mm: introduce kv[mz]alloc helpers

Michal Hocko · torvalds · commit a7c3e901a46f · 2017-05-08T17:15:12.000-07:00
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>
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
@@ -177,8 +177,8 @@ static void recalculate_apic_map(struct kvm *kvm)
 		if (kvm_apic_present(vcpu))
 			max_id = max(max_id, kvm_x2apic_id(vcpu->arch.apic));
 
-	new = kvm_kvzalloc(sizeof(struct kvm_apic_map) +
-	                   sizeof(struct kvm_lapic *) * ((u64)max_id + 1));
+	new = kvzalloc(sizeof(struct kvm_apic_map) +
+	                   sizeof(struct kvm_lapic *) * ((u64)max_id + 1), GFP_KERNEL);
 
 	if (!new)
 		goto out;
diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c
@@ -40,8 +40,8 @@ int kvm_page_track_create_memslot(struct kvm_memory_slot *slot,
 	int  i;
 
 	for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) {
-		slot->arch.gfn_track[i] = kvm_kvzalloc(npages *
-					    sizeof(*slot->arch.gfn_track[i]));
+		slot->arch.gfn_track[i] = kvzalloc(npages *
+					    sizeof(*slot->arch.gfn_track[i]), GFP_KERNEL);
 		if (!slot->arch.gfn_track[i])
 			goto track_free;
 	}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
@@ -8199,13 +8199,13 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 				      slot->base_gfn, level) + 1;
 
 		slot->arch.rmap[i] =
-			kvm_kvzalloc(lpages * sizeof(*slot->arch.rmap[i]));
+			kvzalloc(lpages * sizeof(*slot->arch.rmap[i]), GFP_KERNEL);
 		if (!slot->arch.rmap[i])
 			goto out_free;
 		if (i == 0)
 			continue;
 
-		linfo = kvm_kvzalloc(lpages * sizeof(*linfo));
+		linfo = kvzalloc(lpages * sizeof(*linfo), GFP_KERNEL);
 		if (!linfo)
 			goto out_free;
 
diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
@@ -146,12 +146,7 @@ static void *dm_kvzalloc(size_t alloc_size, int node)
 	if (!claim_shared_memory(alloc_size))
 		return NULL;
 
-	if (alloc_size <= KMALLOC_MAX_SIZE) {
-		p = kzalloc_node(alloc_size, GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN, node);
-		if (p)
-			return p;
-	}
-	p = vzalloc_node(alloc_size, node);
+	p = kvzalloc_node(alloc_size, GFP_KERNEL | __GFP_NOMEMALLOC, node);
 	if (p)
 		return p;
 
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
@@ -2393,7 +2393,7 @@ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups)
 		return 0;
 
 	size = roundup_pow_of_two(sizeof(*sbi->s_group_info) * size);
-	new_groupinfo = ext4_kvzalloc(size, GFP_KERNEL);
+	new_groupinfo = kvzalloc(size, GFP_KERNEL);
 	if (!new_groupinfo) {
 		ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group");
 		return -ENOMEM;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
@@ -2153,7 +2153,7 @@ int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup)
 		return 0;
 
 	size = roundup_pow_of_two(size * sizeof(struct flex_groups));
-	new_groups = ext4_kvzalloc(size, GFP_KERNEL);
+	new_groups = kvzalloc(size, GFP_KERNEL);
 	if (!new_groups) {
 		ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups",
 			 size / (int) sizeof(struct flex_groups));
@@ -3887,7 +3887,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			goto failed_mount;
 		}
 	}
-	sbi->s_group_desc = ext4_kvmalloc(db_count *
+	sbi->s_group_desc = kvmalloc(db_count *
 					  sizeof(struct buffer_head *),
 					  GFP_KERNEL);
 	if (sbi->s_group_desc == NULL) {
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
@@ -2005,26 +2005,6 @@ static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
 	return kmalloc(size, flags);
 }
 
-static inline void *f2fs_kvmalloc(size_t size, gfp_t flags)
-{
-	void *ret;
-
-	ret = kmalloc(size, flags | __GFP_NOWARN);
-	if (!ret)
-		ret = __vmalloc(size, flags, PAGE_KERNEL);
-	return ret;
-}
-
-static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
-{
-	void *ret;
-
-	ret = kzalloc(size, flags | __GFP_NOWARN);
-	if (!ret)
-		ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL);
-	return ret;
-}
-
 #define get_inode_mode(i) \
 	((is_inode_flag_set(i, FI_ACL_MODE)) ? \
 	 (F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
@@ -1012,11 +1012,11 @@ static int __exchange_data_block(struct inode *src_inode,
 	while (len) {
 		olen = min((pgoff_t)4 * ADDRS_PER_BLOCK, len);
 
-		src_blkaddr = f2fs_kvzalloc(sizeof(block_t) * olen, GFP_KERNEL);
+		src_blkaddr = kvzalloc(sizeof(block_t) * olen, GFP_KERNEL);
 		if (!src_blkaddr)
 			return -ENOMEM;
 
-		do_replace = f2fs_kvzalloc(sizeof(int) * olen, GFP_KERNEL);
+		do_replace = kvzalloc(sizeof(int) * olen, GFP_KERNEL);
 		if (!do_replace) {
 			kvfree(src_blkaddr);
 			return -ENOMEM;
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
@@ -2621,17 +2621,17 @@ static int init_free_nid_cache(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 
-	nm_i->free_nid_bitmap = f2fs_kvzalloc(nm_i->nat_blocks *
+	nm_i->free_nid_bitmap = kvzalloc(nm_i->nat_blocks *
 					NAT_ENTRY_BITMAP_SIZE, GFP_KERNEL);
 	if (!nm_i->free_nid_bitmap)
 		return -ENOMEM;
 
-	nm_i->nat_block_bitmap = f2fs_kvzalloc(nm_i->nat_blocks / 8,
+	nm_i->nat_block_bitmap = kvzalloc(nm_i->nat_blocks / 8,
 								GFP_KERNEL);
 	if (!nm_i->nat_block_bitmap)
 		return -ENOMEM;
 
-	nm_i->free_nid_count = f2fs_kvzalloc(nm_i->nat_blocks *
+	nm_i->free_nid_count = kvzalloc(nm_i->nat_blocks *
 					sizeof(unsigned short), GFP_KERNEL);
 	if (!nm_i->free_nid_count)
 		return -ENOMEM;
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
@@ -2501,13 +2501,13 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 
 	SM_I(sbi)->sit_info = sit_i;
 
-	sit_i->sentries = f2fs_kvzalloc(MAIN_SEGS(sbi) *
+	sit_i->sentries = kvzalloc(MAIN_SEGS(sbi) *
 					sizeof(struct seg_entry), GFP_KERNEL);
 	if (!sit_i->sentries)
 		return -ENOMEM;
 
 	bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
-	sit_i->dirty_sentries_bitmap = f2fs_kvzalloc(bitmap_size, GFP_KERNEL);
+	sit_i->dirty_sentries_bitmap = kvzalloc(bitmap_size, GFP_KERNEL);
 	if (!sit_i->dirty_sentries_bitmap)
 		return -ENOMEM;
 
@@ -2540,7 +2540,7 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 		return -ENOMEM;
 
 	if (sbi->segs_per_sec > 1) {
-		sit_i->sec_entries = f2fs_kvzalloc(MAIN_SECS(sbi) *
+		sit_i->sec_entries = kvzalloc(MAIN_SECS(sbi) *
 					sizeof(struct sec_entry), GFP_KERNEL);
 		if (!sit_i->sec_entries)
 			return -ENOMEM;
@@ -2591,12 +2591,12 @@ static int build_free_segmap(struct f2fs_sb_info *sbi)
 	SM_I(sbi)->free_info = free_i;
 
 	bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
-	free_i->free_segmap = f2fs_kvmalloc(bitmap_size, GFP_KERNEL);
+	free_i->free_segmap = kvmalloc(bitmap_size, GFP_KERNEL);
 	if (!free_i->free_segmap)
 		return -ENOMEM;
 
 	sec_bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
-	free_i->free_secmap = f2fs_kvmalloc(sec_bitmap_size, GFP_KERNEL);
+	free_i->free_secmap = kvmalloc(sec_bitmap_size, GFP_KERNEL);
 	if (!free_i->free_secmap)
 		return -ENOMEM;
 
@@ -2764,7 +2764,7 @@ static int init_victim_secmap(struct f2fs_sb_info *sbi)
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	unsigned int bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
 
-	dirty_i->victim_secmap = f2fs_kvzalloc(bitmap_size, GFP_KERNEL);
+	dirty_i->victim_secmap = kvzalloc(bitmap_size, GFP_KERNEL);
 	if (!dirty_i->victim_secmap)
 		return -ENOMEM;
 	return 0;
@@ -2786,7 +2786,7 @@ static int build_dirty_segmap(struct f2fs_sb_info *sbi)
 	bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
 
 	for (i = 0; i < NR_DIRTY_TYPE; i++) {
-		dirty_i->dirty_segmap[i] = f2fs_kvzalloc(bitmap_size, GFP_KERNEL);
+		dirty_i->dirty_segmap[i] = kvzalloc(bitmap_size, GFP_KERNEL);
 		if (!dirty_i->dirty_segmap[i])
 			return -ENOMEM;
 	}
diff --git a/fs/seq_file.c b/fs/seq_file.c
@@ -25,21 +25,7 @@ static void seq_set_overflow(struct seq_file *m)
 
 static void *seq_buf_alloc(unsigned long size)
 {
-	void *buf;
-	gfp_t gfp = GFP_KERNEL;
-
-	/*
-	 * For high order allocations, use __GFP_NORETRY to avoid oom-killing -
-	 * it's better to fall back to vmalloc() than to kill things.  For small
-	 * allocations, just use GFP_KERNEL which will oom kill, thus no need
-	 * for vmalloc fallback.
-	 */
-	if (size > PAGE_SIZE)
-		gfp |= __GFP_NORETRY | __GFP_NOWARN;
-	buf = kmalloc(size, gfp);
-	if (!buf && size > PAGE_SIZE)
-		buf = vmalloc(size);
-	return buf;
+	return kvmalloc(size, GFP_KERNEL);
 }
 
 /**
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
@@ -767,8 +767,6 @@ void kvm_arch_check_processor_compat(void *rtn);
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
 
-void *kvm_kvzalloc(unsigned long size);
-
 #ifndef __KVM_HAVE_ARCH_VM_ALLOC
 static inline struct kvm *kvm_arch_alloc_vm(void)
 {
diff --git a/include/linux/mm.h b/include/linux/mm.h
@@ -518,6 +518,20 @@ static inline int is_vmalloc_or_module_addr(const void *x)
 }
 #endif
 
+extern void *kvmalloc_node(size_t size, gfp_t flags, int node);
+static inline void *kvmalloc(size_t size, gfp_t flags)
+{
+	return kvmalloc_node(size, flags, NUMA_NO_NODE);
+}
+static inline void *kvzalloc_node(size_t size, gfp_t flags, int node)
+{
+	return kvmalloc_node(size, flags | __GFP_ZERO, node);
+}
+static inline void *kvzalloc(size_t size, gfp_t flags)
+{
+	return kvmalloc(size, flags | __GFP_ZERO);
+}
+
 extern void kvfree(const void *addr);
 
 static inline atomic_t *compound_mapcount_ptr(struct page *page)
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
@@ -80,6 +80,7 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align,
 			unsigned long start, unsigned long end, gfp_t gfp_mask,
 			pgprot_t prot, unsigned long vm_flags, int node,
 			const void *caller);
+extern void *__vmalloc_node_flags(unsigned long size, int node, gfp_t flags);
 
 extern void vfree(const void *addr);
 extern void vfree_atomic(const void *addr);
diff --git a/ipc/util.c b/ipc/util.c
@@ -403,12 +403,7 @@ void ipc_rmid(struct ipc_ids *ids, struct kern_ipc_perm *ipcp)
  */
 void *ipc_alloc(int size)
 {
-	void *out;
-	if (size > PAGE_SIZE)
-		out = vmalloc(size);
-	else
-		out = kmalloc(size, GFP_KERNEL);
-	return out;
+	return kvmalloc(size, GFP_KERNEL);
 }
 
 /**
diff --git 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
@@ -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
@@ -1786,6 +1786,13 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
  *	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,
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
@@ -98,7 +98,7 @@ static struct aa_loaddata *aa_simple_write_to_buffer(const char __user *userbuf,
 		return ERR_PTR(-ESPIPE);
 
 	/* freed by caller to simple_write_to_buffer */
-	data = kvmalloc(sizeof(*data) + alloc_size);
+	data = kvmalloc(sizeof(*data) + alloc_size, GFP_KERNEL);
 	if (data == NULL)
 		return ERR_PTR(-ENOMEM);
 	kref_init(&data->count);
diff --git a/security/apparmor/include/lib.h b/security/apparmor/include/lib.h
@@ -64,17 +64,6 @@ char *aa_split_fqname(char *args, char **ns_name);
 const char *aa_splitn_fqname(const char *fqname, size_t n, const char **ns_name,
 			     size_t *ns_len);
 void aa_info_message(const char *str);
-void *__aa_kvmalloc(size_t size, gfp_t flags);
-
-static inline void *kvmalloc(size_t size)
-{
-	return __aa_kvmalloc(size, 0);
-}
-
-static inline void *kvzalloc(size_t size)
-{
-	return __aa_kvmalloc(size, __GFP_ZERO);
-}
 
 /**
  * aa_strneq - compare null terminated @str to a non null terminated substring
diff --git a/security/apparmor/lib.c b/security/apparmor/lib.c
diff --git a/security/apparmor/match.c b/security/apparmor/match.c
diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
