linux_dsm_epyc7002/include/linux/vmalloc.h
Michal Hocko a7c3e901a4 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>
2017-05-08 17:15:12 -07:00

198 lines
5.9 KiB
C

#ifndef _LINUX_VMALLOC_H
#define _LINUX_VMALLOC_H
#include <linux/spinlock.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/llist.h>
#include <asm/page.h> /* pgprot_t */
#include <linux/rbtree.h>
struct vm_area_struct; /* vma defining user mapping in mm_types.h */
struct notifier_block; /* in notifier.h */
/* bits in flags of vmalloc's vm_struct below */
#define VM_IOREMAP 0x00000001 /* ioremap() and friends */
#define VM_ALLOC 0x00000002 /* vmalloc() */
#define VM_MAP 0x00000004 /* vmap()ed pages */
#define VM_USERMAP 0x00000008 /* suitable for remap_vmalloc_range */
#define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */
#define VM_NO_GUARD 0x00000040 /* don't add guard page */
#define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */
/* bits [20..32] reserved for arch specific ioremap internals */
/*
* Maximum alignment for ioremap() regions.
* Can be overriden by arch-specific value.
*/
#ifndef IOREMAP_MAX_ORDER
#define IOREMAP_MAX_ORDER (7 + PAGE_SHIFT) /* 128 pages */
#endif
struct vm_struct {
struct vm_struct *next;
void *addr;
unsigned long size;
unsigned long flags;
struct page **pages;
unsigned int nr_pages;
phys_addr_t phys_addr;
const void *caller;
};
struct vmap_area {
unsigned long va_start;
unsigned long va_end;
unsigned long flags;
struct rb_node rb_node; /* address sorted rbtree */
struct list_head list; /* address sorted list */
struct llist_node purge_list; /* "lazy purge" list */
struct vm_struct *vm;
struct rcu_head rcu_head;
};
/*
* Highlevel APIs for driver use
*/
extern void vm_unmap_ram(const void *mem, unsigned int count);
extern void *vm_map_ram(struct page **pages, unsigned int count,
int node, pgprot_t prot);
extern void vm_unmap_aliases(void);
#ifdef CONFIG_MMU
extern void __init vmalloc_init(void);
#else
static inline void vmalloc_init(void)
{
}
#endif
extern void *vmalloc(unsigned long size);
extern void *vzalloc(unsigned long size);
extern void *vmalloc_user(unsigned long size);
extern void *vmalloc_node(unsigned long size, int node);
extern void *vzalloc_node(unsigned long size, int node);
extern void *vmalloc_exec(unsigned long size);
extern void *vmalloc_32(unsigned long size);
extern void *vmalloc_32_user(unsigned long size);
extern void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot);
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);
extern void *vmap(struct page **pages, unsigned int count,
unsigned long flags, pgprot_t prot);
extern void vunmap(const void *addr);
extern int remap_vmalloc_range_partial(struct vm_area_struct *vma,
unsigned long uaddr, void *kaddr,
unsigned long size);
extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
unsigned long pgoff);
void vmalloc_sync_all(void);
/*
* Lowlevel-APIs (not for driver use!)
*/
static inline size_t get_vm_area_size(const struct vm_struct *area)
{
if (!(area->flags & VM_NO_GUARD))
/* return actual size without guard page */
return area->size - PAGE_SIZE;
else
return area->size;
}
extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags);
extern struct vm_struct *get_vm_area_caller(unsigned long size,
unsigned long flags, const void *caller);
extern struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
unsigned long start, unsigned long end);
extern struct vm_struct *__get_vm_area_caller(unsigned long size,
unsigned long flags,
unsigned long start, unsigned long end,
const void *caller);
extern struct vm_struct *remove_vm_area(const void *addr);
extern struct vm_struct *find_vm_area(const void *addr);
extern int map_vm_area(struct vm_struct *area, pgprot_t prot,
struct page **pages);
#ifdef CONFIG_MMU
extern int map_kernel_range_noflush(unsigned long start, unsigned long size,
pgprot_t prot, struct page **pages);
extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size);
extern void unmap_kernel_range(unsigned long addr, unsigned long size);
#else
static inline int
map_kernel_range_noflush(unsigned long start, unsigned long size,
pgprot_t prot, struct page **pages)
{
return size >> PAGE_SHIFT;
}
static inline void
unmap_kernel_range_noflush(unsigned long addr, unsigned long size)
{
}
static inline void
unmap_kernel_range(unsigned long addr, unsigned long size)
{
}
#endif
/* Allocate/destroy a 'vmalloc' VM area. */
extern struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes);
extern void free_vm_area(struct vm_struct *area);
/* for /dev/kmem */
extern long vread(char *buf, char *addr, unsigned long count);
extern long vwrite(char *buf, char *addr, unsigned long count);
/*
* Internals. Dont't use..
*/
extern struct list_head vmap_area_list;
extern __init void vm_area_add_early(struct vm_struct *vm);
extern __init void vm_area_register_early(struct vm_struct *vm, size_t align);
#ifdef CONFIG_SMP
# ifdef CONFIG_MMU
struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
const size_t *sizes, int nr_vms,
size_t align);
void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms);
# else
static inline struct vm_struct **
pcpu_get_vm_areas(const unsigned long *offsets,
const size_t *sizes, int nr_vms,
size_t align)
{
return NULL;
}
static inline void
pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms)
{
}
# endif
#endif
#ifdef CONFIG_MMU
#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START)
#else
#define VMALLOC_TOTAL 0UL
#endif
int register_vmap_purge_notifier(struct notifier_block *nb);
int unregister_vmap_purge_notifier(struct notifier_block *nb);
#endif /* _LINUX_VMALLOC_H */