summaryrefslogtreecommitdiff
path: root/arch/x86/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/mm')
-rw-r--r--arch/x86/mm/dump_pagetables.c4
-rw-r--r--arch/x86/mm/fault.c32
-rw-r--r--arch/x86/mm/init_32.c5
-rw-r--r--arch/x86/mm/init_64.c41
-rw-r--r--arch/x86/mm/mmap.c2
-rw-r--r--arch/x86/mm/numa.c34
-rw-r--r--arch/x86/mm/pgtable_32.c35
-rw-r--r--arch/x86/mm/tlb.c10
8 files changed, 81 insertions, 82 deletions
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 167ffcac16ed..95a427e57887 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -48,7 +48,9 @@ enum address_markers_idx {
LOW_KERNEL_NR,
VMALLOC_START_NR,
VMEMMAP_START_NR,
+# ifdef CONFIG_X86_ESPFIX64
ESPFIX_START_NR,
+# endif
HIGH_KERNEL_NR,
MODULES_VADDR_NR,
MODULES_END_NR,
@@ -71,7 +73,9 @@ static struct addr_marker address_markers[] = {
{ PAGE_OFFSET, "Low Kernel Mapping" },
{ VMALLOC_START, "vmalloc() Area" },
{ VMEMMAP_START, "Vmemmap" },
+# ifdef CONFIG_X86_ESPFIX64
{ ESPFIX_BASE_ADDR, "ESPfix Area", 16 },
+# endif
{ __START_KERNEL_map, "High Kernel Mapping" },
{ MODULES_VADDR, "Modules" },
{ MODULES_END, "End Modules" },
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 1dbade870f90..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);
@@ -1218,7 +1233,8 @@ good_area:
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
- * the fault:
+ * the fault. Since we never set FAULT_FLAG_RETRY_NOWAIT, if
+ * we get VM_FAULT_RETRY back, the mmap_sem has been unlocked.
*/
fault = handle_mm_fault(mm, vma, address, flags);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index e39504878aec..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 */
@@ -825,7 +825,8 @@ void __init mem_init(void)
int arch_add_memory(int nid, u64 start, u64 size)
{
struct pglist_data *pgdata = NODE_DATA(nid);
- struct zone *zone = pgdata->node_zones + ZONE_HIGHMEM;
+ struct zone *zone = pgdata->node_zones +
+ zone_for_memory(nid, start, size, ZONE_HIGHMEM);
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index df1a9927ad29..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();
@@ -691,7 +702,8 @@ static void update_end_of_memory_vars(u64 start, u64 size)
int arch_add_memory(int nid, u64 start, u64 size)
{
struct pglist_data *pgdat = NODE_DATA(nid);
- struct zone *zone = pgdat->node_zones + ZONE_NORMAL;
+ struct zone *zone = pgdat->node_zones +
+ zone_for_memory(nid, start, size, ZONE_NORMAL);
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
int ret;
@@ -975,25 +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();
}
@@ -1340,7 +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/mmap.c b/arch/x86/mm/mmap.c
index 25e7e1372bb2..919b91205cd4 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -31,7 +31,7 @@
#include <linux/sched.h>
#include <asm/elf.h>
-struct __read_mostly va_alignment va_align = {
+struct va_alignment __read_mostly va_align = {
.flags = -1,
};
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index a32b706c401a..d221374d5ce8 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);
}
@@ -523,8 +508,17 @@ 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. */
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);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 1fe33987de02..ee61c36d64f8 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -49,7 +49,13 @@ void leave_mm(int cpu)
if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) {
cpumask_clear_cpu(cpu, mm_cpumask(active_mm));
load_cr3(swapper_pg_dir);
- trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+ /*
+ * This gets called in the idle path where RCU
+ * functions differently. Tracing normally
+ * uses RCU, so we have to call the tracepoint
+ * specially here.
+ */
+ trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
}
}
EXPORT_SYMBOL_GPL(leave_mm);
@@ -174,7 +180,7 @@ void flush_tlb_current_task(void)
*
* This is in units of pages.
*/
-unsigned long tlb_single_page_flush_ceiling = 33;
+static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
unsigned long end, unsigned long vmflag)