diff options
Diffstat (limited to 'arch/x86/mm')
| -rw-r--r-- | arch/x86/mm/fault.c | 3 | ||||
| -rw-r--r-- | arch/x86/mm/ident_map.c | 14 | ||||
| -rw-r--r-- | arch/x86/mm/init.c | 12 | ||||
| -rw-r--r-- | arch/x86/mm/init_32.c | 9 | ||||
| -rw-r--r-- | arch/x86/mm/init_64.c | 8 | ||||
| -rw-r--r-- | arch/x86/mm/ioremap.c | 125 | ||||
| -rw-r--r-- | arch/x86/mm/kasan_init_64.c | 1 | ||||
| -rw-r--r-- | arch/x86/mm/kaslr.c | 10 | ||||
| -rw-r--r-- | arch/x86/mm/mem_encrypt.c | 2 | ||||
| -rw-r--r-- | arch/x86/mm/mem_encrypt_amd.c | 5 | ||||
| -rw-r--r-- | arch/x86/mm/mem_encrypt_boot.S | 1 | ||||
| -rw-r--r-- | arch/x86/mm/mem_encrypt_identity.c | 6 | ||||
| -rw-r--r-- | arch/x86/mm/mmap.c | 9 | ||||
| -rw-r--r-- | arch/x86/mm/pat/cpa-test.c | 2 | ||||
| -rw-r--r-- | arch/x86/mm/pat/memtype.c | 6 | ||||
| -rw-r--r-- | arch/x86/mm/pat/set_memory.c | 245 | ||||
| -rw-r--r-- | arch/x86/mm/pgtable.c | 77 | ||||
| -rw-r--r-- | arch/x86/mm/tlb.c | 491 |
18 files changed, 756 insertions, 270 deletions
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index e6c469b323cc..296d294142c8 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -7,7 +7,6 @@ #include <linux/sched.h> /* test_thread_flag(), ... */ #include <linux/sched/task_stack.h> /* task_stack_*(), ... */ #include <linux/kdebug.h> /* oops_begin/end, ... */ -#include <linux/extable.h> /* search_exception_tables */ #include <linux/memblock.h> /* max_low_pfn */ #include <linux/kfence.h> /* kfence_handle_page_fault */ #include <linux/kprobes.h> /* NOKPROBE_SYMBOL, ... */ @@ -678,7 +677,7 @@ page_fault_oops(struct pt_regs *regs, unsigned long error_code, ASM_CALL_ARG3, , [arg1] "r" (regs), [arg2] "r" (address), [arg3] "r" (&info)); - unreachable(); + BUG(); } #endif diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index 5ab7bd2f1983..bd5d101c5c37 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -101,9 +101,7 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, pmd_t *pmd; bool use_gbpage; - next = (addr & PUD_MASK) + PUD_SIZE; - if (next > end) - next = end; + next = pud_addr_end(addr, end); /* if this is already a gbpage, this portion is already mapped */ if (pud_leaf(*pud)) @@ -154,10 +152,7 @@ static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page, p4d_t *p4d = p4d_page + p4d_index(addr); pud_t *pud; - next = (addr & P4D_MASK) + P4D_SIZE; - if (next > end) - next = end; - + next = p4d_addr_end(addr, end); if (p4d_present(*p4d)) { pud = pud_offset(p4d, 0); result = ident_pud_init(info, pud, addr, next); @@ -199,10 +194,7 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, pgd_t *pgd = pgd_page + pgd_index(addr); p4d_t *p4d; - next = (addr & PGDIR_MASK) + PGDIR_SIZE; - if (next > end) - next = end; - + next = pgd_addr_end(addr, end); if (pgd_present(*pgd)) { p4d = p4d_offset(pgd, 0); result = ident_p4d_init(info, p4d, addr, next); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index c6d29f283001..bfa444a7dbb0 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -645,8 +645,13 @@ static void __init memory_map_top_down(unsigned long map_start, */ addr = memblock_phys_alloc_range(PMD_SIZE, PMD_SIZE, map_start, map_end); - memblock_phys_free(addr, PMD_SIZE); - real_end = addr + PMD_SIZE; + if (!addr) { + pr_warn("Failed to release memory for alloc_low_pages()"); + real_end = max(map_start, ALIGN_DOWN(map_end, PMD_SIZE)); + } else { + memblock_phys_free(addr, PMD_SIZE); + real_end = addr + PMD_SIZE; + } /* step_size need to be small so pgt_buf from BRK could cover it */ step_size = PMD_SIZE; @@ -1080,7 +1085,8 @@ struct execmem_info __init *execmem_arch_setup(void) start = MODULES_VADDR + offset; - if (IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX)) { + if (IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) && + cpu_feature_enabled(X86_FEATURE_PSE)) { pgprot = PAGE_KERNEL_ROX; flags = EXECMEM_KASAN_SHADOW | EXECMEM_ROX_CACHE; } else { diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index ac41b1e0940d..f288aad8dc74 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -582,7 +582,7 @@ static void __init lowmem_pfn_init(void) "only %luMB highmem pages available, ignoring highmem size of %luMB!\n" #define MSG_HIGHMEM_TRIMMED \ - "Warning: only 4GB will be used. Use a HIGHMEM64G enabled kernel!\n" + "Warning: only 4GB will be used. Support for for CONFIG_HIGHMEM64G was removed!\n" /* * We have more RAM than fits into lowmem - we try to put it into * highmem, also taking the highmem=x boot parameter into account: @@ -606,18 +606,13 @@ static void __init highmem_pfn_init(void) #ifndef CONFIG_HIGHMEM /* Maximum memory usable is what is directly addressable */ printk(KERN_WARNING "Warning only %ldMB will be used.\n", MAXMEM>>20); - if (max_pfn > MAX_NONPAE_PFN) - printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n"); - else - printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n"); + printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n"); max_pfn = MAXMEM_PFN; #else /* !CONFIG_HIGHMEM */ -#ifndef CONFIG_HIGHMEM64G if (max_pfn > MAX_NONPAE_PFN) { max_pfn = MAX_NONPAE_PFN; printk(KERN_WARNING MSG_HIGHMEM_TRIMMED); } -#endif /* !CONFIG_HIGHMEM64G */ #endif /* !CONFIG_HIGHMEM */ } diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 01ea7c6df303..519aa53114fa 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -469,8 +469,6 @@ phys_pte_init(pte_t *pte_page, unsigned long paddr, unsigned long paddr_end, !e820__mapped_any(paddr & PAGE_MASK, paddr_next, E820_TYPE_RAM) && !e820__mapped_any(paddr & PAGE_MASK, paddr_next, - E820_TYPE_RESERVED_KERN) && - !e820__mapped_any(paddr & PAGE_MASK, paddr_next, E820_TYPE_ACPI)) set_pte_init(pte, __pte(0), init); continue; @@ -526,8 +524,6 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end, !e820__mapped_any(paddr & PMD_MASK, paddr_next, E820_TYPE_RAM) && !e820__mapped_any(paddr & PMD_MASK, paddr_next, - E820_TYPE_RESERVED_KERN) && - !e820__mapped_any(paddr & PMD_MASK, paddr_next, E820_TYPE_ACPI)) set_pmd_init(pmd, __pmd(0), init); continue; @@ -615,8 +611,6 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end, !e820__mapped_any(paddr & PUD_MASK, paddr_next, E820_TYPE_RAM) && !e820__mapped_any(paddr & PUD_MASK, paddr_next, - E820_TYPE_RESERVED_KERN) && - !e820__mapped_any(paddr & PUD_MASK, paddr_next, E820_TYPE_ACPI)) set_pud_init(pud, __pud(0), init); continue; @@ -704,8 +698,6 @@ phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end, !e820__mapped_any(paddr & P4D_MASK, paddr_next, E820_TYPE_RAM) && !e820__mapped_any(paddr & P4D_MASK, paddr_next, - E820_TYPE_RESERVED_KERN) && - !e820__mapped_any(paddr & P4D_MASK, paddr_next, E820_TYPE_ACPI)) set_p4d_init(p4d, __p4d(0), init); continue; diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 8d29163568a7..42c90b420773 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -503,6 +503,14 @@ void iounmap(volatile void __iomem *addr) } EXPORT_SYMBOL(iounmap); +void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags) +{ + if ((flags & MEMREMAP_DEC) || cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) + return (void __force *)ioremap_cache(phys_addr, size); + + return (void __force *)ioremap_encrypted(phys_addr, size); +} + /* * Convert a physical pointer to a virtual kernel pointer for /dev/mem * access @@ -593,8 +601,7 @@ static bool memremap_should_map_decrypted(resource_size_t phys_addr, * Examine the physical address to determine if it is EFI data. Check * it against the boot params structure and EFI tables and memory types. */ -static bool memremap_is_efi_data(resource_size_t phys_addr, - unsigned long size) +static bool memremap_is_efi_data(resource_size_t phys_addr) { u64 paddr; @@ -632,42 +639,54 @@ static bool memremap_is_efi_data(resource_size_t phys_addr, * Examine the physical address to determine if it is boot data by checking * it against the boot params setup_data chain. */ -static bool memremap_is_setup_data(resource_size_t phys_addr, - unsigned long size) +static bool __ref __memremap_is_setup_data(resource_size_t phys_addr, bool early) { + unsigned int setup_data_sz = sizeof(struct setup_data); struct setup_indirect *indirect; struct setup_data *data; u64 paddr, paddr_next; paddr = boot_params.hdr.setup_data; while (paddr) { - unsigned int len; + unsigned int len, size; if (phys_addr == paddr) return true; - data = memremap(paddr, sizeof(*data), - MEMREMAP_WB | MEMREMAP_DEC); + if (early) + data = early_memremap_decrypted(paddr, setup_data_sz); + else + data = memremap(paddr, setup_data_sz, MEMREMAP_WB | MEMREMAP_DEC); if (!data) { - pr_warn("failed to memremap setup_data entry\n"); + pr_warn("failed to remap setup_data entry\n"); return false; } + size = setup_data_sz; + paddr_next = data->next; len = data->len; if ((phys_addr > paddr) && - (phys_addr < (paddr + sizeof(struct setup_data) + len))) { - memunmap(data); + (phys_addr < (paddr + setup_data_sz + len))) { + if (early) + early_memunmap(data, setup_data_sz); + else + memunmap(data); return true; } if (data->type == SETUP_INDIRECT) { - memunmap(data); - data = memremap(paddr, sizeof(*data) + len, - MEMREMAP_WB | MEMREMAP_DEC); + size += len; + if (early) { + early_memunmap(data, setup_data_sz); + data = early_memremap_decrypted(paddr, size); + } else { + memunmap(data); + data = memremap(paddr, size, MEMREMAP_WB | MEMREMAP_DEC); + } if (!data) { - pr_warn("failed to memremap indirect setup_data\n"); + pr_warn("failed to remap indirect setup_data\n"); return false; } @@ -679,7 +698,10 @@ static bool memremap_is_setup_data(resource_size_t phys_addr, } } - memunmap(data); + if (early) + early_memunmap(data, size); + else + memunmap(data); if ((phys_addr > paddr) && (phys_addr < (paddr + len))) return true; @@ -690,67 +712,14 @@ static bool memremap_is_setup_data(resource_size_t phys_addr, return false; } -/* - * Examine the physical address to determine if it is boot data by checking - * it against the boot params setup_data chain (early boot version). - */ -static bool __init early_memremap_is_setup_data(resource_size_t phys_addr, - unsigned long size) +static bool memremap_is_setup_data(resource_size_t phys_addr) { - struct setup_indirect *indirect; - struct setup_data *data; - u64 paddr, paddr_next; - - paddr = boot_params.hdr.setup_data; - while (paddr) { - unsigned int len, size; - - if (phys_addr == paddr) - return true; - - data = early_memremap_decrypted(paddr, sizeof(*data)); - if (!data) { - pr_warn("failed to early memremap setup_data entry\n"); - return false; - } - - size = sizeof(*data); - - paddr_next = data->next; - len = data->len; - - if ((phys_addr > paddr) && - (phys_addr < (paddr + sizeof(struct setup_data) + len))) { - early_memunmap(data, sizeof(*data)); - return true; - } - - if (data->type == SETUP_INDIRECT) { - size += len; - early_memunmap(data, sizeof(*data)); - data = early_memremap_decrypted(paddr, size); - if (!data) { - pr_warn("failed to early memremap indirect setup_data\n"); - return false; - } - - indirect = (struct setup_indirect *)data->data; - - if (indirect->type != SETUP_INDIRECT) { - paddr = indirect->addr; - len = indirect->len; - } - } - - early_memunmap(data, size); - - if ((phys_addr > paddr) && (phys_addr < (paddr + len))) - return true; - - paddr = paddr_next; - } + return __memremap_is_setup_data(phys_addr, false); +} - return false; +static bool __init early_memremap_is_setup_data(resource_size_t phys_addr) +{ + return __memremap_is_setup_data(phys_addr, true); } /* @@ -771,8 +740,8 @@ bool arch_memremap_can_ram_remap(resource_size_t phys_addr, unsigned long size, return false; if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { - if (memremap_is_setup_data(phys_addr, size) || - memremap_is_efi_data(phys_addr, size)) + if (memremap_is_setup_data(phys_addr) || + memremap_is_efi_data(phys_addr)) return false; } @@ -797,8 +766,8 @@ pgprot_t __init early_memremap_pgprot_adjust(resource_size_t phys_addr, encrypted_prot = true; if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { - if (early_memremap_is_setup_data(phys_addr, size) || - memremap_is_efi_data(phys_addr, size)) + if (early_memremap_is_setup_data(phys_addr) || + memremap_is_efi_data(phys_addr)) encrypted_prot = false; } diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 9dddf19a5571..0539efd0d216 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -1,5 +1,4 @@ // SPDX-License-Identifier: GPL-2.0 -#define DISABLE_BRANCH_PROFILING #define pr_fmt(fmt) "kasan: " fmt /* cpu_feature_enabled() cannot be used this early */ diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 11a93542d198..3c306de52fd4 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -113,8 +113,14 @@ void __init kernel_randomize_memory(void) memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) + CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING; - /* Adapt physical memory region size based on available memory */ - if (memory_tb < kaslr_regions[0].size_tb) + /* + * Adapt physical memory region size based on available memory, + * except when CONFIG_PCI_P2PDMA is enabled. P2PDMA exposes the + * device BAR space assuming the direct map space is large enough + * for creating a ZONE_DEVICE mapping in the direct map corresponding + * to the physical BAR address. + */ + if (!IS_ENABLED(CONFIG_PCI_P2PDMA) && (memory_tb < kaslr_regions[0].size_tb)) kaslr_regions[0].size_tb = memory_tb; /* diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 0a120d85d7bb..95bae74fdab2 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -94,6 +94,8 @@ void __init mem_encrypt_init(void) /* Call into SWIOTLB to update the SWIOTLB DMA buffers */ swiotlb_update_mem_attributes(); + snp_secure_tsc_prepare(); + print_mem_encrypt_feature_info(); } diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index 774f9677458f..7490ff6d83b1 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -7,8 +7,6 @@ * Author: Tom Lendacky <thomas.lendacky@amd.com> */ -#define DISABLE_BRANCH_PROFILING - #include <linux/linkage.h> #include <linux/init.h> #include <linux/mm.h> @@ -541,6 +539,9 @@ void __init sme_early_init(void) * kernel mapped. */ snp_update_svsm_ca(); + + if (sev_status & MSR_AMD64_SNP_SECURE_TSC) + setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); } void __init mem_encrypt_free_decrypted_mem(void) diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index e25288ee33c2..f8a33b25ae86 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -72,6 +72,7 @@ SYM_FUNC_START(sme_encrypt_execute) SYM_FUNC_END(sme_encrypt_execute) SYM_FUNC_START(__enc_copy) + ANNOTATE_NOENDBR /* * Routine used to encrypt memory in place. * This routine must be run outside of the kernel proper since diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index e6c7686f443a..5eecdd92da10 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -7,8 +7,6 @@ * Author: Tom Lendacky <thomas.lendacky@amd.com> */ -#define DISABLE_BRANCH_PROFILING - /* * Since we're dealing with identity mappings, physical and virtual * addresses are the same, so override these defines which are ultimately @@ -565,7 +563,7 @@ void __head sme_enable(struct boot_params *bp) } RIP_REL_REF(sme_me_mask) = me_mask; - physical_mask &= ~me_mask; - cc_vendor = CC_VENDOR_AMD; + RIP_REL_REF(physical_mask) &= ~me_mask; + RIP_REL_REF(cc_vendor) = CC_VENDOR_AMD; cc_set_mask(me_mask); } diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index b8a6ffffb451..5ed2109211da 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -84,7 +84,6 @@ static unsigned long mmap_base(unsigned long rnd, unsigned long task_size, { unsigned long gap = rlim_stack->rlim_cur; unsigned long pad = stack_maxrandom_size(task_size) + stack_guard_gap; - unsigned long gap_min, gap_max; /* Values close to RLIM_INFINITY can overflow. */ if (gap + pad > gap) @@ -94,13 +93,7 @@ static unsigned long mmap_base(unsigned long rnd, unsigned long task_size, * Top of mmap area (just below the process stack). * Leave an at least ~128 MB hole with possible stack randomization. */ - gap_min = SIZE_128M; - gap_max = (task_size / 6) * 5; - - if (gap < gap_min) - gap = gap_min; - else if (gap > gap_max) - gap = gap_max; + gap = clamp(gap, SIZE_128M, (task_size / 6) * 5); return PAGE_ALIGN(task_size - gap - rnd); } diff --git a/arch/x86/mm/pat/cpa-test.c b/arch/x86/mm/pat/cpa-test.c index 3d2f7f0a6ed1..ad3c1feec990 100644 --- a/arch/x86/mm/pat/cpa-test.c +++ b/arch/x86/mm/pat/cpa-test.c @@ -183,7 +183,7 @@ static int pageattr_test(void) break; case 1: - err = change_page_attr_set(addrs, len[1], PAGE_CPA_TEST, 1); + err = change_page_attr_set(addrs, len[i], PAGE_CPA_TEST, 1); break; case 2: diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index feb8cc6a12bf..e40861c9cb90 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -43,6 +43,7 @@ #include <linux/fs.h> #include <linux/rbtree.h> +#include <asm/cpu_device_id.h> #include <asm/cacheflush.h> #include <asm/cacheinfo.h> #include <asm/processor.h> @@ -290,9 +291,8 @@ void __init pat_bp_init(void) return; } - if ((c->x86_vendor == X86_VENDOR_INTEL) && - (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || - ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) { + if ((c->x86_vfm >= INTEL_PENTIUM_PRO && c->x86_vfm <= INTEL_PENTIUM_M_DOTHAN) || + (c->x86_vfm >= INTEL_P4_WILLAMETTE && c->x86_vfm <= INTEL_P4_CEDARMILL)) { /* * PAT support with the lower four entries. Intel Pentium 2, * 3, M, and 4 are affected by PAT errata, which makes the diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 95bc50a8541c..72405d315b41 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -32,8 +32,6 @@ #include <asm/pgalloc.h> #include <asm/proto.h> #include <asm/memtype.h> -#include <asm/hyperv-tlfs.h> -#include <asm/mshyperv.h> #include "../mm_internal.h" @@ -75,6 +73,7 @@ static DEFINE_SPINLOCK(cpa_lock); #define CPA_ARRAY 2 #define CPA_PAGES_ARRAY 4 #define CPA_NO_CHECK_ALIAS 8 /* Do not search for aliases */ +#define CPA_COLLAPSE 16 /* try to collapse large pages */ static inline pgprot_t cachemode2pgprot(enum page_cache_mode pcm) { @@ -107,6 +106,18 @@ static void split_page_count(int level) direct_pages_count[level - 1] += PTRS_PER_PTE; } +static void collapse_page_count(int level) +{ + direct_pages_count[level]++; + if (system_state == SYSTEM_RUNNING) { + if (level == PG_LEVEL_2M) + count_vm_event(DIRECT_MAP_LEVEL2_COLLAPSE); + else if (level == PG_LEVEL_1G) + count_vm_event(DIRECT_MAP_LEVEL3_COLLAPSE); + } + direct_pages_count[level - 1] -= PTRS_PER_PTE; +} + void arch_report_meminfo(struct seq_file *m) { seq_printf(m, "DirectMap4k: %8lu kB\n", @@ -124,6 +135,7 @@ void arch_report_meminfo(struct seq_file *m) } #else static inline void split_page_count(int level) { } +static inline void collapse_page_count(int level) { } #endif #ifdef CONFIG_X86_CPA_STATISTICS @@ -213,14 +225,14 @@ within(unsigned long addr, unsigned long start, unsigned long end) return addr >= start && addr < end; } +#ifdef CONFIG_X86_64 + static inline int within_inclusive(unsigned long addr, unsigned long start, unsigned long end) { return addr >= start && addr <= end; } -#ifdef CONFIG_X86_64 - /* * The kernel image is mapped into two places in the virtual address space * (addresses without KASLR, of course): @@ -396,16 +408,49 @@ static void __cpa_flush_tlb(void *data) flush_tlb_one_kernel(fix_addr(__cpa_addr(cpa, i))); } -static void cpa_flush(struct cpa_data *data, int cache) +static int collapse_large_pages(unsigned long addr, struct list_head *pgtables); + +static void cpa_collapse_large_pages(struct cpa_data *cpa) +{ + unsigned long start, addr, end; + struct ptdesc *ptdesc, *tmp; + LIST_HEAD(pgtables); + int collapsed = 0; + int i; + + if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) { + for (i = 0; i < cpa->numpages; i++) + collapsed += collapse_large_pages(__cpa_addr(cpa, i), + &pgtables); + } else { + addr = __cpa_addr(cpa, 0); + start = addr & PMD_MASK; + end = addr + PAGE_SIZE * cpa->numpages; + + for (addr = start; within(addr, start, end); addr += PMD_SIZE) + collapsed += collapse_large_pages(addr, &pgtables); + } + + if (!collapsed) + return; + + flush_tlb_all(); + + list_for_each_entry_safe(ptdesc, tmp, &pgtables, pt_list) { + list_del(&ptdesc->pt_list); + __free_page(ptdesc_page(ptdesc)); + } +} + +static void cpa_flush(struct cpa_data *cpa, int cache) { - struct cpa_data *cpa = data; unsigned int i; BUG_ON(irqs_disabled() && !early_boot_irqs_disabled); if (cache && !static_cpu_has(X86_FEATURE_CLFLUSH)) { cpa_flush_all(cache); - return; + goto collapse_large_pages; } if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling) @@ -414,7 +459,7 @@ static void cpa_flush(struct cpa_data *data, int cache) on_each_cpu(__cpa_flush_tlb, cpa, 1); if (!cache) - return; + goto collapse_large_pages; mb(); for (i = 0; i < cpa->numpages; i++) { @@ -430,6 +475,10 @@ static void cpa_flush(struct cpa_data *data, int cache) clflush_cache_range_opt((void *)fix_addr(addr), PAGE_SIZE); } mb(); + +collapse_large_pages: + if (cpa->flags & CPA_COLLAPSE) + cpa_collapse_large_pages(cpa); } static bool overlaps(unsigned long r1_start, unsigned long r1_end, @@ -1199,6 +1248,161 @@ static int split_large_page(struct cpa_data *cpa, pte_t *kpte, return 0; } +static int collapse_pmd_page(pmd_t *pmd, unsigned long addr, + struct list_head *pgtables) +{ + pmd_t _pmd, old_pmd; + pte_t *pte, first; + unsigned long pfn; + pgprot_t pgprot; + int i = 0; + + addr &= PMD_MASK; + pte = pte_offset_kernel(pmd, addr); + first = *pte; + pfn = pte_pfn(first); + + /* Make sure alignment is suitable */ + if (PFN_PHYS(pfn) & ~PMD_MASK) + return 0; + + /* The page is 4k intentionally */ + if (pte_flags(first) & _PAGE_KERNEL_4K) + return 0; + + /* Check that the rest of PTEs are compatible with the first one */ + for (i = 1, pte++; i < PTRS_PER_PTE; i++, pte++) { + pte_t entry = *pte; + + if (!pte_present(entry)) + return 0; + if (pte_flags(entry) != pte_flags(first)) + return 0; + if (pte_pfn(entry) != pte_pfn(first) + i) + return 0; + } + + old_pmd = *pmd; + + /* Success: set up a large page */ + pgprot = pgprot_4k_2_large(pte_pgprot(first)); + pgprot_val(pgprot) |= _PAGE_PSE; + _pmd = pfn_pmd(pfn, pgprot); + set_pmd(pmd, _pmd); + + /* Queue the page table to be freed after TLB flush */ + list_add(&page_ptdesc(pmd_page(old_pmd))->pt_list, pgtables); + + if (IS_ENABLED(CONFIG_X86_32) && !SHARED_KERNEL_PMD) { + struct page *page; + + /* Update all PGD tables to use the same large page */ + list_for_each_entry(page, &pgd_list, lru) { + pgd_t *pgd = (pgd_t *)page_address(page) + pgd_index(addr); + p4d_t *p4d = p4d_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); + pmd_t *pmd = pmd_offset(pud, addr); + /* Something is wrong if entries doesn't match */ + if (WARN_ON(pmd_val(old_pmd) != pmd_val(*pmd))) + continue; + set_pmd(pmd, _pmd); + } + } + + if (virt_addr_valid(addr) && pfn_range_is_mapped(pfn, pfn + 1)) + collapse_page_count(PG_LEVEL_2M); + + return 1; +} + +static int collapse_pud_page(pud_t *pud, unsigned long addr, + struct list_head *pgtables) +{ + unsigned long pfn; + pmd_t *pmd, first; + int i; + + if (!direct_gbpages) + return 0; + + addr &= PUD_MASK; + pmd = pmd_offset(pud, addr); + first = *pmd; + + /* + * To restore PUD page all PMD entries must be large and + * have suitable alignment + */ + pfn = pmd_pfn(first); + if (!pmd_leaf(first) || (PFN_PHYS(pfn) & ~PUD_MASK)) + return 0; + + /* + * To restore PUD page, all following PMDs must be compatible with the + * first one. + */ + for (i = 1, pmd++; i < PTRS_PER_PMD; i++, pmd++) { + pmd_t entry = *pmd; + + if (!pmd_present(entry) || !pmd_leaf(entry)) + return 0; + if (pmd_flags(entry) != pmd_flags(first)) + return 0; + if (pmd_pfn(entry) != pmd_pfn(first) + i * PTRS_PER_PTE) + return 0; + } + + /* Restore PUD page and queue page table to be freed after TLB flush */ + list_add(&page_ptdesc(pud_page(*pud))->pt_list, pgtables); + set_pud(pud, pfn_pud(pfn, pmd_pgprot(first))); + + if (virt_addr_valid(addr) && pfn_range_is_mapped(pfn, pfn + 1)) + collapse_page_count(PG_LEVEL_1G); + + return 1; +} + +/* + * Collapse PMD and PUD pages in the kernel mapping around the address where + * possible. + * + * Caller must flush TLB and free page tables queued on the list before + * touching the new entries. CPU must not see TLB entries of different size + * with different attributes. + */ +static int collapse_large_pages(unsigned long addr, struct list_head *pgtables) +{ + int collapsed = 0; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + addr &= PMD_MASK; + + spin_lock(&pgd_lock); + pgd = pgd_offset_k(addr); + if (pgd_none(*pgd)) + goto out; + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) + goto out; + pud = pud_offset(p4d, addr); + if (!pud_present(*pud) || pud_leaf(*pud)) + goto out; + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd) || pmd_leaf(*pmd)) + goto out; + + collapsed = collapse_pmd_page(pmd, addr, pgtables); + if (collapsed) + collapsed += collapse_pud_page(pud, addr, pgtables); + +out: + spin_unlock(&pgd_lock); + return collapsed; +} + static bool try_to_free_pte_page(pte_t *pte) { int i; @@ -1944,19 +2148,6 @@ static inline int cpa_clear_pages_array(struct page **pages, int numpages, CPA_PAGES_ARRAY, pages); } -/* - * __set_memory_prot is an internal helper for callers that have been passed - * a pgprot_t value from upper layers and a reservation has already been taken. - * If you want to set the pgprot to a specific page protocol, use the - * set_memory_xx() functions. - */ -int __set_memory_prot(unsigned long addr, int numpages, pgprot_t prot) -{ - return change_page_attr_set_clr(&addr, numpages, prot, - __pgprot(~pgprot_val(prot)), 0, 0, - NULL); -} - int _set_memory_uc(unsigned long addr, int numpages) { /* @@ -2122,7 +2313,8 @@ int set_memory_rox(unsigned long addr, int numpages) if (__supported_pte_mask & _PAGE_NX) clr.pgprot |= _PAGE_NX; - return change_page_attr_clear(&addr, numpages, clr, 0); + return change_page_attr_set_clr(&addr, numpages, __pgprot(0), clr, 0, + CPA_COLLAPSE, NULL); } int set_memory_rw(unsigned long addr, int numpages) @@ -2149,7 +2341,8 @@ int set_memory_p(unsigned long addr, int numpages) int set_memory_4k(unsigned long addr, int numpages) { - return change_page_attr_set_clr(&addr, numpages, __pgprot(0), + return change_page_attr_set_clr(&addr, numpages, + __pgprot(_PAGE_KERNEL_4K), __pgprot(0), 1, 0, NULL); } @@ -2422,7 +2615,7 @@ static int __set_pages_np(struct page *page, int numpages) .pgd = NULL, .numpages = numpages, .mask_set = __pgprot(0), - .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW), + .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY), .flags = CPA_NO_CHECK_ALIAS }; /* @@ -2509,7 +2702,7 @@ int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, .pgd = pgd, .numpages = numpages, .mask_set = __pgprot(0), - .mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW)), + .mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW|_PAGE_DIRTY)), .flags = CPA_NO_CHECK_ALIAS, }; @@ -2552,7 +2745,7 @@ int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address, .pgd = pgd, .numpages = numpages, .mask_set = __pgprot(0), - .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW), + .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY), .flags = CPA_NO_CHECK_ALIAS, }; diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 5745a354a241..cec321fb74f2 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -12,55 +12,20 @@ phys_addr_t physical_mask __ro_after_init = (1ULL << __PHYSICAL_MASK_SHIFT) - 1; EXPORT_SYMBOL(physical_mask); #endif -#ifdef CONFIG_HIGHPTE -#define PGTABLE_HIGHMEM __GFP_HIGHMEM -#else -#define PGTABLE_HIGHMEM 0 -#endif - -#ifndef CONFIG_PARAVIRT -static inline -void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table) -{ - tlb_remove_page(tlb, table); -} -#endif - -gfp_t __userpte_alloc_gfp = GFP_PGTABLE_USER | PGTABLE_HIGHMEM; - pgtable_t pte_alloc_one(struct mm_struct *mm) { - return __pte_alloc_one(mm, __userpte_alloc_gfp); + return __pte_alloc_one(mm, GFP_PGTABLE_USER); } -static int __init setup_userpte(char *arg) -{ - if (!arg) - return -EINVAL; - - /* - * "userpte=nohigh" disables allocation of user pagetables in - * high memory. - */ - if (strcmp(arg, "nohigh") == 0) - __userpte_alloc_gfp &= ~__GFP_HIGHMEM; - else - return -EINVAL; - return 0; -} -early_param("userpte", setup_userpte); - void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) { - pagetable_pte_dtor(page_ptdesc(pte)); paravirt_release_pte(page_to_pfn(pte)); - paravirt_tlb_remove_table(tlb, pte); + tlb_remove_table(tlb, page_ptdesc(pte)); } #if CONFIG_PGTABLE_LEVELS > 2 void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) { - struct ptdesc *ptdesc = virt_to_ptdesc(pmd); paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT); /* * NOTE! For PAE, any changes to the top page-directory-pointer-table @@ -69,25 +34,21 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) #ifdef CONFIG_X86_PAE tlb->need_flush_all = 1; #endif - pagetable_pmd_dtor(ptdesc); - paravirt_tlb_remove_table(tlb, ptdesc_page(ptdesc)); + tlb_remove_table(tlb, virt_to_ptdesc(pmd)); } #if CONFIG_PGTABLE_LEVELS > 3 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) { - struct ptdesc *ptdesc = virt_to_ptdesc(pud); - - pagetable_pud_dtor(ptdesc); paravirt_release_pud(__pa(pud) >> PAGE_SHIFT); - paravirt_tlb_remove_table(tlb, virt_to_page(pud)); + tlb_remove_table(tlb, virt_to_ptdesc(pud)); } #if CONFIG_PGTABLE_LEVELS > 4 void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d) { paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT); - paravirt_tlb_remove_table(tlb, virt_to_page(p4d)); + tlb_remove_table(tlb, virt_to_ptdesc(p4d)); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ @@ -222,7 +183,7 @@ static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) if (pmds[i]) { ptdesc = virt_to_ptdesc(pmds[i]); - pagetable_pmd_dtor(ptdesc); + pagetable_dtor(ptdesc); pagetable_free(ptdesc); mm_dec_nr_pmds(mm); } @@ -392,15 +353,14 @@ void __init pgtable_cache_init(void) SLAB_PANIC, NULL); } -static inline pgd_t *_pgd_alloc(void) +static inline pgd_t *_pgd_alloc(struct mm_struct *mm) { /* * If no SHARED_KERNEL_PMD, PAE kernel is running as a Xen domain. * We allocate one page for pgd. */ if (!SHARED_KERNEL_PMD) - return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER, - PGD_ALLOCATION_ORDER); + return __pgd_alloc(mm, PGD_ALLOCATION_ORDER); /* * Now PAE kernel is not running as a Xen domain. We can allocate @@ -409,24 +369,23 @@ static inline pgd_t *_pgd_alloc(void) return kmem_cache_alloc(pgd_cache, GFP_PGTABLE_USER); } -static inline void _pgd_free(pgd_t *pgd) +static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd) { if (!SHARED_KERNEL_PMD) - free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER); + __pgd_free(mm, pgd); else kmem_cache_free(pgd_cache, pgd); } #else -static inline pgd_t *_pgd_alloc(void) +static inline pgd_t *_pgd_alloc(struct mm_struct *mm) { - return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER, - PGD_ALLOCATION_ORDER); + return __pgd_alloc(mm, PGD_ALLOCATION_ORDER); } -static inline void _pgd_free(pgd_t *pgd) +static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd) { - free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER); + __pgd_free(mm, pgd); } #endif /* CONFIG_X86_PAE */ @@ -436,7 +395,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS]; pmd_t *pmds[MAX_PREALLOCATED_PMDS]; - pgd = _pgd_alloc(); + pgd = _pgd_alloc(mm); if (pgd == NULL) goto out; @@ -479,7 +438,7 @@ out_free_pmds: if (sizeof(pmds) != 0) free_pmds(mm, pmds, PREALLOCATED_PMDS); out_free_pgd: - _pgd_free(pgd); + _pgd_free(mm, pgd); out: return NULL; } @@ -489,7 +448,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd) pgd_mop_up_pmds(mm, pgd); pgd_dtor(pgd); paravirt_pgd_free(mm, pgd); - _pgd_free(pgd); + _pgd_free(mm, pgd); } /* @@ -856,7 +815,7 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr) free_page((unsigned long)pmd_sv); - pagetable_pmd_dtor(virt_to_ptdesc(pmd)); + pagetable_dtor(virt_to_ptdesc(pmd)); free_page((unsigned long)pmd); return 1; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index a2becb85bea7..e459d97ef397 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -74,13 +74,15 @@ * use different names for each of them: * * ASID - [0, TLB_NR_DYN_ASIDS-1] - * the canonical identifier for an mm + * the canonical identifier for an mm, dynamically allocated on each CPU + * [TLB_NR_DYN_ASIDS, MAX_ASID_AVAILABLE-1] + * the canonical, global identifier for an mm, identical across all CPUs * - * kPCID - [1, TLB_NR_DYN_ASIDS] + * kPCID - [1, MAX_ASID_AVAILABLE] * the value we write into the PCID part of CR3; corresponds to the * ASID+1, because PCID 0 is special. * - * uPCID - [2048 + 1, 2048 + TLB_NR_DYN_ASIDS] + * uPCID - [2048 + 1, 2048 + MAX_ASID_AVAILABLE] * for KPTI each mm has two address spaces and thus needs two * PCID values, but we can still do with a single ASID denomination * for each mm. Corresponds to kPCID + 2048. @@ -225,6 +227,20 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen, return; } + /* + * TLB consistency for global ASIDs is maintained with hardware assisted + * remote TLB flushing. Global ASIDs are always up to date. + */ + if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) { + u16 global_asid = mm_global_asid(next); + + if (global_asid) { + *new_asid = global_asid; + *need_flush = false; + return; + } + } + if (this_cpu_read(cpu_tlbstate.invalidate_other)) clear_asid_other(); @@ -252,6 +268,268 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen, } /* + * Global ASIDs are allocated for multi-threaded processes that are + * active on multiple CPUs simultaneously, giving each of those + * processes the same PCID on every CPU, for use with hardware-assisted + * TLB shootdown on remote CPUs, like AMD INVLPGB or Intel RAR. + * + * These global ASIDs are held for the lifetime of the process. + */ +static DEFINE_RAW_SPINLOCK(global_asid_lock); +static u16 last_global_asid = MAX_ASID_AVAILABLE; +static DECLARE_BITMAP(global_asid_used, MAX_ASID_AVAILABLE); +static DECLARE_BITMAP(global_asid_freed, MAX_ASID_AVAILABLE); +static int global_asid_available = MAX_ASID_AVAILABLE - TLB_NR_DYN_ASIDS - 1; + +/* + * When the search for a free ASID in the global ASID space reaches + * MAX_ASID_AVAILABLE, a global TLB flush guarantees that previously + * freed global ASIDs are safe to re-use. + * + * This way the global flush only needs to happen at ASID rollover + * time, and not at ASID allocation time. + */ +static void reset_global_asid_space(void) +{ + lockdep_assert_held(&global_asid_lock); + + invlpgb_flush_all_nonglobals(); + + /* + * The TLB flush above makes it safe to re-use the previously + * freed global ASIDs. + */ + bitmap_andnot(global_asid_used, global_asid_used, + global_asid_freed, MAX_ASID_AVAILABLE); + bitmap_clear(global_asid_freed, 0, MAX_ASID_AVAILABLE); + + /* Restart the search from the start of global ASID space. */ + last_global_asid = TLB_NR_DYN_ASIDS; +} + +static u16 allocate_global_asid(void) +{ + u16 asid; + + lockdep_assert_held(&global_asid_lock); + + /* The previous allocation hit the edge of available address space */ + if (last_global_asid >= MAX_ASID_AVAILABLE - 1) + reset_global_asid_space(); + + asid = find_next_zero_bit(global_asid_used, MAX_ASID_AVAILABLE, last_global_asid); + + if (asid >= MAX_ASID_AVAILABLE && !global_asid_available) { + /* This should never happen. */ + VM_WARN_ONCE(1, "Unable to allocate global ASID despite %d available\n", + global_asid_available); + return 0; + } + + /* Claim this global ASID. */ + __set_bit(asid, global_asid_used); + last_global_asid = asid; + global_asid_available--; + return asid; +} + +/* + * Check whether a process is currently active on more than @threshold CPUs. + * This is a cheap estimation on whether or not it may make sense to assign + * a global ASID to this process, and use broadcast TLB invalidation. + */ +static bool mm_active_cpus_exceeds(struct mm_struct *mm, int threshold) +{ + int count = 0; + int cpu; + + /* This quick check should eliminate most single threaded programs. */ + if (cpumask_weight(mm_cpumask(mm)) <= threshold) + return false; + + /* Slower check to make sure. */ + for_each_cpu(cpu, mm_cpumask(mm)) { + /* Skip the CPUs that aren't really running this process. */ + if (per_cpu(cpu_tlbstate.loaded_mm, cpu) != mm) + continue; + + if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu)) + continue; + + if (++count > threshold) + return true; + } + return false; +} + +/* + * Assign a global ASID to the current process, protecting against + * races between multiple threads in the process. + */ +static void use_global_asid(struct mm_struct *mm) +{ + u16 asid; + + guard(raw_spinlock_irqsave)(&global_asid_lock); + + /* This process is already using broadcast TLB invalidation. */ + if (mm_global_asid(mm)) + return; + + /* + * The last global ASID was consumed while waiting for the lock. + * + * If this fires, a more aggressive ASID reuse scheme might be + * needed. + */ + if (!global_asid_available) { + VM_WARN_ONCE(1, "Ran out of global ASIDs\n"); + return; + } + + asid = allocate_global_asid(); + if (!asid) + return; + + mm_assign_global_asid(mm, asid); +} + +void mm_free_global_asid(struct mm_struct *mm) +{ + if (!cpu_feature_enabled(X86_FEATURE_INVLPGB)) + return; + + if (!mm_global_asid(mm)) + return; + + guard(raw_spinlock_irqsave)(&global_asid_lock); + + /* The global ASID can be re-used only after flush at wrap-around. */ +#ifdef CONFIG_BROADCAST_TLB_FLUSH + __set_bit(mm->context.global_asid, global_asid_freed); + + mm->context.global_asid = 0; + global_asid_available++; +#endif +} + +/* + * Is the mm transitioning from a CPU-local ASID to a global ASID? + */ +static bool mm_needs_global_asid(struct mm_struct *mm, u16 asid) +{ + u16 global_asid = mm_global_asid(mm); + + if (!cpu_feature_enabled(X86_FEATURE_INVLPGB)) + return false; + + /* Process is transitioning to a global ASID */ + if (global_asid && asid != global_asid) + return true; + + return false; +} + +/* + * x86 has 4k ASIDs (2k when compiled with KPTI), but the largest x86 + * systems have over 8k CPUs. Because of this potential ASID shortage, + * global ASIDs are handed out to processes that have frequent TLB + * flushes and are active on 4 or more CPUs simultaneously. + */ +static void consider_global_asid(struct mm_struct *mm) +{ + if (!cpu_feature_enabled(X86_FEATURE_INVLPGB)) + return; + + /* Check every once in a while. */ + if ((current->pid & 0x1f) != (jiffies & 0x1f)) + return; + + /* + * Assign a global ASID if the process is active on + * 4 or more CPUs simultaneously. + */ + if (mm_active_cpus_exceeds(mm, 3)) + use_global_asid(mm); +} + +static void finish_asid_transition(struct flush_tlb_info *info) +{ + struct mm_struct *mm = info->mm; + int bc_asid = mm_global_asid(mm); + int cpu; + + if (!mm_in_asid_transition(mm)) + return; + + for_each_cpu(cpu, mm_cpumask(mm)) { + /* + * The remote CPU is context switching. Wait for that to + * finish, to catch the unlikely case of it switching to + * the target mm with an out of date ASID. + */ + while (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm, cpu)) == LOADED_MM_SWITCHING) + cpu_relax(); + + if (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm, cpu)) != mm) + continue; + + /* + * If at least one CPU is not using the global ASID yet, + * send a TLB flush IPI. The IPI should cause stragglers + * to transition soon. + * + * This can race with the CPU switching to another task; + * that results in a (harmless) extra IPI. + */ + if (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm_asid, cpu)) != bc_asid) { + flush_tlb_multi(mm_cpumask(info->mm), info); + return; + } + } + + /* All the CPUs running this process are using the global ASID. */ + mm_clear_asid_transition(mm); +} + +static void broadcast_tlb_flush(struct flush_tlb_info *info) +{ + bool pmd = info->stride_shift == PMD_SHIFT; + unsigned long asid = mm_global_asid(info->mm); + unsigned long addr = info->start; + + /* + * TLB flushes with INVLPGB are kicked off asynchronously. + * The inc_mm_tlb_gen() guarantees page table updates are done + * before these TLB flushes happen. + */ + if (info->end == TLB_FLUSH_ALL) { + invlpgb_flush_single_pcid_nosync(kern_pcid(asid)); + /* Do any CPUs supporting INVLPGB need PTI? */ + if (cpu_feature_enabled(X86_FEATURE_PTI)) + invlpgb_flush_single_pcid_nosync(user_pcid(asid)); + } else do { + unsigned long nr = 1; + + if (info->stride_shift <= PMD_SHIFT) { + nr = (info->end - addr) >> info->stride_shift; + nr = clamp_val(nr, 1, invlpgb_count_max); + } + + invlpgb_flush_user_nr_nosync(kern_pcid(asid), addr, nr, pmd); + if (cpu_feature_enabled(X86_FEATURE_PTI)) + invlpgb_flush_user_nr_nosync(user_pcid(asid), addr, nr, pmd); + + addr += nr << info->stride_shift; + } while (addr < info->end); + + finish_asid_transition(info); + + /* Wait for the INVLPGBs kicked off above to finish. */ + __tlbsync(); +} + +/* * Given an ASID, flush the corresponding user ASID. We can delay this * until the next time we switch to it. * @@ -447,8 +725,7 @@ static void cond_mitigation(struct task_struct *next) * different context than the user space task which ran * last on this CPU. */ - if ((prev_mm & ~LAST_USER_MM_SPEC_MASK) != - (unsigned long)next->mm) + if ((prev_mm & ~LAST_USER_MM_SPEC_MASK) != (unsigned long)next->mm) indirect_branch_prediction_barrier(); } @@ -556,7 +833,8 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next, */ if (prev == next) { /* Not actually switching mm's */ - VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != + VM_WARN_ON(is_dyn_asid(prev_asid) && + this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != next->context.ctx_id); /* @@ -573,6 +851,20 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next, !cpumask_test_cpu(cpu, mm_cpumask(next)))) cpumask_set_cpu(cpu, mm_cpumask(next)); + /* Check if the current mm is transitioning to a global ASID */ + if (mm_needs_global_asid(next, prev_asid)) { + next_tlb_gen = atomic64_read(&next->context.tlb_gen); + choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush); + goto reload_tlb; + } + + /* + * Broadcast TLB invalidation keeps this ASID up to date + * all the time. + */ + if (is_global_asid(prev_asid)) + return; + /* * If the CPU is not in lazy TLB mode, we are just switching * from one thread in a process to another thread in the same @@ -607,30 +899,32 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next, cond_mitigation(tsk); /* - * Stop remote flushes for the previous mm. - * Skip kernel threads; we never send init_mm TLB flushing IPIs, - * but the bitmap manipulation can cause cache line contention. + * Let nmi_uaccess_okay() and finish_asid_transition() + * know that CR3 is changing. */ - if (prev != &init_mm) { - VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, - mm_cpumask(prev))); - cpumask_clear_cpu(cpu, mm_cpumask(prev)); - } + this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING); + barrier(); + + /* + * Leave this CPU in prev's mm_cpumask. Atomic writes to + * mm_cpumask can be expensive under contention. The CPU + * will be removed lazily at TLB flush time. + */ + VM_WARN_ON_ONCE(prev != &init_mm && !cpumask_test_cpu(cpu, + mm_cpumask(prev))); /* Start receiving IPIs and then read tlb_gen (and LAM below) */ - if (next != &init_mm) + if (next != &init_mm && !cpumask_test_cpu(cpu, mm_cpumask(next))) cpumask_set_cpu(cpu, mm_cpumask(next)); next_tlb_gen = atomic64_read(&next->context.tlb_gen); choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush); - - /* Let nmi_uaccess_okay() know that we're changing CR3. */ - this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING); - barrier(); } +reload_tlb: new_lam = mm_lam_cr3_mask(next); if (need_flush) { + VM_WARN_ON_ONCE(is_global_asid(new_asid)); this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); load_new_mm_cr3(next->pgd, new_asid, new_lam, true); @@ -749,7 +1043,7 @@ static void flush_tlb_func(void *info) 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 local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen); + u64 local_tlb_gen; bool local = smp_processor_id() == f->initiating_cpu; unsigned long nr_invalidate = 0; u64 mm_tlb_gen; @@ -760,15 +1054,28 @@ static void flush_tlb_func(void *info) 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; + /* The CPU was left in the mm_cpumask of the target mm. Clear it. */ + if (f->mm && f->mm != loaded_mm) { + cpumask_clear_cpu(raw_smp_processor_id(), mm_cpumask(f->mm)); + trace_tlb_flush(TLB_REMOTE_WRONG_CPU, 0); + return; } if (unlikely(loaded_mm == &init_mm)) return; + /* Reload the ASID if transitioning into or out of a global ASID */ + if (mm_needs_global_asid(loaded_mm, loaded_mm_asid)) { + switch_mm_irqs_off(NULL, loaded_mm, NULL); + loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); + } + + /* Broadcast ASIDs are always kept up to date with INVLPGB. */ + if (is_global_asid(loaded_mm_asid)) + return; + VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) != loaded_mm->context.ctx_id); @@ -786,6 +1093,8 @@ static void flush_tlb_func(void *info) return; } + local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen); + if (unlikely(f->new_tlb_gen != TLB_GENERATION_INVALID && f->new_tlb_gen <= local_tlb_gen)) { /* @@ -893,9 +1202,36 @@ done: nr_invalidate); } -static bool tlb_is_not_lazy(int cpu, void *data) +static bool should_flush_tlb(int cpu, void *data) { - return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu); + struct flush_tlb_info *info = data; + + /* Lazy TLB will get flushed at the next context switch. */ + if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu)) + return false; + + /* No mm means kernel memory flush. */ + if (!info->mm) + return true; + + /* The target mm is loaded, and the CPU is not lazy. */ + if (per_cpu(cpu_tlbstate.loaded_mm, cpu) == info->mm) + return true; + + /* In cpumask, but not the loaded mm? Periodically remove by flushing. */ + if (info->trim_cpumask) + return true; + + return false; +} + +static bool should_trim_cpumask(struct mm_struct *mm) +{ + if (time_after(jiffies, READ_ONCE(mm->context.next_trim_cpumask))) { + WRITE_ONCE(mm->context.next_trim_cpumask, jiffies + HZ); + return true; + } + return false; } DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared); @@ -926,10 +1262,10 @@ STATIC_NOPV void native_flush_tlb_multi(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) + if (info->freed_tables || mm_in_asid_transition(info->mm)) on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true); else - on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func, + on_each_cpu_cond_mask(should_flush_tlb, flush_tlb_func, (void *)info, 1, cpumask); } @@ -973,6 +1309,15 @@ static struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm, BUG_ON(this_cpu_inc_return(flush_tlb_info_idx) != 1); #endif + /* + * If the number of flushes is so large that a full flush + * would be faster, do a full flush. + */ + if ((end - start) >> stride_shift > tlb_single_page_flush_ceiling) { + start = 0; + end = TLB_FLUSH_ALL; + } + info->start = start; info->end = end; info->mm = mm; @@ -980,6 +1325,7 @@ static struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm, info->freed_tables = freed_tables; info->new_tlb_gen = new_tlb_gen; info->initiating_cpu = smp_processor_id(); + info->trim_cpumask = 0; return info; } @@ -998,17 +1344,8 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, bool freed_tables) { struct flush_tlb_info *info; + int cpu = get_cpu(); u64 new_tlb_gen; - int cpu; - - cpu = get_cpu(); - - /* Should we flush just the requested range? */ - if ((end == TLB_FLUSH_ALL) || - ((end - start) >> stride_shift) > tlb_single_page_flush_ceiling) { - start = 0; - end = TLB_FLUSH_ALL; - } /* This is also a barrier that synchronizes with switch_mm(). */ new_tlb_gen = inc_mm_tlb_gen(mm); @@ -1021,8 +1358,12 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, * 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) { + if (mm_global_asid(mm)) { + broadcast_tlb_flush(info); + } else if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) { + info->trim_cpumask = should_trim_cpumask(mm); flush_tlb_multi(mm_cpumask(mm), info); + consider_global_asid(mm); } else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) { lockdep_assert_irqs_enabled(); local_irq_disable(); @@ -1035,7 +1376,6 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end); } - static void do_flush_tlb_all(void *info) { count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); @@ -1045,7 +1385,32 @@ static void do_flush_tlb_all(void *info) void flush_tlb_all(void) { count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); - on_each_cpu(do_flush_tlb_all, NULL, 1); + + /* First try (faster) hardware-assisted TLB invalidation. */ + if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) + invlpgb_flush_all(); + else + /* Fall back to the IPI-based invalidation. */ + on_each_cpu(do_flush_tlb_all, NULL, 1); +} + +/* Flush an arbitrarily large range of memory with INVLPGB. */ +static void invlpgb_kernel_range_flush(struct flush_tlb_info *info) +{ + unsigned long addr, nr; + + for (addr = info->start; addr < info->end; addr += nr << PAGE_SHIFT) { + nr = (info->end - addr) >> PAGE_SHIFT; + + /* + * INVLPGB has a limit on the size of ranges it can + * flush. Break up large flushes. + */ + nr = clamp_val(nr, 1, invlpgb_count_max); + + invlpgb_flush_addr_nosync(addr, nr); + } + __tlbsync(); } static void do_kernel_range_flush(void *info) @@ -1058,24 +1423,37 @@ static void do_kernel_range_flush(void *info) flush_tlb_one_kernel(addr); } -void flush_tlb_kernel_range(unsigned long start, unsigned long end) +static void kernel_tlb_flush_all(struct flush_tlb_info *info) { - /* Balance as user space task's flush, a bit conservative */ - if (end == TLB_FLUSH_ALL || - (end - start) > tlb_single_page_flush_ceiling << PAGE_SHIFT) { + if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) + invlpgb_flush_all(); + else on_each_cpu(do_flush_tlb_all, NULL, 1); - } else { - struct flush_tlb_info *info; - - preempt_disable(); - info = get_flush_tlb_info(NULL, start, end, 0, false, - TLB_GENERATION_INVALID); +} +static void kernel_tlb_flush_range(struct flush_tlb_info *info) +{ + if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) + invlpgb_kernel_range_flush(info); + else on_each_cpu(do_kernel_range_flush, info, 1); +} - put_flush_tlb_info(); - preempt_enable(); - } +void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + struct flush_tlb_info *info; + + guard(preempt)(); + + info = get_flush_tlb_info(NULL, start, end, PAGE_SHIFT, false, + TLB_GENERATION_INVALID); + + if (info->end == TLB_FLUSH_ALL) + kernel_tlb_flush_all(info); + else + kernel_tlb_flush_range(info); + + put_flush_tlb_info(); } /* @@ -1254,7 +1632,10 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) * 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) { + if (cpu_feature_enabled(X86_FEATURE_INVLPGB) && batch->unmapped_pages) { + invlpgb_flush_all_nonglobals(); + batch->unmapped_pages = false; + } else 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(); @@ -1296,7 +1677,7 @@ bool nmi_uaccess_okay(void) if (loaded_mm != current_mm) return false; - VM_WARN_ON_ONCE(current_mm->pgd != __va(read_cr3_pa())); + VM_WARN_ON_ONCE(__pa(current_mm->pgd) != read_cr3_pa()); return true; } |