+#define ALLOC_NO_WATERMARKS 0x01 /* don't check watermarks at all */
+#define ALLOC_WMARK_MIN 0x02 /* use pages_min watermark */
+#define ALLOC_WMARK_LOW 0x04 /* use pages_low watermark */
+#define ALLOC_WMARK_HIGH 0x08 /* use pages_high watermark */
+#define ALLOC_HARDER 0x10 /* try to alloc harder */
+#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */
+#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
+
+#ifdef CONFIG_FAIL_PAGE_ALLOC
+
+static struct fail_page_alloc_attr {
+ struct fault_attr attr;
+
+ u32 ignore_gfp_highmem;
+ u32 ignore_gfp_wait;
+
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+
+ struct dentry *ignore_gfp_highmem_file;
+ struct dentry *ignore_gfp_wait_file;
+
+#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
+
+} fail_page_alloc = {
+ .attr = FAULT_ATTR_INITIALIZER,
+ .ignore_gfp_wait = 1,
+ .ignore_gfp_highmem = 1,
+};
+
+static int __init setup_fail_page_alloc(char *str)
+{
+ return setup_fault_attr(&fail_page_alloc.attr, str);
+}
+__setup("fail_page_alloc=", setup_fail_page_alloc);
+
+static int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
+{
+ if (gfp_mask & __GFP_NOFAIL)
+ return 0;
+ if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM))
+ return 0;
+ if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT))
+ return 0;
+
+ return should_fail(&fail_page_alloc.attr, 1 << order);
+}
+
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+
+static int __init fail_page_alloc_debugfs(void)
+{
+ mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
+ struct dentry *dir;
+ int err;
+
+ err = init_fault_attr_dentries(&fail_page_alloc.attr,
+ "fail_page_alloc");
+ if (err)
+ return err;
+ dir = fail_page_alloc.attr.dentries.dir;
+
+ fail_page_alloc.ignore_gfp_wait_file =
+ debugfs_create_bool("ignore-gfp-wait", mode, dir,
+ &fail_page_alloc.ignore_gfp_wait);
+
+ fail_page_alloc.ignore_gfp_highmem_file =
+ debugfs_create_bool("ignore-gfp-highmem", mode, dir,
+ &fail_page_alloc.ignore_gfp_highmem);
+
+ if (!fail_page_alloc.ignore_gfp_wait_file ||
+ !fail_page_alloc.ignore_gfp_highmem_file) {
+ err = -ENOMEM;
+ debugfs_remove(fail_page_alloc.ignore_gfp_wait_file);
+ debugfs_remove(fail_page_alloc.ignore_gfp_highmem_file);
+ cleanup_fault_attr_dentries(&fail_page_alloc.attr);
+ }
+
+ return err;
+}
+
+late_initcall(fail_page_alloc_debugfs);
+
+#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
+
+#else /* CONFIG_FAIL_PAGE_ALLOC */
+
+static inline int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
+{
+ return 0;
+}
+
+#endif /* CONFIG_FAIL_PAGE_ALLOC */
+
+/*
+ * Return 1 if free pages are above 'mark'. This takes into account the order
+ * of the allocation.
+ */
+int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
+ int classzone_idx, int alloc_flags)
+{
+ /* free_pages my go negative - that's OK */
+ long min = mark, free_pages = z->free_pages - (1 << order) + 1;
+ int o;
+
+ if (alloc_flags & ALLOC_HIGH)
+ min -= min / 2;
+ if (alloc_flags & ALLOC_HARDER)
+ min -= min / 4;
+
+ if (free_pages <= min + z->lowmem_reserve[classzone_idx])
+ return 0;
+ for (o = 0; o < order; o++) {
+ /* At the next order, this order's pages become unavailable */
+ free_pages -= z->free_area[o].nr_free << o;
+
+ /* Require fewer higher order pages to be free */
+ min >>= 1;
+
+ if (free_pages <= min)
+ return 0;
+ }
+ return 1;
+}
+
+#ifdef CONFIG_NUMA
+/*
+ * zlc_setup - Setup for "zonelist cache". Uses cached zone data to
+ * skip over zones that are not allowed by the cpuset, or that have
+ * been recently (in last second) found to be nearly full. See further
+ * comments in mmzone.h. Reduces cache footprint of zonelist scans
+ * that have to skip over alot of full or unallowed zones.
+ *
+ * If the zonelist cache is present in the passed in zonelist, then
+ * returns a pointer to the allowed node mask (either the current
+ * tasks mems_allowed, or node_online_map.)
+ *
+ * If the zonelist cache is not available for this zonelist, does
+ * nothing and returns NULL.
+ *
+ * If the fullzones BITMAP in the zonelist cache is stale (more than
+ * a second since last zap'd) then we zap it out (clear its bits.)
+ *
+ * We hold off even calling zlc_setup, until after we've checked the
+ * first zone in the zonelist, on the theory that most allocations will
+ * be satisfied from that first zone, so best to examine that zone as
+ * quickly as we can.
+ */
+static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
+{
+ struct zonelist_cache *zlc; /* cached zonelist speedup info */
+ nodemask_t *allowednodes; /* zonelist_cache approximation */
+
+ zlc = zonelist->zlcache_ptr;
+ if (!zlc)
+ return NULL;
+
+ if (jiffies - zlc->last_full_zap > 1 * HZ) {
+ bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
+ zlc->last_full_zap = jiffies;
+ }
+
+ allowednodes = !in_interrupt() && (alloc_flags & ALLOC_CPUSET) ?
+ &cpuset_current_mems_allowed :
+ &node_online_map;
+ return allowednodes;
+}
+
+/*
+ * Given 'z' scanning a zonelist, run a couple of quick checks to see
+ * if it is worth looking at further for free memory:
+ * 1) Check that the zone isn't thought to be full (doesn't have its
+ * bit set in the zonelist_cache fullzones BITMAP).
+ * 2) Check that the zones node (obtained from the zonelist_cache
+ * z_to_n[] mapping) is allowed in the passed in allowednodes mask.
+ * Return true (non-zero) if zone is worth looking at further, or
+ * else return false (zero) if it is not.
+ *
+ * This check -ignores- the distinction between various watermarks,
+ * such as GFP_HIGH, GFP_ATOMIC, PF_MEMALLOC, ... If a zone is
+ * found to be full for any variation of these watermarks, it will
+ * be considered full for up to one second by all requests, unless
+ * we are so low on memory on all allowed nodes that we are forced
+ * into the second scan of the zonelist.
+ *
+ * In the second scan we ignore this zonelist cache and exactly
+ * apply the watermarks to all zones, even it is slower to do so.
+ * We are low on memory in the second scan, and should leave no stone
+ * unturned looking for a free page.
+ */
+static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zone **z,
+ nodemask_t *allowednodes)
+{
+ struct zonelist_cache *zlc; /* cached zonelist speedup info */
+ int i; /* index of *z in zonelist zones */
+ int n; /* node that zone *z is on */
+
+ zlc = zonelist->zlcache_ptr;
+ if (!zlc)
+ return 1;
+
+ i = z - zonelist->zones;
+ n = zlc->z_to_n[i];
+
+ /* This zone is worth trying if it is allowed but not full */
+ return node_isset(n, *allowednodes) && !test_bit(i, zlc->fullzones);
+}
+
+/*
+ * Given 'z' scanning a zonelist, set the corresponding bit in
+ * zlc->fullzones, so that subsequent attempts to allocate a page
+ * from that zone don't waste time re-examining it.
+ */
+static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z)
+{
+ struct zonelist_cache *zlc; /* cached zonelist speedup info */
+ int i; /* index of *z in zonelist zones */
+
+ zlc = zonelist->zlcache_ptr;
+ if (!zlc)
+ return;
+
+ i = z - zonelist->zones;
+
+ set_bit(i, zlc->fullzones);
+}
+
+#else /* CONFIG_NUMA */
+
+static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
+{
+ return NULL;
+}
+
+static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zone **z,
+ nodemask_t *allowednodes)
+{
+ return 1;
+}
+
+static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z)
+{
+}
+#endif /* CONFIG_NUMA */
+
+/*
+ * get_page_from_freelist goes through the zonelist trying to allocate
+ * a page.
+ */
+static struct page *
+get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
+ struct zonelist *zonelist, int alloc_flags)
+{
+ struct zone **z;
+ struct page *page = NULL;
+ int classzone_idx = zone_idx(zonelist->zones[0]);
+ struct zone *zone;
+ nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
+ int zlc_active = 0; /* set if using zonelist_cache */
+ int did_zlc_setup = 0; /* just call zlc_setup() one time */
+
+zonelist_scan:
+ /*
+ * Scan zonelist, looking for a zone with enough free.
+ * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+ */
+ z = zonelist->zones;
+
+ do {
+ if (NUMA_BUILD && zlc_active &&
+ !zlc_zone_worth_trying(zonelist, z, allowednodes))
+ continue;
+ zone = *z;
+ if (unlikely(NUMA_BUILD && (gfp_mask & __GFP_THISNODE) &&
+ zone->zone_pgdat != zonelist->zones[0]->zone_pgdat))
+ break;
+ if ((alloc_flags & ALLOC_CPUSET) &&
+ !cpuset_zone_allowed_softwall(zone, gfp_mask))
+ goto try_next_zone;
+
+ if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
+ unsigned long mark;
+ if (alloc_flags & ALLOC_WMARK_MIN)
+ mark = zone->pages_min;
+ else if (alloc_flags & ALLOC_WMARK_LOW)
+ mark = zone->pages_low;
+ else
+ mark = zone->pages_high;
+ if (!zone_watermark_ok(zone, order, mark,
+ classzone_idx, alloc_flags)) {
+ if (!zone_reclaim_mode ||
+ !zone_reclaim(zone, gfp_mask, order))
+ goto this_zone_full;
+ }
+ }
+
+ page = buffered_rmqueue(zonelist, zone, order, gfp_mask);
+ if (page)
+ break;
+this_zone_full:
+ if (NUMA_BUILD)
+ zlc_mark_zone_full(zonelist, z);
+try_next_zone:
+ if (NUMA_BUILD && !did_zlc_setup) {
+ /* we do zlc_setup after the first zone is tried */
+ allowednodes = zlc_setup(zonelist, alloc_flags);
+ zlc_active = 1;
+ did_zlc_setup = 1;
+ }
+ } while (*(++z) != NULL);
+
+ if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) {
+ /* Disable zlc cache for second zonelist scan */
+ zlc_active = 0;
+ goto zonelist_scan;
+ }
+ return page;
+}
+
+/*
+ * This is the 'heart' of the zoned buddy allocator.
+ */