7 files changed, 133 insertions, 41 deletions

diff --git a/mm/bootmem.c b/mm/bootmem.c
index d3e3bd2ffcea..d213feded10d 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -401,7 +401,7 @@ unsigned long __init free_all_bootmem (void)
         return(free_all_bootmem_core(NODE_DATA(0)));
 }
 
-void * __init __alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal)
+void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align, unsigned long goal)
 {
         bootmem_data_t *bdata;
         void *ptr;
@@ -409,7 +409,14 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align, unsigned
         list_for_each_entry(bdata, &bdata_list, list)
                 if ((ptr = __alloc_bootmem_core(bdata, size, align, goal, 0)))
                         return(ptr);
+        return NULL;
+}
 
+void * __init __alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal)
+{
+        void *mem = __alloc_bootmem_nopanic(size,align,goal);
+        if (mem)
+                return mem;
         /*
          * Whoops, we cannot satisfy the allocation request.
          */
diff --git a/mm/migrate.c b/mm/migrate.c
index 09f6e4aa87fc..d444229f2599 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -16,8 +16,7 @@
 #include <linux/module.h>
 #include <linux/swap.h>
 #include <linux/pagemap.h>
-#include <linux/buffer_head.h>  /* for try_to_release_page(),
-                                        buffer_heads_over_limit */
+#include <linux/buffer_head.h>
 #include <linux/mm_inline.h>
 #include <linux/pagevec.h>
 #include <linux/rmap.h>
@@ -28,8 +27,6 @@
 
 #include "internal.h"
 
-#include "internal.h"
-
 /* The maximum number of pages to take off the LRU for migration */
 #define MIGRATE_CHUNK_SIZE 256
 
@@ -176,7 +173,6 @@ unlock_retry:
 retry:
         return -EAGAIN;
 }
-EXPORT_SYMBOL(swap_page);
 
 /*
  * Remove references for a page and establish the new page with the correct
@@ -234,7 +230,7 @@ int migrate_page_remove_references(struct page *newpage,
         if (!page_mapping(page) || page_count(page) != nr_refs ||
                         *radix_pointer != page) {
                 write_unlock_irq(&mapping->tree_lock);
-                return 1;
+                return -EAGAIN;
         }
 
         /*
diff --git a/mm/mmap.c b/mm/mmap.c
index e780d19aa214..e6ee12344b13 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -121,14 +121,26 @@ int __vm_enough_memory(long pages, int cap_sys_admin)
                  * only call if we're about to fail.
                  */
                 n = nr_free_pages();
+
+                /*
+                 * Leave reserved pages. The pages are not for anonymous pages.
+                 */
+                if (n <= totalreserve_pages)
+                        goto error;
+                else
+                        n -= totalreserve_pages;
+
+                /*
+                 * Leave the last 3% for root
+                 */
                 if (!cap_sys_admin)
                         n -= n / 32;
                 free += n;
 
                 if (free > pages)
                         return 0;
-                vm_unacct_memory(pages);
-                return -ENOMEM;
+
+                goto error;
         }
 
         allowed = (totalram_pages - hugetlb_total_pages())
@@ -150,7 +162,7 @@ int __vm_enough_memory(long pages, int cap_sys_admin)
          */
         if (atomic_read(&vm_committed_space) < (long)allowed)
                 return 0;
-
+error:
         vm_unacct_memory(pages);
 
         return -ENOMEM;
@@ -220,6 +232,17 @@ asmlinkage unsigned long sys_brk(unsigned long brk)
 
         if (brk < mm->end_code)
                 goto out;
+
+        /*
+         * Check against rlimit here. If this check is done later after the test
+         * of oldbrk with newbrk then it can escape the test and let the data
+         * segment grow beyond its set limit the in case where the limit is
+         * not page aligned -Ram Gupta
+         */
+        rlim = current->signal->rlim[RLIMIT_DATA].rlim_cur;
+        if (rlim < RLIM_INFINITY && brk - mm->start_data > rlim)
+                goto out;
+
         newbrk = PAGE_ALIGN(brk);
         oldbrk = PAGE_ALIGN(mm->brk);
         if (oldbrk == newbrk)
@@ -232,11 +255,6 @@ asmlinkage unsigned long sys_brk(unsigned long brk)
                 goto out;
         }
 
-        /* Check against rlimit.. */
-        rlim = current->signal->rlim[RLIMIT_DATA].rlim_cur;
-        if (rlim < RLIM_INFINITY && brk - mm->start_data > rlim)
-                goto out;
-
         /* Check against existing mmap mappings. */
         if (find_vma_intersection(mm, oldbrk, newbrk+PAGE_SIZE))
                 goto out;
diff --git a/mm/nommu.c b/mm/nommu.c
index db45efac17cc..029fadac0fb5 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1147,14 +1147,26 @@ int __vm_enough_memory(long pages, int cap_sys_admin)
                  * only call if we're about to fail.
                  */
                 n = nr_free_pages();
+
+                /*
+                 * Leave reserved pages. The pages are not for anonymous pages.
+                 */
+                if (n <= totalreserve_pages)
+                        goto error;
+                else
+                        n -= totalreserve_pages;
+
+                /*
+                 * Leave the last 3% for root
+                 */
                 if (!cap_sys_admin)
                         n -= n / 32;
                 free += n;
 
                 if (free > pages)
                         return 0;
-                vm_unacct_memory(pages);
-                return -ENOMEM;
+
+                goto error;
         }
 
         allowed = totalram_pages * sysctl_overcommit_ratio / 100;
@@ -1175,7 +1187,7 @@ int __vm_enough_memory(long pages, int cap_sys_admin)
          */
         if (atomic_read(&vm_committed_space) < (long)allowed)
                 return 0;
-
+error:
         vm_unacct_memory(pages);
 
         return -ENOMEM;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 6dcce3a4bbdc..75d7f48b79bb 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -72,13 +72,12 @@ int dirty_background_ratio = 10;
 int vm_dirty_ratio = 40;
 
 /*
- * The interval between `kupdate'-style writebacks, in centiseconds
- * (hundredths of a second)
+ * The interval between `kupdate'-style writebacks, in jiffies
  */
 int dirty_writeback_interval = 5 * HZ;
 
 /*
- * The longest number of centiseconds for which data is allowed to remain dirty
+ * The longest number of jiffies for which data is allowed to remain dirty
  */
 int dirty_expire_interval = 30 * HZ;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index dc523a1f270d..97d6827c7d66 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -51,6 +51,7 @@ nodemask_t node_possible_map __read_mostly = NODE_MASK_ALL;
 EXPORT_SYMBOL(node_possible_map);
 unsigned long totalram_pages __read_mostly;
 unsigned long totalhigh_pages __read_mostly;
+unsigned long totalreserve_pages __read_mostly;
 long nr_swap_pages;
 int percpu_pagelist_fraction;
 
@@ -151,7 +152,8 @@ static void bad_page(struct page *page)
                         1 << PG_reclaim |
                         1 << PG_slab    |
                         1 << PG_swapcache |
-                        1 << PG_writeback );
+                        1 << PG_writeback |
+                        1 << PG_buddy );
         set_page_count(page, 0);
         reset_page_mapcount(page);
         page->mapping = NULL;
@@ -236,12 +238,12 @@ static inline unsigned long page_order(struct page *page) {
 
 static inline void set_page_order(struct page *page, int order) {
         set_page_private(page, order);
-        __SetPagePrivate(page);
+        __SetPageBuddy(page);
 }
 
 static inline void rmv_page_order(struct page *page)
 {
-        __ClearPagePrivate(page);
+        __ClearPageBuddy(page);
         set_page_private(page, 0);
 }
 
@@ -280,11 +282,13 @@ __find_combined_index(unsigned long page_idx, unsigned int order)
  * This function checks whether a page is free && is the buddy
  * we can do coalesce a page and its buddy if
  * (a) the buddy is not in a hole &&
- * (b) the buddy is free &&
- * (c) the buddy is on the buddy system &&
- * (d) a page and its buddy have the same order.
- * for recording page's order, we use page_private(page) and PG_private.
+ * (b) the buddy is in the buddy system &&
+ * (c) a page and its buddy have the same order.
+ *
+ * For recording whether a page is in the buddy system, we use PG_buddy.
+ * Setting, clearing, and testing PG_buddy is serialized by zone->lock.
  *
+ * For recording page's order, we use page_private(page).
  */
 static inline int page_is_buddy(struct page *page, int order)
 {
@@ -293,10 +297,10 @@ static inline int page_is_buddy(struct page *page, int order)
                 return 0;
 #endif
 
-       if (PagePrivate(page)           &&
-           (page_order(page) == order) &&
-            page_count(page) == 0)
+        if (PageBuddy(page) && page_order(page) == order) {
+                BUG_ON(page_count(page) != 0);
                return 1;
+        }
        return 0;
 }
 
@@ -313,7 +317,7 @@ static inline int page_is_buddy(struct page *page, int order)
  * as necessary, plus some accounting needed to play nicely with other
  * parts of the VM system.
  * At each level, we keep a list of pages, which are heads of continuous
- * free pages of length of (1 << order) and marked with PG_Private.Page's
+ * free pages of length of (1 << order) and marked with PG_buddy. Page's
  * order is recorded in page_private(page) field.
  * So when we are allocating or freeing one, we can derive the state of the
  * other.  That is, if we allocate a small block, and both were   
@@ -376,7 +380,8 @@ static inline int free_pages_check(struct page *page)
                         1 << PG_slab    |
                         1 << PG_swapcache |
                         1 << PG_writeback |
-                        1 << PG_reserved ))))
+                        1 << PG_reserved |
+                        1 << PG_buddy ))))
                 bad_page(page);
         if (PageDirty(page))
                 __ClearPageDirty(page);
@@ -524,7 +529,8 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
                         1 << PG_slab    |
                         1 << PG_swapcache |
                         1 << PG_writeback |
-                        1 << PG_reserved ))))
+                        1 << PG_reserved |
+                        1 << PG_buddy ))))
                 bad_page(page);
 
         /*
@@ -2472,6 +2478,38 @@ void __init page_alloc_init(void)
 }
 
 /*
+ * calculate_totalreserve_pages - called when sysctl_lower_zone_reserve_ratio
+ *      or min_free_kbytes changes.
+ */
+static void calculate_totalreserve_pages(void)
+{
+        struct pglist_data *pgdat;
+        unsigned long reserve_pages = 0;
+        int i, j;
+
+        for_each_online_pgdat(pgdat) {
+                for (i = 0; i < MAX_NR_ZONES; i++) {
+                        struct zone *zone = pgdat->node_zones + i;
+                        unsigned long max = 0;
+
+                        /* Find valid and maximum lowmem_reserve in the zone */
+                        for (j = i; j < MAX_NR_ZONES; j++) {
+                                if (zone->lowmem_reserve[j] > max)
+                                        max = zone->lowmem_reserve[j];
+                        }
+
+                        /* we treat pages_high as reserved pages. */
+                        max += zone->pages_high;
+
+                        if (max > zone->present_pages)
+                                max = zone->present_pages;
+                        reserve_pages += max;
+                }
+        }
+        totalreserve_pages = reserve_pages;
+}
+
+/*
  * setup_per_zone_lowmem_reserve - called whenever
  *      sysctl_lower_zone_reserve_ratio changes.  Ensures that each zone
  *      has a correct pages reserved value, so an adequate number of
@@ -2502,6 +2540,9 @@ static void setup_per_zone_lowmem_reserve(void)
                         }
                 }
         }
+
+        /* update totalreserve_pages */
+        calculate_totalreserve_pages();
 }
 
 /*
@@ -2556,6 +2597,9 @@ void setup_per_zone_pages_min(void)
                 zone->pages_high  = zone->pages_min + tmp / 2;
                 spin_unlock_irqrestore(&zone->lru_lock, flags);
         }
+
+        /* update totalreserve_pages */
+        calculate_totalreserve_pages();
 }
 
 /*
diff --git a/mm/slab.c b/mm/slab.c
index f055c1420216..e6ef9bd52335 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -420,6 +420,7 @@ struct kmem_cache {
         unsigned long max_freeable;
         unsigned long node_allocs;
         unsigned long node_frees;
+        unsigned long node_overflow;
         atomic_t allochit;
         atomic_t allocmiss;
         atomic_t freehit;
@@ -465,6 +466,7 @@ struct kmem_cache {
 #define STATS_INC_ERR(x)        ((x)->errors++)
 #define STATS_INC_NODEALLOCS(x) ((x)->node_allocs++)
 #define STATS_INC_NODEFREES(x)  ((x)->node_frees++)
+#define STATS_INC_ACOVERFLOW(x)   ((x)->node_overflow++)
 #define STATS_SET_FREEABLE(x, i)                                        \
         do {                                                            \
                 if ((x)->max_freeable < i)                              \
@@ -484,6 +486,7 @@ struct kmem_cache {
 #define STATS_INC_ERR(x)        do { } while (0)
 #define STATS_INC_NODEALLOCS(x) do { } while (0)
 #define STATS_INC_NODEFREES(x)  do { } while (0)
+#define STATS_INC_ACOVERFLOW(x)   do { } while (0)
 #define STATS_SET_FREEABLE(x, i) do { } while (0)
 #define STATS_INC_ALLOCHIT(x)   do { } while (0)
 #define STATS_INC_ALLOCMISS(x)  do { } while (0)
@@ -1453,7 +1456,14 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
         int i;
 
         flags |= cachep->gfpflags;
+#ifndef CONFIG_MMU
+        /* nommu uses slab's for process anonymous memory allocations, so
+         * requires __GFP_COMP to properly refcount higher order allocations"
+         */
+        page = alloc_pages_node(nodeid, (flags | __GFP_COMP), cachep->gfporder);
+#else
         page = alloc_pages_node(nodeid, flags, cachep->gfporder);
+#endif
         if (!page)
                 return NULL;
         addr = page_address(page);
@@ -2318,13 +2328,15 @@ EXPORT_SYMBOL(kmem_cache_destroy);
 
 /* Get the memory for a slab management obj. */
 static struct slab *alloc_slabmgmt(struct kmem_cache *cachep, void *objp,
-                                   int colour_off, gfp_t local_flags)
+                                   int colour_off, gfp_t local_flags,
+                                   int nodeid)
 {
         struct slab *slabp;
 
         if (OFF_SLAB(cachep)) {
                 /* Slab management obj is off-slab. */
-                slabp = kmem_cache_alloc(cachep->slabp_cache, local_flags);
+                slabp = kmem_cache_alloc_node(cachep->slabp_cache,
+                                              local_flags, nodeid);
                 if (!slabp)
                         return NULL;
         } else {
@@ -2334,6 +2346,7 @@ static struct slab *alloc_slabmgmt(struct kmem_cache *cachep, void *objp,
         slabp->inuse = 0;
         slabp->colouroff = colour_off;
         slabp->s_mem = objp + colour_off;
+        slabp->nodeid = nodeid;
         return slabp;
 }
 
@@ -2519,7 +2532,7 @@ static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid)
                 goto failed;
 
         /* Get slab management. */
-        slabp = alloc_slabmgmt(cachep, objp, offset, local_flags);
+        slabp = alloc_slabmgmt(cachep, objp, offset, local_flags, nodeid);
         if (!slabp)
                 goto opps1;
 
@@ -3080,9 +3093,11 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp)
                         if (l3->alien && l3->alien[nodeid]) {
                                 alien = l3->alien[nodeid];
                                 spin_lock(&alien->lock);
-                                if (unlikely(alien->avail == alien->limit))
+                                if (unlikely(alien->avail == alien->limit)) {
+                                        STATS_INC_ACOVERFLOW(cachep);
                                         __drain_alien_cache(cachep,
                                                             alien, nodeid);
+                                }
                                 alien->entry[alien->avail++] = objp;
                                 spin_unlock(&alien->lock);
                         } else {
@@ -3760,7 +3775,7 @@ static void print_slabinfo_header(struct seq_file *m)
         seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>");
 #if STATS
         seq_puts(m, " : globalstat <listallocs> <maxobjs> <grown> <reaped> "
-                 "<error> <maxfreeable> <nodeallocs> <remotefrees>");
+                 "<error> <maxfreeable> <nodeallocs> <remotefrees> <alienoverflow>");
         seq_puts(m, " : cpustat <allochit> <allocmiss> <freehit> <freemiss>");
 #endif
         seq_putc(m, '\n');
@@ -3874,11 +3889,12 @@ static int s_show(struct seq_file *m, void *p)
                 unsigned long max_freeable = cachep->max_freeable;
                 unsigned long node_allocs = cachep->node_allocs;
                 unsigned long node_frees = cachep->node_frees;
+                unsigned long overflows = cachep->node_overflow;
 
                 seq_printf(m, " : globalstat %7lu %6lu %5lu %4lu \
-                                %4lu %4lu %4lu %4lu", allocs, high, grown,
+                                %4lu %4lu %4lu %4lu %4lu", allocs, high, grown,
                                 reaped, errors, max_freeable, node_allocs,
-                                node_frees);
+                                node_frees, overflows);
         }
         /* cpu stats */
         {