diff options
Diffstat (limited to 'arch/x86/mm')
| -rw-r--r-- | arch/x86/mm/fault.c | 29 | ||||
| -rw-r--r-- | arch/x86/mm/init_32.c | 2 | ||||
| -rw-r--r-- | arch/x86/mm/init_64.c | 38 | ||||
| -rw-r--r-- | arch/x86/mm/ioremap.c | 20 | ||||
| -rw-r--r-- | arch/x86/mm/kmemcheck/kmemcheck.c | 14 | ||||
| -rw-r--r-- | arch/x86/mm/numa.c | 123 | ||||
| -rw-r--r-- | arch/x86/mm/pgtable_32.c | 35 |
7 files changed, 130 insertions, 131 deletions
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index a24194681513..d973e61e450d 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -3,7 +3,6 @@ * Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs. * Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar */ -#include <linux/magic.h> /* STACK_END_MAGIC */ #include <linux/sched.h> /* test_thread_flag(), ... */ #include <linux/kdebug.h> /* oops_begin/end, ... */ #include <linux/module.h> /* search_exception_table */ @@ -350,7 +349,7 @@ out: void vmalloc_sync_all(void) { - sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END); + sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END, 0); } /* @@ -649,7 +648,6 @@ no_context(struct pt_regs *regs, unsigned long error_code, unsigned long address, int signal, int si_code) { struct task_struct *tsk = current; - unsigned long *stackend; unsigned long flags; int sig; @@ -709,8 +707,7 @@ no_context(struct pt_regs *regs, unsigned long error_code, show_fault_oops(regs, error_code, address); - stackend = end_of_stack(tsk); - if (tsk != &init_task && *stackend != STACK_END_MAGIC) + if (task_stack_end_corrupted(tsk)) printk(KERN_EMERG "Thread overran stack, or stack corrupted\n"); tsk->thread.cr2 = address; @@ -933,8 +930,17 @@ static int spurious_fault_check(unsigned long error_code, pte_t *pte) * cross-processor TLB flush, even if no stale TLB entries exist * on other processors. * + * Spurious faults may only occur if the TLB contains an entry with + * fewer permission than the page table entry. Non-present (P = 0) + * and reserved bit (R = 1) faults are never spurious. + * * There are no security implications to leaving a stale TLB when * increasing the permissions on a page. + * + * Returns non-zero if a spurious fault was handled, zero otherwise. + * + * See Intel Developer's Manual Vol 3 Section 4.10.4.3, bullet 3 + * (Optional Invalidation). */ static noinline int spurious_fault(unsigned long error_code, unsigned long address) @@ -945,8 +951,17 @@ spurious_fault(unsigned long error_code, unsigned long address) pte_t *pte; int ret; - /* Reserved-bit violation or user access to kernel space? */ - if (error_code & (PF_USER | PF_RSVD)) + /* + * Only writes to RO or instruction fetches from NX may cause + * spurious faults. + * + * These could be from user or supervisor accesses but the TLB + * is only lazily flushed after a kernel mapping protection + * change, so user accesses are not expected to cause spurious + * faults. + */ + if (error_code != (PF_WRITE | PF_PROT) + && error_code != (PF_INSTR | PF_PROT)) return 0; pgd = init_mm.pgd + pgd_index(address); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 7d05565ba781..c8140e12816a 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -537,7 +537,7 @@ static void __init pagetable_init(void) permanent_kmaps_init(pgd_base); } -pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL | _PAGE_IOMAP); +pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL); EXPORT_SYMBOL_GPL(__supported_pte_mask); /* user-defined highmem size */ diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 5621c47d7a1a..4cb8763868fc 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -151,7 +151,7 @@ early_param("gbpages", parse_direct_gbpages_on); * around without checking the pgd every time. */ -pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP; +pteval_t __supported_pte_mask __read_mostly = ~0; EXPORT_SYMBOL_GPL(__supported_pte_mask); int force_personality32; @@ -178,7 +178,7 @@ __setup("noexec32=", nonx32_setup); * When memory was added/removed make sure all the processes MM have * suitable PGD entries in the local PGD level page. */ -void sync_global_pgds(unsigned long start, unsigned long end) +void sync_global_pgds(unsigned long start, unsigned long end, int removed) { unsigned long address; @@ -186,7 +186,12 @@ void sync_global_pgds(unsigned long start, unsigned long end) const pgd_t *pgd_ref = pgd_offset_k(address); struct page *page; - if (pgd_none(*pgd_ref)) + /* + * When it is called after memory hot remove, pgd_none() + * returns true. In this case (removed == 1), we must clear + * the PGD entries in the local PGD level page. + */ + if (pgd_none(*pgd_ref) && !removed) continue; spin_lock(&pgd_lock); @@ -199,12 +204,18 @@ void sync_global_pgds(unsigned long start, unsigned long end) pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); - if (pgd_none(*pgd)) - set_pgd(pgd, *pgd_ref); - else + if (!pgd_none(*pgd_ref) && !pgd_none(*pgd)) BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); + if (removed) { + if (pgd_none(*pgd_ref) && !pgd_none(*pgd)) + pgd_clear(pgd); + } else { + if (pgd_none(*pgd)) + set_pgd(pgd, *pgd_ref); + } + spin_unlock(pgt_lock); } spin_unlock(&pgd_lock); @@ -633,7 +644,7 @@ kernel_physical_mapping_init(unsigned long start, } if (pgd_changed) - sync_global_pgds(addr, end - 1); + sync_global_pgds(addr, end - 1, 0); __flush_tlb_all(); @@ -976,25 +987,26 @@ static void __meminit remove_pagetable(unsigned long start, unsigned long end, bool direct) { unsigned long next; + unsigned long addr; pgd_t *pgd; pud_t *pud; bool pgd_changed = false; - for (; start < end; start = next) { - next = pgd_addr_end(start, end); + for (addr = start; addr < end; addr = next) { + next = pgd_addr_end(addr, end); - pgd = pgd_offset_k(start); + pgd = pgd_offset_k(addr); if (!pgd_present(*pgd)) continue; pud = (pud_t *)pgd_page_vaddr(*pgd); - remove_pud_table(pud, start, next, direct); + remove_pud_table(pud, addr, next, direct); if (free_pud_table(pud, pgd)) pgd_changed = true; } if (pgd_changed) - sync_global_pgds(start, end - 1); + sync_global_pgds(start, end - 1, 1); flush_tlb_all(); } @@ -1341,7 +1353,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) else err = vmemmap_populate_basepages(start, end, node); if (!err) - sync_global_pgds(start, end - 1); + sync_global_pgds(start, end - 1, 0); return err; } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index baff1da354e0..af78e50ca6ce 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -86,6 +86,7 @@ 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; @@ -108,12 +109,23 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, /* * Don't allow anybody to remap normal RAM that we're using.. */ - 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) + /* 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); 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 */ diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c index dd89a13f1051..b4f2e7e9e907 100644 --- a/arch/x86/mm/kmemcheck/kmemcheck.c +++ b/arch/x86/mm/kmemcheck/kmemcheck.c @@ -140,7 +140,7 @@ static DEFINE_PER_CPU(struct kmemcheck_context, kmemcheck_context); bool kmemcheck_active(struct pt_regs *regs) { - struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context); + struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); return data->balance > 0; } @@ -148,7 +148,7 @@ bool kmemcheck_active(struct pt_regs *regs) /* Save an address that needs to be shown/hidden */ static void kmemcheck_save_addr(unsigned long addr) { - struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context); + struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); BUG_ON(data->n_addrs >= ARRAY_SIZE(data->addr)); data->addr[data->n_addrs++] = addr; @@ -156,7 +156,7 @@ static void kmemcheck_save_addr(unsigned long addr) static unsigned int kmemcheck_show_all(void) { - struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context); + struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); unsigned int i; unsigned int n; @@ -169,7 +169,7 @@ static unsigned int kmemcheck_show_all(void) static unsigned int kmemcheck_hide_all(void) { - struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context); + struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); unsigned int i; unsigned int n; @@ -185,7 +185,7 @@ static unsigned int kmemcheck_hide_all(void) */ void kmemcheck_show(struct pt_regs *regs) { - struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context); + struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); BUG_ON(!irqs_disabled()); @@ -226,7 +226,7 @@ void kmemcheck_show(struct pt_regs *regs) */ void kmemcheck_hide(struct pt_regs *regs) { - struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context); + struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); int n; BUG_ON(!irqs_disabled()); @@ -528,7 +528,7 @@ static void kmemcheck_access(struct pt_regs *regs, const uint8_t *insn_primary; unsigned int size; - struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context); + struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); /* Recursive fault -- ouch. */ if (data->busy) { diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index a32b706c401a..1a883705a12a 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -185,8 +185,8 @@ int __init numa_add_memblk(int nid, u64 start, u64 end) return numa_add_memblk_to(nid, start, end, &numa_meminfo); } -/* Initialize NODE_DATA for a node on the local memory */ -static void __init setup_node_data(int nid, u64 start, u64 end) +/* Allocate NODE_DATA for a node on the local memory */ +static void __init alloc_node_data(int nid) { const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE); u64 nd_pa; @@ -194,18 +194,6 @@ static void __init setup_node_data(int nid, u64 start, u64 end) int tnid; /* - * Don't confuse VM with a node that doesn't have the - * minimum amount of memory: - */ - if (end && (end - start) < NODE_MIN_SIZE) - return; - - start = roundup(start, ZONE_ALIGN); - - printk(KERN_INFO "Initmem setup node %d [mem %#010Lx-%#010Lx]\n", - nid, start, end - 1); - - /* * Allocate node data. Try node-local memory and then any node. * Never allocate in DMA zone. */ @@ -222,7 +210,7 @@ static void __init setup_node_data(int nid, u64 start, u64 end) nd = __va(nd_pa); /* report and initialize */ - printk(KERN_INFO " NODE_DATA [mem %#010Lx-%#010Lx]\n", + printk(KERN_INFO "NODE_DATA(%d) allocated [mem %#010Lx-%#010Lx]\n", nid, nd_pa, nd_pa + nd_size - 1); tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); if (tnid != nid) @@ -230,9 +218,6 @@ static void __init setup_node_data(int nid, u64 start, u64 end) node_data[nid] = nd; memset(NODE_DATA(nid), 0, sizeof(pg_data_t)); - NODE_DATA(nid)->node_id = nid; - NODE_DATA(nid)->node_start_pfn = start >> PAGE_SHIFT; - NODE_DATA(nid)->node_spanned_pages = (end - start) >> PAGE_SHIFT; node_set_online(nid); } @@ -478,6 +463,42 @@ static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi) return true; } +static void __init numa_clear_kernel_node_hotplug(void) +{ + int i, nid; + nodemask_t numa_kernel_nodes = NODE_MASK_NONE; + unsigned long start, end; + struct memblock_region *r; + + /* + * At this time, all memory regions reserved by memblock are + * used by the kernel. Set the nid in memblock.reserved will + * mark out all the nodes the kernel resides in. + */ + for (i = 0; i < numa_meminfo.nr_blks; i++) { + struct numa_memblk *mb = &numa_meminfo.blk[i]; + + memblock_set_node(mb->start, mb->end - mb->start, + &memblock.reserved, mb->nid); + } + + /* Mark all kernel nodes. */ + for_each_memblock(reserved, r) + node_set(r->nid, numa_kernel_nodes); + + /* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */ + for (i = 0; i < numa_meminfo.nr_blks; i++) { + nid = numa_meminfo.blk[i].nid; + if (!node_isset(nid, numa_kernel_nodes)) + continue; + + start = numa_meminfo.blk[i].start; + end = numa_meminfo.blk[i].end; + + memblock_clear_hotplug(start, end - start); + } +} + static int __init numa_register_memblks(struct numa_meminfo *mi) { unsigned long uninitialized_var(pfn_align); @@ -496,6 +517,15 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) } /* + * At very early time, the kernel have to use some memory such as + * loading the kernel image. We cannot prevent this anyway. So any + * node the kernel resides in should be un-hotpluggable. + * + * And when we come here, alloc node data won't fail. + */ + numa_clear_kernel_node_hotplug(); + + /* * If sections array is gonna be used for pfn -> nid mapping, check * whether its granularity is fine enough. */ @@ -523,8 +553,17 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) end = max(mi->blk[i].end, end); } - if (start < end) - setup_node_data(nid, start, end); + if (start >= end) + continue; + + /* + * Don't confuse VM with a node that doesn't have the + * minimum amount of memory: + */ + if (end && (end - start) < NODE_MIN_SIZE) + continue; + + alloc_node_data(nid); } /* Dump memblock with node info and return. */ @@ -554,41 +593,6 @@ static void __init numa_init_array(void) } } -static void __init numa_clear_kernel_node_hotplug(void) -{ - int i, nid; - nodemask_t numa_kernel_nodes = NODE_MASK_NONE; - unsigned long start, end; - struct memblock_region *r; - - /* - * At this time, all memory regions reserved by memblock are - * used by the kernel. Set the nid in memblock.reserved will - * mark out all the nodes the kernel resides in. - */ - for (i = 0; i < numa_meminfo.nr_blks; i++) { - struct numa_memblk *mb = &numa_meminfo.blk[i]; - memblock_set_node(mb->start, mb->end - mb->start, - &memblock.reserved, mb->nid); - } - - /* Mark all kernel nodes. */ - for_each_memblock(reserved, r) - node_set(r->nid, numa_kernel_nodes); - - /* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */ - for (i = 0; i < numa_meminfo.nr_blks; i++) { - nid = numa_meminfo.blk[i].nid; - if (!node_isset(nid, numa_kernel_nodes)) - continue; - - start = numa_meminfo.blk[i].start; - end = numa_meminfo.blk[i].end; - - memblock_clear_hotplug(start, end - start); - } -} - static int __init numa_init(int (*init_func)(void)) { int i; @@ -643,15 +647,6 @@ static int __init numa_init(int (*init_func)(void)) } numa_init_array(); - /* - * At very early time, the kernel have to use some memory such as - * loading the kernel image. We cannot prevent this anyway. So any - * node the kernel resides in should be un-hotpluggable. - * - * And when we come here, numa_init() won't fail. - */ - numa_clear_kernel_node_hotplug(); - return 0; } diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 4dd8cf652579..75cc0978d45d 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -59,41 +59,6 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval) __flush_tlb_one(vaddr); } -/* - * Associate a large virtual page frame with a given physical page frame - * and protection flags for that frame. pfn is for the base of the page, - * vaddr is what the page gets mapped to - both must be properly aligned. - * The pmd must already be instantiated. Assumes PAE mode. - */ -void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - - if (vaddr & (PMD_SIZE-1)) { /* vaddr is misaligned */ - printk(KERN_WARNING "set_pmd_pfn: vaddr misaligned\n"); - return; /* BUG(); */ - } - if (pfn & (PTRS_PER_PTE-1)) { /* pfn is misaligned */ - printk(KERN_WARNING "set_pmd_pfn: pfn misaligned\n"); - return; /* BUG(); */ - } - pgd = swapper_pg_dir + pgd_index(vaddr); - if (pgd_none(*pgd)) { - printk(KERN_WARNING "set_pmd_pfn: pgd_none\n"); - return; /* BUG(); */ - } - pud = pud_offset(pgd, vaddr); - pmd = pmd_offset(pud, vaddr); - set_pmd(pmd, pfn_pmd(pfn, flags)); - /* - * It's enough to flush this one mapping. - * (PGE mappings get flushed as well) - */ - __flush_tlb_one(vaddr); -} - unsigned long __FIXADDR_TOP = 0xfffff000; EXPORT_SYMBOL(__FIXADDR_TOP); |
