summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorAnton Arapov <anton@redhat.com>2012-10-29 11:32:50 +0100
committerAnton Arapov <anton@redhat.com>2012-10-29 11:32:50 +0100
commit7f6dc119ae2a77a23a3c07ebefba6fd7df65a74c (patch)
tree109fdbb7cff60b946bdadae15f5de052d96abae8 /mm
parent4f87faf0a40754afe619316ef1e5980a1811d883 (diff)
downloadkernel-uprobes-7f6dc119ae2a77a23a3c07ebefba6fd7df65a74c.zip
kernel-uprobes-7f6dc119ae2a77a23a3c07ebefba6fd7df65a74c.tar.gz
kernel-uprobes-7f6dc119ae2a77a23a3c07ebefba6fd7df65a74c.tar.xz
fedora kernel: 1c1fad82422e58b20bf06bb371c38154b4b965dbv3.6.3-4f18
Signed-off-by: Anton Arapov <anton@redhat.com>
Diffstat (limited to 'mm')
-rw-r--r--mm/huge_memory.c1
-rw-r--r--mm/hugetlb.c3
-rw-r--r--mm/memory_hotplug.c16
-rw-r--r--mm/mempolicy.c137
-rw-r--r--mm/page_alloc.c2
-rw-r--r--mm/shmem.c6
-rw-r--r--mm/slab.c12
-rw-r--r--mm/slub.c15
-rw-r--r--mm/truncate.c3
-rw-r--r--mm/vmscan.c1
10 files changed, 124 insertions, 72 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 57c4b93..141dbb6 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1811,7 +1811,6 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
src_page = pte_page(pteval);
copy_user_highpage(page, src_page, address, vma);
VM_BUG_ON(page_mapcount(src_page) != 1);
- VM_BUG_ON(page_count(src_page) != 2);
release_pte_page(src_page);
/*
* ptl mostly unnecessary, but preempt has to
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index bc72712..3adceaf 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2481,7 +2481,8 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
* from page cache lookup which is in HPAGE_SIZE units.
*/
address = address & huge_page_mask(h);
- pgoff = vma_hugecache_offset(h, vma, address);
+ pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) +
+ vma->vm_pgoff;
mapping = vma->vm_file->f_dentry->d_inode->i_mapping;
/*
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 3ad25f9..6a5b90d 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -126,9 +126,6 @@ static void register_page_bootmem_info_section(unsigned long start_pfn)
struct mem_section *ms;
struct page *page, *memmap;
- if (!pfn_valid(start_pfn))
- return;
-
section_nr = pfn_to_section_nr(start_pfn);
ms = __nr_to_section(section_nr);
@@ -187,9 +184,16 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat)
end_pfn = pfn + pgdat->node_spanned_pages;
/* register_section info */
- for (; pfn < end_pfn; pfn += PAGES_PER_SECTION)
- register_page_bootmem_info_section(pfn);
-
+ for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+ /*
+ * Some platforms can assign the same pfn to multiple nodes - on
+ * node0 as well as nodeN. To avoid registering a pfn against
+ * multiple nodes we check that this pfn does not already
+ * reside in some other node.
+ */
+ if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node))
+ register_page_bootmem_info_section(pfn);
+ }
}
#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 4ada3be..3d64b36 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -607,6 +607,42 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
return first;
}
+/*
+ * Apply policy to a single VMA
+ * This must be called with the mmap_sem held for writing.
+ */
+static int vma_replace_policy(struct vm_area_struct *vma,
+ struct mempolicy *pol)
+{
+ int err;
+ struct mempolicy *old;
+ struct mempolicy *new;
+
+ pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n",
+ vma->vm_start, vma->vm_end, vma->vm_pgoff,
+ vma->vm_ops, vma->vm_file,
+ vma->vm_ops ? vma->vm_ops->set_policy : NULL);
+
+ new = mpol_dup(pol);
+ if (IS_ERR(new))
+ return PTR_ERR(new);
+
+ if (vma->vm_ops && vma->vm_ops->set_policy) {
+ err = vma->vm_ops->set_policy(vma, new);
+ if (err)
+ goto err_out;
+ }
+
+ old = vma->vm_policy;
+ vma->vm_policy = new; /* protected by mmap_sem */
+ mpol_put(old);
+
+ return 0;
+ err_out:
+ mpol_put(new);
+ return err;
+}
+
/* Step 2: apply policy to a range and do splits. */
static int mbind_range(struct mm_struct *mm, unsigned long start,
unsigned long end, struct mempolicy *new_pol)
@@ -655,23 +691,9 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
if (err)
goto out;
}
-
- /*
- * Apply policy to a single VMA. The reference counting of
- * policy for vma_policy linkages has already been handled by
- * vma_merge and split_vma as necessary. If this is a shared
- * policy then ->set_policy will increment the reference count
- * for an sp node.
- */
- pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n",
- vma->vm_start, vma->vm_end, vma->vm_pgoff,
- vma->vm_ops, vma->vm_file,
- vma->vm_ops ? vma->vm_ops->set_policy : NULL);
- if (vma->vm_ops && vma->vm_ops->set_policy) {
- err = vma->vm_ops->set_policy(vma, new_pol);
- if (err)
- goto out;
- }
+ err = vma_replace_policy(vma, new_pol);
+ if (err)
+ goto out;
}
out:
@@ -1530,8 +1552,18 @@ struct mempolicy *get_vma_policy(struct task_struct *task,
addr);
if (vpol)
pol = vpol;
- } else if (vma->vm_policy)
+ } else if (vma->vm_policy) {
pol = vma->vm_policy;
+
+ /*
+ * shmem_alloc_page() passes MPOL_F_SHARED policy with
+ * a pseudo vma whose vma->vm_ops=NULL. Take a reference
+ * count on these policies which will be dropped by
+ * mpol_cond_put() later
+ */
+ if (mpol_needs_cond_ref(pol))
+ mpol_get(pol);
+ }
}
if (!pol)
pol = &default_policy;
@@ -2061,7 +2093,7 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
*/
/* lookup first element intersecting start-end */
-/* Caller holds sp->lock */
+/* Caller holds sp->mutex */
static struct sp_node *
sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end)
{
@@ -2125,36 +2157,50 @@ mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
if (!sp->root.rb_node)
return NULL;
- spin_lock(&sp->lock);
+ mutex_lock(&sp->mutex);
sn = sp_lookup(sp, idx, idx+1);
if (sn) {
mpol_get(sn->policy);
pol = sn->policy;
}
- spin_unlock(&sp->lock);
+ mutex_unlock(&sp->mutex);
return pol;
}
+static void sp_free(struct sp_node *n)
+{
+ mpol_put(n->policy);
+ kmem_cache_free(sn_cache, n);
+}
+
static void sp_delete(struct shared_policy *sp, struct sp_node *n)
{
pr_debug("deleting %lx-l%lx\n", n->start, n->end);
rb_erase(&n->nd, &sp->root);
- mpol_put(n->policy);
- kmem_cache_free(sn_cache, n);
+ sp_free(n);
}
static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
struct mempolicy *pol)
{
- struct sp_node *n = kmem_cache_alloc(sn_cache, GFP_KERNEL);
+ struct sp_node *n;
+ struct mempolicy *newpol;
+ n = kmem_cache_alloc(sn_cache, GFP_KERNEL);
if (!n)
return NULL;
+
+ newpol = mpol_dup(pol);
+ if (IS_ERR(newpol)) {
+ kmem_cache_free(sn_cache, n);
+ return NULL;
+ }
+ newpol->flags |= MPOL_F_SHARED;
+
n->start = start;
n->end = end;
- mpol_get(pol);
- pol->flags |= MPOL_F_SHARED; /* for unref */
- n->policy = pol;
+ n->policy = newpol;
+
return n;
}
@@ -2162,10 +2208,10 @@ static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
unsigned long end, struct sp_node *new)
{
- struct sp_node *n, *new2 = NULL;
+ struct sp_node *n;
+ int ret = 0;
-restart:
- spin_lock(&sp->lock);
+ mutex_lock(&sp->mutex);
n = sp_lookup(sp, start, end);
/* Take care of old policies in the same range. */
while (n && n->start < end) {
@@ -2178,16 +2224,14 @@ restart:
} else {
/* Old policy spanning whole new range. */
if (n->end > end) {
+ struct sp_node *new2;
+ new2 = sp_alloc(end, n->end, n->policy);
if (!new2) {
- spin_unlock(&sp->lock);
- new2 = sp_alloc(end, n->end, n->policy);
- if (!new2)
- return -ENOMEM;
- goto restart;
+ ret = -ENOMEM;
+ goto out;
}
n->end = start;
sp_insert(sp, new2);
- new2 = NULL;
break;
} else
n->end = start;
@@ -2198,12 +2242,9 @@ restart:
}
if (new)
sp_insert(sp, new);
- spin_unlock(&sp->lock);
- if (new2) {
- mpol_put(new2->policy);
- kmem_cache_free(sn_cache, new2);
- }
- return 0;
+out:
+ mutex_unlock(&sp->mutex);
+ return ret;
}
/**
@@ -2221,7 +2262,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
int ret;
sp->root = RB_ROOT; /* empty tree == default mempolicy */
- spin_lock_init(&sp->lock);
+ mutex_init(&sp->mutex);
if (mpol) {
struct vm_area_struct pvma;
@@ -2275,7 +2316,7 @@ int mpol_set_shared_policy(struct shared_policy *info,
}
err = shared_policy_replace(info, vma->vm_pgoff, vma->vm_pgoff+sz, new);
if (err && new)
- kmem_cache_free(sn_cache, new);
+ sp_free(new);
return err;
}
@@ -2287,16 +2328,14 @@ void mpol_free_shared_policy(struct shared_policy *p)
if (!p->root.rb_node)
return;
- spin_lock(&p->lock);
+ mutex_lock(&p->mutex);
next = rb_first(&p->root);
while (next) {
n = rb_entry(next, struct sp_node, nd);
next = rb_next(&n->nd);
- rb_erase(&n->nd, &p->root);
- mpol_put(n->policy);
- kmem_cache_free(sn_cache, n);
+ sp_delete(p, n);
}
- spin_unlock(&p->lock);
+ mutex_unlock(&p->mutex);
}
/* assumes fs == KERNEL_DS */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c66fb87..c13ea75 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -584,7 +584,7 @@ static inline void __free_one_page(struct page *page,
combined_idx = buddy_idx & page_idx;
higher_page = page + (combined_idx - page_idx);
buddy_idx = __find_buddy_index(combined_idx, order + 1);
- higher_buddy = page + (buddy_idx - combined_idx);
+ higher_buddy = higher_page + (buddy_idx - combined_idx);
if (page_is_buddy(higher_page, higher_buddy, order + 1)) {
list_add_tail(&page->lru,
&zone->free_area[order].free_list[migratetype]);
diff --git a/mm/shmem.c b/mm/shmem.c
index d4e184e..d2eeca1 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2366,12 +2366,14 @@ static struct dentry *shmem_fh_to_dentry(struct super_block *sb,
{
struct inode *inode;
struct dentry *dentry = NULL;
- u64 inum = fid->raw[2];
- inum = (inum << 32) | fid->raw[1];
+ u64 inum;
if (fh_len < 3)
return NULL;
+ inum = fid->raw[2];
+ inum = (inum << 32) | fid->raw[1];
+
inode = ilookup5(sb, (unsigned long)(inum + fid->raw[0]),
shmem_match, fid->raw);
if (inode) {
diff --git a/mm/slab.c b/mm/slab.c
index 811af03..d066037 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -983,7 +983,7 @@ static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
}
/* The caller cannot use PFMEMALLOC objects, find another one */
- for (i = 1; i < ac->avail; i++) {
+ for (i = 0; i < ac->avail; i++) {
/* If a !PFMEMALLOC object is found, swap them */
if (!is_obj_pfmemalloc(ac->entry[i])) {
objp = ac->entry[i];
@@ -1000,7 +1000,7 @@ static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
l3 = cachep->nodelists[numa_mem_id()];
if (!list_empty(&l3->slabs_free) && force_refill) {
struct slab *slabp = virt_to_slab(objp);
- ClearPageSlabPfmemalloc(virt_to_page(slabp->s_mem));
+ ClearPageSlabPfmemalloc(virt_to_head_page(slabp->s_mem));
clear_obj_pfmemalloc(&objp);
recheck_pfmemalloc_active(cachep, ac);
return objp;
@@ -1032,7 +1032,7 @@ static void *__ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
{
if (unlikely(pfmemalloc_active)) {
/* Some pfmemalloc slabs exist, check if this is one */
- struct page *page = virt_to_page(objp);
+ struct page *page = virt_to_head_page(objp);
if (PageSlabPfmemalloc(page))
set_obj_pfmemalloc(&objp);
}
@@ -1781,9 +1781,6 @@ void __init kmem_cache_init_late(void)
slab_state = UP;
- /* Annotate slab for lockdep -- annotate the malloc caches */
- init_lock_keys();
-
/* 6) resize the head arrays to their final sizes */
mutex_lock(&slab_mutex);
list_for_each_entry(cachep, &slab_caches, list)
@@ -1791,6 +1788,9 @@ void __init kmem_cache_init_late(void)
BUG();
mutex_unlock(&slab_mutex);
+ /* Annotate slab for lockdep -- annotate the malloc caches */
+ init_lock_keys();
+
/* Done! */
slab_state = FULL;
diff --git a/mm/slub.c b/mm/slub.c
index 8f78e25..2fdd96f 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1524,12 +1524,13 @@ static inline void *acquire_slab(struct kmem_cache *s,
}
static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain);
+static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags);
/*
* Try to allocate a partial slab from a specific node.
*/
-static void *get_partial_node(struct kmem_cache *s,
- struct kmem_cache_node *n, struct kmem_cache_cpu *c)
+static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
+ struct kmem_cache_cpu *c, gfp_t flags)
{
struct page *page, *page2;
void *object = NULL;
@@ -1545,9 +1546,13 @@ static void *get_partial_node(struct kmem_cache *s,
spin_lock(&n->list_lock);
list_for_each_entry_safe(page, page2, &n->partial, lru) {
- void *t = acquire_slab(s, n, page, object == NULL);
+ void *t;
int available;
+ if (!pfmemalloc_match(page, flags))
+ continue;
+
+ t = acquire_slab(s, n, page, object == NULL);
if (!t)
break;
@@ -1614,7 +1619,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
n->nr_partial > s->min_partial) {
- object = get_partial_node(s, n, c);
+ object = get_partial_node(s, n, c, flags);
if (object) {
/*
* Return the object even if
@@ -1643,7 +1648,7 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
void *object;
int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node;
- object = get_partial_node(s, get_node(s, searchnode), c);
+ object = get_partial_node(s, get_node(s, searchnode), c, flags);
if (object || node != NUMA_NO_NODE)
return object;
diff --git a/mm/truncate.c b/mm/truncate.c
index 75801ac..f38055c 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -394,11 +394,12 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL))
return 0;
+ clear_page_mlock(page);
+
spin_lock_irq(&mapping->tree_lock);
if (PageDirty(page))
goto failed;
- clear_page_mlock(page);
BUG_ON(page_has_private(page));
__delete_from_page_cache(page);
spin_unlock_irq(&mapping->tree_lock);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8d01243..99b434b 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3102,6 +3102,7 @@ int kswapd_run(int nid)
/* failure at boot is fatal */
BUG_ON(system_state == SYSTEM_BOOTING);
printk("Failed to start kswapd on node %d\n",nid);
+ pgdat->kswapd = NULL;
ret = -1;
}
return ret;