diff options
Diffstat (limited to 'arch')
124 files changed, 926 insertions, 571 deletions
diff --git a/arch/alpha/kernel/pci.c b/arch/alpha/kernel/pci.c index 076c35cd6cde..98a1525fa164 100644 --- a/arch/alpha/kernel/pci.c +++ b/arch/alpha/kernel/pci.c @@ -285,8 +285,12 @@ pcibios_claim_one_bus(struct pci_bus *b) if (r->parent || !r->start || !r->flags) continue; if (pci_has_flag(PCI_PROBE_ONLY) || - (r->flags & IORESOURCE_PCI_FIXED)) - pci_claim_resource(dev, i); + (r->flags & IORESOURCE_PCI_FIXED)) { + if (pci_claim_resource(dev, i) == 0) + continue; + + pci_claim_bridge_resource(dev, i); + } } } diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 98838a05ba6d..9d0ac091a52a 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -156,6 +156,8 @@ retry: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index 6f7e3a68803a..563cb27e37f5 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -161,6 +161,8 @@ good_area: if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; diff --git a/arch/arm/boot/dts/imx6sx-sdb.dts b/arch/arm/boot/dts/imx6sx-sdb.dts index 1e6e5cc1c14c..c108bb451337 100644 --- a/arch/arm/boot/dts/imx6sx-sdb.dts +++ b/arch/arm/boot/dts/imx6sx-sdb.dts @@ -159,13 +159,28 @@ pinctrl-0 = <&pinctrl_enet1>; phy-supply = <®_enet_3v3>; phy-mode = "rgmii"; + phy-handle = <ðphy1>; status = "okay"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + ethphy1: ethernet-phy@1 { + reg = <1>; + }; + + ethphy2: ethernet-phy@2 { + reg = <2>; + }; + }; }; &fec2 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet2>; phy-mode = "rgmii"; + phy-handle = <ðphy2>; status = "okay"; }; diff --git a/arch/arm/boot/dts/tegra20-seaboard.dts b/arch/arm/boot/dts/tegra20-seaboard.dts index ea282c7c0ca5..e2fed2712249 100644 --- a/arch/arm/boot/dts/tegra20-seaboard.dts +++ b/arch/arm/boot/dts/tegra20-seaboard.dts @@ -406,7 +406,7 @@ clock-frequency = <400000>; magnetometer@c { - compatible = "ak,ak8975"; + compatible = "asahi-kasei,ak8975"; reg = <0xc>; interrupt-parent = <&gpio>; interrupts = <TEGRA_GPIO(N, 5) IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm/boot/dts/vf610-twr.dts b/arch/arm/boot/dts/vf610-twr.dts index a0f762159cb2..f2b64b1b00fa 100644 --- a/arch/arm/boot/dts/vf610-twr.dts +++ b/arch/arm/boot/dts/vf610-twr.dts @@ -129,13 +129,28 @@ &fec0 { phy-mode = "rmii"; + phy-handle = <ðphy0>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_fec0>; status = "okay"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + ethphy0: ethernet-phy@0 { + reg = <0>; + }; + + ethphy1: ethernet-phy@1 { + reg = <1>; + }; + }; }; &fec1 { phy-mode = "rmii"; + phy-handle = <ðphy1>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_fec1>; status = "okay"; diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index 66ce17655bb9..7b0152321b20 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -38,6 +38,16 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) vcpu->arch.hcr = HCR_GUEST_MASK; } +static inline unsigned long vcpu_get_hcr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.hcr; +} + +static inline void vcpu_set_hcr(struct kvm_vcpu *vcpu, unsigned long hcr) +{ + vcpu->arch.hcr = hcr; +} + static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu) { return 1; diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 254e0650e48b..04b4ea0b550a 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -125,9 +125,6 @@ struct kvm_vcpu_arch { * Anything that is not used directly from assembly code goes * here. */ - /* dcache set/way operation pending */ - int last_pcpu; - cpumask_t require_dcache_flush; /* Don't run the guest on this vcpu */ bool pause; diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 63e0ecc04901..1bca8f8af442 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -44,6 +44,7 @@ #ifndef __ASSEMBLY__ +#include <linux/highmem.h> #include <asm/cacheflush.h> #include <asm/pgalloc.h> @@ -161,13 +162,10 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101; } -static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, - unsigned long size, - bool ipa_uncached) +static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, + unsigned long size, + bool ipa_uncached) { - if (!vcpu_has_cache_enabled(vcpu) || ipa_uncached) - kvm_flush_dcache_to_poc((void *)hva, size); - /* * If we are going to insert an instruction page and the icache is * either VIPT or PIPT, there is a potential problem where the host @@ -179,18 +177,77 @@ static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, * * VIVT caches are tagged using both the ASID and the VMID and doesn't * need any kind of flushing (DDI 0406C.b - Page B3-1392). + * + * We need to do this through a kernel mapping (using the + * user-space mapping has proved to be the wrong + * solution). For that, we need to kmap one page at a time, + * and iterate over the range. */ - if (icache_is_pipt()) { - __cpuc_coherent_user_range(hva, hva + size); - } else if (!icache_is_vivt_asid_tagged()) { + + bool need_flush = !vcpu_has_cache_enabled(vcpu) || ipa_uncached; + + VM_BUG_ON(size & PAGE_MASK); + + if (!need_flush && !icache_is_pipt()) + goto vipt_cache; + + while (size) { + void *va = kmap_atomic_pfn(pfn); + + if (need_flush) + kvm_flush_dcache_to_poc(va, PAGE_SIZE); + + if (icache_is_pipt()) + __cpuc_coherent_user_range((unsigned long)va, + (unsigned long)va + PAGE_SIZE); + + size -= PAGE_SIZE; + pfn++; + + kunmap_atomic(va); + } + +vipt_cache: + if (!icache_is_pipt() && !icache_is_vivt_asid_tagged()) { /* any kind of VIPT cache */ __flush_icache_all(); } } +static inline void __kvm_flush_dcache_pte(pte_t pte) +{ + void *va = kmap_atomic(pte_page(pte)); + + kvm_flush_dcache_to_poc(va, PAGE_SIZE); + + kunmap_atomic(va); +} + +static inline void __kvm_flush_dcache_pmd(pmd_t pmd) +{ + unsigned long size = PMD_SIZE; + pfn_t pfn = pmd_pfn(pmd); + + while (size) { + void *va = kmap_atomic_pfn(pfn); + + kvm_flush_dcache_to_poc(va, PAGE_SIZE); + + pfn++; + size -= PAGE_SIZE; + + kunmap_atomic(va); + } +} + +static inline void __kvm_flush_dcache_pud(pud_t pud) +{ +} + #define kvm_virt_to_phys(x) virt_to_idmap((unsigned long)(x)) -void stage2_flush_vm(struct kvm *kvm); +void kvm_set_way_flush(struct kvm_vcpu *vcpu); +void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled); #endif /* !__ASSEMBLY__ */ diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S index 4176df721bf0..1a0045abead7 100644 --- a/arch/arm/kernel/entry-header.S +++ b/arch/arm/kernel/entry-header.S @@ -253,21 +253,22 @@ .endm .macro restore_user_regs, fast = 0, offset = 0 - ldr r1, [sp, #\offset + S_PSR] @ get calling cpsr - ldr lr, [sp, #\offset + S_PC]! @ get pc + mov r2, sp + ldr r1, [r2, #\offset + S_PSR] @ get calling cpsr + ldr lr, [r2, #\offset + S_PC]! @ get pc msr spsr_cxsf, r1 @ save in spsr_svc #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K) @ We must avoid clrex due to Cortex-A15 erratum #830321 - strex r1, r2, [sp] @ clear the exclusive monitor + strex r1, r2, [r2] @ clear the exclusive monitor #endif .if \fast - ldmdb sp, {r1 - lr}^ @ get calling r1 - lr + ldmdb r2, {r1 - lr}^ @ get calling r1 - lr .else - ldmdb sp, {r0 - lr}^ @ get calling r0 - lr + ldmdb r2, {r0 - lr}^ @ get calling r0 - lr .endif mov r0, r0 @ ARMv5T and earlier require a nop @ after ldm {}^ - add sp, sp, #S_FRAME_SIZE - S_PC + add sp, sp, #\offset + S_FRAME_SIZE movs pc, lr @ return & move spsr_svc into cpsr .endm diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index f7c65adaa428..557e128e4df0 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -116,8 +116,14 @@ int armpmu_event_set_period(struct perf_event *event) ret = 1; } - if (left > (s64)armpmu->max_period) - left = armpmu->max_period; + /* + * Limit the maximum period to prevent the counter value + * from overtaking the one we are about to program. In + * effect we are reducing max_period to account for + * interrupt latency (and we are being very conservative). + */ + if (left > (armpmu->max_period >> 1)) + left = armpmu->max_period >> 1; local64_set(&hwc->prev_count, (u64)-left); diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 715ae19bc7c8..e55408e96559 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -657,10 +657,13 @@ int __init arm_add_memory(u64 start, u64 size) /* * Ensure that start/size are aligned to a page boundary. - * Size is appropriately rounded down, start is rounded up. + * Size is rounded down, start is rounded up. */ - size -= start & ~PAGE_MASK; aligned_start = PAGE_ALIGN(start); + if (aligned_start > start + size) + size = 0; + else + size -= aligned_start - start; #ifndef CONFIG_ARCH_PHYS_ADDR_T_64BIT if (aligned_start > ULONG_MAX) { diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 2d6d91001062..0b0d58a905c4 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -281,15 +281,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vcpu->cpu = cpu; vcpu->arch.host_cpu_context = this_cpu_ptr(kvm_host_cpu_state); - /* - * Check whether this vcpu requires the cache to be flushed on - * this physical CPU. This is a consequence of doing dcache - * operations by set/way on this vcpu. We do it here to be in - * a non-preemptible section. - */ - if (cpumask_test_and_clear_cpu(cpu, &vcpu->arch.require_dcache_flush)) - flush_cache_all(); /* We'd really want v7_flush_dcache_all() */ - kvm_arm_set_running_vcpu(vcpu); } @@ -541,7 +532,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) ret = kvm_call_hyp(__kvm_vcpu_run, vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; - vcpu->arch.last_pcpu = smp_processor_id(); kvm_guest_exit(); trace_kvm_exit(*vcpu_pc(vcpu)); /* diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index 7928dbdf2102..f3d88dc388bc 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -189,82 +189,40 @@ static bool access_l2ectlr(struct kvm_vcpu *vcpu, return true; } -/* See note at ARM ARM B1.14.4 */ +/* + * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized). + */ static bool access_dcsw(struct kvm_vcpu *vcpu, const struct coproc_params *p, const struct coproc_reg *r) { - unsigned long val; - int cpu; - if (!p->is_write) return read_from_write_only(vcpu, p); - cpu = get_cpu(); - - cpumask_setall(&vcpu->arch.require_dcache_flush); - cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush); - - /* If we were already preempted, take the long way around */ - if (cpu != vcpu->arch.last_pcpu) { - flush_cache_all(); - goto done; - } - - val = *vcpu_reg(vcpu, p->Rt1); - - switch (p->CRm) { - case 6: /* Upgrade DCISW to DCCISW, as per HCR.SWIO */ - case 14: /* DCCISW */ - asm volatile("mcr p15, 0, %0, c7, c14, 2" : : "r" (val)); - break; - - case 10: /* DCCSW */ - asm volatile("mcr p15, 0, %0, c7, c10, 2" : : "r" (val)); - break; - } - -done: - put_cpu(); - + kvm_set_way_flush(vcpu); return true; } /* * Generic accessor for VM registers. Only called as long as HCR_TVM - * is set. + * is set. If the guest enables the MMU, we stop trapping the VM + * sys_regs and leave it in complete control of the caches. + * + * Used by the cpu-specific code. */ -static bool access_vm_reg(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) +bool access_vm_reg(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r) { + bool was_enabled = vcpu_has_cache_enabled(vcpu); + BUG_ON(!p->is_write); vcpu->arch.cp15[r->reg] = *vcpu_reg(vcpu, p->Rt1); if (p->is_64bit) vcpu->arch.cp15[r->reg + 1] = *vcpu_reg(vcpu, p->Rt2); - return true; -} - -/* - * SCTLR accessor. Only called as long as HCR_TVM is set. If the - * guest enables the MMU, we stop trapping the VM sys_regs and leave - * it in complete control of the caches. - * - * Used by the cpu-specific code. - */ -bool access_sctlr(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - access_vm_reg(vcpu, p, r); - - if (vcpu_has_cache_enabled(vcpu)) { /* MMU+Caches enabled? */ - vcpu->arch.hcr &= ~HCR_TVM; - stage2_flush_vm(vcpu->kvm); - } - + kvm_toggle_cache(vcpu, was_enabled); return true; } diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h index 1a44bbe39643..88d24a3a9778 100644 --- a/arch/arm/kvm/coproc.h +++ b/arch/arm/kvm/coproc.h @@ -153,8 +153,8 @@ static inline int cmp_reg(const struct coproc_reg *i1, #define is64 .is_64 = true #define is32 .is_64 = false -bool access_sctlr(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r); +bool access_vm_reg(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r); #endif /* __ARM_KVM_COPROC_LOCAL_H__ */ diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c index e6f4ae48bda9..a7136757d373 100644 --- a/arch/arm/kvm/coproc_a15.c +++ b/arch/arm/kvm/coproc_a15.c @@ -34,7 +34,7 @@ static const struct coproc_reg a15_regs[] = { /* SCTLR: swapped by interrupt.S. */ { CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32, - access_sctlr, reset_val, c1_SCTLR, 0x00C50078 }, + access_vm_reg, reset_val, c1_SCTLR, 0x00C50078 }, }; static struct kvm_coproc_target_table a15_target_table = { diff --git a/arch/arm/kvm/coproc_a7.c b/arch/arm/kvm/coproc_a7.c index 17fc7cd479d3..b19e46d1b2c0 100644 --- a/arch/arm/kvm/coproc_a7.c +++ b/arch/arm/kvm/coproc_a7.c @@ -37,7 +37,7 @@ static const struct coproc_reg a7_regs[] = { /* SCTLR: swapped by interrupt.S. */ { CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32, - access_sctlr, reset_val, c1_SCTLR, 0x00C50878 }, + access_vm_reg, reset_val, c1_SCTLR, 0x00C50878 }, }; static struct kvm_coproc_target_table a7_target_table = { diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 1dc9778a00af..136662547ca6 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -58,6 +58,26 @@ static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa); } +/* + * D-Cache management functions. They take the page table entries by + * value, as they are flushing the cache using the kernel mapping (or + * kmap on 32bit). + */ +static void kvm_flush_dcache_pte(pte_t pte) +{ + __kvm_flush_dcache_pte(pte); +} + +static void kvm_flush_dcache_pmd(pmd_t pmd) +{ + __kvm_flush_dcache_pmd(pmd); +} + +static void kvm_flush_dcache_pud(pud_t pud) +{ + __kvm_flush_dcache_pud(pud); +} + static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, int min, int max) { @@ -119,6 +139,26 @@ static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr) put_page(virt_to_page(pmd)); } +/* + * Unmapping vs dcache management: + * + * If a guest maps certain memory pages as uncached, all writes will + * bypass the data cache and go directly to RAM. However, the CPUs + * can still speculate reads (not writes) and fill cache lines with + * data. + * + * Those cache lines will be *clean* cache lines though, so a + * clean+invalidate operation is equivalent to an invalidate + * operation, because no cache lines are marked dirty. + * + * Those clean cache lines could be filled prior to an uncached write + * by the guest, and the cache coherent IO subsystem would therefore + * end up writing old data to disk. + * + * This is why right after unmapping a page/section and invalidating + * the corresponding TLBs, we call kvm_flush_dcache_p*() to make sure + * the IO subsystem will never hit in the cache. + */ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr, phys_addr_t end) { @@ -128,9 +168,16 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd, start_pte = pte = pte_offset_kernel(pmd, addr); do { if (!pte_none(*pte)) { + pte_t old_pte = *pte; + kvm_set_pte(pte, __pte(0)); - put_page(virt_to_page(pte)); kvm_tlb_flush_vmid_ipa(kvm, addr); + + /* No need to invalidate the cache for device mappings */ + if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE) + kvm_flush_dcache_pte(old_pte); + + put_page(virt_to_page(pte)); } } while (pte++, addr += PAGE_SIZE, addr != end); @@ -149,8 +196,13 @@ static void unmap_pmds(struct kvm *kvm, pud_t *pud, next = kvm_pmd_addr_end(addr, end); if (!pmd_none(*pmd)) { if (kvm_pmd_huge(*pmd)) { + pmd_t old_pmd = *pmd; + pmd_clear(pmd); kvm_tlb_flush_vmid_ipa(kvm, addr); + + kvm_flush_dcache_pmd(old_pmd); + put_page(virt_to_page(pmd)); } else { unmap_ptes(kvm, pmd, addr, next); @@ -173,8 +225,13 @@ static void unmap_puds(struct kvm *kvm, pgd_t *pgd, next = kvm_pud_addr_end(addr, end); if (!pud_none(*pud)) { if (pud_huge(*pud)) { + pud_t old_pud = *pud; + pud_clear(pud); kvm_tlb_flush_vmid_ipa(kvm, addr); + + kvm_flush_dcache_pud(old_pud); + put_page(virt_to_page(pud)); } else { unmap_pmds(kvm, pud, addr, next); @@ -209,10 +266,9 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd, pte = pte_offset_kernel(pmd, addr); do { - if (!pte_none(*pte)) { - hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT); - kvm_flush_dcache_to_poc((void*)hva, PAGE_SIZE); - } + if (!pte_none(*pte) && + (pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE) + kvm_flush_dcache_pte(*pte); } while (pte++, addr += PAGE_SIZE, addr != end); } @@ -226,12 +282,10 @@ static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud, do { next = kvm_pmd_addr_end(addr, end); if (!pmd_none(*pmd)) { - if (kvm_pmd_huge(*pmd)) { - hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT); - kvm_flush_dcache_to_poc((void*)hva, PMD_SIZE); - } else { + if (kvm_pmd_huge(*pmd)) + kvm_flush_dcache_pmd(*pmd); + else stage2_flush_ptes(kvm, pmd, addr, next); - } } } while (pmd++, addr = next, addr != end); } @@ -246,12 +300,10 @@ static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd, do { next = kvm_pud_addr_end(addr, end); if (!pud_none(*pud)) { - if (pud_huge(*pud)) { - hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT); - kvm_flush_dcache_to_poc((void*)hva, PUD_SIZE); - } else { + if (pud_huge(*pud)) + kvm_flush_dcache_pud(*pud); + else stage2_flush_pmds(kvm, pud, addr, next); - } } } while (pud++, addr = next, addr != end); } @@ -278,7 +330,7 @@ static void stage2_flush_memslot(struct kvm *kvm, * Go through the stage 2 page tables and invalidate any cache lines * backing memory already mapped to the VM. */ -void stage2_flush_vm(struct kvm *kvm) +static void stage2_flush_vm(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; @@ -905,6 +957,12 @@ static bool kvm_is_device_pfn(unsigned long pfn) return !pfn_valid(pfn); } +static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, + unsigned long size, bool uncached) +{ + __coherent_cache_guest_page(vcpu, pfn, size, uncached); +} + static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_memory_slot *memslot, unsigned long hva, unsigned long fault_status) @@ -994,8 +1052,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, kvm_set_s2pmd_writable(&new_pmd); kvm_set_pfn_dirty(pfn); } - coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE, - fault_ipa_uncached); + coherent_cache_guest_page(vcpu, pfn, PMD_SIZE, fault_ipa_uncached); ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd); } else { pte_t new_pte = pfn_pte(pfn, mem_type); @@ -1003,8 +1060,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, kvm_set_s2pte_writable(&new_pte); kvm_set_pfn_dirty(pfn); } - coherent_cache_guest_page(vcpu, hva, PAGE_SIZE, - fault_ipa_uncached); + coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE, fault_ipa_uncached); ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE)); } @@ -1411,3 +1467,71 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, unmap_stage2_range(kvm, gpa, size); spin_unlock(&kvm->mmu_lock); } + +/* + * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized). + * + * Main problems: + * - S/W ops are local to a CPU (not broadcast) + * - We have line migration behind our back (speculation) + * - System caches don't support S/W at all (damn!) + * + * In the face of the above, the best we can do is to try and convert + * S/W ops to VA ops. Because the guest is not allowed to infer the + * S/W to PA mapping, it can only use S/W to nuke the whole cache, + * which is a rather good thing for us. + * + * Also, it is only used when turning caches on/off ("The expected + * usage of the cache maintenance instructions that operate by set/way + * is associated with the cache maintenance instructions associated + * with the powerdown and powerup of caches, if this is required by + * the implementation."). + * + * We use the following policy: + * + * - If we trap a S/W operation, we enable VM trapping to detect + * caches being turned on/off, and do a full clean. + * + * - We flush the caches on both caches being turned on and off. + * + * - Once the caches are enabled, we stop trapping VM ops. + */ +void kvm_set_way_flush(struct kvm_vcpu *vcpu) +{ + unsigned long hcr = vcpu_get_hcr(vcpu); + + /* + * If this is the first time we do a S/W operation + * (i.e. HCR_TVM not set) flush the whole memory, and set the + * VM trapping. + * + * Otherwise, rely on the VM trapping to wait for the MMU + + * Caches to be turned off. At that point, we'll be able to + * clean the caches again. + */ + if (!(hcr & HCR_TVM)) { + trace_kvm_set_way_flush(*vcpu_pc(vcpu), + vcpu_has_cache_enabled(vcpu)); + stage2_flush_vm(vcpu->kvm); + vcpu_set_hcr(vcpu, hcr | HCR_TVM); + } +} + +void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled) +{ + bool now_enabled = vcpu_has_cache_enabled(vcpu); + + /* + * If switching the MMU+caches on, need to invalidate the caches. + * If switching it off, need to clean the caches. + * Clean + invalidate does the trick always. + */ + if (now_enabled != was_enabled) + stage2_flush_vm(vcpu->kvm); + + /* Caches are now on, stop trapping VM ops (until a S/W op) */ + if (now_enabled) + vcpu_set_hcr(vcpu, vcpu_get_hcr(vcpu) & ~HCR_TVM); + + trace_kvm_toggle_cache(*vcpu_pc(vcpu), was_enabled, now_enabled); +} diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h index b1d640f78623..b6a6e7102201 100644 --- a/arch/arm/kvm/trace.h +++ b/arch/arm/kvm/trace.h @@ -223,6 +223,45 @@ TRACE_EVENT(kvm_hvc, __entry->vcpu_pc, __entry->r0, __entry->imm) ); +TRACE_EVENT(kvm_set_way_flush, + TP_PROTO(unsigned long vcpu_pc, bool cache), + TP_ARGS(vcpu_pc, cache), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_pc ) + __field( bool, cache ) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->cache = cache; + ), + + TP_printk("S/W flush at 0x%016lx (cache %s)", + __entry->vcpu_pc, __entry->cache ? "on" : "off") +); + +TRACE_EVENT(kvm_toggle_cache, + TP_PROTO(unsigned long vcpu_pc, bool was, bool now), + TP_ARGS(vcpu_pc, was, now), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_pc ) + __field( bool, was ) + __field( bool, now ) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->was = was; + __entry->now = now; + ), + + TP_printk("VM op at 0x%016lx (cache was %s, now %s)", + __entry->vcpu_pc, __entry->was ? "on" : "off", + __entry->now ? "on" : "off") +); + #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 1c43cec971b5..066688863920 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -85,6 +85,7 @@ vdso_install: # We use MRPROPER_FILES and CLEAN_FILES now archclean: $(Q)$(MAKE) $(clean)=$(boot) + $(Q)$(MAKE) $(clean)=$(boot)/dts define archhelp echo '* Image.gz - Compressed kernel image (arch/$(ARCH)/boot/Image.gz)' diff --git a/arch/arm64/boot/dts/Makefile b/arch/arm64/boot/dts/Makefile index 3b8d427c3985..c62b0f4d9ef6 100644 --- a/arch/arm64/boot/dts/Makefile +++ b/arch/arm64/boot/dts/Makefile @@ -3,6 +3,4 @@ dts-dirs += apm dts-dirs += arm dts-dirs += cavium -always := $(dtb-y) subdir-y := $(dts-dirs) -clean-files := *.dtb diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 8127e45e2637..3cb4c856b10d 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -41,6 +41,18 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) { vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS; + if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) + vcpu->arch.hcr_el2 &= ~HCR_RW; +} + +static inline unsigned long vcpu_get_hcr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.hcr_el2; +} + +static inline void vcpu_set_hcr(struct kvm_vcpu *vcpu, unsigned long hcr) +{ + vcpu->arch.hcr_el2 = hcr; } static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 0b7dfdb931df..acd101a9014d 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -116,9 +116,6 @@ struct kvm_vcpu_arch { * Anything that is not used directly from assembly code goes * here. */ - /* dcache set/way operation pending */ - int last_pcpu; - cpumask_t require_dcache_flush; /* Don't run the guest */ bool pause; diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 14a74f136272..adcf49547301 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -243,24 +243,46 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101; } -static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, - unsigned long size, - bool ipa_uncached) +static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, + unsigned long size, + bool ipa_uncached) { + void *va = page_address(pfn_to_page(pfn)); + if (!vcpu_has_cache_enabled(vcpu) || ipa_uncached) - kvm_flush_dcache_to_poc((void *)hva, size); + kvm_flush_dcache_to_poc(va, size); if (!icache_is_aliasing()) { /* PIPT */ - flush_icache_range(hva, hva + size); + flush_icache_range((unsigned long)va, + (unsigned long)va + size); } else if (!icache_is_aivivt()) { /* non ASID-tagged VIVT */ /* any kind of VIPT cache */ __flush_icache_all(); } } +static inline void __kvm_flush_dcache_pte(pte_t pte) +{ + struct page *page = pte_page(pte); + kvm_flush_dcache_to_poc(page_address(page), PAGE_SIZE); +} + +static inline void __kvm_flush_dcache_pmd(pmd_t pmd) +{ + struct page *page = pmd_page(pmd); + kvm_flush_dcache_to_poc(page_address(page), PMD_SIZE); +} + +static inline void __kvm_flush_dcache_pud(pud_t pud) +{ + struct page *page = pud_page(pud); + kvm_flush_dcache_to_poc(page_address(page), PUD_SIZE); +} + #define kvm_virt_to_phys(x) __virt_to_phys((unsigned long)(x)) -void stage2_flush_vm(struct kvm *kvm); +void kvm_set_way_flush(struct kvm_vcpu *vcpu); +void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled); #endif /* __ASSEMBLY__ */ #endif /* __ARM64_KVM_MMU_H__ */ diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index b780c6c76eec..23e9432ac112 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -44,7 +44,7 @@ #define __ARM_NR_compat_cacheflush (__ARM_NR_COMPAT_BASE+2) #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE+5) -#define __NR_compat_syscalls 387 +#define __NR_compat_syscalls 388 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 8893cebcea5b..27224426e0bf 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -795,3 +795,5 @@ __SYSCALL(__NR_getrandom, sys_getrandom) __SYSCALL(__NR_memfd_create, sys_memfd_create) #define __NR_bpf 386 __SYSCALL(__NR_bpf, sys_bpf) +#define __NR_execveat 387 +__SYSCALL(__NR_execveat, compat_sys_execveat) diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index fbe909fb0a1a..c3ca89c27c6b 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -1014,6 +1014,7 @@ ENTRY(__kvm_tlb_flush_vmid_ipa) * Instead, we invalidate Stage-2 for this IPA, and the * whole of Stage-1. Weep... */ + lsr x1, x1, #12 tlbi ipas2e1is, x1 /* * We have to ensure completion of the invalidation at Stage-2, diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 70a7816535cd..0b4326578985 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -90,7 +90,6 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) if (!cpu_has_32bit_el1()) return -EINVAL; cpu_reset = &default_regs_reset32; - vcpu->arch.hcr_el2 &= ~HCR_RW; } else { cpu_reset = &default_regs_reset; } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 3d7c2df89946..f31e8bb2bc5b 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -69,68 +69,31 @@ static u32 get_ccsidr(u32 csselr) return ccsidr; } -static void do_dc_cisw(u32 val) -{ - asm volatile("dc cisw, %x0" : : "r" (val)); - dsb(ish); -} - -static void do_dc_csw(u32 val) -{ - asm volatile("dc csw, %x0" : : "r" (val)); - dsb(ish); -} - -/* See note at ARM ARM B1.14.4 */ +/* + * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized). + */ static bool access_dcsw(struct kvm_vcpu *vcpu, const struct sys_reg_params *p, const struct sys_reg_desc *r) { - unsigned long val; - int cpu; - if (!p->is_write) return read_from_write_only(vcpu, p); - cpu = get_cpu(); - - cpumask_setall(&vcpu->arch.require_dcache_flush); - cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush); - - /* If we were already preempted, take the long way around */ - if (cpu != vcpu->arch.last_pcpu) { - flush_cache_all(); - goto done; - } - - val = *vcpu_reg(vcpu, p->Rt); - - switch (p->CRm) { - case 6: /* Upgrade DCISW to DCCISW, as per HCR.SWIO */ - case 14: /* DCCISW */ - do_dc_cisw(val); - break; - - case 10: /* DCCSW */ - do_dc_csw(val); - break; - } - -done: - put_cpu(); - + kvm_set_way_flush(vcpu); return true; } /* * Generic accessor for VM registers. Only called as long as HCR_TVM - * is set. + * is set. If the guest enables the MMU, we stop trapping the VM + * sys_regs and leave it in complete control of the caches. */ static bool access_vm_reg(struct kvm_vcpu *vcpu, const struct sys_reg_params *p, const struct sys_reg_desc *r) { unsigned long val; + bool was_enabled = vcpu_has_cache_enabled(vcpu); BUG_ON(!p->is_write); @@ -143,25 +106,7 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu, vcpu_cp15_64_low(vcpu, r->reg) = val & 0xffffffffUL; } - return true; -} - -/* - * SCTLR_EL1 accessor. Only called as long as HCR_TVM is set. If the - * guest enables the MMU, we stop trapping the VM sys_regs and leave - * it in complete control of the caches. - */ -static bool access_sctlr(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, - const struct sys_reg_desc *r) -{ - access_vm_reg(vcpu, p, r); - - if (vcpu_has_cache_enabled(vcpu)) { /* MMU+Caches enabled? */ - vcpu->arch.hcr_el2 &= ~HCR_TVM; - stage2_flush_vm(vcpu->kvm); - } - + kvm_toggle_cache(vcpu, was_enabled); return true; } @@ -377,7 +322,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { NULL, reset_mpidr, MPIDR_EL1 }, /* SCTLR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000), - access_sctlr, reset_val, SCTLR_EL1, 0x00C50078 }, + access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 }, /* CPACR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b010), NULL, reset_val, CPACR_EL1, 0 }, @@ -657,7 +602,7 @@ static const struct sys_reg_desc cp14_64_regs[] = { * register). */ static const struct sys_reg_desc cp15_regs[] = { - { Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_sctlr, NULL, c1_SCTLR }, + { Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, NULL, c1_SCTLR }, { Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 }, { Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 }, { Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR }, diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index cf33f33333cc..d54dc9ac4b70 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -15,6 +15,7 @@ */ #include <linux/debugfs.h> #include <linux/fs.h> +#include <linux/io.h> #include <linux/mm.h> #include <linux/sched.h> #include <linux/seq_file.h> diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index bac492c12fcc..c95464a33f36 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -335,14 +335,8 @@ static int keep_initrd; void free_initrd_mem(unsigned long start, unsigned long end) { - if (!keep_initrd) { - if (start == initrd_start) - start = round_down(start, PAGE_SIZE); - if (end == initrd_end) - end = round_up(end, PAGE_SIZE); - + if (!keep_initrd) free_reserved_area((void *)start, (void *)end, 0, "initrd"); - } } static int __init keepinitrd_setup(char *__unused) diff --git a/arch/avr32/kernel/module.c b/arch/avr32/kernel/module.c index 2c9412908024..164efa009e5b 100644 --- a/arch/avr32/kernel/module.c +++ b/arch/avr32/kernel/module.c @@ -19,12 +19,10 @@ #include <linux/moduleloader.h> #include <linux/vmalloc.h> -void module_free(struct module *mod, void *module_region) +void module_arch_freeing_init(struct module *mod) { vfree(mod->arch.syminfo); mod->arch.syminfo = NULL; - - vfree(module_region); } static inline int check_rela(Elf32_Rela *rela, struct module *module, @@ -291,12 +289,3 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab, return ret; } - -int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, - struct module *module) -{ - vfree(module->arch.syminfo); - module->arch.syminfo = NULL; - - return 0; -} diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c index 0eca93327195..d223a8b57c1e 100644 --- a/arch/avr32/mm/fault.c +++ b/arch/avr32/mm/fault.c @@ -142,6 +142,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/cris/arch-v32/drivers/sync_serial.c b/arch/cris/arch-v32/drivers/sync_serial.c index 08a313fc2241..f772068d9e79 100644 --- a/arch/cris/arch-v32/drivers/sync_serial.c +++ b/arch/cris/arch-v32/drivers/sync_serial.c @@ -604,7 +604,7 @@ static ssize_t __sync_serial_read(struct file *file, struct timespec *ts) { unsigned long flags; - int dev = MINOR(file->f_dentry->d_inode->i_rdev); + int dev = MINOR(file_inode(file)->i_rdev); int avail; struct sync_port *port; unsigned char *start; diff --git a/arch/cris/kernel/module.c b/arch/cris/kernel/module.c index 51123f985eb5..af04cb6b6dc9 100644 --- a/arch/cris/kernel/module.c +++ b/arch/cris/kernel/module.c @@ -36,7 +36,7 @@ void *module_alloc(unsigned long size) } /* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) +void module_memfree(void *module_region) { kfree(module_region); } diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c index 1790f22e71a2..2686a7aa8ec8 100644 --- a/arch/cris/mm/fault.c +++ b/arch/cris/mm/fault.c @@ -176,6 +176,8 @@ retry: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/frv/mb93090-mb00/pci-frv.c b/arch/frv/mb93090-mb00/pci-frv.c index 67b1d1685759..0635bd6c2af3 100644 --- a/arch/frv/mb93090-mb00/pci-frv.c +++ b/arch/frv/mb93090-mb00/pci-frv.c @@ -94,7 +94,7 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list) r = &dev->resource[idx]; if (!r->start) continue; - pci_claim_resource(dev, idx); + pci_claim_bridge_resource(dev, idx); } } pcibios_allocate_bus_resources(&bus->children); diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c index 9a66372fc7c7..ec4917ddf678 100644 --- a/arch/frv/mm/fault.c +++ b/arch/frv/mm/fault.c @@ -168,6 +168,8 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c index 24603be24c14..29754aae5177 100644 --- a/arch/ia64/kernel/module.c +++ b/arch/ia64/kernel/module.c @@ -305,14 +305,12 @@ plt_target (struct plt_entry *plt) #endif /* !USE_BRL */ void -module_free (struct module *mod, void *module_region) +module_arch_freeing_init (struct module *mod) { - if (mod && mod->arch.init_unw_table && - module_region == mod->module_init) { + if (mod->arch.init_unw_table) { unw_remove_unwind_table(mod->arch.init_unw_table); mod->arch.init_unw_table = NULL; } - vfree(module_region); } /* Have we already seen one of these relocations? */ diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 7225dad87094..ba5ba7accd0d 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -172,6 +172,8 @@ retry: */ if (fault & VM_FAULT_OOM) { goto out_of_memory; + } else if (fault & VM_FAULT_SIGSEGV) { + goto bad_area; } else if (fault & VM_FAULT_SIGBUS) { signal = SIGBUS; goto bad_area; diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c index 291a582777cf..900cc93e5409 100644 --- a/arch/ia64/pci/pci.c +++ b/arch/ia64/pci/pci.c @@ -487,45 +487,39 @@ int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge) return 0; } -static int is_valid_resource(struct pci_dev *dev, int idx) +void pcibios_fixup_device_resources(struct pci_dev *dev) { - unsigned int i, type_mask = IORESOURCE_IO | IORESOURCE_MEM; - struct resource *devr = &dev->resource[idx], *busr; + int idx; if (!dev->bus) - return 0; - - pci_bus_for_each_resource(dev->bus, busr, i) { - if (!busr || ((busr->flags ^ devr->flags) & type_mask)) - continue; - if ((devr->start) && (devr->start >= busr->start) && - (devr->end <= busr->end)) - return 1; - } - return 0; -} + return; -static void pcibios_fixup_resources(struct pci_dev *dev, int start, int limit) -{ - int i; + for (idx = 0; idx < PCI_BRIDGE_RESOURCES; idx++) { + struct resource *r = &dev->resource[idx]; - for (i = start; i < limit; i++) { - if (!dev->resource[i].flags) + if (!r->flags || r->parent || !r->start) continue; - if ((is_valid_resource(dev, i))) - pci_claim_resource(dev, i); - } -} -void pcibios_fixup_device_resources(struct pci_dev *dev) -{ - pcibios_fixup_resources(dev, 0, PCI_BRIDGE_RESOURCES); + pci_claim_resource(dev, idx); + } } EXPORT_SYMBOL_GPL(pcibios_fixup_device_resources); static void pcibios_fixup_bridge_resources(struct pci_dev *dev) { - pcibios_fixup_resources(dev, PCI_BRIDGE_RESOURCES, PCI_NUM_RESOURCES); + int idx; + + if (!dev->bus) + return; + + for (idx = PCI_BRIDGE_RESOURCES; idx < PCI_NUM_RESOURCES; idx++) { + struct resource *r = &dev->resource[idx]; + + if (!r->flags || r->parent || !r->start) + continue; + + pci_claim_bridge_resource(dev, idx); + } } /* diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c index e9c6a8014bd6..e3d4d4890104 100644 --- a/arch/m32r/mm/fault.c +++ b/arch/m32r/mm/fault.c @@ -200,6 +200,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h index 75e75d7b1702..244e0dbe45db 100644 --- a/arch/m68k/include/asm/unistd.h +++ b/arch/m68k/include/asm/unistd.h @@ -4,7 +4,7 @@ #include <uapi/asm/unistd.h> -#define NR_syscalls 355 +#define NR_syscalls 356 #define __ARCH_WANT_OLD_READDIR #define __ARCH_WANT_OLD_STAT diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h index 2c1bec9a14b6..61fb6cb9d2ae 100644 --- a/arch/m68k/include/uapi/asm/unistd.h +++ b/arch/m68k/include/uapi/asm/unistd.h @@ -360,5 +360,6 @@ #define __NR_getrandom 352 #define __NR_memfd_create 353 #define __NR_bpf 354 +#define __NR_execveat 355 #endif /* _UAPI_ASM_M68K_UNISTD_H_ */ diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S index 2ca219e184cd..a0ec4303f2c8 100644 --- a/arch/m68k/kernel/syscalltable.S +++ b/arch/m68k/kernel/syscalltable.S @@ -375,4 +375,5 @@ ENTRY(sys_call_table) .long sys_getrandom .long sys_memfd_create .long sys_bpf + .long sys_execveat /* 355 */ diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 2bd7487440c4..b2f04aee46ec 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -145,6 +145,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto map_err; else if (fault & VM_FAULT_SIGBUS) goto bus_err; BUG(); diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c index 332680e5ebf2..2de5dc695a87 100644 --- a/arch/metag/mm/fault.c +++ b/arch/metag/mm/fault.c @@ -141,6 +141,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index fa4cf52aa7a6..d46a5ebb7570 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -224,6 +224,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c index b30e41c0c033..48528fb81eff 100644 --- a/arch/microblaze/pci/pci-common.c +++ b/arch/microblaze/pci/pci-common.c @@ -1026,6 +1026,8 @@ static void pcibios_allocate_bus_resources(struct pci_bus *bus) pr, (pr && pr->name) ? pr->name : "nil"); if (pr && !(pr->flags & IORESOURCE_UNSET)) { + struct pci_dev *dev = bus->self; + if (request_resource(pr, res) == 0) continue; /* @@ -1035,6 +1037,12 @@ static void pcibios_allocate_bus_resources(struct pci_bus *bus) */ if (reparent_resources(pr, res) == 0) continue; + + if (dev && i < PCI_BRIDGE_RESOURCE_NUM && + pci_claim_bridge_resource(dev, + i + PCI_BRIDGE_RESOURCES) == 0) + continue; + } pr_warn("PCI: Cannot allocate resource region "); pr_cont("%d of PCI bridge %d, will remap\n", i, bus->number); @@ -1227,7 +1235,10 @@ void pcibios_claim_one_bus(struct pci_bus *bus) (unsigned long long)r->end, (unsigned int)r->flags); - pci_claim_resource(dev, i); + if (pci_claim_resource(dev, i) == 0) + continue; + + pci_claim_bridge_resource(dev, i); } } diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index becc42bb1849..70ab5d664332 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -158,6 +158,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c index 9fd6834a2172..5d6139390bf8 100644 --- a/arch/mips/net/bpf_jit.c +++ b/arch/mips/net/bpf_jit.c @@ -1388,7 +1388,7 @@ out: void bpf_jit_free(struct bpf_prog *fp) { if (fp->jited) - module_free(NULL, fp->bpf_func); + module_memfree(fp->bpf_func); bpf_prog_unlock_free(fp); } diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c index 3516cbdf1ee9..0c2cc5d39c8e 100644 --- a/arch/mn10300/mm/fault.c +++ b/arch/mn10300/mm/fault.c @@ -262,6 +262,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/mn10300/unit-asb2305/pci-asb2305.c b/arch/mn10300/unit-asb2305/pci-asb2305.c index febb9cd83177..b5b036f64275 100644 --- a/arch/mn10300/unit-asb2305/pci-asb2305.c +++ b/arch/mn10300/unit-asb2305/pci-asb2305.c @@ -106,7 +106,7 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list) if (!r->flags) continue; if (!r->start || - pci_claim_resource(dev, idx) < 0) { + pci_claim_bridge_resource(dev, idx) < 0) { printk(KERN_ERR "PCI:" " Cannot allocate resource" " region %d of bridge %s\n", diff --git a/arch/mn10300/unit-asb2305/pci.c b/arch/mn10300/unit-asb2305/pci.c index 6b4339f8c9c2..471ff398090c 100644 --- a/arch/mn10300/unit-asb2305/pci.c +++ b/arch/mn10300/unit-asb2305/pci.c @@ -281,42 +281,37 @@ static int __init pci_check_direct(void) return -ENODEV; } -static int is_valid_resource(struct pci_dev *dev, int idx) +static void pcibios_fixup_device_resources(struct pci_dev *dev) { - unsigned int i, type_mask = IORESOURCE_IO | IORESOURCE_MEM; - struct resource *devr = &dev->resource[idx], *busr; - - if (dev->bus) { - pci_bus_for_each_resource(dev->bus, busr, i) { - if (!busr || (busr->flags ^ devr->flags) & type_mask) - continue; - - if (devr->start && - devr->start >= busr->start && - devr->end <= busr->end) - return 1; - } - } + int idx; - return 0; + if (!dev->bus) + return; + + for (idx = 0; idx < PCI_BRIDGE_RESOURCES; idx++) { + struct resource *r = &dev->resource[idx]; + + if (!r->flags || r->parent || !r->start) + continue; + + pci_claim_resource(dev, idx); + } } -static void pcibios_fixup_device_resources(struct pci_dev *dev) +static void pcibios_fixup_bridge_resources(struct pci_dev *dev) { - int limit, i; + int idx; - if (dev->bus->number != 0) + if (!dev->bus) return; - limit = (dev->hdr_type == PCI_HEADER_TYPE_NORMAL) ? - PCI_BRIDGE_RESOURCES : PCI_NUM_RESOURCES; + for (idx = PCI_BRIDGE_RESOURCES; idx < PCI_NUM_RESOURCES; idx++) { + struct resource *r = &dev->resource[idx]; - for (i = 0; i < limit; i++) { - if (!dev->resource[i].flags) + if (!r->flags || r->parent || !r->start) continue; - if (is_valid_resource(dev, i)) - pci_claim_resource(dev, i); + pci_claim_bridge_resource(dev, idx); } } @@ -330,7 +325,7 @@ void pcibios_fixup_bus(struct pci_bus *bus) if (bus->self) { pci_read_bridge_bases(bus); - pcibios_fixup_device_resources(bus->self); + pcibios_fixup_bridge_resources(bus->self); } list_for_each_entry(dev, &bus->devices, bus_list) diff --git a/arch/nios2/kernel/module.c b/arch/nios2/kernel/module.c index cc924a38f22a..e2e3f13f98d5 100644 --- a/arch/nios2/kernel/module.c +++ b/arch/nios2/kernel/module.c @@ -36,7 +36,7 @@ void *module_alloc(unsigned long size) } /* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) +void module_memfree(void *module_region) { kfree(module_region); } diff --git a/arch/nios2/kernel/signal.c b/arch/nios2/kernel/signal.c index f9d27883a714..2d0ea25be171 100644 --- a/arch/nios2/kernel/signal.c +++ b/arch/nios2/kernel/signal.c @@ -200,7 +200,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, /* Set up to return from userspace; jump to fixed address sigreturn trampoline on kuser page. */ - regs->ra = (unsigned long) (0x1040); + regs->ra = (unsigned long) (0x1044); /* Set up registers for signal handler */ regs->sp = (unsigned long) frame; diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index 15a0bb5fc06d..34429d5a0ccd 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -135,6 +135,8 @@ survive: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 0703acf7d327..230ac20ae794 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -171,6 +171,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c index 50dfafc3f2c1..5822e8e200e6 100644 --- a/arch/parisc/kernel/module.c +++ b/arch/parisc/kernel/module.c @@ -298,14 +298,10 @@ static inline unsigned long count_stubs(const Elf_Rela *rela, unsigned long n) } #endif - -/* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) +void module_arch_freeing_init(struct module *mod) { kfree(mod->arch.section); mod->arch.section = NULL; - - vfree(module_region); } /* Additional bytes needed in front of individual sections */ diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 3ca9c1131cfe..e5120e653240 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -256,6 +256,8 @@ good_area: */ if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto bad_area; BUG(); diff --git a/arch/powerpc/crypto/sha1.c b/arch/powerpc/crypto/sha1.c index d3feba5a275f..c154cebc1041 100644 --- a/arch/powerpc/crypto/sha1.c +++ b/arch/powerpc/crypto/sha1.c @@ -154,4 +154,5 @@ module_exit(sha1_powerpc_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm"); +MODULE_ALIAS_CRYPTO("sha1"); MODULE_ALIAS_CRYPTO("sha1-powerpc"); diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index ebc4f165690a..0be6c681cab1 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -23,9 +23,9 @@ #define THREAD_SIZE (1 << THREAD_SHIFT) #ifdef CONFIG_PPC64 -#define CURRENT_THREAD_INFO(dest, sp) clrrdi dest, sp, THREAD_SHIFT +#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(clrrdi dest, sp, THREAD_SHIFT) #else -#define CURRENT_THREAD_INFO(dest, sp) rlwinm dest, sp, 0, 0, 31-THREAD_SHIFT +#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(rlwinm dest, sp, 0, 0, 31-THREAD_SHIFT) #endif #ifndef __ASSEMBLY__ @@ -71,12 +71,13 @@ struct thread_info { #define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT) /* how to get the thread information struct from C */ -register unsigned long __current_r1 asm("r1"); static inline struct thread_info *current_thread_info(void) { - /* gcc4, at least, is smart enough to turn this into a single - * rlwinm for ppc32 and clrrdi for ppc64 */ - return (struct thread_info *)(__current_r1 & ~(THREAD_SIZE-1)); + unsigned long val; + + asm (CURRENT_THREAD_INFO(%0,1) : "=r" (val)); + + return (struct thread_info *)val; } #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 37d512d35943..2a525c938158 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1184,6 +1184,8 @@ static void pcibios_allocate_bus_resources(struct pci_bus *bus) pr, (pr && pr->name) ? pr->name : "nil"); if (pr && !(pr->flags & IORESOURCE_UNSET)) { + struct pci_dev *dev = bus->self; + if (request_resource(pr, res) == 0) continue; /* @@ -1193,6 +1195,11 @@ static void pcibios_allocate_bus_resources(struct pci_bus *bus) */ if (reparent_resources(pr, res) == 0) continue; + + if (dev && i < PCI_BRIDGE_RESOURCE_NUM && + pci_claim_bridge_resource(dev, + i + PCI_BRIDGE_RESOURCES) == 0) + continue; } pr_warning("PCI: Cannot allocate resource region " "%d of PCI bridge %d, will remap\n", i, bus->number); @@ -1401,7 +1408,10 @@ void pcibios_claim_one_bus(struct pci_bus *bus) (unsigned long long)r->end, (unsigned int)r->flags); - pci_claim_resource(dev, i); + if (pci_claim_resource(dev, i) == 0) + continue; + + pci_claim_bridge_resource(dev, i); } } diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index 5a236f082c78..1b5305d4bdab 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -76,7 +76,7 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; goto out_unlock; - } else if (*flt & VM_FAULT_SIGBUS) { + } else if (*flt & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) { ret = -EFAULT; goto out_unlock; } diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index eb79907f34fa..6154b0a2b063 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -437,6 +437,8 @@ good_area: */ fault = handle_mm_fault(mm, vma, address, flags); if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) { + if (fault & VM_FAULT_SIGSEGV) + goto bad_area; rc = mm_fault_error(regs, address, fault); if (rc >= MM_FAULT_RETURN) goto bail; diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 1ca125b9c226..d1916b577f2c 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -699,7 +699,7 @@ out: void bpf_jit_free(struct bpf_prog *fp) { if (fp->jited) - module_free(NULL, fp->bpf_func); + module_memfree(fp->bpf_func); bpf_prog_unlock_free(fp); } diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index 54eca8b3b288..0509bca5e830 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -40,7 +40,6 @@ BEGIN_FTR_SECTION; \ b 1f; \ END_FTR_SECTION(0, 1); \ ld r12,opal_tracepoint_refcount@toc(r2); \ - std r12,32(r1); \ cmpdi r12,0; \ bne- LABEL; \ 1: diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index b700a329c31d..d2de7d5d7574 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -304,7 +304,7 @@ int pnv_save_sprs_for_winkle(void) * all cpus at boot. Get these reg values of current cpu and use the * same accross all cpus. */ - uint64_t lpcr_val = mfspr(SPRN_LPCR); + uint64_t lpcr_val = mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1; uint64_t hid0_val = mfspr(SPRN_HID0); uint64_t hid1_val = mfspr(SPRN_HID1); uint64_t hid4_val = mfspr(SPRN_HID4); diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 5b150f0c5df9..13c6e200b24e 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -337,6 +337,7 @@ static inline void disable_surveillance(void) args.token = rtas_token("set-indicator"); if (args.token == RTAS_UNKNOWN_SERVICE) return; + args.token = cpu_to_be32(args.token); args.nargs = cpu_to_be32(3); args.nret = cpu_to_be32(1); args.rets = &args.args[3]; diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c index 32040ace00ea..afbe07907c10 100644 --- a/arch/s390/hypfs/hypfs_vm.c +++ b/arch/s390/hypfs/hypfs_vm.c @@ -231,7 +231,7 @@ failed: struct dbfs_d2fc_hdr { u64 len; /* Length of d2fc buffer without header */ u16 version; /* Version of header */ - char tod_ext[16]; /* TOD clock for d2fc */ + char tod_ext[STORE_CLOCK_EXT_SIZE]; /* TOD clock for d2fc */ u64 count; /* Number of VM guests in d2fc buffer */ char reserved[30]; } __attribute__ ((packed)); diff --git a/arch/s390/include/asm/irqflags.h b/arch/s390/include/asm/irqflags.h index 37b9091ab8c0..16aa0c779e07 100644 --- a/arch/s390/include/asm/irqflags.h +++ b/arch/s390/include/asm/irqflags.h @@ -36,7 +36,7 @@ static inline notrace void __arch_local_irq_ssm(unsigned long flags) static inline notrace unsigned long arch_local_save_flags(void) { - return __arch_local_irq_stosm(0x00); + return __arch_local_irq_stnsm(0xff); } static inline notrace unsigned long arch_local_irq_save(void) diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 8beee1cceba4..98eb2a579223 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -67,20 +67,22 @@ static inline void local_tick_enable(unsigned long long comp) set_clock_comparator(S390_lowcore.clock_comparator); } -#define CLOCK_TICK_RATE 1193180 /* Underlying HZ */ +#define CLOCK_TICK_RATE 1193180 /* Underlying HZ */ +#define STORE_CLOCK_EXT_SIZE 16 /* stcke writes 16 bytes */ typedef unsigned long long cycles_t; -static inline void get_tod_clock_ext(char clk[16]) +static inline void get_tod_clock_ext(char *clk) { - typedef struct { char _[sizeof(clk)]; } addrtype; + typedef struct { char _[STORE_CLOCK_EXT_SIZE]; } addrtype; asm volatile("stcke %0" : "=Q" (*(addrtype *) clk) : : "cc"); } static inline unsigned long long get_tod_clock(void) { - unsigned char clk[16]; + unsigned char clk[STORE_CLOCK_EXT_SIZE]; + get_tod_clock_ext(clk); return *((unsigned long long *)&clk[1]); } diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h index 2b446cf0cc65..67878af257a0 100644 --- a/arch/s390/include/uapi/asm/unistd.h +++ b/arch/s390/include/uapi/asm/unistd.h @@ -289,7 +289,8 @@ #define __NR_bpf 351 #define __NR_s390_pci_mmio_write 352 #define __NR_s390_pci_mmio_read 353 -#define NR_syscalls 354 +#define __NR_execveat 354 +#define NR_syscalls 355 /* * There are some system calls that are not present on 64 bit, some diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index b89b59158b95..409d152585be 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -55,14 +55,10 @@ void *module_alloc(unsigned long size) } #endif -/* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) +void module_arch_freeing_init(struct module *mod) { - if (mod) { - vfree(mod->arch.syminfo); - mod->arch.syminfo = NULL; - } - vfree(module_region); + vfree(mod->arch.syminfo); + mod->arch.syminfo = NULL; } static void check_rela(Elf_Rela *rela, struct module *me) diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index a2987243bc76..939ec474b1dd 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -362,3 +362,4 @@ SYSCALL(sys_memfd_create,sys_memfd_create,compat_sys_memfd_create) /* 350 */ SYSCALL(sys_bpf,sys_bpf,compat_sys_bpf) SYSCALL(sys_ni_syscall,sys_s390_pci_mmio_write,compat_sys_s390_pci_mmio_write) SYSCALL(sys_ni_syscall,sys_s390_pci_mmio_read,compat_sys_s390_pci_mmio_read) +SYSCALL(sys_execveat,sys_execveat,compat_sys_execveat) diff --git a/arch/s390/kernel/uprobes.c b/arch/s390/kernel/uprobes.c index f6b3cd056ec2..cc7328080b60 100644 --- a/arch/s390/kernel/uprobes.c +++ b/arch/s390/kernel/uprobes.c @@ -48,6 +48,30 @@ bool arch_uprobe_xol_was_trapped(struct task_struct *tsk) return false; } +static int check_per_event(unsigned short cause, unsigned long control, + struct pt_regs *regs) +{ + if (!(regs->psw.mask & PSW_MASK_PER)) + return 0; + /* user space single step */ + if (control == 0) + return 1; + /* over indication for storage alteration */ + if ((control & 0x20200000) && (cause & 0x2000)) + return 1; + if (cause & 0x8000) { + /* all branches */ + if ((control & 0x80800000) == 0x80000000) + return 1; + /* branch into selected range */ + if (((control & 0x80800000) == 0x80800000) && + regs->psw.addr >= current->thread.per_user.start && + regs->psw.addr <= current->thread.per_user.end) + return 1; + } + return 0; +} + int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { int fixup = probe_get_fixup_type(auprobe->insn); @@ -71,9 +95,13 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) if (regs->psw.addr - utask->xol_vaddr == ilen) regs->psw.addr = utask->vaddr + ilen; } - /* If per tracing was active generate trap */ - if (regs->psw.mask & PSW_MASK_PER) - do_per_trap(regs); + if (check_per_event(current->thread.per_event.cause, + current->thread.per_user.control, regs)) { + /* fix per address */ + current->thread.per_event.address = utask->vaddr; + /* trigger per event */ + set_pt_regs_flag(regs, PIF_PER_TRAP); + } return 0; } @@ -106,6 +134,7 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) clear_thread_flag(TIF_UPROBE_SINGLESTEP); regs->int_code = auprobe->saved_int_code; regs->psw.addr = current->utask->vaddr; + current->thread.per_event.address = current->utask->vaddr; } unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline, @@ -146,17 +175,20 @@ static void adjust_psw_addr(psw_t *psw, unsigned long len) __rc; \ }) -#define emu_store_ril(ptr, input) \ +#define emu_store_ril(regs, ptr, input) \ ({ \ unsigned int mask = sizeof(*(ptr)) - 1; \ + __typeof__(ptr) __ptr = (ptr); \ int __rc = 0; \ \ if (!test_facility(34)) \ __rc = EMU_ILLEGAL_OP; \ - else if ((u64 __force)ptr & mask) \ + else if ((u64 __force)__ptr & mask) \ __rc = EMU_SPECIFICATION; \ - else if (put_user(*(input), ptr)) \ + else if (put_user(*(input), __ptr)) \ __rc = EMU_ADDRESSING; \ + if (__rc == 0) \ + sim_stor_event(regs, __ptr, mask + 1); \ __rc; \ }) @@ -198,6 +230,25 @@ union split_register { }; /* + * If user per registers are setup to trace storage alterations and an + * emulated store took place on a fitting address a user trap is generated. + */ +static void sim_stor_event(struct pt_regs *regs, void *addr, int len) +{ + if (!(regs->psw.mask & PSW_MASK_PER)) + return; + if (!(current->thread.per_user.control & PER_EVENT_STORE)) + return; + if ((void *)current->thread.per_user.start > (addr + len)) + return; + if ((void *)current->thread.per_user.end < addr) + return; + current->thread.per_event.address = regs->psw.addr; + current->thread.per_event.cause = PER_EVENT_STORE >> 16; + set_pt_regs_flag(regs, PIF_PER_TRAP); +} + +/* * pc relative instructions are emulated, since parameters may not be * accessible from the xol area due to range limitations. */ @@ -249,13 +300,13 @@ static void handle_insn_ril(struct arch_uprobe *auprobe, struct pt_regs *regs) rc = emu_load_ril((u32 __user *)uptr, &rx->u64); break; case 0x07: /* sthrl */ - rc = emu_store_ril((u16 __user *)uptr, &rx->u16[3]); + rc = emu_store_ril(regs, (u16 __user *)uptr, &rx->u16[3]); break; case 0x0b: /* stgrl */ - rc = emu_store_ril((u64 __user *)uptr, &rx->u64); + rc = emu_store_ril(regs, (u64 __user *)uptr, &rx->u64); break; case 0x0f: /* strl */ - rc = emu_store_ril((u32 __user *)uptr, &rx->u32[1]); + rc = emu_store_ril(regs, (u32 __user *)uptr, &rx->u32[1]); break; } break; diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 7f0089d9a4aa..e34122e539a1 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -128,8 +128,6 @@ void vtime_account_irq_enter(struct task_struct *tsk) struct thread_info *ti = task_thread_info(tsk); u64 timer, system; - WARN_ON_ONCE(!irqs_disabled()); - timer = S390_lowcore.last_update_timer; S390_lowcore.last_update_timer = get_vtimer(); S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 811937bb90be..9065d5aa3932 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -374,6 +374,12 @@ static noinline void do_fault_error(struct pt_regs *regs, int fault) do_no_context(regs); else pagefault_out_of_memory(); + } else if (fault & VM_FAULT_SIGSEGV) { + /* Kernel mode? Handle exceptions or die */ + if (!user_mode(regs)) + do_no_context(regs); + else + do_sigsegv(regs, SEGV_MAPERR); } else if (fault & VM_FAULT_SIGBUS) { /* Kernel mode? Handle exceptions or die */ if (!user_mode(regs)) diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index be99357d238c..3cf8cc03fff6 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -322,11 +322,12 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table, static unsigned long __gmap_segment_gaddr(unsigned long *entry) { struct page *page; - unsigned long offset; + unsigned long offset, mask; offset = (unsigned long) entry / sizeof(unsigned long); offset = (offset & (PTRS_PER_PMD - 1)) * PMD_SIZE; - page = pmd_to_page((pmd_t *) entry); + mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1); + page = virt_to_page((void *)((unsigned long) entry & mask)); return page->index + offset; } diff --git a/arch/s390/net/bpf_jit.S b/arch/s390/net/bpf_jit.S index 7e45d13816c1..ba44c9f55346 100644 --- a/arch/s390/net/bpf_jit.S +++ b/arch/s390/net/bpf_jit.S @@ -22,8 +22,8 @@ * skb_copy_bits takes 4 parameters: * %r2 = skb pointer * %r3 = offset into skb data - * %r4 = length to copy - * %r5 = pointer to temp buffer + * %r4 = pointer to temp buffer + * %r5 = length to copy */ #define SKBDATA %r8 @@ -44,8 +44,9 @@ ENTRY(sk_load_word) sk_load_word_slow: lgr %r9,%r2 # save %r2 - lhi %r4,4 # 4 bytes - la %r5,160(%r15) # pointer to temp buffer + lgr %r3,%r1 # offset + la %r4,160(%r15) # pointer to temp buffer + lghi %r5,4 # 4 bytes brasl %r14,skb_copy_bits # get data from skb l %r5,160(%r15) # load result from temp buffer ltgr %r2,%r2 # set cc to (%r2 != 0) @@ -69,8 +70,9 @@ ENTRY(sk_load_half) sk_load_half_slow: lgr %r9,%r2 # save %r2 - lhi %r4,2 # 2 bytes - la %r5,162(%r15) # pointer to temp buffer + lgr %r3,%r1 # offset + la %r4,162(%r15) # pointer to temp buffer + lghi %r5,2 # 2 bytes brasl %r14,skb_copy_bits # get data from skb xc 160(2,%r15),160(%r15) l %r5,160(%r15) # load result from temp buffer @@ -95,8 +97,9 @@ ENTRY(sk_load_byte) sk_load_byte_slow: lgr %r9,%r2 # save %r2 - lhi %r4,1 # 1 bytes - la %r5,163(%r15) # pointer to temp buffer + lgr %r3,%r1 # offset + la %r4,163(%r15) # pointer to temp buffer + lghi %r5,1 # 1 byte brasl %r14,skb_copy_bits # get data from skb xc 160(3,%r15),160(%r15) l %r5,160(%r15) # load result from temp buffer @@ -104,11 +107,11 @@ sk_load_byte_slow: lgr %r2,%r9 # restore %r2 br %r8 - /* A = (*(u8 *)(skb->data+K) & 0xf) << 2 */ + /* X = (*(u8 *)(skb->data+K) & 0xf) << 2 */ ENTRY(sk_load_byte_msh) llgfr %r1,%r3 # extend offset clr %r11,%r3 # hlen < offset ? - jle sk_load_byte_slow + jle sk_load_byte_msh_slow lhi %r12,0 ic %r12,0(%r1,%r10) # get byte from skb nill %r12,0x0f @@ -118,8 +121,9 @@ ENTRY(sk_load_byte_msh) sk_load_byte_msh_slow: lgr %r9,%r2 # save %r2 - lhi %r4,2 # 2 bytes - la %r5,162(%r15) # pointer to temp buffer + lgr %r3,%r1 # offset + la %r4,163(%r15) # pointer to temp buffer + lghi %r5,1 # 1 byte brasl %r14,skb_copy_bits # get data from skb xc 160(3,%r15),160(%r15) l %r12,160(%r15) # load result from temp buffer diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index c52ac77408ca..bbd1981cc150 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -431,8 +431,8 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, EMIT4_DISP(0x88500000, K); break; case BPF_ALU | BPF_NEG: /* A = -A */ - /* lnr %r5,%r5 */ - EMIT2(0x1155); + /* lcr %r5,%r5 */ + EMIT2(0x1355); break; case BPF_JMP | BPF_JA: /* ip += K */ offset = addrs[i + K] + jit->start - jit->prg; @@ -448,15 +448,12 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, mask = 0x800000; /* je */ kbranch: /* Emit compare if the branch targets are different */ if (filter->jt != filter->jf) { - if (K <= 16383) - /* chi %r5,<K> */ - EMIT4_IMM(0xa75e0000, K); - else if (test_facility(21)) + if (test_facility(21)) /* clfi %r5,<K> */ EMIT6_IMM(0xc25f0000, K); else - /* c %r5,<d(K)>(%r13) */ - EMIT4_DISP(0x5950d000, EMIT_CONST(K)); + /* cl %r5,<d(K)>(%r13) */ + EMIT4_DISP(0x5550d000, EMIT_CONST(K)); } branch: if (filter->jt == filter->jf) { if (filter->jt == 0) @@ -502,8 +499,8 @@ branch: if (filter->jt == filter->jf) { xbranch: /* Emit compare if the branch targets are different */ if (filter->jt != filter->jf) { jit->seen |= SEEN_XREG; - /* cr %r5,%r12 */ - EMIT2(0x195c); + /* clr %r5,%r12 */ + EMIT2(0x155c); } goto branch; case BPF_JMP | BPF_JSET | BPF_X: /* ip += (A & X) ? jt : jf */ diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c index 52238983527d..6860beb2a280 100644 --- a/arch/score/mm/fault.c +++ b/arch/score/mm/fault.c @@ -114,6 +114,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index 541dc6101508..a58fec9b55e0 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -353,6 +353,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, } else { if (fault & VM_FAULT_SIGBUS) do_sigbus(regs, error_code, address); + else if (fault & VM_FAULT_SIGSEGV) + bad_area(regs, error_code, address); else BUG(); } diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index b36365f49478..9ce5afe167ff 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -639,7 +639,10 @@ static void pci_claim_bus_resources(struct pci_bus *bus) (unsigned long long)r->end, (unsigned int)r->flags); - pci_claim_resource(dev, i); + if (pci_claim_resource(dev, i) == 0) + continue; + + pci_claim_bridge_resource(dev, i); } } diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index 908e8c17c902..70d817154fe8 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -249,6 +249,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 18fcd7167095..479823249429 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -446,6 +446,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c index f33e7c7a3bf7..7931eeeb649a 100644 --- a/arch/sparc/net/bpf_jit_comp.c +++ b/arch/sparc/net/bpf_jit_comp.c @@ -776,7 +776,7 @@ cond_branch: f_offset = addrs[i + filter[i].jf]; if (unlikely(proglen + ilen > oldproglen)) { pr_err("bpb_jit_compile fatal error\n"); kfree(addrs); - module_free(NULL, image); + module_memfree(image); return; } memcpy(image + proglen, temp, ilen); @@ -822,7 +822,7 @@ out: void bpf_jit_free(struct bpf_prog *fp) { if (fp->jited) - module_free(NULL, fp->bpf_func); + module_memfree(fp->bpf_func); bpf_prog_unlock_free(fp); } diff --git a/arch/tile/kernel/module.c b/arch/tile/kernel/module.c index 96447c9160a0..2305084c9b93 100644 --- a/arch/tile/kernel/module.c +++ b/arch/tile/kernel/module.c @@ -74,7 +74,7 @@ error: /* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) +void module_memfree(void *module_region) { vfree(module_region); @@ -83,7 +83,7 @@ void module_free(struct module *mod, void *module_region) 0, 0, 0, NULL, NULL, 0); /* - * FIXME: If module_region == mod->module_init, trim exception + * FIXME: Add module_arch_freeing_init to trim exception * table entries. */ } diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c index 565e25a98334..0f61a73534e6 100644 --- a/arch/tile/mm/fault.c +++ b/arch/tile/mm/fault.c @@ -442,6 +442,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 5678c3571e7c..209617302df8 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -80,6 +80,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) { goto out_of_memory; + } else if (fault & VM_FAULT_SIGSEGV) { + goto out; } else if (fault & VM_FAULT_SIGBUS) { err = -EACCES; goto out; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ba397bde7948..0dc9d0144a27 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -857,7 +857,7 @@ source "kernel/Kconfig.preempt" config X86_UP_APIC bool "Local APIC support on uniprocessors" - depends on X86_32 && !SMP && !X86_32_NON_STANDARD && !PCI_MSI + depends on X86_32 && !SMP && !X86_32_NON_STANDARD ---help--- A local APIC (Advanced Programmable Interrupt Controller) is an integrated interrupt controller in the CPU. If you have a single-CPU @@ -868,6 +868,10 @@ config X86_UP_APIC performance counters), and the NMI watchdog which detects hard lockups. +config X86_UP_APIC_MSI + def_bool y + select X86_UP_APIC if X86_32 && !SMP && !X86_32_NON_STANDARD && PCI_MSI + config X86_UP_IOAPIC bool "IO-APIC support on uniprocessors" depends on X86_UP_APIC diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index d999398928bc..ad754b4411f7 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -90,7 +90,7 @@ suffix-$(CONFIG_KERNEL_LZO) := lzo suffix-$(CONFIG_KERNEL_LZ4) := lz4 RUN_SIZE = $(shell $(OBJDUMP) -h vmlinux | \ - perl $(srctree)/arch/x86/tools/calc_run_size.pl) + $(CONFIG_SHELL) $(srctree)/arch/x86/tools/calc_run_size.sh) quiet_cmd_mkpiggy = MKPIGGY $@ cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false ) diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index dcc1c536cc21..a950864a64da 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -373,6 +373,8 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap, unsigned long output_len, unsigned long run_size) { + unsigned char *output_orig = output; + real_mode = rmode; sanitize_boot_params(real_mode); @@ -421,7 +423,12 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap, debug_putstr("\nDecompressing Linux... "); decompress(input_data, input_len, NULL, NULL, output, NULL, error); parse_elf(output); - handle_relocations(output, output_len); + /* + * 32-bit always performs relocations. 64-bit relocations are only + * needed if kASLR has chosen a different load address. + */ + if (!IS_ENABLED(CONFIG_X86_64) || output != output_orig) + handle_relocations(output, output_len); debug_putstr("done.\nBooting the kernel.\n"); return output; } diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c index a225a5ca1037..fd9f6b035b16 100644 --- a/arch/x86/crypto/sha-mb/sha1_mb.c +++ b/arch/x86/crypto/sha-mb/sha1_mb.c @@ -931,4 +931,4 @@ module_exit(sha1_mb_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, multi buffer accelerated"); -MODULE_ALIAS("sha1"); +MODULE_ALIAS_CRYPTO("sha1"); diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 0ab4f9fd2687..3a45668f6dc3 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -50,6 +50,7 @@ void acpi_pic_sci_set_trigger(unsigned int, u16); extern int (*__acpi_register_gsi)(struct device *dev, u32 gsi, int trigger, int polarity); +extern void (*__acpi_unregister_gsi)(u32 gsi); static inline void disable_acpi(void) { diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 50d033a8947d..a94b82e8f156 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -251,7 +251,8 @@ static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]; } -#define _LDT_empty(info) \ +/* This intentionally ignores lm, since 32-bit apps don't have that field. */ +#define LDT_empty(info) \ ((info)->base_addr == 0 && \ (info)->limit == 0 && \ (info)->contents == 0 && \ @@ -261,11 +262,18 @@ static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) (info)->seg_not_present == 1 && \ (info)->useable == 0) -#ifdef CONFIG_X86_64 -#define LDT_empty(info) (_LDT_empty(info) && ((info)->lm == 0)) -#else -#define LDT_empty(info) (_LDT_empty(info)) -#endif +/* Lots of programs expect an all-zero user_desc to mean "no segment at all". */ +static inline bool LDT_zero(const struct user_desc *info) +{ + return (info->base_addr == 0 && + info->limit == 0 && + info->contents == 0 && + info->read_exec_only == 0 && + info->seg_32bit == 0 && + info->limit_in_pages == 0 && + info->seg_not_present == 0 && + info->useable == 0); +} static inline void clear_LDT(void) { diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 40269a2bf6f9..4b75d591eb5e 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -130,7 +130,25 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm, static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long start, unsigned long end) { - mpx_notify_unmap(mm, vma, start, end); + /* + * mpx_notify_unmap() goes and reads a rarely-hot + * cacheline in the mm_struct. That can be expensive + * enough to be seen in profiles. + * + * The mpx_notify_unmap() call and its contents have been + * observed to affect munmap() performance on hardware + * where MPX is not present. + * + * The unlikely() optimizes for the fast case: no MPX + * in the CPU, or no MPX use in the process. Even if + * we get this wrong (in the unlikely event that MPX + * is widely enabled on some system) the overhead of + * MPX itself (reading bounds tables) is expected to + * overwhelm the overhead of getting this unlikely() + * consistently wrong. + */ + if (unlikely(cpu_feature_enabled(X86_FEATURE_MPX))) + mpx_notify_unmap(mm, vma, start, end); } #endif /* _ASM_X86_MMU_CONTEXT_H */ diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index d1626364a28a..b9e30daa0881 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -611,20 +611,20 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp) { - int irq; - - if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) { - *irqp = gsi; - } else { - mutex_lock(&acpi_ioapic_lock); - irq = mp_map_gsi_to_irq(gsi, - IOAPIC_MAP_ALLOC | IOAPIC_MAP_CHECK); - mutex_unlock(&acpi_ioapic_lock); - if (irq < 0) - return -1; - *irqp = irq; + int rc, irq, trigger, polarity; + + rc = acpi_get_override_irq(gsi, &trigger, &polarity); + if (rc == 0) { + trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE; + polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH; + irq = acpi_register_gsi(NULL, gsi, trigger, polarity); + if (irq >= 0) { + *irqp = irq; + return 0; + } } - return 0; + + return -1; } EXPORT_SYMBOL_GPL(acpi_gsi_to_irq); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index a450373e8e91..939155ffdece 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -107,6 +107,7 @@ static struct clocksource hyperv_cs = { .rating = 400, /* use this when running on Hyperv*/ .read = read_hv_clock, .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; static void __init ms_hyperv_init_platform(void) diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 944bf019b74f..498b6d967138 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2431,6 +2431,7 @@ __init int intel_pmu_init(void) break; case 55: /* 22nm Atom "Silvermont" */ + case 76: /* 14nm Atom "Airmont" */ case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */ memcpy(hw_cache_event_ids, slm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 3c895d480cd7..073983398364 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -568,8 +568,8 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { }; struct event_constraint intel_slm_pebs_event_constraints[] = { - /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x1), /* Allow all events as PEBS with no flags */ INTEL_ALL_EVENT_CONSTRAINT(0, 0x1), EVENT_CONSTRAINT_END diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index 673f930c700f..c4bb8b8e5017 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -103,6 +103,13 @@ static struct kobj_attribute format_attr_##_var = \ #define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */ +#define RAPL_EVENT_ATTR_STR(_name, v, str) \ +static struct perf_pmu_events_attr event_attr_##v = { \ + .attr = __ATTR(_name, 0444, rapl_sysfs_show, NULL), \ + .id = 0, \ + .event_str = str, \ +}; + struct rapl_pmu { spinlock_t lock; int hw_unit; /* 1/2^hw_unit Joule */ @@ -135,7 +142,7 @@ static inline u64 rapl_scale(u64 v) * or use ldexp(count, -32). * Watts = Joules/Time delta */ - return v << (32 - __this_cpu_read(rapl_pmu->hw_unit)); + return v << (32 - __this_cpu_read(rapl_pmu)->hw_unit); } static u64 rapl_event_update(struct perf_event *event) @@ -379,23 +386,36 @@ static struct attribute_group rapl_pmu_attr_group = { .attrs = rapl_pmu_attrs, }; -EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01"); -EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02"); -EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03"); -EVENT_ATTR_STR(energy-gpu , rapl_gpu, "event=0x04"); +static ssize_t rapl_sysfs_show(struct device *dev, + struct device_attribute *attr, + char *page) +{ + struct perf_pmu_events_attr *pmu_attr = \ + container_of(attr, struct perf_pmu_events_attr, attr); + + if (pmu_attr->event_str) + return sprintf(page, "%s", pmu_attr->event_str); + + return 0; +} + +RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01"); +RAPL_EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02"); +RAPL_EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03"); +RAPL_EVENT_ATTR_STR(energy-gpu , rapl_gpu, "event=0x04"); -EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules"); -EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules"); -EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules"); -EVENT_ATTR_STR(energy-gpu.unit , rapl_gpu_unit, "Joules"); +RAPL_EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules"); +RAPL_EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules"); +RAPL_EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules"); +RAPL_EVENT_ATTR_STR(energy-gpu.unit , rapl_gpu_unit, "Joules"); /* * we compute in 0.23 nJ increments regardless of MSR */ -EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10"); -EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10"); -EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10"); -EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10"); +RAPL_EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10"); +RAPL_EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10"); +RAPL_EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10"); +RAPL_EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10"); static struct attribute *rapl_events_srv_attr[] = { EVENT_PTR(rapl_cores), diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 10b8d3eaaf15..c635b8b49e93 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -840,7 +840,6 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id box->phys_id = phys_id; box->pci_dev = pdev; box->pmu = pmu; - uncore_box_init(box); pci_set_drvdata(pdev, box); raw_spin_lock(&uncore_box_lock); @@ -1004,10 +1003,8 @@ static int uncore_cpu_starting(int cpu) pmu = &type->pmus[j]; box = *per_cpu_ptr(pmu->box, cpu); /* called by uncore_cpu_init? */ - if (box && box->phys_id >= 0) { - uncore_box_init(box); + if (box && box->phys_id >= 0) continue; - } for_each_online_cpu(k) { exist = *per_cpu_ptr(pmu->box, k); @@ -1023,10 +1020,8 @@ static int uncore_cpu_starting(int cpu) } } - if (box) { + if (box) box->phys_id = phys_id; - uncore_box_init(box); - } } } return 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 863d9b02563e..6c8c1e7e69d8 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -257,6 +257,14 @@ static inline int uncore_num_counters(struct intel_uncore_box *box) return box->pmu->type->num_counters; } +static inline void uncore_box_init(struct intel_uncore_box *box) +{ + if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) { + if (box->pmu->type->ops->init_box) + box->pmu->type->ops->init_box(box); + } +} + static inline void uncore_disable_box(struct intel_uncore_box *box) { if (box->pmu->type->ops->disable_box) @@ -265,6 +273,8 @@ static inline void uncore_disable_box(struct intel_uncore_box *box) static inline void uncore_enable_box(struct intel_uncore_box *box) { + uncore_box_init(box); + if (box->pmu->type->ops->enable_box) box->pmu->type->ops->enable_box(box); } @@ -287,14 +297,6 @@ static inline u64 uncore_read_counter(struct intel_uncore_box *box, return box->pmu->type->ops->read_counter(box, event); } -static inline void uncore_box_init(struct intel_uncore_box *box) -{ - if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) { - if (box->pmu->type->ops->init_box) - box->pmu->type->ops->init_box(box); - } -} - static inline bool uncore_box_is_fake(struct intel_uncore_box *box) { return (box->phys_id < 0); diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 2142376dc8c6..8b7b0a51e742 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -674,7 +674,7 @@ static inline void *alloc_tramp(unsigned long size) } static inline void tramp_free(void *tramp) { - module_free(NULL, tramp); + module_memfree(tramp); } #else /* Trampolines can only be created if modules are supported */ diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 6307a0f0cf17..705ef8d48e2d 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -127,7 +127,7 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_puts(p, " Machine check polls\n"); #endif #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN) - seq_printf(p, "%*s: ", prec, "THR"); + seq_printf(p, "%*s: ", prec, "HYP"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_hv_callback_count); seq_puts(p, " Hypervisor callback interrupts\n"); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index f7e3cd50ece0..98f654d466e5 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1020,6 +1020,15 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) regs->flags &= ~X86_EFLAGS_IF; trace_hardirqs_off(); regs->ip = (unsigned long)(jp->entry); + + /* + * jprobes use jprobe_return() which skips the normal return + * path of the function, and this messes up the accounting of the + * function graph tracer to get messed up. + * + * Pause function graph tracing while performing the jprobe function. + */ + pause_graph_tracing(); return 1; } NOKPROBE_SYMBOL(setjmp_pre_handler); @@ -1048,24 +1057,25 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); u8 *addr = (u8 *) (regs->ip - 1); struct jprobe *jp = container_of(p, struct jprobe, kp); + void *saved_sp = kcb->jprobe_saved_sp; if ((addr > (u8 *) jprobe_return) && (addr < (u8 *) jprobe_return_end)) { - if (stack_addr(regs) != kcb->jprobe_saved_sp) { + if (stack_addr(regs) != saved_sp) { struct pt_regs *saved_regs = &kcb->jprobe_saved_regs; printk(KERN_ERR "current sp %p does not match saved sp %p\n", - stack_addr(regs), kcb->jprobe_saved_sp); + stack_addr(regs), saved_sp); printk(KERN_ERR "Saved registers for jprobe %p\n", jp); show_regs(saved_regs); printk(KERN_ERR "Current registers\n"); show_regs(regs); BUG(); } + /* It's OK to start function graph tracing again */ + unpause_graph_tracing(); *regs = kcb->jprobe_saved_regs; - memcpy((kprobe_opcode_t *)(kcb->jprobe_saved_sp), - kcb->jprobes_stack, - MIN_STACK_SIZE(kcb->jprobe_saved_sp)); + memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp)); preempt_enable_no_resched(); return 1; } diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 4e942f31b1a7..7fc5e843f247 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -29,7 +29,28 @@ static int get_free_idx(void) static bool tls_desc_okay(const struct user_desc *info) { - if (LDT_empty(info)) + /* + * For historical reasons (i.e. no one ever documented how any + * of the segmentation APIs work), user programs can and do + * assume that a struct user_desc that's all zeros except for + * entry_number means "no segment at all". This never actually + * worked. In fact, up to Linux 3.19, a struct user_desc like + * this would create a 16-bit read-write segment with base and + * limit both equal to zero. + * + * That was close enough to "no segment at all" until we + * hardened this function to disallow 16-bit TLS segments. Fix + * it up by interpreting these zeroed segments the way that they + * were almost certainly intended to be interpreted. + * + * The correct way to ask for "no segment at all" is to specify + * a user_desc that satisfies LDT_empty. To keep everything + * working, we accept both. + * + * Note that there's a similar kludge in modify_ldt -- look at + * the distinction between modes 1 and 0x11. + */ + if (LDT_empty(info) || LDT_zero(info)) return true; /* @@ -71,7 +92,7 @@ static void set_tls_desc(struct task_struct *p, int idx, cpu = get_cpu(); while (n-- > 0) { - if (LDT_empty(info)) + if (LDT_empty(info) || LDT_zero(info)) desc->a = desc->b = 0; else fill_ldt(desc, info); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index b7e50bba3bbb..505449700e0c 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -617,7 +617,7 @@ static unsigned long quick_pit_calibrate(void) goto success; } } - pr_err("Fast TSC calibration failed\n"); + pr_info("Fast TSC calibration failed\n"); return 0; success: diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 169b09d76ddd..de12c1d379f1 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2348,7 +2348,7 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) * Not recognized on AMD in compat mode (but is recognized in legacy * mode). */ - if ((ctxt->mode == X86EMUL_MODE_PROT32) && (efer & EFER_LMA) + if ((ctxt->mode != X86EMUL_MODE_PROT64) && (efer & EFER_LMA) && !vendor_intel(ctxt)) return emulate_ud(ctxt); @@ -2359,25 +2359,13 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) setup_syscalls_segments(ctxt, &cs, &ss); ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data); - switch (ctxt->mode) { - case X86EMUL_MODE_PROT32: - if ((msr_data & 0xfffc) == 0x0) - return emulate_gp(ctxt, 0); - break; - case X86EMUL_MODE_PROT64: - if (msr_data == 0x0) - return emulate_gp(ctxt, 0); - break; - default: - break; - } + if ((msr_data & 0xfffc) == 0x0) + return emulate_gp(ctxt, 0); ctxt->eflags &= ~(EFLG_VM | EFLG_IF); - cs_sel = (u16)msr_data; - cs_sel &= ~SELECTOR_RPL_MASK; + cs_sel = (u16)msr_data & ~SELECTOR_RPL_MASK; ss_sel = cs_sel + 8; - ss_sel &= ~SELECTOR_RPL_MASK; - if (ctxt->mode == X86EMUL_MODE_PROT64 || (efer & EFER_LMA)) { + if (efer & EFER_LMA) { cs.d = 0; cs.l = 1; } @@ -2386,10 +2374,11 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); ops->get_msr(ctxt, MSR_IA32_SYSENTER_EIP, &msr_data); - ctxt->_eip = msr_data; + ctxt->_eip = (efer & EFER_LMA) ? msr_data : (u32)msr_data; ops->get_msr(ctxt, MSR_IA32_SYSENTER_ESP, &msr_data); - *reg_write(ctxt, VCPU_REGS_RSP) = msr_data; + *reg_write(ctxt, VCPU_REGS_RSP) = (efer & EFER_LMA) ? msr_data : + (u32)msr_data; return X86EMUL_CONTINUE; } @@ -3791,8 +3780,8 @@ static const struct opcode group5[] = { }; static const struct opcode group6[] = { - DI(Prot, sldt), - DI(Prot, str), + DI(Prot | DstMem, sldt), + DI(Prot | DstMem, str), II(Prot | Priv | SrcMem16, em_lldt, lldt), II(Prot | Priv | SrcMem16, em_ltr, ltr), N, N, N, N, diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4f0c0b954686..d52dcf0776ea 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -192,6 +192,9 @@ static void recalculate_apic_map(struct kvm *kvm) u16 cid, lid; u32 ldr, aid; + if (!kvm_apic_present(vcpu)) + continue; + aid = kvm_apic_id(apic); ldr = kvm_apic_get_reg(apic, APIC_LDR); cid = apic_cluster_id(new, ldr); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 38dcec403b46..e3ff27a5b634 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -898,6 +898,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| VM_FAULT_HWPOISON_LARGE)) do_sigbus(regs, error_code, address, fault); + else if (fault & VM_FAULT_SIGSEGV) + bad_area_nosemaphore(regs, error_code, address); else BUG(); } diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 08a7d313538a..079c3b6a3ff1 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -43,7 +43,7 @@ uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = { [_PAGE_CACHE_MODE_WT] = _PAGE_PCD, [_PAGE_CACHE_MODE_WP] = _PAGE_PCD, }; -EXPORT_SYMBOL_GPL(__cachemode2pte_tbl); +EXPORT_SYMBOL(__cachemode2pte_tbl); uint8_t __pte2cachemode_tbl[8] = { [__pte2cm_idx(0)] = _PAGE_CACHE_MODE_WB, [__pte2cm_idx(_PAGE_PWT)] = _PAGE_CACHE_MODE_WC, @@ -54,7 +54,7 @@ uint8_t __pte2cachemode_tbl[8] = { [__pte2cm_idx(_PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC, }; -EXPORT_SYMBOL_GPL(__pte2cachemode_tbl); +EXPORT_SYMBOL(__pte2cachemode_tbl); static unsigned long __initdata pgt_buf_start; static unsigned long __initdata pgt_buf_end; diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index 67ebf5751222..c439ec478216 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -349,6 +349,12 @@ static __user void *task_get_bounds_dir(struct task_struct *tsk) return MPX_INVALID_BOUNDS_DIR; /* + * 32-bit binaries on 64-bit kernels are currently + * unsupported. + */ + if (IS_ENABLED(CONFIG_X86_64) && test_thread_flag(TIF_IA32)) + return MPX_INVALID_BOUNDS_DIR; + /* * The bounds directory pointer is stored in a register * only accessible if we first do an xsave. */ diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index edf299c8ff6c..7ac68698406c 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -234,8 +234,13 @@ void pat_init(void) PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC); /* Boot CPU check */ - if (!boot_pat_state) + if (!boot_pat_state) { rdmsrl(MSR_IA32_CR_PAT, boot_pat_state); + if (!boot_pat_state) { + pat_disable("PAT read returns always zero, disabled."); + return; + } + } wrmsrl(MSR_IA32_CR_PAT, pat); diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 9b18ef315a55..349c0d32cc0b 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -216,7 +216,7 @@ static void pcibios_allocate_bridge_resources(struct pci_dev *dev) continue; if (r->parent) /* Already allocated */ continue; - if (!r->start || pci_claim_resource(dev, idx) < 0) { + if (!r->start || pci_claim_bridge_resource(dev, idx) < 0) { /* * Something is wrong with the region. * Invalidate the resource to prevent diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index c489ef2c1a39..9098d880c476 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -458,6 +458,7 @@ int __init pci_xen_hvm_init(void) * just how GSIs get registered. */ __acpi_register_gsi = acpi_register_gsi_xen_hvm; + __acpi_unregister_gsi = NULL; #endif #ifdef CONFIG_PCI_MSI @@ -471,52 +472,6 @@ int __init pci_xen_hvm_init(void) } #ifdef CONFIG_XEN_DOM0 -static __init void xen_setup_acpi_sci(void) -{ - int rc; - int trigger, polarity; - int gsi = acpi_sci_override_gsi; - int irq = -1; - int gsi_override = -1; - - if (!gsi) - return; - - rc = acpi_get_override_irq(gsi, &trigger, &polarity); - if (rc) { - printk(KERN_WARNING "xen: acpi_get_override_irq failed for acpi" - " sci, rc=%d\n", rc); - return; - } - trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE; - polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH; - - printk(KERN_INFO "xen: sci override: global_irq=%d trigger=%d " - "polarity=%d\n", gsi, trigger, polarity); - - /* Before we bind the GSI to a Linux IRQ, check whether - * we need to override it with bus_irq (IRQ) value. Usually for - * IRQs below IRQ_LEGACY_IRQ this holds IRQ == GSI, as so: - * ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 9 low level) - * but there are oddballs where the IRQ != GSI: - * ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 20 low level) - * which ends up being: gsi_to_irq[9] == 20 - * (which is what acpi_gsi_to_irq ends up calling when starting the - * the ACPI interpreter and keels over since IRQ 9 has not been - * setup as we had setup IRQ 20 for it). - */ - if (acpi_gsi_to_irq(gsi, &irq) == 0) { - /* Use the provided value if it's valid. */ - if (irq >= 0) - gsi_override = irq; - } - - gsi = xen_register_gsi(gsi, gsi_override, trigger, polarity); - printk(KERN_INFO "xen: acpi sci %d\n", gsi); - - return; -} - int __init pci_xen_initial_domain(void) { int irq; @@ -527,8 +482,8 @@ int __init pci_xen_initial_domain(void) x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs; pci_msi_ignore_mask = 1; #endif - xen_setup_acpi_sci(); __acpi_register_gsi = acpi_register_gsi_xen; + __acpi_unregister_gsi = NULL; /* Pre-allocate legacy irqs */ for (irq = 0; irq < nr_legacy_irqs(); irq++) { int trigger, polarity; diff --git a/arch/x86/tools/calc_run_size.pl b/arch/x86/tools/calc_run_size.pl deleted file mode 100644 index 23210baade2d..000000000000 --- a/arch/x86/tools/calc_run_size.pl +++ /dev/null @@ -1,39 +0,0 @@ -#!/usr/bin/perl -# -# Calculate the amount of space needed to run the kernel, including room for -# the .bss and .brk sections. -# -# Usage: -# objdump -h a.out | perl calc_run_size.pl -use strict; - -my $mem_size = 0; -my $file_offset = 0; - -my $sections=" *[0-9]+ \.(?:bss|brk) +"; -while (<>) { - if (/^$sections([0-9a-f]+) +(?:[0-9a-f]+ +){2}([0-9a-f]+)/) { - my $size = hex($1); - my $offset = hex($2); - $mem_size += $size; - if ($file_offset == 0) { - $file_offset = $offset; - } elsif ($file_offset != $offset) { - # BFD linker shows the same file offset in ELF. - # Gold linker shows them as consecutive. - next if ($file_offset + $mem_size == $offset + $size); - - printf STDERR "file_offset: 0x%lx\n", $file_offset; - printf STDERR "mem_size: 0x%lx\n", $mem_size; - printf STDERR "offset: 0x%lx\n", $offset; - printf STDERR "size: 0x%lx\n", $size; - - die ".bss and .brk are non-contiguous\n"; - } - } -} - -if ($file_offset == 0) { - die "Never found .bss or .brk file offset\n"; -} -printf("%d\n", $mem_size + $file_offset); diff --git a/arch/x86/tools/calc_run_size.sh b/arch/x86/tools/calc_run_size.sh new file mode 100644 index 000000000000..1a4c17bb3910 --- /dev/null +++ b/arch/x86/tools/calc_run_size.sh @@ -0,0 +1,42 @@ +#!/bin/sh +# +# Calculate the amount of space needed to run the kernel, including room for +# the .bss and .brk sections. +# +# Usage: +# objdump -h a.out | sh calc_run_size.sh + +NUM='\([0-9a-fA-F]*[ \t]*\)' +OUT=$(sed -n 's/^[ \t0-9]*.b[sr][sk][ \t]*'"$NUM$NUM$NUM$NUM"'.*/\1\4/p') +if [ -z "$OUT" ] ; then + echo "Never found .bss or .brk file offset" >&2 + exit 1 +fi + +OUT=$(echo ${OUT# }) +sizeA=$(printf "%d" 0x${OUT%% *}) +OUT=${OUT#* } +offsetA=$(printf "%d" 0x${OUT%% *}) +OUT=${OUT#* } +sizeB=$(printf "%d" 0x${OUT%% *}) +OUT=${OUT#* } +offsetB=$(printf "%d" 0x${OUT%% *}) + +run_size=$(( $offsetA + $sizeA + $sizeB )) + +# BFD linker shows the same file offset in ELF. +if [ "$offsetA" -ne "$offsetB" ] ; then + # Gold linker shows them as consecutive. + endB=$(( $offsetB + $sizeB )) + if [ "$endB" != "$run_size" ] ; then + printf "sizeA: 0x%x\n" $sizeA >&2 + printf "offsetA: 0x%x\n" $offsetA >&2 + printf "sizeB: 0x%x\n" $sizeB >&2 + printf "offsetB: 0x%x\n" $offsetB >&2 + echo ".bss and .brk are non-contiguous" >&2 + exit 1 + fi +fi + +printf "%d\n" $run_size +exit 0 diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 6bf3a13e3e0f..78a881b7fc41 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -40,6 +40,7 @@ #include <xen/interface/physdev.h> #include <xen/interface/vcpu.h> #include <xen/interface/memory.h> +#include <xen/interface/nmi.h> #include <xen/interface/xen-mca.h> #include <xen/features.h> #include <xen/page.h> @@ -66,6 +67,7 @@ #include <asm/reboot.h> #include <asm/stackprotector.h> #include <asm/hypervisor.h> +#include <asm/mach_traps.h> #include <asm/mwait.h> #include <asm/pci_x86.h> #include <asm/pat.h> @@ -1351,6 +1353,21 @@ static const struct machine_ops xen_machine_ops __initconst = { .emergency_restart = xen_emergency_restart, }; +static unsigned char xen_get_nmi_reason(void) +{ + unsigned char reason = 0; + + /* Construct a value which looks like it came from port 0x61. */ + if (test_bit(_XEN_NMIREASON_io_error, + &HYPERVISOR_shared_info->arch.nmi_reason)) + reason |= NMI_REASON_IOCHK; + if (test_bit(_XEN_NMIREASON_pci_serr, + &HYPERVISOR_shared_info->arch.nmi_reason)) + reason |= NMI_REASON_SERR; + + return reason; +} + static void __init xen_boot_params_init_edd(void) { #if IS_ENABLED(CONFIG_EDD) @@ -1535,9 +1552,12 @@ asmlinkage __visible void __init xen_start_kernel(void) pv_info = xen_info; pv_init_ops = xen_init_ops; pv_apic_ops = xen_apic_ops; - if (!xen_pvh_domain()) + if (!xen_pvh_domain()) { pv_cpu_ops = xen_cpu_ops; + x86_platform.get_nmi_reason = xen_get_nmi_reason; + } + if (xen_feature(XENFEAT_auto_translated_physmap)) x86_init.resources.memory_setup = xen_auto_xlated_memory_setup; else diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index edbc7a63fd73..70fb5075c901 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -167,10 +167,13 @@ static void * __ref alloc_p2m_page(void) return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT); } -/* Only to be called in case of a race for a page just allocated! */ -static void free_p2m_page(void *p) +static void __ref free_p2m_page(void *p) { - BUG_ON(!slab_is_available()); + if (unlikely(!slab_is_available())) { + free_bootmem((unsigned long)p, PAGE_SIZE); + return; + } + free_page((unsigned long)p); } @@ -375,7 +378,7 @@ static void __init xen_rebuild_p2m_list(unsigned long *p2m) p2m_missing_pte : p2m_identity_pte; for (i = 0; i < PMDS_PER_MID_PAGE; i++) { pmdp = populate_extra_pmd( - (unsigned long)(p2m + pfn + i * PTRS_PER_PTE)); + (unsigned long)(p2m + pfn) + i * PMD_SIZE); set_pmd(pmdp, __pmd(__pa(ptep) | _KERNPG_TABLE)); } } @@ -436,10 +439,9 @@ EXPORT_SYMBOL_GPL(get_phys_to_machine); * a new pmd is to replace p2m_missing_pte or p2m_identity_pte by a individual * pmd. In case of PAE/x86-32 there are multiple pmds to allocate! */ -static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *ptep, pte_t *pte_pg) +static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *pte_pg) { pte_t *ptechk; - pte_t *pteret = ptep; pte_t *pte_newpg[PMDS_PER_MID_PAGE]; pmd_t *pmdp; unsigned int level; @@ -473,8 +475,6 @@ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *ptep, pte_t *pte_pg) if (ptechk == pte_pg) { set_pmd(pmdp, __pmd(__pa(pte_newpg[i]) | _KERNPG_TABLE)); - if (vaddr == (addr & ~(PMD_SIZE - 1))) - pteret = pte_offset_kernel(pmdp, addr); pte_newpg[i] = NULL; } @@ -488,7 +488,7 @@ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *ptep, pte_t *pte_pg) vaddr += PMD_SIZE; } - return pteret; + return lookup_address(addr, &level); } /* @@ -517,7 +517,7 @@ static bool alloc_p2m(unsigned long pfn) if (pte_pg == p2m_missing_pte || pte_pg == p2m_identity_pte) { /* PMD level is missing, allocate a new one */ - ptep = alloc_p2m_pmd(addr, ptep, pte_pg); + ptep = alloc_p2m_pmd(addr, pte_pg); if (!ptep) return false; } diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index dfd77dec8e2b..865e56cea7a0 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -140,7 +140,7 @@ static void __init xen_del_extra_mem(u64 start, u64 size) unsigned long __ref xen_chk_extra_mem(unsigned long pfn) { int i; - unsigned long addr = PFN_PHYS(pfn); + phys_addr_t addr = PFN_PHYS(pfn); for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { if (addr >= xen_extra_mem[i].start && @@ -160,6 +160,8 @@ void __init xen_inv_extra_mem(void) int i; for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { + if (!xen_extra_mem[i].size) + continue; pfn_s = PFN_DOWN(xen_extra_mem[i].start); pfn_e = PFN_UP(xen_extra_mem[i].start + xen_extra_mem[i].size); for (pfn = pfn_s; pfn < pfn_e; pfn++) @@ -229,15 +231,14 @@ static int __init xen_free_mfn(unsigned long mfn) * as a fallback if the remapping fails. */ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn, - unsigned long end_pfn, unsigned long nr_pages, unsigned long *identity, - unsigned long *released) + unsigned long end_pfn, unsigned long nr_pages, unsigned long *released) { - unsigned long len = 0; unsigned long pfn, end; int ret; WARN_ON(start_pfn > end_pfn); + /* Release pages first. */ end = min(end_pfn, nr_pages); for (pfn = start_pfn; pfn < end; pfn++) { unsigned long mfn = pfn_to_mfn(pfn); @@ -250,16 +251,14 @@ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn, WARN(ret != 1, "Failed to release pfn %lx err=%d\n", pfn, ret); if (ret == 1) { + (*released)++; if (!__set_phys_to_machine(pfn, INVALID_P2M_ENTRY)) break; - len++; } else break; } - /* Need to release pages first */ - *released += len; - *identity += set_phys_range_identity(start_pfn, end_pfn); + set_phys_range_identity(start_pfn, end_pfn); } /* @@ -287,7 +286,7 @@ static void __init xen_update_mem_tables(unsigned long pfn, unsigned long mfn) } /* Update kernel mapping, but not for highmem. */ - if ((pfn << PAGE_SHIFT) >= __pa(high_memory)) + if (pfn >= PFN_UP(__pa(high_memory - 1))) return; if (HYPERVISOR_update_va_mapping((unsigned long)__va(pfn << PAGE_SHIFT), @@ -318,7 +317,6 @@ static void __init xen_do_set_identity_and_remap_chunk( unsigned long ident_pfn_iter, remap_pfn_iter; unsigned long ident_end_pfn = start_pfn + size; unsigned long left = size; - unsigned long ident_cnt = 0; unsigned int i, chunk; WARN_ON(size == 0); @@ -347,8 +345,7 @@ static void __init xen_do_set_identity_and_remap_chunk( xen_remap_mfn = mfn; /* Set identity map */ - ident_cnt += set_phys_range_identity(ident_pfn_iter, - ident_pfn_iter + chunk); + set_phys_range_identity(ident_pfn_iter, ident_pfn_iter + chunk); left -= chunk; } @@ -371,7 +368,7 @@ static void __init xen_do_set_identity_and_remap_chunk( static unsigned long __init xen_set_identity_and_remap_chunk( const struct e820entry *list, size_t map_size, unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages, unsigned long remap_pfn, - unsigned long *identity, unsigned long *released) + unsigned long *released, unsigned long *remapped) { unsigned long pfn; unsigned long i = 0; @@ -386,8 +383,7 @@ static unsigned long __init xen_set_identity_and_remap_chunk( /* Do not remap pages beyond the current allocation */ if (cur_pfn >= nr_pages) { /* Identity map remaining pages */ - *identity += set_phys_range_identity(cur_pfn, - cur_pfn + size); + set_phys_range_identity(cur_pfn, cur_pfn + size); break; } if (cur_pfn + size > nr_pages) @@ -398,7 +394,7 @@ static unsigned long __init xen_set_identity_and_remap_chunk( if (!remap_range_size) { pr_warning("Unable to find available pfn range, not remapping identity pages\n"); xen_set_identity_and_release_chunk(cur_pfn, - cur_pfn + left, nr_pages, identity, released); + cur_pfn + left, nr_pages, released); break; } /* Adjust size to fit in current e820 RAM region */ @@ -410,7 +406,7 @@ static unsigned long __init xen_set_identity_and_remap_chunk( /* Update variables to reflect new mappings. */ i += size; remap_pfn += size; - *identity += size; + *remapped += size; } /* @@ -427,13 +423,13 @@ static unsigned long __init xen_set_identity_and_remap_chunk( static void __init xen_set_identity_and_remap( const struct e820entry *list, size_t map_size, unsigned long nr_pages, - unsigned long *released) + unsigned long *released, unsigned long *remapped) { phys_addr_t start = 0; - unsigned long identity = 0; unsigned long last_pfn = nr_pages; const struct e820entry *entry; unsigned long num_released = 0; + unsigned long num_remapped = 0; int i; /* @@ -460,14 +456,14 @@ static void __init xen_set_identity_and_remap( last_pfn = xen_set_identity_and_remap_chunk( list, map_size, start_pfn, end_pfn, nr_pages, last_pfn, - &identity, &num_released); + &num_released, &num_remapped); start = end; } } *released = num_released; + *remapped = num_remapped; - pr_info("Set %ld page(s) to 1-1 mapping\n", identity); pr_info("Released %ld page(s)\n", num_released); } @@ -586,6 +582,7 @@ char * __init xen_memory_setup(void) struct xen_memory_map memmap; unsigned long max_pages; unsigned long extra_pages = 0; + unsigned long remapped_pages; int i; int op; @@ -635,9 +632,10 @@ char * __init xen_memory_setup(void) * underlying RAM. */ xen_set_identity_and_remap(map, memmap.nr_entries, max_pfn, - &xen_released_pages); + &xen_released_pages, &remapped_pages); extra_pages += xen_released_pages; + extra_pages += remapped_pages; /* * Clamp the amount of extra memory to a EXTRA_MEM_RATIO diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index f473d268d387..69087341d9ae 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -391,7 +391,7 @@ static const struct clock_event_device *xen_clockevent = struct xen_clock_event_device { struct clock_event_device evt; - char *name; + char name[16]; }; static DEFINE_PER_CPU(struct xen_clock_event_device, xen_clock_events) = { .evt.irq = -1 }; @@ -420,46 +420,38 @@ void xen_teardown_timer(int cpu) if (evt->irq >= 0) { unbind_from_irqhandler(evt->irq, NULL); evt->irq = -1; - kfree(per_cpu(xen_clock_events, cpu).name); - per_cpu(xen_clock_events, cpu).name = NULL; } } void xen_setup_timer(int cpu) { - char *name; - struct clock_event_device *evt; + struct xen_clock_event_device *xevt = &per_cpu(xen_clock_events, cpu); + struct clock_event_device *evt = &xevt->evt; int irq; - evt = &per_cpu(xen_clock_events, cpu).evt; WARN(evt->irq >= 0, "IRQ%d for CPU%d is already allocated\n", evt->irq, cpu); if (evt->irq >= 0) xen_teardown_timer(cpu); printk(KERN_INFO "installing Xen timer for CPU %d\n", cpu); - name = kasprintf(GFP_KERNEL, "timer%d", cpu); - if (!name) - name = "<timer kasprintf failed>"; + snprintf(xevt->name, sizeof(xevt->name), "timer%d", cpu); irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt, IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER| IRQF_FORCE_RESUME|IRQF_EARLY_RESUME, - name, NULL); + xevt->name, NULL); (void)xen_set_irq_priority(irq, XEN_IRQ_PRIORITY_MAX); memcpy(evt, xen_clockevent, sizeof(*evt)); evt->cpumask = cpumask_of(cpu); evt->irq = irq; - per_cpu(xen_clock_events, cpu).name = name; } void xen_setup_cpu_clockevents(void) { - BUG_ON(preemptible()); - clockevents_register_device(this_cpu_ptr(&xen_clock_events.evt)); } diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index b57c4f91f487..9e3571a6535c 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -117,6 +117,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); |