] __initconst = { +static const struct of_device_id sysmmu_of_match[] = { { .compatible = "samsung,exynos-sysmmu", }, { }, }; diff --git a/kernel/drivers/misc/mei/hw-me-regs.h b/kernel/drivers/misc/mei/hw-me-regs.h index cde23f9aa..c29f128ab 100644 --- a/kernel/drivers/misc/mei/hw-me-regs.h +++ b/kernel/drivers/misc/mei/hw-me-regs.h @@ -128,6 +128,8 @@ #define MEI_DEV_ID_BXT_M 0x1A9A /* Broxton M */ #define MEI_DEV_ID_APL_I 0x5A9A /* Apollo Lake I */ +#define MEI_DEV_ID_GLK 0x319A /* Gemini Lake */ + #define MEI_DEV_ID_KBP 0xA2BA /* Kaby Point */ #define MEI_DEV_ID_KBP_2 0xA2BB /* Kaby Point 2 */ diff --git a/kernel/drivers/misc/mei/pci-me.c b/kernel/drivers/misc/mei/pci-me.c index fa23ab185..e5b6b3b6e 100644 --- a/kernel/drivers/misc/mei/pci-me.c +++ b/kernel/drivers/misc/mei/pci-me.c @@ -94,6 +94,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_BXT_M, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_APL_I, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_GLK, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_KBP, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_KBP_2, MEI_ME_PCH8_CFG)}, @@ -227,12 +229,15 @@ static int mei_me_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pdev->dev_flags |= PCI_DEV_FLAGS_NEEDS_RESUME; /* - * For not wake-able HW runtime pm framework - * can't be used on pci device level. - * Use domain runtime pm callbacks instead. - */ - if (!pci_dev_run_wake(pdev)) - mei_me_set_pm_domain(dev); + * ME maps runtime suspend/resume to D0i states, + * hence we need to go around native PCI runtime service which + * eventually brings the device into D3cold/hot state, + * but the mei device cannot wake up from D3 unlike from D0i3. + * To get around the PCI device native runtime pm, + * ME uses runtime pm domain handlers which take precedence + * over the driver's pm handlers. + */ + mei_me_set_pm_domain(dev); if (mei_pg_is_enabled(dev)) pm_runtime_put_noidle(&pdev->dev); @@ -272,8 +277,7 @@ static void mei_me_shutdown(struct pci_dev *pdev) dev_dbg(&pdev->dev, "shutdown\n"); mei_stop(dev); - if (!pci_dev_run_wake(pdev)) - mei_me_unset_pm_domain(dev); + mei_me_unset_pm_domain(dev); mei_disable_interrupts(dev); free_irq(pdev->irq, dev); @@ -301,8 +305,7 @@ static void mei_me_remove(struct pci_dev *pdev) dev_dbg(&pdev->dev, "stop\n"); mei_stop(dev); - if (!pci_dev_run_wake(pdev)) - mei_me_unset_pm_domain(dev); + mei_me_unset_pm_domain(dev); mei_disable_interrupts(dev); diff --git a/kernel/drivers/misc/mei/pci-txe.c b/kernel/drivers/misc/mei/pci-txe.c index e38a5f144..0566f9bfa 100644 --- a/kernel/drivers/misc/mei/pci-txe.c +++ b/kernel/drivers/misc/mei/pci-txe.c @@ -144,12 +144,14 @@ static int mei_txe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pdev->dev_flags |= PCI_DEV_FLAGS_NEEDS_RESUME; /* - * For not wake-able HW runtime pm framework - * can't be used on pci device level. - * Use domain runtime pm callbacks instead. - */ - if (!pci_dev_run_wake(pdev)) - mei_txe_set_pm_domain(dev); + * TXE maps runtime suspend/resume to own power gating states, + * hence we need to go around native PCI runtime service which + * eventually brings the device into D3cold/hot state. + * But the TXE device cannot wake up from D3 unlike from own + * power gating. To get around PCI device native runtime pm, + * TXE uses runtime pm domain handlers which take precedence. + */ + mei_txe_set_pm_domain(dev); pm_runtime_put_noidle(&pdev->dev); @@ -186,8 +188,7 @@ static void mei_txe_shutdown(struct pci_dev *pdev) dev_dbg(&pdev->dev, "shutdown\n"); mei_stop(dev); - if (!pci_dev_run_wake(pdev)) - mei_txe_unset_pm_domain(dev); + mei_txe_unset_pm_domain(dev); mei_disable_interrupts(dev); free_irq(pdev->irq, dev); @@ -215,8 +216,7 @@ static void mei_txe_remove(struct pci_dev *pdev) mei_stop(dev); - if (!pci_dev_run_wake(pdev)) - mei_txe_unset_pm_domain(dev); + mei_txe_unset_pm_domain(dev); mei_disable_interrupts(dev); free_irq(pdev->irq, dev); @@ -318,15 +318,7 @@ static int mei_txe_pm_runtime_suspend(struct device *device) else ret = -EAGAIN; - /* - * If everything is okay we're about to enter PCI low - * power state (D3) therefor we need to disable the - * interrupts towards host. - * However if device is not wakeable we do not enter - * D-low state and we need to keep the interrupt kicking - */ - if (!ret && pci_dev_run_wake(pdev)) - mei_disable_interrupts(dev); + /* keep irq on we are staying in D0 */ dev_dbg(&pdev->dev, "rpm: txe: runtime suspend ret=%d\n", ret); diff --git a/kernel/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/kernel/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 49b80da51..805ab45e9 100644 --- a/kernel/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/kernel/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -565,8 +565,10 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog, return true; default: bpf_warn_invalid_xdp_action(action); + /* fall through */ case XDP_ABORTED: trace_xdp_exception(nic->netdev, prog, action); + /* fall through */ case XDP_DROP: /* Check if it's a recycled page, if not * unmap the DMA mapping. diff --git a/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c index 523f9d05a..8a32eb7d4 100644 --- a/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c +++ b/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c @@ -175,31 +175,9 @@ static s32 ixgbe_init_phy_ops_82598(struct ixgbe_hw *hw) **/ static s32 ixgbe_start_hw_82598(struct ixgbe_hw *hw) { -#ifndef CONFIG_SPARC - u32 regval; - u32 i; -#endif s32 ret_val; ret_val = ixgbe_start_hw_generic(hw); - -#ifndef CONFIG_SPARC - /* Disable relaxed ordering */ - for (i = 0; ((i < hw->mac.max_tx_queues) && - (i < IXGBE_DCA_MAX_QUEUES_82598)); i++) { - regval = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL(i)); - regval &= ~IXGBE_DCA_TXCTRL_DESC_WRO_EN; - IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL(i), regval); - } - - for (i = 0; ((i < hw->mac.max_rx_queues) && - (i < IXGBE_DCA_MAX_QUEUES_82598)); i++) { - regval = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i)); - regval &= ~(IXGBE_DCA_RXCTRL_DATA_WRO_EN | - IXGBE_DCA_RXCTRL_HEAD_WRO_EN); - IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(i), regval); - } -#endif if (ret_val) return ret_val; diff --git a/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 2c19070d2..6e6ab6f68 100644 --- a/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -366,25 +366,6 @@ s32 ixgbe_start_hw_gen2(struct ixgbe_hw *hw) } IXGBE_WRITE_FLUSH(hw); -#ifndef CONFIG_ARCH_WANT_RELAX_ORDER - /* Disable relaxed ordering */ - for (i = 0; i < hw->mac.max_tx_queues; i++) { - u32 regval; - - regval = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL_82599(i)); - regval &= ~IXGBE_DCA_TXCTRL_DESC_WRO_EN; - IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL_82599(i), regval); - } - - for (i = 0; i < hw->mac.max_rx_queues; i++) { - u32 regval; - - regval = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i)); - regval &= ~(IXGBE_DCA_RXCTRL_DATA_WRO_EN | - IXGBE_DCA_RXCTRL_HEAD_WRO_EN); - IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(i), regval); - } -#endif return 0; } diff --git a/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 72c565712..c3e7a8191 100644 --- a/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -1048,7 +1048,7 @@ static int ixgbe_set_ringparam(struct net_device *netdev, { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_ring *temp_ring; - int i, err = 0; + int i, j, err = 0; u32 new_rx_count, new_tx_count; if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) @@ -1085,8 +1085,8 @@ static int ixgbe_set_ringparam(struct net_device *netdev, } /* allocate temporary buffer to store rings in */ - i = max_t(int, adapter->num_tx_queues, adapter->num_rx_queues); - i = max_t(int, i, adapter->num_xdp_queues); + i = max_t(int, adapter->num_tx_queues + adapter->num_xdp_queues, + adapter->num_rx_queues); temp_ring = vmalloc(i * sizeof(struct ixgbe_ring)); if (!temp_ring) { @@ -1118,8 +1118,8 @@ static int ixgbe_set_ringparam(struct net_device *netdev, } } - for (i = 0; i < adapter->num_xdp_queues; i++) { - memcpy(&temp_ring[i], adapter->xdp_ring[i], + for (j = 0; j < adapter->num_xdp_queues; j++, i++) { + memcpy(&temp_ring[i], adapter->xdp_ring[j], sizeof(struct ixgbe_ring)); temp_ring[i].count = new_tx_count; @@ -1139,10 +1139,10 @@ static int ixgbe_set_ringparam(struct net_device *netdev, memcpy(adapter->tx_ring[i], &temp_ring[i], sizeof(struct ixgbe_ring)); } - for (i = 0; i < adapter->num_xdp_queues; i++) { - ixgbe_free_tx_resources(adapter->xdp_ring[i]); + for (j = 0; j < adapter->num_xdp_queues; j++, i++) { + ixgbe_free_tx_resources(adapter->xdp_ring[j]); - memcpy(adapter->xdp_ring[i], &temp_ring[i], + memcpy(adapter->xdp_ring[j], &temp_ring[i], sizeof(struct ixgbe_ring)); } diff --git a/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index d962368d0..4d76afd13 100644 --- a/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -4881,7 +4881,7 @@ static void ixgbe_clear_udp_tunnel_port(struct ixgbe_adapter *adapter, u32 mask) IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE))) return; - vxlanctrl = IXGBE_READ_REG(hw, IXGBE_VXLANCTRL) && ~mask; + vxlanctrl = IXGBE_READ_REG(hw, IXGBE_VXLANCTRL) & ~mask; IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, vxlanctrl); if (mask & IXGBE_VXLANCTRL_VXLAN_UDPPORT_MASK) @@ -8529,6 +8529,10 @@ static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) return ixgbe_ptp_set_ts_config(adapter, req); case SIOCGHWTSTAMP: return ixgbe_ptp_get_ts_config(adapter, req); + case SIOCGMIIPHY: + if (!adapter->hw.phy.ops.read_reg) + return -EOPNOTSUPP; + /* fall through */ default: return mdio_mii_ioctl(&adapter->hw.phy.mdio, if_mii(req), cmd); } diff --git a/kernel/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/kernel/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 032089efc..c16718d29 100644 --- a/kernel/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/kernel/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -3505,20 +3505,6 @@ static int mlxsw_sp_fib_lpm_tree_link(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_fib_lpm_tree_unlink(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib *fib) { - struct mlxsw_sp_prefix_usage req_prefix_usage = {{ 0 } }; - struct mlxsw_sp_lpm_tree *lpm_tree; - - /* Aggregate prefix lengths across all virtual routers to make - * sure we only have used prefix lengths in the LPM tree. - */ - mlxsw_sp_vrs_prefixes(mlxsw_sp, fib->proto, &req_prefix_usage); - lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage, - fib->proto); - if (IS_ERR(lpm_tree)) - goto err_tree_get; - mlxsw_sp_vrs_lpm_tree_replace(mlxsw_sp, fib, lpm_tree); - -err_tree_get: if (!mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) return; mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, fib); diff --git a/kernel/drivers/net/ppp/ppp_generic.c b/kernel/drivers/net/ppp/ppp_generic.c index c3f77e3b7..e36586660 100644 --- a/kernel/drivers/net/ppp/ppp_generic.c +++ b/kernel/drivers/net/ppp/ppp_generic.c @@ -1339,7 +1339,17 @@ ppp_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats64) static int ppp_dev_init(struct net_device *dev) { + struct ppp *ppp; + netdev_lockdep_set_classes(dev); + + ppp = netdev_priv(dev); + /* Let the netdevice take a reference on the ppp file. This ensures + * that ppp_destroy_interface() won't run before the device gets + * unregistered. + */ + atomic_inc(&ppp->file.refcnt); + return 0; } @@ -1362,6 +1372,15 @@ static void ppp_dev_uninit(struct net_device *dev) wake_up_interruptible(&ppp->file.rwait); } +static void ppp_dev_priv_destructor(struct net_device *dev) +{ + struct ppp *ppp; + + ppp = netdev_priv(dev); + if (atomic_dec_and_test(&ppp->file.refcnt)) + ppp_destroy_interface(ppp); +} + static const struct net_device_ops ppp_netdev_ops = { .ndo_init = ppp_dev_init, .ndo_uninit = ppp_dev_uninit, @@ -1387,6 +1406,7 @@ static void ppp_setup(struct net_device *dev) dev->tx_queue_len = 3; dev->type = ARPHRD_PPP; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; + dev->priv_destructor = ppp_dev_priv_destructor; netif_keep_dst(dev); } diff --git a/kernel/drivers/net/usb/cdc_ether.c b/kernel/drivers/net/usb/cdc_ether.c index 5a42469c7..9ad70736c 100644 --- a/kernel/drivers/net/usb/cdc_ether.c +++ b/kernel/drivers/net/usb/cdc_ether.c @@ -560,6 +560,7 @@ static const struct driver_info wwan_info = { #define NVIDIA_VENDOR_ID 0x0955 #define HP_VENDOR_ID 0x03f0 #define MICROSOFT_VENDOR_ID 0x045e +#define UBLOX_VENDOR_ID 0x1546 static const struct usb_device_id products[] = { /* BLACKLIST !! @@ -861,6 +862,18 @@ static const struct usb_device_id products[] = { USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&zte_cdc_info, +}, { + /* U-blox TOBY-L2 */ + USB_DEVICE_AND_INTERFACE_INFO(UBLOX_VENDOR_ID, 0x1143, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, + USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_info, +}, { + /* U-blox SARA-U2 */ + USB_DEVICE_AND_INTERFACE_INFO(UBLOX_VENDOR_ID, 0x1104, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, + USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_info, }, { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), diff --git a/kernel/drivers/of/base.c b/kernel/drivers/of/base.c index 260d33c0f..63897531c 100644 --- a/kernel/drivers/of/base.c +++ b/kernel/drivers/of/base.c @@ -1781,8 +1781,12 @@ bool of_console_check(struct device_node *dn, char *name, int index) { if (!dn || dn != of_stdout || console_set_on_cmdline) return false; - return !add_preferred_console(name, index, - kstrdup(of_stdout_options, GFP_KERNEL)); + + /* + * XXX: cast `options' to char pointer to suppress complication + * warnings: printk, UART and console drivers expect char pointer. + */ + return !add_preferred_console(name, index, (char *)of_stdout_options); } EXPORT_SYMBOL_GPL(of_console_check); diff --git a/kernel/drivers/of/of_reserved_mem.c b/kernel/drivers/of/of_reserved_mem.c index d507c3569..32771c2ce 100644 --- a/kernel/drivers/of/of_reserved_mem.c +++ b/kernel/drivers/of/of_reserved_mem.c @@ -25,7 +25,7 @@ #include #include -#define MAX_RESERVED_REGIONS 16 +#define MAX_RESERVED_REGIONS 32 static struct reserved_mem reserved_mem[MAX_RESERVED_REGIONS]; static int reserved_mem_count; diff --git a/kernel/drivers/of/property.c b/kernel/drivers/of/property.c index fbb72116e..264c355ba 100644 --- a/kernel/drivers/of/property.c +++ b/kernel/drivers/of/property.c @@ -954,7 +954,7 @@ of_fwnode_graph_get_port_parent(struct fwnode_handle *fwnode) struct device_node *np; /* Get the parent of the port */ - np = of_get_next_parent(to_of_node(fwnode)); + np = of_get_parent(to_of_node(fwnode)); if (!np) return NULL; diff --git a/kernel/drivers/pci/host/pci-aardvark.c b/kernel/drivers/pci/host/pci-aardvark.c index 89f4e3d07..26ed0c08f 100644 --- a/kernel/drivers/pci/host/pci-aardvark.c +++ b/kernel/drivers/pci/host/pci-aardvark.c @@ -935,6 +935,8 @@ static int advk_pcie_probe(struct platform_device *pdev) bridge->sysdata = pcie; bridge->busnr = 0; bridge->ops = &advk_pcie_ops; + bridge->map_irq = of_irq_parse_and_map_pci; + bridge->swizzle_irq = pci_common_swizzle; ret = pci_scan_root_bus_bridge(bridge); if (ret < 0) { diff --git a/kernel/drivers/pci/host/pci-tegra.c b/kernel/drivers/pci/host/pci-tegra.c index 9c40da54f..1987fec1f 100644 --- a/kernel/drivers/pci/host/pci-tegra.c +++ b/kernel/drivers/pci/host/pci-tegra.c @@ -233,6 +233,7 @@ struct tegra_msi { struct msi_controller chip; DECLARE_BITMAP(used, INT_PCI_MSI_NR); struct irq_domain *domain; + unsigned long pages; struct mutex lock; u64 phys; int irq; @@ -1529,22 +1530,9 @@ static int tegra_pcie_enable_msi(struct tegra_pcie *pcie) goto err; } - /* - * The PCI host bridge on Tegra contains some logic that intercepts - * MSI writes, which means that the MSI target address doesn't have - * to point to actual physical memory. Rather than allocating one 4 - * KiB page of system memory that's never used, we can simply pick - * an arbitrary address within an area reserved for system memory - * in the FPCI address map. - * - * However, in order to avoid confusion, we pick an address that - * doesn't map to physical memory. The FPCI address map reserves a - * 1012 GiB region for system memory and memory-mapped I/O. Since - * none of the Tegra SoCs that contain this PCI host bridge can - * address more than 16 GiB of system memory, the last 4 KiB of - * these 1012 GiB is a good candidate. - */ - msi->phys = 0xfcfffff000; + /* setup AFI/FPCI range */ + msi->pages = __get_free_pages(GFP_KERNEL, 0); + msi->phys = virt_to_phys((void *)msi->pages); afi_writel(pcie, msi->phys >> soc->msi_base_shift, AFI_MSI_FPCI_BAR_ST); afi_writel(pcie, msi->phys, AFI_MSI_AXI_BAR_ST); @@ -1596,6 +1584,8 @@ static int tegra_pcie_disable_msi(struct tegra_pcie *pcie) afi_writel(pcie, 0, AFI_MSI_EN_VEC6); afi_writel(pcie, 0, AFI_MSI_EN_VEC7); + free_pages(msi->pages, 0); + if (msi->irq > 0) free_irq(msi->irq, pcie); diff --git a/kernel/drivers/pinctrl/Kconfig b/kernel/drivers/pinctrl/Kconfig index 1778cf4f8..82cd8b08d 100644 --- a/kernel/drivers/pinctrl/Kconfig +++ b/kernel/drivers/pinctrl/Kconfig @@ -100,6 +100,7 @@ config PINCTRL_AMD tristate "AMD GPIO pin control" depends on GPIOLIB select GPIOLIB_IRQCHIP + select PINMUX select PINCONF select GENERIC_PINCONF help diff --git a/kernel/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/kernel/drivers/pinctrl/bcm/pinctrl-bcm2835.c index 094431022..ff782445d 100644 --- a/kernel/drivers/pinctrl/bcm/pinctrl-bcm2835.c +++ b/kernel/drivers/pinctrl/bcm/pinctrl-bcm2835.c @@ -373,16 +373,12 @@ static void bcm2835_gpio_irq_handle_bank(struct bcm2835_pinctrl *pc, unsigned long events; unsigned offset; unsigned gpio; - unsigned int type; events = bcm2835_gpio_rd(pc, GPEDS0 + bank * 4); events &= mask; events &= pc->enabled_irq_map[bank]; for_each_set_bit(offset, &events, 32) { gpio = (32 * bank) + offset; - /* FIXME: no clue why the code looks up the type here */ - type = pc->irq_type[gpio]; - generic_handle_irq(irq_linear_revmap(pc->gpio_chip.irqdomain, gpio)); } diff --git a/kernel/drivers/pinctrl/intel/pinctrl-cherryview.c b/kernel/drivers/pinctrl/intel/pinctrl-cherryview.c index 04e929fd0..fadbca907 100644 --- a/kernel/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/kernel/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1577,6 +1577,7 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) struct gpio_chip *chip = &pctrl->chip; bool need_valid_mask = !dmi_check_system(chv_no_valid_mask); int ret, i, offset; + int irq_base; *chip = chv_gpio_chip; @@ -1622,7 +1623,18 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) /* Clear all interrupts */ chv_writel(0xffff, pctrl->regs + CHV_INTSTAT); - ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, 0, + if (!need_valid_mask) { + irq_base = devm_irq_alloc_descs(pctrl->dev, -1, 0, + chip->ngpio, NUMA_NO_NODE); + if (irq_base < 0) { + dev_err(pctrl->dev, "Failed to allocate IRQ numbers\n"); + return irq_base; + } + } else { + irq_base = 0; + } + + ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, irq_base, handle_bad_irq, IRQ_TYPE_NONE); if (ret) { dev_err(pctrl->dev, "failed to add IRQ chip\n"); diff --git a/kernel/drivers/ras/cec.c b/kernel/drivers/ras/cec.c index d0e5d6ee8..e2c1988cd 100644 --- a/kernel/drivers/ras/cec.c +++ b/kernel/drivers/ras/cec.c @@ -523,7 +523,7 @@ int __init parse_cec_param(char *str) if (*str == '=') str++; - if (!strncmp(str, "cec_disable", 7)) + if (!strcmp(str, "cec_disable")) ce_arr.disabled = 1; else return 0; diff --git a/kernel/drivers/remoteproc/Kconfig b/kernel/drivers/remoteproc/Kconfig index df63e4452..bf0447945 100644 --- a/kernel/drivers/remoteproc/Kconfig +++ b/kernel/drivers/remoteproc/Kconfig @@ -109,6 +109,7 @@ config QCOM_Q6V5_PIL depends on OF && ARCH_QCOM depends on QCOM_SMEM depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n) + depends on RPMSG_QCOM_GLINK_SMEM || RPMSG_QCOM_GLINK_SMEM=n select MFD_SYSCON select QCOM_RPROC_COMMON select QCOM_SCM @@ -120,6 +121,7 @@ config QCOM_WCNSS_PIL tristate "Qualcomm WCNSS Peripheral Image Loader" depends on OF && ARCH_QCOM depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n) + depends on RPMSG_QCOM_GLINK_SMEM || RPMSG_QCOM_GLINK_SMEM=n depends on QCOM_SMEM select QCOM_MDT_LOADER select QCOM_RPROC_COMMON diff --git a/kernel/drivers/remoteproc/imx_rproc.c b/kernel/drivers/remoteproc/imx_rproc.c index 612d91403..633268e9d 100644 --- a/kernel/drivers/remoteproc/imx_rproc.c +++ b/kernel/drivers/remoteproc/imx_rproc.c @@ -264,15 +264,14 @@ static int imx_rproc_addr_init(struct imx_rproc *priv, if (!(att->flags & ATT_OWN)) continue; - if (b > IMX7D_RPROC_MEM_MAX) + if (b >= IMX7D_RPROC_MEM_MAX) break; priv->mem[b].cpu_addr = devm_ioremap(&pdev->dev, att->sa, att->size); - if (IS_ERR(priv->mem[b].cpu_addr)) { + if (!priv->mem[b].cpu_addr) { dev_err(dev, "devm_ioremap_resource failed\n"); - err = PTR_ERR(priv->mem[b].cpu_addr); - return err; + return -ENOMEM; } priv->mem[b].sys_addr = att->sa; priv->mem[b].size = att->size; @@ -296,7 +295,7 @@ static int imx_rproc_addr_init(struct imx_rproc *priv, return err; } - if (b > IMX7D_RPROC_MEM_MAX) + if (b >= IMX7D_RPROC_MEM_MAX) break; priv->mem[b].cpu_addr = devm_ioremap_resource(&pdev->dev, &res); diff --git a/kernel/drivers/rpmsg/qcom_glink_native.c b/kernel/drivers/rpmsg/qcom_glink_native.c index 5a5e927ea..5dcc9bf1c 100644 --- a/kernel/drivers/rpmsg/qcom_glink_native.c +++ b/kernel/drivers/rpmsg/qcom_glink_native.c @@ -635,19 +635,18 @@ qcom_glink_alloc_intent(struct qcom_glink *glink, unsigned long flags; intent = kzalloc(sizeof(*intent), GFP_KERNEL); - if (!intent) return NULL; intent->data = kzalloc(size, GFP_KERNEL); if (!intent->data) - return NULL; + goto free_intent; spin_lock_irqsave(&channel->intent_lock, flags); ret = idr_alloc_cyclic(&channel->liids, intent, 1, -1, GFP_ATOMIC); if (ret < 0) { spin_unlock_irqrestore(&channel->intent_lock, flags); - return NULL; + goto free_data; } spin_unlock_irqrestore(&channel->intent_lock, flags); @@ -656,6 +655,12 @@ qcom_glink_alloc_intent(struct qcom_glink *glink, intent->reuse = reuseable; return intent; + +free_data: + kfree(intent->data); +free_intent: + kfree(intent); + return NULL; } static void qcom_glink_handle_rx_done(struct qcom_glink *glink, @@ -1197,7 +1202,7 @@ static int qcom_glink_request_intent(struct qcom_glink *glink, ret = qcom_glink_tx(glink, &cmd, sizeof(cmd), NULL, 0, true); if (ret) - return ret; + goto unlock; ret = wait_for_completion_timeout(&channel->intent_req_comp, 10 * HZ); if (!ret) { @@ -1207,6 +1212,7 @@ static int qcom_glink_request_intent(struct qcom_glink *glink, ret = channel->intent_req_result ? 0 : -ECANCELED; } +unlock: mutex_unlock(&channel->intent_req_lock); return ret; } diff --git a/kernel/drivers/tty/tty_ldisc.c b/kernel/drivers/tty/tty_ldisc.c index 2fe216b27..84a8ac2a7 100644 --- a/kernel/drivers/tty/tty_ldisc.c +++ b/kernel/drivers/tty/tty_ldisc.c @@ -694,10 +694,8 @@ int tty_ldisc_reinit(struct tty_struct *tty, int disc) tty_set_termios_ldisc(tty, disc); retval = tty_ldisc_open(tty, tty->ldisc); if (retval) { - if (!WARN_ON(disc == N_TTY)) { - tty_ldisc_put(tty->ldisc); - tty->ldisc = NULL; - } + tty_ldisc_put(tty->ldisc); + tty->ldisc = NULL; } return retval; } @@ -752,8 +750,9 @@ void tty_ldisc_hangup(struct tty_struct *tty, bool reinit) if (tty->ldisc) { if (reinit) { - if (tty_ldisc_reinit(tty, tty->termios.c_line) < 0) - tty_ldisc_reinit(tty, N_TTY); + if (tty_ldisc_reinit(tty, tty->termios.c_line) < 0 && + tty_ldisc_reinit(tty, N_TTY) < 0) + WARN_ON(tty_ldisc_reinit(tty, N_NULL) < 0); } else tty_ldisc_kill(tty); } diff --git a/kernel/drivers/usb/gadget/composite.c b/kernel/drivers/usb/gadget/composite.c index dd74c99d6..5d061b3d8 100644 --- a/kernel/drivers/usb/gadget/composite.c +++ b/kernel/drivers/usb/gadget/composite.c @@ -2026,6 +2026,8 @@ static DEVICE_ATTR_RO(suspended); static void __composite_unbind(struct usb_gadget *gadget, bool unbind_driver) { struct usb_composite_dev *cdev = get_gadget_data(gadget); + struct usb_gadget_strings *gstr = cdev->driver->strings[0]; + struct usb_string *dev_str = gstr->strings; /* composite_disconnect() must already have been called * by the underlying peripheral controller driver! @@ -2045,6 +2047,9 @@ static void __composite_unbind(struct usb_gadget *gadget, bool unbind_driver) composite_dev_cleanup(cdev); + if (dev_str[USB_GADGET_MANUFACTURER_IDX].s == cdev->def_manufacturer) + dev_str[USB_GADGET_MANUFACTURER_IDX].s = ""; + kfree(cdev->def_manufacturer); kfree(cdev); set_gadget_data(gadget, NULL); diff --git a/kernel/drivers/usb/gadget/configfs.c b/kernel/drivers/usb/gadget/configfs.c index a22a892de..aeb9f3c40 100644 --- a/kernel/drivers/usb/gadget/configfs.c +++ b/kernel/drivers/usb/gadget/configfs.c @@ -1143,11 +1143,12 @@ static struct configfs_attribute *interf_grp_attrs[] = { NULL }; -int usb_os_desc_prepare_interf_dir(struct config_group *parent, - int n_interf, - struct usb_os_desc **desc, - char **names, - struct module *owner) +struct config_group *usb_os_desc_prepare_interf_dir( + struct config_group *parent, + int n_interf, + struct usb_os_desc **desc, + char **names, + struct module *owner) { struct config_group *os_desc_group; struct config_item_type *os_desc_type, *interface_type; @@ -1159,7 +1160,7 @@ int usb_os_desc_prepare_interf_dir(struct config_group *parent, char *vlabuf = kzalloc(vla_group_size(data_chunk), GFP_KERNEL); if (!vlabuf) - return -ENOMEM; + return ERR_PTR(-ENOMEM); os_desc_group = vla_ptr(vlabuf, data_chunk, os_desc_group); os_desc_type = vla_ptr(vlabuf, data_chunk, os_desc_type); @@ -1184,7 +1185,7 @@ int usb_os_desc_prepare_interf_dir(struct config_group *parent, configfs_add_default_group(&d->group, os_desc_group); } - return 0; + return os_desc_group; } EXPORT_SYMBOL(usb_os_desc_prepare_interf_dir); diff --git a/kernel/drivers/usb/gadget/configfs.h b/kernel/drivers/usb/gadget/configfs.h index 36c468c4f..540d5e92e 100644 --- a/kernel/drivers/usb/gadget/configfs.h +++ b/kernel/drivers/usb/gadget/configfs.h @@ -5,11 +5,12 @@ void unregister_gadget_item(struct config_item *item); -int usb_os_desc_prepare_interf_dir(struct config_group *parent, - int n_interf, - struct usb_os_desc **desc, - char **names, - struct module *owner); +struct config_group *usb_os_desc_prepare_interf_dir( + struct config_group *parent, + int n_interf, + struct usb_os_desc **desc, + char **names, + struct module *owner); static inline struct usb_os_desc *to_usb_os_desc(struct config_item *item) { diff --git a/kernel/drivers/usb/gadget/function/f_rndis.c b/kernel/drivers/usb/gadget/function/f_rndis.c index e1d5853ef..c7c5b3ce1 100644 --- a/kernel/drivers/usb/gadget/function/f_rndis.c +++ b/kernel/drivers/usb/gadget/function/f_rndis.c @@ -908,6 +908,7 @@ static void rndis_free_inst(struct usb_function_instance *f) free_netdev(opts->net); } + kfree(opts->rndis_interf_group); /* single VLA chunk */ kfree(opts); } @@ -916,6 +917,7 @@ static struct usb_function_instance *rndis_alloc_inst(void) struct f_rndis_opts *opts; struct usb_os_desc *descs[1]; char *names[1]; + struct config_group *rndis_interf_group; opts = kzalloc(sizeof(*opts), GFP_KERNEL); if (!opts) @@ -940,8 +942,14 @@ static struct usb_function_instance *rndis_alloc_inst(void) names[0] = "rndis"; config_group_init_type_name(&opts->func_inst.group, "", &rndis_func_type); - usb_os_desc_prepare_interf_dir(&opts->func_inst.group, 1, descs, - names, THIS_MODULE); + rndis_interf_group = + usb_os_desc_prepare_interf_dir(&opts->func_inst.group, 1, descs, + names, THIS_MODULE); + if (IS_ERR(rndis_interf_group)) { + rndis_free_inst(&opts->func_inst); + return ERR_CAST(rndis_interf_group); + } + opts->rndis_interf_group = rndis_interf_group; return &opts->func_inst; } diff --git a/kernel/drivers/usb/gadget/function/u_rndis.h b/kernel/drivers/usb/gadget/function/u_rndis.h index a35ee3c25..efdb7ac38 100644 --- a/kernel/drivers/usb/gadget/function/u_rndis.h +++ b/kernel/drivers/usb/gadget/function/u_rndis.h @@ -26,6 +26,7 @@ struct f_rndis_opts { bool bound; bool borrowed_net; + struct config_group *rndis_interf_group; struct usb_os_desc rndis_os_desc; char rndis_ext_compat_id[16]; diff --git a/kernel/drivers/usb/gadget/udc/dummy_hcd.c b/kernel/drivers/usb/gadget/udc/dummy_hcd.c index b17618a55..f04e91ef9 100644 --- a/kernel/drivers/usb/gadget/udc/dummy_hcd.c +++ b/kernel/drivers/usb/gadget/udc/dummy_hcd.c @@ -419,6 +419,7 @@ static void set_link_state_by_speed(struct dummy_hcd *dum_hcd) static void set_link_state(struct dummy_hcd *dum_hcd) { struct dummy *dum = dum_hcd->dum; + unsigned int power_bit; dum_hcd->active = 0; if (dum->pullup) @@ -429,17 +430,19 @@ static void set_link_state(struct dummy_hcd *dum_hcd) return; set_link_state_by_speed(dum_hcd); + power_bit = (dummy_hcd_to_hcd(dum_hcd)->speed == HCD_USB3 ? + USB_SS_PORT_STAT_POWER : USB_PORT_STAT_POWER); if ((dum_hcd->port_status & USB_PORT_STAT_ENABLE) == 0 || dum_hcd->active) dum_hcd->resuming = 0; /* Currently !connected or in reset */ - if ((dum_hcd->port_status & USB_PORT_STAT_CONNECTION) == 0 || + if ((dum_hcd->port_status & power_bit) == 0 || (dum_hcd->port_status & USB_PORT_STAT_RESET) != 0) { - unsigned disconnect = USB_PORT_STAT_CONNECTION & + unsigned int disconnect = power_bit & dum_hcd->old_status & (~dum_hcd->port_status); - unsigned reset = USB_PORT_STAT_RESET & + unsigned int reset = USB_PORT_STAT_RESET & (~dum_hcd->old_status) & dum_hcd->port_status; /* Report reset and disconnect events to the driver */ diff --git a/kernel/drivers/usb/misc/usbtest.c b/kernel/drivers/usb/misc/usbtest.c index eee82ca55..b3fc602b2 100644 --- a/kernel/drivers/usb/misc/usbtest.c +++ b/kernel/drivers/usb/misc/usbtest.c @@ -202,12 +202,13 @@ found: return tmp; } - if (in) { + if (in) dev->in_pipe = usb_rcvbulkpipe(udev, in->desc.bEndpointAddress & USB_ENDPOINT_NUMBER_MASK); + if (out) dev->out_pipe = usb_sndbulkpipe(udev, out->desc.bEndpointAddress & USB_ENDPOINT_NUMBER_MASK); - } + if (iso_in) { dev->iso_in = &iso_in->desc; dev->in_iso_pipe = usb_rcvisocpipe(udev, @@ -1964,6 +1965,9 @@ test_queue(struct usbtest_dev *dev, struct usbtest_param_32 *param, int status = 0; struct urb *urbs[param->sglen]; + if (!param->sglen || param->iterations > UINT_MAX / param->sglen) + return -EINVAL; + memset(&context, 0, sizeof(context)); context.count = param->iterations * param->sglen; context.dev = dev; @@ -2087,6 +2091,8 @@ usbtest_do_ioctl(struct usb_interface *intf, struct usbtest_param_32 *param) if (param->iterations <= 0) return -EINVAL; + if (param->sglen > MAX_SGLEN) + return -EINVAL; /* * Just a bunch of test cases that every HCD is expected to handle. * diff --git a/kernel/drivers/usb/phy/phy-tegra-usb.c b/kernel/drivers/usb/phy/phy-tegra-usb.c index 5fe4a5704..ccc2bf527 100644 --- a/kernel/drivers/usb/phy/phy-tegra-usb.c +++ b/kernel/drivers/usb/phy/phy-tegra-usb.c @@ -329,6 +329,14 @@ static void utmi_phy_clk_disable(struct tegra_usb_phy *phy) unsigned long val; void __iomem *base = phy->regs; + /* + * The USB driver may have already initiated the phy clock + * disable so wait to see if the clock turns off and if not + * then proceed with gating the clock. + */ + if (utmi_wait_register(base + USB_SUSP_CTRL, USB_PHY_CLK_VALID, 0) == 0) + return; + if (phy->is_legacy_phy) { val = readl(base + USB_SUSP_CTRL); val |= USB_SUSP_SET; @@ -351,6 +359,15 @@ static void utmi_phy_clk_enable(struct tegra_usb_phy *phy) unsigned long val; void __iomem *base = phy->regs; + /* + * The USB driver may have already initiated the phy clock + * enable so wait to see if the clock turns on and if not + * then proceed with ungating the clock. + */ + if (utmi_wait_register(base + USB_SUSP_CTRL, USB_PHY_CLK_VALID, + USB_PHY_CLK_VALID) == 0) + return; + if (phy->is_legacy_phy) { val = readl(base + USB_SUSP_CTRL); val |= USB_SUSP_CLR; diff --git a/kernel/drivers/usb/renesas_usbhs/fifo.c b/kernel/drivers/usb/renesas_usbhs/fifo.c index 68f26904c..50285b01d 100644 --- a/kernel/drivers/usb/renesas_usbhs/fifo.c +++ b/kernel/drivers/usb/renesas_usbhs/fifo.c @@ -857,9 +857,9 @@ static void xfer_work(struct work_struct *work) fifo->name, usbhs_pipe_number(pipe), pkt->length, pkt->zero); usbhs_pipe_running(pipe, 1); - usbhsf_dma_start(pipe, fifo); usbhs_pipe_set_trans_count_if_bulk(pipe, pkt->trans); dma_async_issue_pending(chan); + usbhsf_dma_start(pipe, fifo); usbhs_pipe_enable(pipe); xfer_work_end: diff --git a/kernel/drivers/usb/serial/console.c b/kernel/drivers/usb/serial/console.c index fdf89800e..43a862a90 100644 --- a/kernel/drivers/usb/serial/console.c +++ b/kernel/drivers/usb/serial/console.c @@ -186,6 +186,7 @@ static int usb_console_setup(struct console *co, char *options) tty_kref_put(tty); reset_open_count: port->port.count = 0; + info->port = NULL; usb_autopm_put_interface(serial->interface); error_get_interface: usb_serial_put(serial); @@ -265,7 +266,7 @@ static struct console usbcons = { void usb_serial_console_disconnect(struct usb_serial *serial) { - if (serial->port[0] == usbcons_info.port) { + if (serial->port[0] && serial->port[0] == usbcons_info.port) { usb_serial_console_exit(); usb_serial_put(serial); } diff --git a/kernel/drivers/usb/serial/cp210x.c b/kernel/drivers/usb/serial/cp210x.c index 2d945c9f9..412f81252 100644 --- a/kernel/drivers/usb/serial/cp210x.c +++ b/kernel/drivers/usb/serial/cp210x.c @@ -177,6 +177,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */ { USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */ { USB_DEVICE(0x18EF, 0xE025) }, /* ELV Marble Sound Board 1 */ + { USB_DEVICE(0x18EF, 0xE032) }, /* ELV TFD500 Data Logger */ { USB_DEVICE(0x1901, 0x0190) }, /* GE B850 CP2105 Recorder interface */ { USB_DEVICE(0x1901, 0x0193) }, /* GE B650 CP2104 PMC interface */ { USB_DEVICE(0x1901, 0x0194) }, /* GE Healthcare Remote Alarm Box */ @@ -352,6 +353,7 @@ static struct usb_serial_driver * const serial_drivers[] = { #define CP210X_PARTNUM_CP2104 0x04 #define CP210X_PARTNUM_CP2105 0x05 #define CP210X_PARTNUM_CP2108 0x08 +#define CP210X_PARTNUM_UNKNOWN 0xFF /* CP210X_GET_COMM_STATUS returns these 0x13 bytes */ struct cp210x_comm_status { @@ -1491,8 +1493,11 @@ static int cp210x_attach(struct usb_serial *serial) result = cp210x_read_vendor_block(serial, REQTYPE_DEVICE_TO_HOST, CP210X_GET_PARTNUM, &priv->partnum, sizeof(priv->partnum)); - if (result < 0) - goto err_free_priv; + if (result < 0) { + dev_warn(&serial->interface->dev, + "querying part number failed\n"); + priv->partnum = CP210X_PARTNUM_UNKNOWN; + } usb_set_serial_data(serial, priv); @@ -1505,10 +1510,6 @@ static int cp210x_attach(struct usb_serial *serial) } return 0; -err_free_priv: - kfree(priv); - - return result; } static void cp210x_disconnect(struct usb_serial *serial) diff --git a/kernel/drivers/usb/serial/ftdi_sio.c b/kernel/drivers/usb/serial/ftdi_sio.c index 1cec03799..49d1b2d46 100644 --- a/kernel/drivers/usb/serial/ftdi_sio.c +++ b/kernel/drivers/usb/serial/ftdi_sio.c @@ -1015,6 +1015,8 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(WICED_VID, WICED_USB20706V2_PID) }, { USB_DEVICE(TI_VID, TI_CC3200_LAUNCHPAD_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_BT_USB_PID) }, + { USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_WL_USB_PID) }, { } /* Terminating entry */ }; diff --git a/kernel/drivers/usb/serial/ftdi_sio_ids.h b/kernel/drivers/usb/serial/ftdi_sio_ids.h index 4fcf1cecb..f9d15bd62 100644 --- a/kernel/drivers/usb/serial/ftdi_sio_ids.h +++ b/kernel/drivers/usb/serial/ftdi_sio_ids.h @@ -609,6 +609,13 @@ #define ADI_GNICE_PID 0xF000 #define ADI_GNICEPLUS_PID 0xF001 +/* + * Cypress WICED USB UART + */ +#define CYPRESS_VID 0x04B4 +#define CYPRESS_WICED_BT_USB_PID 0x009B +#define CYPRESS_WICED_WL_USB_PID 0xF900 + /* * Microchip Technology, Inc. * diff --git a/kernel/drivers/usb/serial/option.c b/kernel/drivers/usb/serial/option.c index 54bfef139..ba672cf4e 100644 --- a/kernel/drivers/usb/serial/option.c +++ b/kernel/drivers/usb/serial/option.c @@ -522,6 +522,7 @@ static void option_instat_callback(struct urb *urb); /* TP-LINK Incorporated products */ #define TPLINK_VENDOR_ID 0x2357 +#define TPLINK_PRODUCT_LTE 0x000D #define TPLINK_PRODUCT_MA180 0x0201 /* Changhong products */ @@ -2011,6 +2012,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(CELLIENT_VENDOR_ID, CELLIENT_PRODUCT_MEN200) }, { USB_DEVICE(PETATEL_VENDOR_ID, PETATEL_PRODUCT_NP10T_600A) }, { USB_DEVICE(PETATEL_VENDOR_ID, PETATEL_PRODUCT_NP10T_600E) }, + { USB_DEVICE_AND_INTERFACE_INFO(TPLINK_VENDOR_ID, TPLINK_PRODUCT_LTE, 0xff, 0x00, 0x00) }, /* TP-Link LTE Module */ { USB_DEVICE(TPLINK_VENDOR_ID, TPLINK_PRODUCT_MA180), .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE(TPLINK_VENDOR_ID, 0x9000), /* TP-Link MA260 */ diff --git a/kernel/drivers/usb/serial/qcserial.c b/kernel/drivers/usb/serial/qcserial.c index ebc0beea6..eb9928963 100644 --- a/kernel/drivers/usb/serial/qcserial.c +++ b/kernel/drivers/usb/serial/qcserial.c @@ -174,6 +174,10 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x413c, 0x81b3)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {DEVICE_SWI(0x413c, 0x81b5)}, /* Dell Wireless 5811e QDL */ {DEVICE_SWI(0x413c, 0x81b6)}, /* Dell Wireless 5811e QDL */ + {DEVICE_SWI(0x413c, 0x81cf)}, /* Dell Wireless 5819 */ + {DEVICE_SWI(0x413c, 0x81d0)}, /* Dell Wireless 5819 */ + {DEVICE_SWI(0x413c, 0x81d1)}, /* Dell Wireless 5818 */ + {DEVICE_SWI(0x413c, 0x81d2)}, /* Dell Wireless 5818 */ /* Huawei devices */ {DEVICE_HWI(0x03f0, 0x581d)}, /* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */ diff --git a/kernel/fs/9p/vfs_addr.c b/kernel/fs/9p/vfs_addr.c index adaf6f6dd..e1cbdfdb7 100644 --- a/kernel/fs/9p/vfs_addr.c +++ b/kernel/fs/9p/vfs_addr.c @@ -310,9 +310,13 @@ static int v9fs_write_end(struct file *filp, struct address_space *mapping, p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping); - if (unlikely(copied < len && !PageUptodate(page))) { - copied = 0; - goto out; + if (!PageUptodate(page)) { + if (unlikely(copied < len)) { + copied = 0; + goto out; + } else if (len == PAGE_SIZE) { + SetPageUptodate(page); + } } /* * No need to use i_size_read() here, the i_size diff --git a/kernel/fs/binfmt_misc.c b/kernel/fs/binfmt_misc.c index 2a46762de..a7c5a9861 100644 --- a/kernel/fs/binfmt_misc.c +++ b/kernel/fs/binfmt_misc.c @@ -596,7 +596,7 @@ static void bm_evict_inode(struct inode *inode) { Node *e = inode->i_private; - if (e->flags & MISC_FMT_OPEN_FILE) + if (e && e->flags & MISC_FMT_OPEN_FILE) filp_close(e->interp_file, NULL); clear_inode(inode); diff --git a/kernel/fs/block_dev.c b/kernel/fs/block_dev.c index 93d088ffc..789f55e85 100644 --- a/kernel/fs/block_dev.c +++ b/kernel/fs/block_dev.c @@ -716,10 +716,12 @@ int bdev_write_page(struct block_device *bdev, sector_t sector, set_page_writeback(page); result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, true); - if (result) + if (result) { end_page_writeback(page); - else + } else { + clean_page_buffers(page); unlock_page(page); + } blk_queue_exit(bdev->bd_queue); return result; } diff --git a/kernel/fs/direct-io.c b/kernel/fs/direct-io.c index 62cf812ed..96415c65b 100644 --- a/kernel/fs/direct-io.c +++ b/kernel/fs/direct-io.c @@ -866,7 +866,8 @@ out: */ if (sdio->boundary) { ret = dio_send_cur_page(dio, sdio, map_bh); - dio_bio_submit(dio, sdio); + if (sdio->bio) + dio_bio_submit(dio, sdio); put_page(sdio->cur_page); sdio->cur_page = NULL; } diff --git a/kernel/fs/f2fs/f2fs.h b/kernel/fs/f2fs/f2fs.h index 9a7c90386..4b4a72f39 100644 --- a/kernel/fs/f2fs/f2fs.h +++ b/kernel/fs/f2fs/f2fs.h @@ -2525,7 +2525,7 @@ void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr); bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr); void refresh_sit_entry(struct f2fs_sb_info *sbi, block_t old, block_t new); void stop_discard_thread(struct f2fs_sb_info *sbi); -void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi); +void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi, bool umount); void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc); void release_discard_addrs(struct f2fs_sb_info *sbi); int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra); diff --git a/kernel/fs/f2fs/segment.c b/kernel/fs/f2fs/segment.c index 621b9b3d3..c695ff462 100644 --- a/kernel/fs/f2fs/segment.c +++ b/kernel/fs/f2fs/segment.c @@ -1210,11 +1210,11 @@ void stop_discard_thread(struct f2fs_sb_info *sbi) } /* This comes from f2fs_put_super and f2fs_trim_fs */ -void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi) +void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi, bool umount) { __issue_discard_cmd(sbi, false); __drop_discard_cmd(sbi); - __wait_discard_cmd(sbi, false); + __wait_discard_cmd(sbi, !umount); } static void mark_discard_range_all(struct f2fs_sb_info *sbi) @@ -2244,7 +2244,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) } /* It's time to issue all the filed discards */ mark_discard_range_all(sbi); - f2fs_wait_discard_bios(sbi); + f2fs_wait_discard_bios(sbi, false); out: range->len = F2FS_BLK_TO_BYTES(cpc.trimmed); return err; diff --git a/kernel/fs/f2fs/super.c b/kernel/fs/f2fs/super.c index 89f61eb3d..933c3d529 100644 --- a/kernel/fs/f2fs/super.c +++ b/kernel/fs/f2fs/super.c @@ -801,7 +801,7 @@ static void f2fs_put_super(struct super_block *sb) } /* be sure to wait for any on-going discard commands */ - f2fs_wait_discard_bios(sbi); + f2fs_wait_discard_bios(sbi, true); if (f2fs_discard_en(sbi) && !sbi->discard_blks) { struct cp_control cpc = { diff --git a/kernel/fs/mpage.c b/kernel/fs/mpage.c index 37bb77c13..c991faec7 100644 --- a/kernel/fs/mpage.c +++ b/kernel/fs/mpage.c @@ -468,6 +468,16 @@ static void clean_buffers(struct page *page, unsigned first_unmapped) try_to_free_buffers(page); } +/* + * For situations where we want to clean all buffers attached to a page. + * We don't need to calculate how many buffers are attached to the page, + * we just need to specify a number larger than the maximum number of buffers. + */ +void clean_page_buffers(struct page *page) +{ + clean_buffers(page, ~0U); +} + static int __mpage_writepage(struct page *page, struct writeback_control *wbc, void *data) { @@ -605,10 +615,8 @@ alloc_new: if (bio == NULL) { if (first_unmapped == blocks_per_page) { if (!bdev_write_page(bdev, blocks[0] << (blkbits - 9), - page, wbc)) { - clean_buffers(page, first_unmapped); + page, wbc)) goto out; - } } bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), BIO_MAX_PAGES, GFP_NOFS|__GFP_HIGH); diff --git a/kernel/fs/nfs/client.c b/kernel/fs/nfs/client.c index efebe6cf4..22880ef6d 100644 --- a/kernel/fs/nfs/client.c +++ b/kernel/fs/nfs/client.c @@ -218,7 +218,6 @@ static void nfs_cb_idr_remove_locked(struct nfs_client *clp) static void pnfs_init_server(struct nfs_server *server) { rpc_init_wait_queue(&server->roc_rpcwaitq, "pNFS ROC"); - rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC"); } #else @@ -888,6 +887,7 @@ struct nfs_server *nfs_alloc_server(void) ida_init(&server->openowner_id); ida_init(&server->lockowner_id); pnfs_init_server(server); + rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC"); return server; } diff --git a/kernel/fs/nfs/filelayout/filelayout.c b/kernel/fs/nfs/filelayout/filelayout.c index 44c638b78..508126eb4 100644 --- a/kernel/fs/nfs/filelayout/filelayout.c +++ b/kernel/fs/nfs/filelayout/filelayout.c @@ -745,7 +745,8 @@ filelayout_free_lseg(struct pnfs_layout_segment *lseg) struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); dprintk("--> %s\n", __func__); - nfs4_fl_put_deviceid(fl->dsaddr); + if (fl->dsaddr != NULL) + nfs4_fl_put_deviceid(fl->dsaddr); /* This assumes a single RW lseg */ if (lseg->pls_range.iomode == IOMODE_RW) { struct nfs4_filelayout *flo; diff --git a/kernel/fs/nfs/nfs4idmap.c b/kernel/fs/nfs/nfs4idmap.c index dd5d27da8..30426c1a1 100644 --- a/kernel/fs/nfs/nfs4idmap.c +++ b/kernel/fs/nfs/nfs4idmap.c @@ -274,7 +274,7 @@ static struct key *nfs_idmap_request_key(const char *name, size_t namelen, ssize_t ret; ret = nfs_idmap_get_desc(name, namelen, type, strlen(type), &desc); - if (ret <= 0) + if (ret < 0) return ERR_PTR(ret); rkey = request_key(&key_type_id_resolver, desc, ""); diff --git a/kernel/fs/nfs/nfs4proc.c b/kernel/fs/nfs/nfs4proc.c index 6c61e2b99..f90090e8c 100644 --- a/kernel/fs/nfs/nfs4proc.c +++ b/kernel/fs/nfs/nfs4proc.c @@ -8399,8 +8399,7 @@ nfs4_layoutget_handle_exception(struct rpc_task *task, lo = NFS_I(inode)->layout; /* If the open stateid was bad, then recover it. */ if (!lo || test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) || - nfs4_stateid_match_other(&lgp->args.stateid, - &lgp->args.ctx->state->stateid)) { + !nfs4_stateid_match_other(&lgp->args.stateid, &lo->plh_stateid)) { spin_unlock(&inode->i_lock); exception->state = lgp->args.ctx->state; exception->stateid = &lgp->args.stateid; diff --git a/kernel/fs/nfs/nfs4xdr.c b/kernel/fs/nfs/nfs4xdr.c index 37c8af003..14ed9791e 100644 --- a/kernel/fs/nfs/nfs4xdr.c +++ b/kernel/fs/nfs/nfs4xdr.c @@ -1842,8 +1842,8 @@ static void encode_create_session(struct xdr_stream *xdr, * Assumes OPEN is the biggest non-idempotent compound. * 2 is the verifier. */ - max_resp_sz_cached = (NFS4_dec_open_sz + RPC_REPHDRSIZE + - RPC_MAX_AUTH_SIZE + 2) * XDR_UNIT; + max_resp_sz_cached = (NFS4_dec_open_sz + RPC_REPHDRSIZE + 2) + * XDR_UNIT + RPC_MAX_AUTH_SIZE; encode_op_hdr(xdr, OP_CREATE_SESSION, decode_create_session_maxsz, hdr); p = reserve_space(xdr, 16 + 2*28 + 20 + clnt->cl_nodelen + 12); diff --git a/kernel/fs/nfsd/nfs4proc.c b/kernel/fs/nfsd/nfs4proc.c index 3c69db7d4..8487486ec 100644 --- a/kernel/fs/nfsd/nfs4proc.c +++ b/kernel/fs/nfsd/nfs4proc.c @@ -927,6 +927,13 @@ nfsd4_secinfo_release(union nfsd4_op_u *u) exp_put(u->secinfo.si_exp); } +static void +nfsd4_secinfo_no_name_release(union nfsd4_op_u *u) +{ + if (u->secinfo_no_name.sin_exp) + exp_put(u->secinfo_no_name.sin_exp); +} + static __be32 nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -2375,7 +2382,7 @@ static const struct nfsd4_operation nfsd4_ops[] = { }, [OP_SECINFO_NO_NAME] = { .op_func = nfsd4_secinfo_no_name, - .op_release = nfsd4_secinfo_release, + .op_release = nfsd4_secinfo_no_name_release, .op_flags = OP_HANDLES_WRONGSEC, .op_name = "OP_SECINFO_NO_NAME", .op_rsize_bop = nfsd4_secinfo_rsize, diff --git a/kernel/fs/quota/dquot.c b/kernel/fs/quota/dquot.c index 50b0556a1..52ad15192 100644 --- a/kernel/fs/quota/dquot.c +++ b/kernel/fs/quota/dquot.c @@ -1297,21 +1297,18 @@ static int dquot_add_space(struct dquot *dquot, qsize_t space, spin_lock(&dquot->dq_dqb_lock); if (!sb_has_quota_limits_enabled(sb, dquot->dq_id.type) || test_bit(DQ_FAKE_B, &dquot->dq_flags)) - goto add; + goto finish; tspace = dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace + space + rsv_space; - if (flags & DQUOT_SPACE_NOFAIL) - goto add; - if (dquot->dq_dqb.dqb_bhardlimit && tspace > dquot->dq_dqb.dqb_bhardlimit && !ignore_hardlimit(dquot)) { if (flags & DQUOT_SPACE_WARN) prepare_warning(warn, dquot, QUOTA_NL_BHARDWARN); ret = -EDQUOT; - goto out; + goto finish; } if (dquot->dq_dqb.dqb_bsoftlimit && @@ -1322,7 +1319,7 @@ static int dquot_add_space(struct dquot *dquot, qsize_t space, if (flags & DQUOT_SPACE_WARN) prepare_warning(warn, dquot, QUOTA_NL_BSOFTLONGWARN); ret = -EDQUOT; - goto out; + goto finish; } if (dquot->dq_dqb.dqb_bsoftlimit && @@ -1338,13 +1335,21 @@ static int dquot_add_space(struct dquot *dquot, qsize_t space, * be always printed */ ret = -EDQUOT; - goto out; + goto finish; } } -add: - dquot->dq_dqb.dqb_rsvspace += rsv_space; - dquot->dq_dqb.dqb_curspace += space; -out: +finish: + /* + * We have to be careful and go through warning generation & grace time + * setting even if DQUOT_SPACE_NOFAIL is set. That's why we check it + * only here... + */ + if (flags & DQUOT_SPACE_NOFAIL) + ret = 0; + if (!ret) { + dquot->dq_dqb.dqb_rsvspace += rsv_space; + dquot->dq_dqb.dqb_curspace += space; + } spin_unlock(&dquot->dq_dqb_lock); return ret; } diff --git a/kernel/fs/xfs/libxfs/xfs_alloc.c b/kernel/fs/xfs/libxfs/xfs_alloc.c index 744dcaec3..f965ce832 100644 --- a/kernel/fs/xfs/libxfs/xfs_alloc.c +++ b/kernel/fs/xfs/libxfs/xfs_alloc.c @@ -1584,6 +1584,10 @@ xfs_alloc_ag_vextent_small( bp = xfs_btree_get_bufs(args->mp, args->tp, args->agno, fbno, 0); + if (!bp) { + error = -EFSCORRUPTED; + goto error0; + } xfs_trans_binval(args->tp, bp); } args->len = 1; @@ -2141,6 +2145,10 @@ xfs_alloc_fix_freelist( if (error) goto out_agbp_relse; bp = xfs_btree_get_bufs(mp, tp, args->agno, bno, 0); + if (!bp) { + error = -EFSCORRUPTED; + goto out_agbp_relse; + } xfs_trans_binval(tp, bp); } diff --git a/kernel/fs/xfs/libxfs/xfs_bmap.c b/kernel/fs/xfs/libxfs/xfs_bmap.c index 044a36311..def32fa1c 100644 --- a/kernel/fs/xfs/libxfs/xfs_bmap.c +++ b/kernel/fs/xfs/libxfs/xfs_bmap.c @@ -1477,14 +1477,14 @@ xfs_bmap_isaeof( int is_empty; int error; - bma->aeof = 0; + bma->aeof = false; error = xfs_bmap_last_extent(NULL, bma->ip, whichfork, &rec, &is_empty); if (error) return error; if (is_empty) { - bma->aeof = 1; + bma->aeof = true; return 0; } diff --git a/kernel/fs/xfs/libxfs/xfs_ialloc.c b/kernel/fs/xfs/libxfs/xfs_ialloc.c index 988bb3f31..dfd643909 100644 --- a/kernel/fs/xfs/libxfs/xfs_ialloc.c +++ b/kernel/fs/xfs/libxfs/xfs_ialloc.c @@ -1962,7 +1962,7 @@ xfs_difree_inobt( if (!(mp->m_flags & XFS_MOUNT_IKEEP) && rec.ir_free == XFS_INOBT_ALL_FREE && mp->m_sb.sb_inopblock <= XFS_INODES_PER_CHUNK) { - xic->deleted = 1; + xic->deleted = true; xic->first_ino = XFS_AGINO_TO_INO(mp, agno, rec.ir_startino); xic->alloc = xfs_inobt_irec_to_allocmask(&rec); @@ -1989,7 +1989,7 @@ xfs_difree_inobt( xfs_difree_inode_chunk(mp, agno, &rec, dfops); } else { - xic->deleted = 0; + xic->deleted = false; error = xfs_inobt_update(cur, &rec); if (error) { diff --git a/kernel/fs/xfs/libxfs/xfs_log_format.h b/kernel/fs/xfs/libxfs/xfs_log_format.h index 8372e9bcd..71de18573 100644 --- a/kernel/fs/xfs/libxfs/xfs_log_format.h +++ b/kernel/fs/xfs/libxfs/xfs_log_format.h @@ -270,6 +270,7 @@ typedef struct xfs_inode_log_format { uint32_t ilf_fields; /* flags for fields logged */ uint16_t ilf_asize; /* size of attr d/ext/root */ uint16_t ilf_dsize; /* size of data/ext/root */ + uint32_t ilf_pad; /* pad for 64 bit boundary */ uint64_t ilf_ino; /* inode number */ union { uint32_t ilfu_rdev; /* rdev value for dev inode*/ @@ -280,7 +281,12 @@ typedef struct xfs_inode_log_format { int32_t ilf_boffset; /* off of inode in buffer */ } xfs_inode_log_format_t; -typedef struct xfs_inode_log_format_32 { +/* + * Old 32 bit systems will log in this format without the 64 bit + * alignment padding. Recovery will detect this and convert it to the + * correct format. + */ +struct xfs_inode_log_format_32 { uint16_t ilf_type; /* inode log item type */ uint16_t ilf_size; /* size of this item */ uint32_t ilf_fields; /* flags for fields logged */ @@ -294,24 +300,7 @@ typedef struct xfs_inode_log_format_32 { int64_t ilf_blkno; /* blkno of inode buffer */ int32_t ilf_len; /* len of inode buffer */ int32_t ilf_boffset; /* off of inode in buffer */ -} __attribute__((packed)) xfs_inode_log_format_32_t; - -typedef struct xfs_inode_log_format_64 { - uint16_t ilf_type; /* inode log item type */ - uint16_t ilf_size; /* size of this item */ - uint32_t ilf_fields; /* flags for fields logged */ - uint16_t ilf_asize; /* size of attr d/ext/root */ - uint16_t ilf_dsize; /* size of data/ext/root */ - uint32_t ilf_pad; /* pad for 64 bit boundary */ - uint64_t ilf_ino; /* inode number */ - union { - uint32_t ilfu_rdev; /* rdev value for dev inode*/ - uuid_t ilfu_uuid; /* mount point value */ - } ilf_u; - int64_t ilf_blkno; /* blkno of inode buffer */ - int32_t ilf_len; /* len of inode buffer */ - int32_t ilf_boffset; /* off of inode in buffer */ -} xfs_inode_log_format_64_t; +} __attribute__((packed)); /* diff --git a/kernel/fs/xfs/xfs_acl.c b/kernel/fs/xfs/xfs_acl.c index 7034e1753..3354140de 100644 --- a/kernel/fs/xfs/xfs_acl.c +++ b/kernel/fs/xfs/xfs_acl.c @@ -247,6 +247,8 @@ xfs_set_mode(struct inode *inode, umode_t mode) int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) { + umode_t mode; + bool set_mode = false; int error = 0; if (!acl) @@ -257,16 +259,24 @@ xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) return error; if (type == ACL_TYPE_ACCESS) { - umode_t mode; - error = posix_acl_update_mode(inode, &mode, &acl); if (error) return error; - error = xfs_set_mode(inode, mode); - if (error) - return error; + set_mode = true; } set_acl: - return __xfs_set_acl(inode, acl, type); + error = __xfs_set_acl(inode, acl, type); + if (error) + return error; + + /* + * We set the mode after successfully updating the ACL xattr because the + * xattr update can fail at ENOSPC and we don't want to change the mode + * if the ACL update hasn't been applied. + */ + if (set_mode) + error = xfs_set_mode(inode, mode); + + return error; } diff --git a/kernel/fs/xfs/xfs_attr_inactive.c b/kernel/fs/xfs/xfs_attr_inactive.c index ebd66b19f..e3a950ed3 100644 --- a/kernel/fs/xfs/xfs_attr_inactive.c +++ b/kernel/fs/xfs/xfs_attr_inactive.c @@ -302,6 +302,8 @@ xfs_attr3_node_inactive( &bp, XFS_ATTR_FORK); if (error) return error; + node = bp->b_addr; + btree = dp->d_ops->node_tree_p(node); child_fsb = be32_to_cpu(btree[i + 1].before); xfs_trans_brelse(*trans, bp); } diff --git a/kernel/fs/xfs/xfs_bmap_util.c b/kernel/fs/xfs/xfs_bmap_util.c index e9db7fc95..6503cfa44 100644 --- a/kernel/fs/xfs/xfs_bmap_util.c +++ b/kernel/fs/xfs/xfs_bmap_util.c @@ -84,6 +84,7 @@ xfs_zero_extent( GFP_NOFS, 0); } +#ifdef CONFIG_XFS_RT int xfs_bmap_rtalloc( struct xfs_bmalloca *ap) /* bmap alloc argument struct */ @@ -190,6 +191,7 @@ xfs_bmap_rtalloc( } return 0; } +#endif /* CONFIG_XFS_RT */ /* * Check if the endoff is outside the last extent. If so the caller will grow diff --git a/kernel/fs/xfs/xfs_bmap_util.h b/kernel/fs/xfs/xfs_bmap_util.h index 0eaa81dc4..7d330b3c7 100644 --- a/kernel/fs/xfs/xfs_bmap_util.h +++ b/kernel/fs/xfs/xfs_bmap_util.h @@ -28,7 +28,20 @@ struct xfs_mount; struct xfs_trans; struct xfs_bmalloca; +#ifdef CONFIG_XFS_RT int xfs_bmap_rtalloc(struct xfs_bmalloca *ap); +#else /* !CONFIG_XFS_RT */ +/* + * Attempts to allocate RT extents when RT is disable indicates corruption and + * should trigger a shutdown. + */ +static inline int +xfs_bmap_rtalloc(struct xfs_bmalloca *ap) +{ + return -EFSCORRUPTED; +} +#endif /* CONFIG_XFS_RT */ + int xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff, int whichfork, int *eof); int xfs_bmap_punch_delalloc_range(struct xfs_inode *ip, diff --git a/kernel/fs/xfs/xfs_file.c b/kernel/fs/xfs/xfs_file.c index 309e26c9d..56d0e5268 100644 --- a/kernel/fs/xfs/xfs_file.c +++ b/kernel/fs/xfs/xfs_file.c @@ -764,7 +764,7 @@ xfs_file_fallocate( enum xfs_prealloc_flags flags = 0; uint iolock = XFS_IOLOCK_EXCL; loff_t new_size = 0; - bool do_file_insert = 0; + bool do_file_insert = false; if (!S_ISREG(inode->i_mode)) return -EINVAL; @@ -825,7 +825,7 @@ xfs_file_fallocate( error = -EINVAL; goto out_unlock; } - do_file_insert = 1; + do_file_insert = true; } else { flags |= XFS_PREALLOC_SET; diff --git a/kernel/fs/xfs/xfs_fsmap.c b/kernel/fs/xfs/xfs_fsmap.c index 814ed7298..560e0b40a 100644 --- a/kernel/fs/xfs/xfs_fsmap.c +++ b/kernel/fs/xfs/xfs_fsmap.c @@ -521,6 +521,7 @@ __xfs_getfsmap_rtdev( return query_fn(tp, info); } +#ifdef CONFIG_XFS_RT /* Actually query the realtime bitmap. */ STATIC int xfs_getfsmap_rtdev_rtbitmap_query( @@ -561,6 +562,7 @@ xfs_getfsmap_rtdev_rtbitmap( return __xfs_getfsmap_rtdev(tp, keys, xfs_getfsmap_rtdev_rtbitmap_query, info); } +#endif /* CONFIG_XFS_RT */ /* Execute a getfsmap query against the regular data device. */ STATIC int @@ -795,7 +797,15 @@ xfs_getfsmap_check_keys( return false; } +/* + * There are only two devices if we didn't configure RT devices at build time. + */ +#ifdef CONFIG_XFS_RT #define XFS_GETFSMAP_DEVS 3 +#else +#define XFS_GETFSMAP_DEVS 2 +#endif /* CONFIG_XFS_RT */ + /* * Get filesystem's extents as described in head, and format for * output. Calls formatter to fill the user's buffer until all @@ -853,10 +863,12 @@ xfs_getfsmap( handlers[1].dev = new_encode_dev(mp->m_logdev_targp->bt_dev); handlers[1].fn = xfs_getfsmap_logdev; } +#ifdef CONFIG_XFS_RT if (mp->m_rtdev_targp) { handlers[2].dev = new_encode_dev(mp->m_rtdev_targp->bt_dev); handlers[2].fn = xfs_getfsmap_rtdev_rtbitmap; } +#endif /* CONFIG_XFS_RT */ xfs_sort(handlers, XFS_GETFSMAP_DEVS, sizeof(struct xfs_getfsmap_dev), xfs_getfsmap_dev_compare); diff --git a/kernel/fs/xfs/xfs_inode_item.c b/kernel/fs/xfs/xfs_inode_item.c index a705f34b5..9bbc2d7cc 100644 --- a/kernel/fs/xfs/xfs_inode_item.c +++ b/kernel/fs/xfs/xfs_inode_item.c @@ -364,6 +364,9 @@ xfs_inode_to_log_dinode( to->di_dmstate = from->di_dmstate; to->di_flags = from->di_flags; + /* log a dummy value to ensure log structure is fully initialised */ + to->di_next_unlinked = NULLAGINO; + if (from->di_version == 3) { to->di_changecount = inode->i_version; to->di_crtime.t_sec = from->di_crtime.t_sec; @@ -404,6 +407,11 @@ xfs_inode_item_format_core( * the second with the on-disk inode structure, and a possible third and/or * fourth with the inode data/extents/b-tree root and inode attributes * data/extents/b-tree root. + * + * Note: Always use the 64 bit inode log format structure so we don't + * leave an uninitialised hole in the format item on 64 bit systems. Log + * recovery on 32 bit systems handles this just fine, so there's no reason + * for not using an initialising the properly padded structure all the time. */ STATIC void xfs_inode_item_format( @@ -412,8 +420,8 @@ xfs_inode_item_format( { struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; - struct xfs_inode_log_format *ilf; struct xfs_log_iovec *vecp = NULL; + struct xfs_inode_log_format *ilf; ASSERT(ip->i_d.di_version > 1); @@ -425,7 +433,17 @@ xfs_inode_item_format( ilf->ilf_boffset = ip->i_imap.im_boffset; ilf->ilf_fields = XFS_ILOG_CORE; ilf->ilf_size = 2; /* format + core */ - xlog_finish_iovec(lv, vecp, sizeof(struct xfs_inode_log_format)); + + /* + * make sure we don't leak uninitialised data into the log in the case + * when we don't log every field in the inode. + */ + ilf->ilf_dsize = 0; + ilf->ilf_asize = 0; + ilf->ilf_pad = 0; + uuid_copy(&ilf->ilf_u.ilfu_uuid, &uuid_null); + + xlog_finish_iovec(lv, vecp, sizeof(*ilf)); xfs_inode_item_format_core(ip, lv, &vecp); xfs_inode_item_format_data_fork(iip, ilf, lv, &vecp); @@ -855,44 +873,29 @@ xfs_istale_done( } /* - * convert an xfs_inode_log_format struct from either 32 or 64 bit versions - * (which can have different field alignments) to the native version + * convert an xfs_inode_log_format struct from the old 32 bit version + * (which can have different field alignments) to the native 64 bit version */ int xfs_inode_item_format_convert( - xfs_log_iovec_t *buf, - xfs_inode_log_format_t *in_f) + struct xfs_log_iovec *buf, + struct xfs_inode_log_format *in_f) { - if (buf->i_len == sizeof(xfs_inode_log_format_32_t)) { - xfs_inode_log_format_32_t *in_f32 = buf->i_addr; + struct xfs_inode_log_format_32 *in_f32 = buf->i_addr; - in_f->ilf_type = in_f32->ilf_type; - in_f->ilf_size = in_f32->ilf_size; - in_f->ilf_fields = in_f32->ilf_fields; - in_f->ilf_asize = in_f32->ilf_asize; - in_f->ilf_dsize = in_f32->ilf_dsize; - in_f->ilf_ino = in_f32->ilf_ino; - /* copy biggest field of ilf_u */ - uuid_copy(&in_f->ilf_u.ilfu_uuid, &in_f32->ilf_u.ilfu_uuid); - in_f->ilf_blkno = in_f32->ilf_blkno; - in_f->ilf_len = in_f32->ilf_len; - in_f->ilf_boffset = in_f32->ilf_boffset; - return 0; - } else if (buf->i_len == sizeof(xfs_inode_log_format_64_t)){ - xfs_inode_log_format_64_t *in_f64 = buf->i_addr; + if (buf->i_len != sizeof(*in_f32)) + return -EFSCORRUPTED; - in_f->ilf_type = in_f64->ilf_type; - in_f->ilf_size = in_f64->ilf_size; - in_f->ilf_fields = in_f64->ilf_fields; - in_f->ilf_asize = in_f64->ilf_asize; - in_f->ilf_dsize = in_f64->ilf_dsize; - in_f->ilf_ino = in_f64->ilf_ino; - /* copy biggest field of ilf_u */ - uuid_copy(&in_f->ilf_u.ilfu_uuid, &in_f64->ilf_u.ilfu_uuid); - in_f->ilf_blkno = in_f64->ilf_blkno; - in_f->ilf_len = in_f64->ilf_len; - in_f->ilf_boffset = in_f64->ilf_boffset; - return 0; - } - return -EFSCORRUPTED; + in_f->ilf_type = in_f32->ilf_type; + in_f->ilf_size = in_f32->ilf_size; + in_f->ilf_fields = in_f32->ilf_fields; + in_f->ilf_asize = in_f32->ilf_asize; + in_f->ilf_dsize = in_f32->ilf_dsize; + in_f->ilf_ino = in_f32->ilf_ino; + /* copy biggest field of ilf_u */ + uuid_copy(&in_f->ilf_u.ilfu_uuid, &in_f32->ilf_u.ilfu_uuid); + in_f->ilf_blkno = in_f32->ilf_blkno; + in_f->ilf_len = in_f32->ilf_len; + in_f->ilf_boffset = in_f32->ilf_boffset; + return 0; } diff --git a/kernel/fs/xfs/xfs_log.c b/kernel/fs/xfs/xfs_log.c index c5107c7bc..dc95a49d6 100644 --- a/kernel/fs/xfs/xfs_log.c +++ b/kernel/fs/xfs/xfs_log.c @@ -2515,7 +2515,7 @@ next_lv: if (lv) vecp = lv->lv_iovecp; } - if (record_cnt == 0 && ordered == false) { + if (record_cnt == 0 && !ordered) { if (!lv) return 0; break; diff --git a/kernel/fs/xfs/xfs_mount.c b/kernel/fs/xfs/xfs_mount.c index ea7d4b4e5..e9727d0a5 100644 --- a/kernel/fs/xfs/xfs_mount.c +++ b/kernel/fs/xfs/xfs_mount.c @@ -704,7 +704,7 @@ xfs_mountfs( xfs_set_maxicount(mp); /* enable fail_at_unmount as default */ - mp->m_fail_unmount = 1; + mp->m_fail_unmount = true; error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype, NULL, mp->m_fsname); if (error) diff --git a/kernel/fs/xfs/xfs_ondisk.h b/kernel/fs/xfs/xfs_ondisk.h index 0c381d71b..0492436a0 100644 --- a/kernel/fs/xfs/xfs_ondisk.h +++ b/kernel/fs/xfs/xfs_ondisk.h @@ -134,7 +134,7 @@ xfs_check_ondisk_structs(void) XFS_CHECK_STRUCT_SIZE(struct xfs_icreate_log, 28); XFS_CHECK_STRUCT_SIZE(struct xfs_ictimestamp, 8); XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_32, 52); - XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_64, 56); + XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format, 56); XFS_CHECK_STRUCT_SIZE(struct xfs_qoff_logformat, 20); XFS_CHECK_STRUCT_SIZE(struct xfs_trans_header, 16); } diff --git a/kernel/include/linux/bpf.h b/kernel/include/linux/bpf.h index 8390859e7..f1af7d63d 100644 --- a/kernel/include/linux/bpf.h +++ b/kernel/include/linux/bpf.h @@ -368,6 +368,11 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { } +static inline int bpf_obj_get_user(const char __user *pathname) +{ + return -EOPNOTSUPP; +} + static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { diff --git a/kernel/include/linux/buffer_head.h b/kernel/include/linux/buffer_head.h index c8dae555e..446b24cac 100644 --- a/kernel/include/linux/buffer_head.h +++ b/kernel/include/linux/buffer_head.h @@ -232,6 +232,7 @@ int generic_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page *, void *); void page_zero_new_buffers(struct page *page, unsigned from, unsigned to); +void clean_page_buffers(struct page *page); int cont_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t *, loff_t *); diff --git a/kernel/include/linux/hyperv.h b/kernel/include/linux/hyperv.h index c458d7b7a..643108781 100644 --- a/kernel/include/linux/hyperv.h +++ b/kernel/include/linux/hyperv.h @@ -1403,7 +1403,7 @@ extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, const int *srv_version, int srv_vercnt, int *nego_fw_version, int *nego_srv_version); -void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid); +void hv_process_channel_removal(u32 relid); void vmbus_setevent(struct vmbus_channel *channel); /* diff --git a/kernel/include/linux/kernel.h b/kernel/include/linux/kernel.h index 0ad4c3044..91189bb0c 100644 --- a/kernel/include/linux/kernel.h +++ b/kernel/include/linux/kernel.h @@ -44,6 +44,12 @@ #define STACK_MAGIC 0xdeadbeef +/** + * REPEAT_BYTE - repeat the value @x multiple times as an unsigned long value + * @x: value to repeat + * + * NOTE: @x is not checked for > 0xff; larger values produce odd results. + */ #define REPEAT_BYTE(x) ((~0ul / 0xff) * (x)) /* @a is a power of 2 value */ @@ -57,6 +63,10 @@ #define READ 0 #define WRITE 1 +/** + * ARRAY_SIZE - get the number of elements in array @arr + * @arr: array to be sized + */ #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr)) #define u64_to_user_ptr(x) ( \ @@ -76,7 +86,15 @@ #define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) #define round_down(x, y) ((x) & ~__round_mask(x, y)) +/** + * FIELD_SIZEOF - get the size of a struct's field + * @t: the target struct + * @f: the target struct's field + * Return: the size of @f in the struct definition without having a + * declared instance of @t. + */ #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) + #define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP #define DIV_ROUND_DOWN_ULL(ll, d) \ @@ -107,7 +125,7 @@ /* * Divide positive or negative dividend by positive or negative divisor * and round to closest integer. Result is undefined for negative - * divisors if he dividend variable type is unsigned and for negative + * divisors if the dividend variable type is unsigned and for negative * dividends if the divisor variable type is unsigned. */ #define DIV_ROUND_CLOSEST(x, divisor)( \ @@ -247,13 +265,13 @@ extern int _cond_resched(void); * @ep_ro: right open interval endpoint * * Perform a "reciprocal multiplication" in order to "scale" a value into - * range [0, ep_ro), where the upper interval endpoint is right-open. + * range [0, @ep_ro), where the upper interval endpoint is right-open. * This is useful, e.g. for accessing a index of an array containing - * ep_ro elements, for example. Think of it as sort of modulus, only that + * @ep_ro elements, for example. Think of it as sort of modulus, only that * the result isn't that of modulo. ;) Note that if initial input is a * small value, then result will return 0. * - * Return: a result based on val in interval [0, ep_ro). + * Return: a result based on @val in interval [0, @ep_ro). */ static inline u32 reciprocal_scale(u32 val, u32 ep_ro) { @@ -618,8 +636,8 @@ do { \ * trace_printk - printf formatting in the ftrace buffer * @fmt: the printf format for printing * - * Note: __trace_printk is an internal function for trace_printk and - * the @ip is passed in via the trace_printk macro. + * Note: __trace_printk is an internal function for trace_printk() and + * the @ip is passed in via the trace_printk() macro. * * This function allows a kernel developer to debug fast path sections * that printk is not appropriate for. By scattering in various @@ -629,7 +647,7 @@ do { \ * This is intended as a debugging tool for the developer only. * Please refrain from leaving trace_printks scattered around in * your code. (Extra memory is used for special buffers that are - * allocated when trace_printk() is used) + * allocated when trace_printk() is used.) * * A little optization trick is done here. If there's only one * argument, there's no need to scan the string for printf formats. @@ -681,7 +699,7 @@ int __trace_printk(unsigned long ip, const char *fmt, ...); * the @ip is passed in via the trace_puts macro. * * This is similar to trace_printk() but is made for those really fast - * paths that a developer wants the least amount of "Heisenbug" affects, + * paths that a developer wants the least amount of "Heisenbug" effects, * where the processing of the print format is still too much. * * This function allows a kernel developer to debug fast path sections @@ -692,7 +710,7 @@ int __trace_printk(unsigned long ip, const char *fmt, ...); * This is intended as a debugging tool for the developer only. * Please refrain from leaving trace_puts scattered around in * your code. (Extra memory is used for special buffers that are - * allocated when trace_puts() is used) + * allocated when trace_puts() is used.) * * Returns: 0 if nothing was written, positive # if string was. * (1 when __trace_bputs is used, strlen(str) when __trace_puts is used) @@ -771,6 +789,12 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } t2 min2 = (y); \ (void) (&min1 == &min2); \ min1 < min2 ? min1 : min2; }) + +/** + * min - return minimum of two values of the same or compatible types + * @x: first value + * @y: second value + */ #define min(x, y) \ __min(typeof(x), typeof(y), \ __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ @@ -781,12 +805,31 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } t2 max2 = (y); \ (void) (&max1 == &max2); \ max1 > max2 ? max1 : max2; }) + +/** + * max - return maximum of two values of the same or compatible types + * @x: first value + * @y: second value + */ #define max(x, y) \ __max(typeof(x), typeof(y), \ __UNIQUE_ID(max1_), __UNIQUE_ID(max2_), \ x, y) +/** + * min3 - return minimum of three values + * @x: first value + * @y: second value + * @z: third value + */ #define min3(x, y, z) min((typeof(x))min(x, y), z) + +/** + * max3 - return maximum of three values + * @x: first value + * @y: second value + * @z: third value + */ #define max3(x, y, z) max((typeof(x))max(x, y), z) /** @@ -805,8 +848,8 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * @lo: lowest allowable value * @hi: highest allowable value * - * This macro does strict typechecking of lo/hi to make sure they are of the - * same type as val. See the unnecessary pointer comparisons. + * This macro does strict typechecking of @lo/@hi to make sure they are of the + * same type as @val. See the unnecessary pointer comparisons. */ #define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi) @@ -816,11 +859,24 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * * Or not use min/max/clamp at all, of course. */ + +/** + * min_t - return minimum of two values, using the specified type + * @type: data type to use + * @x: first value + * @y: second value + */ #define min_t(type, x, y) \ __min(type, type, \ __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ x, y) +/** + * max_t - return maximum of two values, using the specified type + * @type: data type to use + * @x: first value + * @y: second value + */ #define max_t(type, x, y) \ __max(type, type, \ __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ @@ -834,7 +890,7 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * @hi: maximum allowable value * * This macro does no typechecking and uses temporary variables of type - * 'type' to make all the comparisons. + * @type to make all the comparisons. */ #define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi) @@ -845,15 +901,17 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * @hi: maximum allowable value * * This macro does no typechecking and uses temporary variables of whatever - * type the input argument 'val' is. This is useful when val is an unsigned - * type and min and max are literals that will otherwise be assigned a signed + * type the input argument @val is. This is useful when @val is an unsigned + * type and @lo and @hi are literals that will otherwise be assigned a signed * integer type. */ #define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi) -/* - * swap - swap value of @a and @b +/** + * swap - swap values of @a and @b + * @a: first value + * @b: second value */ #define swap(a, b) \ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) diff --git a/kernel/include/linux/netfilter_bridge/ebtables.h b/kernel/include/linux/netfilter_bridge/ebtables.h index 2c2a5514b..528b24c78 100644 --- a/kernel/include/linux/netfilter_bridge/ebtables.h +++ b/kernel/include/linux/netfilter_bridge/ebtables.h @@ -108,9 +108,10 @@ struct ebt_table { #define EBT_ALIGN(s) (((s) + (__alignof__(struct _xt_align)-1)) & \ ~(__alignof__(struct _xt_align)-1)) -extern struct ebt_table *ebt_register_table(struct net *net, - const struct ebt_table *table, - const struct nf_hook_ops *); +extern int ebt_register_table(struct net *net, + const struct ebt_table *table, + const struct nf_hook_ops *ops, + struct ebt_table **res); extern void ebt_unregister_table(struct net *net, struct ebt_table *table, const struct nf_hook_ops *); extern unsigned int ebt_do_table(struct sk_buff *skb, diff --git a/kernel/include/linux/of.h b/kernel/include/linux/of.h index cfc34117f..b240ed69d 100644 --- a/kernel/include/linux/of.h +++ b/kernel/include/linux/of.h @@ -734,6 +734,16 @@ static inline struct device_node *of_get_cpu_node(int cpu, return NULL; } +static inline int of_n_addr_cells(struct device_node *np) +{ + return 0; + +} +static inline int of_n_size_cells(struct device_node *np) +{ + return 0; +} + static inline int of_property_read_u64(const struct device_node *np, const char *propname, u64 *out_value) { diff --git a/kernel/include/linux/sched/topology.h b/kernel/include/linux/sched/topology.h index d7b6dab95..7d065abc7 100644 --- a/kernel/include/linux/sched/topology.h +++ b/kernel/include/linux/sched/topology.h @@ -71,14 +71,6 @@ struct sched_domain_shared { atomic_t ref; atomic_t nr_busy_cpus; int has_idle_cores; - - /* - * Some variables from the most recent sd_lb_stats for this domain, - * used by wake_affine(). - */ - unsigned long nr_running; - unsigned long load; - unsigned long capacity; }; struct sched_domain { diff --git a/kernel/include/linux/thread_info.h b/kernel/include/linux/thread_info.h index 905d769d8..5f7eeab99 100644 --- a/kernel/include/linux/thread_info.h +++ b/kernel/include/linux/thread_info.h @@ -42,7 +42,7 @@ enum { #define THREAD_ALIGN THREAD_SIZE #endif -#ifdef CONFIG_DEBUG_STACK_USAGE +#if IS_ENABLED(CONFIG_DEBUG_STACK_USAGE) || IS_ENABLED(CONFIG_DEBUG_KMEMLEAK) # define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | \ __GFP_ZERO) #else diff --git a/kernel/include/sound/seq_virmidi.h b/kernel/include/sound/seq_virmidi.h index a03acd0d3..695257ae6 100644 --- a/kernel/include/sound/seq_virmidi.h +++ b/kernel/include/sound/seq_virmidi.h @@ -60,6 +60,7 @@ struct snd_virmidi_dev { int port; /* created/attached port */ unsigned int flags; /* SNDRV_VIRMIDI_* */ rwlock_t filelist_lock; + struct rw_semaphore filelist_sem; struct list_head filelist; }; diff --git a/kernel/include/uapi/linux/netfilter/xt_bpf.h b/kernel/include/uapi/linux/netfilter/xt_bpf.h index b97725af2..da161b56c 100644 --- a/kernel/include/uapi/linux/netfilter/xt_bpf.h +++ b/kernel/include/uapi/linux/netfilter/xt_bpf.h @@ -23,6 +23,7 @@ enum xt_bpf_modes { XT_BPF_MODE_FD_PINNED, XT_BPF_MODE_FD_ELF, }; +#define XT_BPF_MODE_PATH_PINNED XT_BPF_MODE_FD_PINNED struct xt_bpf_info_v1 { __u16 mode; diff --git a/kernel/kernel/bpf/inode.c b/kernel/kernel/bpf/inode.c index e833ed914..be1dde967 100644 --- a/kernel/kernel/bpf/inode.c +++ b/kernel/kernel/bpf/inode.c @@ -363,6 +363,7 @@ out: putname(pname); return ret; } +EXPORT_SYMBOL_GPL(bpf_obj_get_user); static void bpf_evict_inode(struct inode *inode) { diff --git a/kernel/kernel/bpf/verifier.c b/kernel/kernel/bpf/verifier.c index b914fbe13..8b8d6ba39 100644 --- a/kernel/kernel/bpf/verifier.c +++ b/kernel/kernel/bpf/verifier.c @@ -653,6 +653,10 @@ static void mark_reg_read(const struct bpf_verifier_state *state, u32 regno) { struct bpf_verifier_state *parent = state->parent; + if (regno == BPF_REG_FP) + /* We don't need to worry about FP liveness because it's read-only */ + return; + while (parent) { /* if read wasn't screened by an earlier write ... */ if (state->regs[regno].live & REG_LIVE_WRITTEN) @@ -2345,6 +2349,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) * copy register state to dest reg */ regs[insn->dst_reg] = regs[insn->src_reg]; + regs[insn->dst_reg].live |= REG_LIVE_WRITTEN; } else { /* R1 = (u32) R2 */ if (is_pointer_value(env, insn->src_reg)) { diff --git a/kernel/kernel/events/core.c b/kernel/kernel/events/core.c index 6bc21e202..9d93db81f 100644 --- a/kernel/kernel/events/core.c +++ b/kernel/kernel/events/core.c @@ -662,7 +662,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) /* * Do not update time when cgroup is not active */ - if (cgrp == event->cgrp) + if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) __update_cgrp_time(event->cgrp); } @@ -8955,6 +8955,14 @@ static struct perf_cpu_context __percpu *find_pmu_context(int ctxn) static void free_pmu_context(struct pmu *pmu) { + /* + * Static contexts such as perf_sw_context have a global lifetime + * and may be shared between different PMUs. Avoid freeing them + * when a single PMU is going away. + */ + if (pmu->task_ctx_nr > perf_invalid_context) + return; + mutex_lock(&pmus_lock); free_percpu(pmu->pmu_cpu_context); mutex_unlock(&pmus_lock); diff --git a/kernel/kernel/exit.c b/kernel/kernel/exit.c index f2cd53e92..cf2852884 100644 --- a/kernel/kernel/exit.c +++ b/kernel/kernel/exit.c @@ -1610,6 +1610,9 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, if (!infop) return err; + if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop))) + goto Efault; + user_access_begin(); unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); @@ -1735,6 +1738,9 @@ COMPAT_SYSCALL_DEFINE5(waitid, if (!infop) return err; + if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop))) + goto Efault; + user_access_begin(); unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); diff --git a/kernel/kernel/fork.c b/kernel/kernel/fork.c index e702cb9ff..07cc74369 100644 --- a/kernel/kernel/fork.c +++ b/kernel/kernel/fork.c @@ -215,6 +215,10 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) if (!s) continue; +#ifdef CONFIG_DEBUG_KMEMLEAK + /* Clear stale pointers from reused stack. */ + memset(s->addr, 0, THREAD_SIZE); +#endif tsk->stack_vm_area = s; return s->addr; } diff --git a/kernel/kernel/irq/chip.c b/kernel/kernel/irq/chip.c index 6fc89fd93..5a2ef92c2 100644 --- a/kernel/kernel/irq/chip.c +++ b/kernel/kernel/irq/chip.c @@ -265,8 +265,8 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force) irq_setup_affinity(desc); break; case IRQ_STARTUP_MANAGED: + irq_do_set_affinity(d, aff, false); ret = __irq_startup(desc); - irq_set_affinity_locked(d, aff, false); break; case IRQ_STARTUP_ABORT: return 0; diff --git a/kernel/kernel/irq/cpuhotplug.c b/kernel/kernel/irq/cpuhotplug.c index 638eb9c83..9eb09aef0 100644 --- a/kernel/kernel/irq/cpuhotplug.c +++ b/kernel/kernel/irq/cpuhotplug.c @@ -18,8 +18,34 @@ static inline bool irq_needs_fixup(struct irq_data *d) { const struct cpumask *m = irq_data_get_effective_affinity_mask(d); + unsigned int cpu = smp_processor_id(); - return cpumask_test_cpu(smp_processor_id(), m); +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + /* + * The cpumask_empty() check is a workaround for interrupt chips, + * which do not implement effective affinity, but the architecture has + * enabled the config switch. Use the general affinity mask instead. + */ + if (cpumask_empty(m)) + m = irq_data_get_affinity_mask(d); + + /* + * Sanity check. If the mask is not empty when excluding the outgoing + * CPU then it must contain at least one online CPU. The outgoing CPU + * has been removed from the online mask already. + */ + if (cpumask_any_but(m, cpu) < nr_cpu_ids && + cpumask_any_and(m, cpu_online_mask) >= nr_cpu_ids) { + /* + * If this happens then there was a missed IRQ fixup at some + * point. Warn about it and enforce fixup. + */ + pr_warn("Eff. affinity %*pbl of IRQ %u contains only offline CPUs after offlining CPU %u\n", + cpumask_pr_args(m), d->irq, cpu); + return true; + } +#endif + return cpumask_test_cpu(cpu, m); } static bool migrate_one_irq(struct irq_desc *desc) diff --git a/kernel/kernel/irq/manage.c b/kernel/kernel/irq/manage.c index d00132b5c..4bff6a10a 100644 --- a/kernel/kernel/irq/manage.c +++ b/kernel/kernel/irq/manage.c @@ -168,6 +168,19 @@ void irq_set_thread_affinity(struct irq_desc *desc) set_bit(IRQTF_AFFINITY, &action->thread_flags); } +static void irq_validate_effective_affinity(struct irq_data *data) +{ +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + const struct cpumask *m = irq_data_get_effective_affinity_mask(data); + struct irq_chip *chip = irq_data_get_irq_chip(data); + + if (!cpumask_empty(m)) + return; + pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n", + chip->name, data->irq); +#endif +} + int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -175,12 +188,16 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, struct irq_chip *chip = irq_data_get_irq_chip(data); int ret; + if (!chip || !chip->irq_set_affinity) + return -EINVAL; + ret = chip->irq_set_affinity(data, mask, force); switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: cpumask_copy(desc->irq_common_data.affinity, mask); case IRQ_SET_MASK_OK_NOCOPY: + irq_validate_effective_affinity(data); irq_set_thread_affinity(desc); ret = 0; } diff --git a/kernel/kernel/livepatch/core.c b/kernel/kernel/livepatch/core.c index b9628e43c..bf8c8fd72 100644 --- a/kernel/kernel/livepatch/core.c +++ b/kernel/kernel/livepatch/core.c @@ -830,6 +830,41 @@ int klp_register_patch(struct klp_patch *patch) } EXPORT_SYMBOL_GPL(klp_register_patch); +/* + * Remove parts of patches that touch a given kernel module. The list of + * patches processed might be limited. When limit is NULL, all patches + * will be handled. + */ +static void klp_cleanup_module_patches_limited(struct module *mod, + struct klp_patch *limit) +{ + struct klp_patch *patch; + struct klp_object *obj; + + list_for_each_entry(patch, &klp_patches, list) { + if (patch == limit) + break; + + klp_for_each_object(patch, obj) { + if (!klp_is_module(obj) || strcmp(obj->name, mod->name)) + continue; + + /* + * Only unpatch the module if the patch is enabled or + * is in transition. + */ + if (patch->enabled || patch == klp_transition_patch) { + pr_notice("reverting patch '%s' on unloading module '%s'\n", + patch->mod->name, obj->mod->name); + klp_unpatch_object(obj); + } + + klp_free_object_loaded(obj); + break; + } + } +} + int klp_module_coming(struct module *mod) { int ret; @@ -894,7 +929,7 @@ err: pr_warn("patch '%s' failed for module '%s', refusing to load module '%s'\n", patch->mod->name, obj->mod->name, obj->mod->name); mod->klp_alive = false; - klp_free_object_loaded(obj); + klp_cleanup_module_patches_limited(mod, patch); mutex_unlock(&klp_mutex); return ret; @@ -902,9 +937,6 @@ err: void klp_module_going(struct module *mod) { - struct klp_patch *patch; - struct klp_object *obj; - if (WARN_ON(mod->state != MODULE_STATE_GOING && mod->state != MODULE_STATE_COMING)) return; @@ -917,25 +949,7 @@ void klp_module_going(struct module *mod) */ mod->klp_alive = false; - list_for_each_entry(patch, &klp_patches, list) { - klp_for_each_object(patch, obj) { - if (!klp_is_module(obj) || strcmp(obj->name, mod->name)) - continue; - - /* - * Only unpatch the module if the patch is enabled or - * is in transition. - */ - if (patch->enabled || patch == klp_transition_patch) { - pr_notice("reverting patch '%s' on unloading module '%s'\n", - patch->mod->name, obj->mod->name); - klp_unpatch_object(obj); - } - - klp_free_object_loaded(obj); - break; - } - } + klp_cleanup_module_patches_limited(mod, NULL); mutex_unlock(&klp_mutex); } diff --git a/kernel/kernel/locking/lockdep.c b/kernel/kernel/locking/lockdep.c index 44c8d0d17..e36e652d9 100644 --- a/kernel/kernel/locking/lockdep.c +++ b/kernel/kernel/locking/lockdep.c @@ -1873,10 +1873,10 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, struct held_lock *next, int distance, struct stack_trace *trace, int (*save)(struct stack_trace *trace)) { - struct lock_list *entry; - int ret; - struct lock_list this; struct lock_list *uninitialized_var(target_entry); + struct lock_list *entry; + struct lock_list this; + int ret; /* * Prove that the new -> dependency would not @@ -1890,8 +1890,17 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, this.class = hlock_class(next); this.parent = NULL; ret = check_noncircular(&this, hlock_class(prev), &target_entry); - if (unlikely(!ret)) + if (unlikely(!ret)) { + if (!trace->entries) { + /* + * If @save fails here, the printing might trigger + * a WARN but because of the !nr_entries it should + * not do bad things. + */ + save(trace); + } return print_circular_bug(&this, target_entry, next, prev, trace); + } else if (unlikely(ret < 0)) return print_bfs_bug(ret); @@ -1938,7 +1947,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, return print_bfs_bug(ret); - if (save && !save(trace)) + if (!trace->entries && !save(trace)) return 0; /* @@ -1958,20 +1967,6 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, if (!ret) return 0; - /* - * Debugging printouts: - */ - if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) { - graph_unlock(); - printk("\n new dependency: "); - print_lock_name(hlock_class(prev)); - printk(KERN_CONT " => "); - print_lock_name(hlock_class(next)); - printk(KERN_CONT "\n"); - dump_stack(); - if (!graph_lock()) - return 0; - } return 2; } @@ -1986,8 +1981,12 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next) { int depth = curr->lockdep_depth; struct held_lock *hlock; - struct stack_trace trace; - int (*save)(struct stack_trace *trace) = save_trace; + struct stack_trace trace = { + .nr_entries = 0, + .max_entries = 0, + .entries = NULL, + .skip = 0, + }; /* * Debugging checks. @@ -2018,17 +2017,10 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next) */ if (hlock->read != 2 && hlock->check) { int ret = check_prev_add(curr, hlock, next, - distance, &trace, save); + distance, &trace, save_trace); if (!ret) return 0; - /* - * Stop saving stack_trace if save_trace() was - * called at least once: - */ - if (save && ret == 2) - save = NULL; - /* * Stop after the first non-trylock entry, * as non-trylock entries have added their diff --git a/kernel/kernel/sched/fair.c b/kernel/kernel/sched/fair.c index 70ba32e08..d3f309485 100644 --- a/kernel/kernel/sched/fair.c +++ b/kernel/kernel/sched/fair.c @@ -5356,91 +5356,62 @@ static int wake_wide(struct task_struct *p) return 1; } -struct llc_stats { - unsigned long nr_running; - unsigned long load; - unsigned long capacity; - int has_capacity; -}; +/* + * The purpose of wake_affine() is to quickly determine on which CPU we can run + * soonest. For the purpose of speed we only consider the waking and previous + * CPU. + * + * wake_affine_idle() - only considers 'now', it check if the waking CPU is (or + * will be) idle. + * + * wake_affine_weight() - considers the weight to reflect the average + * scheduling latency of the CPUs. This seems to work + * for the overloaded case. + */ -static bool get_llc_stats(struct llc_stats *stats, int cpu) +static bool +wake_affine_idle(struct sched_domain *sd, struct task_struct *p, + int this_cpu, int prev_cpu, int sync) { - struct sched_domain_shared *sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); + if (idle_cpu(this_cpu)) + return true; - if (!sds) - return false; + if (sync && cpu_rq(this_cpu)->nr_running == 1) + return true; - stats->nr_running = READ_ONCE(sds->nr_running); - stats->load = READ_ONCE(sds->load); - stats->capacity = READ_ONCE(sds->capacity); - stats->has_capacity = stats->nr_running < per_cpu(sd_llc_size, cpu); - - return true; + return false; } -/* - * Can a task be moved from prev_cpu to this_cpu without causing a load - * imbalance that would trigger the load balancer? - * - * Since we're running on 'stale' values, we might in fact create an imbalance - * but recomputing these values is expensive, as that'd mean iteration 2 cache - * domains worth of CPUs. - */ static bool -wake_affine_llc(struct sched_domain *sd, struct task_struct *p, - int this_cpu, int prev_cpu, int sync) +wake_affine_weight(struct sched_domain *sd, struct task_struct *p, + int this_cpu, int prev_cpu, int sync) { - struct llc_stats prev_stats, this_stats; s64 this_eff_load, prev_eff_load; unsigned long task_load; - if (!get_llc_stats(&prev_stats, prev_cpu) || - !get_llc_stats(&this_stats, this_cpu)) - return false; + this_eff_load = target_load(this_cpu, sd->wake_idx); + prev_eff_load = source_load(prev_cpu, sd->wake_idx); - /* - * If sync wakeup then subtract the (maximum possible) - * effect of the currently running task from the load - * of the current LLC. - */ if (sync) { unsigned long current_load = task_h_load(current); - /* in this case load hits 0 and this LLC is considered 'idle' */ - if (current_load > this_stats.load) + if (current_load > this_eff_load) return true; - this_stats.load -= current_load; + this_eff_load -= current_load; } - /* - * The has_capacity stuff is not SMT aware, but by trying to balance - * the nr_running on both ends we try and fill the domain at equal - * rates, thereby first consuming cores before siblings. - */ - - /* if the old cache has capacity, stay there */ - if (prev_stats.has_capacity && prev_stats.nr_running < this_stats.nr_running+1) - return false; - - /* if this cache has capacity, come here */ - if (this_stats.has_capacity && this_stats.nr_running+1 < prev_stats.nr_running) - return true; - - /* - * Check to see if we can move the load without causing too much - * imbalance. - */ task_load = task_h_load(p); - this_eff_load = 100; - this_eff_load *= prev_stats.capacity; + this_eff_load += task_load; + if (sched_feat(WA_BIAS)) + this_eff_load *= 100; + this_eff_load *= capacity_of(prev_cpu); - prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2; - prev_eff_load *= this_stats.capacity; - - this_eff_load *= this_stats.load + task_load; - prev_eff_load *= prev_stats.load - task_load; + prev_eff_load -= task_load; + if (sched_feat(WA_BIAS)) + prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2; + prev_eff_load *= capacity_of(this_cpu); return this_eff_load <= prev_eff_load; } @@ -5449,22 +5420,13 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int prev_cpu, int sync) { int this_cpu = smp_processor_id(); - bool affine; + bool affine = false; - /* - * Default to no affine wakeups; wake_affine() should not effect a task - * placement the load-balancer feels inclined to undo. The conservative - * option is therefore to not move tasks when they wake up. - */ - affine = false; + if (sched_feat(WA_IDLE) && !affine) + affine = wake_affine_idle(sd, p, this_cpu, prev_cpu, sync); - /* - * If the wakeup is across cache domains, try to evaluate if movement - * makes sense, otherwise rely on select_idle_siblings() to do - * placement inside the cache domain. - */ - if (!cpus_share_cache(prev_cpu, this_cpu)) - affine = wake_affine_llc(sd, p, this_cpu, prev_cpu, sync); + if (sched_feat(WA_WEIGHT) && !affine) + affine = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync); schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts); if (affine) { @@ -7600,7 +7562,6 @@ static inline enum fbq_type fbq_classify_rq(struct rq *rq) */ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds) { - struct sched_domain_shared *shared = env->sd->shared; struct sched_domain *child = env->sd->child; struct sched_group *sg = env->sd->groups; struct sg_lb_stats *local = &sds->local_stat; @@ -7672,22 +7633,6 @@ next_group: if (env->dst_rq->rd->overload != overload) env->dst_rq->rd->overload = overload; } - - if (!shared) - return; - - /* - * Since these are sums over groups they can contain some CPUs - * multiple times for the NUMA domains. - * - * Currently only wake_affine_llc() and find_busiest_group() - * uses these numbers, only the last is affected by this problem. - * - * XXX fix that. - */ - WRITE_ONCE(shared->nr_running, sds->total_running); - WRITE_ONCE(shared->load, sds->total_load); - WRITE_ONCE(shared->capacity, sds->total_capacity); } /** @@ -8097,6 +8042,13 @@ static int should_we_balance(struct lb_env *env) struct sched_group *sg = env->sd->groups; int cpu, balance_cpu = -1; + /* + * Ensure the balancing environment is consistent; can happen + * when the softirq triggers 'during' hotplug. + */ + if (!cpumask_test_cpu(env->dst_cpu, env->cpus)) + return 0; + /* * In the newly idle case, we will allow all the cpu's * to do the newly idle load balance. diff --git a/kernel/kernel/sched/features.h b/kernel/kernel/sched/features.h index d3fb15555..319ed0e8a 100644 --- a/kernel/kernel/sched/features.h +++ b/kernel/kernel/sched/features.h @@ -81,3 +81,6 @@ SCHED_FEAT(RT_RUNTIME_SHARE, true) SCHED_FEAT(LB_MIN, false) SCHED_FEAT(ATTACH_AGE_LOAD, true) +SCHED_FEAT(WA_IDLE, true) +SCHED_FEAT(WA_WEIGHT, true) +SCHED_FEAT(WA_BIAS, true) diff --git a/kernel/kernel/seccomp.c b/kernel/kernel/seccomp.c index bb3a38005..0ae832e13 100644 --- a/kernel/kernel/seccomp.c +++ b/kernel/kernel/seccomp.c @@ -473,7 +473,7 @@ static long seccomp_attach_filter(unsigned int flags, return 0; } -void __get_seccomp_filter(struct seccomp_filter *filter) +static void __get_seccomp_filter(struct seccomp_filter *filter) { /* Reference count is bounded by the number of total processes. */ refcount_inc(&filter->usage); diff --git a/kernel/lib/Kconfig.debug b/kernel/lib/Kconfig.debug index 2689b7c50..dfdad67d8 100644 --- a/kernel/lib/Kconfig.debug +++ b/kernel/lib/Kconfig.debug @@ -1092,8 +1092,8 @@ config PROVE_LOCKING select DEBUG_MUTEXES select DEBUG_RT_MUTEXES if RT_MUTEXES select DEBUG_LOCK_ALLOC - select LOCKDEP_CROSSRELEASE - select LOCKDEP_COMPLETIONS + select LOCKDEP_CROSSRELEASE if BROKEN + select LOCKDEP_COMPLETIONS if BROKEN select TRACE_IRQFLAGS default n help @@ -1590,6 +1590,54 @@ config LATENCYTOP source kernel/trace/Kconfig +config PROVIDE_OHCI1394_DMA_INIT + bool "Remote debugging over FireWire early on boot" + depends on PCI && X86 + help + If you want to debug problems which hang or crash the kernel early + on boot and the crashing machine has a FireWire port, you can use + this feature to remotely access the memory of the crashed machine + over FireWire. This employs remote DMA as part of the OHCI1394 + specification which is now the standard for FireWire controllers. + + With remote DMA, you can monitor the printk buffer remotely using + firescope and access all memory below 4GB using fireproxy from gdb. + Even controlling a kernel debugger is possible using remote DMA. + + Usage: + + If ohci1394_dma=early is used as boot parameter, it will initialize + all OHCI1394 controllers which are found in the PCI config space. + + As all changes to the FireWire bus such as enabling and disabling + devices cause a bus reset and thereby disable remote DMA for all + devices, be sure to have the cable plugged and FireWire enabled on + the debugging host before booting the debug target for debugging. + + This code (~1k) is freed after boot. By then, the firewire stack + in charge of the OHCI-1394 controllers should be used instead. + + See Documentation/debugging-via-ohci1394.txt for more information. + +config DMA_API_DEBUG + bool "Enable debugging of DMA-API usage" + depends on HAVE_DMA_API_DEBUG + help + Enable this option to debug the use of the DMA API by device drivers. + With this option you will be able to detect common bugs in device + drivers like double-freeing of DMA mappings or freeing mappings that + were never allocated. + + This also attempts to catch cases where a page owned by DMA is + accessed by the cpu in a way that could cause data corruption. For + example, this enables cow_user_page() to check that the source page is + not undergoing DMA. + + This option causes a performance degradation. Use only if you want to + debug device drivers and dma interactions. + + If unsure, say N. + menu "Runtime Testing" config LKDTM @@ -1749,56 +1797,6 @@ config TEST_PARMAN If unsure, say N. -endmenu # runtime tests - -config PROVIDE_OHCI1394_DMA_INIT - bool "Remote debugging over FireWire early on boot" - depends on PCI && X86 - help - If you want to debug problems which hang or crash the kernel early - on boot and the crashing machine has a FireWire port, you can use - this feature to remotely access the memory of the crashed machine - over FireWire. This employs remote DMA as part of the OHCI1394 - specification which is now the standard for FireWire controllers. - - With remote DMA, you can monitor the printk buffer remotely using - firescope and access all memory below 4GB using fireproxy from gdb. - Even controlling a kernel debugger is possible using remote DMA. - - Usage: - - If ohci1394_dma=early is used as boot parameter, it will initialize - all OHCI1394 controllers which are found in the PCI config space. - - As all changes to the FireWire bus such as enabling and disabling - devices cause a bus reset and thereby disable remote DMA for all - devices, be sure to have the cable plugged and FireWire enabled on - the debugging host before booting the debug target for debugging. - - This code (~1k) is freed after boot. By then, the firewire stack - in charge of the OHCI-1394 controllers should be used instead. - - See Documentation/debugging-via-ohci1394.txt for more information. - -config DMA_API_DEBUG - bool "Enable debugging of DMA-API usage" - depends on HAVE_DMA_API_DEBUG - help - Enable this option to debug the use of the DMA API by device drivers. - With this option you will be able to detect common bugs in device - drivers like double-freeing of DMA mappings or freeing mappings that - were never allocated. - - This also attempts to catch cases where a page owned by DMA is - accessed by the cpu in a way that could cause data corruption. For - example, this enables cow_user_page() to check that the source page is - not undergoing DMA. - - This option causes a performance degradation. Use only if you want to - debug device drivers and dma interactions. - - If unsure, say N. - config TEST_LKM tristate "Test module loading with 'hello world' module" default n @@ -1873,18 +1871,6 @@ config TEST_UDELAY If unsure, say N. -config MEMTEST - bool "Memtest" - depends on HAVE_MEMBLOCK - ---help--- - This option adds a kernel parameter 'memtest', which allows memtest - to be set. - memtest=0, mean disabled; -- default - memtest=1, mean do 1 test pattern; - ... - memtest=17, mean do 17 test patterns. - If you are unsure how to answer this question, answer N. - config TEST_STATIC_KEYS tristate "Test static keys" default n @@ -1894,16 +1880,6 @@ config TEST_STATIC_KEYS If unsure, say N. -config BUG_ON_DATA_CORRUPTION - bool "Trigger a BUG when data corruption is detected" - select DEBUG_LIST - help - Select this option if the kernel should BUG when it encounters - data corruption in kernel memory structures when they get checked - for validity. - - If unsure, say N. - config TEST_KMOD tristate "kmod stress tester" default n @@ -1941,6 +1917,29 @@ config TEST_DEBUG_VIRTUAL If unsure, say N. +endmenu # runtime tests + +config MEMTEST + bool "Memtest" + depends on HAVE_MEMBLOCK + ---help--- + This option adds a kernel parameter 'memtest', which allows memtest + to be set. + memtest=0, mean disabled; -- default + memtest=1, mean do 1 test pattern; + ... + memtest=17, mean do 17 test patterns. + If you are unsure how to answer this question, answer N. + +config BUG_ON_DATA_CORRUPTION + bool "Trigger a BUG when data corruption is detected" + select DEBUG_LIST + help + Select this option if the kernel should BUG when it encounters + data corruption in kernel memory structures when they get checked + for validity. + + If unsure, say N. source "samples/Kconfig" diff --git a/kernel/lib/locking-selftest.c b/kernel/lib/locking-selftest.c index cd0b5c964..2b827b8a1 100644 --- a/kernel/lib/locking-selftest.c +++ b/kernel/lib/locking-selftest.c @@ -2031,11 +2031,13 @@ void locking_selftest(void) print_testname("mixed read-lock/lock-write ABBA"); pr_cont(" |"); dotest(rlock_ABBA1, FAILURE, LOCKTYPE_RWLOCK); +#ifdef CONFIG_PROVE_LOCKING /* * Lockdep does indeed fail here, but there's nothing we can do about * that now. Don't kill lockdep for it. */ unexpected_testcase_failures--; +#endif pr_cont(" |"); dotest(rwsem_ABBA1, FAILURE, LOCKTYPE_RWSEM); diff --git a/kernel/mm/cma.c b/kernel/mm/cma.c index c0da318c0..022e52bd8 100644 --- a/kernel/mm/cma.c +++ b/kernel/mm/cma.c @@ -460,7 +460,7 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, trace_cma_alloc(pfn, page, count, align); - if (ret) { + if (ret && !(gfp_mask & __GFP_NOWARN)) { pr_info("%s: alloc failed, req-size: %zu pages, ret: %d\n", __func__, count, ret); cma_debug_show_areas(cma); diff --git a/kernel/mm/madvise.c b/kernel/mm/madvise.c index 25bade36e..fd70d6aab 100644 --- a/kernel/mm/madvise.c +++ b/kernel/mm/madvise.c @@ -757,6 +757,9 @@ madvise_behavior_valid(int behavior) * MADV_DONTFORK - omit this area from child's address space when forking: * typically, to avoid COWing pages pinned by get_user_pages(). * MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking. + * MADV_WIPEONFORK - present the child process with zero-filled memory in this + * range after a fork. + * MADV_KEEPONFORK - undo the effect of MADV_WIPEONFORK * MADV_HWPOISON - trigger memory error handler as if the given memory range * were corrupted by unrecoverable hardware memory failure. * MADV_SOFT_OFFLINE - try to soft-offline the given range of memory. @@ -777,7 +780,9 @@ madvise_behavior_valid(int behavior) * zero - success * -EINVAL - start + len < 0, start is not page-aligned, * "behavior" is not a valid value, or application - * is attempting to release locked or shared pages. + * is attempting to release locked or shared pages, + * or the specified address range includes file, Huge TLB, + * MAP_SHARED or VMPFNMAP range. * -ENOMEM - addresses in the specified range are not currently * mapped, or are outside the AS of the process. * -EIO - an I/O error occurred while paging in data. diff --git a/kernel/mm/mempolicy.c b/kernel/mm/mempolicy.c index 006ba625c..a2af6d58a 100644 --- a/kernel/mm/mempolicy.c +++ b/kernel/mm/mempolicy.c @@ -1920,8 +1920,11 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, struct page *page; page = __alloc_pages(gfp, order, nid); - if (page && page_to_nid(page) == nid) - inc_zone_page_state(page, NUMA_INTERLEAVE_HIT); + if (page && page_to_nid(page) == nid) { + preempt_disable(); + __inc_numa_state(page_zone(page), NUMA_INTERLEAVE_HIT); + preempt_enable(); + } return page; } diff --git a/kernel/mm/migrate.c b/kernel/mm/migrate.c index 6954c1435..e00814ca3 100644 --- a/kernel/mm/migrate.c +++ b/kernel/mm/migrate.c @@ -2146,8 +2146,9 @@ static int migrate_vma_collect_hole(unsigned long start, unsigned long addr; for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) { - migrate->src[migrate->npages++] = MIGRATE_PFN_MIGRATE; + migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE; migrate->dst[migrate->npages] = 0; + migrate->npages++; migrate->cpages++; } diff --git a/kernel/mm/page_vma_mapped.c b/kernel/mm/page_vma_mapped.c index 6a0394646..53afbb919 100644 --- a/kernel/mm/page_vma_mapped.c +++ b/kernel/mm/page_vma_mapped.c @@ -6,17 +6,6 @@ #include "internal.h" -static inline bool check_pmd(struct page_vma_mapped_walk *pvmw) -{ - pmd_t pmde; - /* - * Make sure we don't re-load pmd between present and !trans_huge check. - * We need a consistent view. - */ - pmde = READ_ONCE(*pvmw->pmd); - return pmd_present(pmde) && !pmd_trans_huge(pmde); -} - static inline bool not_found(struct page_vma_mapped_walk *pvmw) { page_vma_mapped_walk_done(pvmw); @@ -116,6 +105,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) pgd_t *pgd; p4d_t *p4d; pud_t *pud; + pmd_t pmde; /* The only possible pmd mapping has been handled on last iteration */ if (pvmw->pmd && !pvmw->pte) @@ -148,7 +138,13 @@ restart: if (!pud_present(*pud)) return false; pvmw->pmd = pmd_offset(pud, pvmw->address); - if (pmd_trans_huge(*pvmw->pmd) || is_pmd_migration_entry(*pvmw->pmd)) { + /* + * Make sure the pmd value isn't cached in a register by the + * compiler and used as a stale value after we've observed a + * subsequent update. + */ + pmde = READ_ONCE(*pvmw->pmd); + if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) { pvmw->ptl = pmd_lock(mm, pvmw->pmd); if (likely(pmd_trans_huge(*pvmw->pmd))) { if (pvmw->flags & PVMW_MIGRATION) @@ -167,17 +163,15 @@ restart: return not_found(pvmw); return true; } - } else - WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!"); + } return not_found(pvmw); } else { /* THP pmd was split under us: handle on pte level */ spin_unlock(pvmw->ptl); pvmw->ptl = NULL; } - } else { - if (!check_pmd(pvmw)) - return false; + } else if (!pmd_present(pmde)) { + return false; } if (!map_pte(pvmw)) goto next_pte; diff --git a/kernel/mm/swap_state.c b/kernel/mm/swap_state.c index ed91091d1..05b6803f0 100644 --- a/kernel/mm/swap_state.c +++ b/kernel/mm/swap_state.c @@ -39,10 +39,6 @@ struct address_space *swapper_spaces[MAX_SWAPFILES]; static unsigned int nr_swapper_spaces[MAX_SWAPFILES]; bool swap_vma_readahead = true; -#define SWAP_RA_MAX_ORDER_DEFAULT 3 - -static int swap_ra_max_order = SWAP_RA_MAX_ORDER_DEFAULT; - #define SWAP_RA_WIN_SHIFT (PAGE_SHIFT / 2) #define SWAP_RA_HITS_MASK ((1UL << SWAP_RA_WIN_SHIFT) - 1) #define SWAP_RA_HITS_MAX SWAP_RA_HITS_MASK @@ -664,6 +660,13 @@ struct page *swap_readahead_detect(struct vm_fault *vmf, pte_t *tpte; #endif + max_win = 1 << min_t(unsigned int, READ_ONCE(page_cluster), + SWAP_RA_ORDER_CEILING); + if (max_win == 1) { + swap_ra->win = 1; + return NULL; + } + faddr = vmf->address; entry = pte_to_swp_entry(vmf->orig_pte); if ((unlikely(non_swap_entry(entry)))) @@ -672,12 +675,6 @@ struct page *swap_readahead_detect(struct vm_fault *vmf, if (page) return page; - max_win = 1 << READ_ONCE(swap_ra_max_order); - if (max_win == 1) { - swap_ra->win = 1; - return NULL; - } - fpfn = PFN_DOWN(faddr); swap_ra_info = GET_SWAP_RA_VAL(vma); pfn = PFN_DOWN(SWAP_RA_ADDR(swap_ra_info)); @@ -786,32 +783,8 @@ static struct kobj_attribute vma_ra_enabled_attr = __ATTR(vma_ra_enabled, 0644, vma_ra_enabled_show, vma_ra_enabled_store); -static ssize_t vma_ra_max_order_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - return sprintf(buf, "%d\n", swap_ra_max_order); -} -static ssize_t vma_ra_max_order_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - int err, v; - - err = kstrtoint(buf, 10, &v); - if (err || v > SWAP_RA_ORDER_CEILING || v <= 0) - return -EINVAL; - - swap_ra_max_order = v; - - return count; -} -static struct kobj_attribute vma_ra_max_order_attr = - __ATTR(vma_ra_max_order, 0644, vma_ra_max_order_show, - vma_ra_max_order_store); - static struct attribute *swap_attrs[] = { &vma_ra_enabled_attr.attr, - &vma_ra_max_order_attr.attr, NULL, }; diff --git a/kernel/mm/vmalloc.c b/kernel/mm/vmalloc.c index 8a43db628..673942094 100644 --- a/kernel/mm/vmalloc.c +++ b/kernel/mm/vmalloc.c @@ -1695,11 +1695,6 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, for (i = 0; i < area->nr_pages; i++) { struct page *page; - if (fatal_signal_pending(current)) { - area->nr_pages = i; - goto fail_no_warn; - } - if (node == NUMA_NO_NODE) page = alloc_page(alloc_mask|highmem_mask); else @@ -1723,7 +1718,6 @@ fail: warn_alloc(gfp_mask, NULL, "vmalloc: allocation failure, allocated %ld of %ld bytes", (area->nr_pages*PAGE_SIZE), area->size); -fail_no_warn: vfree(area->addr); return NULL; } diff --git a/kernel/net/bridge/netfilter/ebtable_broute.c b/kernel/net/bridge/netfilter/ebtable_broute.c index 2585b100e..276b60262 100644 --- a/kernel/net/bridge/netfilter/ebtable_broute.c +++ b/kernel/net/bridge/netfilter/ebtable_broute.c @@ -65,8 +65,8 @@ static int ebt_broute(struct sk_buff *skb) static int __net_init broute_net_init(struct net *net) { - net->xt.broute_table = ebt_register_table(net, &broute_table, NULL); - return PTR_ERR_OR_ZERO(net->xt.broute_table); + return ebt_register_table(net, &broute_table, NULL, + &net->xt.broute_table); } static void __net_exit broute_net_exit(struct net *net) diff --git a/kernel/net/bridge/netfilter/ebtable_filter.c b/kernel/net/bridge/netfilter/ebtable_filter.c index 45a00dbdb..c41da5fac 100644 --- a/kernel/net/bridge/netfilter/ebtable_filter.c +++ b/kernel/net/bridge/netfilter/ebtable_filter.c @@ -93,8 +93,8 @@ static const struct nf_hook_ops ebt_ops_filter[] = { static int __net_init frame_filter_net_init(struct net *net) { - net->xt.frame_filter = ebt_register_table(net, &frame_filter, ebt_ops_filter); - return PTR_ERR_OR_ZERO(net->xt.frame_filter); + return ebt_register_table(net, &frame_filter, ebt_ops_filter, + &net->xt.frame_filter); } static void __net_exit frame_filter_net_exit(struct net *net) diff --git a/kernel/net/bridge/netfilter/ebtable_nat.c b/kernel/net/bridge/netfilter/ebtable_nat.c index 57cd5bb15..08df7406e 100644 --- a/kernel/net/bridge/netfilter/ebtable_nat.c +++ b/kernel/net/bridge/netfilter/ebtable_nat.c @@ -93,8 +93,8 @@ static const struct nf_hook_ops ebt_ops_nat[] = { static int __net_init frame_nat_net_init(struct net *net) { - net->xt.frame_nat = ebt_register_table(net, &frame_nat, ebt_ops_nat); - return PTR_ERR_OR_ZERO(net->xt.frame_nat); + return ebt_register_table(net, &frame_nat, ebt_ops_nat, + &net->xt.frame_nat); } static void __net_exit frame_nat_net_exit(struct net *net) diff --git a/kernel/net/bridge/netfilter/ebtables.c b/kernel/net/bridge/netfilter/ebtables.c index 83951f978..3b3dcf719 100644 --- a/kernel/net/bridge/netfilter/ebtables.c +++ b/kernel/net/bridge/netfilter/ebtables.c @@ -1169,9 +1169,8 @@ static void __ebt_unregister_table(struct net *net, struct ebt_table *table) kfree(table); } -struct ebt_table * -ebt_register_table(struct net *net, const struct ebt_table *input_table, - const struct nf_hook_ops *ops) +int ebt_register_table(struct net *net, const struct ebt_table *input_table, + const struct nf_hook_ops *ops, struct ebt_table **res) { struct ebt_table_info *newinfo; struct ebt_table *t, *table; @@ -1183,7 +1182,7 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table, repl->entries == NULL || repl->entries_size == 0 || repl->counters != NULL || input_table->private != NULL) { BUGPRINT("Bad table data for ebt_register_table!!!\n"); - return ERR_PTR(-EINVAL); + return -EINVAL; } /* Don't add one table to multiple lists. */ @@ -1252,16 +1251,18 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table, list_add(&table->list, &net->xt.tables[NFPROTO_BRIDGE]); mutex_unlock(&ebt_mutex); + WRITE_ONCE(*res, table); + if (!ops) - return table; + return 0; ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks)); if (ret) { __ebt_unregister_table(net, table); - return ERR_PTR(ret); + *res = NULL; } - return table; + return ret; free_unlock: mutex_unlock(&ebt_mutex); free_chainstack: @@ -1276,7 +1277,7 @@ free_newinfo: free_table: kfree(table); out: - return ERR_PTR(ret); + return ret; } void ebt_unregister_table(struct net *net, struct ebt_table *table, diff --git a/kernel/net/ipv4/gre_offload.c b/kernel/net/ipv4/gre_offload.c index 416bb304a..1859c473b 100644 --- a/kernel/net/ipv4/gre_offload.c +++ b/kernel/net/ipv4/gre_offload.c @@ -86,7 +86,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, greh = (struct gre_base_hdr *)skb_transport_header(skb); pcsum = (__sum16 *)(greh + 1); - if (gso_partial) { + if (gso_partial && skb_is_gso(skb)) { unsigned int partial_adj; /* Adjust checksum to account for the fact that diff --git a/kernel/net/ipv4/netfilter/ipt_SYNPROXY.c b/kernel/net/ipv4/netfilter/ipt_SYNPROXY.c index 811689e52..f75fc6b53 100644 --- a/kernel/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/kernel/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -330,7 +330,8 @@ static unsigned int ipv4_synproxy_hook(void *priv, if (synproxy == NULL) return NF_ACCEPT; - if (nf_is_loopback_packet(skb)) + if (nf_is_loopback_packet(skb) || + ip_hdr(skb)->protocol != IPPROTO_TCP) return NF_ACCEPT; thoff = ip_hdrlen(skb); diff --git a/kernel/net/ipv4/route.c b/kernel/net/ipv4/route.c index ac6fde5d4..3d9f1c2f8 100644 --- a/kernel/net/ipv4/route.c +++ b/kernel/net/ipv4/route.c @@ -2513,7 +2513,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or struct rtable *ort = (struct rtable *) dst_orig; struct rtable *rt; - rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE, 0); + rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_DEAD, 0); if (rt) { struct dst_entry *new = &rt->dst; diff --git a/kernel/net/ipv4/udp.c b/kernel/net/ipv4/udp.c index 5676237d2..e45177ceb 100644 --- a/kernel/net/ipv4/udp.c +++ b/kernel/net/ipv4/udp.c @@ -2240,20 +2240,16 @@ int udp_v4_early_demux(struct sk_buff *skb) iph = ip_hdr(skb); uh = udp_hdr(skb); - if (skb->pkt_type == PACKET_BROADCAST || - skb->pkt_type == PACKET_MULTICAST) { + if (skb->pkt_type == PACKET_MULTICAST) { in_dev = __in_dev_get_rcu(skb->dev); if (!in_dev) return 0; - /* we are supposed to accept bcast packets */ - if (skb->pkt_type == PACKET_MULTICAST) { - ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, - iph->protocol); - if (!ours) - return 0; - } + ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, + iph->protocol); + if (!ours) + return 0; sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, diff --git a/kernel/net/ipv4/udp_offload.c b/kernel/net/ipv4/udp_offload.c index 97658bfc1..e360d55be 100644 --- a/kernel/net/ipv4/udp_offload.c +++ b/kernel/net/ipv4/udp_offload.c @@ -120,7 +120,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, * will be using a length value equal to only one MSS sized * segment instead of the entire frame. */ - if (gso_partial) { + if (gso_partial && skb_is_gso(skb)) { uh->len = htons(skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)uh); diff --git a/kernel/net/ipv6/addrconf.c b/kernel/net/ipv6/addrconf.c index 96861c702..4a96ebbf8 100644 --- a/kernel/net/ipv6/addrconf.c +++ b/kernel/net/ipv6/addrconf.c @@ -3820,8 +3820,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) goto out; if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) || - dev_net(dev)->ipv6.devconf_all->accept_dad < 1 || - idev->cnf.accept_dad < 1 || + (dev_net(dev)->ipv6.devconf_all->accept_dad < 1 && + idev->cnf.accept_dad < 1) || !(ifp->flags&IFA_F_TENTATIVE) || ifp->flags & IFA_F_NODAD) { bump_id = ifp->flags & IFA_F_TENTATIVE; diff --git a/kernel/net/ipv6/ip6_offload.c b/kernel/net/ipv6/ip6_offload.c index cdb3728fa..4a87f9428 100644 --- a/kernel/net/ipv6/ip6_offload.c +++ b/kernel/net/ipv6/ip6_offload.c @@ -105,7 +105,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, for (skb = segs; skb; skb = skb->next) { ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff); - if (gso_partial) + if (gso_partial && skb_is_gso(skb)) payload_len = skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)(ipv6h + 1); diff --git a/kernel/net/ipv6/netfilter/ip6t_SYNPROXY.c b/kernel/net/ipv6/netfilter/ip6t_SYNPROXY.c index a5cd43d75..437af8c95 100644 --- a/kernel/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/kernel/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -353,7 +353,7 @@ static unsigned int ipv6_synproxy_hook(void *priv, nexthdr = ipv6_hdr(skb)->nexthdr; thoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); - if (thoff < 0) + if (thoff < 0 || nexthdr != IPPROTO_TCP) return NF_ACCEPT; th = skb_header_pointer(skb, thoff, sizeof(_th), &_th); diff --git a/kernel/net/ipv6/route.c b/kernel/net/ipv6/route.c index 26cc9f483..a96d5b385 100644 --- a/kernel/net/ipv6/route.c +++ b/kernel/net/ipv6/route.c @@ -1325,7 +1325,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori struct dst_entry *new = NULL; rt = dst_alloc(&ip6_dst_blackhole_ops, loopback_dev, 1, - DST_OBSOLETE_NONE, 0); + DST_OBSOLETE_DEAD, 0); if (rt) { rt6_info_init(rt); diff --git a/kernel/net/netfilter/ipset/ip_set_core.c b/kernel/net/netfilter/ipset/ip_set_core.c index e495b5e48..cf84f7b37 100644 --- a/kernel/net/netfilter/ipset/ip_set_core.c +++ b/kernel/net/netfilter/ipset/ip_set_core.c @@ -1191,14 +1191,17 @@ static int ip_set_swap(struct net *net, struct sock *ctnl, struct sk_buff *skb, from->family == to->family)) return -IPSET_ERR_TYPE_MISMATCH; - if (from->ref_netlink || to->ref_netlink) + write_lock_bh(&ip_set_ref_lock); + + if (from->ref_netlink || to->ref_netlink) { + write_unlock_bh(&ip_set_ref_lock); return -EBUSY; + } strncpy(from_name, from->name, IPSET_MAXNAMELEN); strncpy(from->name, to->name, IPSET_MAXNAMELEN); strncpy(to->name, from_name, IPSET_MAXNAMELEN); - write_lock_bh(&ip_set_ref_lock); swap(from->ref, to->ref); ip_set(inst, from_id) = to; ip_set(inst, to_id) = from; @@ -2072,25 +2075,28 @@ static struct pernet_operations ip_set_net_ops = { static int __init ip_set_init(void) { - int ret = nfnetlink_subsys_register(&ip_set_netlink_subsys); + int ret = register_pernet_subsys(&ip_set_net_ops); - if (ret != 0) { - pr_err("ip_set: cannot register with nfnetlink.\n"); + if (ret) { + pr_err("ip_set: cannot register pernet_subsys.\n"); return ret; } + + ret = nfnetlink_subsys_register(&ip_set_netlink_subsys); + if (ret != 0) { + pr_err("ip_set: cannot register with nfnetlink.\n"); + unregister_pernet_subsys(&ip_set_net_ops); + return ret; + } + ret = nf_register_sockopt(&so_set); if (ret != 0) { pr_err("SO_SET registry failed: %d\n", ret); nfnetlink_subsys_unregister(&ip_set_netlink_subsys); + unregister_pernet_subsys(&ip_set_net_ops); return ret; } - ret = register_pernet_subsys(&ip_set_net_ops); - if (ret) { - pr_err("ip_set: cannot register pernet_subsys.\n"); - nf_unregister_sockopt(&so_set); - nfnetlink_subsys_unregister(&ip_set_netlink_subsys); - return ret; - } + pr_info("ip_set: protocol %u\n", IPSET_PROTOCOL); return 0; } @@ -2098,9 +2104,10 @@ ip_set_init(void) static void __exit ip_set_fini(void) { - unregister_pernet_subsys(&ip_set_net_ops); nf_unregister_sockopt(&so_set); nfnetlink_subsys_unregister(&ip_set_netlink_subsys); + + unregister_pernet_subsys(&ip_set_net_ops); pr_debug("these are the famous last words\n"); } diff --git a/kernel/net/netfilter/ipset/ip_set_hash_ip.c b/kernel/net/netfilter/ipset/ip_set_hash_ip.c index 20bfbd315..613eb212c 100644 --- a/kernel/net/netfilter/ipset/ip_set_hash_ip.c +++ b/kernel/net/netfilter/ipset/ip_set_hash_ip.c @@ -123,13 +123,12 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], return ret; ip &= ip_set_hostmask(h->netmask); + e.ip = htonl(ip); + if (e.ip == 0) + return -IPSET_ERR_HASH_ELEM; - if (adt == IPSET_TEST) { - e.ip = htonl(ip); - if (e.ip == 0) - return -IPSET_ERR_HASH_ELEM; + if (adt == IPSET_TEST) return adtfn(set, &e, &ext, &ext, flags); - } ip_to = ip; if (tb[IPSET_ATTR_IP_TO]) { @@ -148,17 +147,20 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1); - if (retried) + if (retried) { ip = ntohl(h->next.ip); - for (; !before(ip_to, ip); ip += hosts) { e.ip = htonl(ip); - if (e.ip == 0) - return -IPSET_ERR_HASH_ELEM; + } + for (; ip <= ip_to;) { ret = adtfn(set, &e, &ext, &ext, flags); - if (ret && !ip_set_eexist(ret, flags)) return ret; + ip += hosts; + e.ip = htonl(ip); + if (e.ip == 0) + return 0; + ret = 0; } return ret; diff --git a/kernel/net/netfilter/ipset/ip_set_hash_ipmark.c b/kernel/net/netfilter/ipset/ip_set_hash_ipmark.c index b64cf14e8..f3ba8348c 100644 --- a/kernel/net/netfilter/ipset/ip_set_hash_ipmark.c +++ b/kernel/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -149,7 +149,7 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - for (; !before(ip_to, ip); ip++) { + for (; ip <= ip_to; ip++) { e.ip = htonl(ip); ret = adtfn(set, &e, &ext, &ext, flags); diff --git a/kernel/net/netfilter/ipset/ip_set_hash_ipport.c b/kernel/net/netfilter/ipset/ip_set_hash_ipport.c index f438740e6..ddb8039ec 100644 --- a/kernel/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/kernel/net/netfilter/ipset/ip_set_hash_ipport.c @@ -178,7 +178,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - for (; !before(ip_to, ip); ip++) { + for (; ip <= ip_to; ip++) { p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; for (; p <= port_to; p++) { diff --git a/kernel/net/netfilter/ipset/ip_set_hash_ipportip.c b/kernel/net/netfilter/ipset/ip_set_hash_ipportip.c index 6215fb898..a7f4d7a85 100644 --- a/kernel/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/kernel/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -185,7 +185,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - for (; !before(ip_to, ip); ip++) { + for (; ip <= ip_to; ip++) { p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; for (; p <= port_to; p++) { diff --git a/kernel/net/netfilter/ipset/ip_set_hash_ipportnet.c b/kernel/net/netfilter/ipset/ip_set_hash_ipportnet.c index 5ab1b99a5..a2f19b990 100644 --- a/kernel/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/kernel/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -271,7 +271,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - for (; !before(ip_to, ip); ip++) { + for (; ip <= ip_to; ip++) { e.ip = htonl(ip); p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; @@ -281,7 +281,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], ip == ntohl(h->next.ip) && p == ntohs(h->next.port) ? ntohl(h->next.ip2) : ip2_from; - while (!after(ip2, ip2_to)) { + while (ip2 <= ip2_to) { e.ip2 = htonl(ip2); ip2_last = ip_set_range_to_cidr(ip2, ip2_to, &cidr); diff --git a/kernel/net/netfilter/ipset/ip_set_hash_net.c b/kernel/net/netfilter/ipset/ip_set_hash_net.c index 5d9e89545..1c67a1761 100644 --- a/kernel/net/netfilter/ipset/ip_set_hash_net.c +++ b/kernel/net/netfilter/ipset/ip_set_hash_net.c @@ -193,7 +193,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], } if (retried) ip = ntohl(h->next.ip); - while (!after(ip, ip_to)) { + while (ip <= ip_to) { e.ip = htonl(ip); last = ip_set_range_to_cidr(ip, ip_to, &e.cidr); ret = adtfn(set, &e, &ext, &ext, flags); diff --git a/kernel/net/netfilter/ipset/ip_set_hash_netiface.c b/kernel/net/netfilter/ipset/ip_set_hash_netiface.c index 44cf11939..d417074f1 100644 --- a/kernel/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/kernel/net/netfilter/ipset/ip_set_hash_netiface.c @@ -255,7 +255,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - while (!after(ip, ip_to)) { + while (ip <= ip_to) { e.ip = htonl(ip); last = ip_set_range_to_cidr(ip, ip_to, &e.cidr); ret = adtfn(set, &e, &ext, &ext, flags); diff --git a/kernel/net/netfilter/ipset/ip_set_hash_netnet.c b/kernel/net/netfilter/ipset/ip_set_hash_netnet.c index db614e13b..7f9ae2e96 100644 --- a/kernel/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/kernel/net/netfilter/ipset/ip_set_hash_netnet.c @@ -250,13 +250,13 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip[0]); - while (!after(ip, ip_to)) { + while (ip <= ip_to) { e.ip[0] = htonl(ip); last = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]); ip2 = (retried && ip == ntohl(h->next.ip[0])) ? ntohl(h->next.ip[1]) : ip2_from; - while (!after(ip2, ip2_to)) { + while (ip2 <= ip2_to) { e.ip[1] = htonl(ip2); last2 = ip_set_range_to_cidr(ip2, ip2_to, &e.cidr[1]); ret = adtfn(set, &e, &ext, &ext, flags); diff --git a/kernel/net/netfilter/ipset/ip_set_hash_netport.c b/kernel/net/netfilter/ipset/ip_set_hash_netport.c index 54b64b6cd..e6ef382fe 100644 --- a/kernel/net/netfilter/ipset/ip_set_hash_netport.c +++ b/kernel/net/netfilter/ipset/ip_set_hash_netport.c @@ -241,7 +241,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - while (!after(ip, ip_to)) { + while (ip <= ip_to) { e.ip = htonl(ip); last = ip_set_range_to_cidr(ip, ip_to, &cidr); e.cidr = cidr - 1; diff --git a/kernel/net/netfilter/ipset/ip_set_hash_netportnet.c b/kernel/net/netfilter/ipset/ip_set_hash_netportnet.c index aff846960..8602f2595 100644 --- a/kernel/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/kernel/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -291,7 +291,7 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip[0]); - while (!after(ip, ip_to)) { + while (ip <= ip_to) { e.ip[0] = htonl(ip); ip_last = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]); p = retried && ip == ntohl(h->next.ip[0]) ? ntohs(h->next.port) @@ -301,7 +301,7 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], ip2 = (retried && ip == ntohl(h->next.ip[0]) && p == ntohs(h->next.port)) ? ntohl(h->next.ip[1]) : ip2_from; - while (!after(ip2, ip2_to)) { + while (ip2 <= ip2_to) { e.ip[1] = htonl(ip2); ip2_last = ip_set_range_to_cidr(ip2, ip2_to, &e.cidr[1]); diff --git a/kernel/net/netfilter/ipvs/ip_vs_xmit.c b/kernel/net/netfilter/ipvs/ip_vs_xmit.c index 90d396814..4527921b1 100644 --- a/kernel/net/netfilter/ipvs/ip_vs_xmit.c +++ b/kernel/net/netfilter/ipvs/ip_vs_xmit.c @@ -921,6 +921,7 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af, { struct sk_buff *new_skb = NULL; struct iphdr *old_iph = NULL; + __u8 old_dsfield; #ifdef CONFIG_IP_VS_IPV6 struct ipv6hdr *old_ipv6h = NULL; #endif @@ -945,7 +946,7 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af, *payload_len = ntohs(old_ipv6h->payload_len) + sizeof(*old_ipv6h); - *dsfield = ipv6_get_dsfield(old_ipv6h); + old_dsfield = ipv6_get_dsfield(old_ipv6h); *ttl = old_ipv6h->hop_limit; if (df) *df = 0; @@ -960,12 +961,15 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af, /* fix old IP header checksum */ ip_send_check(old_iph); - *dsfield = ipv4_get_dsfield(old_iph); + old_dsfield = ipv4_get_dsfield(old_iph); *ttl = old_iph->ttl; if (payload_len) *payload_len = ntohs(old_iph->tot_len); } + /* Implement full-functionality option for ECN encapsulation */ + *dsfield = INET_ECN_encapsulate(old_dsfield, old_dsfield); + return skb; error: kfree_skb(skb); diff --git a/kernel/net/netfilter/nf_tables_api.c b/kernel/net/netfilter/nf_tables_api.c index 929927171..64e1ee091 100644 --- a/kernel/net/netfilter/nf_tables_api.c +++ b/kernel/net/netfilter/nf_tables_api.c @@ -1048,7 +1048,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, if (nla_put_string(skb, NFTA_CHAIN_TYPE, basechain->type->name)) goto nla_put_failure; - if (nft_dump_stats(skb, nft_base_chain(chain)->stats)) + if (basechain->stats && nft_dump_stats(skb, basechain->stats)) goto nla_put_failure; } @@ -1487,8 +1487,8 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, chain2 = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask); - if (IS_ERR(chain2)) - return PTR_ERR(chain2); + if (!IS_ERR(chain2)) + return -EEXIST; } if (nla[NFTA_CHAIN_COUNTERS]) { @@ -2741,8 +2741,10 @@ cont: list_for_each_entry(i, &ctx->table->sets, list) { if (!nft_is_active_next(ctx->net, i)) continue; - if (!strcmp(set->name, i->name)) + if (!strcmp(set->name, i->name)) { + kfree(set->name); return -ENFILE; + } } return 0; } diff --git a/kernel/net/netfilter/x_tables.c b/kernel/net/netfilter/x_tables.c index c83a3b5e1..d8571f414 100644 --- a/kernel/net/netfilter/x_tables.c +++ b/kernel/net/netfilter/x_tables.c @@ -892,7 +892,7 @@ void *xt_copy_counters_from_user(const void __user *user, unsigned int len, if (copy_from_user(&compat_tmp, user, sizeof(compat_tmp)) != 0) return ERR_PTR(-EFAULT); - strlcpy(info->name, compat_tmp.name, sizeof(info->name)); + memcpy(info->name, compat_tmp.name, sizeof(info->name) - 1); info->num_counters = compat_tmp.num_counters; user += sizeof(compat_tmp); } else @@ -905,9 +905,9 @@ void *xt_copy_counters_from_user(const void __user *user, unsigned int len, if (copy_from_user(info, user, sizeof(*info)) != 0) return ERR_PTR(-EFAULT); - info->name[sizeof(info->name) - 1] = '\0'; user += sizeof(*info); } + info->name[sizeof(info->name) - 1] = '\0'; size = sizeof(struct xt_counters); size *= info->num_counters; diff --git a/kernel/net/netfilter/xt_bpf.c b/kernel/net/netfilter/xt_bpf.c index 38986a952..291239348 100644 --- a/kernel/net/netfilter/xt_bpf.c +++ b/kernel/net/netfilter/xt_bpf.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include @@ -49,6 +50,22 @@ static int __bpf_mt_check_fd(int fd, struct bpf_prog **ret) return 0; } +static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret) +{ + mm_segment_t oldfs = get_fs(); + int retval, fd; + + set_fs(KERNEL_DS); + fd = bpf_obj_get_user(path); + set_fs(oldfs); + if (fd < 0) + return fd; + + retval = __bpf_mt_check_fd(fd, ret); + sys_close(fd); + return retval; +} + static int bpf_mt_check(const struct xt_mtchk_param *par) { struct xt_bpf_info *info = par->matchinfo; @@ -66,9 +83,10 @@ static int bpf_mt_check_v1(const struct xt_mtchk_param *par) return __bpf_mt_check_bytecode(info->bpf_program, info->bpf_program_num_elem, &info->filter); - else if (info->mode == XT_BPF_MODE_FD_PINNED || - info->mode == XT_BPF_MODE_FD_ELF) + else if (info->mode == XT_BPF_MODE_FD_ELF) return __bpf_mt_check_fd(info->fd, &info->filter); + else if (info->mode == XT_BPF_MODE_PATH_PINNED) + return __bpf_mt_check_path(info->path, &info->filter); else return -EINVAL; } diff --git a/kernel/net/netfilter/xt_socket.c b/kernel/net/netfilter/xt_socket.c index e75ef3966..575d2153e 100644 --- a/kernel/net/netfilter/xt_socket.c +++ b/kernel/net/netfilter/xt_socket.c @@ -76,7 +76,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, transparent = nf_sk_is_transparent(sk); if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && - transparent) + transparent && sk_fullsock(sk)) pskb->mark = sk->sk_mark; if (sk != skb->sk) @@ -133,7 +133,7 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) transparent = nf_sk_is_transparent(sk); if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && - transparent) + transparent && sk_fullsock(sk)) pskb->mark = sk->sk_mark; if (sk != skb->sk) diff --git a/kernel/net/netlink/af_netlink.c b/kernel/net/netlink/af_netlink.c index 94c11cf04..f34750691 100644 --- a/kernel/net/netlink/af_netlink.c +++ b/kernel/net/netlink/af_netlink.c @@ -2266,16 +2266,17 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, cb->min_dump_alloc = control->min_dump_alloc; cb->skb = skb; + if (cb->start) { + ret = cb->start(cb); + if (ret) + goto error_unlock; + } + nlk->cb_running = true; mutex_unlock(nlk->cb_mutex); - ret = 0; - if (cb->start) - ret = cb->start(cb); - - if (!ret) - ret = netlink_dump(sk); + ret = netlink_dump(sk); sock_put(sk); diff --git a/kernel/net/sunrpc/xprtsock.c b/kernel/net/sunrpc/xprtsock.c index 9b5de31aa..c1841f234 100644 --- a/kernel/net/sunrpc/xprtsock.c +++ b/kernel/net/sunrpc/xprtsock.c @@ -2203,7 +2203,7 @@ static void xs_udp_setup_socket(struct work_struct *work) struct sock_xprt *transport = container_of(work, struct sock_xprt, connect_worker.work); struct rpc_xprt *xprt = &transport->xprt; - struct socket *sock = transport->sock; + struct socket *sock; int status = -EIO; sock = xs_create_sock(xprt, transport, diff --git a/kernel/net/tipc/bcast.c b/kernel/net/tipc/bcast.c index 7d99029df..a140dd4a8 100644 --- a/kernel/net/tipc/bcast.c +++ b/kernel/net/tipc/bcast.c @@ -233,7 +233,7 @@ static int tipc_bcast_xmit(struct net *net, struct sk_buff_head *pkts, struct sk_buff_head xmitq; int rc = 0; - __skb_queue_head_init(&xmitq); + skb_queue_head_init(&xmitq); tipc_bcast_lock(net); if (tipc_link_bc_peers(l)) rc = tipc_link_xmit(l, pkts, &xmitq); @@ -263,7 +263,7 @@ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts, u32 dst, selector; selector = msg_link_selector(buf_msg(skb_peek(pkts))); - __skb_queue_head_init(&_pkts); + skb_queue_head_init(&_pkts); list_for_each_entry_safe(n, tmp, &dests->list, list) { dst = n->value; diff --git a/kernel/net/tipc/msg.c b/kernel/net/tipc/msg.c index 121e59a1d..17146c16e 100644 --- a/kernel/net/tipc/msg.c +++ b/kernel/net/tipc/msg.c @@ -568,6 +568,14 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err) msg_set_destnode(msg, dnode); msg_set_destport(msg, dport); *err = TIPC_OK; + + if (!skb_cloned(skb)) + return true; + + /* Unclone buffer in case it was bundled */ + if (pskb_expand_head(skb, BUF_HEADROOM, BUF_TAILROOM, GFP_ATOMIC)) + return false; + return true; } diff --git a/kernel/net/wireless/nl80211.c b/kernel/net/wireless/nl80211.c index 690874293..d396cb61a 100644 --- a/kernel/net/wireless/nl80211.c +++ b/kernel/net/wireless/nl80211.c @@ -549,6 +549,14 @@ nl80211_nan_srf_policy[NL80211_NAN_SRF_ATTR_MAX + 1] = { [NL80211_NAN_SRF_MAC_ADDRS] = { .type = NLA_NESTED }, }; +/* policy for packet pattern attributes */ +static const struct nla_policy +nl80211_packet_pattern_policy[MAX_NL80211_PKTPAT + 1] = { + [NL80211_PKTPAT_MASK] = { .type = NLA_BINARY, }, + [NL80211_PKTPAT_PATTERN] = { .type = NLA_BINARY, }, + [NL80211_PKTPAT_OFFSET] = { .type = NLA_U32 }, +}; + static int nl80211_prepare_wdev_dump(struct sk_buff *skb, struct netlink_callback *cb, struct cfg80211_registered_device **rdev, @@ -10532,7 +10540,8 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) u8 *mask_pat; nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, - NULL, info->extack); + nl80211_packet_pattern_policy, + info->extack); err = -EINVAL; if (!pat_tb[NL80211_PKTPAT_MASK] || !pat_tb[NL80211_PKTPAT_PATTERN]) @@ -10781,7 +10790,8 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev, rem) { u8 *mask_pat; - nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, NULL, NULL); + nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, + nl80211_packet_pattern_policy, NULL); if (!pat_tb[NL80211_PKTPAT_MASK] || !pat_tb[NL80211_PKTPAT_PATTERN]) return -EINVAL; diff --git a/kernel/net/xfrm/xfrm_device.c b/kernel/net/xfrm/xfrm_device.c index acf00104e..30e574608 100644 --- a/kernel/net/xfrm/xfrm_device.c +++ b/kernel/net/xfrm/xfrm_device.c @@ -91,6 +91,7 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, } if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_state_add) { + xso->dev = NULL; dev_put(dev); return 0; } diff --git a/kernel/net/xfrm/xfrm_input.c b/kernel/net/xfrm/xfrm_input.c index 2515cd2bc..8ac9d32fb 100644 --- a/kernel/net/xfrm/xfrm_input.c +++ b/kernel/net/xfrm/xfrm_input.c @@ -429,7 +429,8 @@ resume: nf_reset(skb); if (decaps) { - skb->sp->olen = 0; + if (skb->sp) + skb->sp->olen = 0; skb_dst_drop(skb); gro_cells_receive(&gro_cells, skb); return 0; @@ -440,7 +441,8 @@ resume: err = x->inner_mode->afinfo->transport_finish(skb, xfrm_gro || async); if (xfrm_gro) { - skb->sp->olen = 0; + if (skb->sp) + skb->sp->olen = 0; skb_dst_drop(skb); gro_cells_receive(&gro_cells, skb); return err; diff --git a/kernel/net/xfrm/xfrm_state.c b/kernel/net/xfrm/xfrm_state.c index 0dab1cd79..12213477c 100644 --- a/kernel/net/xfrm/xfrm_state.c +++ b/kernel/net/xfrm/xfrm_state.c @@ -732,12 +732,12 @@ restart: } } } +out: + spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (cnt) { err = 0; xfrm_policy_cache_flush(); } -out: - spin_unlock_bh(&net->xfrm.xfrm_state_lock); return err; } EXPORT_SYMBOL(xfrm_state_flush); diff --git a/kernel/net/xfrm/xfrm_user.c b/kernel/net/xfrm/xfrm_user.c index 2bfbd9121..b997f1395 100644 --- a/kernel/net/xfrm/xfrm_user.c +++ b/kernel/net/xfrm/xfrm_user.c @@ -657,6 +657,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) { x->km.state = XFRM_STATE_DEAD; + xfrm_dev_state_delete(x); __xfrm_state_put(x); goto out; } diff --git a/kernel/scripts/faddr2line b/kernel/scripts/faddr2line index 29df825d3..2f6ce8023 100755 --- a/kernel/scripts/faddr2line +++ b/kernel/scripts/faddr2line @@ -103,11 +103,12 @@ __faddr2line() { # Go through each of the object's symbols which match the func name. # In rare cases there might be duplicates. + file_end=$(size -Ax $objfile | awk '$1 == ".text" {print $2}') while read symbol; do local fields=($symbol) local sym_base=0x${fields[0]} local sym_type=${fields[1]} - local sym_end=0x${fields[3]} + local sym_end=${fields[3]} # calculate the size local sym_size=$(($sym_end - $sym_base)) @@ -157,7 +158,7 @@ __faddr2line() { addr2line -fpie $objfile $addr | sed "s; $dir_prefix\(\./\)*; ;" DONE=1 - done < <(nm -n $objfile | awk -v fn=$func '$3 == fn { found=1; line=$0; start=$1; next } found == 1 { found=0; print line, $1 }') + done < <(nm -n $objfile | awk -v fn=$func -v end=$file_end '$3 == fn { found=1; line=$0; start=$1; next } found == 1 { found=0; print line, "0x"$1 } END {if (found == 1) print line, end; }') } [[ $# -lt 2 ]] && usage diff --git a/kernel/scripts/kallsyms.c b/kernel/scripts/kallsyms.c index 5d5544191..9ee9bf7fd 100644 --- a/kernel/scripts/kallsyms.c +++ b/kernel/scripts/kallsyms.c @@ -158,7 +158,7 @@ static int read_symbol(FILE *in, struct sym_entry *s) else if (str[0] == '$') return -1; /* exclude debugging symbols */ - else if (stype == 'N') + else if (stype == 'N' || stype == 'n') return -1; /* include the type field in the symbol name, so that it gets diff --git a/kernel/sound/core/seq/seq_clientmgr.c b/kernel/sound/core/seq/seq_clientmgr.c index ea2d0ae85..6c9cba216 100644 --- a/kernel/sound/core/seq/seq_clientmgr.c +++ b/kernel/sound/core/seq/seq_clientmgr.c @@ -1259,6 +1259,7 @@ static int snd_seq_ioctl_create_port(struct snd_seq_client *client, void *arg) struct snd_seq_port_info *info = arg; struct snd_seq_client_port *port; struct snd_seq_port_callback *callback; + int port_idx; /* it is not allowed to create the port for an another client */ if (info->addr.client != client->number) @@ -1269,7 +1270,9 @@ static int snd_seq_ioctl_create_port(struct snd_seq_client *client, void *arg) return -ENOMEM; if (client->type == USER_CLIENT && info->kernel) { - snd_seq_delete_port(client, port->addr.port); + port_idx = port->addr.port; + snd_seq_port_unlock(port); + snd_seq_delete_port(client, port_idx); return -EINVAL; } if (client->type == KERNEL_CLIENT) { @@ -1290,6 +1293,7 @@ static int snd_seq_ioctl_create_port(struct snd_seq_client *client, void *arg) snd_seq_set_port_info(port, info); snd_seq_system_client_ev_port_start(port->addr.client, port->addr.port); + snd_seq_port_unlock(port); return 0; } diff --git a/kernel/sound/core/seq/seq_ports.c b/kernel/sound/core/seq/seq_ports.c index 0a7020c82..d21ece9f8 100644 --- a/kernel/sound/core/seq/seq_ports.c +++ b/kernel/sound/core/seq/seq_ports.c @@ -122,7 +122,9 @@ static void port_subs_info_init(struct snd_seq_port_subs_info *grp) } -/* create a port, port number is returned (-1 on failure) */ +/* create a port, port number is returned (-1 on failure); + * the caller needs to unref the port via snd_seq_port_unlock() appropriately + */ struct snd_seq_client_port *snd_seq_create_port(struct snd_seq_client *client, int port) { @@ -151,6 +153,7 @@ struct snd_seq_client_port *snd_seq_create_port(struct snd_seq_client *client, snd_use_lock_init(&new_port->use_lock); port_subs_info_init(&new_port->c_src); port_subs_info_init(&new_port->c_dest); + snd_use_lock_use(&new_port->use_lock); num = port >= 0 ? port : 0; mutex_lock(&client->ports_mutex); @@ -165,9 +168,9 @@ struct snd_seq_client_port *snd_seq_create_port(struct snd_seq_client *client, list_add_tail(&new_port->list, &p->list); client->num_ports++; new_port->addr.port = num; /* store the port number in the port */ + sprintf(new_port->name, "port-%d", num); write_unlock_irqrestore(&client->ports_lock, flags); mutex_unlock(&client->ports_mutex); - sprintf(new_port->name, "port-%d", num); return new_port; } diff --git a/kernel/sound/core/seq/seq_virmidi.c b/kernel/sound/core/seq/seq_virmidi.c index 8d93a4021..f48a4cd24 100644 --- a/kernel/sound/core/seq/seq_virmidi.c +++ b/kernel/sound/core/seq/seq_virmidi.c @@ -77,13 +77,17 @@ static void snd_virmidi_init_event(struct snd_virmidi *vmidi, * decode input event and put to read buffer of each opened file */ static int snd_virmidi_dev_receive_event(struct snd_virmidi_dev *rdev, - struct snd_seq_event *ev) + struct snd_seq_event *ev, + bool atomic) { struct snd_virmidi *vmidi; unsigned char msg[4]; int len; - read_lock(&rdev->filelist_lock); + if (atomic) + read_lock(&rdev->filelist_lock); + else + down_read(&rdev->filelist_sem); list_for_each_entry(vmidi, &rdev->filelist, list) { if (!vmidi->trigger) continue; @@ -97,7 +101,10 @@ static int snd_virmidi_dev_receive_event(struct snd_virmidi_dev *rdev, snd_rawmidi_receive(vmidi->substream, msg, len); } } - read_unlock(&rdev->filelist_lock); + if (atomic) + read_unlock(&rdev->filelist_lock); + else + up_read(&rdev->filelist_sem); return 0; } @@ -115,7 +122,7 @@ int snd_virmidi_receive(struct snd_rawmidi *rmidi, struct snd_seq_event *ev) struct snd_virmidi_dev *rdev; rdev = rmidi->private_data; - return snd_virmidi_dev_receive_event(rdev, ev); + return snd_virmidi_dev_receive_event(rdev, ev, true); } #endif /* 0 */ @@ -130,7 +137,7 @@ static int snd_virmidi_event_input(struct snd_seq_event *ev, int direct, rdev = private_data; if (!(rdev->flags & SNDRV_VIRMIDI_USE)) return 0; /* ignored */ - return snd_virmidi_dev_receive_event(rdev, ev); + return snd_virmidi_dev_receive_event(rdev, ev, atomic); } /* @@ -209,7 +216,6 @@ static int snd_virmidi_input_open(struct snd_rawmidi_substream *substream) struct snd_virmidi_dev *rdev = substream->rmidi->private_data; struct snd_rawmidi_runtime *runtime = substream->runtime; struct snd_virmidi *vmidi; - unsigned long flags; vmidi = kzalloc(sizeof(*vmidi), GFP_KERNEL); if (vmidi == NULL) @@ -223,9 +229,11 @@ static int snd_virmidi_input_open(struct snd_rawmidi_substream *substream) vmidi->client = rdev->client; vmidi->port = rdev->port; runtime->private_data = vmidi; - write_lock_irqsave(&rdev->filelist_lock, flags); + down_write(&rdev->filelist_sem); + write_lock_irq(&rdev->filelist_lock); list_add_tail(&vmidi->list, &rdev->filelist); - write_unlock_irqrestore(&rdev->filelist_lock, flags); + write_unlock_irq(&rdev->filelist_lock); + up_write(&rdev->filelist_sem); vmidi->rdev = rdev; return 0; } @@ -264,9 +272,11 @@ static int snd_virmidi_input_close(struct snd_rawmidi_substream *substream) struct snd_virmidi_dev *rdev = substream->rmidi->private_data; struct snd_virmidi *vmidi = substream->runtime->private_data; + down_write(&rdev->filelist_sem); write_lock_irq(&rdev->filelist_lock); list_del(&vmidi->list); write_unlock_irq(&rdev->filelist_lock); + up_write(&rdev->filelist_sem); snd_midi_event_free(vmidi->parser); substream->runtime->private_data = NULL; kfree(vmidi); @@ -520,6 +530,7 @@ int snd_virmidi_new(struct snd_card *card, int device, struct snd_rawmidi **rrmi rdev->rmidi = rmidi; rdev->device = device; rdev->client = -1; + init_rwsem(&rdev->filelist_sem); rwlock_init(&rdev->filelist_lock); INIT_LIST_HEAD(&rdev->filelist); rdev->seq_mode = SNDRV_VIRMIDI_SEQ_DISPATCH; diff --git a/kernel/sound/usb/caiaq/device.c b/kernel/sound/usb/caiaq/device.c index 0fb6b1b79..d8409d9ae 100644 --- a/kernel/sound/usb/caiaq/device.c +++ b/kernel/sound/usb/caiaq/device.c @@ -469,10 +469,12 @@ static int init_card(struct snd_usb_caiaqdev *cdev) err = snd_usb_caiaq_send_command(cdev, EP1_CMD_GET_DEVICE_INFO, NULL, 0); if (err) - return err; + goto err_kill_urb; - if (!wait_event_timeout(cdev->ep1_wait_queue, cdev->spec_received, HZ)) - return -ENODEV; + if (!wait_event_timeout(cdev->ep1_wait_queue, cdev->spec_received, HZ)) { + err = -ENODEV; + goto err_kill_urb; + } usb_string(usb_dev, usb_dev->descriptor.iManufacturer, cdev->vendor_name, CAIAQ_USB_STR_LEN); @@ -507,6 +509,10 @@ static int init_card(struct snd_usb_caiaqdev *cdev) setup_card(cdev); return 0; + + err_kill_urb: + usb_kill_urb(&cdev->ep1_in_urb); + return err; } static int snd_probe(struct usb_interface *intf, diff --git a/kernel/sound/usb/line6/driver.c b/kernel/sound/usb/line6/driver.c index 0ff5a7d2e..c8f723c3a 100644 --- a/kernel/sound/usb/line6/driver.c +++ b/kernel/sound/usb/line6/driver.c @@ -779,9 +779,10 @@ int line6_probe(struct usb_interface *interface, return 0; error: - if (line6->disconnect) - line6->disconnect(line6); - snd_card_free(card); + /* we can call disconnect callback here because no close-sync is + * needed yet at this point + */ + line6_disconnect(interface); return ret; } EXPORT_SYMBOL_GPL(line6_probe); diff --git a/kernel/sound/usb/line6/podhd.c b/kernel/sound/usb/line6/podhd.c index 956f847a9..451007c27 100644 --- a/kernel/sound/usb/line6/podhd.c +++ b/kernel/sound/usb/line6/podhd.c @@ -301,7 +301,8 @@ static void podhd_disconnect(struct usb_line6 *line6) intf = usb_ifnum_to_if(line6->usbdev, pod->line6.properties->ctrl_if); - usb_driver_release_interface(&podhd_driver, intf); + if (intf) + usb_driver_release_interface(&podhd_driver, intf); } } @@ -317,6 +318,9 @@ static int podhd_init(struct usb_line6 *line6, line6->disconnect = podhd_disconnect; + init_timer(&pod->startup_timer); + INIT_WORK(&pod->startup_work, podhd_startup_workqueue); + if (pod->line6.properties->capabilities & LINE6_CAP_CONTROL) { /* claim the data interface */ intf = usb_ifnum_to_if(line6->usbdev, @@ -358,8 +362,6 @@ static int podhd_init(struct usb_line6 *line6, } /* init device and delay registering */ - init_timer(&pod->startup_timer); - INIT_WORK(&pod->startup_work, podhd_startup_workqueue); podhd_startup(pod); return 0; } diff --git a/kernel/sound/usb/mixer.c b/kernel/sound/usb/mixer.c index 9732edf77..91bc8f187 100644 --- a/kernel/sound/usb/mixer.c +++ b/kernel/sound/usb/mixer.c @@ -2234,6 +2234,9 @@ static int parse_audio_unit(struct mixer_build *state, int unitid) static void snd_usb_mixer_free(struct usb_mixer_interface *mixer) { + /* kill pending URBs */ + snd_usb_mixer_disconnect(mixer); + kfree(mixer->id_elems); if (mixer->urb) { kfree(mixer->urb->transfer_buffer); @@ -2584,8 +2587,13 @@ _error: void snd_usb_mixer_disconnect(struct usb_mixer_interface *mixer) { - usb_kill_urb(mixer->urb); - usb_kill_urb(mixer->rc_urb); + if (mixer->disconnected) + return; + if (mixer->urb) + usb_kill_urb(mixer->urb); + if (mixer->rc_urb) + usb_kill_urb(mixer->rc_urb); + mixer->disconnected = true; } #ifdef CONFIG_PM diff --git a/kernel/sound/usb/mixer.h b/kernel/sound/usb/mixer.h index 2b4b06764..545d99b09 100644 --- a/kernel/sound/usb/mixer.h +++ b/kernel/sound/usb/mixer.h @@ -22,6 +22,8 @@ struct usb_mixer_interface { struct urb *rc_urb; struct usb_ctrlrequest *rc_setup_packet; u8 rc_buffer[6]; + + bool disconnected; }; #define MAX_CHANNELS 16 /* max logical channels */ diff --git a/kernel/sound/usb/quirks.c b/kernel/sound/usb/quirks.c index b8cb57aee..9ddaae378 100644 --- a/kernel/sound/usb/quirks.c +++ b/kernel/sound/usb/quirks.c @@ -1138,6 +1138,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x047F, 0x0415): /* Plantronics BT-300 */ case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */ case USB_ID(0x047F, 0xC022): /* Plantronics C310 */ + case USB_ID(0x047F, 0xC02F): /* Plantronics P610 */ case USB_ID(0x047F, 0xC036): /* Plantronics C520-M */ case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ case USB_ID(0x0556, 0x0014): /* Phoenix Audio TMX320VC */ diff --git a/kernel/tools/include/uapi/linux/bpf.h b/kernel/tools/include/uapi/linux/bpf.h index 43ab5c402..f90860d1f 100644 --- a/kernel/tools/include/uapi/linux/bpf.h +++ b/kernel/tools/include/uapi/linux/bpf.h @@ -312,7 +312,7 @@ union bpf_attr { * jump into another BPF program * @ctx: context pointer passed to next program * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY - * @index: index inside array that selects specific program to run + * @index: 32-bit index inside array that selects specific program to run * Return: 0 on success or negative error * * int bpf_clone_redirect(skb, ifindex, flags) diff --git a/kernel/tools/perf/builtin-script.c b/kernel/tools/perf/builtin-script.c index 3d4c3b5e1..0c977b6e0 100644 --- a/kernel/tools/perf/builtin-script.c +++ b/kernel/tools/perf/builtin-script.c @@ -586,7 +586,7 @@ static void print_sample_brstack(struct perf_sample *sample, thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt); } - printf("0x%"PRIx64, from); + printf(" 0x%"PRIx64, from); if (PRINT_FIELD(DSO)) { printf("("); map__fprintf_dsoname(alf.map, stdout); @@ -681,7 +681,7 @@ static void print_sample_brstackoff(struct perf_sample *sample, if (alt.map && !alt.map->dso->adjust_symbols) to = map__map_ip(alt.map, to); - printf("0x%"PRIx64, from); + printf(" 0x%"PRIx64, from); if (PRINT_FIELD(DSO)) { printf("("); map__fprintf_dsoname(alf.map, stdout); diff --git a/kernel/tools/perf/util/callchain.c b/kernel/tools/perf/util/callchain.c index be09d77ca..a971caf37 100644 --- a/kernel/tools/perf/util/callchain.c +++ b/kernel/tools/perf/util/callchain.c @@ -685,6 +685,8 @@ static enum match_result match_chain(struct callchain_cursor_node *node, { struct symbol *sym = node->sym; u64 left, right; + struct dso *left_dso = NULL; + struct dso *right_dso = NULL; if (callchain_param.key == CCKEY_SRCLINE) { enum match_result match = match_chain_srcline(node, cnode); @@ -696,12 +698,14 @@ static enum match_result match_chain(struct callchain_cursor_node *node, if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) { left = cnode->ms.sym->start; right = sym->start; + left_dso = cnode->ms.map->dso; + right_dso = node->map->dso; } else { left = cnode->ip; right = node->ip; } - if (left == right) { + if (left == right && left_dso == right_dso) { if (node->branch) { cnode->branch_count++; diff --git a/kernel/tools/perf/util/parse-events.c b/kernel/tools/perf/util/parse-events.c index f6257fb4f..39b15968e 100644 --- a/kernel/tools/perf/util/parse-events.c +++ b/kernel/tools/perf/util/parse-events.c @@ -309,10 +309,11 @@ static char *get_config_name(struct list_head *head_terms) static struct perf_evsel * __add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, - char *name, struct cpu_map *cpus, + char *name, struct perf_pmu *pmu, struct list_head *config_terms, bool auto_merge_stats) { struct perf_evsel *evsel; + struct cpu_map *cpus = pmu ? pmu->cpus : NULL; event_attr_init(attr); @@ -323,7 +324,7 @@ __add_event(struct list_head *list, int *idx, (*idx)++; evsel->cpus = cpu_map__get(cpus); evsel->own_cpus = cpu_map__get(cpus); - evsel->system_wide = !!cpus; + evsel->system_wide = pmu ? pmu->is_uncore : false; evsel->auto_merge_stats = auto_merge_stats; if (name) @@ -1233,7 +1234,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state, if (!head_config) { attr.type = pmu->type; - evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu->cpus, NULL, auto_merge_stats); + evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats); return evsel ? 0 : -ENOMEM; } @@ -1254,7 +1255,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state, return -EINVAL; evsel = __add_event(list, &parse_state->idx, &attr, - get_config_name(head_config), pmu->cpus, + get_config_name(head_config), pmu, &config_terms, auto_merge_stats); if (evsel) { evsel->unit = info.unit; diff --git a/kernel/tools/perf/util/pmu.c b/kernel/tools/perf/util/pmu.c index ac16a9db1..1c4d7b4e4 100644 --- a/kernel/tools/perf/util/pmu.c +++ b/kernel/tools/perf/util/pmu.c @@ -470,31 +470,10 @@ static void pmu_read_sysfs(void) closedir(dir); } -static struct cpu_map *pmu_cpumask(const char *name) +static struct cpu_map *__pmu_cpumask(const char *path) { - struct stat st; - char path[PATH_MAX]; FILE *file; struct cpu_map *cpus; - const char *sysfs = sysfs__mountpoint(); - const char *templates[] = { - "%s/bus/event_source/devices/%s/cpumask", - "%s/bus/event_source/devices/%s/cpus", - NULL - }; - const char **template; - - if (!sysfs) - return NULL; - - for (template = templates; *template; template++) { - snprintf(path, PATH_MAX, *template, sysfs, name); - if (stat(path, &st) == 0) - break; - } - - if (!*template) - return NULL; file = fopen(path, "r"); if (!file) @@ -505,6 +484,51 @@ static struct cpu_map *pmu_cpumask(const char *name) return cpus; } +/* + * Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64) + * may have a "cpus" file. + */ +#define CPUS_TEMPLATE_UNCORE "%s/bus/event_source/devices/%s/cpumask" +#define CPUS_TEMPLATE_CPU "%s/bus/event_source/devices/%s/cpus" + +static struct cpu_map *pmu_cpumask(const char *name) +{ + char path[PATH_MAX]; + struct cpu_map *cpus; + const char *sysfs = sysfs__mountpoint(); + const char *templates[] = { + CPUS_TEMPLATE_UNCORE, + CPUS_TEMPLATE_CPU, + NULL + }; + const char **template; + + if (!sysfs) + return NULL; + + for (template = templates; *template; template++) { + snprintf(path, PATH_MAX, *template, sysfs, name); + cpus = __pmu_cpumask(path); + if (cpus) + return cpus; + } + + return NULL; +} + +static bool pmu_is_uncore(const char *name) +{ + char path[PATH_MAX]; + struct cpu_map *cpus; + const char *sysfs = sysfs__mountpoint(); + + snprintf(path, PATH_MAX, CPUS_TEMPLATE_UNCORE, sysfs, name); + cpus = __pmu_cpumask(path); + cpu_map__put(cpus); + + return !!cpus; +} + /* * Return the CPU id as a raw string. * @@ -617,6 +641,8 @@ static struct perf_pmu *pmu_lookup(const char *name) pmu->cpus = pmu_cpumask(name); + pmu->is_uncore = pmu_is_uncore(name); + INIT_LIST_HEAD(&pmu->format); INIT_LIST_HEAD(&pmu->aliases); list_splice(&format, &pmu->format); diff --git a/kernel/tools/perf/util/pmu.h b/kernel/tools/perf/util/pmu.h index 389e97293..fe0de0502 100644 --- a/kernel/tools/perf/util/pmu.h +++ b/kernel/tools/perf/util/pmu.h @@ -22,6 +22,7 @@ struct perf_pmu { char *name; __u32 type; bool selectable; + bool is_uncore; struct perf_event_attr *default_config; struct cpu_map *cpus; struct list_head format; /* HEAD struct perf_pmu_format -> list */ diff --git a/kernel/tools/testing/selftests/mqueue/Makefile b/kernel/tools/testing/selftests/mqueue/Makefile index 0f5e347b0..152823b6c 100644 --- a/kernel/tools/testing/selftests/mqueue/Makefile +++ b/kernel/tools/testing/selftests/mqueue/Makefile @@ -5,8 +5,8 @@ TEST_GEN_PROGS := mq_open_tests mq_perf_tests include ../lib.mk override define RUN_TESTS - $(OUTPUT)/mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]" - $(OUTPUT)//mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]" + @$(OUTPUT)/mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]" + @$(OUTPUT)/mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]" endef override define EMIT_TESTS diff --git a/kernel/tools/testing/selftests/networking/timestamping/rxtimestamp.c b/kernel/tools/testing/selftests/networking/timestamping/rxtimestamp.c index 00f286661..dd4162fc0 100644 --- a/kernel/tools/testing/selftests/networking/timestamping/rxtimestamp.c +++ b/kernel/tools/testing/selftests/networking/timestamping/rxtimestamp.c @@ -341,7 +341,7 @@ int main(int argc, char **argv) return 0; case 'n': t = atoi(optarg); - if (t > ARRAY_SIZE(test_cases)) + if (t >= ARRAY_SIZE(test_cases)) error(1, 0, "Invalid test case: %d", t); all_tests = false; test_cases[t].enabled = true; diff --git a/kernel/tools/testing/selftests/vm/userfaultfd.c b/kernel/tools/testing/selftests/vm/userfaultfd.c index a2c53a3d2..de2f9ec8a 100644 --- a/kernel/tools/testing/selftests/vm/userfaultfd.c +++ b/kernel/tools/testing/selftests/vm/userfaultfd.c @@ -397,7 +397,7 @@ static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy, } } -static int copy_page(int ufd, unsigned long offset) +static int __copy_page(int ufd, unsigned long offset, bool retry) { struct uffdio_copy uffdio_copy; @@ -418,7 +418,7 @@ static int copy_page(int ufd, unsigned long offset) fprintf(stderr, "UFFDIO_COPY unexpected copy %Ld\n", uffdio_copy.copy), exit(1); } else { - if (test_uffdio_copy_eexist) { + if (test_uffdio_copy_eexist && retry) { test_uffdio_copy_eexist = false; retry_copy_page(ufd, &uffdio_copy, offset); } @@ -427,6 +427,16 @@ static int copy_page(int ufd, unsigned long offset) return 0; } +static int copy_page_retry(int ufd, unsigned long offset) +{ + return __copy_page(ufd, offset, true); +} + +static int copy_page(int ufd, unsigned long offset) +{ + return __copy_page(ufd, offset, false); +} + static void *uffd_poll_thread(void *arg) { unsigned long cpu = (unsigned long) arg; @@ -544,7 +554,7 @@ static void *background_thread(void *arg) for (page_nr = cpu * nr_pages_per_cpu; page_nr < (cpu+1) * nr_pages_per_cpu; page_nr++) - copy_page(uffd, page_nr * page_size); + copy_page_retry(uffd, page_nr * page_size); return NULL; } @@ -779,7 +789,7 @@ static void retry_uffdio_zeropage(int ufd, } } -static int uffdio_zeropage(int ufd, unsigned long offset) +static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry) { struct uffdio_zeropage uffdio_zeropage; int ret; @@ -814,7 +824,7 @@ static int uffdio_zeropage(int ufd, unsigned long offset) fprintf(stderr, "UFFDIO_ZEROPAGE unexpected %Ld\n", uffdio_zeropage.zeropage), exit(1); } else { - if (test_uffdio_zeropage_eexist) { + if (test_uffdio_zeropage_eexist && retry) { test_uffdio_zeropage_eexist = false; retry_uffdio_zeropage(ufd, &uffdio_zeropage, offset); @@ -830,6 +840,11 @@ static int uffdio_zeropage(int ufd, unsigned long offset) return 0; } +static int uffdio_zeropage(int ufd, unsigned long offset) +{ + return __uffdio_zeropage(ufd, offset, false); +} + /* exercise UFFDIO_ZEROPAGE */ static int userfaultfd_zeropage_test(void) { diff --git a/kernel/tools/testing/selftests/x86/Makefile b/kernel/tools/testing/selftests/x86/Makefile index 97f187e26..0a74a20ca 100644 --- a/kernel/tools/testing/selftests/x86/Makefile +++ b/kernel/tools/testing/selftests/x86/Makefile @@ -20,7 +20,7 @@ BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) -CFLAGS := -O2 -g -std=gnu99 -pthread -Wall +CFLAGS := -O2 -g -std=gnu99 -pthread -Wall -no-pie UNAME_M := $(shell uname -m) CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32)