diff options
Diffstat (limited to 'arch')
69 files changed, 694 insertions, 323 deletions
diff --git a/arch/alpha/kernel/module.c b/arch/alpha/kernel/module.c index 2fd00b7077e4..936bc8f89a67 100644 --- a/arch/alpha/kernel/module.c +++ b/arch/alpha/kernel/module.c @@ -160,7 +160,7 @@ apply_relocate_add(Elf64_Shdr *sechdrs, const char *strtab, /* The small sections were sorted to the end of the segment. The following should definitely cover them. */ - gp = (u64)me->module_core + me->core_size - 0x8000; + gp = (u64)me->core_layout.base + me->core_layout.size - 0x8000; got = sechdrs[me->arch.gotsecindex].sh_addr; for (i = 0; i < n; i++) { diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 93c6ea52b671..e0034a6656ef 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -372,8 +372,8 @@ void *unwind_add_table(struct module *module, const void *table_start, return NULL; init_unwind_table(table, module->name, - module->module_core, module->core_size, - module->module_init, module->init_size, + module->core_layout.base, module->core_layout.size, + module->init_layout.base, module->init_layout.size, table_start, table_size, NULL, 0); diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi index feb9d34b239c..f818ea483aeb 100644 --- a/arch/arm/boot/dts/imx27.dtsi +++ b/arch/arm/boot/dts/imx27.dtsi @@ -486,7 +486,10 @@ compatible = "fsl,imx27-usb"; reg = <0x10024000 0x200>; interrupts = <56>; - clocks = <&clks IMX27_CLK_USB_IPG_GATE>; + clocks = <&clks IMX27_CLK_USB_IPG_GATE>, + <&clks IMX27_CLK_USB_AHB_GATE>, + <&clks IMX27_CLK_USB_DIV>; + clock-names = "ipg", "ahb", "per"; fsl,usbmisc = <&usbmisc 0>; status = "disabled"; }; @@ -495,7 +498,10 @@ compatible = "fsl,imx27-usb"; reg = <0x10024200 0x200>; interrupts = <54>; - clocks = <&clks IMX27_CLK_USB_IPG_GATE>; + clocks = <&clks IMX27_CLK_USB_IPG_GATE>, + <&clks IMX27_CLK_USB_AHB_GATE>, + <&clks IMX27_CLK_USB_DIV>; + clock-names = "ipg", "ahb", "per"; fsl,usbmisc = <&usbmisc 1>; dr_mode = "host"; status = "disabled"; @@ -505,7 +511,10 @@ compatible = "fsl,imx27-usb"; reg = <0x10024400 0x200>; interrupts = <55>; - clocks = <&clks IMX27_CLK_USB_IPG_GATE>; + clocks = <&clks IMX27_CLK_USB_IPG_GATE>, + <&clks IMX27_CLK_USB_AHB_GATE>, + <&clks IMX27_CLK_USB_DIV>; + clock-names = "ipg", "ahb", "per"; fsl,usbmisc = <&usbmisc 2>; dr_mode = "host"; status = "disabled"; @@ -515,7 +524,6 @@ #index-cells = <1>; compatible = "fsl,imx27-usbmisc"; reg = <0x10024600 0x200>; - clocks = <&clks IMX27_CLK_USB_AHB_GATE>; }; sahara2: sahara@10025000 { diff --git a/arch/arm/kernel/module-plts.c b/arch/arm/kernel/module-plts.c index 097e2e201b9f..0c7efc3446c0 100644 --- a/arch/arm/kernel/module-plts.c +++ b/arch/arm/kernel/module-plts.c @@ -32,7 +32,7 @@ struct plt_entries { static bool in_init(const struct module *mod, u32 addr) { - return addr - (u32)mod->module_init < mod->init_size; + return addr - (u32)mod->init_layout.base < mod->init_layout.size; } u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val) diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index eab83b2435b8..e06fd299de08 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -564,17 +564,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) vcpu_sleep(vcpu); /* - * Disarming the background timer must be done in a - * preemptible context, as this call may sleep. - */ - kvm_timer_flush_hwstate(vcpu); - - /* * Preparing the interrupts to be injected also * involves poking the GIC, which must be done in a * non-preemptible context. */ preempt_disable(); + kvm_timer_flush_hwstate(vcpu); kvm_vgic_flush_hwstate(vcpu); local_irq_disable(); diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 6984342da13d..7dace909d5cf 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -98,6 +98,11 @@ static void kvm_flush_dcache_pud(pud_t pud) __kvm_flush_dcache_pud(pud); } +static bool kvm_is_device_pfn(unsigned long pfn) +{ + return !pfn_valid(pfn); +} + /** * stage2_dissolve_pmd() - clear and flush huge PMD entry * @kvm: pointer to kvm structure. @@ -213,7 +218,7 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd, 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) + if (!kvm_is_device_pfn(__phys_to_pfn(addr))) kvm_flush_dcache_pte(old_pte); put_page(virt_to_page(pte)); @@ -305,8 +310,7 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd, pte = pte_offset_kernel(pmd, addr); do { - if (!pte_none(*pte) && - (pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE) + if (!pte_none(*pte) && !kvm_is_device_pfn(__phys_to_pfn(addr))) kvm_flush_dcache_pte(*pte); } while (pte++, addr += PAGE_SIZE, addr != end); } @@ -1037,11 +1041,6 @@ static bool kvm_is_write_fault(struct kvm_vcpu *vcpu) return kvm_vcpu_dabt_iswrite(vcpu); } -static bool kvm_is_device_pfn(unsigned long pfn) -{ - return !pfn_valid(pfn); -} - /** * stage2_wp_ptes - write protect PMD range * @pmd: pointer to pmd entry diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 9ac16a482ff1..e55848c1edf4 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -316,6 +316,27 @@ config ARM64_ERRATUM_832075 If unsure, say Y. +config ARM64_ERRATUM_834220 + bool "Cortex-A57: 834220: Stage 2 translation fault might be incorrectly reported in presence of a Stage 1 fault" + depends on KVM + default y + help + This option adds an alternative code sequence to work around ARM + erratum 834220 on Cortex-A57 parts up to r1p2. + + Affected Cortex-A57 parts might report a Stage 2 translation + fault as the result of a Stage 1 fault for load crossing a + page boundary when there is a permission or device memory + alignment fault at Stage 1 and a translation fault at Stage 2. + + The workaround is to verify that the Stage 1 translation + doesn't generate a fault before handling the Stage 2 fault. + Please note that this does not necessarily enable the workaround, + as it depends on the alternative framework, which will only patch + the kernel if an affected CPU is detected. + + If unsure, say Y. + config ARM64_ERRATUM_845719 bool "Cortex-A53: 845719: a load might read incorrect data" depends on COMPAT diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c index ce47792a983d..f7bd9bf0bbb3 100644 --- a/arch/arm64/crypto/aes-ce-cipher.c +++ b/arch/arm64/crypto/aes-ce-cipher.c @@ -237,7 +237,7 @@ EXPORT_SYMBOL(ce_aes_setkey); static struct crypto_alg aes_alg = { .cra_name = "aes", .cra_driver_name = "aes-ce", - .cra_priority = 300, + .cra_priority = 250, .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = AES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct crypto_aes_ctx), diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 624f9679f4b0..9622eb48f894 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -64,27 +64,31 @@ do { \ #define smp_load_acquire(p) \ ({ \ - typeof(*p) ___p1; \ + union { typeof(*p) __val; char __c[1]; } __u; \ compiletime_assert_atomic_type(*p); \ switch (sizeof(*p)) { \ case 1: \ asm volatile ("ldarb %w0, %1" \ - : "=r" (___p1) : "Q" (*p) : "memory"); \ + : "=r" (*(__u8 *)__u.__c) \ + : "Q" (*p) : "memory"); \ break; \ case 2: \ asm volatile ("ldarh %w0, %1" \ - : "=r" (___p1) : "Q" (*p) : "memory"); \ + : "=r" (*(__u16 *)__u.__c) \ + : "Q" (*p) : "memory"); \ break; \ case 4: \ asm volatile ("ldar %w0, %1" \ - : "=r" (___p1) : "Q" (*p) : "memory"); \ + : "=r" (*(__u32 *)__u.__c) \ + : "Q" (*p) : "memory"); \ break; \ case 8: \ asm volatile ("ldar %0, %1" \ - : "=r" (___p1) : "Q" (*p) : "memory"); \ + : "=r" (*(__u64 *)__u.__c) \ + : "Q" (*p) : "memory"); \ break; \ } \ - ___p1; \ + __u.__val; \ }) #define read_barrier_depends() do { } while(0) diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index 7fbed6919b54..eb8432bb82b8 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -23,7 +23,6 @@ */ #include <linux/types.h> #include <linux/sched.h> -#include <linux/ptrace.h> #define COMPAT_USER_HZ 100 #ifdef __AARCH64EB__ @@ -234,7 +233,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -#define compat_user_stack_pointer() (user_stack_pointer(current_pt_regs())) +#define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current))) static inline void __user *arch_compat_alloc_user_space(long len) { diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 11d5bb0fdd54..52722ee73dba 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -29,8 +29,9 @@ #define ARM64_HAS_PAN 4 #define ARM64_HAS_LSE_ATOMICS 5 #define ARM64_WORKAROUND_CAVIUM_23154 6 +#define ARM64_WORKAROUND_834220 7 -#define ARM64_NCAPS 7 +#define ARM64_NCAPS 8 #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h index 54d0ead41afc..61e08f360e31 100644 --- a/arch/arm64/include/asm/dma-mapping.h +++ b/arch/arm64/include/asm/dma-mapping.h @@ -18,7 +18,6 @@ #ifdef __KERNEL__ -#include <linux/acpi.h> #include <linux/types.h> #include <linux/vmalloc.h> @@ -26,22 +25,16 @@ #include <asm/xen/hypervisor.h> #define DMA_ERROR_CODE (~(dma_addr_t)0) -extern struct dma_map_ops *dma_ops; extern struct dma_map_ops dummy_dma_ops; static inline struct dma_map_ops *__generic_dma_ops(struct device *dev) { - if (unlikely(!dev)) - return dma_ops; - else if (dev->archdata.dma_ops) + if (dev && dev->archdata.dma_ops) return dev->archdata.dma_ops; - else if (acpi_disabled) - return dma_ops; /* - * When ACPI is enabled, if arch_set_dma_ops is not called, - * we will disable device DMA capability by setting it - * to dummy_dma_ops. + * We expect no ISA devices, and all other DMA masters are expected to + * have someone call arch_setup_dma_ops at device creation time. */ return &dummy_dma_ops; } diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 17e92f05b1fe..3ca894ecf699 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -99,11 +99,13 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) *vcpu_cpsr(vcpu) |= COMPAT_PSR_T_BIT; } +/* + * vcpu_reg should always be passed a register number coming from a + * read of ESR_EL2. Otherwise, it may give the wrong result on AArch32 + * with banked registers. + */ static inline unsigned long *vcpu_reg(const struct kvm_vcpu *vcpu, u8 reg_num) { - if (vcpu_mode_is_32bit(vcpu)) - return vcpu_reg32(vcpu, reg_num); - return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.regs[reg_num]; } diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index c0e87898ba96..24165784b803 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -101,7 +101,7 @@ static inline void cpu_set_default_tcr_t0sz(void) #define destroy_context(mm) do { } while(0) void check_and_switch_context(struct mm_struct *mm, unsigned int cpu); -#define init_new_context(tsk,mm) ({ atomic64_set(&mm->context.id, 0); 0; }) +#define init_new_context(tsk,mm) ({ atomic64_set(&(mm)->context.id, 0); 0; }) /* * This is called when "tsk" is about to enter lazy TLB mode. diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 9819a9426b69..7e074f93f383 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -81,6 +81,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE) #define PAGE_KERNEL_RO __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY) +#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE) #define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 24926f2504f7..feb6b4efa641 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -75,6 +75,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = { (1 << MIDR_VARIANT_SHIFT) | 2), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_834220 + { + /* Cortex-A57 r0p0 - r1p2 */ + .desc = "ARM erratum 834220", + .capability = ARM64_WORKAROUND_834220, + MIDR_RANGE(MIDR_CORTEX_A57, 0x00, + (1 << MIDR_VARIANT_SHIFT) | 2), + }, +#endif #ifdef CONFIG_ARM64_ERRATUM_845719 { /* Cortex-A53 r0p[01234] */ diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 706679d0a0b4..212ae6361d8b 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -30,6 +30,7 @@ #include <linux/seq_file.h> #include <linux/sched.h> #include <linux/smp.h> +#include <linux/delay.h> /* * In case the boot CPU is hotpluggable, we record its initial state and @@ -112,6 +113,10 @@ static int c_show(struct seq_file *m, void *v) */ seq_printf(m, "processor\t: %d\n", i); + seq_printf(m, "BogoMIPS\t: %lu.%02lu\n", + loops_per_jiffy / (500000UL/HZ), + loops_per_jiffy / (5000UL/HZ) % 100); + /* * Dump out the common processor features in a single line. * Userspace should read the hwcaps with getauxval(AT_HWCAP) diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index de46b50f4cdf..fc5508e0df57 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -224,6 +224,8 @@ static bool __init efi_virtmap_init(void) { efi_memory_desc_t *md; + init_new_context(NULL, &efi_mm); + for_each_efi_memory_desc(&memmap, md) { u64 paddr, npages, size; pgprot_t prot; @@ -254,7 +256,8 @@ static bool __init efi_virtmap_init(void) else prot = PAGE_KERNEL; - create_pgd_mapping(&efi_mm, paddr, md->virt_addr, size, prot); + create_pgd_mapping(&efi_mm, paddr, md->virt_addr, size, + __pgprot(pgprot_val(prot) | PTE_NG)); } return true; } @@ -329,14 +332,7 @@ core_initcall(arm64_dmi_init); static void efi_set_pgd(struct mm_struct *mm) { - if (mm == &init_mm) - cpu_set_reserved_ttbr0(); - else - cpu_switch_mm(mm->pgd, mm); - - local_flush_tlb_all(); - if (icache_is_aivivt()) - __local_flush_icache_all(); + switch_mm(NULL, mm, NULL); } void efi_virtmap_load(void) diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index fce95e17cf7f..1095aa483a1c 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -1,3 +1,4 @@ +#include <linux/ftrace.h> #include <linux/percpu.h> #include <linux/slab.h> #include <asm/cacheflush.h> @@ -71,6 +72,13 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) local_dbg_save(flags); /* + * Function graph tracer state gets incosistent when the kernel + * calls functions that never return (aka suspend finishers) hence + * disable graph tracing during their execution. + */ + pause_graph_tracing(); + + /* * mm context saved on the stack, it will be restored when * the cpu comes out of reset through the identity mapped * page tables, so that the thread address space is properly @@ -111,6 +119,8 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) hw_breakpoint_restore(NULL); } + unpause_graph_tracing(); + /* * Restore pstate flags. OS lock and mdscr have been already * restored, so from this point onwards, debugging is fully diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index 1599701ef044..86c289832272 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -864,6 +864,10 @@ ENTRY(__kvm_flush_vm_context) ENDPROC(__kvm_flush_vm_context) __kvm_hyp_panic: + // Stash PAR_EL1 before corrupting it in __restore_sysregs + mrs x0, par_el1 + push x0, xzr + // Guess the context by looking at VTTBR: // If zero, then we're already a host. // Otherwise restore a minimal host context before panicing. @@ -898,7 +902,7 @@ __kvm_hyp_panic: mrs x3, esr_el2 mrs x4, far_el2 mrs x5, hpfar_el2 - mrs x6, par_el1 + pop x6, xzr // active context PAR_EL1 mrs x7, tpidr_el2 mov lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\ @@ -914,7 +918,7 @@ __kvm_hyp_panic: ENDPROC(__kvm_hyp_panic) __hyp_panic_str: - .ascii "HYP panic:\nPS:%08x PC:%p ESR:%p\nFAR:%p HPFAR:%p PAR:%p\nVCPU:%p\n\0" + .ascii "HYP panic:\nPS:%08x PC:%016x ESR:%08x\nFAR:%016x HPFAR:%016x PAR:%016x\nVCPU:%p\n\0" .align 2 @@ -1015,9 +1019,15 @@ el1_trap: b.ne 1f // Not an abort we care about /* This is an abort. Check for permission fault */ +alternative_if_not ARM64_WORKAROUND_834220 and x2, x1, #ESR_ELx_FSC_TYPE cmp x2, #FSC_PERM b.ne 1f // Not a permission fault +alternative_else + nop // Use the permission fault path to + nop // check for a valid S1 translation, + nop // regardless of the ESR value. +alternative_endif /* * Check for Stage-1 page table walk, which is guaranteed diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index 85c57158dcd9..648112e90ed5 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -48,7 +48,7 @@ static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset) /* Note: These now point to the banked copies */ *vcpu_spsr(vcpu) = new_spsr_value; - *vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) + return_offset; + *vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset; /* Branch to exception vector */ if (sctlr & (1 << 13)) diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 131a199114b4..7963aa4b5d28 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -18,6 +18,7 @@ */ #include <linux/gfp.h> +#include <linux/acpi.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/genalloc.h> @@ -28,9 +29,6 @@ #include <asm/cacheflush.h> -struct dma_map_ops *dma_ops; -EXPORT_SYMBOL(dma_ops); - static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot, bool coherent) { @@ -515,13 +513,7 @@ EXPORT_SYMBOL(dummy_dma_ops); static int __init arm64_dma_init(void) { - int ret; - - dma_ops = &swiotlb_dma_ops; - - ret = atomic_pool_init(); - - return ret; + return atomic_pool_init(); } arch_initcall(arm64_dma_init); @@ -552,10 +544,14 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, { bool coherent = is_device_dma_coherent(dev); int ioprot = dma_direction_to_prot(DMA_BIDIRECTIONAL, coherent); + size_t iosize = size; void *addr; if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n")) return NULL; + + size = PAGE_ALIGN(size); + /* * Some drivers rely on this, and we probably don't want the * possibility of stale kernel data being read by devices anyway. @@ -566,7 +562,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, struct page **pages; pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent); - pages = iommu_dma_alloc(dev, size, gfp, ioprot, handle, + pages = iommu_dma_alloc(dev, iosize, gfp, ioprot, handle, flush_page); if (!pages) return NULL; @@ -574,7 +570,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot, __builtin_return_address(0)); if (!addr) - iommu_dma_free(dev, pages, size, handle); + iommu_dma_free(dev, pages, iosize, handle); } else { struct page *page; /* @@ -591,7 +587,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, if (!addr) return NULL; - *handle = iommu_dma_map_page(dev, page, 0, size, ioprot); + *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot); if (iommu_dma_mapping_error(dev, *handle)) { if (coherent) __free_pages(page, get_order(size)); @@ -606,6 +602,9 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle, struct dma_attrs *attrs) { + size_t iosize = size; + + size = PAGE_ALIGN(size); /* * @cpu_addr will be one of 3 things depending on how it was allocated: * - A remapped array of pages from iommu_dma_alloc(), for all @@ -617,17 +616,17 @@ static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, * Hence how dodgy the below logic looks... */ if (__in_atomic_pool(cpu_addr, size)) { - iommu_dma_unmap_page(dev, handle, size, 0, NULL); + iommu_dma_unmap_page(dev, handle, iosize, 0, NULL); __free_from_pool(cpu_addr, size); } else if (is_vmalloc_addr(cpu_addr)){ struct vm_struct *area = find_vm_area(cpu_addr); if (WARN_ON(!area || !area->pages)) return; - iommu_dma_free(dev, area->pages, size, &handle); + iommu_dma_free(dev, area->pages, iosize, &handle); dma_common_free_remap(cpu_addr, size, VM_USERMAP); } else { - iommu_dma_unmap_page(dev, handle, size, 0, NULL); + iommu_dma_unmap_page(dev, handle, iosize, 0, NULL); __free_pages(virt_to_page(cpu_addr), get_order(size)); } } @@ -984,8 +983,8 @@ static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, struct iommu_ops *iommu, bool coherent) { - if (!acpi_disabled && !dev->archdata.dma_ops) - dev->archdata.dma_ops = dma_ops; + if (!dev->archdata.dma_ops) + dev->archdata.dma_ops = &swiotlb_dma_ops; dev->archdata.dma_coherent = coherent; __iommu_setup_dma_ops(dev, dma_base, size, iommu); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index e3f563c81c48..abb66f84d4ac 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -362,8 +362,8 @@ static void __init __map_memblock(phys_addr_t start, phys_addr_t end) * for now. This will get more fine grained later once all memory * is mapped */ - unsigned long kernel_x_start = round_down(__pa(_stext), SECTION_SIZE); - unsigned long kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE); + unsigned long kernel_x_start = round_down(__pa(_stext), SWAPPER_BLOCK_SIZE); + unsigned long kernel_x_end = round_up(__pa(__init_end), SWAPPER_BLOCK_SIZE); if (end < kernel_x_start) { create_mapping(start, __phys_to_virt(start), @@ -451,18 +451,18 @@ static void __init fixup_executable(void) { #ifdef CONFIG_DEBUG_RODATA /* now that we are actually fully mapped, make the start/end more fine grained */ - if (!IS_ALIGNED((unsigned long)_stext, SECTION_SIZE)) { + if (!IS_ALIGNED((unsigned long)_stext, SWAPPER_BLOCK_SIZE)) { unsigned long aligned_start = round_down(__pa(_stext), - SECTION_SIZE); + SWAPPER_BLOCK_SIZE); create_mapping(aligned_start, __phys_to_virt(aligned_start), __pa(_stext) - aligned_start, PAGE_KERNEL); } - if (!IS_ALIGNED((unsigned long)__init_end, SECTION_SIZE)) { + if (!IS_ALIGNED((unsigned long)__init_end, SWAPPER_BLOCK_SIZE)) { unsigned long aligned_end = round_up(__pa(__init_end), - SECTION_SIZE); + SWAPPER_BLOCK_SIZE); create_mapping(__pa(__init_end), (unsigned long)__init_end, aligned_end - __pa(__init_end), PAGE_KERNEL); @@ -475,7 +475,7 @@ void mark_rodata_ro(void) { create_mapping_late(__pa(_stext), (unsigned long)_stext, (unsigned long)_etext - (unsigned long)_stext, - PAGE_KERNEL_EXEC | PTE_RDONLY); + PAGE_KERNEL_ROX); } #endif diff --git a/arch/avr32/kernel/module.c b/arch/avr32/kernel/module.c index 164efa009e5b..2b4c54c04cb6 100644 --- a/arch/avr32/kernel/module.c +++ b/arch/avr32/kernel/module.c @@ -118,9 +118,9 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, * Increase core size to make room for GOT and set start * offset for GOT. */ - module->core_size = ALIGN(module->core_size, 4); - module->arch.got_offset = module->core_size; - module->core_size += module->arch.got_size; + module->core_layout.size = ALIGN(module->core_layout.size, 4); + module->arch.got_offset = module->core_layout.size; + module->core_layout.size += module->arch.got_size; return 0; @@ -177,7 +177,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab, if (!info->got_initialized) { Elf32_Addr *gotent; - gotent = (module->module_core + gotent = (module->core_layout.base + module->arch.got_offset + info->got_offset); *gotent = relocation; @@ -255,8 +255,8 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab, */ pr_debug("GOTPC: PC=0x%x, got_offset=0x%lx, core=0x%p\n", relocation, module->arch.got_offset, - module->module_core); - relocation -= ((unsigned long)module->module_core + module->core_layout.base); + relocation -= ((unsigned long)module->core_layout.base + module->arch.got_offset); *location = relocation; break; diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c index b15933c31b2f..6ab0ae7d6535 100644 --- a/arch/ia64/kernel/module.c +++ b/arch/ia64/kernel/module.c @@ -486,13 +486,13 @@ module_frob_arch_sections (Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, char *secstrings, static inline int in_init (const struct module *mod, uint64_t addr) { - return addr - (uint64_t) mod->module_init < mod->init_size; + return addr - (uint64_t) mod->init_layout.base < mod->init_layout.size; } static inline int in_core (const struct module *mod, uint64_t addr) { - return addr - (uint64_t) mod->module_core < mod->core_size; + return addr - (uint64_t) mod->core_layout.base < mod->core_layout.size; } static inline int @@ -675,7 +675,7 @@ do_reloc (struct module *mod, uint8_t r_type, Elf64_Sym *sym, uint64_t addend, break; case RV_BDREL: - val -= (uint64_t) (in_init(mod, val) ? mod->module_init : mod->module_core); + val -= (uint64_t) (in_init(mod, val) ? mod->init_layout.base : mod->core_layout.base); break; case RV_LTV: @@ -810,15 +810,15 @@ apply_relocate_add (Elf64_Shdr *sechdrs, const char *strtab, unsigned int symind * addresses have been selected... */ uint64_t gp; - if (mod->core_size > MAX_LTOFF) + if (mod->core_layout.size > MAX_LTOFF) /* * This takes advantage of fact that SHF_ARCH_SMALL gets allocated * at the end of the module. */ - gp = mod->core_size - MAX_LTOFF / 2; + gp = mod->core_layout.size - MAX_LTOFF / 2; else - gp = mod->core_size / 2; - gp = (uint64_t) mod->module_core + ((gp + 7) & -8); + gp = mod->core_layout.size / 2; + gp = (uint64_t) mod->core_layout.base + ((gp + 7) & -8); mod->arch.gp = gp; DEBUGP("%s: placing gp at 0x%lx\n", __func__, gp); } diff --git a/arch/metag/kernel/module.c b/arch/metag/kernel/module.c index 986331cd0a52..bb8dfba9a763 100644 --- a/arch/metag/kernel/module.c +++ b/arch/metag/kernel/module.c @@ -176,8 +176,8 @@ static uint32_t do_plt_call(void *location, Elf32_Addr val, tramp[1] = 0xac000001 | ((val & 0x0000ffff) << 3); /* Init, or core PLT? */ - if (location >= mod->module_core - && location < mod->module_core + mod->core_size) + if (location >= mod->core_layout.base + && location < mod->core_layout.base + mod->core_layout.size) entry = (void *)sechdrs[mod->arch.core_plt_section].sh_addr; else entry = (void *)sechdrs[mod->arch.init_plt_section].sh_addr; diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c index 1ba21204ebe0..8755d618e116 100644 --- a/arch/mips/ath79/setup.c +++ b/arch/mips/ath79/setup.c @@ -216,9 +216,9 @@ void __init plat_mem_setup(void) AR71XX_RESET_SIZE); ath79_pll_base = ioremap_nocache(AR71XX_PLL_BASE, AR71XX_PLL_SIZE); + ath79_detect_sys_type(); ath79_ddr_ctrl_init(); - ath79_detect_sys_type(); if (mips_machtype != ATH79_MACH_GENERIC_OF) detect_memory_region(0, ATH79_MEM_SIZE_MIN, ATH79_MEM_SIZE_MAX); @@ -281,3 +281,8 @@ MIPS_MACHINE(ATH79_MACH_GENERIC, "Generic", "Generic AR71XX/AR724X/AR913X based board", ath79_generic_init); + +MIPS_MACHINE(ATH79_MACH_GENERIC_OF, + "DTB", + "Generic AR71XX/AR724X/AR913X based board (DT)", + NULL); diff --git a/arch/mips/boot/dts/qca/ar9132.dtsi b/arch/mips/boot/dts/qca/ar9132.dtsi index fb7734eadbf0..13d0439496a9 100644 --- a/arch/mips/boot/dts/qca/ar9132.dtsi +++ b/arch/mips/boot/dts/qca/ar9132.dtsi @@ -107,7 +107,7 @@ miscintc: interrupt-controller@18060010 { compatible = "qca,ar9132-misc-intc", "qca,ar7100-misc-intc"; - reg = <0x18060010 0x4>; + reg = <0x18060010 0x8>; interrupt-parent = <&cpuintc>; interrupts = <6>; diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index ad1fccdb8d13..2046c0230224 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -200,8 +200,9 @@ static inline int pfn_valid(unsigned long pfn) { /* avoid <linux/mm.h> include hell */ extern unsigned long max_mapnr; + unsigned long pfn_offset = ARCH_PFN_OFFSET; - return pfn >= ARCH_PFN_OFFSET && pfn < max_mapnr; + return pfn >= pfn_offset && pfn < max_mapnr; } #elif defined(CONFIG_SPARSEMEM) diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 9067b651c7a2..544ea21bfef9 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -205,11 +205,11 @@ static void layout_sections(struct module *mod, const Elf_Ehdr *hdr, || s->sh_entsize != ~0UL) continue; s->sh_entsize = - get_offset((unsigned long *)&mod->core_size, s); + get_offset((unsigned long *)&mod->core_layout.size, s); } if (m == 0) - mod->core_text_size = mod->core_size; + mod->core_layout.text_size = mod->core_layout.size; } } @@ -641,7 +641,7 @@ static int vpe_elfload(struct vpe *v) layout_sections(&mod, hdr, sechdrs, secstrings); } - v->load_addr = alloc_progmem(mod.core_size); + v->load_addr = alloc_progmem(mod.core_layout.size); if (!v->load_addr) return -ENOMEM; diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index d5fa3eaf39a1..41b1b090f56f 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -1581,7 +1581,7 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc, base = (inst >> 21) & 0x1f; op_inst = (inst >> 16) & 0x1f; - offset = inst & 0xffff; + offset = (int16_t)inst; cache = (inst >> 16) & 0x3; op = (inst >> 18) & 0x7; diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S index 7bab3a4e8f7d..7e2210846b8b 100644 --- a/arch/mips/kvm/locore.S +++ b/arch/mips/kvm/locore.S @@ -157,9 +157,11 @@ FEXPORT(__kvm_mips_vcpu_run) FEXPORT(__kvm_mips_load_asid) /* Set the ASID for the Guest Kernel */ - INT_SLL t0, t0, 1 /* with kseg0 @ 0x40000000, kernel */ - /* addresses shift to 0x80000000 */ - bltz t0, 1f /* If kernel */ + PTR_L t0, VCPU_COP0(k1) + LONG_L t0, COP0_STATUS(t0) + andi t0, KSU_USER | ST0_ERL | ST0_EXL + xori t0, KSU_USER + bnez t0, 1f /* If kernel */ INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID /* (BD) */ INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID /* else user */ 1: @@ -474,9 +476,11 @@ __kvm_mips_return_to_guest: mtc0 t0, CP0_EPC /* Set the ASID for the Guest Kernel */ - INT_SLL t0, t0, 1 /* with kseg0 @ 0x40000000, kernel */ - /* addresses shift to 0x80000000 */ - bltz t0, 1f /* If kernel */ + PTR_L t0, VCPU_COP0(k1) + LONG_L t0, COP0_STATUS(t0) + andi t0, KSU_USER | ST0_ERL | ST0_EXL + xori t0, KSU_USER + bnez t0, 1f /* If kernel */ INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID /* (BD) */ INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID /* else user */ 1: diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 49ff3bfc007e..b9b803facdbf 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -279,7 +279,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) if (!gebase) { err = -ENOMEM; - goto out_free_cpu; + goto out_uninit_cpu; } kvm_debug("Allocated %d bytes for KVM Exception Handlers @ %p\n", ALIGN(size, PAGE_SIZE), gebase); @@ -343,6 +343,9 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) out_free_gebase: kfree(gebase); +out_uninit_cpu: + kvm_vcpu_uninit(vcpu); + out_free_cpu: kfree(vcpu); diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index c36546959e86..729f89163bc3 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -108,6 +108,9 @@ config PGTABLE_LEVELS default 3 if 64BIT && PARISC_PAGE_SIZE_4KB default 2 +config SYS_SUPPORTS_HUGETLBFS + def_bool y if PA20 + source "init/Kconfig" source "kernel/Kconfig.freezer" diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h new file mode 100644 index 000000000000..7d56a9ccb752 --- /dev/null +++ b/arch/parisc/include/asm/hugetlb.h @@ -0,0 +1,85 @@ +#ifndef _ASM_PARISC64_HUGETLB_H +#define _ASM_PARISC64_HUGETLB_H + +#include <asm/page.h> +#include <asm-generic/hugetlb.h> + + +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte); + +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep); + +static inline int is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, + unsigned long len) { + return 0; +} + +/* + * If the arch doesn't supply something else, assume that hugepage + * size aligned regions are ok without further preparation. + */ +static inline int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) +{ + if (len & ~HPAGE_MASK) + return -EINVAL; + if (addr & ~HPAGE_MASK) + return -EINVAL; + return 0; +} + +static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, + unsigned long addr, unsigned long end, + unsigned long floor, + unsigned long ceiling) +{ + free_pgd_range(tlb, addr, end, floor, ceiling); +} + +static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ +} + +static inline int huge_pte_none(pte_t pte) +{ + return pte_none(pte); +} + +static inline pte_t huge_pte_wrprotect(pte_t pte) +{ + return pte_wrprotect(pte); +} + +static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + pte_t old_pte = *ptep; + set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); +} + +static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) +{ + int changed = !pte_same(*ptep, pte); + if (changed) { + set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + flush_tlb_page(vma, addr); + } + return changed; +} + +static inline pte_t huge_ptep_get(pte_t *ptep) +{ + return *ptep; +} + +static inline void arch_clear_hugepage_flags(struct page *page) +{ +} + +#endif /* _ASM_PARISC64_HUGETLB_H */ diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h index 60d5d174dfe4..80e742a1c162 100644 --- a/arch/parisc/include/asm/page.h +++ b/arch/parisc/include/asm/page.h @@ -145,11 +145,22 @@ extern int npmem_ranges; #endif /* CONFIG_DISCONTIGMEM */ #ifdef CONFIG_HUGETLB_PAGE -#define HPAGE_SHIFT 22 /* 4MB (is this fixed?) */ +#define HPAGE_SHIFT PMD_SHIFT /* fixed for transparent huge pages */ #define HPAGE_SIZE ((1UL) << HPAGE_SHIFT) #define HPAGE_MASK (~(HPAGE_SIZE - 1)) #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) + +#if defined(CONFIG_64BIT) && defined(CONFIG_PARISC_PAGE_SIZE_4KB) +# define REAL_HPAGE_SHIFT 20 /* 20 = 1MB */ +# define _HUGE_PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_1M +#elif !defined(CONFIG_64BIT) && defined(CONFIG_PARISC_PAGE_SIZE_4KB) +# define REAL_HPAGE_SHIFT 22 /* 22 = 4MB */ +# define _HUGE_PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_4M +#else +# define REAL_HPAGE_SHIFT 24 /* 24 = 16MB */ +# define _HUGE_PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_16M #endif +#endif /* CONFIG_HUGETLB_PAGE */ #define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h index 3edbb9fc91b4..f2fd327dce2e 100644 --- a/arch/parisc/include/asm/pgalloc.h +++ b/arch/parisc/include/asm/pgalloc.h @@ -35,7 +35,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) PxD_FLAG_VALID | PxD_FLAG_ATTACHED) + (__u32)(__pa((unsigned long)pgd) >> PxD_VALUE_SHIFT)); - /* The first pmd entry also is marked with _PAGE_GATEWAY as + /* The first pmd entry also is marked with PxD_FLAG_ATTACHED as * a signal that this pmd may not be freed */ __pgd_val_set(*pgd, PxD_FLAG_ATTACHED); #endif diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index f93c4a4e6580..d8534f95915a 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -83,7 +83,11 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, (unsigned long)pgd_val(e)) /* This is the size of the initially mapped kernel memory */ -#define KERNEL_INITIAL_ORDER 24 /* 0 to 1<<24 = 16MB */ +#ifdef CONFIG_64BIT +#define KERNEL_INITIAL_ORDER 25 /* 1<<25 = 32MB */ +#else +#define KERNEL_INITIAL_ORDER 24 /* 1<<24 = 16MB */ +#endif #define KERNEL_INITIAL_SIZE (1 << KERNEL_INITIAL_ORDER) #if CONFIG_PGTABLE_LEVELS == 3 @@ -167,7 +171,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) #define _PAGE_NO_CACHE_BIT 24 /* (0x080) Uncached Page (U bit) */ #define _PAGE_ACCESSED_BIT 23 /* (0x100) Software: Page Accessed */ #define _PAGE_PRESENT_BIT 22 /* (0x200) Software: translation valid */ -/* bit 21 was formerly the FLUSH bit but is now unused */ +#define _PAGE_HPAGE_BIT 21 /* (0x400) Software: Huge Page */ #define _PAGE_USER_BIT 20 /* (0x800) Software: User accessible page */ /* N.B. The bits are defined in terms of a 32 bit word above, so the */ @@ -194,6 +198,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) #define _PAGE_NO_CACHE (1 << xlate_pabit(_PAGE_NO_CACHE_BIT)) #define _PAGE_ACCESSED (1 << xlate_pabit(_PAGE_ACCESSED_BIT)) #define _PAGE_PRESENT (1 << xlate_pabit(_PAGE_PRESENT_BIT)) +#define _PAGE_HUGE (1 << xlate_pabit(_PAGE_HPAGE_BIT)) #define _PAGE_USER (1 << xlate_pabit(_PAGE_USER_BIT)) #define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | _PAGE_DIRTY | _PAGE_ACCESSED) @@ -217,7 +222,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) #define PxD_FLAG_VALID (1 << xlate_pabit(_PxD_VALID_BIT)) #define PxD_FLAG_MASK (0xf) #define PxD_FLAG_SHIFT (4) -#define PxD_VALUE_SHIFT (8) /* (PAGE_SHIFT-PxD_FLAG_SHIFT) */ +#define PxD_VALUE_SHIFT (PFN_PTE_SHIFT-PxD_FLAG_SHIFT) #ifndef __ASSEMBLY__ @@ -363,6 +368,18 @@ static inline pte_t pte_mkwrite(pte_t pte) { pte_val(pte) |= _PAGE_WRITE; return static inline pte_t pte_mkspecial(pte_t pte) { return pte; } /* + * Huge pte definitions. + */ +#ifdef CONFIG_HUGETLB_PAGE +#define pte_huge(pte) (pte_val(pte) & _PAGE_HUGE) +#define pte_mkhuge(pte) (__pte(pte_val(pte) | _PAGE_HUGE)) +#else +#define pte_huge(pte) (0) +#define pte_mkhuge(pte) (pte) +#endif + + +/* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. */ @@ -410,8 +427,9 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) /* Find an entry in the second-level page table.. */ #if CONFIG_PGTABLE_LEVELS == 3 +#define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)) #define pmd_offset(dir,address) \ -((pmd_t *) pgd_page_vaddr(*(dir)) + (((address)>>PMD_SHIFT) & (PTRS_PER_PMD-1))) +((pmd_t *) pgd_page_vaddr(*(dir)) + pmd_index(address)) #else #define pmd_offset(dir,addr) ((pmd_t *) dir) #endif diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index 54adb60c0a42..7e759ecb1343 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -192,33 +192,6 @@ void show_trace(struct task_struct *task, unsigned long *stack); */ typedef unsigned int elf_caddr_t; -#define start_thread_som(regs, new_pc, new_sp) do { \ - unsigned long *sp = (unsigned long *)new_sp; \ - __u32 spaceid = (__u32)current->mm->context; \ - unsigned long pc = (unsigned long)new_pc; \ - /* offset pc for priv. level */ \ - pc |= 3; \ - \ - regs->iasq[0] = spaceid; \ - regs->iasq[1] = spaceid; \ - regs->iaoq[0] = pc; \ - regs->iaoq[1] = pc + 4; \ - regs->sr[2] = LINUX_GATEWAY_SPACE; \ - regs->sr[3] = 0xffff; \ - regs->sr[4] = spaceid; \ - regs->sr[5] = spaceid; \ - regs->sr[6] = spaceid; \ - regs->sr[7] = spaceid; \ - regs->gr[ 0] = USER_PSW; \ - regs->gr[30] = ((new_sp)+63)&~63; \ - regs->gr[31] = pc; \ - \ - get_user(regs->gr[26],&sp[0]); \ - get_user(regs->gr[25],&sp[-1]); \ - get_user(regs->gr[24],&sp[-2]); \ - get_user(regs->gr[23],&sp[-3]); \ -} while(0) - /* The ELF abi wants things done a "wee bit" differently than * som does. Supporting this behavior here avoids * having our own version of create_elf_tables. diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index ecc3ae1ca28e..dd4d1876a020 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -49,16 +49,6 @@ #define MADV_DONTFORK 10 /* don't inherit across fork */ #define MADV_DOFORK 11 /* do inherit across fork */ -/* The range 12-64 is reserved for page size specification. */ -#define MADV_4K_PAGES 12 /* Use 4K pages */ -#define MADV_16K_PAGES 14 /* Use 16K pages */ -#define MADV_64K_PAGES 16 /* Use 64K pages */ -#define MADV_256K_PAGES 18 /* Use 256K pages */ -#define MADV_1M_PAGES 20 /* Use 1 Megabyte pages */ -#define MADV_4M_PAGES 22 /* Use 4 Megabyte pages */ -#define MADV_16M_PAGES 24 /* Use 16 Megabyte pages */ -#define MADV_64M_PAGES 26 /* Use 64 Megabyte pages */ - #define MADV_MERGEABLE 65 /* KSM may merge identical pages */ #define MADV_UNMERGEABLE 66 /* KSM may not merge identical pages */ diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c index 59001cea13f9..d2f62570a7b1 100644 --- a/arch/parisc/kernel/asm-offsets.c +++ b/arch/parisc/kernel/asm-offsets.c @@ -290,6 +290,14 @@ int main(void) DEFINE(ASM_PFN_PTE_SHIFT, PFN_PTE_SHIFT); DEFINE(ASM_PT_INITIAL, PT_INITIAL); BLANK(); + /* HUGEPAGE_SIZE is only used in vmlinux.lds.S to align kernel text + * and kernel data on physical huge pages */ +#ifdef CONFIG_HUGETLB_PAGE + DEFINE(HUGEPAGE_SIZE, 1UL << REAL_HPAGE_SHIFT); +#else + DEFINE(HUGEPAGE_SIZE, PAGE_SIZE); +#endif + BLANK(); DEFINE(EXCDATA_IP, offsetof(struct exception_data, fault_ip)); DEFINE(EXCDATA_SPACE, offsetof(struct exception_data, fault_space)); DEFINE(EXCDATA_ADDR, offsetof(struct exception_data, fault_addr)); diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index c5ef4081b01d..623496c11756 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -502,21 +502,38 @@ STREG \pte,0(\ptp) .endm + /* We have (depending on the page size): + * - 38 to 52-bit Physical Page Number + * - 12 to 26-bit page offset + */ /* bitshift difference between a PFN (based on kernel's PAGE_SIZE) * to a CPU TLB 4k PFN (4k => 12 bits to shift) */ - #define PAGE_ADD_SHIFT (PAGE_SHIFT-12) + #define PAGE_ADD_SHIFT (PAGE_SHIFT-12) + #define PAGE_ADD_HUGE_SHIFT (REAL_HPAGE_SHIFT-12) /* Drop prot bits and convert to page addr for iitlbt and idtlbt */ - .macro convert_for_tlb_insert20 pte + .macro convert_for_tlb_insert20 pte,tmp +#ifdef CONFIG_HUGETLB_PAGE + copy \pte,\tmp + extrd,u \tmp,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\ + 64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte + + depdi _PAGE_SIZE_ENCODING_DEFAULT,63,\ + (63-58)+PAGE_ADD_SHIFT,\pte + extrd,u,*= \tmp,_PAGE_HPAGE_BIT+32,1,%r0 + depdi _HUGE_PAGE_SIZE_ENCODING_DEFAULT,63,\ + (63-58)+PAGE_ADD_HUGE_SHIFT,\pte +#else /* Huge pages disabled */ extrd,u \pte,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\ 64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte depdi _PAGE_SIZE_ENCODING_DEFAULT,63,\ (63-58)+PAGE_ADD_SHIFT,\pte +#endif .endm /* Convert the pte and prot to tlb insertion values. How * this happens is quite subtle, read below */ - .macro make_insert_tlb spc,pte,prot + .macro make_insert_tlb spc,pte,prot,tmp space_to_prot \spc \prot /* create prot id from space */ /* The following is the real subtlety. This is depositing * T <-> _PAGE_REFTRAP @@ -553,7 +570,7 @@ depdi 1,12,1,\prot /* Drop prot bits and convert to page addr for iitlbt and idtlbt */ - convert_for_tlb_insert20 \pte + convert_for_tlb_insert20 \pte \tmp .endm /* Identical macro to make_insert_tlb above, except it @@ -646,17 +663,12 @@ /* - * Align fault_vector_20 on 4K boundary so that both - * fault_vector_11 and fault_vector_20 are on the - * same page. This is only necessary as long as we - * write protect the kernel text, which we may stop - * doing once we use large page translations to cover - * the static part of the kernel address space. + * Fault_vectors are architecturally required to be aligned on a 2K + * boundary */ .text - - .align 4096 + .align 2048 ENTRY(fault_vector_20) /* First vector is invalid (0) */ @@ -1147,7 +1159,7 @@ dtlb_miss_20w: tlb_lock spc,ptp,pte,t0,t1,dtlb_check_alias_20w update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 idtlbt pte,prot @@ -1173,7 +1185,7 @@ nadtlb_miss_20w: tlb_lock spc,ptp,pte,t0,t1,nadtlb_check_alias_20w update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 idtlbt pte,prot @@ -1267,7 +1279,7 @@ dtlb_miss_20: tlb_lock spc,ptp,pte,t0,t1,dtlb_check_alias_20 update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 f_extend pte,t1 @@ -1295,7 +1307,7 @@ nadtlb_miss_20: tlb_lock spc,ptp,pte,t0,t1,nadtlb_check_alias_20 update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 f_extend pte,t1 @@ -1404,7 +1416,7 @@ itlb_miss_20w: tlb_lock spc,ptp,pte,t0,t1,itlb_fault update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 iitlbt pte,prot @@ -1428,7 +1440,7 @@ naitlb_miss_20w: tlb_lock spc,ptp,pte,t0,t1,naitlb_check_alias_20w update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 iitlbt pte,prot @@ -1514,7 +1526,7 @@ itlb_miss_20: tlb_lock spc,ptp,pte,t0,t1,itlb_fault update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 f_extend pte,t1 @@ -1534,7 +1546,7 @@ naitlb_miss_20: tlb_lock spc,ptp,pte,t0,t1,naitlb_check_alias_20 update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 f_extend pte,t1 @@ -1566,7 +1578,7 @@ dbit_trap_20w: tlb_lock spc,ptp,pte,t0,t1,dbit_fault update_dirty ptp,pte,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 idtlbt pte,prot @@ -1610,7 +1622,7 @@ dbit_trap_20: tlb_lock spc,ptp,pte,t0,t1,dbit_fault update_dirty ptp,pte,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 f_extend pte,t1 diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S index e7d64527aff9..75aa0db9f69e 100644 --- a/arch/parisc/kernel/head.S +++ b/arch/parisc/kernel/head.S @@ -69,7 +69,7 @@ $bss_loop: stw,ma %arg2,4(%r1) stw,ma %arg3,4(%r1) - /* Initialize startup VM. Just map first 8/16 MB of memory */ + /* Initialize startup VM. Just map first 16/32 MB of memory */ load32 PA(swapper_pg_dir),%r4 mtctl %r4,%cr24 /* Initialize kernel root pointer */ mtctl %r4,%cr25 /* Initialize user root pointer */ @@ -107,7 +107,7 @@ $bss_loop: /* Now initialize the PTEs themselves. We use RWX for * everything ... it will get remapped correctly later */ ldo 0+_PAGE_KERNEL_RWX(%r0),%r3 /* Hardwired 0 phys addr start */ - ldi (1<<(KERNEL_INITIAL_ORDER-PAGE_SHIFT)),%r11 /* PFN count */ + load32 (1<<(KERNEL_INITIAL_ORDER-PAGE_SHIFT)),%r11 /* PFN count */ load32 PA(pg0),%r1 $pgt_fill_loop: diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c index 3c63a820fcda..b9d75d9fa9ac 100644 --- a/arch/parisc/kernel/module.c +++ b/arch/parisc/kernel/module.c @@ -42,9 +42,9 @@ * We are not doing SEGREL32 handling correctly. According to the ABI, we * should do a value offset, like this: * if (in_init(me, (void *)val)) - * val -= (uint32_t)me->module_init; + * val -= (uint32_t)me->init_layout.base; * else - * val -= (uint32_t)me->module_core; + * val -= (uint32_t)me->core_layout.base; * However, SEGREL32 is used only for PARISC unwind entries, and we want * those entries to have an absolute address, and not just an offset. * @@ -100,14 +100,14 @@ * or init pieces the location is */ static inline int in_init(struct module *me, void *loc) { - return (loc >= me->module_init && - loc <= (me->module_init + me->init_size)); + return (loc >= me->init_layout.base && + loc <= (me->init_layout.base + me->init_layout.size)); } static inline int in_core(struct module *me, void *loc) { - return (loc >= me->module_core && - loc <= (me->module_core + me->core_size)); + return (loc >= me->core_layout.base && + loc <= (me->core_layout.base + me->core_layout.size)); } static inline int in_local(struct module *me, void *loc) @@ -367,13 +367,13 @@ int module_frob_arch_sections(CONST Elf_Ehdr *hdr, } /* align things a bit */ - me->core_size = ALIGN(me->core_size, 16); - me->arch.got_offset = me->core_size; - me->core_size += gots * sizeof(struct got_entry); + me->core_layout.size = ALIGN(me->core_layout.size, 16); + me->arch.got_offset = me->core_layout.size; + me->core_layout.size += gots * sizeof(struct got_entry); - me->core_size = ALIGN(me->core_size, 16); - me->arch.fdesc_offset = me->core_size; - me->core_size += fdescs * sizeof(Elf_Fdesc); + me->core_layout.size = ALIGN(me->core_layout.size, 16); + me->arch.fdesc_offset = me->core_layout.size; + me->core_layout.size += fdescs * sizeof(Elf_Fdesc); me->arch.got_max = gots; me->arch.fdesc_max = fdescs; @@ -391,7 +391,7 @@ static Elf64_Word get_got(struct module *me, unsigned long value, long addend) BUG_ON(value == 0); - got = me->module_core + me->arch.got_offset; + got = me->core_layout.base + me->arch.got_offset; for (i = 0; got[i].addr; i++) if (got[i].addr == value) goto out; @@ -409,7 +409,7 @@ static Elf64_Word get_got(struct module *me, unsigned long value, long addend) #ifdef CONFIG_64BIT static Elf_Addr get_fdesc(struct module *me, unsigned long value) { - Elf_Fdesc *fdesc = me->module_core + me->arch.fdesc_offset; + Elf_Fdesc *fdesc = me->core_layout.base + me->arch.fdesc_offset; if (!value) { printk(KERN_ERR "%s: zero OPD requested!\n", me->name); @@ -427,7 +427,7 @@ static Elf_Addr get_fdesc(struct module *me, unsigned long value) /* Create new one */ fdesc->addr = value; - fdesc->gp = (Elf_Addr)me->module_core + me->arch.got_offset; + fdesc->gp = (Elf_Addr)me->core_layout.base + me->arch.got_offset; return (Elf_Addr)fdesc; } #endif /* CONFIG_64BIT */ @@ -839,7 +839,7 @@ register_unwind_table(struct module *me, table = (unsigned char *)sechdrs[me->arch.unwind_section].sh_addr; end = table + sechdrs[me->arch.unwind_section].sh_size; - gp = (Elf_Addr)me->module_core + me->arch.got_offset; + gp = (Elf_Addr)me->core_layout.base + me->arch.got_offset; DEBUGP("register_unwind_table(), sect = %d at 0x%p - 0x%p (gp=0x%lx)\n", me->arch.unwind_section, table, end, gp); diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index 72a3c658ad7b..f7ea626e29c9 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -130,7 +130,16 @@ void __init setup_arch(char **cmdline_p) printk(KERN_INFO "The 32-bit Kernel has started...\n"); #endif - printk(KERN_INFO "Default page size is %dKB.\n", (int)(PAGE_SIZE / 1024)); + printk(KERN_INFO "Kernel default page size is %d KB. Huge pages ", + (int)(PAGE_SIZE / 1024)); +#ifdef CONFIG_HUGETLB_PAGE + printk(KERN_CONT "enabled with %d MB physical and %d MB virtual size", + 1 << (REAL_HPAGE_SHIFT - 20), 1 << (HPAGE_SHIFT - 20)); +#else + printk(KERN_CONT "disabled"); +#endif + printk(KERN_CONT ".\n"); + pdc_console_init(); @@ -377,6 +386,7 @@ arch_initcall(parisc_init); void start_parisc(void) { extern void start_kernel(void); + extern void early_trap_init(void); int ret, cpunum; struct pdc_coproc_cfg coproc_cfg; @@ -397,6 +407,8 @@ void start_parisc(void) panic("must have an fpu to boot linux"); } + early_trap_init(); /* initialize checksum of fault_vector */ + start_kernel(); // not reached } diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 0b8d26d3ba43..3fbd7252a4b2 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -369,7 +369,7 @@ tracesys_exit: ldo -16(%r30),%r29 /* Reference param save area */ #endif ldo TASK_REGS(%r1),%r26 - bl do_syscall_trace_exit,%r2 + BL do_syscall_trace_exit,%r2 STREG %r28,TASK_PT_GR28(%r1) /* save return value now */ ldo -THREAD_SZ_ALGN-FRAME_SIZE(%r30),%r1 /* get task ptr */ LDREG TI_TASK(%r1), %r1 @@ -390,7 +390,7 @@ tracesys_sigexit: #ifdef CONFIG_64BIT ldo -16(%r30),%r29 /* Reference param save area */ #endif - bl do_syscall_trace_exit,%r2 + BL do_syscall_trace_exit,%r2 ldo TASK_REGS(%r1),%r26 ldil L%syscall_exit_rfi,%r1 diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index b99b39f1da02..553b09855cfd 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -807,7 +807,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs) } -int __init check_ivt(void *iva) +void __init initialize_ivt(const void *iva) { extern u32 os_hpmc_size; extern const u32 os_hpmc[]; @@ -818,8 +818,8 @@ int __init check_ivt(void *iva) u32 *hpmcp; u32 length; - if (strcmp((char *)iva, "cows can fly")) - return -1; + if (strcmp((const char *)iva, "cows can fly")) + panic("IVT invalid"); ivap = (u32 *)iva; @@ -839,28 +839,23 @@ int __init check_ivt(void *iva) check += ivap[i]; ivap[5] = -check; - - return 0; } -#ifndef CONFIG_64BIT -extern const void fault_vector_11; -#endif -extern const void fault_vector_20; -void __init trap_init(void) +/* early_trap_init() is called before we set up kernel mappings and + * write-protect the kernel */ +void __init early_trap_init(void) { - void *iva; + extern const void fault_vector_20; - if (boot_cpu_data.cpu_type >= pcxu) - iva = (void *) &fault_vector_20; - else -#ifdef CONFIG_64BIT - panic("Can't boot 64-bit OS on PA1.1 processor!"); -#else - iva = (void *) &fault_vector_11; +#ifndef CONFIG_64BIT + extern const void fault_vector_11; + initialize_ivt(&fault_vector_11); #endif - if (check_ivt(iva)) - panic("IVT invalid"); + initialize_ivt(&fault_vector_20); +} + +void __init trap_init(void) +{ } diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index 0dacc5ca555a..308f29081d46 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -60,7 +60,7 @@ SECTIONS EXIT_DATA } PERCPU_SECTION(8) - . = ALIGN(PAGE_SIZE); + . = ALIGN(HUGEPAGE_SIZE); __init_end = .; /* freed after init ends here */ @@ -116,7 +116,7 @@ SECTIONS * that we can properly leave these * as writable */ - . = ALIGN(PAGE_SIZE); + . = ALIGN(HUGEPAGE_SIZE); data_start = .; EXCEPTION_TABLE(8) @@ -135,8 +135,11 @@ SECTIONS _edata = .; /* BSS */ - BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 8) + BSS_SECTION(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE) + + /* bootmap is allocated in setup_bootmem() directly behind bss. */ + . = ALIGN(HUGEPAGE_SIZE); _end = . ; STABS_DEBUG diff --git a/arch/parisc/mm/Makefile b/arch/parisc/mm/Makefile index 758ceefb373a..134393de69d2 100644 --- a/arch/parisc/mm/Makefile +++ b/arch/parisc/mm/Makefile @@ -3,3 +3,4 @@ # obj-y := init.o fault.o ioremap.o +obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c new file mode 100644 index 000000000000..f6fdc77a72bd --- /dev/null +++ b/arch/parisc/mm/hugetlbpage.c @@ -0,0 +1,161 @@ +/* + * PARISC64 Huge TLB page support. + * + * This parisc implementation is heavily based on the SPARC and x86 code. + * + * Copyright (C) 2015 Helge Deller <deller@gmx.de> + */ + +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/hugetlb.h> +#include <linux/pagemap.h> +#include <linux/sysctl.h> + +#include <asm/mman.h> +#include <asm/pgalloc.h> +#include <asm/tlb.h> +#include <asm/tlbflush.h> +#include <asm/cacheflush.h> +#include <asm/mmu_context.h> + + +unsigned long +hugetlb_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) +{ + struct hstate *h = hstate_file(file); + + if (len & ~huge_page_mask(h)) + return -EINVAL; + if (len > TASK_SIZE) + return -ENOMEM; + + if (flags & MAP_FIXED) + if (prepare_hugepage_range(file, addr, len)) + return -EINVAL; + + if (addr) + addr = ALIGN(addr, huge_page_size(h)); + + /* we need to make sure the colouring is OK */ + return arch_get_unmapped_area(file, addr, len, pgoff, flags); +} + + +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte = NULL; + + /* We must align the address, because our caller will run + * set_huge_pte_at() on whatever we return, which writes out + * all of the sub-ptes for the hugepage range. So we have + * to give it the first such sub-pte. + */ + addr &= HPAGE_MASK; + + pgd = pgd_offset(mm, addr); + pud = pud_alloc(mm, pgd, addr); + if (pud) { + pmd = pmd_alloc(mm, pud, addr); + if (pmd) + pte = pte_alloc_map(mm, NULL, pmd, addr); + } + return pte; +} + +pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte = NULL; + + addr &= HPAGE_MASK; + + pgd = pgd_offset(mm, addr); + if (!pgd_none(*pgd)) { + pud = pud_offset(pgd, addr); + if (!pud_none(*pud)) { + pmd = pmd_offset(pud, addr); + if (!pmd_none(*pmd)) + pte = pte_offset_map(pmd, addr); + } + } + return pte; +} + +/* Purge data and instruction TLB entries. Must be called holding + * the pa_tlb_lock. The TLB purge instructions are slow on SMP + * machines since the purge must be broadcast to all CPUs. + */ +static inline void purge_tlb_entries_huge(struct mm_struct *mm, unsigned long addr) +{ + int i; + + /* We may use multiple physical huge pages (e.g. 2x1 MB) to emulate + * Linux standard huge pages (e.g. 2 MB) */ + BUILD_BUG_ON(REAL_HPAGE_SHIFT > HPAGE_SHIFT); + + addr &= HPAGE_MASK; + addr |= _HUGE_PAGE_SIZE_ENCODING_DEFAULT; + + for (i = 0; i < (1 << (HPAGE_SHIFT-REAL_HPAGE_SHIFT)); i++) { + mtsp(mm->context, 1); + pdtlb(addr); + if (unlikely(split_tlb)) + pitlb(addr); + addr += (1UL << REAL_HPAGE_SHIFT); + } +} + +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t entry) +{ + unsigned long addr_start; + int i; + + addr &= HPAGE_MASK; + addr_start = addr; + + for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) { + /* Directly write pte entry. We could call set_pte_at(mm, addr, ptep, entry) + * instead, but then we get double locking on pa_tlb_lock. */ + *ptep = entry; + ptep++; + + /* Drop the PAGE_SIZE/non-huge tlb entry */ + purge_tlb_entries(mm, addr); + + addr += PAGE_SIZE; + pte_val(entry) += PAGE_SIZE; + } + + purge_tlb_entries_huge(mm, addr_start); +} + + +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pte_t entry; + + entry = *ptep; + set_huge_pte_at(mm, addr, ptep, __pte(0)); + + return entry; +} + +int pmd_huge(pmd_t pmd) +{ + return 0; +} + +int pud_huge(pud_t pud) +{ + return 0; +} diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index c5fec4890fdf..1b366c477687 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -409,15 +409,11 @@ static void __init map_pages(unsigned long start_vaddr, unsigned long vaddr; unsigned long ro_start; unsigned long ro_end; - unsigned long fv_addr; - unsigned long gw_addr; - extern const unsigned long fault_vector_20; - extern void * const linux_gateway_page; + unsigned long kernel_end; ro_start = __pa((unsigned long)_text); ro_end = __pa((unsigned long)&data_start); - fv_addr = __pa((unsigned long)&fault_vector_20) & PAGE_MASK; - gw_addr = __pa((unsigned long)&linux_gateway_page) & PAGE_MASK; + kernel_end = __pa((unsigned long)&_end); end_paddr = start_paddr + size; @@ -475,24 +471,25 @@ static void __init map_pages(unsigned long start_vaddr, for (tmp2 = start_pte; tmp2 < PTRS_PER_PTE; tmp2++, pg_table++) { pte_t pte; - /* - * Map the fault vector writable so we can - * write the HPMC checksum. - */ if (force) pte = __mk_pte(address, pgprot); - else if (parisc_text_address(vaddr) && - address != fv_addr) + else if (parisc_text_address(vaddr)) { pte = __mk_pte(address, PAGE_KERNEL_EXEC); + if (address >= ro_start && address < kernel_end) + pte = pte_mkhuge(pte); + } else #if defined(CONFIG_PARISC_PAGE_SIZE_4KB) - if (address >= ro_start && address < ro_end - && address != fv_addr - && address != gw_addr) - pte = __mk_pte(address, PAGE_KERNEL_RO); - else + if (address >= ro_start && address < ro_end) { + pte = __mk_pte(address, PAGE_KERNEL_EXEC); + pte = pte_mkhuge(pte); + } else #endif + { pte = __mk_pte(address, pgprot); + if (address >= ro_start && address < kernel_end) + pte = pte_mkhuge(pte); + } if (address >= end_paddr) { if (force) @@ -536,15 +533,12 @@ void free_initmem(void) /* force the kernel to see the new TLB entries */ __flush_tlb_range(0, init_begin, init_end); - /* Attempt to catch anyone trying to execute code here - * by filling the page with BRK insns. - */ - memset((void *)init_begin, 0x00, init_end - init_begin); + /* finally dump all the instructions which were cached, since the * pages are no-longer executable */ flush_icache_range(init_begin, init_end); - free_initmem_default(-1); + free_initmem_default(POISON_FREE_INITMEM); /* set up a new led state on systems shipped LED State panel */ pdc_chassis_send_status(PDC_CHASSIS_DIRECT_BCOMPLETE); @@ -728,8 +722,8 @@ static void __init pagetable_init(void) unsigned long size; start_paddr = pmem_ranges[range].start_pfn << PAGE_SHIFT; - end_paddr = start_paddr + (pmem_ranges[range].pages << PAGE_SHIFT); size = pmem_ranges[range].pages << PAGE_SHIFT; + end_paddr = start_paddr + size; map_pages((unsigned long)__va(start_paddr), start_paddr, size, PAGE_KERNEL, 0); diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index c9e26cb264f4..f2b0b1b0c72a 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -382,3 +382,4 @@ COMPAT_SYS(shmat) SYSCALL(shmdt) SYSCALL(shmget) COMPAT_SYS(shmctl) +SYSCALL(mlock2) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 6d8f8023ac27..4b6b8ace18e0 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -12,7 +12,7 @@ #include <uapi/asm/unistd.h> -#define __NR_syscalls 378 +#define __NR_syscalls 379 #define __NR__exit __NR_exit #define NR_syscalls __NR_syscalls diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h index 81579e93c659..1effea5193d6 100644 --- a/arch/powerpc/include/uapi/asm/unistd.h +++ b/arch/powerpc/include/uapi/asm/unistd.h @@ -400,5 +400,6 @@ #define __NR_shmdt 375 #define __NR_shmget 376 #define __NR_shmctl 377 +#define __NR_mlock2 378 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */ diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index c94d2e018d84..2c01665eb410 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -188,8 +188,8 @@ static uint32_t do_plt_call(void *location, pr_debug("Doing plt for call to 0x%x at 0x%x\n", val, (unsigned int)location); /* Init, or core PLT? */ - if (location >= mod->module_core - && location < mod->module_core + mod->core_size) + if (location >= mod->core_layout.base + && location < mod->core_layout.base + mod->core_layout.size) entry = (void *)sechdrs[mod->arch.core_plt_section].sh_addr; else entry = (void *)sechdrs[mod->arch.init_plt_section].sh_addr; @@ -296,7 +296,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, } #ifdef CONFIG_DYNAMIC_FTRACE module->arch.tramp = - do_plt_call(module->module_core, + do_plt_call(module->core_layout.base, (unsigned long)ftrace_caller, sechdrs, module); #endif diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index 0c1a679314dd..7873e171457c 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -159,11 +159,11 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, /* Increase core size by size of got & plt and set start offsets for got and plt. */ - me->core_size = ALIGN(me->core_size, 4); - me->arch.got_offset = me->core_size; - me->core_size += me->arch.got_size; - me->arch.plt_offset = me->core_size; - me->core_size += me->arch.plt_size; + me->core_layout.size = ALIGN(me->core_layout.size, 4); + me->arch.got_offset = me->core_layout.size; + me->core_layout.size += me->arch.got_size; + me->arch.plt_offset = me->core_layout.size; + me->core_layout.size += me->arch.plt_size; return 0; } @@ -279,7 +279,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, if (info->got_initialized == 0) { Elf_Addr *gotent; - gotent = me->module_core + me->arch.got_offset + + gotent = me->core_layout.base + me->arch.got_offset + info->got_offset; *gotent = val; info->got_initialized = 1; @@ -302,7 +302,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, rc = apply_rela_bits(loc, val, 0, 64, 0); else if (r_type == R_390_GOTENT || r_type == R_390_GOTPLTENT) { - val += (Elf_Addr) me->module_core - loc; + val += (Elf_Addr) me->core_layout.base - loc; rc = apply_rela_bits(loc, val, 1, 32, 1); } break; @@ -315,7 +315,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_PLTOFF64: /* 16 bit offset from GOT to PLT. */ if (info->plt_initialized == 0) { unsigned int *ip; - ip = me->module_core + me->arch.plt_offset + + ip = me->core_layout.base + me->arch.plt_offset + info->plt_offset; ip[0] = 0x0d10e310; /* basr 1,0; lg 1,10(1); br 1 */ ip[1] = 0x100a0004; @@ -334,7 +334,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, val - loc + 0xffffUL < 0x1ffffeUL) || (r_type == R_390_PLT32DBL && val - loc + 0xffffffffULL < 0x1fffffffeULL))) - val = (Elf_Addr) me->module_core + + val = (Elf_Addr) me->core_layout.base + me->arch.plt_offset + info->plt_offset; val += rela->r_addend - loc; @@ -356,7 +356,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_GOTOFF32: /* 32 bit offset to GOT. */ case R_390_GOTOFF64: /* 64 bit offset to GOT. */ val = val + rela->r_addend - - ((Elf_Addr) me->module_core + me->arch.got_offset); + ((Elf_Addr) me->core_layout.base + me->arch.got_offset); if (r_type == R_390_GOTOFF16) rc = apply_rela_bits(loc, val, 0, 16, 0); else if (r_type == R_390_GOTOFF32) @@ -366,7 +366,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, break; case R_390_GOTPC: /* 32 bit PC relative offset to GOT. */ case R_390_GOTPCDBL: /* 32 bit PC rel. off. to GOT shifted by 1. */ - val = (Elf_Addr) me->module_core + me->arch.got_offset + + val = (Elf_Addr) me->core_layout.base + me->arch.got_offset + rela->r_addend - loc; if (r_type == R_390_GOTPC) rc = apply_rela_bits(loc, val, 1, 32, 0); diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 373e32346d68..6a75352f453c 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1030,8 +1030,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) src_id, 0); /* sending vcpu invalid */ - if (src_id >= KVM_MAX_VCPUS || - kvm_get_vcpu(vcpu->kvm, src_id) == NULL) + if (kvm_get_vcpu_by_id(vcpu->kvm, src_id) == NULL) return -EINVAL; if (sclp.has_sigpif) @@ -1110,6 +1109,10 @@ static int __inject_sigp_emergency(struct kvm_vcpu *vcpu, trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY, irq->u.emerg.code, 0); + /* sending vcpu invalid */ + if (kvm_get_vcpu_by_id(vcpu->kvm, irq->u.emerg.code) == NULL) + return -EINVAL; + set_bit(irq->u.emerg.code, li->sigp_emerg_pending); set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs); atomic_or(CPUSTAT_EXT_INT, li->cpuflags); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 8fe2f1c722dc..846589281b04 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -342,12 +342,16 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) r = 0; break; case KVM_CAP_S390_VECTOR_REGISTERS: - if (MACHINE_HAS_VX) { + mutex_lock(&kvm->lock); + if (atomic_read(&kvm->online_vcpus)) { + r = -EBUSY; + } else if (MACHINE_HAS_VX) { set_kvm_facility(kvm->arch.model.fac->mask, 129); set_kvm_facility(kvm->arch.model.fac->list, 129); r = 0; } else r = -EINVAL; + mutex_unlock(&kvm->lock); VM_EVENT(kvm, 3, "ENABLE: CAP_S390_VECTOR_REGISTERS %s", r ? "(not available)" : "(success)"); break; diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 77191b85ea7a..d76b51cb4b62 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -660,7 +660,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) kvm_s390_get_regs_rre(vcpu, ®1, ®2); - if (!MACHINE_HAS_PFMF) + if (!test_kvm_facility(vcpu->kvm, 8)) return kvm_s390_inject_program_int(vcpu, PGM_OPERATION); if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index da690b69f9fe..77c22d685c7a 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -291,12 +291,8 @@ static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code, u16 cpu_addr, u32 parameter, u64 *status_reg) { int rc; - struct kvm_vcpu *dst_vcpu; + struct kvm_vcpu *dst_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, cpu_addr); - if (cpu_addr >= KVM_MAX_VCPUS) - return SIGP_CC_NOT_OPERATIONAL; - - dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr); if (!dst_vcpu) return SIGP_CC_NOT_OPERATIONAL; @@ -478,7 +474,7 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu) trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr); if (order_code == SIGP_EXTERNAL_CALL) { - dest_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr); + dest_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, cpu_addr); BUG_ON(dest_vcpu == NULL); kvm_s390_vcpu_wakeup(dest_vcpu); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 9f3905697f12..690b4027e17c 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -35,7 +35,7 @@ #define MSR_IA32_PERFCTR0 0x000000c1 #define MSR_IA32_PERFCTR1 0x000000c2 #define MSR_FSB_FREQ 0x000000cd -#define MSR_NHM_PLATFORM_INFO 0x000000ce +#define MSR_PLATFORM_INFO 0x000000ce #define MSR_NHM_SNB_PKG_CST_CFG_CTL 0x000000e2 #define NHM_C3_AUTO_DEMOTE (1UL << 25) @@ -44,7 +44,6 @@ #define SNB_C1_AUTO_UNDEMOTE (1UL << 27) #define SNB_C3_AUTO_UNDEMOTE (1UL << 28) -#define MSR_PLATFORM_INFO 0x000000ce #define MSR_MTRRcap 0x000000fe #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 4ddd780aeac9..c2b7522cbf35 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -273,10 +273,9 @@ __setup("nosmap", setup_disable_smap); static __always_inline void setup_smap(struct cpuinfo_x86 *c) { - unsigned long eflags; + unsigned long eflags = native_save_fl(); /* This should have been cleared long ago */ - raw_local_save_flags(eflags); BUG_ON(eflags & X86_EFLAGS_AC); if (cpu_has(c, X86_FEATURE_SMAP)) { diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index ef29b742cea7..31c6a60505e6 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -385,20 +385,19 @@ fpu__alloc_mathframe(unsigned long sp, int ia32_frame, */ void fpu__init_prepare_fx_sw_frame(void) { - int fsave_header_size = sizeof(struct fregs_state); int size = xstate_size + FP_XSTATE_MAGIC2_SIZE; - if (config_enabled(CONFIG_X86_32)) - size += fsave_header_size; - fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1; fx_sw_reserved.extended_size = size; fx_sw_reserved.xfeatures = xfeatures_mask; fx_sw_reserved.xstate_size = xstate_size; - if (config_enabled(CONFIG_IA32_EMULATION)) { + if (config_enabled(CONFIG_IA32_EMULATION) || + config_enabled(CONFIG_X86_32)) { + int fsave_header_size = sizeof(struct fregs_state); + fx_sw_reserved_ia32 = fx_sw_reserved; - fx_sw_reserved_ia32.extended_size += fsave_header_size; + fx_sw_reserved_ia32.extended_size = size + fsave_header_size; } } diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 6454f2731b56..70fc312221fc 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -694,7 +694,6 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature) if (!boot_cpu_has(X86_FEATURE_XSAVE)) return NULL; - xsave = ¤t->thread.fpu.state.xsave; /* * We should not ever be requesting features that we * have not enabled. Remember that pcntxt_mask is diff --git a/arch/x86/kernel/livepatch.c b/arch/x86/kernel/livepatch.c index d1d35ccffed3..bcc06e82a593 100644 --- a/arch/x86/kernel/livepatch.c +++ b/arch/x86/kernel/livepatch.c @@ -41,8 +41,8 @@ int klp_write_module_reloc(struct module *mod, unsigned long type, int ret, numpages, size = 4; bool readonly; unsigned long val; - unsigned long core = (unsigned long)mod->module_core; - unsigned long core_size = mod->core_size; + unsigned long core = (unsigned long)mod->core_layout.base; + unsigned long core_size = mod->core_layout.size; switch (type) { case R_X86_64_NONE: @@ -72,7 +72,7 @@ int klp_write_module_reloc(struct module *mod, unsigned long type, readonly = false; #ifdef CONFIG_DEBUG_SET_MODULE_RONX - if (loc < core + mod->core_ro_size) + if (loc < core + mod->core_layout.ro_size) readonly = true; #endif diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S index 94ea120fa21f..87e1762e2bca 100644 --- a/arch/x86/kernel/mcount_64.S +++ b/arch/x86/kernel/mcount_64.S @@ -278,6 +278,12 @@ trace: /* save_mcount_regs fills in first two parameters */ save_mcount_regs + /* + * When DYNAMIC_FTRACE is not defined, ARCH_SUPPORTS_FTRACE_OPS is not + * set (see include/asm/ftrace.h and include/linux/ftrace.h). Only the + * ip and parent ip are used and the list function is called when + * function tracing is enabled. + */ call *ftrace_trace_function restore_mcount_regs diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 87acc5221740..af823a388c19 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -7394,11 +7394,6 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) switch (type) { case VMX_VPID_EXTENT_ALL_CONTEXT: - if (get_vmcs12(vcpu)->virtual_processor_id == 0) { - nested_vmx_failValid(vcpu, - VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); - return 1; - } __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02); nested_vmx_succeed(vcpu); break; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 00462bd63129..eed32283d22c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2763,6 +2763,26 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, return 0; } +static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu) +{ + return (!lapic_in_kernel(vcpu) || + kvm_apic_accept_pic_intr(vcpu)); +} + +/* + * if userspace requested an interrupt window, check that the + * interrupt window is open. + * + * No need to exit to userspace if we already have an interrupt queued. + */ +static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) +{ + return kvm_arch_interrupt_allowed(vcpu) && + !kvm_cpu_has_interrupt(vcpu) && + !kvm_event_needs_reinjection(vcpu) && + kvm_cpu_accept_dm_intr(vcpu); +} + static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) { @@ -2786,6 +2806,7 @@ static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, return -EEXIST; vcpu->arch.pending_external_vector = irq->irq; + kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; } @@ -5910,23 +5931,10 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) return emulator_write_emulated(ctxt, rip, instruction, 3, NULL); } -/* - * Check if userspace requested an interrupt window, and that the - * interrupt window is open. - * - * No need to exit to userspace if we already have an interrupt queued. - */ static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) { - if (!vcpu->run->request_interrupt_window || pic_in_kernel(vcpu->kvm)) - return false; - - if (kvm_cpu_has_interrupt(vcpu)) - return false; - - return (irqchip_split(vcpu->kvm) - ? kvm_apic_accept_pic_intr(vcpu) - : kvm_arch_interrupt_allowed(vcpu)); + return vcpu->run->request_interrupt_window && + likely(!pic_in_kernel(vcpu->kvm)); } static void post_kvm_run_save(struct kvm_vcpu *vcpu) @@ -5937,17 +5945,9 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0; kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); - if (!irqchip_in_kernel(vcpu->kvm)) - kvm_run->ready_for_interrupt_injection = - kvm_arch_interrupt_allowed(vcpu) && - !kvm_cpu_has_interrupt(vcpu) && - !kvm_event_needs_reinjection(vcpu); - else if (!pic_in_kernel(vcpu->kvm)) - kvm_run->ready_for_interrupt_injection = - kvm_apic_accept_pic_intr(vcpu) && - !kvm_cpu_has_interrupt(vcpu); - else - kvm_run->ready_for_interrupt_injection = 1; + kvm_run->ready_for_interrupt_injection = + pic_in_kernel(vcpu->kvm) || + kvm_vcpu_ready_for_interrupt_injection(vcpu); } static void update_cr8_intercept(struct kvm_vcpu *vcpu) @@ -6360,8 +6360,10 @@ void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; - bool req_int_win = !lapic_in_kernel(vcpu) && - vcpu->run->request_interrupt_window; + bool req_int_win = + dm_request_for_irq_injection(vcpu) && + kvm_cpu_accept_dm_intr(vcpu); + bool req_immediate_exit = false; if (vcpu->requests) { @@ -6663,7 +6665,8 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); - if (dm_request_for_irq_injection(vcpu)) { + if (dm_request_for_irq_injection(vcpu) && + kvm_vcpu_ready_for_interrupt_injection(vcpu)) { r = 0; vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; ++vcpu->stat.request_irq_exits; diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index b0ae85f90f10..1202d5ca2fb5 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -586,6 +586,29 @@ static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm, } /* + * We only want to do a 4-byte get_user() on 32-bit. Otherwise, + * we might run off the end of the bounds table if we are on + * a 64-bit kernel and try to get 8 bytes. + */ +int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret, + long __user *bd_entry_ptr) +{ + u32 bd_entry_32; + int ret; + + if (is_64bit_mm(mm)) + return get_user(*bd_entry_ret, bd_entry_ptr); + + /* + * Note that get_user() uses the type of the *pointer* to + * establish the size of the get, not the destination. + */ + ret = get_user(bd_entry_32, (u32 __user *)bd_entry_ptr); + *bd_entry_ret = bd_entry_32; + return ret; +} + +/* * Get the base of bounds tables pointed by specific bounds * directory entry. */ @@ -605,7 +628,7 @@ static int get_bt_addr(struct mm_struct *mm, int need_write = 0; pagefault_disable(); - ret = get_user(bd_entry, bd_entry_ptr); + ret = get_user_bd_entry(mm, &bd_entry, bd_entry_ptr); pagefault_enable(); if (!ret) break; @@ -700,11 +723,23 @@ static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm, */ static inline unsigned long bd_entry_virt_space(struct mm_struct *mm) { - unsigned long long virt_space = (1ULL << boot_cpu_data.x86_virt_bits); - if (is_64bit_mm(mm)) - return virt_space / MPX_BD_NR_ENTRIES_64; - else - return virt_space / MPX_BD_NR_ENTRIES_32; + unsigned long long virt_space; + unsigned long long GB = (1ULL << 30); + + /* + * This covers 32-bit emulation as well as 32-bit kernels + * running on 64-bit harware. + */ + if (!is_64bit_mm(mm)) + return (4ULL * GB) / MPX_BD_NR_ENTRIES_32; + + /* + * 'x86_virt_bits' returns what the hardware is capable + * of, and returns the full >32-bit adddress space when + * running 32-bit kernels on 64-bit hardware. + */ + virt_space = (1ULL << boot_cpu_data.x86_virt_bits); + return virt_space / MPX_BD_NR_ENTRIES_64; } /* |