diff options
Diffstat (limited to 'arch/x86/mm')
-rw-r--r-- | arch/x86/mm/fault.c | 4 | ||||
-rw-r--r-- | arch/x86/mm/init.c | 8 | ||||
-rw-r--r-- | arch/x86/mm/init_32.c | 2 | ||||
-rw-r--r-- | arch/x86/mm/init_64.c | 210 | ||||
-rw-r--r-- | arch/x86/mm/ioremap.c | 19 | ||||
-rw-r--r-- | arch/x86/mm/kaslr.c | 2 | ||||
-rw-r--r-- | arch/x86/mm/kmmio.c | 2 | ||||
-rw-r--r-- | arch/x86/mm/mem_encrypt.c | 6 | ||||
-rw-r--r-- | arch/x86/mm/mem_encrypt_boot.S | 2 | ||||
-rw-r--r-- | arch/x86/mm/mem_encrypt_identity.c | 35 | ||||
-rw-r--r-- | arch/x86/mm/pat/memtype.c | 4 | ||||
-rw-r--r-- | arch/x86/mm/pat/set_memory.c | 2 | ||||
-rw-r--r-- | arch/x86/mm/pgtable.c | 13 | ||||
-rw-r--r-- | arch/x86/mm/pkeys.c | 2 | ||||
-rw-r--r-- | arch/x86/mm/pti.c | 11 | ||||
-rw-r--r-- | arch/x86/mm/tlb.c | 182 |
16 files changed, 283 insertions, 221 deletions
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index a73347e2cdfc..1c548ad00752 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1497,7 +1497,7 @@ DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault) * userspace task is trying to access some valid (from guest's point of * view) memory which is not currently mapped by the host (e.g. the * memory is swapped out). Note, the corresponding "page ready" event - * which is injected when the memory becomes available, is delived via + * which is injected when the memory becomes available, is delivered via * an interrupt mechanism and not a #PF exception * (see arch/x86/kernel/kvm.c: sysvec_kvm_asyncpf_interrupt()). * @@ -1523,7 +1523,7 @@ DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault) * * In case the fault hit a RCU idle region the conditional entry * code reenabled RCU to avoid subsequent wreckage which helps - * debugability. + * debuggability. */ state = irqentry_enter(regs); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index dd694fb93916..75ef19aa8903 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -29,7 +29,7 @@ /* * We need to define the tracepoints somewhere, and tlb.c - * is only compied when SMP=y. + * is only compiled when SMP=y. */ #define CREATE_TRACE_POINTS #include <trace/events/tlb.h> @@ -756,7 +756,7 @@ void __init init_mem_mapping(void) #ifdef CONFIG_X86_64 if (max_pfn > max_low_pfn) { - /* can we preseve max_low_pfn ?*/ + /* can we preserve max_low_pfn ?*/ max_low_pfn = max_pfn; } #else @@ -939,7 +939,7 @@ void __init free_initrd_mem(unsigned long start, unsigned long end) { /* * end could be not aligned, and We can not align that, - * decompresser could be confused by aligned initrd_end + * decompressor could be confused by aligned initrd_end * We already reserve the end partial page before in * - i386_start_kernel() * - x86_64_start_kernel() @@ -1017,7 +1017,7 @@ void __init zone_sizes_init(void) free_area_init(max_zone_pfns); } -__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = { +__visible DEFINE_PER_CPU_ALIGNED(struct tlb_state, cpu_tlbstate) = { .loaded_mm = &init_mm, .next_asid = 1, .cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */ diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index da31c2635ee4..21ffb03f6c72 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -755,8 +755,6 @@ void __init mem_init(void) after_bootmem = 1; x86_init.hyper.init_after_bootmem(); - mem_init_print_info(NULL); - /* * Check boundaries twice: Some fundamental inconsistencies can * be detected at build time already. diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index b5a3fa4033d3..e527d829e1ed 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -172,7 +172,7 @@ static void sync_global_pgds_l4(unsigned long start, unsigned long end) /* * With folded p4d, pgd_none() is always false, we need to - * handle synchonization on p4d level. + * handle synchronization on p4d level. */ MAYBE_BUILD_BUG_ON(pgd_none(*pgd_ref)); p4d_ref = p4d_offset(pgd_ref, addr); @@ -826,6 +826,106 @@ void __init paging_init(void) zone_sizes_init(); } +#ifdef CONFIG_SPARSEMEM_VMEMMAP +#define PAGE_UNUSED 0xFD + +/* + * The unused vmemmap range, which was not yet memset(PAGE_UNUSED), ranges + * from unused_pmd_start to next PMD_SIZE boundary. + */ +static unsigned long unused_pmd_start __meminitdata; + +static void __meminit vmemmap_flush_unused_pmd(void) +{ + if (!unused_pmd_start) + return; + /* + * Clears (unused_pmd_start, PMD_END] + */ + memset((void *)unused_pmd_start, PAGE_UNUSED, + ALIGN(unused_pmd_start, PMD_SIZE) - unused_pmd_start); + unused_pmd_start = 0; +} + +#ifdef CONFIG_MEMORY_HOTPLUG +/* Returns true if the PMD is completely unused and thus it can be freed */ +static bool __meminit vmemmap_pmd_is_unused(unsigned long addr, unsigned long end) +{ + unsigned long start = ALIGN_DOWN(addr, PMD_SIZE); + + /* + * Flush the unused range cache to ensure that memchr_inv() will work + * for the whole range. + */ + vmemmap_flush_unused_pmd(); + memset((void *)addr, PAGE_UNUSED, end - addr); + + return !memchr_inv((void *)start, PAGE_UNUSED, PMD_SIZE); +} +#endif + +static void __meminit __vmemmap_use_sub_pmd(unsigned long start) +{ + /* + * As we expect to add in the same granularity as we remove, it's + * sufficient to mark only some piece used to block the memmap page from + * getting removed when removing some other adjacent memmap (just in + * case the first memmap never gets initialized e.g., because the memory + * block never gets onlined). + */ + memset((void *)start, 0, sizeof(struct page)); +} + +static void __meminit vmemmap_use_sub_pmd(unsigned long start, unsigned long end) +{ + /* + * We only optimize if the new used range directly follows the + * previously unused range (esp., when populating consecutive sections). + */ + if (unused_pmd_start == start) { + if (likely(IS_ALIGNED(end, PMD_SIZE))) + unused_pmd_start = 0; + else + unused_pmd_start = end; + return; + } + + /* + * If the range does not contiguously follows previous one, make sure + * to mark the unused range of the previous one so it can be removed. + */ + vmemmap_flush_unused_pmd(); + __vmemmap_use_sub_pmd(start); +} + + +static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end) +{ + vmemmap_flush_unused_pmd(); + + /* + * Could be our memmap page is filled with PAGE_UNUSED already from a + * previous remove. Make sure to reset it. + */ + __vmemmap_use_sub_pmd(start); + + /* + * Mark with PAGE_UNUSED the unused parts of the new memmap range + */ + if (!IS_ALIGNED(start, PMD_SIZE)) + memset((void *)start, PAGE_UNUSED, + start - ALIGN_DOWN(start, PMD_SIZE)); + + /* + * We want to avoid memset(PAGE_UNUSED) when populating the vmemmap of + * consecutive sections. Remember for the last added PMD where the + * unused range begins. + */ + if (!IS_ALIGNED(end, PMD_SIZE)) + unused_pmd_start = end; +} +#endif + /* * Memory hotplug specific functions */ @@ -871,8 +971,6 @@ int arch_add_memory(int nid, u64 start, u64 size, return add_pages(nid, start_pfn, nr_pages, params); } -#define PAGE_INUSE 0xFD - static void __meminit free_pagetable(struct page *page, int order) { unsigned long magic; @@ -962,7 +1060,6 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, { unsigned long next, pages = 0; pte_t *pte; - void *page_addr; phys_addr_t phys_addr; pte = pte_start + pte_index(addr); @@ -983,42 +1080,15 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, if (phys_addr < (phys_addr_t)0x40000000) return; - if (PAGE_ALIGNED(addr) && PAGE_ALIGNED(next)) { - /* - * Do not free direct mapping pages since they were - * freed when offlining, or simplely not in use. - */ - if (!direct) - free_pagetable(pte_page(*pte), 0); - - spin_lock(&init_mm.page_table_lock); - pte_clear(&init_mm, addr, pte); - spin_unlock(&init_mm.page_table_lock); - - /* For non-direct mapping, pages means nothing. */ - pages++; - } else { - /* - * If we are here, we are freeing vmemmap pages since - * direct mapped memory ranges to be freed are aligned. - * - * If we are not removing the whole page, it means - * other page structs in this page are being used and - * we canot remove them. So fill the unused page_structs - * with 0xFD, and remove the page when it is wholly - * filled with 0xFD. - */ - memset((void *)addr, PAGE_INUSE, next - addr); + if (!direct) + free_pagetable(pte_page(*pte), 0); - page_addr = page_address(pte_page(*pte)); - if (!memchr_inv(page_addr, PAGE_INUSE, PAGE_SIZE)) { - free_pagetable(pte_page(*pte), 0); + spin_lock(&init_mm.page_table_lock); + pte_clear(&init_mm, addr, pte); + spin_unlock(&init_mm.page_table_lock); - spin_lock(&init_mm.page_table_lock); - pte_clear(&init_mm, addr, pte); - spin_unlock(&init_mm.page_table_lock); - } - } + /* For non-direct mapping, pages means nothing. */ + pages++; } /* Call free_pte_table() in remove_pmd_table(). */ @@ -1034,7 +1104,6 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, unsigned long next, pages = 0; pte_t *pte_base; pmd_t *pmd; - void *page_addr; pmd = pmd_start + pmd_index(addr); for (; addr < end; addr = next, pmd++) { @@ -1054,22 +1123,16 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, pmd_clear(pmd); spin_unlock(&init_mm.page_table_lock); pages++; - } else { - /* If here, we are freeing vmemmap pages. */ - memset((void *)addr, PAGE_INUSE, next - addr); - - page_addr = page_address(pmd_page(*pmd)); - if (!memchr_inv(page_addr, PAGE_INUSE, - PMD_SIZE)) { + } +#ifdef CONFIG_SPARSEMEM_VMEMMAP + else if (vmemmap_pmd_is_unused(addr, next)) { free_hugepage_table(pmd_page(*pmd), altmap); - spin_lock(&init_mm.page_table_lock); pmd_clear(pmd); spin_unlock(&init_mm.page_table_lock); - } } - +#endif continue; } @@ -1090,7 +1153,6 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, unsigned long next, pages = 0; pmd_t *pmd_base; pud_t *pud; - void *page_addr; pud = pud_start + pud_index(addr); for (; addr < end; addr = next, pud++) { @@ -1099,33 +1161,13 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, if (!pud_present(*pud)) continue; - if (pud_large(*pud)) { - if (IS_ALIGNED(addr, PUD_SIZE) && - IS_ALIGNED(next, PUD_SIZE)) { - if (!direct) - free_pagetable(pud_page(*pud), - get_order(PUD_SIZE)); - - spin_lock(&init_mm.page_table_lock); - pud_clear(pud); - spin_unlock(&init_mm.page_table_lock); - pages++; - } else { - /* If here, we are freeing vmemmap pages. */ - memset((void *)addr, PAGE_INUSE, next - addr); - - page_addr = page_address(pud_page(*pud)); - if (!memchr_inv(page_addr, PAGE_INUSE, - PUD_SIZE)) { - free_pagetable(pud_page(*pud), - get_order(PUD_SIZE)); - - spin_lock(&init_mm.page_table_lock); - pud_clear(pud); - spin_unlock(&init_mm.page_table_lock); - } - } - + if (pud_large(*pud) && + IS_ALIGNED(addr, PUD_SIZE) && + IS_ALIGNED(next, PUD_SIZE)) { + spin_lock(&init_mm.page_table_lock); + pud_clear(pud); + spin_unlock(&init_mm.page_table_lock); + pages++; continue; } @@ -1197,6 +1239,9 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct, void __ref vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap) { + VM_BUG_ON(!IS_ALIGNED(start, PAGE_SIZE)); + VM_BUG_ON(!IS_ALIGNED(end, PAGE_SIZE)); + remove_pagetable(start, end, false, altmap); } @@ -1306,8 +1351,6 @@ void __init mem_init(void) kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, PAGE_SIZE, KCORE_USER); preallocate_vmalloc_pages(); - - mem_init_print_info(NULL); } #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT @@ -1538,11 +1581,17 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, addr_end = addr + PMD_SIZE; p_end = p + PMD_SIZE; + + if (!IS_ALIGNED(addr, PMD_SIZE) || + !IS_ALIGNED(next, PMD_SIZE)) + vmemmap_use_new_sub_pmd(addr, next); + continue; } else if (altmap) return -ENOMEM; /* no fallback */ } else if (pmd_large(*pmd)) { vmemmap_verify((pte_t *)pmd, node, addr, next); + vmemmap_use_sub_pmd(addr, next); continue; } if (vmemmap_populate_basepages(addr, next, node, NULL)) @@ -1556,6 +1605,9 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, { int err; + VM_BUG_ON(!IS_ALIGNED(start, PAGE_SIZE)); + VM_BUG_ON(!IS_ALIGNED(end, PAGE_SIZE)); + if (end - start < PAGES_PER_SECTION * sizeof(struct page)) err = vmemmap_populate_basepages(start, end, node, NULL); else if (boot_cpu_has(X86_FEATURE_PSE)) diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 9e5ccc56f8e0..12c686c65ea9 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -481,25 +481,6 @@ void iounmap(volatile void __iomem *addr) } EXPORT_SYMBOL(iounmap); -int __init arch_ioremap_p4d_supported(void) -{ - return 0; -} - -int __init arch_ioremap_pud_supported(void) -{ -#ifdef CONFIG_X86_64 - return boot_cpu_has(X86_FEATURE_GBPAGES); -#else - return 0; -#endif -} - -int __init arch_ioremap_pmd_supported(void) -{ - return boot_cpu_has(X86_FEATURE_PSE); -} - /* * Convert a physical pointer to a virtual kernel pointer for /dev/mem * access diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 6e6b39710e5f..557f0fe25dff 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -96,7 +96,7 @@ void __init kernel_randomize_memory(void) memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) + CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING; - /* Adapt phyiscal memory region size based on available memory */ + /* Adapt physical memory region size based on available memory */ if (memory_tb < kaslr_regions[0].size_tb) kaslr_regions[0].size_tb = memory_tb; diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index be020a7bc414..d3efbc5b3449 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Support for MMIO probes. - * Benfit many code from kprobes + * Benefit many code from kprobes * (C) 2002 Louis Zhuang <louis.zhuang@intel.com>. * 2007 Alexander Eichner * 2008 Pekka Paalanen <pq@iki.fi> diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index ae78cef79980..f633f9e23b8f 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -19,6 +19,7 @@ #include <linux/kernel.h> #include <linux/bitops.h> #include <linux/dma-mapping.h> +#include <linux/virtio_config.h> #include <asm/tlbflush.h> #include <asm/fixmap.h> @@ -484,3 +485,8 @@ void __init mem_encrypt_init(void) print_mem_encrypt_feature_info(); } +int arch_has_restricted_virtio_memory_access(void) +{ + return sev_active(); +} +EXPORT_SYMBOL_GPL(arch_has_restricted_virtio_memory_access); diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index 7a84fc8bc5c3..17d292b7072f 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -27,7 +27,7 @@ SYM_FUNC_START(sme_encrypt_execute) * - stack page (PAGE_SIZE) * - encryption routine page (PAGE_SIZE) * - intermediate copy buffer (PMD_PAGE_SIZE) - * R8 - physcial address of the pagetables to use for encryption + * R8 - physical address of the pagetables to use for encryption */ push %rbp diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index 6c5eb6f3f14f..a19374d26101 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -503,14 +503,10 @@ void __init sme_enable(struct boot_params *bp) #define AMD_SME_BIT BIT(0) #define AMD_SEV_BIT BIT(1) - /* - * Set the feature mask (SME or SEV) based on whether we are - * running under a hypervisor. - */ - eax = 1; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - feature_mask = (ecx & BIT(31)) ? AMD_SEV_BIT : AMD_SME_BIT; + + /* Check the SEV MSR whether SEV or SME is enabled */ + sev_status = __rdmsr(MSR_AMD64_SEV); + feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; /* * Check for the SME/SEV feature: @@ -530,19 +526,26 @@ void __init sme_enable(struct boot_params *bp) /* Check if memory encryption is enabled */ if (feature_mask == AMD_SME_BIT) { + /* + * No SME if Hypervisor bit is set. This check is here to + * prevent a guest from trying to enable SME. For running as a + * KVM guest the MSR_K8_SYSCFG will be sufficient, but there + * might be other hypervisors which emulate that MSR as non-zero + * or even pass it through to the guest. + * A malicious hypervisor can still trick a guest into this + * path, but there is no way to protect against that. + */ + eax = 1; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + if (ecx & BIT(31)) + return; + /* For SME, check the SYSCFG MSR */ msr = __rdmsr(MSR_K8_SYSCFG); if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) return; } else { - /* For SEV, check the SEV MSR */ - msr = __rdmsr(MSR_AMD64_SEV); - if (!(msr & MSR_AMD64_SEV_ENABLED)) - return; - - /* Save SEV_STATUS to avoid reading MSR again */ - sev_status = msr; - /* SEV state cannot be controlled by a command line option */ sme_me_mask = me_mask; sev_enabled = true; diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index ca311aaa67b8..3112ca7786ed 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -695,7 +695,7 @@ int memtype_free(u64 start, u64 end) /** - * lookup_memtype - Looksup the memory type for a physical address + * lookup_memtype - Looks up the memory type for a physical address * @paddr: physical address of which memory type needs to be looked up * * Only to be called when PAT is enabled @@ -800,6 +800,7 @@ void memtype_free_io(resource_size_t start, resource_size_t end) memtype_free(start, end); } +#ifdef CONFIG_X86_PAT int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size) { enum page_cache_mode type = _PAGE_CACHE_MODE_WC; @@ -813,6 +814,7 @@ void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size) memtype_free_io(start, start + size); } EXPORT_SYMBOL(arch_io_free_memtype_wc); +#endif pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot) diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 16f878c26667..427980617557 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -680,7 +680,7 @@ pmd_t *lookup_pmd_address(unsigned long address) * end up in this kind of memory, for instance. * * This could be optimized, but it is only intended to be - * used at inititalization time, and keeping it + * used at initialization time, and keeping it * unoptimized should increase the testing coverage for * the more obscure platforms. */ diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index f6a9e2e36642..d27cf69e811d 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -780,14 +780,6 @@ int pmd_clear_huge(pmd_t *pmd) return 0; } -/* - * Until we support 512GB pages, skip them in the vmap area. - */ -int p4d_free_pud_page(p4d_t *p4d, unsigned long addr) -{ - return 0; -} - #ifdef CONFIG_X86_64 /** * pud_free_pmd_page - Clear pud entry and free pmd page. @@ -861,11 +853,6 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) #else /* !CONFIG_X86_64 */ -int pud_free_pmd_page(pud_t *pud, unsigned long addr) -{ - return pud_none(*pud); -} - /* * Disable free page handling on x86-PAE. This assures that ioremap() * does not update sync'd pmd entries. See vmalloc_sync_one(). diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index 8873ed1438a9..a2332eef66e9 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -128,7 +128,7 @@ u32 init_pkru_value = PKRU_AD_KEY( 1) | PKRU_AD_KEY( 2) | PKRU_AD_KEY( 3) | /* * Called from the FPU code when creating a fresh set of FPU * registers. This is called from a very specific context where - * we know the FPU regstiers are safe for use and we can use PKRU + * we know the FPU registers are safe for use and we can use PKRU * directly. */ void copy_init_pkru_to_fpregs(void) diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 1aab92930569..5d5c7bb50ce9 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -361,7 +361,7 @@ pti_clone_pgtable(unsigned long start, unsigned long end, * global, so set it as global in both copies. Note: * the X86_FEATURE_PGE check is not _required_ because * the CPU ignores _PAGE_GLOBAL when PGE is not - * supported. The check keeps consistentency with + * supported. The check keeps consistency with * code that only set this bit when supported. */ if (boot_cpu_has(X86_FEATURE_PGE)) @@ -440,10 +440,9 @@ static void __init pti_clone_user_shared(void) for_each_possible_cpu(cpu) { /* - * The SYSCALL64 entry code needs to be able to find the - * thread stack and needs one word of scratch space in which - * to spill a register. All of this lives in the TSS, in - * the sp1 and sp2 slots. + * The SYSCALL64 entry code needs one word of scratch space + * in which to spill a register. It lives in the sp2 slot + * of the CPU's TSS. * * This is done for all possible CPUs during boot to ensure * that it's propagated to all mms. @@ -512,7 +511,7 @@ static void pti_clone_entry_text(void) static inline bool pti_kernel_image_global_ok(void) { /* - * Systems with PCIDs get litlle benefit from global + * Systems with PCIDs get little benefit from global * kernel text and are not worth the downsides. */ if (cpu_feature_enabled(X86_FEATURE_PCID)) diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 569ac1d57f55..78804680e923 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -24,7 +24,7 @@ # define __flush_tlb_local native_flush_tlb_local # define __flush_tlb_global native_flush_tlb_global # define __flush_tlb_one_user(addr) native_flush_tlb_one_user(addr) -# define __flush_tlb_others(msk, info) native_flush_tlb_others(msk, info) +# define __flush_tlb_multi(msk, info) native_flush_tlb_multi(msk, info) #endif /* @@ -106,7 +106,7 @@ static inline u16 kern_pcid(u16 asid) #ifdef CONFIG_PAGE_TABLE_ISOLATION /* - * Make sure that the dynamic ASID space does not confict with the + * Make sure that the dynamic ASID space does not conflict with the * bit we are using to switch between user and kernel ASIDs. */ BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_PCID_USER_BIT)); @@ -300,7 +300,7 @@ void leave_mm(int cpu) return; /* Warn if we're not lazy. */ - WARN_ON(!this_cpu_read(cpu_tlbstate.is_lazy)); + WARN_ON(!this_cpu_read(cpu_tlbstate_shared.is_lazy)); switch_mm(NULL, &init_mm, NULL); } @@ -316,7 +316,7 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next, local_irq_restore(flags); } -static inline unsigned long mm_mangle_tif_spec_ib(struct task_struct *next) +static unsigned long mm_mangle_tif_spec_ib(struct task_struct *next) { unsigned long next_tif = task_thread_info(next)->flags; unsigned long ibpb = (next_tif >> TIF_SPEC_IB) & LAST_USER_MM_IBPB; @@ -424,7 +424,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, { struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm); u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); - bool was_lazy = this_cpu_read(cpu_tlbstate.is_lazy); + bool was_lazy = this_cpu_read(cpu_tlbstate_shared.is_lazy); unsigned cpu = smp_processor_id(); u64 next_tlb_gen; bool need_flush; @@ -439,7 +439,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * NB: leave_mm() calls us with prev == NULL and tsk == NULL. */ - /* We don't want flush_tlb_func_* to run concurrently with us. */ + /* We don't want flush_tlb_func() to run concurrently with us. */ if (IS_ENABLED(CONFIG_PROVE_LOCKING)) WARN_ON_ONCE(!irqs_disabled()); @@ -469,7 +469,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, __flush_tlb_all(); } #endif - this_cpu_write(cpu_tlbstate.is_lazy, false); + if (was_lazy) + this_cpu_write(cpu_tlbstate_shared.is_lazy, false); /* * The membarrier system call requires a full memory barrier and @@ -490,7 +491,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, /* * Even in lazy TLB mode, the CPU should stay set in the * mm_cpumask. The TLB shootdown code can figure out from - * from cpu_tlbstate.is_lazy whether or not to send an IPI. + * cpu_tlbstate_shared.is_lazy whether or not to send an IPI. */ if (WARN_ON_ONCE(real_prev != &init_mm && !cpumask_test_cpu(cpu, mm_cpumask(next)))) @@ -598,7 +599,7 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm) return; - this_cpu_write(cpu_tlbstate.is_lazy, true); + this_cpu_write(cpu_tlbstate_shared.is_lazy, true); } /* @@ -647,14 +648,13 @@ void initialize_tlbstate_and_flush(void) } /* - * flush_tlb_func_common()'s memory ordering requirement is that any + * flush_tlb_func()'s memory ordering requirement is that any * TLB fills that happen after we flush the TLB are ordered after we * read active_mm's tlb_gen. We don't need any explicit barriers * because all x86 flush operations are serializing and the * atomic64_read operation won't be reordered by the compiler. */ -static void flush_tlb_func_common(const struct flush_tlb_info *f, - bool local, enum tlb_flush_reason reason) +static void flush_tlb_func(void *info) { /* * We have three different tlb_gen values in here. They are: @@ -665,28 +665,40 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, * - f->new_tlb_gen: the generation that the requester of the flush * wants us to catch up to. */ + const struct flush_tlb_info *f = info; struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm); u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); u64 mm_tlb_gen = atomic64_read(&loaded_mm->context.tlb_gen); u64 local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen); + bool local = smp_processor_id() == f->initiating_cpu; + unsigned long nr_invalidate = 0; /* This code cannot presently handle being reentered. */ VM_WARN_ON(!irqs_disabled()); + if (!local) { + inc_irq_stat(irq_tlb_count); + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); + + /* Can only happen on remote CPUs */ + if (f->mm && f->mm != loaded_mm) + return; + } + if (unlikely(loaded_mm == &init_mm)) return; VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) != loaded_mm->context.ctx_id); - if (this_cpu_read(cpu_tlbstate.is_lazy)) { + if (this_cpu_read(cpu_tlbstate_shared.is_lazy)) { /* * We're in lazy mode. We need to at least flush our * paging-structure cache to avoid speculatively reading * garbage into our TLB. Since switching to init_mm is barely * slower than a minimal flush, just switch to init_mm. * - * This should be rare, with native_flush_tlb_others skipping + * This should be rare, with native_flush_tlb_multi() skipping * IPIs to lazy TLB mode CPUs. */ switch_mm_irqs_off(NULL, &init_mm, NULL); @@ -700,8 +712,7 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, * be handled can catch us all the way up, leaving no work for * the second flush. */ - trace_tlb_flush(reason, 0); - return; + goto done; } WARN_ON_ONCE(local_tlb_gen > mm_tlb_gen); @@ -736,7 +747,7 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, * 3, we'd be break the invariant: we'd update local_tlb_gen above * 1 without the full flush that's needed for tlb_gen 2. * - * 2. f->new_tlb_gen == mm_tlb_gen. This is purely an optimiation. + * 2. f->new_tlb_gen == mm_tlb_gen. This is purely an optimization. * Partial TLB flushes are not all that much cheaper than full TLB * flushes, so it seems unlikely that it would be a performance win * to do a partial flush if that won't bring our TLB fully up to @@ -748,56 +759,54 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, f->new_tlb_gen == local_tlb_gen + 1 && f->new_tlb_gen == mm_tlb_gen) { /* Partial flush */ - unsigned long nr_invalidate = (f->end - f->start) >> f->stride_shift; unsigned long addr = f->start; + nr_invalidate = (f->end - f->start) >> f->stride_shift; + while (addr < f->end) { flush_tlb_one_user(addr); addr += 1UL << f->stride_shift; } if (local) count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_invalidate); - trace_tlb_flush(reason, nr_invalidate); } else { /* Full flush. */ + nr_invalidate = TLB_FLUSH_ALL; + flush_tlb_local(); if (local) count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - trace_tlb_flush(reason, TLB_FLUSH_ALL); } /* Both paths above update our state to mm_tlb_gen. */ this_cpu_write(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen, mm_tlb_gen); -} - -static void flush_tlb_func_local(const void *info, enum tlb_flush_reason reason) -{ - const struct flush_tlb_info *f = info; - flush_tlb_func_common(f, true, reason); + /* Tracing is done in a unified manner to reduce the code size */ +done: + trace_tlb_flush(!local ? TLB_REMOTE_SHOOTDOWN : + (f->mm == NULL) ? TLB_LOCAL_SHOOTDOWN : + TLB_LOCAL_MM_SHOOTDOWN, + nr_invalidate); } -static void flush_tlb_func_remote(void *info) +static bool tlb_is_not_lazy(int cpu) { - const struct flush_tlb_info *f = info; - - inc_irq_stat(irq_tlb_count); - - if (f->mm && f->mm != this_cpu_read(cpu_tlbstate.loaded_mm)) - return; - - count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); - flush_tlb_func_common(f, false, TLB_REMOTE_SHOOTDOWN); + return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu); } -static bool tlb_is_not_lazy(int cpu, void *data) -{ - return !per_cpu(cpu_tlbstate.is_lazy, cpu); -} +static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask); + +DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared); +EXPORT_PER_CPU_SYMBOL(cpu_tlbstate_shared); -STATIC_NOPV void native_flush_tlb_others(const struct cpumask *cpumask, +STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask, const struct flush_tlb_info *info) { + /* + * Do accounting and tracing. Note that there are (and have always been) + * cases in which a remote TLB flush will be traced, but eventually + * would not happen. + */ count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); if (info->end == TLB_FLUSH_ALL) trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL); @@ -815,18 +824,42 @@ STATIC_NOPV void native_flush_tlb_others(const struct cpumask *cpumask, * up on the new contents of what used to be page tables, while * doing a speculative memory access. */ - if (info->freed_tables) - smp_call_function_many(cpumask, flush_tlb_func_remote, - (void *)info, 1); - else - on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func_remote, - (void *)info, 1, cpumask); + if (info->freed_tables) { + on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true); + } else { + /* + * Although we could have used on_each_cpu_cond_mask(), + * open-coding it has performance advantages, as it eliminates + * the need for indirect calls or retpolines. In addition, it + * allows to use a designated cpumask for evaluating the + * condition, instead of allocating one. + * + * This code works under the assumption that there are no nested + * TLB flushes, an assumption that is already made in + * flush_tlb_mm_range(). + * + * cond_cpumask is logically a stack-local variable, but it is + * more efficient to have it off the stack and not to allocate + * it on demand. Preemption is disabled and this code is + * non-reentrant. + */ + struct cpumask *cond_cpumask = this_cpu_ptr(&flush_tlb_mask); + int cpu; + + cpumask_clear(cond_cpumask); + + for_each_cpu(cpu, cpumask) { + if (tlb_is_not_lazy(cpu)) + __cpumask_set_cpu(cpu, cond_cpumask); + } + on_each_cpu_mask(cond_cpumask, flush_tlb_func, (void *)info, true); + } } -void flush_tlb_others(const struct cpumask *cpumask, +void flush_tlb_multi(const struct cpumask *cpumask, const struct flush_tlb_info *info) { - __flush_tlb_others(cpumask, info); + __flush_tlb_multi(cpumask, info); } /* @@ -847,7 +880,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct flush_tlb_info, flush_tlb_info); static DEFINE_PER_CPU(unsigned int, flush_tlb_info_idx); #endif -static inline struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm, +static struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned int stride_shift, bool freed_tables, u64 new_tlb_gen) @@ -869,14 +902,15 @@ static inline struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm, info->stride_shift = stride_shift; info->freed_tables = freed_tables; info->new_tlb_gen = new_tlb_gen; + info->initiating_cpu = smp_processor_id(); return info; } -static inline void put_flush_tlb_info(void) +static void put_flush_tlb_info(void) { #ifdef CONFIG_DEBUG_VM - /* Complete reentrency prevention checks */ + /* Complete reentrancy prevention checks */ barrier(); this_cpu_dec(flush_tlb_info_idx); #endif @@ -905,16 +939,20 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, info = get_flush_tlb_info(mm, start, end, stride_shift, freed_tables, new_tlb_gen); - if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) { + /* + * flush_tlb_multi() is not optimized for the common case in which only + * a local TLB flush is needed. Optimize this use-case by calling + * flush_tlb_func_local() directly in this case. + */ + if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) { + flush_tlb_multi(mm_cpumask(mm), info); + } else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) { lockdep_assert_irqs_enabled(); local_irq_disable(); - flush_tlb_func_local(info, TLB_LOCAL_MM_SHOOTDOWN); + flush_tlb_func(info); local_irq_enable(); } - if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) - flush_tlb_others(mm_cpumask(mm), info); - put_flush_tlb_info(); put_cpu(); } @@ -1119,34 +1157,30 @@ void __flush_tlb_all(void) } EXPORT_SYMBOL_GPL(__flush_tlb_all); -/* - * arch_tlbbatch_flush() performs a full TLB flush regardless of the active mm. - * This means that the 'struct flush_tlb_info' that describes which mappings to - * flush is actually fixed. We therefore set a single fixed struct and use it in - * arch_tlbbatch_flush(). - */ -static const struct flush_tlb_info full_flush_tlb_info = { - .mm = NULL, - .start = 0, - .end = TLB_FLUSH_ALL, -}; - void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) { + struct flush_tlb_info *info; + int cpu = get_cpu(); - if (cpumask_test_cpu(cpu, &batch->cpumask)) { + info = get_flush_tlb_info(NULL, 0, TLB_FLUSH_ALL, 0, false, 0); + /* + * flush_tlb_multi() is not optimized for the common case in which only + * a local TLB flush is needed. Optimize this use-case by calling + * flush_tlb_func_local() directly in this case. + */ + if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) { + flush_tlb_multi(&batch->cpumask, info); + } else if (cpumask_test_cpu(cpu, &batch->cpumask)) { lockdep_assert_irqs_enabled(); local_irq_disable(); - flush_tlb_func_local(&full_flush_tlb_info, TLB_LOCAL_SHOOTDOWN); + flush_tlb_func(info); local_irq_enable(); } - if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) - flush_tlb_others(&batch->cpumask, &full_flush_tlb_info); - cpumask_clear(&batch->cpumask); + put_flush_tlb_info(); put_cpu(); } |