diff --git a/Makefile b/Makefile index 35faaf8fb651..eab97c3d462d 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 3 PATCHLEVEL = 18 -SUBLEVEL = 18 +SUBLEVEL = 19 EXTRAVERSION = NAME = Diseased Newt diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S index 01dcb0e752d9..d66d608f7ce7 100644 --- a/arch/arm/kvm/interrupts.S +++ b/arch/arm/kvm/interrupts.S @@ -159,13 +159,9 @@ __kvm_vcpu_return: @ Don't trap coprocessor accesses for host kernel set_hstr vmexit set_hdcr vmexit - set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)) + set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)), after_vfp_restore #ifdef CONFIG_VFPv3 - @ Save floating point registers we if let guest use them. - tst r2, #(HCPTR_TCP(10) | HCPTR_TCP(11)) - bne after_vfp_restore - @ Switch VFP/NEON hardware state to the host's add r7, vcpu, #VCPU_VFP_GUEST store_vfp_state r7 @@ -177,6 +173,8 @@ after_vfp_restore: @ Restore FPEXC_EN which we clobbered on entry pop {r2} VFPFMXR FPEXC, r2 +#else +after_vfp_restore: #endif @ Reset Hyp-role @@ -472,7 +470,7 @@ switch_to_guest_vfp: push {r3-r7} @ NEON/VFP used. Turn on VFP access. - set_hcptr vmexit, (HCPTR_TCP(10) | HCPTR_TCP(11)) + set_hcptr vmtrap, (HCPTR_TCP(10) | HCPTR_TCP(11)) @ Switch VFP/NEON hardware state to the guest's add r7, r0, #VCPU_VFP_HOST diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S index 14d488388480..f6f14812d106 100644 --- a/arch/arm/kvm/interrupts_head.S +++ b/arch/arm/kvm/interrupts_head.S @@ -599,8 +599,13 @@ ARM_BE8(rev r6, r6 ) .endm /* Configures the HCPTR (Hyp Coprocessor Trap Register) on entry/return - * (hardware reset value is 0). Keep previous value in r2. */ -.macro set_hcptr operation, mask + * (hardware reset value is 0). Keep previous value in r2. + * An ISB is emited on vmexit/vmtrap, but executed on vmexit only if + * VFP wasn't already enabled (always executed on vmtrap). + * If a label is specified with vmexit, it is branched to if VFP wasn't + * enabled. + */ +.macro set_hcptr operation, mask, label = none mrc p15, 4, r2, c1, c1, 2 ldr r3, =\mask .if \operation == vmentry @@ -609,6 +614,17 @@ ARM_BE8(rev r6, r6 ) bic r3, r2, r3 @ Don't trap defined coproc-accesses .endif mcr p15, 4, r3, c1, c1, 2 + .if \operation != vmentry + .if \operation == vmexit + tst r2, #(HCPTR_TCP(10) | HCPTR_TCP(11)) + beq 1f + .endif + isb + .if \label != none + b \label + .endif +1: + .endif .endm /* Configures the HDCR (Hyp Debug Configuration Register) on entry/return diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c index 2daef619d053..5474a76803f0 100644 --- a/arch/arm/mach-imx/clk-imx6q.c +++ b/arch/arm/mach-imx/clk-imx6q.c @@ -439,7 +439,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node) clk[IMX6QDL_CLK_GPMI_IO] = imx_clk_gate2("gpmi_io", "enfc", base + 0x78, 28); clk[IMX6QDL_CLK_GPMI_APB] = imx_clk_gate2("gpmi_apb", "usdhc3", base + 0x78, 30); clk[IMX6QDL_CLK_ROM] = imx_clk_gate2("rom", "ahb", base + 0x7c, 0); - clk[IMX6QDL_CLK_SATA] = imx_clk_gate2("sata", "ipg", base + 0x7c, 4); + clk[IMX6QDL_CLK_SATA] = imx_clk_gate2("sata", "ahb", base + 0x7c, 4); clk[IMX6QDL_CLK_SDMA] = imx_clk_gate2("sdma", "ahb", base + 0x7c, 6); clk[IMX6QDL_CLK_SPBA] = imx_clk_gate2("spba", "ipg", base + 0x7c, 12); clk[IMX6QDL_CLK_SPDIF] = imx_clk_gate2("spdif", "spdif_podf", base + 0x7c, 14); diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 7fd3e27e3ccc..8afb863f5a9e 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -18,6 +18,7 @@ #ifndef __ARM64_KVM_ARM_H__ #define __ARM64_KVM_ARM_H__ +#include #include /* Hyp Configuration Register (HCR) bits */ @@ -160,9 +161,9 @@ #endif #define VTTBR_BADDR_SHIFT (VTTBR_X - 1) -#define VTTBR_BADDR_MASK (((1LLU << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT) -#define VTTBR_VMID_SHIFT (48LLU) -#define VTTBR_VMID_MASK (0xffLLU << VTTBR_VMID_SHIFT) +#define VTTBR_BADDR_MASK (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT) +#define VTTBR_VMID_SHIFT (UL(48)) +#define VTTBR_VMID_MASK (UL(0xFF) << VTTBR_VMID_SHIFT) /* Hyp System Trap Register */ #define HSTR_EL2_TTEE (1 << 16) @@ -185,13 +186,13 @@ /* Exception Syndrome Register (ESR) bits */ #define ESR_EL2_EC_SHIFT (26) -#define ESR_EL2_EC (0x3fU << ESR_EL2_EC_SHIFT) -#define ESR_EL2_IL (1U << 25) +#define ESR_EL2_EC (UL(0x3f) << ESR_EL2_EC_SHIFT) +#define ESR_EL2_IL (UL(1) << 25) #define ESR_EL2_ISS (ESR_EL2_IL - 1) #define ESR_EL2_ISV_SHIFT (24) -#define ESR_EL2_ISV (1U << ESR_EL2_ISV_SHIFT) +#define ESR_EL2_ISV (UL(1) << ESR_EL2_ISV_SHIFT) #define ESR_EL2_SAS_SHIFT (22) -#define ESR_EL2_SAS (3U << ESR_EL2_SAS_SHIFT) +#define ESR_EL2_SAS (UL(3) << ESR_EL2_SAS_SHIFT) #define ESR_EL2_SSE (1 << 21) #define ESR_EL2_SRT_SHIFT (16) #define ESR_EL2_SRT_MASK (0x1f << ESR_EL2_SRT_SHIFT) @@ -205,16 +206,16 @@ #define ESR_EL2_FSC_TYPE (0x3c) #define ESR_EL2_CV_SHIFT (24) -#define ESR_EL2_CV (1U << ESR_EL2_CV_SHIFT) +#define ESR_EL2_CV (UL(1) << ESR_EL2_CV_SHIFT) #define ESR_EL2_COND_SHIFT (20) -#define ESR_EL2_COND (0xfU << ESR_EL2_COND_SHIFT) +#define ESR_EL2_COND (UL(0xf) << ESR_EL2_COND_SHIFT) #define FSC_FAULT (0x04) #define FSC_PERM (0x0c) /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ -#define HPFAR_MASK (~0xFUL) +#define HPFAR_MASK (~UL(0xf)) #define ESR_EL2_EC_UNKNOWN (0x00) #define ESR_EL2_EC_WFI (0x01) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 3635fff7b32d..c9148e268512 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -173,7 +173,7 @@ config SBUS config NEED_DMA_MAP_STATE def_bool y - depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG + depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG || SWIOTLB config NEED_SG_DMA_LENGTH def_bool y diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6c0709ff2f38..306d152336cd 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -571,7 +571,7 @@ struct kvm_arch { struct kvm_pic *vpic; struct kvm_ioapic *vioapic; struct kvm_pit *vpit; - int vapics_in_nmi_mode; + atomic_t vapics_in_nmi_mode; struct mutex apic_map_lock; struct kvm_apic_map *apic_map; diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c index ec9df6f9cd47..5e109a31f62b 100644 --- a/arch/x86/kernel/cpu/microcode/intel_early.c +++ b/arch/x86/kernel/cpu/microcode/intel_early.c @@ -321,7 +321,7 @@ get_matching_model_microcode(int cpu, unsigned long start, unsigned int mc_saved_count = mc_saved_data->mc_saved_count; int i; - while (leftover) { + while (leftover && mc_saved_count < ARRAY_SIZE(mc_saved_tmp)) { mc_header = (struct microcode_header_intel *)ucode_ptr; mc_size = get_totalsize(mc_header); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 498b6d967138..df11583a9041 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2604,13 +2604,13 @@ __init int intel_pmu_init(void) * counter, so do not extend mask to generic counters */ for_each_event_constraint(c, x86_pmu.event_constraints) { - if (c->cmask != FIXED_EVENT_FLAGS - || c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) { - continue; + if (c->cmask == FIXED_EVENT_FLAGS + && c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) { + c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; } - - c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; - c->weight += x86_pmu.num_counters; + c->idxmsk64 &= + ~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed)); + c->weight = hweight64(c->idxmsk64); } } diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 344b63f18d14..3dddb89ba320 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -982,6 +982,9 @@ ENTRY(xen_hypervisor_callback) ENTRY(xen_do_upcall) 1: mov %esp, %eax call xen_evtchn_do_upcall +#ifndef CONFIG_PREEMPT + call xen_maybe_preempt_hcall +#endif jmp ret_from_intr CFI_ENDPROC ENDPROC(xen_hypervisor_callback) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index f1dc27f457f1..e36d9815ef56 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1173,6 +1173,9 @@ ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs) popq %rsp CFI_DEF_CFA_REGISTER rsp decl PER_CPU_VAR(irq_count) +#ifndef CONFIG_PREEMPT + call xen_maybe_preempt_hcall +#endif jmp error_exit CFI_ENDPROC END(xen_do_hypervisor_callback) diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 30a2aa3782fa..e7be5290fe1f 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -61,9 +61,16 @@ #define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD) #endif -/* Number of possible pages in the lowmem region */ -LOWMEM_PAGES = (((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) - +/* + * Number of possible pages in the lowmem region. + * + * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a + * gas warning about overflowing shift count when gas has been compiled + * with only a host target support using a 32-bit type for internal + * representation. + */ +LOWMEM_PAGES = (((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT) + /* Enough space to fit pagetables for the low memory linear map */ MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 93d2c04c6f8f..f2e281cf8c19 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -330,13 +330,16 @@ int __copy_instruction(u8 *dest, u8 *src) { struct insn insn; kprobe_opcode_t buf[MAX_INSN_SIZE]; + int length; kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, (unsigned long)src)); insn_get_length(&insn); + length = insn.length; + /* Another subsystem puts a breakpoint, failed to recover */ if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) return 0; - memcpy(dest, insn.kaddr, insn.length); + memcpy(dest, insn.kaddr, length); #ifdef CONFIG_X86_64 if (insn_rip_relative(&insn)) { @@ -366,7 +369,7 @@ int __copy_instruction(u8 *dest, u8 *src) *(s32 *) disp = (s32) newdisp; } #endif - return insn.length; + return length; } static int arch_copy_kprobe(struct kprobe *p) diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 298781d4cfb4..1406ffde3e35 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -305,7 +305,7 @@ static void pit_do_work(struct kthread_work *work) * LVT0 to NMI delivery. Other PIC interrupts are just sent to * VCPU0, and only if its LVT0 is in EXTINT mode. */ - if (kvm->arch.vapics_in_nmi_mode > 0) + if (atomic_read(&kvm->arch.vapics_in_nmi_mode) > 0) kvm_for_each_vcpu(i, vcpu, kvm) kvm_apic_nmi_wd_deliver(vcpu); } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index b8345dd41b25..de8e50040124 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1112,10 +1112,10 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) if (!nmi_wd_enabled) { apic_debug("Receive NMI setting on APIC_LVT0 " "for cpu %d\n", apic->vcpu->vcpu_id); - apic->vcpu->kvm->arch.vapics_in_nmi_mode++; + atomic_inc(&apic->vcpu->kvm->arch.vapics_in_nmi_mode); } } else if (nmi_wd_enabled) - apic->vcpu->kvm->arch.vapics_in_nmi_mode--; + atomic_dec(&apic->vcpu->kvm->arch.vapics_in_nmi_mode); } static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) @@ -1687,6 +1687,7 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, apic_update_ppr(apic); hrtimer_cancel(&apic->lapic_timer.timer); + apic_manage_nmi_watchdog(apic, kvm_apic_get_reg(apic, APIC_LVT0)); update_divide_count(apic); start_apic_timer(apic); apic->irr_pending = true; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 170e7d49ba65..b83bff87408f 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -511,8 +511,10 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - if (svm->vmcb->control.next_rip != 0) + if (svm->vmcb->control.next_rip != 0) { + WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS)); svm->next_rip = svm->vmcb->control.next_rip; + } if (!svm->next_rip) { if (emulate_instruction(vcpu, EMULTYPE_SKIP) != @@ -4306,7 +4308,9 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu, break; } - vmcb->control.next_rip = info->next_rip; + /* TODO: Advertise NRIPS to guest hypervisor unconditionally */ + if (static_cpu_has(X86_FEATURE_NRIPS)) + vmcb->control.next_rip = info->next_rip; vmcb->control.exit_code = icpt_info.exit_code; vmexit = nested_svm_exit_handled(svm); diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index a46c4af2ac98..15697c630139 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -910,7 +910,7 @@ static void get_memory_layout(const struct mem_ctl_info *mci) u32 reg; u64 limit, prv = 0; u64 tmp_mb; - u32 mb, kb; + u32 gb, mb; u32 rir_way; /* @@ -920,15 +920,17 @@ static void get_memory_layout(const struct mem_ctl_info *mci) pvt->tolm = pvt->info.get_tolm(pvt); tmp_mb = (1 + pvt->tolm) >> 20; - mb = div_u64_rem(tmp_mb, 1000, &kb); - edac_dbg(0, "TOLM: %u.%03u GB (0x%016Lx)\n", mb, kb, (u64)pvt->tolm); + gb = div_u64_rem(tmp_mb, 1024, &mb); + edac_dbg(0, "TOLM: %u.%03u GB (0x%016Lx)\n", + gb, (mb*1000)/1024, (u64)pvt->tolm); /* Address range is already 45:25 */ pvt->tohm = pvt->info.get_tohm(pvt); tmp_mb = (1 + pvt->tohm) >> 20; - mb = div_u64_rem(tmp_mb, 1000, &kb); - edac_dbg(0, "TOHM: %u.%03u GB (0x%016Lx)\n", mb, kb, (u64)pvt->tohm); + gb = div_u64_rem(tmp_mb, 1024, &mb); + edac_dbg(0, "TOHM: %u.%03u GB (0x%016Lx)\n", + gb, (mb*1000)/1024, (u64)pvt->tohm); /* * Step 2) Get SAD range and SAD Interleave list @@ -950,11 +952,11 @@ static void get_memory_layout(const struct mem_ctl_info *mci) break; tmp_mb = (limit + 1) >> 20; - mb = div_u64_rem(tmp_mb, 1000, &kb); + gb = div_u64_rem(tmp_mb, 1024, &mb); edac_dbg(0, "SAD#%d %s up to %u.%03u GB (0x%016Lx) Interleave: %s reg=0x%08x\n", n_sads, get_dram_attr(reg), - mb, kb, + gb, (mb*1000)/1024, ((u64)tmp_mb) << 20L, INTERLEAVE_MODE(reg) ? "8:6" : "[8:6]XOR[18:16]", reg); @@ -985,9 +987,9 @@ static void get_memory_layout(const struct mem_ctl_info *mci) break; tmp_mb = (limit + 1) >> 20; - mb = div_u64_rem(tmp_mb, 1000, &kb); + gb = div_u64_rem(tmp_mb, 1024, &mb); edac_dbg(0, "TAD#%d: up to %u.%03u GB (0x%016Lx), socket interleave %d, memory interleave %d, TGT: %d, %d, %d, %d, reg=0x%08x\n", - n_tads, mb, kb, + n_tads, gb, (mb*1000)/1024, ((u64)tmp_mb) << 20L, (u32)TAD_SOCK(reg), (u32)TAD_CH(reg), @@ -1010,10 +1012,10 @@ static void get_memory_layout(const struct mem_ctl_info *mci) tad_ch_nilv_offset[j], ®); tmp_mb = TAD_OFFSET(reg) >> 20; - mb = div_u64_rem(tmp_mb, 1000, &kb); + gb = div_u64_rem(tmp_mb, 1024, &mb); edac_dbg(0, "TAD CH#%d, offset #%d: %u.%03u GB (0x%016Lx), reg=0x%08x\n", i, j, - mb, kb, + gb, (mb*1000)/1024, ((u64)tmp_mb) << 20L, reg); } @@ -1035,10 +1037,10 @@ static void get_memory_layout(const struct mem_ctl_info *mci) tmp_mb = pvt->info.rir_limit(reg) >> 20; rir_way = 1 << RIR_WAY(reg); - mb = div_u64_rem(tmp_mb, 1000, &kb); + gb = div_u64_rem(tmp_mb, 1024, &mb); edac_dbg(0, "CH#%d RIR#%d, limit: %u.%03u GB (0x%016Lx), way: %d, reg=0x%08x\n", i, j, - mb, kb, + gb, (mb*1000)/1024, ((u64)tmp_mb) << 20L, rir_way, reg); @@ -1049,10 +1051,10 @@ static void get_memory_layout(const struct mem_ctl_info *mci) ®); tmp_mb = RIR_OFFSET(reg) << 6; - mb = div_u64_rem(tmp_mb, 1000, &kb); + gb = div_u64_rem(tmp_mb, 1024, &mb); edac_dbg(0, "CH#%d RIR#%d INTL#%d, offset %u.%03u GB (0x%016Lx), tgt: %d, reg=0x%08x\n", i, j, k, - mb, kb, + gb, (mb*1000)/1024, ((u64)tmp_mb) << 20L, (u32)RIR_RNK_TGT(reg), reg); @@ -1090,7 +1092,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, u8 ch_way, sck_way, pkg, sad_ha = 0; u32 tad_offset; u32 rir_way; - u32 mb, kb; + u32 mb, gb; u64 ch_addr, offset, limit = 0, prv = 0; @@ -1359,10 +1361,10 @@ static int get_memory_error_data(struct mem_ctl_info *mci, continue; limit = pvt->info.rir_limit(reg); - mb = div_u64_rem(limit >> 20, 1000, &kb); + gb = div_u64_rem(limit >> 20, 1024, &mb); edac_dbg(0, "RIR#%d, limit: %u.%03u GB (0x%016Lx), way: %d\n", n_rir, - mb, kb, + gb, (mb*1000)/1024, limit, 1 << RIR_WAY(reg)); if (ch_addr <= limit) diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index f599357e8392..826ef3df2dc7 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -149,6 +149,7 @@ static const struct min_max_quirk min_max_pnpid_table[] = { }, { (const char * const []){"LEN2000", NULL}, + {ANY_BOARD_ID, ANY_BOARD_ID}, 1024, 5113, 2021, 4832 }, { diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 505a9adac2d5..fab0ea1a46d1 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -1870,9 +1870,15 @@ static void free_pt_##LVL (unsigned long __pt) \ pt = (u64 *)__pt; \ \ for (i = 0; i < 512; ++i) { \ + /* PTE present? */ \ if (!IOMMU_PTE_PRESENT(pt[i])) \ continue; \ \ + /* Large PTE? */ \ + if (PM_PTE_LEVEL(pt[i]) == 0 || \ + PM_PTE_LEVEL(pt[i]) == 7) \ + continue; \ + \ p = (unsigned long)IOMMU_PTE_PAGE(pt[i]); \ FN(p); \ } \ diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index 573b53b38af4..bb686e15102c 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -360,6 +360,9 @@ unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx) struct can_frame *cf = (struct can_frame *)skb->data; u8 dlc = cf->can_dlc; + if (!(skb->tstamp.tv64)) + __net_timestamp(skb); + netif_rx(priv->echo_skb[idx]); priv->echo_skb[idx] = NULL; @@ -496,6 +499,7 @@ struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf) if (unlikely(!skb)) return NULL; + __net_timestamp(skb); skb->protocol = htons(ETH_P_CAN); skb->pkt_type = PACKET_BROADCAST; skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -524,6 +528,7 @@ struct sk_buff *alloc_canfd_skb(struct net_device *dev, if (unlikely(!skb)) return NULL; + __net_timestamp(skb); skb->protocol = htons(ETH_P_CANFD); skb->pkt_type = PACKET_BROADCAST; skb->ip_summed = CHECKSUM_UNNECESSARY; diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index acb5b92ace92..cb6b4723af4a 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -210,6 +210,7 @@ static void slc_bump(struct slcan *sl) if (!skb) return; + __net_timestamp(skb); skb->dev = sl->dev; skb->protocol = htons(ETH_P_CAN); skb->pkt_type = PACKET_BROADCAST; diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c index 4e94057ef5cf..30e4627a0c01 100644 --- a/drivers/net/can/vcan.c +++ b/drivers/net/can/vcan.c @@ -81,6 +81,9 @@ static void vcan_rx(struct sk_buff *skb, struct net_device *dev) skb->dev = dev; skb->ip_summed = CHECKSUM_UNNECESSARY; + if (!(skb->tstamp.tv64)) + __net_timestamp(skb); + netif_rx_ni(skb); } diff --git a/drivers/s390/kvm/virtio_ccw.c b/drivers/s390/kvm/virtio_ccw.c index bda52f18e967..397e6b8b9656 100644 --- a/drivers/s390/kvm/virtio_ccw.c +++ b/drivers/s390/kvm/virtio_ccw.c @@ -64,6 +64,7 @@ struct virtio_ccw_device { bool is_thinint; bool going_away; bool device_lost; + unsigned int config_ready; void *airq_info; }; @@ -758,8 +759,11 @@ static void virtio_ccw_get_config(struct virtio_device *vdev, if (ret) goto out_free; - memcpy(vcdev->config, config_area, sizeof(vcdev->config)); - memcpy(buf, &vcdev->config[offset], len); + memcpy(vcdev->config, config_area, offset + len); + if (buf) + memcpy(buf, &vcdev->config[offset], len); + if (vcdev->config_ready < offset + len) + vcdev->config_ready = offset + len; out_free: kfree(config_area); @@ -782,6 +786,9 @@ static void virtio_ccw_set_config(struct virtio_device *vdev, if (!config_area) goto out_free; + /* Make sure we don't overwrite fields. */ + if (vcdev->config_ready < offset) + virtio_ccw_get_config(vdev, 0, NULL, offset); memcpy(&vcdev->config[offset], buf, len); /* Write the config area to the host. */ memcpy(config_area, vcdev->config, sizeof(vcdev->config)); diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index 11300f7b49cb..daaed7c79e4f 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -311,8 +311,7 @@ void atmel_config_rs485(struct uart_port *port, struct serial_rs485 *rs485conf) if (rs485conf->flags & SER_RS485_ENABLED) { dev_dbg(port->dev, "Setting UART to RS485\n"); atmel_port->tx_done_mask = ATMEL_US_TXEMPTY; - if ((rs485conf->delay_rts_after_send) > 0) - UART_PUT_TTGR(port, rs485conf->delay_rts_after_send); + UART_PUT_TTGR(port, rs485conf->delay_rts_after_send); mode |= ATMEL_US_USMODE_RS485; } else { dev_dbg(port->dev, "Setting UART to RS232\n"); @@ -2016,9 +2015,7 @@ static void atmel_set_termios(struct uart_port *port, struct ktermios *termios, mode &= ~ATMEL_US_USMODE; if (atmel_port->rs485.flags & SER_RS485_ENABLED) { - if ((atmel_port->rs485.delay_rts_after_send) > 0) - UART_PUT_TTGR(port, - atmel_port->rs485.delay_rts_after_send); + UART_PUT_TTGR(port, atmel_port->rs485.delay_rts_after_send); mode |= ATMEL_US_USMODE_RS485; } diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 63314ede7ba6..ab9b7ac63407 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3400,6 +3400,7 @@ done: static void ffs_closed(struct ffs_data *ffs) { struct ffs_dev *ffs_obj; + struct f_fs_opts *opts; ENTER(); ffs_dev_lock(); @@ -3413,8 +3414,13 @@ static void ffs_closed(struct ffs_data *ffs) if (ffs_obj->ffs_closed_callback) ffs_obj->ffs_closed_callback(ffs); - if (!ffs_obj->opts || ffs_obj->opts->no_configfs - || !ffs_obj->opts->func_inst.group.cg_item.ci_parent) + if (ffs_obj->opts) + opts = ffs_obj->opts; + else + goto done; + + if (opts->no_configfs || !opts->func_inst.group.cg_item.ci_parent + || !atomic_read(&opts->func_inst.group.cg_item.ci_kref.refcount)) goto done; unregister_gadget_item(ffs_obj->opts-> diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index 2140398a2a8c..2ccd3592d41f 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -2,7 +2,7 @@ ifeq ($(filter y, $(CONFIG_ARM) $(CONFIG_ARM64)),) obj-$(CONFIG_HOTPLUG_CPU) += cpu_hotplug.o endif obj-$(CONFIG_X86) += fallback.o -obj-y += grant-table.o features.o balloon.o manage.o +obj-y += grant-table.o features.o balloon.o manage.o preempt.o obj-y += events/ obj-y += xenbus/ diff --git a/drivers/xen/preempt.c b/drivers/xen/preempt.c new file mode 100644 index 000000000000..a1800c150839 --- /dev/null +++ b/drivers/xen/preempt.c @@ -0,0 +1,44 @@ +/* + * Preemptible hypercalls + * + * Copyright (C) 2014 Citrix Systems R&D ltd. + * + * This source code is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License, or (at your option) any later version. + */ + +#include +#include + +#ifndef CONFIG_PREEMPT + +/* + * Some hypercalls issued by the toolstack can take many 10s of + * seconds. Allow tasks running hypercalls via the privcmd driver to + * be voluntarily preempted even if full kernel preemption is + * disabled. + * + * Such preemptible hypercalls are bracketed by + * xen_preemptible_hcall_begin() and xen_preemptible_hcall_end() + * calls. + */ + +DEFINE_PER_CPU(bool, xen_in_preemptible_hcall); +EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall); + +asmlinkage __visible void xen_maybe_preempt_hcall(void) +{ + if (unlikely(__this_cpu_read(xen_in_preemptible_hcall) + && should_resched())) { + /* + * Clear flag as we may be rescheduled on a different + * cpu. + */ + __this_cpu_write(xen_in_preemptible_hcall, false); + _cond_resched(); + __this_cpu_write(xen_in_preemptible_hcall, true); + } +} +#endif /* CONFIG_PREEMPT */ diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 569a13b9e856..59ac71c4a043 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -56,10 +56,12 @@ static long privcmd_ioctl_hypercall(void __user *udata) if (copy_from_user(&hypercall, udata, sizeof(hypercall))) return -EFAULT; + xen_preemptible_hcall_begin(); ret = privcmd_call(hypercall.op, hypercall.arg[0], hypercall.arg[1], hypercall.arg[2], hypercall.arg[3], hypercall.arg[4]); + xen_preemptible_hcall_end(); return ret; } diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index c81ce0c7c1a9..f54511dd287e 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2920,7 +2920,7 @@ done: */ if (!p->leave_spinning) btrfs_set_path_blocking(p); - if (ret < 0) + if (ret < 0 && !p->skip_release_on_error) btrfs_release_path(p); return ret; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index fe69edda11fb..ba5aec76e6f8 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -607,6 +607,7 @@ struct btrfs_path { unsigned int leave_spinning:1; unsigned int search_commit_root:1; unsigned int need_commit_sem:1; + unsigned int skip_release_on_error:1; }; /* @@ -3686,6 +3687,10 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans, int verify_dir_item(struct btrfs_root *root, struct extent_buffer *leaf, struct btrfs_dir_item *dir_item); +struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, + struct btrfs_path *path, + const char *name, + int name_len); /* orphan.c */ int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index fc8df866e919..1752625fb4dd 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -21,10 +21,6 @@ #include "hash.h" #include "transaction.h" -static struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, - struct btrfs_path *path, - const char *name, int name_len); - /* * insert a name into a directory, doing overflow properly if there is a hash * collision. data_size indicates how big the item inserted should be. On @@ -383,9 +379,9 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans, * this walks through all the entries in a dir item and finds one * for a specific name. */ -static struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, - struct btrfs_path *path, - const char *name, int name_len) +struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, + struct btrfs_path *path, + const char *name, int name_len) { struct btrfs_dir_item *dir_item; unsigned long name_ptr; diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 00eacd83ce3d..01bad724b5f7 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -29,6 +29,7 @@ #include "xattr.h" #include "disk-io.h" #include "props.h" +#include "locking.h" ssize_t __btrfs_getxattr(struct inode *inode, const char *name, @@ -91,7 +92,7 @@ static int do_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, const char *name, const void *value, size_t size, int flags) { - struct btrfs_dir_item *di; + struct btrfs_dir_item *di = NULL; struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_path *path; size_t name_len = strlen(name); @@ -103,84 +104,119 @@ static int do_setxattr(struct btrfs_trans_handle *trans, path = btrfs_alloc_path(); if (!path) return -ENOMEM; + path->skip_release_on_error = 1; + + if (!value) { + di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), + name, name_len, -1); + if (!di && (flags & XATTR_REPLACE)) + ret = -ENODATA; + else if (di) + ret = btrfs_delete_one_dir_name(trans, root, path, di); + goto out; + } + /* + * For a replace we can't just do the insert blindly. + * Do a lookup first (read-only btrfs_search_slot), and return if xattr + * doesn't exist. If it exists, fall down below to the insert/replace + * path - we can't race with a concurrent xattr delete, because the VFS + * locks the inode's i_mutex before calling setxattr or removexattr. + */ if (flags & XATTR_REPLACE) { - di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), name, - name_len, -1); - if (IS_ERR(di)) { - ret = PTR_ERR(di); - goto out; - } else if (!di) { + ASSERT(mutex_is_locked(&inode->i_mutex)); + di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode), + name, name_len, 0); + if (!di) { ret = -ENODATA; goto out; } - ret = btrfs_delete_one_dir_name(trans, root, path, di); - if (ret) - goto out; btrfs_release_path(path); + di = NULL; + } + ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode), + name, name_len, value, size); + if (ret == -EOVERFLOW) { /* - * remove the attribute + * We have an existing item in a leaf, split_leaf couldn't + * expand it. That item might have or not a dir_item that + * matches our target xattr, so lets check. */ - if (!value) - goto out; - } else { - di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode), - name, name_len, 0); - if (IS_ERR(di)) { - ret = PTR_ERR(di); + ret = 0; + btrfs_assert_tree_locked(path->nodes[0]); + di = btrfs_match_dir_item_name(root, path, name, name_len); + if (!di && !(flags & XATTR_REPLACE)) { + ret = -ENOSPC; goto out; } - if (!di && !value) - goto out; - btrfs_release_path(path); + } else if (ret == -EEXIST) { + ret = 0; + di = btrfs_match_dir_item_name(root, path, name, name_len); + ASSERT(di); /* logic error */ + } else if (ret) { + goto out; } -again: - ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode), - name, name_len, value, size); - /* - * If we're setting an xattr to a new value but the new value is say - * exactly BTRFS_MAX_XATTR_SIZE, we could end up with EOVERFLOW getting - * back from split_leaf. This is because it thinks we'll be extending - * the existing item size, but we're asking for enough space to add the - * item itself. So if we get EOVERFLOW just set ret to EEXIST and let - * the rest of the function figure it out. - */ - if (ret == -EOVERFLOW) + if (di && (flags & XATTR_CREATE)) { ret = -EEXIST; + goto out; + } - if (ret == -EEXIST) { - if (flags & XATTR_CREATE) - goto out; + if (di) { /* - * We can't use the path we already have since we won't have the - * proper locking for a delete, so release the path and - * re-lookup to delete the thing. + * We're doing a replace, and it must be atomic, that is, at + * any point in time we have either the old or the new xattr + * value in the tree. We don't want readers (getxattr and + * listxattrs) to miss a value, this is specially important + * for ACLs. */ - btrfs_release_path(path); - di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), - name, name_len, -1); - if (IS_ERR(di)) { - ret = PTR_ERR(di); - goto out; - } else if (!di) { - /* Shouldn't happen but just in case... */ - btrfs_release_path(path); - goto again; + const int slot = path->slots[0]; + struct extent_buffer *leaf = path->nodes[0]; + const u16 old_data_len = btrfs_dir_data_len(leaf, di); + const u32 item_size = btrfs_item_size_nr(leaf, slot); + const u32 data_size = sizeof(*di) + name_len + size; + struct btrfs_item *item; + unsigned long data_ptr; + char *ptr; + + if (size > old_data_len) { + if (btrfs_leaf_free_space(root, leaf) < + (size - old_data_len)) { + ret = -ENOSPC; + goto out; + } } - ret = btrfs_delete_one_dir_name(trans, root, path, di); - if (ret) - goto out; + if (old_data_len + name_len + sizeof(*di) == item_size) { + /* No other xattrs packed in the same leaf item. */ + if (size > old_data_len) + btrfs_extend_item(root, path, + size - old_data_len); + else if (size < old_data_len) + btrfs_truncate_item(root, path, data_size, 1); + } else { + /* There are other xattrs packed in the same item. */ + ret = btrfs_delete_one_dir_name(trans, root, path, di); + if (ret) + goto out; + btrfs_extend_item(root, path, data_size); + } + item = btrfs_item_nr(slot); + ptr = btrfs_item_ptr(leaf, slot, char); + ptr += btrfs_item_size(leaf, item) - data_size; + di = (struct btrfs_dir_item *)ptr; + btrfs_set_dir_data_len(leaf, di, size); + data_ptr = ((unsigned long)(di + 1)) + name_len; + write_extent_buffer(leaf, value, data_ptr, size); + btrfs_mark_buffer_dirty(leaf); + } else { /* - * We have a value to set, so go back and try to insert it now. + * Insert, and we had space for the xattr, so path->slots[0] is + * where our xattr dir_item is and btrfs_insert_xattr_item() + * filled it. */ - if (value) { - btrfs_release_path(path); - goto again; - } } out: btrfs_free_path(path); diff --git a/fs/dcache.c b/fs/dcache.c index e0750b8f51aa..d0539a4a1ab1 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2893,17 +2893,6 @@ restart: vfsmnt = &mnt->mnt; continue; } - /* - * Filesystems needing to implement special "root names" - * should do so with ->d_dname() - */ - if (IS_ROOT(dentry) && - (dentry->d_name.len != 1 || - dentry->d_name.name[0] != '/')) { - WARN(1, "Root dentry has weird name <%.*s>\n", - (int) dentry->d_name.len, - dentry->d_name.name); - } if (!error) error = is_mounted(vfsmnt) ? 1 : 2; break; diff --git a/fs/inode.c b/fs/inode.c index 26753ba7b6d6..56d1d2b4bf31 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1631,8 +1631,8 @@ int file_remove_suid(struct file *file) error = security_inode_killpriv(dentry); if (!error && killsuid) error = __remove_suid(dentry, killsuid); - if (!error && (inode->i_sb->s_flags & MS_NOSEC)) - inode->i_flags |= S_NOSEC; + if (!error) + inode_has_no_xattr(inode); return error; } diff --git a/fs/namespace.c b/fs/namespace.c index a19d05c4ebe5..da23ad8a2c85 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2297,6 +2297,8 @@ unlock: return err; } +static bool fs_fully_visible(struct file_system_type *fs_type, int *new_mnt_flags); + /* * create a new mount for userspace and request it to be added into the * namespace's tree @@ -2328,6 +2330,10 @@ static int do_new_mount(struct path *path, const char *fstype, int flags, flags |= MS_NODEV; mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV; } + if (type->fs_flags & FS_USERNS_VISIBLE) { + if (!fs_fully_visible(type, &mnt_flags)) + return -EPERM; + } } mnt = vfs_kern_mount(type, flags, name, data); @@ -3125,9 +3131,10 @@ bool current_chrooted(void) return chrooted; } -bool fs_fully_visible(struct file_system_type *type) +static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags) { struct mnt_namespace *ns = current->nsproxy->mnt_ns; + int new_flags = *new_mnt_flags; struct mount *mnt; bool visible = false; @@ -3146,16 +3153,37 @@ bool fs_fully_visible(struct file_system_type *type) if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root) continue; - /* This mount is not fully visible if there are any child mounts - * that cover anything except for empty directories. + /* Verify the mount flags are equal to or more permissive + * than the proposed new mount. + */ + if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) && + !(new_flags & MNT_READONLY)) + continue; + if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) && + !(new_flags & MNT_NODEV)) + continue; + if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) && + ((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK))) + continue; + + /* This mount is not fully visible if there are any + * locked child mounts that cover anything except for + * empty directories. */ list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { struct inode *inode = child->mnt_mountpoint->d_inode; + /* Only worry about locked mounts */ + if (!(mnt->mnt.mnt_flags & MNT_LOCKED)) + continue; if (!S_ISDIR(inode->i_mode)) goto next; if (inode->i_nlink > 2) goto next; } + /* Preserve the locked attributes */ + *new_mnt_flags |= mnt->mnt.mnt_flags & (MNT_LOCK_READONLY | \ + MNT_LOCK_NODEV | \ + MNT_LOCK_ATIME); visible = true; goto found; next: ; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index b13edc0865f7..c9ff4a176a25 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5356,7 +5356,6 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl, atomic_inc(&lsp->ls_count); /* Ensure we don't close file until we're done freeing locks! */ p->ctx = get_nfs_open_context(ctx); - get_file(fl->fl_file); memcpy(&p->fl, fl, sizeof(p->fl)); p->server = NFS_SERVER(inode); return p; @@ -5368,7 +5367,6 @@ static void nfs4_locku_release_calldata(void *data) nfs_free_seqid(calldata->arg.seqid); nfs4_put_lock_state(calldata->lsp); put_nfs_open_context(calldata->ctx); - fput(calldata->fl.fl_file); kfree(calldata); } diff --git a/fs/proc/root.c b/fs/proc/root.c index 094e44d4a6be..9e772f1a5386 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -112,9 +112,6 @@ static struct dentry *proc_mount(struct file_system_type *fs_type, ns = task_active_pid_ns(current); options = data; - if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type)) - return ERR_PTR(-EPERM); - /* Does the mounter have privilege over the pid namespace? */ if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); @@ -159,7 +156,7 @@ static struct file_system_type proc_fs_type = { .name = "proc", .mount = proc_mount, .kill_sb = proc_kill_sb, - .fs_flags = FS_USERNS_MOUNT, + .fs_flags = FS_USERNS_VISIBLE | FS_USERNS_MOUNT, }; void __init proc_root_init(void) diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 8a49486bf30c..1c6ac6fcee9f 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -31,9 +31,6 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, bool new_sb; if (!(flags & MS_KERNMOUNT)) { - if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type)) - return ERR_PTR(-EPERM); - if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET)) return ERR_PTR(-EPERM); } @@ -58,7 +55,7 @@ static struct file_system_type sysfs_fs_type = { .name = "sysfs", .mount = sysfs_mount, .kill_sb = sysfs_kill_sb, - .fs_flags = FS_USERNS_MOUNT, + .fs_flags = FS_USERNS_VISIBLE | FS_USERNS_MOUNT, }; int __init sysfs_init(void) diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c index 2c1036080d52..a7106eda5024 100644 --- a/fs/ufs/balloc.c +++ b/fs/ufs/balloc.c @@ -51,8 +51,8 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count) if (ufs_fragnum(fragment) + count > uspi->s_fpg) ufs_error (sb, "ufs_free_fragments", "internal error"); - - lock_ufs(sb); + + mutex_lock(&UFS_SB(sb)->s_lock); cgno = ufs_dtog(uspi, fragment); bit = ufs_dtogd(uspi, fragment); @@ -115,13 +115,13 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count) if (sb->s_flags & MS_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); ufs_mark_sb_dirty(sb); - - unlock_ufs(sb); + + mutex_unlock(&UFS_SB(sb)->s_lock); UFSD("EXIT\n"); return; failed: - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); UFSD("EXIT (FAILED)\n"); return; } @@ -151,7 +151,7 @@ void ufs_free_blocks(struct inode *inode, u64 fragment, unsigned count) goto failed; } - lock_ufs(sb); + mutex_lock(&UFS_SB(sb)->s_lock); do_more: overflow = 0; @@ -211,12 +211,12 @@ do_more: } ufs_mark_sb_dirty(sb); - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); UFSD("EXIT\n"); return; failed_unlock: - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); failed: UFSD("EXIT (FAILED)\n"); return; @@ -357,7 +357,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, usb1 = ubh_get_usb_first(uspi); *err = -ENOSPC; - lock_ufs(sb); + mutex_lock(&UFS_SB(sb)->s_lock); tmp = ufs_data_ptr_to_cpu(sb, p); if (count + ufs_fragnum(fragment) > uspi->s_fpb) { @@ -378,19 +378,19 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, "fragment %llu, tmp %llu\n", (unsigned long long)fragment, (unsigned long long)tmp); - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); return INVBLOCK; } if (fragment < UFS_I(inode)->i_lastfrag) { UFSD("EXIT (ALREADY ALLOCATED)\n"); - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); return 0; } } else { if (tmp) { UFSD("EXIT (ALREADY ALLOCATED)\n"); - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); return 0; } } @@ -399,7 +399,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, * There is not enough space for user on the device */ if (!capable(CAP_SYS_RESOURCE) && ufs_freespace(uspi, UFS_MINFREE) <= 0) { - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); UFSD("EXIT (FAILED)\n"); return 0; } @@ -424,7 +424,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, ufs_clear_frags(inode, result + oldcount, newcount - oldcount, locked_page != NULL); } - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); UFSD("EXIT, result %llu\n", (unsigned long long)result); return result; } @@ -439,7 +439,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, fragment + count); ufs_clear_frags(inode, result + oldcount, newcount - oldcount, locked_page != NULL); - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); UFSD("EXIT, result %llu\n", (unsigned long long)result); return result; } @@ -477,7 +477,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, *err = 0; UFS_I(inode)->i_lastfrag = max(UFS_I(inode)->i_lastfrag, fragment + count); - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); if (newcount < request) ufs_free_fragments (inode, result + newcount, request - newcount); ufs_free_fragments (inode, tmp, oldcount); @@ -485,7 +485,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, return result; } - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); UFSD("EXIT (FAILED)\n"); return 0; } diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c index 7caa01652888..fd0203ce1f7f 100644 --- a/fs/ufs/ialloc.c +++ b/fs/ufs/ialloc.c @@ -69,11 +69,11 @@ void ufs_free_inode (struct inode * inode) ino = inode->i_ino; - lock_ufs(sb); + mutex_lock(&UFS_SB(sb)->s_lock); if (!((ino > 1) && (ino < (uspi->s_ncg * uspi->s_ipg )))) { ufs_warning(sb, "ufs_free_inode", "reserved inode or nonexistent inode %u\n", ino); - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); return; } @@ -81,7 +81,7 @@ void ufs_free_inode (struct inode * inode) bit = ufs_inotocgoff (ino); ucpi = ufs_load_cylinder (sb, cg); if (!ucpi) { - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); return; } ucg = ubh_get_ucg(UCPI_UBH(ucpi)); @@ -115,7 +115,7 @@ void ufs_free_inode (struct inode * inode) ubh_sync_block(UCPI_UBH(ucpi)); ufs_mark_sb_dirty(sb); - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); UFSD("EXIT\n"); } @@ -193,7 +193,7 @@ struct inode *ufs_new_inode(struct inode *dir, umode_t mode) sbi = UFS_SB(sb); uspi = sbi->s_uspi; - lock_ufs(sb); + mutex_lock(&sbi->s_lock); /* * Try to place the inode in its parent directory @@ -331,21 +331,21 @@ cg_found: sync_dirty_buffer(bh); brelse(bh); } - unlock_ufs(sb); + mutex_unlock(&sbi->s_lock); UFSD("allocating inode %lu\n", inode->i_ino); UFSD("EXIT\n"); return inode; fail_remove_inode: - unlock_ufs(sb); + mutex_unlock(&sbi->s_lock); clear_nlink(inode); unlock_new_inode(inode); iput(inode); UFSD("EXIT (FAILED): err %d\n", err); return ERR_PTR(err); failed: - unlock_ufs(sb); + mutex_unlock(&sbi->s_lock); make_bad_inode(inode); iput (inode); UFSD("EXIT (FAILED): err %d\n", err); diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index be7d42c7d938..2d93ab07da8a 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -902,6 +902,9 @@ void ufs_evict_inode(struct inode * inode) invalidate_inode_buffers(inode); clear_inode(inode); - if (want_delete) + if (want_delete) { + lock_ufs(inode->i_sb); ufs_free_inode(inode); + unlock_ufs(inode->i_sb); + } } diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index fd65deb4b5f0..e8ee2985b068 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -128,12 +128,12 @@ static int ufs_symlink (struct inode * dir, struct dentry * dentry, if (l > sb->s_blocksize) goto out_notlocked; + lock_ufs(dir->i_sb); inode = ufs_new_inode(dir, S_IFLNK | S_IRWXUGO); err = PTR_ERR(inode); if (IS_ERR(inode)) - goto out_notlocked; + goto out; - lock_ufs(dir->i_sb); if (l > UFS_SB(sb)->s_uspi->s_maxsymlinklen) { /* slow symlink */ inode->i_op = &ufs_symlink_inode_operations; @@ -174,7 +174,12 @@ static int ufs_link (struct dentry * old_dentry, struct inode * dir, inode_inc_link_count(inode); ihold(inode); - error = ufs_add_nondir(dentry, inode); + error = ufs_add_link(dentry, inode); + if (error) { + inode_dec_link_count(inode); + iput(inode); + } else + d_instantiate(dentry, inode); unlock_ufs(dir->i_sb); return error; } @@ -184,9 +189,13 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode) struct inode * inode; int err; + lock_ufs(dir->i_sb); + inode_inc_link_count(dir); + inode = ufs_new_inode(dir, S_IFDIR|mode); + err = PTR_ERR(inode); if (IS_ERR(inode)) - return PTR_ERR(inode); + goto out_dir; inode->i_op = &ufs_dir_inode_operations; inode->i_fop = &ufs_dir_operations; @@ -194,9 +203,6 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode) inode_inc_link_count(inode); - lock_ufs(dir->i_sb); - inode_inc_link_count(dir); - err = ufs_make_empty(inode, dir); if (err) goto out_fail; @@ -206,6 +212,7 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode) goto out_fail; unlock_ufs(dir->i_sb); + unlock_new_inode(inode); d_instantiate(dentry, inode); out: return err; @@ -215,6 +222,7 @@ out_fail: inode_dec_link_count(inode); unlock_new_inode(inode); iput (inode); +out_dir: inode_dec_link_count(dir); unlock_ufs(dir->i_sb); goto out; diff --git a/fs/ufs/super.c b/fs/ufs/super.c index da73801301d5..ce02dff5572f 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -698,6 +698,7 @@ static int ufs_sync_fs(struct super_block *sb, int wait) unsigned flags; lock_ufs(sb); + mutex_lock(&UFS_SB(sb)->s_lock); UFSD("ENTER\n"); @@ -715,6 +716,7 @@ static int ufs_sync_fs(struct super_block *sb, int wait) ufs_put_cstotal(sb); UFSD("EXIT\n"); + mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return 0; @@ -803,6 +805,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) UFSD("flag %u\n", (int)(sb->s_flags & MS_RDONLY)); mutex_init(&sbi->mutex); + mutex_init(&sbi->s_lock); spin_lock_init(&sbi->work_lock); INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs); /* @@ -1281,6 +1284,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) sync_filesystem(sb); lock_ufs(sb); + mutex_lock(&UFS_SB(sb)->s_lock); uspi = UFS_SB(sb)->s_uspi; flags = UFS_SB(sb)->s_flags; usb1 = ubh_get_usb_first(uspi); @@ -1294,6 +1298,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) new_mount_opt = 0; ufs_set_opt (new_mount_opt, ONERROR_LOCK); if (!ufs_parse_options (data, &new_mount_opt)) { + mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return -EINVAL; } @@ -1301,12 +1306,14 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) new_mount_opt |= ufstype; } else if ((new_mount_opt & UFS_MOUNT_UFSTYPE) != ufstype) { pr_err("ufstype can't be changed during remount\n"); + mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return -EINVAL; } if ((*mount_flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) { UFS_SB(sb)->s_mount_opt = new_mount_opt; + mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return 0; } @@ -1330,6 +1337,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) */ #ifndef CONFIG_UFS_FS_WRITE pr_err("ufs was compiled with read-only support, can't be mounted as read-write\n"); + mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return -EINVAL; #else @@ -1339,11 +1347,13 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) ufstype != UFS_MOUNT_UFSTYPE_SUNx86 && ufstype != UFS_MOUNT_UFSTYPE_UFS2) { pr_err("this ufstype is read-only supported\n"); + mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return -EINVAL; } if (!ufs_read_cylinder_structures(sb)) { pr_err("failed during remounting\n"); + mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return -EPERM; } @@ -1351,6 +1361,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) #endif } UFS_SB(sb)->s_mount_opt = new_mount_opt; + mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return 0; } diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h index 2a07396d5f9e..cf6368d42d4a 100644 --- a/fs/ufs/ufs.h +++ b/fs/ufs/ufs.h @@ -30,6 +30,7 @@ struct ufs_sb_info { int work_queued; /* non-zero if the delayed work is queued */ struct delayed_work sync_work; /* FS sync delayed work */ spinlock_t work_lock; /* protects sync_work and work_queued */ + struct mutex s_lock; }; struct ufs_inode_info { diff --git a/include/linux/fs.h b/include/linux/fs.h index 9ab779e8a63c..84d672914bd8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1791,6 +1791,7 @@ struct file_system_type { #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_USERNS_DEV_MOUNT 16 /* A userns mount does not imply MNT_NODEV */ +#define FS_USERNS_VISIBLE 32 /* FS must already be visible */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); @@ -1878,7 +1879,6 @@ extern int vfs_ustat(dev_t, struct kstatfs *); extern int freeze_super(struct super_block *super); extern int thaw_super(struct super_block *super); extern bool our_mnt(struct vfsmount *mnt); -extern bool fs_fully_visible(struct file_system_type *); extern int current_umask(void); diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 7491ee5d8164..83338210ee04 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -46,4 +46,30 @@ static inline efi_system_table_t __init *xen_efi_probe(void) } #endif +#ifdef CONFIG_PREEMPT + +static inline void xen_preemptible_hcall_begin(void) +{ +} + +static inline void xen_preemptible_hcall_end(void) +{ +} + +#else + +DECLARE_PER_CPU(bool, xen_in_preemptible_hcall); + +static inline void xen_preemptible_hcall_begin(void) +{ + __this_cpu_write(xen_in_preemptible_hcall, true); +} + +static inline void xen_preemptible_hcall_end(void) +{ + __this_cpu_write(xen_in_preemptible_hcall, false); +} + +#endif /* CONFIG_PREEMPT */ + #endif /* INCLUDE_XEN_OPS_H */ diff --git a/kernel/events/core.c b/kernel/events/core.c index e631dacdb165..cb86038cad47 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4057,20 +4057,20 @@ static void ring_buffer_attach(struct perf_event *event, WARN_ON_ONCE(event->rcu_pending); old_rb = event->rb; - event->rcu_batches = get_state_synchronize_rcu(); - event->rcu_pending = 1; - spin_lock_irqsave(&old_rb->event_lock, flags); list_del_rcu(&event->rb_entry); spin_unlock_irqrestore(&old_rb->event_lock, flags); - } - if (event->rcu_pending && rb) { - cond_synchronize_rcu(event->rcu_batches); - event->rcu_pending = 0; + event->rcu_batches = get_state_synchronize_rcu(); + event->rcu_pending = 1; } if (rb) { + if (event->rcu_pending) { + cond_synchronize_rcu(event->rcu_batches); + event->rcu_pending = 0; + } + spin_lock_irqsave(&rb->event_lock, flags); list_add_rcu(&event->rb_entry, &rb->event_list); spin_unlock_irqrestore(&rb->event_lock, flags); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index bcb9145a7913..51afcb76d32b 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1369,19 +1369,24 @@ static int check_preds(struct filter_parse_state *ps) { int n_normal_preds = 0, n_logical_preds = 0; struct postfix_elt *elt; + int cnt = 0; list_for_each_entry(elt, &ps->postfix, list) { - if (elt->op == OP_NONE) + if (elt->op == OP_NONE) { + cnt++; continue; + } + cnt--; if (elt->op == OP_AND || elt->op == OP_OR) { n_logical_preds++; continue; } n_normal_preds++; + WARN_ON_ONCE(cnt < 0); } - if (!n_normal_preds || n_logical_preds >= n_normal_preds) { + if (cnt != 1 || !n_normal_preds || n_logical_preds >= n_normal_preds) { parse_error(ps, FILT_ERR_INVALID_FILTER, 0); return -EINVAL; } diff --git a/net/can/af_can.c b/net/can/af_can.c index d6030d6949df..9a3244941a5c 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -313,8 +313,12 @@ int can_send(struct sk_buff *skb, int loop) return err; } - if (newskb) + if (newskb) { + if (!(newskb->tstamp.tv64)) + __net_timestamp(newskb); + netif_rx_ni(newskb); + } /* update statistics */ can_stats.tx_frames++; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 24d3242f0e01..c522f7a00eab 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2229,9 +2229,6 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, int err = -ENOBUFS; size_t if_info_size; - if (dev->reg_state != NETREG_REGISTERED) - return; - skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), flags); if (skb == NULL) goto errout; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 71b574c7bde9..9fe2baa01fbe 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1221,7 +1221,10 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, if (nla[NFTA_CHAIN_POLICY]) { if ((chain != NULL && - !(chain->flags & NFT_BASE_CHAIN)) || + !(chain->flags & NFT_BASE_CHAIN))) + return -EOPNOTSUPP; + + if (chain == NULL && nla[NFTA_CHAIN_HOOK] == NULL) return -EOPNOTSUPP; diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 9e287cb56a04..54330fb5efaf 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -77,6 +77,9 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple, if (!tb[NFCTH_TUPLE_L3PROTONUM] || !tb[NFCTH_TUPLE_L4PROTONUM]) return -EINVAL; + /* Not all fields are initialized so first zero the tuple */ + memset(tuple, 0, sizeof(struct nf_conntrack_tuple)); + tuple->src.l3num = ntohs(nla_get_be16(tb[NFCTH_TUPLE_L3PROTONUM])); tuple->dst.protonum = nla_get_u8(tb[NFCTH_TUPLE_L4PROTONUM]); @@ -86,7 +89,7 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple, static int nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct) { - const struct nf_conn_help *help = nfct_help(ct); + struct nf_conn_help *help = nfct_help(ct); if (attr == NULL) return -EINVAL; @@ -94,7 +97,7 @@ nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct) if (help->helper->data_len == 0) return -EINVAL; - memcpy(&help->data, nla_data(attr), help->helper->data_len); + memcpy(help->data, nla_data(attr), help->helper->data_len); return 0; } diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 265e190f2218..e22a2961cc39 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -97,6 +97,9 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par, entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0; break; case AF_INET6: + if (proto) + entry->e6.ipv6.flags |= IP6T_F_PROTO; + entry->e6.ipv6.proto = proto; entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0; break; @@ -304,6 +307,9 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx, entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0; break; case AF_INET6: + if (proto) + entry->e6.ipv6.flags |= IP6T_F_PROTO; + entry->e6.ipv6.proto = proto; entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0; break; diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index c603b20356ad..b1e455b47b82 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -405,7 +405,8 @@ static int selinux_is_sblabel_mnt(struct super_block *sb) if (sbsec->behavior == SECURITY_FS_USE_XATTR || sbsec->behavior == SECURITY_FS_USE_TRANS || - sbsec->behavior == SECURITY_FS_USE_TASK) + sbsec->behavior == SECURITY_FS_USE_TASK || + sbsec->behavior == SECURITY_FS_USE_NATIVE) return 1; /* Special handling for sysfs. Is genfs but also has setxattr handler*/