summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorMichal Hocko <mhocko@suse.com>2017-05-08 15:57:09 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-05-08 17:15:12 -0700
commita7c3e901a46ff54c016d040847eda598a9e3e653 (patch)
treed149d70d420ff19586daa827db47a2e26a5598fe /mm
parent60f3e00d25b44e3aa51846590d1e10f408466a83 (diff)
mm: introduce kv[mz]alloc helpers
Patch series "kvmalloc", v5. There are many open coded kmalloc with vmalloc fallback instances in the tree. Most of them are not careful enough or simply do not care about the underlying semantic of the kmalloc/page allocator which means that a) some vmalloc fallbacks are basically unreachable because the kmalloc part will keep retrying until it succeeds b) the page allocator can invoke a really disruptive steps like the OOM killer to move forward which doesn't sound appropriate when we consider that the vmalloc fallback is available. As it can be seen implementing kvmalloc requires quite an intimate knowledge if the page allocator and the memory reclaim internals which strongly suggests that a helper should be implemented in the memory subsystem proper. Most callers, I could find, have been converted to use the helper instead. This is patch 6. There are some more relying on __GFP_REPEAT in the networking stack which I have converted as well and Eric Dumazet was not opposed [2] to convert them as well. [1] http://lkml.kernel.org/r/20170130094940.13546-1-mhocko@kernel.org [2] http://lkml.kernel.org/r/1485273626.16328.301.camel@edumazet-glaptop3.roam.corp.google.com This patch (of 9): Using kmalloc with the vmalloc fallback for larger allocations is a common pattern in the kernel code. Yet we do not have any common helper for that and so users have invented their own helpers. Some of them are really creative when doing so. Let's just add kv[mz]alloc and make sure it is implemented properly. This implementation makes sure to not make a large memory pressure for > PAGE_SZE requests (__GFP_NORETRY) and also to not warn about allocation failures. This also rules out the OOM killer as the vmalloc is a more approapriate fallback than a disruptive user visible action. This patch also changes some existing users and removes helpers which are specific for them. In some cases this is not possible (e.g. ext4_kvmalloc, libcfs_kvzalloc) because those seems to be broken and require GFP_NO{FS,IO} context which is not vmalloc compatible in general (note that the page table allocation is GFP_KERNEL). Those need to be fixed separately. While we are at it, document that __vmalloc{_node} about unsupported gfp mask because there seems to be a lot of confusion out there. kvmalloc_node will warn about GFP_KERNEL incompatible (which are not superset) flags to catch new abusers. Existing ones would have to die slowly. [sfr@canb.auug.org.au: f2fs fixup] Link: http://lkml.kernel.org/r/20170320163735.332e64b7@canb.auug.org.au Link: http://lkml.kernel.org/r/20170306103032.2540-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Reviewed-by: Andreas Dilger <adilger@dilger.ca> [ext4 part] Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: John Hubbard <jhubbard@nvidia.com> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/nommu.c5
-rw-r--r--mm/util.c45
-rw-r--r--mm/vmalloc.c9
3 files changed, 58 insertions, 1 deletions
diff --git a/mm/nommu.c b/mm/nommu.c
index 2d131b97a851..a80411d258fc 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -237,6 +237,11 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
}
EXPORT_SYMBOL(__vmalloc);
+void *__vmalloc_node_flags(unsigned long size, int node, gfp_t flags)
+{
+ return __vmalloc(size, flags, PAGE_KERNEL);
+}
+
void *vmalloc_user(unsigned long size)
{
void *ret;
diff --git a/mm/util.c b/mm/util.c
index 656dc5e37a87..10a14a0ac3c2 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -329,6 +329,51 @@ unsigned long vm_mmap(struct file *file, unsigned long addr,
}
EXPORT_SYMBOL(vm_mmap);
+/**
+ * kvmalloc_node - attempt to allocate physically contiguous memory, but upon
+ * failure, fall back to non-contiguous (vmalloc) allocation.
+ * @size: size of the request.
+ * @flags: gfp mask for the allocation - must be compatible (superset) with GFP_KERNEL.
+ * @node: numa node to allocate from
+ *
+ * Uses kmalloc to get the memory but if the allocation fails then falls back
+ * to the vmalloc allocator. Use kvfree for freeing the memory.
+ *
+ * Reclaim modifiers - __GFP_NORETRY, __GFP_REPEAT and __GFP_NOFAIL are not supported
+ *
+ * Any use of gfp flags outside of GFP_KERNEL should be consulted with mm people.
+ */
+void *kvmalloc_node(size_t size, gfp_t flags, int node)
+{
+ gfp_t kmalloc_flags = flags;
+ void *ret;
+
+ /*
+ * vmalloc uses GFP_KERNEL for some internal allocations (e.g page tables)
+ * so the given set of flags has to be compatible.
+ */
+ WARN_ON_ONCE((flags & GFP_KERNEL) != GFP_KERNEL);
+
+ /*
+ * Make sure that larger requests are not too disruptive - no OOM
+ * killer and no allocation failure warnings as we have a fallback
+ */
+ if (size > PAGE_SIZE)
+ kmalloc_flags |= __GFP_NORETRY | __GFP_NOWARN;
+
+ ret = kmalloc_node(size, kmalloc_flags, node);
+
+ /*
+ * It doesn't really make sense to fallback to vmalloc for sub page
+ * requests
+ */
+ if (ret || size <= PAGE_SIZE)
+ return ret;
+
+ return __vmalloc_node_flags(size, node, flags | __GFP_HIGHMEM);
+}
+EXPORT_SYMBOL(kvmalloc_node);
+
void kvfree(const void *addr)
{
if (is_vmalloc_addr(addr))
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index b52aeed3f58e..33603239560e 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1786,6 +1786,13 @@ fail:
* Allocate enough pages to cover @size from the page level
* allocator with @gfp_mask flags. Map them into contiguous
* kernel virtual space, using a pagetable protection of @prot.
+ *
+ * Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_REPEAT
+ * and __GFP_NOFAIL are not supported
+ *
+ * Any use of gfp flags outside of GFP_KERNEL should be consulted
+ * with mm people.
+ *
*/
static void *__vmalloc_node(unsigned long size, unsigned long align,
gfp_t gfp_mask, pgprot_t prot,
@@ -1802,7 +1809,7 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
}
EXPORT_SYMBOL(__vmalloc);
-static inline void *__vmalloc_node_flags(unsigned long size,
+void *__vmalloc_node_flags(unsigned long size,
int node, gfp_t flags)
{
return __vmalloc_node(size, 1, flags, PAGE_KERNEL,