Merge branch 'x86/oprofile' into oprofile

9 files changed, 335 insertions, 102 deletions

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 1fbb844c3d7a..dfb932dcf136 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,5 +1,5 @@
 obj-y   :=  init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
-            pat.o pgtable.o
+            pat.o pgtable.o gup.o
 
 obj-$(CONFIG_X86_32)            += pgtable_32.o
 
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
new file mode 100644
index 000000000000..007bb06c7504
--- /dev/null
+++ b/arch/x86/mm/gup.c
@@ -0,0 +1,298 @@
+/*
+ * Lockless get_user_pages_fast for x86
+ *
+ * Copyright (C) 2008 Nick Piggin
+ * Copyright (C) 2008 Novell Inc.
+ */
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/vmstat.h>
+#include <linux/highmem.h>
+
+#include <asm/pgtable.h>
+
+static inline pte_t gup_get_pte(pte_t *ptep)
+{
+#ifndef CONFIG_X86_PAE
+        return *ptep;
+#else
+        /*
+         * With get_user_pages_fast, we walk down the pagetables without taking
+         * any locks.  For this we would like to load the pointers atoimcally,
+         * but that is not possible (without expensive cmpxchg8b) on PAE.  What
+         * we do have is the guarantee that a pte will only either go from not
+         * present to present, or present to not present or both -- it will not
+         * switch to a completely different present page without a TLB flush in
+         * between; something that we are blocking by holding interrupts off.
+         *
+         * Setting ptes from not present to present goes:
+         * ptep->pte_high = h;
+         * smp_wmb();
+         * ptep->pte_low = l;
+         *
+         * And present to not present goes:
+         * ptep->pte_low = 0;
+         * smp_wmb();
+         * ptep->pte_high = 0;
+         *
+         * We must ensure here that the load of pte_low sees l iff pte_high
+         * sees h. We load pte_high *after* loading pte_low, which ensures we
+         * don't see an older value of pte_high.  *Then* we recheck pte_low,
+         * which ensures that we haven't picked up a changed pte high. We might
+         * have got rubbish values from pte_low and pte_high, but we are
+         * guaranteed that pte_low will not have the present bit set *unless*
+         * it is 'l'. And get_user_pages_fast only operates on present ptes, so
+         * we're safe.
+         *
+         * gup_get_pte should not be used or copied outside gup.c without being
+         * very careful -- it does not atomically load the pte or anything that
+         * is likely to be useful for you.
+         */
+        pte_t pte;
+
+retry:
+        pte.pte_low = ptep->pte_low;
+        smp_rmb();
+        pte.pte_high = ptep->pte_high;
+        smp_rmb();
+        if (unlikely(pte.pte_low != ptep->pte_low))
+                goto retry;
+
+        return pte;
+#endif
+}
+
+/*
+ * The performance critical leaf functions are made noinline otherwise gcc
+ * inlines everything into a single function which results in too much
+ * register pressure.
+ */
+static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
+                unsigned long end, int write, struct page **pages, int *nr)
+{
+        unsigned long mask;
+        pte_t *ptep;
+
+        mask = _PAGE_PRESENT|_PAGE_USER;
+        if (write)
+                mask |= _PAGE_RW;
+
+        ptep = pte_offset_map(&pmd, addr);
+        do {
+                pte_t pte = gup_get_pte(ptep);
+                struct page *page;
+
+                if ((pte_val(pte) & (mask | _PAGE_SPECIAL)) != mask) {
+                        pte_unmap(ptep);
+                        return 0;
+                }
+                VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+                page = pte_page(pte);
+                get_page(page);
+                pages[*nr] = page;
+                (*nr)++;
+
+        } while (ptep++, addr += PAGE_SIZE, addr != end);
+        pte_unmap(ptep - 1);
+
+        return 1;
+}
+
+static inline void get_head_page_multiple(struct page *page, int nr)
+{
+        VM_BUG_ON(page != compound_head(page));
+        VM_BUG_ON(page_count(page) == 0);
+        atomic_add(nr, &page->_count);
+}
+
+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_val(pte) & mask) != mask)
+                return 0;
+        /* hugepages are never "special" */
+        VM_BUG_ON(pte_val(pte) & _PAGE_SPECIAL);
+        VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+        refs = 0;
+        head = pte_page(pte);
+        page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+        do {
+                VM_BUG_ON(compound_head(page) != head);
+                pages[*nr] = page;
+                (*nr)++;
+                page++;
+                refs++;
+        } while (addr += PAGE_SIZE, addr != end);
+        get_head_page_multiple(head, refs);
+
+        return 1;
+}
+
+static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
+                int write, struct page **pages, int *nr)
+{
+        unsigned long next;
+        pmd_t *pmdp;
+
+        pmdp = pmd_offset(&pud, addr);
+        do {
+                pmd_t pmd = *pmdp;
+
+                next = pmd_addr_end(addr, end);
+                if (pmd_none(pmd))
+                        return 0;
+                if (unlikely(pmd_large(pmd))) {
+                        if (!gup_huge_pmd(pmd, addr, next, write, pages, nr))
+                                return 0;
+                } else {
+                        if (!gup_pte_range(pmd, addr, next, write, pages, nr))
+                                return 0;
+                }
+        } while (pmdp++, addr = next, addr != end);
+
+        return 1;
+}
+
+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_val(pte) & mask) != mask)
+                return 0;
+        /* hugepages are never "special" */
+        VM_BUG_ON(pte_val(pte) & _PAGE_SPECIAL);
+        VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+        refs = 0;
+        head = pte_page(pte);
+        page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+        do {
+                VM_BUG_ON(compound_head(page) != head);
+                pages[*nr] = page;
+                (*nr)++;
+                page++;
+                refs++;
+        } while (addr += PAGE_SIZE, addr != end);
+        get_head_page_multiple(head, refs);
+
+        return 1;
+}
+
+static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
+                        int write, struct page **pages, int *nr)
+{
+        unsigned long next;
+        pud_t *pudp;
+
+        pudp = pud_offset(&pgd, addr);
+        do {
+                pud_t pud = *pudp;
+
+                next = pud_addr_end(addr, end);
+                if (pud_none(pud))
+                        return 0;
+                if (unlikely(pud_large(pud))) {
+                        if (!gup_huge_pud(pud, addr, next, write, pages, nr))
+                                return 0;
+                } else {
+                        if (!gup_pmd_range(pud, addr, next, write, pages, nr))
+                                return 0;
+                }
+        } while (pudp++, addr = next, addr != end);
+
+        return 1;
+}
+
+int get_user_pages_fast(unsigned long start, int nr_pages, int write,
+                        struct page **pages)
+{
+        struct mm_struct *mm = current->mm;
+        unsigned long addr, len, end;
+        unsigned long next;
+        pgd_t *pgdp;
+        int nr = 0;
+
+        start &= PAGE_MASK;
+        addr = start;
+        len = (unsigned long) nr_pages << PAGE_SHIFT;
+        end = start + len;
+        if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
+                                        start, len)))
+                goto slow_irqon;
+
+        /*
+         * XXX: batch / limit 'nr', to avoid large irq off latency
+         * needs some instrumenting to determine the common sizes used by
+         * important workloads (eg. DB2), and whether limiting the batch size
+         * will decrease performance.
+         *
+         * It seems like we're in the clear for the moment. Direct-IO is
+         * the main guy that batches up lots of get_user_pages, and even
+         * they are limited to 64-at-a-time which is not so many.
+         */
+        /*
+         * This doesn't prevent pagetable teardown, but does prevent
+         * the pagetables and pages from being freed on x86.
+         *
+         * So long as we atomically load page table pointers versus teardown
+         * (which we do on x86, with the above PAE exception), we can follow the
+         * address down to the the page and take a ref on it.
+         */
+        local_irq_disable();
+        pgdp = pgd_offset(mm, addr);
+        do {
+                pgd_t pgd = *pgdp;
+
+                next = pgd_addr_end(addr, end);
+                if (pgd_none(pgd))
+                        goto slow;
+                if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+                        goto slow;
+        } while (pgdp++, addr = next, addr != end);
+        local_irq_enable();
+
+        VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT);
+        return nr;
+
+        {
+                int ret;
+
+slow:
+                local_irq_enable();
+slow_irqon:
+                /* Try to get the remaining pages with get_user_pages */
+                start += nr << PAGE_SHIFT;
+                pages += nr;
+
+                down_read(&mm->mmap_sem);
+                ret = get_user_pages(current, mm, start,
+                        (end - start) >> PAGE_SHIFT, write, 0, pages, NULL);
+                up_read(&mm->mmap_sem);
+
+                /* Have to be a bit careful with return values */
+                if (nr > 0) {
+                        if (ret < 0)
+                                ret = nr;
+                        else
+                                ret += nr;
+                }
+
+                return ret;
+        }
+}
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index ec37121f6709..a87ea0e4b3dc 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -60,7 +60,7 @@ static unsigned long dma_reserve __initdata;
 
 DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 
-int direct_gbpages __meminitdata
+int direct_gbpages
 #ifdef CONFIG_DIRECT_GBPAGES
                                 = 1
 #endif
@@ -86,46 +86,13 @@ early_param("gbpages", parse_direct_gbpages_on);
  * around without checking the pgd every time.
  */
 
-void show_mem(void)
-{
-        long i, total = 0, reserved = 0;
-        long shared = 0, cached = 0;
-        struct page *page;
-        pg_data_t *pgdat;
-
-        printk(KERN_INFO "Mem-info:\n");
-        show_free_areas();
-        for_each_online_pgdat(pgdat) {
-                for (i = 0; i < pgdat->node_spanned_pages; ++i) {
-                        /*
-                         * This loop can take a while with 256 GB and
-                         * 4k pages so defer the NMI watchdog:
-                         */
-                        if (unlikely(i % MAX_ORDER_NR_PAGES == 0))
-                                touch_nmi_watchdog();
-
-                        if (!pfn_valid(pgdat->node_start_pfn + i))
-                                continue;
-
-                        page = pfn_to_page(pgdat->node_start_pfn + i);
-                        total++;
-                        if (PageReserved(page))
-                                reserved++;
-                        else if (PageSwapCache(page))
-                                cached++;
-                        else if (page_count(page))
-                                shared += page_count(page) - 1;
-                }
-        }
-        printk(KERN_INFO "%lu pages of RAM\n",          total);
-        printk(KERN_INFO "%lu reserved pages\n",        reserved);
-        printk(KERN_INFO "%lu pages shared\n",          shared);
-        printk(KERN_INFO "%lu pages swap cached\n",     cached);
-}
-
 int after_bootmem;
 
-static __init void *spp_getpage(void)
+/*
+ * NOTE: This function is marked __ref because it calls __init function
+ * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
+ */
+static __ref void *spp_getpage(void)
 {
         void *ptr;
 
@@ -351,6 +318,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
 {
         unsigned long pages = 0;
         unsigned long last_map_addr = end;
+        unsigned long start = address;
 
         int i = pmd_index(address);
 
@@ -371,6 +339,9 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
                         if (!pmd_large(*pmd))
                                 last_map_addr = phys_pte_update(pmd, address,
                                                                  end);
+                        /* Count entries we're using from level2_ident_pgt */
+                        if (start == 0)
+                                pages++;
                         continue;
                 }
 
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 016f335bbeea..6ba6f889c79d 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -170,7 +170,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
         phys_addr &= PAGE_MASK;
         size = PAGE_ALIGN(last_addr+1) - phys_addr;
 
-        retval = reserve_memtype(phys_addr, phys_addr + size,
+        retval = reserve_memtype(phys_addr, (u64)phys_addr + size,
                                                 prot_val, &new_prot_val);
         if (retval) {
                 pr_debug("Warning: reserve_memtype returned %d\n", retval);
diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c
index 0dcd42eb94e6..d4aa503caaa2 100644
--- a/arch/x86/mm/pageattr-test.c
+++ b/arch/x86/mm/pageattr-test.c
@@ -221,8 +221,7 @@ static int pageattr_test(void)
         failed += print_split(&sc);
 
         if (failed) {
-                printk(KERN_ERR "NOT PASSED. Please report.\n");
-                WARN_ON(1);
+                WARN(1, KERN_ERR "NOT PASSED. Please report.\n");
                 return -EINVAL;
         } else {
                 if (print)
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 65c6e46bf059..f5f5154ea11e 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -55,13 +55,19 @@ static void split_page_count(int level)
 
 int arch_report_meminfo(char *page)
 {
-        int n = sprintf(page, "DirectMap4k:  %8lu\n"
-                        "DirectMap2M:  %8lu\n",
-                        direct_pages_count[PG_LEVEL_4K],
-                        direct_pages_count[PG_LEVEL_2M]);
+        int n = sprintf(page, "DirectMap4k:  %8lu kB\n",
+                        direct_pages_count[PG_LEVEL_4K] << 2);
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
+        n += sprintf(page + n, "DirectMap2M:  %8lu kB\n",
+                        direct_pages_count[PG_LEVEL_2M] << 11);
+#else
+        n += sprintf(page + n, "DirectMap4M:  %8lu kB\n",
+                        direct_pages_count[PG_LEVEL_2M] << 12);
+#endif
 #ifdef CONFIG_X86_64
-        n += sprintf(page + n, "DirectMap1G:  %8lu\n",
-                     direct_pages_count[PG_LEVEL_1G]);
+        if (direct_gbpages)
+                n += sprintf(page + n, "DirectMap1G:  %8lu kB\n",
+                        direct_pages_count[PG_LEVEL_1G] << 20);
 #endif
         return n;
 }
@@ -592,10 +598,9 @@ repeat:
         if (!pte_val(old_pte)) {
                 if (!primary)
                         return 0;
-                printk(KERN_WARNING "CPA: called for zero pte. "
+                WARN(1, KERN_WARNING "CPA: called for zero pte. "
                        "vaddr = %lx cpa->vaddr = %lx\n", address,
                        cpa->vaddr);
-                WARN_ON(1);
                 return -EINVAL;
         }
 
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 557b2abceef8..d50302774fe2 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -207,6 +207,9 @@ static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
         unsigned long addr;
         int i;
 
+        if (PREALLOCATED_PMDS == 0) /* Work around gcc-3.4.x bug */
+                return;
+
         pud = pud_offset(pgd, 0);
 
         for (addr = i = 0; i < PREALLOCATED_PMDS;
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index b4becbf8c570..cab0abbd1ebe 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -20,53 +20,6 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 
-void show_mem(void)
-{
-        int total = 0, reserved = 0;
-        int shared = 0, cached = 0;
-        int highmem = 0;
-        struct page *page;
-        pg_data_t *pgdat;
-        unsigned long i;
-        unsigned long flags;
-
-        printk(KERN_INFO "Mem-info:\n");
-        show_free_areas();
-        for_each_online_pgdat(pgdat) {
-                pgdat_resize_lock(pgdat, &flags);
-                for (i = 0; i < pgdat->node_spanned_pages; ++i) {
-                        if (unlikely(i % MAX_ORDER_NR_PAGES == 0))
-                                touch_nmi_watchdog();
-                        page = pgdat_page_nr(pgdat, i);
-                        total++;
-                        if (PageHighMem(page))
-                                highmem++;
-                        if (PageReserved(page))
-                                reserved++;
-                        else if (PageSwapCache(page))
-                                cached++;
-                        else if (page_count(page))
-                                shared += page_count(page) - 1;
-                }
-                pgdat_resize_unlock(pgdat, &flags);
-        }
-        printk(KERN_INFO "%d pages of RAM\n", total);
-        printk(KERN_INFO "%d pages of HIGHMEM\n", highmem);
-        printk(KERN_INFO "%d reserved pages\n", reserved);
-        printk(KERN_INFO "%d pages shared\n", shared);
-        printk(KERN_INFO "%d pages swap cached\n", cached);
-
-        printk(KERN_INFO "%lu pages dirty\n", global_page_state(NR_FILE_DIRTY));
-        printk(KERN_INFO "%lu pages writeback\n",
-                                        global_page_state(NR_WRITEBACK));
-        printk(KERN_INFO "%lu pages mapped\n", global_page_state(NR_FILE_MAPPED));
-        printk(KERN_INFO "%lu pages slab\n",
-                global_page_state(NR_SLAB_RECLAIMABLE) +
-                global_page_state(NR_SLAB_UNRECLAIMABLE));
-        printk(KERN_INFO "%lu pages pagetables\n",
-                                        global_page_state(NR_PAGETABLE));
-}
-
 /*
  * Associate a virtual page frame with a given physical page frame 
  * and protection flags for that frame.
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 1eb2973a301c..16ae70fc57e7 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -178,7 +178,7 @@ void acpi_numa_arch_fixup(void)
  * start of the node, and that the current "end" address is after
  * the previous one.
  */
-static __init void node_read_chunk(int nid, struct node_memory_chunk_s *memory_chunk)
+static __init int node_read_chunk(int nid, struct node_memory_chunk_s *memory_chunk)
 {
         /*
          * Only add present memory as told by the e820.
@@ -189,10 +189,10 @@ static __init void node_read_chunk(int nid, struct node_memory_chunk_s *memory_c
         if (memory_chunk->start_pfn >= max_pfn) {
                 printk(KERN_INFO "Ignoring SRAT pfns: %08lx - %08lx\n",
                         memory_chunk->start_pfn, memory_chunk->end_pfn);
-                return;
+                return -1;
         }
         if (memory_chunk->nid != nid)
-                return;
+                return -1;
 
         if (!node_has_online_mem(nid))
                 node_start_pfn[nid] = memory_chunk->start_pfn;
@@ -202,6 +202,8 @@ static __init void node_read_chunk(int nid, struct node_memory_chunk_s *memory_c
 
         if (node_end_pfn[nid] < memory_chunk->end_pfn)
                 node_end_pfn[nid] = memory_chunk->end_pfn;
+
+        return 0;
 }
 
 int __init get_memcfg_from_srat(void)
@@ -259,7 +261,9 @@ int __init get_memcfg_from_srat(void)
                 printk(KERN_DEBUG
                         "chunk %d nid %d start_pfn %08lx end_pfn %08lx\n",
                        j, chunk->nid, chunk->start_pfn, chunk->end_pfn);
-                node_read_chunk(chunk->nid, chunk);
+                if (node_read_chunk(chunk->nid, chunk))
+                        continue;
+
                 e820_register_active_regions(chunk->nid, chunk->start_pfn,
                                              min(chunk->end_pfn, max_pfn));
         }