10 files changed, 159 insertions, 195 deletions

diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index d406c5239019..e71c5cbc8f35 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -266,16 +266,9 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
         if (!after_bootmem)
                 find_early_table_space(end, use_pse, use_gbpages);
 
-#ifdef CONFIG_X86_32
-        for (i = 0; i < nr_range; i++)
-                kernel_physical_mapping_init(mr[i].start, mr[i].end,
-                                             mr[i].page_size_mask);
-        ret = end;
-#else /* CONFIG_X86_64 */
         for (i = 0; i < nr_range; i++)
                 ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
                                                    mr[i].page_size_mask);
-#endif
 
 #ifdef CONFIG_X86_32
         early_ioremap_page_table_range_init();
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 9a0c258a86be..2226f2c70ea3 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -241,6 +241,7 @@ kernel_physical_mapping_init(unsigned long start,
                              unsigned long page_size_mask)
 {
         int use_pse = page_size_mask == (1<<PG_LEVEL_2M);
+        unsigned long last_map_addr = end;
         unsigned long start_pfn, end_pfn;
         pgd_t *pgd_base = swapper_pg_dir;
         int pgd_idx, pmd_idx, pte_ofs;
@@ -341,9 +342,10 @@ repeat:
                                         prot = PAGE_KERNEL_EXEC;
 
                                 pages_4k++;
-                                if (mapping_iter == 1)
+                                if (mapping_iter == 1) {
                                         set_pte(pte, pfn_pte(pfn, init_prot));
-                                else
+                                        last_map_addr = (pfn << PAGE_SHIFT) + PAGE_SIZE;
+                                } else
                                         set_pte(pte, pfn_pte(pfn, prot));
                         }
                 }
@@ -368,7 +370,7 @@ repeat:
                 mapping_iter = 2;
                 goto repeat;
         }
-        return 0;
+        return last_map_addr;
 }
 
 pte_t *kmap_pte;
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index c246d259822d..5eb1ba74a3a9 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -24,43 +24,6 @@
 
 #include "physaddr.h"
 
-int page_is_ram(unsigned long pagenr)
-{
-        resource_size_t addr, end;
-        int i;
-
-        /*
-         * A special case is the first 4Kb of memory;
-         * This is a BIOS owned area, not kernel ram, but generally
-         * not listed as such in the E820 table.
-         */
-        if (pagenr == 0)
-                return 0;
-
-        /*
-         * Second special case: Some BIOSen report the PC BIOS
-         * area (640->1Mb) as ram even though it is not.
-         */
-        if (pagenr >= (BIOS_BEGIN >> PAGE_SHIFT) &&
-                    pagenr < (BIOS_END >> PAGE_SHIFT))
-                return 0;
-
-        for (i = 0; i < e820.nr_map; i++) {
-                /*
-                 * Not usable memory:
-                 */
-                if (e820.map[i].type != E820_RAM)
-                        continue;
-                addr = (e820.map[i].addr + PAGE_SIZE-1) >> PAGE_SHIFT;
-                end = (e820.map[i].addr + e820.map[i].size) >> PAGE_SHIFT;
-
-
-                if ((pagenr >= addr) && (pagenr < end))
-                        return 1;
-        }
-        return 0;
-}
-
 /*
  * Fix up the linear direct mapping of the kernel to avoid cache attribute
  * conflicts.
@@ -422,6 +385,10 @@ void __init early_ioremap_init(void)
          * The boot-ioremap range spans multiple pmds, for which
          * we are not prepared:
          */
+#define __FIXADDR_TOP (-PAGE_SIZE)
+        BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
+                     != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));
+#undef __FIXADDR_TOP
         if (pmd != early_ioremap_pmd(fix_to_virt(FIX_BTMAP_END))) {
                 WARN_ON(1);
                 printk(KERN_WARNING "pmd %p != %p\n",
diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c
index 8cc183344140..b3b531a4f8e5 100644
--- a/arch/x86/mm/kmemcheck/kmemcheck.c
+++ b/arch/x86/mm/kmemcheck/kmemcheck.c
@@ -337,7 +337,7 @@ bool kmemcheck_is_obj_initialized(unsigned long addr, size_t size)
         if (!shadow)
                 return true;
 
-        status = kmemcheck_shadow_test(shadow, size);
+        status = kmemcheck_shadow_test_all(shadow, size);
 
         return status == KMEMCHECK_SHADOW_INITIALIZED;
 }
diff --git a/arch/x86/mm/kmemcheck/shadow.c b/arch/x86/mm/kmemcheck/shadow.c
index 3f66b82076a3..aec124214d97 100644
--- a/arch/x86/mm/kmemcheck/shadow.c
+++ b/arch/x86/mm/kmemcheck/shadow.c
@@ -125,12 +125,12 @@ void kmemcheck_mark_initialized_pages(struct page *p, unsigned int n)
 
 enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size)
 {
+#ifdef CONFIG_KMEMCHECK_PARTIAL_OK
         uint8_t *x;
         unsigned int i;
 
         x = shadow;
 
-#ifdef CONFIG_KMEMCHECK_PARTIAL_OK
         /*
          * Make sure _some_ bytes are initialized. Gcc frequently generates
          * code to access neighboring bytes.
@@ -139,13 +139,25 @@ enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size)
                 if (x[i] == KMEMCHECK_SHADOW_INITIALIZED)
                         return x[i];
         }
+
+        return x[0];
 #else
+        return kmemcheck_shadow_test_all(shadow, size);
+#endif
+}
+
+enum kmemcheck_shadow kmemcheck_shadow_test_all(void *shadow, unsigned int size)
+{
+        uint8_t *x;
+        unsigned int i;
+
+        x = shadow;
+
         /* All bytes must be initialized. */
         for (i = 0; i < size; ++i) {
                 if (x[i] != KMEMCHECK_SHADOW_INITIALIZED)
                         return x[i];
         }
-#endif
 
         return x[0];
 }
diff --git a/arch/x86/mm/kmemcheck/shadow.h b/arch/x86/mm/kmemcheck/shadow.h
index af46d9ab9d86..ff0b2f70fbcb 100644
--- a/arch/x86/mm/kmemcheck/shadow.h
+++ b/arch/x86/mm/kmemcheck/shadow.h
@@ -11,6 +11,8 @@ enum kmemcheck_shadow {
 void *kmemcheck_shadow_lookup(unsigned long address);
 
 enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size);
+enum kmemcheck_shadow kmemcheck_shadow_test_all(void *shadow,
+                                                unsigned int size);
 void kmemcheck_shadow_set(void *shadow, unsigned int size);
 
 #endif
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index c8191defc38a..1dab5194fd9d 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -71,7 +71,7 @@ static int mmap_is_legacy(void)
         if (current->personality & ADDR_COMPAT_LAYOUT)
                 return 1;
 
-        if (current->signal->rlim[RLIMIT_STACK].rlim_cur == RLIM_INFINITY)
+        if (rlimit(RLIMIT_STACK) == RLIM_INFINITY)
                 return 1;
 
         return sysctl_legacy_va_layout;
@@ -96,7 +96,7 @@ static unsigned long mmap_rnd(void)
 
 static unsigned long mmap_base(void)
 {
-        unsigned long gap = current->signal->rlim[RLIMIT_STACK].rlim_cur;
+        unsigned long gap = rlimit(RLIMIT_STACK);
 
         if (gap < MIN_GAP)
                 gap = MIN_GAP;
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 83bbc70d11bb..3307ea8bd43a 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -427,7 +427,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
          * Calculate the number of big nodes that can be allocated as a result
          * of consolidating the remainder.
          */
-        big = ((size & ~FAKE_NODE_MIN_HASH_MASK) & nr_nodes) /
+        big = ((size & ~FAKE_NODE_MIN_HASH_MASK) * nr_nodes) /
                 FAKE_NODE_MIN_SIZE;
 
         size &= FAKE_NODE_MIN_HASH_MASK;
@@ -502,77 +502,99 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 }
 
 /*
- * Splits num_nodes nodes up equally starting at node_start.  The return value
- * is the number of nodes split up and addr is adjusted to be at the end of the
- * last node allocated.
+ * Returns the end address of a node so that there is at least `size' amount of
+ * non-reserved memory or `max_addr' is reached.
  */
-static int __init split_nodes_equally(u64 *addr, u64 max_addr, int node_start,
-                                      int num_nodes)
+static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size)
 {
-        unsigned int big;
-        u64 size;
-        int i;
-
-        if (num_nodes <= 0)
-                return -1;
-        if (num_nodes > MAX_NUMNODES)
-                num_nodes = MAX_NUMNODES;
-        size = (max_addr - *addr - e820_hole_size(*addr, max_addr)) /
-               num_nodes;
-        /*
-         * Calculate the number of big nodes that can be allocated as a result
-         * of consolidating the leftovers.
-         */
-        big = ((size & ~FAKE_NODE_MIN_HASH_MASK) * num_nodes) /
-              FAKE_NODE_MIN_SIZE;
-
-        /* Round down to nearest FAKE_NODE_MIN_SIZE. */
-        size &= FAKE_NODE_MIN_HASH_MASK;
-        if (!size) {
-                printk(KERN_ERR "Not enough memory for each node.  "
-                       "NUMA emulation disabled.\n");
-                return -1;
-        }
-
-        for (i = node_start; i < num_nodes + node_start; i++) {
-                u64 end = *addr + size;
+        u64 end = start + size;
 
-                if (i < big)
-                        end += FAKE_NODE_MIN_SIZE;
-                /*
-                 * The final node can have the remaining system RAM.  Other
-                 * nodes receive roughly the same amount of available pages.
-                 */
-                if (i == num_nodes + node_start - 1)
+        while (end - start - e820_hole_size(start, end) < size) {
+                end += FAKE_NODE_MIN_SIZE;
+                if (end > max_addr) {
                         end = max_addr;
-                else
-                        while (end - *addr - e820_hole_size(*addr, end) <
-                               size) {
-                                end += FAKE_NODE_MIN_SIZE;
-                                if (end > max_addr) {
-                                        end = max_addr;
-                                        break;
-                                }
-                        }
-                if (setup_node_range(i, addr, end - *addr, max_addr) < 0)
                         break;
+                }
         }
-        return i - node_start + 1;
+        return end;
 }
 
 /*
- * Splits the remaining system RAM into chunks of size.  The remaining memory is
- * always assigned to a final node and can be asymmetric.  Returns the number of
- * nodes split.
+ * Sets up fake nodes of `size' interleaved over physical nodes ranging from
+ * `addr' to `max_addr'.  The return value is the number of nodes allocated.
  */
-static int __init split_nodes_by_size(u64 *addr, u64 max_addr, int node_start,
-                                      u64 size)
+static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
 {
-        int i = node_start;
-        size = (size << 20) & FAKE_NODE_MIN_HASH_MASK;
-        while (!setup_node_range(i++, addr, size, max_addr))
-                ;
-        return i - node_start;
+        nodemask_t physnode_mask = NODE_MASK_NONE;
+        u64 min_size;
+        int ret = 0;
+        int i;
+
+        if (!size)
+                return -1;
+        /*
+         * The limit on emulated nodes is MAX_NUMNODES, so the size per node is
+         * increased accordingly if the requested size is too small.  This
+         * creates a uniform distribution of node sizes across the entire
+         * machine (but not necessarily over physical nodes).
+         */
+        min_size = (max_addr - addr - e820_hole_size(addr, max_addr)) /
+                                                MAX_NUMNODES;
+        min_size = max(min_size, FAKE_NODE_MIN_SIZE);
+        if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size)
+                min_size = (min_size + FAKE_NODE_MIN_SIZE) &
+                                                FAKE_NODE_MIN_HASH_MASK;
+        if (size < min_size) {
+                pr_err("Fake node size %LuMB too small, increasing to %LuMB\n",
+                        size >> 20, min_size >> 20);
+                size = min_size;
+        }
+        size &= FAKE_NODE_MIN_HASH_MASK;
+
+        for (i = 0; i < MAX_NUMNODES; i++)
+                if (physnodes[i].start != physnodes[i].end)
+                        node_set(i, physnode_mask);
+        /*
+         * Fill physical nodes with fake nodes of size until there is no memory
+         * left on any of them.
+         */
+        while (nodes_weight(physnode_mask)) {
+                for_each_node_mask(i, physnode_mask) {
+                        u64 dma32_end = MAX_DMA32_PFN << PAGE_SHIFT;
+                        u64 end;
+
+                        end = find_end_of_node(physnodes[i].start,
+                                                physnodes[i].end, size);
+                        /*
+                         * If there won't be at least FAKE_NODE_MIN_SIZE of
+                         * non-reserved memory in ZONE_DMA32 for the next node,
+                         * this one must extend to the boundary.
+                         */
+                        if (end < dma32_end && dma32_end - end -
+                            e820_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+                                end = dma32_end;
+
+                        /*
+                         * If there won't be enough non-reserved memory for the
+                         * next node, this one must extend to the end of the
+                         * physical node.
+                         */
+                        if (physnodes[i].end - end -
+                            e820_hole_size(end, physnodes[i].end) < size)
+                                end = physnodes[i].end;
+
+                        /*
+                         * Setup the fake node that will be allocated as bootmem
+                         * later.  If setup_node_range() returns non-zero, there
+                         * is no more memory available on this physical node.
+                         */
+                        if (setup_node_range(ret++, &physnodes[i].start,
+                                                end - physnodes[i].start,
+                                                physnodes[i].end) < 0)
+                                node_clear(i, physnode_mask);
+                }
+        }
+        return ret;
 }
 
 /*
@@ -582,87 +604,32 @@ static int __init split_nodes_by_size(u64 *addr, u64 max_addr, int node_start,
 static int __init numa_emulation(unsigned long start_pfn,
                         unsigned long last_pfn, int acpi, int k8)
 {
-        u64 size, addr = start_pfn << PAGE_SHIFT;
+        u64 addr = start_pfn << PAGE_SHIFT;
         u64 max_addr = last_pfn << PAGE_SHIFT;
-        int num_nodes = 0, num = 0, coeff_flag, coeff = -1, i;
         int num_phys_nodes;
+        int num_nodes;
+        int i;
 
         num_phys_nodes = setup_physnodes(addr, max_addr, acpi, k8);
         /*
-         * If the numa=fake command-line is just a single number N, split the
-         * system RAM into N fake nodes.
+         * If the numa=fake command-line contains a 'M' or 'G', it represents
+         * the fixed node size.  Otherwise, if it is just a single number N,
+         * split the system RAM into N fake nodes.
          */
-        if (!strchr(cmdline, '*') && !strchr(cmdline, ',')) {
-                long n = simple_strtol(cmdline, NULL, 0);
-
-                num_nodes = split_nodes_interleave(addr, max_addr,
-                                                        num_phys_nodes, n);
-                if (num_nodes < 0)
-                        return num_nodes;
-                goto out;
-        }
+        if (strchr(cmdline, 'M') || strchr(cmdline, 'G')) {
+                u64 size;
 
-        /* Parse the command line. */
-        for (coeff_flag = 0; ; cmdline++) {
-                if (*cmdline && isdigit(*cmdline)) {
-                        num = num * 10 + *cmdline - '0';
-                        continue;
-                }
-                if (*cmdline == '*') {
-                        if (num > 0)
-                                coeff = num;
-                        coeff_flag = 1;
-                }
-                if (!*cmdline || *cmdline == ',') {
-                        if (!coeff_flag)
-                                coeff = 1;
-                        /*
-                         * Round down to the nearest FAKE_NODE_MIN_SIZE.
-                         * Command-line coefficients are in megabytes.
-                         */
-                        size = ((u64)num << 20) & FAKE_NODE_MIN_HASH_MASK;
-                        if (size)
-                                for (i = 0; i < coeff; i++, num_nodes++)
-                                        if (setup_node_range(num_nodes, &addr,
-                                                size, max_addr) < 0)
-                                                goto done;
-                        if (!*cmdline)
-                                break;
-                        coeff_flag = 0;
-                        coeff = -1;
-                }
-                num = 0;
-        }
-done:
-        if (!num_nodes)
-                return -1;
-        /* Fill remainder of system RAM, if appropriate. */
-        if (addr < max_addr) {
-                if (coeff_flag && coeff < 0) {
-                        /* Split remaining nodes into num-sized chunks */
-                        num_nodes += split_nodes_by_size(&addr, max_addr,
-                                                         num_nodes, num);
-                        goto out;
-                }
-                switch (*(cmdline - 1)) {
-                case '*':
-                        /* Split remaining nodes into coeff chunks */
-                        if (coeff <= 0)
-                                break;
-                        num_nodes += split_nodes_equally(&addr, max_addr,
-                                                         num_nodes, coeff);
-                        break;
-                case ',':
-                        /* Do not allocate remaining system RAM */
-                        break;
-                default:
-                        /* Give one final node */
-                        setup_node_range(num_nodes, &addr, max_addr - addr,
-                                         max_addr);
-                        num_nodes++;
-                }
+                size = memparse(cmdline, &cmdline);
+                num_nodes = split_nodes_size_interleave(addr, max_addr, size);
+        } else {
+                unsigned long n;
+
+                n = simple_strtoul(cmdline, NULL, 0);
+                num_nodes = split_nodes_interleave(addr, max_addr, num_phys_nodes, n);
         }
-out:
+
+        if (num_nodes < 0)
+                return num_nodes;
         memnode_shift = compute_hash_shift(nodes, num_nodes, NULL);
         if (memnode_shift < 0) {
                 memnode_shift = 0;
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index ed34f5e35999..c9ba9deafe83 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -6,6 +6,14 @@
 
 #define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO
 
+#ifdef CONFIG_HIGHPTE
+#define PGALLOC_USER_GFP __GFP_HIGHMEM
+#else
+#define PGALLOC_USER_GFP 0
+#endif
+
+gfp_t __userpte_alloc_gfp = PGALLOC_GFP | PGALLOC_USER_GFP;
+
 pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
         return (pte_t *)__get_free_page(PGALLOC_GFP);
@@ -15,16 +23,29 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
         struct page *pte;
 
-#ifdef CONFIG_HIGHPTE
-        pte = alloc_pages(PGALLOC_GFP | __GFP_HIGHMEM, 0);
-#else
-        pte = alloc_pages(PGALLOC_GFP, 0);
-#endif
+        pte = alloc_pages(__userpte_alloc_gfp, 0);
         if (pte)
                 pgtable_page_ctor(pte);
         return pte;
 }
 
+static int __init setup_userpte(char *arg)
+{
+        if (!arg)
+                return -EINVAL;
+
+        /*
+         * "userpte=nohigh" disables allocation of user pagetables in
+         * high memory.
+         */
+        if (strcmp(arg, "nohigh") == 0)
+                __userpte_alloc_gfp &= ~__GFP_HIGHMEM;
+        else
+                return -EINVAL;
+        return 0;
+}
+early_param("userpte", setup_userpte);
+
 void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
 {
         pgtable_page_dtor(pte);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 65b58e4b0b8b..426f3a1a64d3 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -41,7 +41,7 @@ union smp_flush_state {
         struct {
                 struct mm_struct *flush_mm;
                 unsigned long flush_va;
-                spinlock_t tlbstate_lock;
+                raw_spinlock_t tlbstate_lock;
                 DECLARE_BITMAP(flush_cpumask, NR_CPUS);
         };
         char pad[INTERNODE_CACHE_BYTES];
@@ -181,7 +181,7 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask,
          * num_online_cpus() <= NUM_INVALIDATE_TLB_VECTORS, but it is
          * probably not worth checking this for a cache-hot lock.
          */
-        spin_lock(&f->tlbstate_lock);
+        raw_spin_lock(&f->tlbstate_lock);
 
         f->flush_mm = mm;
         f->flush_va = va;
@@ -199,7 +199,7 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask,
 
         f->flush_mm = NULL;
         f->flush_va = 0;
-        spin_unlock(&f->tlbstate_lock);
+        raw_spin_unlock(&f->tlbstate_lock);
 }
 
 void native_flush_tlb_others(const struct cpumask *cpumask,
@@ -223,7 +223,7 @@ static int __cpuinit init_smp_flush(void)
         int i;
 
         for (i = 0; i < ARRAY_SIZE(flush_state); i++)
-                spin_lock_init(&flush_state[i].tlbstate_lock);
+                raw_spin_lock_init(&flush_state[i].tlbstate_lock);
 
         return 0;
 }