diff options
author | José Pekkarinen <jose.pekkarinen@nokia.com> | 2016-04-11 10:41:07 +0300 |
---|---|---|
committer | José Pekkarinen <jose.pekkarinen@nokia.com> | 2016-04-13 08:17:18 +0300 |
commit | e09b41010ba33a20a87472ee821fa407a5b8da36 (patch) | |
tree | d10dc367189862e7ca5c592f033dc3726e1df4e3 /kernel/arch/x86/mm | |
parent | f93b97fd65072de626c074dbe099a1fff05ce060 (diff) |
These changes are the raw update to linux-4.4.6-rt14. Kernel sources
are taken from kernel.org, and rt patch from the rt wiki download page.
During the rebasing, the following patch collided:
Force tick interrupt and get rid of softirq magic(I70131fb85).
Collisions have been removed because its logic was found on the
source already.
Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>
Diffstat (limited to 'kernel/arch/x86/mm')
-rw-r--r-- | kernel/arch/x86/mm/Makefile | 2 | ||||
-rw-r--r-- | kernel/arch/x86/mm/dump_pagetables.c | 100 | ||||
-rw-r--r-- | kernel/arch/x86/mm/fault.c | 22 | ||||
-rw-r--r-- | kernel/arch/x86/mm/gup.c | 18 | ||||
-rw-r--r-- | kernel/arch/x86/mm/highmem_32.c | 14 | ||||
-rw-r--r-- | kernel/arch/x86/mm/init.c | 19 | ||||
-rw-r--r-- | kernel/arch/x86/mm/init_32.c | 8 | ||||
-rw-r--r-- | kernel/arch/x86/mm/init_64.c | 12 | ||||
-rw-r--r-- | kernel/arch/x86/mm/iomap_32.c | 12 | ||||
-rw-r--r-- | kernel/arch/x86/mm/ioremap.c | 101 | ||||
-rw-r--r-- | kernel/arch/x86/mm/kasan_init_64.c | 126 | ||||
-rw-r--r-- | kernel/arch/x86/mm/mpx.c | 616 | ||||
-rw-r--r-- | kernel/arch/x86/mm/numa.c | 6 | ||||
-rw-r--r-- | kernel/arch/x86/mm/pageattr-test.c | 5 | ||||
-rw-r--r-- | kernel/arch/x86/mm/pageattr.c | 179 | ||||
-rw-r--r-- | kernel/arch/x86/mm/pat.c | 337 | ||||
-rw-r--r-- | kernel/arch/x86/mm/pat_internal.h | 2 | ||||
-rw-r--r-- | kernel/arch/x86/mm/pat_rbtree.c | 6 | ||||
-rw-r--r-- | kernel/arch/x86/mm/pgtable.c | 60 | ||||
-rw-r--r-- | kernel/arch/x86/mm/srat.c | 5 | ||||
-rw-r--r-- | kernel/arch/x86/mm/tlb.c | 30 |
21 files changed, 1001 insertions, 679 deletions
diff --git a/kernel/arch/x86/mm/Makefile b/kernel/arch/x86/mm/Makefile index a482d1051..65c47fda2 100644 --- a/kernel/arch/x86/mm/Makefile +++ b/kernel/arch/x86/mm/Makefile @@ -14,7 +14,7 @@ obj-$(CONFIG_SMP) += tlb.o obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -obj-$(CONFIG_X86_PTDUMP) += dump_pagetables.o +obj-$(CONFIG_X86_PTDUMP_CORE) += dump_pagetables.o obj-$(CONFIG_HIGHMEM) += highmem_32.o diff --git a/kernel/arch/x86/mm/dump_pagetables.c b/kernel/arch/x86/mm/dump_pagetables.c index f0cedf339..0f1c6fc3d 100644 --- a/kernel/arch/x86/mm/dump_pagetables.c +++ b/kernel/arch/x86/mm/dump_pagetables.c @@ -32,6 +32,8 @@ struct pg_state { const struct addr_marker *marker; unsigned long lines; bool to_dmesg; + bool check_wx; + unsigned long wx_pages; }; struct addr_marker { @@ -87,7 +89,7 @@ static struct addr_marker address_markers[] = { { 0/* VMALLOC_START */, "vmalloc() Area" }, { 0/*VMALLOC_END*/, "vmalloc() End" }, # ifdef CONFIG_HIGHMEM - { 0/*PKMAP_BASE*/, "Persisent kmap() Area" }, + { 0/*PKMAP_BASE*/, "Persistent kmap() Area" }, # endif { 0/*FIXADDR_START*/, "Fixmap Area" }, #endif @@ -155,7 +157,7 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) pt_dump_cont_printf(m, dmsg, " "); if ((level == 4 && pr & _PAGE_PAT) || ((level == 3 || level == 2) && pr & _PAGE_PAT_LARGE)) - pt_dump_cont_printf(m, dmsg, "pat "); + pt_dump_cont_printf(m, dmsg, "PAT "); else pt_dump_cont_printf(m, dmsg, " "); if (pr & _PAGE_GLOBAL) @@ -198,8 +200,8 @@ static void note_page(struct seq_file *m, struct pg_state *st, * we have now. "break" is either changing perms, levels or * address space marker. */ - prot = pgprot_val(new_prot) & PTE_FLAGS_MASK; - cur = pgprot_val(st->current_prot) & PTE_FLAGS_MASK; + prot = pgprot_val(new_prot); + cur = pgprot_val(st->current_prot); if (!st->level) { /* First entry */ @@ -214,6 +216,16 @@ static void note_page(struct seq_file *m, struct pg_state *st, const char *unit = units; unsigned long delta; int width = sizeof(unsigned long) * 2; + pgprotval_t pr = pgprot_val(st->current_prot); + + if (st->check_wx && (pr & _PAGE_RW) && !(pr & _PAGE_NX)) { + WARN_ONCE(1, + "x86/mm: Found insecure W+X mapping at address %p/%pS\n", + (void *)st->start_address, + (void *)st->start_address); + st->wx_pages += (st->current_address - + st->start_address) / PAGE_SIZE; + } /* * Now print the actual finished series @@ -269,13 +281,13 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, { int i; pte_t *start; + pgprotval_t prot; start = (pte_t *) pmd_page_vaddr(addr); for (i = 0; i < PTRS_PER_PTE; i++) { - pgprot_t prot = pte_pgprot(*start); - + prot = pte_flags(*start); st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT); - note_page(m, st, prot, 4); + note_page(m, st, __pgprot(prot), 4); start++; } } @@ -287,18 +299,19 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, { int i; pmd_t *start; + pgprotval_t prot; start = (pmd_t *) pud_page_vaddr(addr); for (i = 0; i < PTRS_PER_PMD; i++) { st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT); if (!pmd_none(*start)) { - pgprotval_t prot = pmd_val(*start) & PTE_FLAGS_MASK; - - if (pmd_large(*start) || !pmd_present(*start)) + if (pmd_large(*start) || !pmd_present(*start)) { + prot = pmd_flags(*start); note_page(m, st, __pgprot(prot), 3); - else + } else { walk_pte_level(m, st, *start, P + i * PMD_LEVEL_MULT); + } } else note_page(m, st, __pgprot(0), 3); start++; @@ -318,19 +331,20 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr, { int i; pud_t *start; + pgprotval_t prot; start = (pud_t *) pgd_page_vaddr(addr); for (i = 0; i < PTRS_PER_PUD; i++) { st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT); if (!pud_none(*start)) { - pgprotval_t prot = pud_val(*start) & PTE_FLAGS_MASK; - - if (pud_large(*start) || !pud_present(*start)) + if (pud_large(*start) || !pud_present(*start)) { + prot = pud_flags(*start); note_page(m, st, __pgprot(prot), 2); - else + } else { walk_pmd_level(m, st, *start, P + i * PUD_LEVEL_MULT); + } } else note_page(m, st, __pgprot(0), 2); @@ -344,13 +358,30 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr, #define pgd_none(a) pud_none(__pud(pgd_val(a))) #endif -void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) +#ifdef CONFIG_X86_64 +static inline bool is_hypervisor_range(int idx) +{ + /* + * ffff800000000000 - ffff87ffffffffff is reserved for + * the hypervisor. + */ + return paravirt_enabled() && + (idx >= pgd_index(__PAGE_OFFSET) - 16) && + (idx < pgd_index(__PAGE_OFFSET)); +} +#else +static inline bool is_hypervisor_range(int idx) { return false; } +#endif + +static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, + bool checkwx) { #ifdef CONFIG_X86_64 pgd_t *start = (pgd_t *) &init_level4_pgt; #else pgd_t *start = swapper_pg_dir; #endif + pgprotval_t prot; int i; struct pg_state st = {}; @@ -359,16 +390,20 @@ void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) st.to_dmesg = true; } + st.check_wx = checkwx; + if (checkwx) + st.wx_pages = 0; + for (i = 0; i < PTRS_PER_PGD; i++) { st.current_address = normalize_addr(i * PGD_LEVEL_MULT); - if (!pgd_none(*start)) { - pgprotval_t prot = pgd_val(*start) & PTE_FLAGS_MASK; - - if (pgd_large(*start) || !pgd_present(*start)) + if (!pgd_none(*start) && !is_hypervisor_range(i)) { + if (pgd_large(*start) || !pgd_present(*start)) { + prot = pgd_flags(*start); note_page(m, &st, __pgprot(prot), 1); - else + } else { walk_pud_level(m, &st, *start, i * PGD_LEVEL_MULT); + } } else note_page(m, &st, __pgprot(0), 1); @@ -378,8 +413,26 @@ void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) /* Flush out the last page */ st.current_address = normalize_addr(PTRS_PER_PGD*PGD_LEVEL_MULT); note_page(m, &st, __pgprot(0), 0); + if (!checkwx) + return; + if (st.wx_pages) + pr_info("x86/mm: Checked W+X mappings: FAILED, %lu W+X pages found.\n", + st.wx_pages); + else + pr_info("x86/mm: Checked W+X mappings: passed, no W+X pages found.\n"); +} + +void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) +{ + ptdump_walk_pgd_level_core(m, pgd, false); +} + +void ptdump_walk_pgd_level_checkwx(void) +{ + ptdump_walk_pgd_level_core(NULL, NULL, true); } +#ifdef CONFIG_X86_PTDUMP static int ptdump_show(struct seq_file *m, void *v) { ptdump_walk_pgd_level(m, NULL); @@ -397,10 +450,13 @@ static const struct file_operations ptdump_fops = { .llseek = seq_lseek, .release = single_release, }; +#endif static int pt_dump_init(void) { +#ifdef CONFIG_X86_PTDUMP struct dentry *pe; +#endif #ifdef CONFIG_X86_32 /* Not a compile-time constant on x86-32 */ @@ -412,10 +468,12 @@ static int pt_dump_init(void) address_markers[FIXADDR_START_NR].start_address = FIXADDR_START; #endif +#ifdef CONFIG_X86_PTDUMP pe = debugfs_create_file("kernel_page_tables", 0600, NULL, NULL, &ptdump_fops); if (!pe) return -ENOMEM; +#endif return 0; } diff --git a/kernel/arch/x86/mm/fault.c b/kernel/arch/x86/mm/fault.c index 9dc909841..e830c71a1 100644 --- a/kernel/arch/x86/mm/fault.c +++ b/kernel/arch/x86/mm/fault.c @@ -20,6 +20,7 @@ #include <asm/kmemcheck.h> /* kmemcheck_*(), ... */ #include <asm/fixmap.h> /* VSYSCALL_ADDR */ #include <asm/vsyscall.h> /* emulate_vsyscall */ +#include <asm/vm86.h> /* struct vm86 */ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> @@ -286,6 +287,9 @@ static noinline int vmalloc_fault(unsigned long address) if (!pmd_k) return -1; + if (pmd_huge(*pmd_k)) + return 0; + pte_k = pte_offset_kernel(pmd_k, address); if (!pte_present(*pte_k)) return -1; @@ -301,14 +305,16 @@ static inline void check_v8086_mode(struct pt_regs *regs, unsigned long address, struct task_struct *tsk) { +#ifdef CONFIG_VM86 unsigned long bit; - if (!v8086_mode(regs)) + if (!v8086_mode(regs) || !tsk->thread.vm86) return; bit = (address - 0xA0000) >> PAGE_SHIFT; if (bit < 32) - tsk->thread.screen_bitmap |= 1 << bit; + tsk->thread.vm86->screen_bitmap |= 1 << bit; +#endif } static bool low_pfn(unsigned long pfn) @@ -357,8 +363,6 @@ void vmalloc_sync_all(void) * 64-bit: * * Handle a fault on the vmalloc area - * - * This assumes no large pages in there. */ static noinline int vmalloc_fault(unsigned long address) { @@ -400,17 +404,23 @@ static noinline int vmalloc_fault(unsigned long address) if (pud_none(*pud_ref)) return -1; - if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref)) + if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref)) BUG(); + if (pud_huge(*pud)) + return 0; + pmd = pmd_offset(pud, address); pmd_ref = pmd_offset(pud_ref, address); if (pmd_none(*pmd_ref)) return -1; - if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref)) + if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref)) BUG(); + if (pmd_huge(*pmd)) + return 0; + pte_ref = pte_offset_kernel(pmd_ref, address); if (!pte_present(*pte_ref)) return -1; diff --git a/kernel/arch/x86/mm/gup.c b/kernel/arch/x86/mm/gup.c index 81bf3d2af..ae9a37bf1 100644 --- a/kernel/arch/x86/mm/gup.c +++ b/kernel/arch/x86/mm/gup.c @@ -118,21 +118,20 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { unsigned long mask; - pte_t pte = *(pte_t *)&pmd; struct page *head, *page; int refs; mask = _PAGE_PRESENT|_PAGE_USER; if (write) mask |= _PAGE_RW; - if ((pte_flags(pte) & mask) != mask) + if ((pmd_flags(pmd) & mask) != mask) return 0; /* hugepages are never "special" */ - VM_BUG_ON(pte_flags(pte) & _PAGE_SPECIAL); - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + VM_BUG_ON(pmd_flags(pmd) & _PAGE_SPECIAL); + VM_BUG_ON(!pfn_valid(pmd_pfn(pmd))); refs = 0; - head = pte_page(pte); + head = pmd_page(pmd); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); do { VM_BUG_ON_PAGE(compound_head(page) != head, page); @@ -195,21 +194,20 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { unsigned long mask; - pte_t pte = *(pte_t *)&pud; struct page *head, *page; int refs; mask = _PAGE_PRESENT|_PAGE_USER; if (write) mask |= _PAGE_RW; - if ((pte_flags(pte) & mask) != mask) + if ((pud_flags(pud) & mask) != mask) return 0; /* hugepages are never "special" */ - VM_BUG_ON(pte_flags(pte) & _PAGE_SPECIAL); - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + VM_BUG_ON(pud_flags(pud) & _PAGE_SPECIAL); + VM_BUG_ON(!pfn_valid(pud_pfn(pud))); refs = 0; - head = pte_page(pte); + head = pud_page(pud); page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); do { VM_BUG_ON_PAGE(compound_head(page) != head, page); diff --git a/kernel/arch/x86/mm/highmem_32.c b/kernel/arch/x86/mm/highmem_32.c index 0d1cbcf47..bd24ba1c4 100644 --- a/kernel/arch/x86/mm/highmem_32.c +++ b/kernel/arch/x86/mm/highmem_32.c @@ -111,20 +111,6 @@ void __kunmap_atomic(void *kvaddr) } EXPORT_SYMBOL(__kunmap_atomic); -struct page *kmap_atomic_to_page(void *ptr) -{ - unsigned long idx, vaddr = (unsigned long)ptr; - pte_t *pte; - - if (vaddr < FIXADDR_START) - return virt_to_page(ptr); - - idx = virt_to_fix(vaddr); - pte = kmap_pte - (idx - FIX_KMAP_BEGIN); - return pte_page(*pte); -} -EXPORT_SYMBOL(kmap_atomic_to_page); - void __init set_highmem_pages_init(void) { struct zone *zone; diff --git a/kernel/arch/x86/mm/init.c b/kernel/arch/x86/mm/init.c index 1d553186c..493f54172 100644 --- a/kernel/arch/x86/mm/init.c +++ b/kernel/arch/x86/mm/init.c @@ -30,8 +30,11 @@ /* * Tables translating between page_cache_type_t and pte encoding. * - * Minimal supported modes are defined statically, they are modified - * during bootup if more supported cache modes are available. + * The default values are defined statically as minimal supported mode; + * WC and WT fall back to UC-. pat_init() updates these values to support + * more cache modes, WC and WT, when it is safe to do so. See pat_init() + * for the details. Note, __early_ioremap() used during early boot-time + * takes pgprot_t (pte encoding) and does not use these tables. * * Index into __cachemode2pte_tbl[] is the cachemode. * @@ -40,7 +43,7 @@ */ uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = { [_PAGE_CACHE_MODE_WB ] = 0 | 0 , - [_PAGE_CACHE_MODE_WC ] = _PAGE_PWT | 0 , + [_PAGE_CACHE_MODE_WC ] = 0 | _PAGE_PCD, [_PAGE_CACHE_MODE_UC_MINUS] = 0 | _PAGE_PCD, [_PAGE_CACHE_MODE_UC ] = _PAGE_PWT | _PAGE_PCD, [_PAGE_CACHE_MODE_WT ] = 0 | _PAGE_PCD, @@ -50,11 +53,11 @@ EXPORT_SYMBOL(__cachemode2pte_tbl); uint8_t __pte2cachemode_tbl[8] = { [__pte2cm_idx( 0 | 0 | 0 )] = _PAGE_CACHE_MODE_WB, - [__pte2cm_idx(_PAGE_PWT | 0 | 0 )] = _PAGE_CACHE_MODE_WC, + [__pte2cm_idx(_PAGE_PWT | 0 | 0 )] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx( 0 | _PAGE_PCD | 0 )] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | 0 )] = _PAGE_CACHE_MODE_UC, [__pte2cm_idx( 0 | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_WB, - [__pte2cm_idx(_PAGE_PWT | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_WC, + [__pte2cm_idx(_PAGE_PWT | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(0 | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC, }; @@ -351,7 +354,7 @@ static int __meminit split_mem_range(struct map_range *mr, int nr_range, } for (i = 0; i < nr_range; i++) - printk(KERN_DEBUG " [mem %#010lx-%#010lx] page %s\n", + pr_debug(" [mem %#010lx-%#010lx] page %s\n", mr[i].start, mr[i].end - 1, page_size_string(&mr[i])); @@ -398,7 +401,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, unsigned long ret = 0; int nr_range, i; - pr_info("init_memory_mapping: [mem %#010lx-%#010lx]\n", + pr_debug("init_memory_mapping: [mem %#010lx-%#010lx]\n", start, end - 1); memset(mr, 0, sizeof(mr)); @@ -690,14 +693,12 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { -#ifdef CONFIG_MICROCODE_EARLY /* * Remember, initrd memory may contain microcode or other useful things. * Before we lose initrd mem, we need to find a place to hold them * now that normal virtual memory is enabled. */ save_microcode_in_initrd(); -#endif /* * end could be not aligned, and We can not align that, diff --git a/kernel/arch/x86/mm/init_32.c b/kernel/arch/x86/mm/init_32.c index c23ab1ee3..cb4ef3de6 100644 --- a/kernel/arch/x86/mm/init_32.c +++ b/kernel/arch/x86/mm/init_32.c @@ -434,7 +434,7 @@ void __init add_highpages_with_active_regions(int nid, phys_addr_t start, end; u64 i; - for_each_free_mem_range(i, nid, &start, &end, NULL) { + for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &start, &end, NULL) { unsigned long pfn = clamp_t(unsigned long, PFN_UP(start), start_pfn, end_pfn); unsigned long e_pfn = clamp_t(unsigned long, PFN_DOWN(end), @@ -823,11 +823,11 @@ void __init mem_init(void) } #ifdef CONFIG_MEMORY_HOTPLUG -int arch_add_memory(int nid, u64 start, u64 size) +int arch_add_memory(int nid, u64 start, u64 size, bool for_device) { struct pglist_data *pgdata = NODE_DATA(nid); struct zone *zone = pgdata->node_zones + - zone_for_memory(nid, start, size, ZONE_HIGHMEM); + zone_for_memory(nid, start, size, ZONE_HIGHMEM, for_device); unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; @@ -957,6 +957,8 @@ void mark_rodata_ro(void) set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); #endif mark_nxdata_nx(); + if (__supported_pte_mask & _PAGE_NX) + debug_checkwx(); } #endif diff --git a/kernel/arch/x86/mm/init_64.c b/kernel/arch/x86/mm/init_64.c index 3fba623e3..ec081fe0c 100644 --- a/kernel/arch/x86/mm/init_64.c +++ b/kernel/arch/x86/mm/init_64.c @@ -687,11 +687,11 @@ static void update_end_of_memory_vars(u64 start, u64 size) * Memory is added always to NORMAL zone. This means you will never get * additional DMA/DMA32 memory. */ -int arch_add_memory(int nid, u64 start, u64 size) +int arch_add_memory(int nid, u64 start, u64 size, bool for_device) { struct pglist_data *pgdat = NODE_DATA(nid); struct zone *zone = pgdat->node_zones + - zone_for_memory(nid, start, size, ZONE_NORMAL); + zone_for_memory(nid, start, size, ZONE_NORMAL, for_device); unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; int ret; @@ -1132,7 +1132,7 @@ void mark_rodata_ro(void) * has been zapped already via cleanup_highmem(). */ all_end = roundup((unsigned long)_brk_end, PMD_SIZE); - set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT); + set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT); rodata_test(); @@ -1150,6 +1150,8 @@ void mark_rodata_ro(void) free_init_pages("unused kernel", (unsigned long) __va(__pa_symbol(rodata_end)), (unsigned long) __va(__pa_symbol(_sdata))); + + debug_checkwx(); } #endif @@ -1268,7 +1270,7 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, /* check to see if we have contiguous blocks */ if (p_end != p || node_start != node) { if (p_start) - printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n", + pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n", addr_start, addr_end-1, p_start, p_end-1, node_start); addr_start = addr; node_start = node; @@ -1366,7 +1368,7 @@ void register_page_bootmem_memmap(unsigned long section_nr, void __meminit vmemmap_populate_print_last(void) { if (p_start) { - printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n", + pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n", addr_start, addr_end-1, p_start, p_end-1, node_start); p_start = NULL; p_end = NULL; diff --git a/kernel/arch/x86/mm/iomap_32.c b/kernel/arch/x86/mm/iomap_32.c index b2ffa5c7d..dd25dd167 100644 --- a/kernel/arch/x86/mm/iomap_32.c +++ b/kernel/arch/x86/mm/iomap_32.c @@ -84,13 +84,13 @@ void __iomem * iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) { /* - * For non-PAT systems, promote PAGE_KERNEL_WC to PAGE_KERNEL_UC_MINUS. - * PAGE_KERNEL_WC maps to PWT, which translates to uncached if the - * MTRR is UC or WC. UC_MINUS gets the real intention, of the - * user, which is "WC if the MTRR is WC, UC if you can't do that." + * For non-PAT systems, translate non-WB request to UC- just in + * case the caller set the PWT bit to prot directly without using + * pgprot_writecombine(). UC- translates to uncached if the MTRR + * is UC or WC. UC- gets the real intention, of the user, which is + * "WC if the MTRR is WC, UC if you can't do that." */ - if (!pat_enabled && pgprot_val(prot) == - (__PAGE_KERNEL | cachemode2protval(_PAGE_CACHE_MODE_WC))) + if (!pat_enabled() && pgprot2cachemode(prot) != _PAGE_CACHE_MODE_WB) prot = __pgprot(__PAGE_KERNEL | cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS)); diff --git a/kernel/arch/x86/mm/ioremap.c b/kernel/arch/x86/mm/ioremap.c index 70e7444c6..b9c78f3bc 100644 --- a/kernel/arch/x86/mm/ioremap.c +++ b/kernel/arch/x86/mm/ioremap.c @@ -42,6 +42,9 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size, case _PAGE_CACHE_MODE_WC: err = _set_memory_wc(vaddr, nrpages); break; + case _PAGE_CACHE_MODE_WT: + err = _set_memory_wt(vaddr, nrpages); + break; case _PAGE_CACHE_MODE_WB: err = _set_memory_wb(vaddr, nrpages); break; @@ -60,8 +63,6 @@ static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages, !PageReserved(pfn_to_page(start_pfn + i))) return 1; - WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn); - return 0; } @@ -91,7 +92,6 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, pgprot_t prot; int retval; void __iomem *ret_addr; - int ram_region; /* Don't allow wraparound or zero size */ last_addr = phys_addr + size - 1; @@ -114,23 +114,15 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, /* * Don't allow anybody to remap normal RAM that we're using.. */ - /* First check if whole region can be identified as RAM or not */ - ram_region = region_is_ram(phys_addr, size); - if (ram_region > 0) { - WARN_ONCE(1, "ioremap on RAM at 0x%lx - 0x%lx\n", - (unsigned long int)phys_addr, - (unsigned long int)last_addr); + pfn = phys_addr >> PAGE_SHIFT; + last_pfn = last_addr >> PAGE_SHIFT; + if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL, + __ioremap_check_ram) == 1) { + WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n", + &phys_addr, &last_addr); return NULL; } - /* If could not be identified(-1), check page by page */ - if (ram_region < 0) { - pfn = phys_addr >> PAGE_SHIFT; - last_pfn = last_addr >> PAGE_SHIFT; - if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL, - __ioremap_check_ram) == 1) - return NULL; - } /* * Mappings have to be page-aligned */ @@ -172,6 +164,10 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, prot = __pgprot(pgprot_val(prot) | cachemode2protval(_PAGE_CACHE_MODE_WC)); break; + case _PAGE_CACHE_MODE_WT: + prot = __pgprot(pgprot_val(prot) | + cachemode2protval(_PAGE_CACHE_MODE_WT)); + break; case _PAGE_CACHE_MODE_WB: break; } @@ -234,10 +230,11 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size) { /* * Ideally, this should be: - * pat_enabled ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS; + * pat_enabled() ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS; * * Till we fix all X drivers to use ioremap_wc(), we will use - * UC MINUS. + * UC MINUS. Drivers that are certain they need or can already + * be converted over to strong UC can use ioremap_uc(). */ enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC_MINUS; @@ -247,6 +244,39 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size) EXPORT_SYMBOL(ioremap_nocache); /** + * ioremap_uc - map bus memory into CPU space as strongly uncachable + * @phys_addr: bus address of the memory + * @size: size of the resource to map + * + * ioremap_uc performs a platform specific sequence of operations to + * make bus memory CPU accessible via the readb/readw/readl/writeb/ + * writew/writel functions and the other mmio helpers. The returned + * address is not guaranteed to be usable directly as a virtual + * address. + * + * This version of ioremap ensures that the memory is marked with a strong + * preference as completely uncachable on the CPU when possible. For non-PAT + * systems this ends up setting page-attribute flags PCD=1, PWT=1. For PAT + * systems this will set the PAT entry for the pages as strong UC. This call + * will honor existing caching rules from things like the PCI bus. Note that + * there are other caches and buffers on many busses. In particular driver + * authors should read up on PCI writes. + * + * It's useful if some control registers are in such an area and + * write combining or read caching is not desirable: + * + * Must be freed with iounmap. + */ +void __iomem *ioremap_uc(resource_size_t phys_addr, unsigned long size) +{ + enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC; + + return __ioremap_caller(phys_addr, size, pcm, + __builtin_return_address(0)); +} +EXPORT_SYMBOL_GPL(ioremap_uc); + +/** * ioremap_wc - map memory into CPU space write combined * @phys_addr: bus address of the memory * @size: size of the resource to map @@ -258,14 +288,28 @@ EXPORT_SYMBOL(ioremap_nocache); */ void __iomem *ioremap_wc(resource_size_t phys_addr, unsigned long size) { - if (pat_enabled) - return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC, + return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC, __builtin_return_address(0)); - else - return ioremap_nocache(phys_addr, size); } EXPORT_SYMBOL(ioremap_wc); +/** + * ioremap_wt - map memory into CPU space write through + * @phys_addr: bus address of the memory + * @size: size of the resource to map + * + * This version of ioremap ensures that the memory is marked write through. + * Write through stores data into memory while keeping the cache up-to-date. + * + * Must be freed with iounmap. + */ +void __iomem *ioremap_wt(resource_size_t phys_addr, unsigned long size) +{ + return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WT, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(ioremap_wt); + void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size) { return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WB, @@ -331,7 +375,7 @@ void iounmap(volatile void __iomem *addr) } EXPORT_SYMBOL(iounmap); -int arch_ioremap_pud_supported(void) +int __init arch_ioremap_pud_supported(void) { #ifdef CONFIG_X86_64 return cpu_has_gbpages; @@ -340,7 +384,7 @@ int arch_ioremap_pud_supported(void) #endif } -int arch_ioremap_pmd_supported(void) +int __init arch_ioremap_pmd_supported(void) { return cpu_has_pse; } @@ -353,18 +397,18 @@ void *xlate_dev_mem_ptr(phys_addr_t phys) { unsigned long start = phys & PAGE_MASK; unsigned long offset = phys & ~PAGE_MASK; - unsigned long vaddr; + void *vaddr; /* If page is RAM, we can use __va. Otherwise ioremap and unmap. */ if (page_is_ram(start >> PAGE_SHIFT)) return __va(phys); - vaddr = (unsigned long)ioremap_cache(start, PAGE_SIZE); + vaddr = ioremap_cache(start, PAGE_SIZE); /* Only add the offset on success and return NULL if the ioremap() failed: */ if (vaddr) vaddr += offset; - return (void *)vaddr; + return vaddr; } void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) @@ -373,7 +417,6 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) return; iounmap((void __iomem *)((unsigned long)addr & PAGE_MASK)); - return; } static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss; diff --git a/kernel/arch/x86/mm/kasan_init_64.c b/kernel/arch/x86/mm/kasan_init_64.c index 9a54dbe98..d470cf219 100644 --- a/kernel/arch/x86/mm/kasan_init_64.c +++ b/kernel/arch/x86/mm/kasan_init_64.c @@ -1,3 +1,4 @@ +#define pr_fmt(fmt) "kasan: " fmt #include <linux/bootmem.h> #include <linux/kasan.h> #include <linux/kdebug.h> @@ -11,20 +12,6 @@ extern pgd_t early_level4_pgt[PTRS_PER_PGD]; extern struct range pfn_mapped[E820_X_MAX]; -static pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss; -static pmd_t kasan_zero_pmd[PTRS_PER_PMD] __page_aligned_bss; -static pte_t kasan_zero_pte[PTRS_PER_PTE] __page_aligned_bss; - -/* - * This page used as early shadow. We don't use empty_zero_page - * at early stages, stack instrumentation could write some garbage - * to this page. - * Latter we reuse it as zero shadow for large ranges of memory - * that allowed to access, but not instrumented by kasan - * (vmalloc/vmemmap ...). - */ -static unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss; - static int __init map_range(struct range *range) { unsigned long start; @@ -61,106 +48,6 @@ static void __init kasan_map_early_shadow(pgd_t *pgd) } } -static int __init zero_pte_populate(pmd_t *pmd, unsigned long addr, - unsigned long end) -{ - pte_t *pte = pte_offset_kernel(pmd, addr); - - while (addr + PAGE_SIZE <= end) { - WARN_ON(!pte_none(*pte)); - set_pte(pte, __pte(__pa_nodebug(kasan_zero_page) - | __PAGE_KERNEL_RO)); - addr += PAGE_SIZE; - pte = pte_offset_kernel(pmd, addr); - } - return 0; -} - -static int __init zero_pmd_populate(pud_t *pud, unsigned long addr, - unsigned long end) -{ - int ret = 0; - pmd_t *pmd = pmd_offset(pud, addr); - - while (IS_ALIGNED(addr, PMD_SIZE) && addr + PMD_SIZE <= end) { - WARN_ON(!pmd_none(*pmd)); - set_pmd(pmd, __pmd(__pa_nodebug(kasan_zero_pte) - | _KERNPG_TABLE)); - addr += PMD_SIZE; - pmd = pmd_offset(pud, addr); - } - if (addr < end) { - if (pmd_none(*pmd)) { - void *p = vmemmap_alloc_block(PAGE_SIZE, NUMA_NO_NODE); - if (!p) - return -ENOMEM; - set_pmd(pmd, __pmd(__pa_nodebug(p) | _KERNPG_TABLE)); - } - ret = zero_pte_populate(pmd, addr, end); - } - return ret; -} - - -static int __init zero_pud_populate(pgd_t *pgd, unsigned long addr, - unsigned long end) -{ - int ret = 0; - pud_t *pud = pud_offset(pgd, addr); - - while (IS_ALIGNED(addr, PUD_SIZE) && addr + PUD_SIZE <= end) { - WARN_ON(!pud_none(*pud)); - set_pud(pud, __pud(__pa_nodebug(kasan_zero_pmd) - | _KERNPG_TABLE)); - addr += PUD_SIZE; - pud = pud_offset(pgd, addr); - } - - if (addr < end) { - if (pud_none(*pud)) { - void *p = vmemmap_alloc_block(PAGE_SIZE, NUMA_NO_NODE); - if (!p) - return -ENOMEM; - set_pud(pud, __pud(__pa_nodebug(p) | _KERNPG_TABLE)); - } - ret = zero_pmd_populate(pud, addr, end); - } - return ret; -} - -static int __init zero_pgd_populate(unsigned long addr, unsigned long end) -{ - int ret = 0; - pgd_t *pgd = pgd_offset_k(addr); - - while (IS_ALIGNED(addr, PGDIR_SIZE) && addr + PGDIR_SIZE <= end) { - WARN_ON(!pgd_none(*pgd)); - set_pgd(pgd, __pgd(__pa_nodebug(kasan_zero_pud) - | _KERNPG_TABLE)); - addr += PGDIR_SIZE; - pgd = pgd_offset_k(addr); - } - - if (addr < end) { - if (pgd_none(*pgd)) { - void *p = vmemmap_alloc_block(PAGE_SIZE, NUMA_NO_NODE); - if (!p) - return -ENOMEM; - set_pgd(pgd, __pgd(__pa_nodebug(p) | _KERNPG_TABLE)); - } - ret = zero_pud_populate(pgd, addr, end); - } - return ret; -} - - -static void __init populate_zero_shadow(const void *start, const void *end) -{ - if (zero_pgd_populate((unsigned long)start, (unsigned long)end)) - panic("kasan: unable to map zero shadow!"); -} - - #ifdef CONFIG_KASAN_INLINE static int kasan_die_handler(struct notifier_block *self, unsigned long val, @@ -212,7 +99,7 @@ void __init kasan_init(void) clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); - populate_zero_shadow((void *)KASAN_SHADOW_START, + kasan_populate_zero_shadow((void *)KASAN_SHADOW_START, kasan_mem_to_shadow((void *)PAGE_OFFSET)); for (i = 0; i < E820_X_MAX; i++) { @@ -222,14 +109,15 @@ void __init kasan_init(void) if (map_range(&pfn_mapped[i])) panic("kasan: unable to allocate shadow!"); } - populate_zero_shadow(kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM), - kasan_mem_to_shadow((void *)__START_KERNEL_map)); + kasan_populate_zero_shadow( + kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM), + kasan_mem_to_shadow((void *)__START_KERNEL_map)); vmemmap_populate((unsigned long)kasan_mem_to_shadow(_stext), (unsigned long)kasan_mem_to_shadow(_end), NUMA_NO_NODE); - populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), + kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), (void *)KASAN_SHADOW_END); memset(kasan_zero_page, 0, PAGE_SIZE); @@ -237,4 +125,6 @@ void __init kasan_init(void) load_cr3(init_level4_pgt); __flush_tlb_all(); init_task.kasan_depth = 0; + + pr_info("KernelAddressSanitizer initialized\n"); } diff --git a/kernel/arch/x86/mm/mpx.c b/kernel/arch/x86/mm/mpx.c index 4d1c11c07..ef05755a1 100644 --- a/kernel/arch/x86/mm/mpx.c +++ b/kernel/arch/x86/mm/mpx.c @@ -10,13 +10,31 @@ #include <linux/syscalls.h> #include <linux/sched/sysctl.h> -#include <asm/i387.h> #include <asm/insn.h> #include <asm/mman.h> #include <asm/mmu_context.h> #include <asm/mpx.h> #include <asm/processor.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> + +#define CREATE_TRACE_POINTS +#include <asm/trace/mpx.h> + +static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm) +{ + if (is_64bit_mm(mm)) + return MPX_BD_SIZE_BYTES_64; + else + return MPX_BD_SIZE_BYTES_32; +} + +static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm) +{ + if (is_64bit_mm(mm)) + return MPX_BT_SIZE_BYTES_64; + else + return MPX_BT_SIZE_BYTES_32; +} /* * This is really a simplified "vm_mmap". it only handles MPX @@ -24,58 +42,21 @@ */ static unsigned long mpx_mmap(unsigned long len) { - unsigned long ret; - unsigned long addr, pgoff; struct mm_struct *mm = current->mm; - vm_flags_t vm_flags; - struct vm_area_struct *vma; + unsigned long addr, populate; - /* Only bounds table and bounds directory can be allocated here */ - if (len != MPX_BD_SIZE_BYTES && len != MPX_BT_SIZE_BYTES) + /* Only bounds table can be allocated here */ + if (len != mpx_bt_size_bytes(mm)) return -EINVAL; down_write(&mm->mmap_sem); - - /* Too many mappings? */ - if (mm->map_count > sysctl_max_map_count) { - ret = -ENOMEM; - goto out; - } - - /* Obtain the address to map to. we verify (or select) it and ensure - * that it represents a valid section of the address space. - */ - addr = get_unmapped_area(NULL, 0, len, 0, MAP_ANONYMOUS | MAP_PRIVATE); - if (addr & ~PAGE_MASK) { - ret = addr; - goto out; - } - - vm_flags = VM_READ | VM_WRITE | VM_MPX | - mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; - - /* Set pgoff according to addr for anon_vma */ - pgoff = addr >> PAGE_SHIFT; - - ret = mmap_region(NULL, addr, len, vm_flags, pgoff); - if (IS_ERR_VALUE(ret)) - goto out; - - vma = find_vma(mm, ret); - if (!vma) { - ret = -ENOMEM; - goto out; - } - - if (vm_flags & VM_LOCKED) { - up_write(&mm->mmap_sem); - mm_populate(ret, len); - return ret; - } - -out: + addr = do_mmap(NULL, 0, len, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, VM_MPX, 0, &populate); up_write(&mm->mmap_sem); - return ret; + if (populate) + mm_populate(addr, populate); + + return addr; } enum reg_type { @@ -120,19 +101,19 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs, switch (type) { case REG_TYPE_RM: regno = X86_MODRM_RM(insn->modrm.value); - if (X86_REX_B(insn->rex_prefix.value) == 1) + if (X86_REX_B(insn->rex_prefix.value)) regno += 8; break; case REG_TYPE_INDEX: regno = X86_SIB_INDEX(insn->sib.value); - if (X86_REX_X(insn->rex_prefix.value) == 1) + if (X86_REX_X(insn->rex_prefix.value)) regno += 8; break; case REG_TYPE_BASE: regno = X86_SIB_BASE(insn->sib.value); - if (X86_REX_B(insn->rex_prefix.value) == 1) + if (X86_REX_B(insn->rex_prefix.value)) regno += 8; break; @@ -142,7 +123,7 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs, break; } - if (regno > nr_registers) { + if (regno >= nr_registers) { WARN_ONCE(1, "decoded an instruction with an invalid register"); return -EINVAL; } @@ -254,10 +235,10 @@ bad_opcode: * * The caller is expected to kfree() the returned siginfo_t. */ -siginfo_t *mpx_generate_siginfo(struct pt_regs *regs, - struct xsave_struct *xsave_buf) +siginfo_t *mpx_generate_siginfo(struct pt_regs *regs) { - struct bndreg *bndregs, *bndreg; + const struct mpx_bndreg_state *bndregs; + const struct mpx_bndreg *bndreg; siginfo_t *info = NULL; struct insn insn; uint8_t bndregno; @@ -277,14 +258,14 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs, err = -EINVAL; goto err_out; } - /* get the bndregs _area_ of the xsave structure */ - bndregs = get_xsave_addr(xsave_buf, XSTATE_BNDREGS); + /* get bndregs field from current task's xsave area */ + bndregs = get_xsave_field_ptr(XFEATURE_MASK_BNDREGS); if (!bndregs) { err = -EINVAL; goto err_out; } /* now go select the individual register in the set of 4 */ - bndreg = &bndregs[bndregno]; + bndreg = &bndregs->bndreg[bndregno]; info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) { @@ -316,6 +297,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs, err = -EINVAL; goto err_out; } + trace_mpx_bounds_register_exception(info->si_addr, bndreg); return info; err_out: /* info might be NULL, but kfree() handles that */ @@ -323,25 +305,18 @@ err_out: return ERR_PTR(err); } -static __user void *task_get_bounds_dir(struct task_struct *tsk) +static __user void *mpx_get_bounds_dir(void) { - struct bndcsr *bndcsr; + const struct mpx_bndcsr *bndcsr; if (!cpu_feature_enabled(X86_FEATURE_MPX)) return MPX_INVALID_BOUNDS_DIR; /* - * 32-bit binaries on 64-bit kernels are currently - * unsupported. - */ - if (IS_ENABLED(CONFIG_X86_64) && test_thread_flag(TIF_IA32)) - return MPX_INVALID_BOUNDS_DIR; - /* * The bounds directory pointer is stored in a register * only accessible if we first do an xsave. */ - fpu_save_init(&tsk->thread.fpu); - bndcsr = get_xsave_addr(&tsk->thread.fpu.state->xsave, XSTATE_BNDCSR); + bndcsr = get_xsave_field_ptr(XFEATURE_MASK_BNDCSR); if (!bndcsr) return MPX_INVALID_BOUNDS_DIR; @@ -360,10 +335,10 @@ static __user void *task_get_bounds_dir(struct task_struct *tsk) (bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK); } -int mpx_enable_management(struct task_struct *tsk) +int mpx_enable_management(void) { void __user *bd_base = MPX_INVALID_BOUNDS_DIR; - struct mm_struct *mm = tsk->mm; + struct mm_struct *mm = current->mm; int ret = 0; /* @@ -372,11 +347,12 @@ int mpx_enable_management(struct task_struct *tsk) * directory into XSAVE/XRSTOR Save Area and enable MPX through * XRSTOR instruction. * - * fpu_xsave() is expected to be very expensive. Storing the bounds - * directory here means that we do not have to do xsave in the unmap - * path; we can just use mm->bd_addr instead. + * The copy_xregs_to_kernel() beneath get_xsave_field_ptr() is + * expected to be relatively expensive. Storing the bounds + * directory here means that we do not have to do xsave in the + * unmap path; we can just use mm->bd_addr instead. */ - bd_base = task_get_bounds_dir(tsk); + bd_base = mpx_get_bounds_dir(); down_write(&mm->mmap_sem); mm->bd_addr = bd_base; if (mm->bd_addr == MPX_INVALID_BOUNDS_DIR) @@ -386,7 +362,7 @@ int mpx_enable_management(struct task_struct *tsk) return ret; } -int mpx_disable_management(struct task_struct *tsk) +int mpx_disable_management(void) { struct mm_struct *mm = current->mm; @@ -399,29 +375,59 @@ int mpx_disable_management(struct task_struct *tsk) return 0; } +static int mpx_cmpxchg_bd_entry(struct mm_struct *mm, + unsigned long *curval, + unsigned long __user *addr, + unsigned long old_val, unsigned long new_val) +{ + int ret; + /* + * user_atomic_cmpxchg_inatomic() actually uses sizeof() + * the pointer that we pass to it to figure out how much + * data to cmpxchg. We have to be careful here not to + * pass a pointer to a 64-bit data type when we only want + * a 32-bit copy. + */ + if (is_64bit_mm(mm)) { + ret = user_atomic_cmpxchg_inatomic(curval, + addr, old_val, new_val); + } else { + u32 uninitialized_var(curval_32); + u32 old_val_32 = old_val; + u32 new_val_32 = new_val; + u32 __user *addr_32 = (u32 __user *)addr; + + ret = user_atomic_cmpxchg_inatomic(&curval_32, + addr_32, old_val_32, new_val_32); + *curval = curval_32; + } + return ret; +} + /* - * With 32-bit mode, MPX_BT_SIZE_BYTES is 4MB, and the size of each - * bounds table is 16KB. With 64-bit mode, MPX_BT_SIZE_BYTES is 2GB, + * With 32-bit mode, a bounds directory is 4MB, and the size of each + * bounds table is 16KB. With 64-bit mode, a bounds directory is 2GB, * and the size of each bounds table is 4MB. */ -static int allocate_bt(long __user *bd_entry) +static int allocate_bt(struct mm_struct *mm, long __user *bd_entry) { unsigned long expected_old_val = 0; unsigned long actual_old_val = 0; unsigned long bt_addr; + unsigned long bd_new_entry; int ret = 0; /* * Carve the virtual space out of userspace for the new * bounds table: */ - bt_addr = mpx_mmap(MPX_BT_SIZE_BYTES); + bt_addr = mpx_mmap(mpx_bt_size_bytes(mm)); if (IS_ERR((void *)bt_addr)) return PTR_ERR((void *)bt_addr); /* * Set the valid flag (kinda like _PAGE_PRESENT in a pte) */ - bt_addr = bt_addr | MPX_BD_ENTRY_VALID_FLAG; + bd_new_entry = bt_addr | MPX_BD_ENTRY_VALID_FLAG; /* * Go poke the address of the new bounds table in to the @@ -434,8 +440,8 @@ static int allocate_bt(long __user *bd_entry) * mmap_sem at this point, unlike some of the other part * of the MPX code that have to pagefault_disable(). */ - ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry, - expected_old_val, bt_addr); + ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val, bd_entry, + expected_old_val, bd_new_entry); if (ret) goto out_unmap; @@ -463,9 +469,10 @@ static int allocate_bt(long __user *bd_entry) ret = -EINVAL; goto out_unmap; } + trace_mpx_new_bounds_table(bt_addr); return 0; out_unmap: - vm_munmap(bt_addr & MPX_BT_ADDR_MASK, MPX_BT_SIZE_BYTES); + vm_munmap(bt_addr, mpx_bt_size_bytes(mm)); return ret; } @@ -480,12 +487,13 @@ out_unmap: * bound table is 16KB. With 64-bit mode, the size of BD is 2GB, * and the size of each bound table is 4MB. */ -static int do_mpx_bt_fault(struct xsave_struct *xsave_buf) +static int do_mpx_bt_fault(void) { unsigned long bd_entry, bd_base; - struct bndcsr *bndcsr; + const struct mpx_bndcsr *bndcsr; + struct mm_struct *mm = current->mm; - bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR); + bndcsr = get_xsave_field_ptr(XFEATURE_MASK_BNDCSR); if (!bndcsr) return -EINVAL; /* @@ -502,13 +510,13 @@ static int do_mpx_bt_fault(struct xsave_struct *xsave_buf) * the directory is. */ if ((bd_entry < bd_base) || - (bd_entry >= bd_base + MPX_BD_SIZE_BYTES)) + (bd_entry >= bd_base + mpx_bd_size_bytes(mm))) return -EINVAL; - return allocate_bt((long __user *)bd_entry); + return allocate_bt(mm, (long __user *)bd_entry); } -int mpx_handle_bd_fault(struct xsave_struct *xsave_buf) +int mpx_handle_bd_fault(void) { /* * Userspace never asked us to manage the bounds tables, @@ -517,7 +525,7 @@ int mpx_handle_bd_fault(struct xsave_struct *xsave_buf) if (!kernel_managing_mpx_tables(current->mm)) return -EINVAL; - if (do_mpx_bt_fault(xsave_buf)) { + if (do_mpx_bt_fault()) { force_sig(SIGSEGV, current); /* * The force_sig() is essentially "handling" this @@ -554,29 +562,78 @@ static int mpx_resolve_fault(long __user *addr, int write) return 0; } +static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm, + unsigned long bd_entry) +{ + unsigned long bt_addr = bd_entry; + int align_to_bytes; + /* + * Bit 0 in a bt_entry is always the valid bit. + */ + bt_addr &= ~MPX_BD_ENTRY_VALID_FLAG; + /* + * Tables are naturally aligned at 8-byte boundaries + * on 64-bit and 4-byte boundaries on 32-bit. The + * documentation makes it appear that the low bits + * are ignored by the hardware, so we do the same. + */ + if (is_64bit_mm(mm)) + align_to_bytes = 8; + else + align_to_bytes = 4; + bt_addr &= ~(align_to_bytes-1); + return bt_addr; +} + +/* + * 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. */ static int get_bt_addr(struct mm_struct *mm, - long __user *bd_entry, unsigned long *bt_addr) + long __user *bd_entry_ptr, + unsigned long *bt_addr_result) { int ret; int valid_bit; + unsigned long bd_entry; + unsigned long bt_addr; - if (!access_ok(VERIFY_READ, (bd_entry), sizeof(*bd_entry))) + if (!access_ok(VERIFY_READ, (bd_entry_ptr), sizeof(*bd_entry_ptr))) return -EFAULT; while (1) { int need_write = 0; pagefault_disable(); - ret = get_user(*bt_addr, bd_entry); + ret = get_user_bd_entry(mm, &bd_entry, bd_entry_ptr); pagefault_enable(); if (!ret) break; if (ret == -EFAULT) - ret = mpx_resolve_fault(bd_entry, need_write); + ret = mpx_resolve_fault(bd_entry_ptr, need_write); /* * If we could not resolve the fault, consider it * userspace's fault and error out. @@ -585,8 +642,8 @@ static int get_bt_addr(struct mm_struct *mm, return ret; } - valid_bit = *bt_addr & MPX_BD_ENTRY_VALID_FLAG; - *bt_addr &= MPX_BT_ADDR_MASK; + valid_bit = bd_entry & MPX_BD_ENTRY_VALID_FLAG; + bt_addr = mpx_bd_entry_to_bt_addr(mm, bd_entry); /* * When the kernel is managing bounds tables, a bounds directory @@ -595,7 +652,7 @@ static int get_bt_addr(struct mm_struct *mm, * data in the address field, we know something is wrong. This * -EINVAL return will cause a SIGSEGV. */ - if (!valid_bit && *bt_addr) + if (!valid_bit && bt_addr) return -EINVAL; /* * Do we have an completely zeroed bt entry? That is OK. It @@ -606,19 +663,112 @@ static int get_bt_addr(struct mm_struct *mm, if (!valid_bit) return -ENOENT; + *bt_addr_result = bt_addr; return 0; } +static inline int bt_entry_size_bytes(struct mm_struct *mm) +{ + if (is_64bit_mm(mm)) + return MPX_BT_ENTRY_BYTES_64; + else + return MPX_BT_ENTRY_BYTES_32; +} + +/* + * Take a virtual address and turns it in to the offset in bytes + * inside of the bounds table where the bounds table entry + * controlling 'addr' can be found. + */ +static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm, + unsigned long addr) +{ + unsigned long bt_table_nr_entries; + unsigned long offset = addr; + + if (is_64bit_mm(mm)) { + /* Bottom 3 bits are ignored on 64-bit */ + offset >>= 3; + bt_table_nr_entries = MPX_BT_NR_ENTRIES_64; + } else { + /* Bottom 2 bits are ignored on 32-bit */ + offset >>= 2; + bt_table_nr_entries = MPX_BT_NR_ENTRIES_32; + } + /* + * We know the size of the table in to which we are + * indexing, and we have eliminated all the low bits + * which are ignored for indexing. + * + * Mask out all the high bits which we do not need + * to index in to the table. Note that the tables + * are always powers of two so this gives us a proper + * mask. + */ + offset &= (bt_table_nr_entries-1); + /* + * We now have an entry offset in terms of *entries* in + * the table. We need to scale it back up to bytes. + */ + offset *= bt_entry_size_bytes(mm); + return offset; +} + +/* + * How much virtual address space does a single bounds + * directory entry cover? + * + * Note, we need a long long because 4GB doesn't fit in + * to a long on 32-bit. + */ +static inline unsigned long bd_entry_virt_space(struct mm_struct *mm) +{ + 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; +} + /* * Free the backing physical pages of bounds table 'bt_addr'. * Assume start...end is within that bounds table. */ -static int zap_bt_entries(struct mm_struct *mm, +static noinline int zap_bt_entries_mapping(struct mm_struct *mm, unsigned long bt_addr, - unsigned long start, unsigned long end) + unsigned long start_mapping, unsigned long end_mapping) { struct vm_area_struct *vma; unsigned long addr, len; + unsigned long start; + unsigned long end; + + /* + * if we 'end' on a boundary, the offset will be 0 which + * is not what we want. Back it up a byte to get the + * last bt entry. Then once we have the entry itself, + * move 'end' back up by the table entry size. + */ + start = bt_addr + mpx_get_bt_entry_offset_bytes(mm, start_mapping); + end = bt_addr + mpx_get_bt_entry_offset_bytes(mm, end_mapping - 1); + /* + * Move end back up by one entry. Among other things + * this ensures that it remains page-aligned and does + * not screw up zap_page_range() + */ + end += bt_entry_size_bytes(mm); /* * Find the first overlapping vma. If vma->vm_start > start, there @@ -630,7 +780,7 @@ static int zap_bt_entries(struct mm_struct *mm, return -EINVAL; /* - * A NUMA policy on a VM_MPX VMA could cause this bouds table to + * A NUMA policy on a VM_MPX VMA could cause this bounds table to * be split. So we need to look across the entire 'start -> end' * range of this bounds table, find all of the VM_MPX VMAs, and * zap only those. @@ -648,27 +798,65 @@ static int zap_bt_entries(struct mm_struct *mm, len = min(vma->vm_end, end) - addr; zap_page_range(vma, addr, len, NULL); + trace_mpx_unmap_zap(addr, addr+len); vma = vma->vm_next; addr = vma->vm_start; } - return 0; } -static int unmap_single_bt(struct mm_struct *mm, +static unsigned long mpx_get_bd_entry_offset(struct mm_struct *mm, + unsigned long addr) +{ + /* + * There are several ways to derive the bd offsets. We + * use the following approach here: + * 1. We know the size of the virtual address space + * 2. We know the number of entries in a bounds table + * 3. We know that each entry covers a fixed amount of + * virtual address space. + * So, we can just divide the virtual address by the + * virtual space used by one entry to determine which + * entry "controls" the given virtual address. + */ + if (is_64bit_mm(mm)) { + int bd_entry_size = 8; /* 64-bit pointer */ + /* + * Take the 64-bit addressing hole in to account. + */ + addr &= ((1UL << boot_cpu_data.x86_virt_bits) - 1); + return (addr / bd_entry_virt_space(mm)) * bd_entry_size; + } else { + int bd_entry_size = 4; /* 32-bit pointer */ + /* + * 32-bit has no hole so this case needs no mask + */ + return (addr / bd_entry_virt_space(mm)) * bd_entry_size; + } + /* + * The two return calls above are exact copies. If we + * pull out a single copy and put it in here, gcc won't + * realize that we're doing a power-of-2 divide and use + * shifts. It uses a real divide. If we put them up + * there, it manages to figure it out (gcc 4.8.3). + */ +} + +static int unmap_entire_bt(struct mm_struct *mm, long __user *bd_entry, unsigned long bt_addr) { unsigned long expected_old_val = bt_addr | MPX_BD_ENTRY_VALID_FLAG; - unsigned long actual_old_val = 0; + unsigned long uninitialized_var(actual_old_val); int ret; while (1) { int need_write = 1; + unsigned long cleared_bd_entry = 0; pagefault_disable(); - ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry, - expected_old_val, 0); + ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val, + bd_entry, expected_old_val, cleared_bd_entry); pagefault_enable(); if (!ret) break; @@ -687,9 +875,8 @@ static int unmap_single_bt(struct mm_struct *mm, if (actual_old_val != expected_old_val) { /* * Someone else raced with us to unmap the table. - * There was no bounds table pointed to by the - * directory, so declare success. Somebody freed - * it. + * That is OK, since we were both trying to do + * the same thing. Declare success. */ if (!actual_old_val) return 0; @@ -702,176 +889,113 @@ static int unmap_single_bt(struct mm_struct *mm, */ return -EINVAL; } - /* * Note, we are likely being called under do_munmap() already. To * avoid recursion, do_munmap() will check whether it comes * from one bounds table through VM_MPX flag. */ - return do_munmap(mm, bt_addr, MPX_BT_SIZE_BYTES); + return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm)); } -/* - * If the bounds table pointed by bounds directory 'bd_entry' is - * not shared, unmap this whole bounds table. Otherwise, only free - * those backing physical pages of bounds table entries covered - * in this virtual address region start...end. - */ -static int unmap_shared_bt(struct mm_struct *mm, - long __user *bd_entry, unsigned long start, - unsigned long end, bool prev_shared, bool next_shared) +static int try_unmap_single_bt(struct mm_struct *mm, + unsigned long start, unsigned long end) { - unsigned long bt_addr; - int ret; - - ret = get_bt_addr(mm, bd_entry, &bt_addr); + struct vm_area_struct *next; + struct vm_area_struct *prev; /* - * We could see an "error" ret for not-present bounds - * tables (not really an error), or actual errors, but - * stop unmapping either way. + * "bta" == Bounds Table Area: the area controlled by the + * bounds table that we are unmapping. */ - if (ret) - return ret; - - if (prev_shared && next_shared) - ret = zap_bt_entries(mm, bt_addr, - bt_addr+MPX_GET_BT_ENTRY_OFFSET(start), - bt_addr+MPX_GET_BT_ENTRY_OFFSET(end)); - else if (prev_shared) - ret = zap_bt_entries(mm, bt_addr, - bt_addr+MPX_GET_BT_ENTRY_OFFSET(start), - bt_addr+MPX_BT_SIZE_BYTES); - else if (next_shared) - ret = zap_bt_entries(mm, bt_addr, bt_addr, - bt_addr+MPX_GET_BT_ENTRY_OFFSET(end)); - else - ret = unmap_single_bt(mm, bd_entry, bt_addr); - - return ret; -} - -/* - * A virtual address region being munmap()ed might share bounds table - * with adjacent VMAs. We only need to free the backing physical - * memory of these shared bounds tables entries covered in this virtual - * address region. - */ -static int unmap_edge_bts(struct mm_struct *mm, - unsigned long start, unsigned long end) -{ + unsigned long bta_start_vaddr = start & ~(bd_entry_virt_space(mm)-1); + unsigned long bta_end_vaddr = bta_start_vaddr + bd_entry_virt_space(mm); + unsigned long uninitialized_var(bt_addr); + void __user *bde_vaddr; int ret; - long __user *bde_start, *bde_end; - struct vm_area_struct *prev, *next; - bool prev_shared = false, next_shared = false; - - bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start); - bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1); - /* - * Check whether bde_start and bde_end are shared with adjacent - * VMAs. - * - * We already unliked the VMAs from the mm's rbtree so 'start' + * We already unlinked the VMAs from the mm's rbtree so 'start' * is guaranteed to be in a hole. This gets us the first VMA * before the hole in to 'prev' and the next VMA after the hole * in to 'next'. */ next = find_vma_prev(mm, start, &prev); - if (prev && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(prev->vm_end-1)) - == bde_start) - prev_shared = true; - if (next && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(next->vm_start)) - == bde_end) - next_shared = true; - /* - * This virtual address region being munmap()ed is only - * covered by one bounds table. - * - * In this case, if this table is also shared with adjacent - * VMAs, only part of the backing physical memory of the bounds - * table need be freeed. Otherwise the whole bounds table need - * be unmapped. - */ - if (bde_start == bde_end) { - return unmap_shared_bt(mm, bde_start, start, end, - prev_shared, next_shared); + * Do not count other MPX bounds table VMAs as neighbors. + * Although theoretically possible, we do not allow bounds + * tables for bounds tables so our heads do not explode. + * If we count them as neighbors here, we may end up with + * lots of tables even though we have no actual table + * entries in use. + */ + while (next && (next->vm_flags & VM_MPX)) + next = next->vm_next; + while (prev && (prev->vm_flags & VM_MPX)) + prev = prev->vm_prev; + /* + * We know 'start' and 'end' lie within an area controlled + * by a single bounds table. See if there are any other + * VMAs controlled by that bounds table. If there are not + * then we can "expand" the are we are unmapping to possibly + * cover the entire table. + */ + next = find_vma_prev(mm, start, &prev); + if ((!prev || prev->vm_end <= bta_start_vaddr) && + (!next || next->vm_start >= bta_end_vaddr)) { + /* + * No neighbor VMAs controlled by same bounds + * table. Try to unmap the whole thing + */ + start = bta_start_vaddr; + end = bta_end_vaddr; } + bde_vaddr = mm->bd_addr + mpx_get_bd_entry_offset(mm, start); + ret = get_bt_addr(mm, bde_vaddr, &bt_addr); /* - * If more than one bounds tables are covered in this virtual - * address region being munmap()ed, we need to separately check - * whether bde_start and bde_end are shared with adjacent VMAs. + * No bounds table there, so nothing to unmap. */ - ret = unmap_shared_bt(mm, bde_start, start, end, prev_shared, false); - if (ret) - return ret; - ret = unmap_shared_bt(mm, bde_end, start, end, false, next_shared); + if (ret == -ENOENT) { + ret = 0; + return 0; + } if (ret) return ret; - - return 0; + /* + * We are unmapping an entire table. Either because the + * unmap that started this whole process was large enough + * to cover an entire table, or that the unmap was small + * but was the area covered by a bounds table. + */ + if ((start == bta_start_vaddr) && + (end == bta_end_vaddr)) + return unmap_entire_bt(mm, bde_vaddr, bt_addr); + return zap_bt_entries_mapping(mm, bt_addr, start, end); } static int mpx_unmap_tables(struct mm_struct *mm, unsigned long start, unsigned long end) { - int ret; - long __user *bd_entry, *bde_start, *bde_end; - unsigned long bt_addr; - - /* - * "Edge" bounds tables are those which are being used by the region - * (start -> end), but that may be shared with adjacent areas. If they - * turn out to be completely unshared, they will be freed. If they are - * shared, we will free the backing store (like an MADV_DONTNEED) for - * areas used by this region. - */ - ret = unmap_edge_bts(mm, start, end); - switch (ret) { - /* non-present tables are OK */ - case 0: - case -ENOENT: - /* Success, or no tables to unmap */ - break; - case -EINVAL: - case -EFAULT: - default: - return ret; - } - - /* - * Only unmap the bounds table that are - * 1. fully covered - * 2. not at the edges of the mapping, even if full aligned - */ - bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start); - bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1); - for (bd_entry = bde_start + 1; bd_entry < bde_end; bd_entry++) { - ret = get_bt_addr(mm, bd_entry, &bt_addr); - switch (ret) { - case 0: - break; - case -ENOENT: - /* No table here, try the next one */ - continue; - case -EINVAL: - case -EFAULT: - default: - /* - * Note: we are being strict here. - * Any time we run in to an issue - * unmapping tables, we stop and - * SIGSEGV. - */ - return ret; - } - - ret = unmap_single_bt(mm, bd_entry, bt_addr); + unsigned long one_unmap_start; + trace_mpx_unmap_search(start, end); + + one_unmap_start = start; + while (one_unmap_start < end) { + int ret; + unsigned long next_unmap_start = ALIGN(one_unmap_start+1, + bd_entry_virt_space(mm)); + unsigned long one_unmap_end = end; + /* + * if the end is beyond the current bounds table, + * move it back so we only deal with a single one + * at a time + */ + if (one_unmap_end > next_unmap_start) + one_unmap_end = next_unmap_start; + ret = try_unmap_single_bt(mm, one_unmap_start, one_unmap_end); if (ret) return ret; - } + one_unmap_start = next_unmap_start; + } return 0; } diff --git a/kernel/arch/x86/mm/numa.c b/kernel/arch/x86/mm/numa.c index 4053bb58b..c3b3f653e 100644 --- a/kernel/arch/x86/mm/numa.c +++ b/kernel/arch/x86/mm/numa.c @@ -246,8 +246,10 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi) bi->start = max(bi->start, low); bi->end = min(bi->end, high); - /* and there's no empty block */ - if (bi->start >= bi->end) + /* and there's no empty or non-exist block */ + if (bi->start >= bi->end || + !memblock_overlaps_region(&memblock.memory, + bi->start, bi->end - bi->start)) numa_remove_memblk_from(i--, mi); } diff --git a/kernel/arch/x86/mm/pageattr-test.c b/kernel/arch/x86/mm/pageattr-test.c index 6629f397b..5f169d5d7 100644 --- a/kernel/arch/x86/mm/pageattr-test.c +++ b/kernel/arch/x86/mm/pageattr-test.c @@ -8,7 +8,9 @@ #include <linux/kthread.h> #include <linux/random.h> #include <linux/kernel.h> +#include <linux/init.h> #include <linux/mm.h> +#include <linux/vmalloc.h> #include <asm/cacheflush.h> #include <asm/pgtable.h> @@ -255,5 +257,4 @@ static int start_pageattr_test(void) return 0; } - -module_init(start_pageattr_test); +device_initcall(start_pageattr_test); diff --git a/kernel/arch/x86/mm/pageattr.c b/kernel/arch/x86/mm/pageattr.c index 89af288ec..b599a780a 100644 --- a/kernel/arch/x86/mm/pageattr.c +++ b/kernel/arch/x86/mm/pageattr.c @@ -4,7 +4,6 @@ */ #include <linux/highmem.h> #include <linux/bootmem.h> -#include <linux/module.h> #include <linux/sched.h> #include <linux/mm.h> #include <linux/interrupt.h> @@ -14,6 +13,7 @@ #include <linux/percpu.h> #include <linux/gfp.h> #include <linux/pci.h> +#include <linux/vmalloc.h> #include <asm/e820.h> #include <asm/processor.h> @@ -33,7 +33,7 @@ struct cpa_data { pgd_t *pgd; pgprot_t mask_set; pgprot_t mask_clr; - int numpages; + unsigned long numpages; int flags; unsigned long pfn; unsigned force_split : 1; @@ -129,16 +129,15 @@ within(unsigned long addr, unsigned long start, unsigned long end) */ void clflush_cache_range(void *vaddr, unsigned int size) { - void *vend = vaddr + size - 1; + unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1; + void *vend = vaddr + size; + void *p; mb(); - for (; vaddr < vend; vaddr += boot_cpu_data.x86_clflush_size) - clflushopt(vaddr); - /* - * Flush any possible final partial cacheline: - */ - clflushopt(vend); + for (p = (void *)((unsigned long)vaddr & ~clflush_mask); + p < vend; p += boot_cpu_data.x86_clflush_size) + clflushopt(p); mb(); } @@ -418,17 +417,31 @@ phys_addr_t slow_virt_to_phys(void *__virt_addr) phys_addr_t phys_addr; unsigned long offset; enum pg_level level; - unsigned long psize; - unsigned long pmask; pte_t *pte; pte = lookup_address(virt_addr, &level); BUG_ON(!pte); - psize = page_level_size(level); - pmask = page_level_mask(level); - offset = virt_addr & ~pmask; - phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; - return (phys_addr | offset); + + /* + * pXX_pfn() returns unsigned long, which must be cast to phys_addr_t + * before being left-shifted PAGE_SHIFT bits -- this trick is to + * make 32-PAE kernel work correctly. + */ + switch (level) { + case PG_LEVEL_1G: + phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; + offset = virt_addr & ~PUD_PAGE_MASK; + break; + case PG_LEVEL_2M: + phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; + offset = virt_addr & ~PMD_PAGE_MASK; + break; + default: + phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; + offset = virt_addr & ~PAGE_MASK; + } + + return (phys_addr_t)(phys_addr | offset); } EXPORT_SYMBOL_GPL(slow_virt_to_phys); @@ -461,7 +474,7 @@ static int try_preserve_large_page(pte_t *kpte, unsigned long address, struct cpa_data *cpa) { - unsigned long nextpage_addr, numpages, pmask, psize, addr, pfn; + unsigned long nextpage_addr, numpages, pmask, psize, addr, pfn, old_pfn; pte_t new_pte, old_pte, *tmp; pgprot_t old_prot, new_prot, req_prot; int i, do_split = 1; @@ -481,17 +494,21 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, switch (level) { case PG_LEVEL_2M: -#ifdef CONFIG_X86_64 + old_prot = pmd_pgprot(*(pmd_t *)kpte); + old_pfn = pmd_pfn(*(pmd_t *)kpte); + break; case PG_LEVEL_1G: -#endif - psize = page_level_size(level); - pmask = page_level_mask(level); + old_prot = pud_pgprot(*(pud_t *)kpte); + old_pfn = pud_pfn(*(pud_t *)kpte); break; default: do_split = -EINVAL; goto out_unlock; } + psize = page_level_size(level); + pmask = page_level_mask(level); + /* * Calculate the number of pages, which fit into this large * page starting at address: @@ -507,7 +524,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * up accordingly. */ old_pte = *kpte; - old_prot = req_prot = pgprot_large_2_4k(pte_pgprot(old_pte)); + req_prot = pgprot_large_2_4k(old_prot); pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr); pgprot_val(req_prot) |= pgprot_val(cpa->mask_set); @@ -533,10 +550,10 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, req_prot = canon_pgprot(req_prot); /* - * old_pte points to the large page base address. So we need + * old_pfn points to the large page base pfn. So we need * to add the offset of the virtual address: */ - pfn = pte_pfn(old_pte) + ((address & (psize - 1)) >> PAGE_SHIFT); + pfn = old_pfn + ((address & (psize - 1)) >> PAGE_SHIFT); cpa->pfn = pfn; new_prot = static_protections(req_prot, address, pfn); @@ -547,7 +564,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * the pages in the range we try to preserve: */ addr = address & pmask; - pfn = pte_pfn(old_pte); + pfn = old_pfn; for (i = 0; i < (psize >> PAGE_SHIFT); i++, addr += PAGE_SIZE, pfn++) { pgprot_t chk_prot = static_protections(req_prot, addr, pfn); @@ -577,7 +594,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * The address is aligned and the number of pages * covers the full page. */ - new_pte = pfn_pte(pte_pfn(old_pte), new_prot); + new_pte = pfn_pte(old_pfn, new_prot); __set_pmd_pte(kpte, address, new_pte); cpa->flags |= CPA_FLUSHTLB; do_split = 0; @@ -594,7 +611,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, struct page *base) { pte_t *pbase = (pte_t *)page_address(base); - unsigned long pfn, pfninc = 1; + unsigned long ref_pfn, pfn, pfninc = 1; unsigned int i, level; pte_t *tmp; pgprot_t ref_prot; @@ -611,26 +628,33 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, } paravirt_alloc_pte(&init_mm, page_to_pfn(base)); - ref_prot = pte_pgprot(pte_clrhuge(*kpte)); - /* promote PAT bit to correct position */ - if (level == PG_LEVEL_2M) + switch (level) { + case PG_LEVEL_2M: + ref_prot = pmd_pgprot(*(pmd_t *)kpte); + /* clear PSE and promote PAT bit to correct position */ ref_prot = pgprot_large_2_4k(ref_prot); + ref_pfn = pmd_pfn(*(pmd_t *)kpte); + break; -#ifdef CONFIG_X86_64 - if (level == PG_LEVEL_1G) { + case PG_LEVEL_1G: + ref_prot = pud_pgprot(*(pud_t *)kpte); + ref_pfn = pud_pfn(*(pud_t *)kpte); pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT; + /* - * Set the PSE flags only if the PRESENT flag is set + * Clear the PSE flags if the PRESENT flag is not set * otherwise pmd_present/pmd_huge will return true * even on a non present pmd. */ - if (pgprot_val(ref_prot) & _PAGE_PRESENT) - pgprot_val(ref_prot) |= _PAGE_PSE; - else + if (!(pgprot_val(ref_prot) & _PAGE_PRESENT)) pgprot_val(ref_prot) &= ~_PAGE_PSE; + break; + + default: + spin_unlock(&pgd_lock); + return 1; } -#endif /* * Set the GLOBAL flags only if the PRESENT flag is set @@ -646,13 +670,16 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, /* * Get the target pfn from the original entry: */ - pfn = pte_pfn(*kpte); + pfn = ref_pfn; for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc) set_pte(&pbase[i], pfn_pte(pfn, canon_pgprot(ref_prot))); - if (pfn_range_is_mapped(PFN_DOWN(__pa(address)), - PFN_DOWN(__pa(address)) + 1)) - split_page_count(level); + if (virt_addr_valid(address)) { + unsigned long pfn = PFN_DOWN(__pa(address)); + + if (pfn_range_is_mapped(pfn, pfn + 1)) + split_page_count(level); + } /* * Install the new, split up pagetable. @@ -1324,7 +1351,7 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) * CPA operation. Either a large page has been * preserved or a single page update happened. */ - BUG_ON(cpa->numpages > numpages); + BUG_ON(cpa->numpages > numpages || !cpa->numpages); numpages -= cpa->numpages; if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) cpa->curpage++; @@ -1468,6 +1495,9 @@ int _set_memory_uc(unsigned long addr, int numpages) { /* * for now UC MINUS. see comments in ioremap_nocache() + * If you really need strong UC use ioremap_uc(), but note + * that you cannot override IO areas with set_memory_*() as + * these helpers cannot work with IO memory. */ return change_page_attr_set(&addr, numpages, cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS), @@ -1502,12 +1532,10 @@ EXPORT_SYMBOL(set_memory_uc); static int _set_memory_array(unsigned long *addr, int addrinarray, enum page_cache_mode new_type) { + enum page_cache_mode set_type; int i, j; int ret; - /* - * for now UC MINUS. see comments in ioremap_nocache() - */ for (i = 0; i < addrinarray; i++) { ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE, new_type, NULL); @@ -1515,9 +1543,12 @@ static int _set_memory_array(unsigned long *addr, int addrinarray, goto out_free; } + /* If WC, set to UC- first and then WC */ + set_type = (new_type == _PAGE_CACHE_MODE_WC) ? + _PAGE_CACHE_MODE_UC_MINUS : new_type; + ret = change_page_attr_set(addr, addrinarray, - cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS), - 1); + cachemode2pgprot(set_type), 1); if (!ret && new_type == _PAGE_CACHE_MODE_WC) ret = change_page_attr_set_clr(addr, addrinarray, @@ -1549,6 +1580,12 @@ int set_memory_array_wc(unsigned long *addr, int addrinarray) } EXPORT_SYMBOL(set_memory_array_wc); +int set_memory_array_wt(unsigned long *addr, int addrinarray) +{ + return _set_memory_array(addr, addrinarray, _PAGE_CACHE_MODE_WT); +} +EXPORT_SYMBOL_GPL(set_memory_array_wt); + int _set_memory_wc(unsigned long addr, int numpages) { int ret; @@ -1571,27 +1608,42 @@ int set_memory_wc(unsigned long addr, int numpages) { int ret; - if (!pat_enabled) - return set_memory_uc(addr, numpages); - ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, _PAGE_CACHE_MODE_WC, NULL); if (ret) - goto out_err; + return ret; ret = _set_memory_wc(addr, numpages); if (ret) - goto out_free; + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); - return 0; - -out_free: - free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); -out_err: return ret; } EXPORT_SYMBOL(set_memory_wc); +int _set_memory_wt(unsigned long addr, int numpages) +{ + return change_page_attr_set(&addr, numpages, + cachemode2pgprot(_PAGE_CACHE_MODE_WT), 0); +} + +int set_memory_wt(unsigned long addr, int numpages) +{ + int ret; + + ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, + _PAGE_CACHE_MODE_WT, NULL); + if (ret) + return ret; + + ret = _set_memory_wt(addr, numpages); + if (ret) + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); + + return ret; +} +EXPORT_SYMBOL_GPL(set_memory_wt); + int _set_memory_wb(unsigned long addr, int numpages) { /* WB cache mode is hard wired to all cache attribute bits being 0 */ @@ -1682,6 +1734,7 @@ static int _set_pages_array(struct page **pages, int addrinarray, { unsigned long start; unsigned long end; + enum page_cache_mode set_type; int i; int free_idx; int ret; @@ -1695,8 +1748,12 @@ static int _set_pages_array(struct page **pages, int addrinarray, goto err_out; } + /* If WC, set to UC- first and then WC */ + set_type = (new_type == _PAGE_CACHE_MODE_WC) ? + _PAGE_CACHE_MODE_UC_MINUS : new_type; + ret = cpa_set_pages_array(pages, addrinarray, - cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS)); + cachemode2pgprot(set_type)); if (!ret && new_type == _PAGE_CACHE_MODE_WC) ret = change_page_attr_set_clr(NULL, addrinarray, cachemode2pgprot( @@ -1730,6 +1787,12 @@ int set_pages_array_wc(struct page **pages, int addrinarray) } EXPORT_SYMBOL(set_pages_array_wc); +int set_pages_array_wt(struct page **pages, int addrinarray) +{ + return _set_pages_array(pages, addrinarray, _PAGE_CACHE_MODE_WT); +} +EXPORT_SYMBOL_GPL(set_pages_array_wt); + int set_pages_wb(struct page *page, int numpages) { unsigned long addr = (unsigned long)page_address(page); diff --git a/kernel/arch/x86/mm/pat.c b/kernel/arch/x86/mm/pat.c index 35af6771a..188e3e07e 100644 --- a/kernel/arch/x86/mm/pat.c +++ b/kernel/arch/x86/mm/pat.c @@ -33,13 +33,17 @@ #include "pat_internal.h" #include "mm_internal.h" -#ifdef CONFIG_X86_PAT -int __read_mostly pat_enabled = 1; +#undef pr_fmt +#define pr_fmt(fmt) "" fmt + +static bool boot_cpu_done; + +static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT); static inline void pat_disable(const char *reason) { - pat_enabled = 0; - printk(KERN_INFO "%s\n", reason); + __pat_enabled = 0; + pr_info("x86/PAT: %s\n", reason); } static int __init nopat(char *str) @@ -48,13 +52,12 @@ static int __init nopat(char *str) return 0; } early_param("nopat", nopat); -#else -static inline void pat_disable(const char *reason) + +bool pat_enabled(void) { - (void)reason; + return !!__pat_enabled; } -#endif - +EXPORT_SYMBOL_GPL(pat_enabled); int pat_debug_enable; @@ -65,22 +68,24 @@ static int __init pat_debug_setup(char *str) } __setup("debugpat", pat_debug_setup); -static u64 __read_mostly boot_pat_state; - #ifdef CONFIG_X86_PAT /* - * X86 PAT uses page flags WC and Uncached together to keep track of - * memory type of pages that have backing page struct. X86 PAT supports 3 - * different memory types, _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC and - * _PAGE_CACHE_MODE_UC_MINUS and fourth state where page's memory type has not - * been changed from its default (value of -1 used to denote this). - * Note we do not support _PAGE_CACHE_MODE_UC here. + * X86 PAT uses page flags arch_1 and uncached together to keep track of + * memory type of pages that have backing page struct. + * + * X86 PAT supports 4 different memory types: + * - _PAGE_CACHE_MODE_WB + * - _PAGE_CACHE_MODE_WC + * - _PAGE_CACHE_MODE_UC_MINUS + * - _PAGE_CACHE_MODE_WT + * + * _PAGE_CACHE_MODE_WB is the default type. */ -#define _PGMT_DEFAULT 0 +#define _PGMT_WB 0 #define _PGMT_WC (1UL << PG_arch_1) #define _PGMT_UC_MINUS (1UL << PG_uncached) -#define _PGMT_WB (1UL << PG_uncached | 1UL << PG_arch_1) +#define _PGMT_WT (1UL << PG_uncached | 1UL << PG_arch_1) #define _PGMT_MASK (1UL << PG_uncached | 1UL << PG_arch_1) #define _PGMT_CLEAR_MASK (~_PGMT_MASK) @@ -88,14 +93,14 @@ static inline enum page_cache_mode get_page_memtype(struct page *pg) { unsigned long pg_flags = pg->flags & _PGMT_MASK; - if (pg_flags == _PGMT_DEFAULT) - return -1; + if (pg_flags == _PGMT_WB) + return _PAGE_CACHE_MODE_WB; else if (pg_flags == _PGMT_WC) return _PAGE_CACHE_MODE_WC; else if (pg_flags == _PGMT_UC_MINUS) return _PAGE_CACHE_MODE_UC_MINUS; else - return _PAGE_CACHE_MODE_WB; + return _PAGE_CACHE_MODE_WT; } static inline void set_page_memtype(struct page *pg, @@ -112,11 +117,12 @@ static inline void set_page_memtype(struct page *pg, case _PAGE_CACHE_MODE_UC_MINUS: memtype_flags = _PGMT_UC_MINUS; break; - case _PAGE_CACHE_MODE_WB: - memtype_flags = _PGMT_WB; + case _PAGE_CACHE_MODE_WT: + memtype_flags = _PGMT_WT; break; + case _PAGE_CACHE_MODE_WB: default: - memtype_flags = _PGMT_DEFAULT; + memtype_flags = _PGMT_WB; break; } @@ -174,78 +180,154 @@ static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg) * configuration. * Using lower indices is preferred, so we start with highest index. */ -void pat_init_cache_modes(void) +void pat_init_cache_modes(u64 pat) { - int i; enum page_cache_mode cache; char pat_msg[33]; - u64 pat; + int i; - rdmsrl(MSR_IA32_CR_PAT, pat); pat_msg[32] = 0; for (i = 7; i >= 0; i--) { cache = pat_get_cache_mode((pat >> (i * 8)) & 7, pat_msg + 4 * i); update_cache_mode_entry(i, cache); } - pr_info("PAT configuration [0-7]: %s\n", pat_msg); + pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg); } #define PAT(x, y) ((u64)PAT_ ## y << ((x)*8)) -void pat_init(void) +static void pat_bsp_init(u64 pat) { - u64 pat; - bool boot_cpu = !boot_pat_state; + u64 tmp_pat; - if (!pat_enabled) + if (!cpu_has_pat) { + pat_disable("PAT not supported by CPU."); return; + } - if (!cpu_has_pat) { - if (!boot_pat_state) { - pat_disable("PAT not supported by CPU."); - return; - } else { - /* - * If this happens we are on a secondary CPU, but - * switched to PAT on the boot CPU. We have no way to - * undo PAT. - */ - printk(KERN_ERR "PAT enabled, " - "but not supported by secondary CPU\n"); - BUG(); - } + if (!pat_enabled()) + goto done; + + rdmsrl(MSR_IA32_CR_PAT, tmp_pat); + if (!tmp_pat) { + pat_disable("PAT MSR is 0, disabled."); + return; } - /* Set PWT to Write-Combining. All other bits stay the same */ - /* - * PTE encoding used in Linux: - * PAT - * |PCD - * ||PWT - * ||| - * 000 WB _PAGE_CACHE_WB - * 001 WC _PAGE_CACHE_WC - * 010 UC- _PAGE_CACHE_UC_MINUS - * 011 UC _PAGE_CACHE_UC - * PAT bit unused - */ - pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) | - PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC); - - /* Boot CPU check */ - if (!boot_pat_state) { - rdmsrl(MSR_IA32_CR_PAT, boot_pat_state); - if (!boot_pat_state) { - pat_disable("PAT read returns always zero, disabled."); - return; - } + wrmsrl(MSR_IA32_CR_PAT, pat); + +done: + pat_init_cache_modes(pat); +} + +static void pat_ap_init(u64 pat) +{ + if (!pat_enabled()) + return; + + if (!cpu_has_pat) { + /* + * If this happens we are on a secondary CPU, but switched to + * PAT on the boot CPU. We have no way to undo PAT. + */ + panic("x86/PAT: PAT enabled, but not supported by secondary CPU\n"); } wrmsrl(MSR_IA32_CR_PAT, pat); +} + +void pat_init(void) +{ + u64 pat; + struct cpuinfo_x86 *c = &boot_cpu_data; + + if (!pat_enabled()) { + /* + * No PAT. Emulate the PAT table that corresponds to the two + * cache bits, PWT (Write Through) and PCD (Cache Disable). This + * setup is the same as the BIOS default setup when the system + * has PAT but the "nopat" boot option has been specified. This + * emulated PAT table is used when MSR_IA32_CR_PAT returns 0. + * + * PTE encoding: + * + * PCD + * |PWT PAT + * || slot + * 00 0 WB : _PAGE_CACHE_MODE_WB + * 01 1 WT : _PAGE_CACHE_MODE_WT + * 10 2 UC-: _PAGE_CACHE_MODE_UC_MINUS + * 11 3 UC : _PAGE_CACHE_MODE_UC + * + * NOTE: When WC or WP is used, it is redirected to UC- per + * the default setup in __cachemode2pte_tbl[]. + */ + pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) | + PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC); - if (boot_cpu) - pat_init_cache_modes(); + } else if ((c->x86_vendor == X86_VENDOR_INTEL) && + (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || + ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) { + /* + * PAT support with the lower four entries. Intel Pentium 2, + * 3, M, and 4 are affected by PAT errata, which makes the + * upper four entries unusable. To be on the safe side, we don't + * use those. + * + * PTE encoding: + * PAT + * |PCD + * ||PWT PAT + * ||| slot + * 000 0 WB : _PAGE_CACHE_MODE_WB + * 001 1 WC : _PAGE_CACHE_MODE_WC + * 010 2 UC-: _PAGE_CACHE_MODE_UC_MINUS + * 011 3 UC : _PAGE_CACHE_MODE_UC + * PAT bit unused + * + * NOTE: When WT or WP is used, it is redirected to UC- per + * the default setup in __cachemode2pte_tbl[]. + */ + pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) | + PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC); + } else { + /* + * Full PAT support. We put WT in slot 7 to improve + * robustness in the presence of errata that might cause + * the high PAT bit to be ignored. This way, a buggy slot 7 + * access will hit slot 3, and slot 3 is UC, so at worst + * we lose performance without causing a correctness issue. + * Pentium 4 erratum N46 is an example for such an erratum, + * although we try not to use PAT at all on affected CPUs. + * + * PTE encoding: + * PAT + * |PCD + * ||PWT PAT + * ||| slot + * 000 0 WB : _PAGE_CACHE_MODE_WB + * 001 1 WC : _PAGE_CACHE_MODE_WC + * 010 2 UC-: _PAGE_CACHE_MODE_UC_MINUS + * 011 3 UC : _PAGE_CACHE_MODE_UC + * 100 4 WB : Reserved + * 101 5 WC : Reserved + * 110 6 UC-: Reserved + * 111 7 WT : _PAGE_CACHE_MODE_WT + * + * The reserved slots are unused, but mapped to their + * corresponding types in the presence of PAT errata. + */ + pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) | + PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, WT); + } + + if (!boot_cpu_done) { + pat_bsp_init(pat); + boot_cpu_done = true; + } else { + pat_ap_init(pat); + } } #undef PAT @@ -267,9 +349,9 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, * request is for WB. */ if (req_type == _PAGE_CACHE_MODE_WB) { - u8 mtrr_type; + u8 mtrr_type, uniform; - mtrr_type = mtrr_type_lookup(start, end); + mtrr_type = mtrr_type_lookup(start, end, &uniform); if (mtrr_type != MTRR_TYPE_WRBACK) return _PAGE_CACHE_MODE_UC_MINUS; @@ -324,9 +406,14 @@ static int pat_pagerange_is_ram(resource_size_t start, resource_size_t end) /* * For RAM pages, we use page flags to mark the pages with appropriate type. - * Here we do two pass: - * - Find the memtype of all the pages in the range, look for any conflicts - * - In case of no conflicts, set the new memtype for pages in the range + * The page flags are limited to four types, WB (default), WC, WT and UC-. + * WP request fails with -EINVAL, and UC gets redirected to UC-. Setting + * a new memory type is only allowed for a page mapped with the default WB + * type. + * + * Here we do two passes: + * - Find the memtype of all the pages in the range, look for any conflicts. + * - In case of no conflicts, set the new memtype for pages in the range. */ static int reserve_ram_pages_type(u64 start, u64 end, enum page_cache_mode req_type, @@ -335,6 +422,12 @@ static int reserve_ram_pages_type(u64 start, u64 end, struct page *page; u64 pfn; + if (req_type == _PAGE_CACHE_MODE_WP) { + if (new_type) + *new_type = _PAGE_CACHE_MODE_UC_MINUS; + return -EINVAL; + } + if (req_type == _PAGE_CACHE_MODE_UC) { /* We do not support strong UC */ WARN_ON_ONCE(1); @@ -346,8 +439,8 @@ static int reserve_ram_pages_type(u64 start, u64 end, page = pfn_to_page(pfn); type = get_page_memtype(page); - if (type != -1) { - pr_info("reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n", + if (type != _PAGE_CACHE_MODE_WB) { + pr_info("x86/PAT: reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n", start, end - 1, type, req_type); if (new_type) *new_type = type; @@ -373,7 +466,7 @@ static int free_ram_pages_type(u64 start, u64 end) for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) { page = pfn_to_page(pfn); - set_page_memtype(page, -1); + set_page_memtype(page, _PAGE_CACHE_MODE_WB); } return 0; } @@ -384,6 +477,7 @@ static int free_ram_pages_type(u64 start, u64 end) * - _PAGE_CACHE_MODE_WC * - _PAGE_CACHE_MODE_UC_MINUS * - _PAGE_CACHE_MODE_UC + * - _PAGE_CACHE_MODE_WT * * If new_type is NULL, function will return an error if it cannot reserve the * region with req_type. If new_type is non-NULL, function will return @@ -400,14 +494,10 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type, BUG_ON(start >= end); /* end is exclusive */ - if (!pat_enabled) { + if (!pat_enabled()) { /* This is identical to page table setting without PAT */ - if (new_type) { - if (req_type == _PAGE_CACHE_MODE_WC) - *new_type = _PAGE_CACHE_MODE_UC_MINUS; - else - *new_type = req_type; - } + if (new_type) + *new_type = req_type; return 0; } @@ -451,9 +541,9 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type, err = rbt_memtype_check_insert(new, new_type); if (err) { - printk(KERN_INFO "reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n", - start, end - 1, - cattr_name(new->type), cattr_name(req_type)); + pr_info("x86/PAT: reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n", + start, end - 1, + cattr_name(new->type), cattr_name(req_type)); kfree(new); spin_unlock(&memtype_lock); @@ -475,7 +565,7 @@ int free_memtype(u64 start, u64 end) int is_range_ram; struct memtype *entry; - if (!pat_enabled) + if (!pat_enabled()) return 0; /* Low ISA region is always mapped WB. No need to track */ @@ -497,8 +587,8 @@ int free_memtype(u64 start, u64 end) spin_unlock(&memtype_lock); if (!entry) { - printk(KERN_INFO "%s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n", - current->comm, current->pid, start, end - 1); + pr_info("x86/PAT: %s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n", + current->comm, current->pid, start, end - 1); return -EINVAL; } @@ -517,7 +607,7 @@ int free_memtype(u64 start, u64 end) * Only to be called when PAT is enabled * * Returns _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC, _PAGE_CACHE_MODE_UC_MINUS - * or _PAGE_CACHE_MODE_UC + * or _PAGE_CACHE_MODE_WT. */ static enum page_cache_mode lookup_memtype(u64 paddr) { @@ -529,16 +619,9 @@ static enum page_cache_mode lookup_memtype(u64 paddr) if (pat_pagerange_is_ram(paddr, paddr + PAGE_SIZE)) { struct page *page; - page = pfn_to_page(paddr >> PAGE_SHIFT); - rettype = get_page_memtype(page); - /* - * -1 from get_page_memtype() implies RAM page is in its - * default state and not reserved, and hence of type WB - */ - if (rettype == -1) - rettype = _PAGE_CACHE_MODE_WB; - return rettype; + page = pfn_to_page(paddr >> PAGE_SHIFT); + return get_page_memtype(page); } spin_lock(&memtype_lock); @@ -623,13 +706,13 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size) u64 to = from + size; u64 cursor = from; - if (!pat_enabled) + if (!pat_enabled()) return 1; while (cursor < to) { if (!devmem_is_allowed(pfn)) { - printk(KERN_INFO "Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n", - current->comm, from, to - 1); + pr_info("x86/PAT: Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n", + current->comm, from, to - 1); return 0; } cursor += PAGE_SIZE; @@ -659,7 +742,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, * caching for the high addresses through the KEN pin, but * we maintain the tradition of paranoia in this code. */ - if (!pat_enabled && + if (!pat_enabled() && !(boot_cpu_has(X86_FEATURE_MTRR) || boot_cpu_has(X86_FEATURE_K6_MTRR) || boot_cpu_has(X86_FEATURE_CYRIX_ARR) || @@ -698,8 +781,7 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, size; if (ioremap_change_attr((unsigned long)__va(base), id_sz, pcm) < 0) { - printk(KERN_INFO "%s:%d ioremap_change_attr failed %s " - "for [mem %#010Lx-%#010Lx]\n", + pr_info("x86/PAT: %s:%d ioremap_change_attr failed %s for [mem %#010Lx-%#010Lx]\n", current->comm, current->pid, cattr_name(pcm), base, (unsigned long long)(base + size-1)); @@ -729,12 +811,12 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, * the type requested matches the type of first page in the range. */ if (is_ram) { - if (!pat_enabled) + if (!pat_enabled()) return 0; pcm = lookup_memtype(paddr); if (want_pcm != pcm) { - printk(KERN_WARNING "%s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n", + pr_warn("x86/PAT: %s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n", current->comm, current->pid, cattr_name(want_pcm), (unsigned long long)paddr, @@ -755,13 +837,12 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, if (strict_prot || !is_new_memtype_allowed(paddr, size, want_pcm, pcm)) { free_memtype(paddr, paddr + size); - printk(KERN_ERR "%s:%d map pfn expected mapping type %s" - " for [mem %#010Lx-%#010Lx], got %s\n", - current->comm, current->pid, - cattr_name(want_pcm), - (unsigned long long)paddr, - (unsigned long long)(paddr + size - 1), - cattr_name(pcm)); + pr_err("x86/PAT: %s:%d map pfn expected mapping type %s for [mem %#010Lx-%#010Lx], got %s\n", + current->comm, current->pid, + cattr_name(want_pcm), + (unsigned long long)paddr, + (unsigned long long)(paddr + size - 1), + cattr_name(pcm)); return -EINVAL; } /* @@ -844,7 +925,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, return ret; } - if (!pat_enabled) + if (!pat_enabled()) return 0; /* @@ -872,7 +953,7 @@ int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, { enum page_cache_mode pcm; - if (!pat_enabled) + if (!pat_enabled()) return 0; /* Set prot based on lookup */ @@ -913,14 +994,18 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, pgprot_t pgprot_writecombine(pgprot_t prot) { - if (pat_enabled) - return __pgprot(pgprot_val(prot) | + return __pgprot(pgprot_val(prot) | cachemode2protval(_PAGE_CACHE_MODE_WC)); - else - return pgprot_noncached(prot); } EXPORT_SYMBOL_GPL(pgprot_writecombine); +pgprot_t pgprot_writethrough(pgprot_t prot) +{ + return __pgprot(pgprot_val(prot) | + cachemode2protval(_PAGE_CACHE_MODE_WT)); +} +EXPORT_SYMBOL_GPL(pgprot_writethrough); + #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT) static struct memtype *memtype_get_idx(loff_t pos) @@ -996,7 +1081,7 @@ static const struct file_operations memtype_fops = { static int __init pat_memtype_list_init(void) { - if (pat_enabled) { + if (pat_enabled()) { debugfs_create_file("pat_memtype_list", S_IRUSR, arch_debugfs_dir, NULL, &memtype_fops); } diff --git a/kernel/arch/x86/mm/pat_internal.h b/kernel/arch/x86/mm/pat_internal.h index f64116203..a739bfc40 100644 --- a/kernel/arch/x86/mm/pat_internal.h +++ b/kernel/arch/x86/mm/pat_internal.h @@ -4,7 +4,7 @@ extern int pat_debug_enable; #define dprintk(fmt, arg...) \ - do { if (pat_debug_enable) printk(KERN_INFO fmt, ##arg); } while (0) + do { if (pat_debug_enable) pr_info("x86/PAT: " fmt, ##arg); } while (0) struct memtype { u64 start; diff --git a/kernel/arch/x86/mm/pat_rbtree.c b/kernel/arch/x86/mm/pat_rbtree.c index 6582adcc8..639310803 100644 --- a/kernel/arch/x86/mm/pat_rbtree.c +++ b/kernel/arch/x86/mm/pat_rbtree.c @@ -160,9 +160,9 @@ success: return 0; failure: - printk(KERN_INFO "%s:%d conflicting memory types " - "%Lx-%Lx %s<->%s\n", current->comm, current->pid, start, - end, cattr_name(found_type), cattr_name(match->type)); + pr_info("x86/PAT: %s:%d conflicting memory types %Lx-%Lx %s<->%s\n", + current->comm, current->pid, start, end, + cattr_name(found_type), cattr_name(match->type)); return -EBUSY; } diff --git a/kernel/arch/x86/mm/pgtable.c b/kernel/arch/x86/mm/pgtable.c index 0b97d2c75..fb0a9dd1d 100644 --- a/kernel/arch/x86/mm/pgtable.c +++ b/kernel/arch/x86/mm/pgtable.c @@ -563,16 +563,31 @@ void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys, } #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +/** + * pud_set_huge - setup kernel PUD mapping + * + * MTRRs can override PAT memory types with 4KiB granularity. Therefore, this + * function sets up a huge page only if any of the following conditions are met: + * + * - MTRRs are disabled, or + * + * - MTRRs are enabled and the range is completely covered by a single MTRR, or + * + * - MTRRs are enabled and the corresponding MTRR memory type is WB, which + * has no effect on the requested PAT memory type. + * + * Callers should try to decrease page size (1GB -> 2MB -> 4K) if the bigger + * page mapping attempt fails. + * + * Returns 1 on success and 0 on failure. + */ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) { - u8 mtrr; + u8 mtrr, uniform; - /* - * Do not use a huge page when the range is covered by non-WB type - * of MTRRs. - */ - mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE); - if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF)) + mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE, &uniform); + if ((mtrr != MTRR_TYPE_INVALID) && (!uniform) && + (mtrr != MTRR_TYPE_WRBACK)) return 0; prot = pgprot_4k_2_large(prot); @@ -584,17 +599,24 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) return 1; } +/** + * pmd_set_huge - setup kernel PMD mapping + * + * See text over pud_set_huge() above. + * + * Returns 1 on success and 0 on failure. + */ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { - u8 mtrr; + u8 mtrr, uniform; - /* - * Do not use a huge page when the range is covered by non-WB type - * of MTRRs. - */ - mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE); - if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF)) + mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE, &uniform); + if ((mtrr != MTRR_TYPE_INVALID) && (!uniform) && + (mtrr != MTRR_TYPE_WRBACK)) { + pr_warn_once("%s: Cannot satisfy [mem %#010llx-%#010llx] with a huge-page mapping due to MTRR override.\n", + __func__, addr, addr + PMD_SIZE); return 0; + } prot = pgprot_4k_2_large(prot); @@ -605,6 +627,11 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) return 1; } +/** + * pud_clear_huge - clear kernel PUD mapping when it is set + * + * Returns 1 on success and 0 on failure (no PUD map is found). + */ int pud_clear_huge(pud_t *pud) { if (pud_large(*pud)) { @@ -615,6 +642,11 @@ int pud_clear_huge(pud_t *pud) return 0; } +/** + * pmd_clear_huge - clear kernel PMD mapping when it is set + * + * Returns 1 on success and 0 on failure (no PMD map is found). + */ int pmd_clear_huge(pmd_t *pmd) { if (pmd_large(*pmd)) { diff --git a/kernel/arch/x86/mm/srat.c b/kernel/arch/x86/mm/srat.c index 66338a60a..c2aea63be 100644 --- a/kernel/arch/x86/mm/srat.c +++ b/kernel/arch/x86/mm/srat.c @@ -192,10 +192,11 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) node_set(node, numa_nodes_parsed); - pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s\n", + pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s%s\n", node, pxm, (unsigned long long) start, (unsigned long long) end - 1, - hotpluggable ? " hotplug" : ""); + hotpluggable ? " hotplug" : "", + ma->flags & ACPI_SRAT_MEM_NON_VOLATILE ? " non-volatile" : ""); /* Mark hotplug range in memblock. */ if (hotpluggable && memblock_mark_hotplug(start, ma->length)) diff --git a/kernel/arch/x86/mm/tlb.c b/kernel/arch/x86/mm/tlb.c index 90b924acd..8f4cc3dfa 100644 --- a/kernel/arch/x86/mm/tlb.c +++ b/kernel/arch/x86/mm/tlb.c @@ -140,6 +140,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask, info.flush_end = end; count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); + trace_tlb_flush(TLB_REMOTE_SEND_IPI, end - start); if (is_uv_system()) { unsigned int cpu; @@ -160,7 +161,10 @@ void flush_tlb_current_task(void) preempt_disable(); count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + + /* This is an implicit full barrier that synchronizes with switch_mm. */ local_flush_tlb(); + trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); @@ -187,17 +191,29 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long base_pages_to_flush = TLB_FLUSH_ALL; preempt_disable(); - if (current->active_mm != mm) + if (current->active_mm != mm) { + /* Synchronize with switch_mm. */ + smp_mb(); + goto out; + } if (!current->mm) { leave_mm(smp_processor_id()); + + /* Synchronize with switch_mm. */ + smp_mb(); + goto out; } if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) base_pages_to_flush = (end - start) >> PAGE_SHIFT; + /* + * Both branches below are implicit full barriers (MOV to CR or + * INVLPG) that synchronize with switch_mm. + */ if (base_pages_to_flush > tlb_single_page_flush_ceiling) { base_pages_to_flush = TLB_FLUSH_ALL; count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); @@ -227,10 +243,18 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) preempt_disable(); if (current->active_mm == mm) { - if (current->mm) + if (current->mm) { + /* + * Implicit full barrier (INVLPG) that synchronizes + * with switch_mm. + */ __flush_tlb_one(start); - else + } else { leave_mm(smp_processor_id()); + + /* Synchronize with switch_mm. */ + smp_mb(); + } } if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) |