![Roman Pen](/assets/img/avatar_default.png)
Recently I came across high fragmentation of vm_map_ram allocator:
vmap_block has free space, but still new blocks continue to appear.
Further investigation showed that certain mapping/unmapping sequences
can exhaust vmalloc space. On small 32bit systems that's not a big
problem, cause purging will be called soon on a first allocation failure
(alloc_vmap_area), but on 64bit machines, e.g. x86_64 has 45 bits of
vmalloc space, that can be a disaster.
1) I came up with a simple allocation sequence, which exhausts virtual
space very quickly:
while (iters) {
/* Map/unmap big chunk */
vaddr = vm_map_ram(pages, 16, -1, PAGE_KERNEL);
vm_unmap_ram(vaddr, 16);
/* Map/unmap small chunks.
*
* -1 for hole, which should be left at the end of each block
* to keep it partially used, with some free space available */
for (i = 0; i < (VMAP_BBMAP_BITS - 16) / 8 - 1; i++) {
vaddr = vm_map_ram(pages, 8, -1, PAGE_KERNEL);
vm_unmap_ram(vaddr, 8);
}
}
The idea behind is simple:
1. We have to map a big chunk, e.g. 16 pages.
2. Then we have to occupy the remaining space with smaller chunks, i.e.
8 pages. At the end small hole should remain to keep block in free list,
but do not let big chunk to occupy remaining space.
3. Goto 1 - allocation request of 16 pages can't be completed (only 8 slots
are left free in the block in the #2 step), new block will be allocated,
all further requests will lay into newly allocated block.
To have some measurement numbers for all further tests I setup ftrace and
enabled 4 basic calls in a function profile:
echo vm_map_ram > /sys/kernel/debug/tracing/set_ftrace_filter;
echo alloc_vmap_area >> /sys/kernel/debug/tracing/set_ftrace_filter;
echo vm_unmap_ram >> /sys/kernel/debug/tracing/set_ftrace_filter;
echo free_vmap_block >> /sys/kernel/debug/tracing/set_ftrace_filter;
So for this scenario I got these results:
BEFORE (all new blocks are put to the head of a free list)
# cat /sys/kernel/debug/tracing/trace_stat/function0
Function Hit Time Avg s^2
-------- --- ---- --- ---
vm_map_ram 126000 30683.30 us 0.243 us 30819.36 us
vm_unmap_ram 126000 22003.24 us 0.174 us 340.886 us
alloc_vmap_area 1000 4132.065 us 4.132 us 0.903 us
AFTER (all new blocks are put to the tail of a free list)
# cat /sys/kernel/debug/tracing/trace_stat/function0
Function Hit Time Avg s^2
-------- --- ---- --- ---
vm_map_ram 126000 28713.13 us 0.227 us 24944.70 us
vm_unmap_ram 126000 20403.96 us 0.161 us 1429.872 us
alloc_vmap_area 993 3916.795 us 3.944 us 29.370 us
free_vmap_block 992 654.157 us 0.659 us 1.273 us
SUMMARY:
The most interesting numbers in those tables are numbers of block
allocations and deallocations: alloc_vmap_area and free_vmap_block
calls, which show that before the change blocks were not freed, and
virtual space and physical memory (vmap_block structure allocations,
etc) were consumed.
Average time which were spent in vm_map_ram/vm_unmap_ram became slightly
better. That can be explained with a reasonable amount of blocks in a
free list, which we need to iterate to find a suitable free block.
2) Another scenario is a random allocation:
while (iters) {
/* Randomly take number from a range [1..32/64] */
nr = rand(1, VMAP_MAX_ALLOC);
vaddr = vm_map_ram(pages, nr, -1, PAGE_KERNEL);
vm_unmap_ram(vaddr, nr);
}
I chose mersenne twister PRNG to generate persistent random state to
guarantee that both runs have the same random sequence. For each
vm_map_ram call random number from [1..32/64] was taken to represent
amount of pages which I do map.
I did 10'000 vm_map_ram calls and got these two tables:
BEFORE (all new blocks are put to the head of a free list)
# cat /sys/kernel/debug/tracing/trace_stat/function0
Function Hit Time Avg s^2
-------- --- ---- --- ---
vm_map_ram 10000 10170.01 us 1.017 us 993.609 us
vm_unmap_ram 10000 5321.823 us 0.532 us 59.789 us
alloc_vmap_area 420 2150.239 us 5.119 us 3.307 us
free_vmap_block 37 159.587 us 4.313 us 134.344 us
AFTER (all new blocks are put to the tail of a free list)
# cat /sys/kernel/debug/tracing/trace_stat/function0
Function Hit Time Avg s^2
-------- --- ---- --- ---
vm_map_ram 10000 7745.637 us 0.774 us 395.229 us
vm_unmap_ram 10000 5460.573 us 0.546 us 67.187 us
alloc_vmap_area 414 2201.650 us 5.317 us 5.591 us
free_vmap_block 412 574.421 us 1.394 us 15.138 us
SUMMARY:
'BEFORE' table shows, that 420 blocks were allocated and only 37 were
freed. Remained 383 blocks are still in a free list, consuming virtual
space and physical memory.
'AFTER' table shows, that 414 blocks were allocated and 412 were really
freed. 2 blocks remained in a free list.
So fragmentation was dramatically reduced. Why? Because when we put
newly allocated block to the head, all further requests will occupy new
block, regardless remained space in other blocks. In this scenario all
requests come randomly. Eventually remained free space will be less
than requested size, free list will be iterated and it is possible that
nothing will be found there - finally new block will be created. So
exhaustion in random scenario happens for the maximum possible
allocation size: 32 pages for 32-bit system and 64 pages for 64-bit
system.
Also average cost of vm_map_ram was reduced from 1.017 us to 0.774 us.
Again this can be explained by iteration through smaller list of free
blocks.
3) Next simple scenario is a sequential allocation, when the allocation
order is increased for each block. This scenario forces allocator to
reach maximum amount of partially free blocks in a free list:
while (iters) {
/* Populate free list with blocks with remaining space */
for (order = 0; order <= ilog2(VMAP_MAX_ALLOC); order++) {
nr = VMAP_BBMAP_BITS / (1 << order);
/* Leave a hole */
nr -= 1;
for (i = 0; i < nr; i++) {
vaddr = vm_map_ram(pages, (1 << order), -1, PAGE_KERNEL);
vm_unmap_ram(vaddr, (1 << order));
}
/* Completely occupy blocks from a free list */
for (order = 0; order <= ilog2(VMAP_MAX_ALLOC); order++) {
vaddr = vm_map_ram(pages, (1 << order), -1, PAGE_KERNEL);
vm_unmap_ram(vaddr, (1 << order));
}
}
Results which I got:
BEFORE (all new blocks are put to the head of a free list)
# cat /sys/kernel/debug/tracing/trace_stat/function0
Function Hit Time Avg s^2
-------- --- ---- --- ---
vm_map_ram 2032000 399545.2 us 0.196 us 467123.7 us
vm_unmap_ram 2032000 363225.7 us 0.178 us 111405.9 us
alloc_vmap_area 7001 30627.76 us 4.374 us 495.755 us
free_vmap_block 6993 7011.685 us 1.002 us 159.090 us
AFTER (all new blocks are put to the tail of a free list)
# cat /sys/kernel/debug/tracing/trace_stat/function0
Function Hit Time Avg s^2
-------- --- ---- --- ---
vm_map_ram 2032000 394259.7 us 0.194 us 589395.9 us
vm_unmap_ram 2032000 292500.7 us 0.143 us 94181.08 us
alloc_vmap_area 7000 31103.11 us 4.443 us 703.225 us
free_vmap_block 7000 6750.844 us 0.964 us 119.112 us
SUMMARY:
No surprises here, almost all numbers are the same.
Fixing this fragmentation problem I also did some improvements in a
allocation logic of a new vmap block: occupy block immediately and get
rid of extra search in a free list.
Also I replaced dirty bitmap with min/max dirty range values to make the
logic simpler and slightly faster, since two longs comparison costs
less, than loop thru bitmap.
This patchset raises several questions:
Q: Think the problem you comments is already known so that I wrote comments
about it as "it could consume lots of address space through fragmentation".
Could you tell me about your situation and reason why it should be avoided?
Gioh Kim
A: Indeed, there was a commit 364376383
which adds explicit comment about
fragmentation. But fragmentation which is described in this comment caused
by mixing of long-lived and short-lived objects, when a whole block is pinned
in memory because some page slots are still in use. But here I am talking
about blocks which are free, nobody uses them, and allocator keeps them alive
forever, continuously allocating new blocks.
Q: I think that if you put newly allocated block to the tail of a free
list, below example would results in enormous performance degradation.
new block: 1MB (256 pages)
while (iters--) {
vm_map_ram(3 or something else not dividable for 256) * 85
vm_unmap_ram(3) * 85
}
On every iteration, it needs newly allocated block and it is put to the
tail of a free list so finding it consumes large amount of time.
Joonsoo Kim
A: Second patch in current patchset gets rid of extra search in a free list,
so new block will be immediately occupied..
Also, the scenario above is impossible, cause vm_map_ram allocates virtual
range in orders, i.e. 2^n. I.e. passing 3 to vm_map_ram you will allocate
4 slots in a block and 256 slots (capacity of a block) of course dividable
on 4, so block will be completely occupied.
But there is a worst case which we can achieve: each free block has a hole
equal to order size.
The maximum size of allocation is 64 pages for 64-bit system
(if you try to map more, original alloc_vmap_area will be called).
So the maximum order is 6. That means that worst case, before allocator
makes a decision to allocate a new block, is to iterate 7 blocks:
HEAD
1st block - has 1 page slot free (order 0)
2nd block - has 2 page slots free (order 1)
3rd block - has 4 page slots free (order 2)
4th block - has 8 page slots free (order 3)
5th block - has 16 page slots free (order 4)
6th block - has 32 page slots free (order 5)
7th block - has 64 page slots free (order 6)
TAIL
So the worst scenario on 64-bit system is that each CPU queue can have 7
blocks in a free list.
This can happen only and only if you allocate blocks increasing the order.
(as I did in the function written in the comment of the first patch)
This is weird and rare case, but still it is possible. Afterwards you will
get 7 blocks in a list.
All further requests should be placed in a newly allocated block or some
free slots should be found in a free list.
Seems it does not look dramatically awful.
This patch (of 3):
If suitable block can't be found, new block is allocated and put into a
head of a free list, so on next iteration this new block will be found
first.
That's bad, because old blocks in a free list will not get a chance to be
fully used, thus fragmentation will grow.
Let's consider this simple example:
#1 We have one block in a free list which is partially used, and where only
one page is free:
HEAD |xxxxxxxxx-| TAIL
^
free space for 1 page, order 0
#2 New allocation request of order 1 (2 pages) comes, new block is allocated
since we do not have free space to complete this request. New block is put
into a head of a free list:
HEAD |----------|xxxxxxxxx-| TAIL
#3 Two pages were occupied in a new found block:
HEAD |xx--------|xxxxxxxxx-| TAIL
^
two pages mapped here
#4 New allocation request of order 0 (1 page) comes. Block, which was created
on #2 step, is located at the beginning of a free list, so it will be found
first:
HEAD |xxX-------|xxxxxxxxx-| TAIL
^ ^
page mapped here, but better to use this hole
It is obvious, that it is better to complete request of #4 step using the
old block, where free space is left, because in other case fragmentation
will be highly increased.
But fragmentation is not only the case. The worst thing is that I can
easily create scenario, when the whole vmalloc space is exhausted by
blocks, which are not used, but already dirty and have several free pages.
Let's consider this function which execution should be pinned to one CPU:
static void exhaust_virtual_space(struct page *pages[16], int iters)
{
/* Firstly we have to map a big chunk, e.g. 16 pages.
* Then we have to occupy the remaining space with smaller
* chunks, i.e. 8 pages. At the end small hole should remain.
* So at the end of our allocation sequence block looks like
* this:
* XX big chunk
* |XXxxxxxxx-| x small chunk
* - hole, which is enough for a small chunk,
* but is not enough for a big chunk
*/
while (iters--) {
int i;
void *vaddr;
/* Map/unmap big chunk */
vaddr = vm_map_ram(pages, 16, -1, PAGE_KERNEL);
vm_unmap_ram(vaddr, 16);
/* Map/unmap small chunks.
*
* -1 for hole, which should be left at the end of each block
* to keep it partially used, with some free space available */
for (i = 0; i < (VMAP_BBMAP_BITS - 16) / 8 - 1; i++) {
vaddr = vm_map_ram(pages, 8, -1, PAGE_KERNEL);
vm_unmap_ram(vaddr, 8);
}
}
}
On every iteration new block (1MB of vm area in my case) will be
allocated and then will be occupied, without attempt to resolve small
allocation request using previously allocated blocks in a free list.
In case of random allocation (size should be randomly taken from the
range [1..64] in 64-bit case or [1..32] in 32-bit case) situation is the
same: new blocks continue to appear if maximum possible allocation size
(32 or 64) passed to the allocator, because all remaining blocks in a
free list do not have enough free space to complete this allocation
request.
In summary if new blocks are put into the head of a free list eventually
virtual space will be exhausted.
In current patch I simply put newly allocated block to the tail of a
free list, thus reduce fragmentation, giving a chance to resolve
allocation request using older blocks with possible holes left.
Signed-off-by: Roman Pen <r.peniaev@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: David Rientjes <rientjes@google.com>
Cc: WANG Chao <chaowang@redhat.com>
Cc: Fabian Frederick <fabf@skynet.be>
Cc: Christoph Lameter <cl@linux.com>
Cc: Gioh Kim <gioh.kim@lge.com>
Cc: Rob Jones <rob.jones@codethink.co.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2725 lines
68 KiB
C
2725 lines
68 KiB
C
/*
|
|
* linux/mm/vmalloc.c
|
|
*
|
|
* Copyright (C) 1993 Linus Torvalds
|
|
* Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
|
|
* SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000
|
|
* Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002
|
|
* Numa awareness, Christoph Lameter, SGI, June 2005
|
|
*/
|
|
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/module.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/seq_file.h>
|
|
#include <linux/debugobjects.h>
|
|
#include <linux/kallsyms.h>
|
|
#include <linux/list.h>
|
|
#include <linux/rbtree.h>
|
|
#include <linux/radix-tree.h>
|
|
#include <linux/rcupdate.h>
|
|
#include <linux/pfn.h>
|
|
#include <linux/kmemleak.h>
|
|
#include <linux/atomic.h>
|
|
#include <linux/compiler.h>
|
|
#include <linux/llist.h>
|
|
#include <linux/bitops.h>
|
|
|
|
#include <asm/uaccess.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/shmparam.h>
|
|
|
|
struct vfree_deferred {
|
|
struct llist_head list;
|
|
struct work_struct wq;
|
|
};
|
|
static DEFINE_PER_CPU(struct vfree_deferred, vfree_deferred);
|
|
|
|
static void __vunmap(const void *, int);
|
|
|
|
static void free_work(struct work_struct *w)
|
|
{
|
|
struct vfree_deferred *p = container_of(w, struct vfree_deferred, wq);
|
|
struct llist_node *llnode = llist_del_all(&p->list);
|
|
while (llnode) {
|
|
void *p = llnode;
|
|
llnode = llist_next(llnode);
|
|
__vunmap(p, 1);
|
|
}
|
|
}
|
|
|
|
/*** Page table manipulation functions ***/
|
|
|
|
static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end)
|
|
{
|
|
pte_t *pte;
|
|
|
|
pte = pte_offset_kernel(pmd, addr);
|
|
do {
|
|
pte_t ptent = ptep_get_and_clear(&init_mm, addr, pte);
|
|
WARN_ON(!pte_none(ptent) && !pte_present(ptent));
|
|
} while (pte++, addr += PAGE_SIZE, addr != end);
|
|
}
|
|
|
|
static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end)
|
|
{
|
|
pmd_t *pmd;
|
|
unsigned long next;
|
|
|
|
pmd = pmd_offset(pud, addr);
|
|
do {
|
|
next = pmd_addr_end(addr, end);
|
|
if (pmd_clear_huge(pmd))
|
|
continue;
|
|
if (pmd_none_or_clear_bad(pmd))
|
|
continue;
|
|
vunmap_pte_range(pmd, addr, next);
|
|
} while (pmd++, addr = next, addr != end);
|
|
}
|
|
|
|
static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end)
|
|
{
|
|
pud_t *pud;
|
|
unsigned long next;
|
|
|
|
pud = pud_offset(pgd, addr);
|
|
do {
|
|
next = pud_addr_end(addr, end);
|
|
if (pud_clear_huge(pud))
|
|
continue;
|
|
if (pud_none_or_clear_bad(pud))
|
|
continue;
|
|
vunmap_pmd_range(pud, addr, next);
|
|
} while (pud++, addr = next, addr != end);
|
|
}
|
|
|
|
static void vunmap_page_range(unsigned long addr, unsigned long end)
|
|
{
|
|
pgd_t *pgd;
|
|
unsigned long next;
|
|
|
|
BUG_ON(addr >= end);
|
|
pgd = pgd_offset_k(addr);
|
|
do {
|
|
next = pgd_addr_end(addr, end);
|
|
if (pgd_none_or_clear_bad(pgd))
|
|
continue;
|
|
vunmap_pud_range(pgd, addr, next);
|
|
} while (pgd++, addr = next, addr != end);
|
|
}
|
|
|
|
static int vmap_pte_range(pmd_t *pmd, unsigned long addr,
|
|
unsigned long end, pgprot_t prot, struct page **pages, int *nr)
|
|
{
|
|
pte_t *pte;
|
|
|
|
/*
|
|
* nr is a running index into the array which helps higher level
|
|
* callers keep track of where we're up to.
|
|
*/
|
|
|
|
pte = pte_alloc_kernel(pmd, addr);
|
|
if (!pte)
|
|
return -ENOMEM;
|
|
do {
|
|
struct page *page = pages[*nr];
|
|
|
|
if (WARN_ON(!pte_none(*pte)))
|
|
return -EBUSY;
|
|
if (WARN_ON(!page))
|
|
return -ENOMEM;
|
|
set_pte_at(&init_mm, addr, pte, mk_pte(page, prot));
|
|
(*nr)++;
|
|
} while (pte++, addr += PAGE_SIZE, addr != end);
|
|
return 0;
|
|
}
|
|
|
|
static int vmap_pmd_range(pud_t *pud, unsigned long addr,
|
|
unsigned long end, pgprot_t prot, struct page **pages, int *nr)
|
|
{
|
|
pmd_t *pmd;
|
|
unsigned long next;
|
|
|
|
pmd = pmd_alloc(&init_mm, pud, addr);
|
|
if (!pmd)
|
|
return -ENOMEM;
|
|
do {
|
|
next = pmd_addr_end(addr, end);
|
|
if (vmap_pte_range(pmd, addr, next, prot, pages, nr))
|
|
return -ENOMEM;
|
|
} while (pmd++, addr = next, addr != end);
|
|
return 0;
|
|
}
|
|
|
|
static int vmap_pud_range(pgd_t *pgd, unsigned long addr,
|
|
unsigned long end, pgprot_t prot, struct page **pages, int *nr)
|
|
{
|
|
pud_t *pud;
|
|
unsigned long next;
|
|
|
|
pud = pud_alloc(&init_mm, pgd, addr);
|
|
if (!pud)
|
|
return -ENOMEM;
|
|
do {
|
|
next = pud_addr_end(addr, end);
|
|
if (vmap_pmd_range(pud, addr, next, prot, pages, nr))
|
|
return -ENOMEM;
|
|
} while (pud++, addr = next, addr != end);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Set up page tables in kva (addr, end). The ptes shall have prot "prot", and
|
|
* will have pfns corresponding to the "pages" array.
|
|
*
|
|
* Ie. pte at addr+N*PAGE_SIZE shall point to pfn corresponding to pages[N]
|
|
*/
|
|
static int vmap_page_range_noflush(unsigned long start, unsigned long end,
|
|
pgprot_t prot, struct page **pages)
|
|
{
|
|
pgd_t *pgd;
|
|
unsigned long next;
|
|
unsigned long addr = start;
|
|
int err = 0;
|
|
int nr = 0;
|
|
|
|
BUG_ON(addr >= end);
|
|
pgd = pgd_offset_k(addr);
|
|
do {
|
|
next = pgd_addr_end(addr, end);
|
|
err = vmap_pud_range(pgd, addr, next, prot, pages, &nr);
|
|
if (err)
|
|
return err;
|
|
} while (pgd++, addr = next, addr != end);
|
|
|
|
return nr;
|
|
}
|
|
|
|
static int vmap_page_range(unsigned long start, unsigned long end,
|
|
pgprot_t prot, struct page **pages)
|
|
{
|
|
int ret;
|
|
|
|
ret = vmap_page_range_noflush(start, end, prot, pages);
|
|
flush_cache_vmap(start, end);
|
|
return ret;
|
|
}
|
|
|
|
int is_vmalloc_or_module_addr(const void *x)
|
|
{
|
|
/*
|
|
* ARM, x86-64 and sparc64 put modules in a special place,
|
|
* and fall back on vmalloc() if that fails. Others
|
|
* just put it in the vmalloc space.
|
|
*/
|
|
#if defined(CONFIG_MODULES) && defined(MODULES_VADDR)
|
|
unsigned long addr = (unsigned long)x;
|
|
if (addr >= MODULES_VADDR && addr < MODULES_END)
|
|
return 1;
|
|
#endif
|
|
return is_vmalloc_addr(x);
|
|
}
|
|
|
|
/*
|
|
* Walk a vmap address to the struct page it maps.
|
|
*/
|
|
struct page *vmalloc_to_page(const void *vmalloc_addr)
|
|
{
|
|
unsigned long addr = (unsigned long) vmalloc_addr;
|
|
struct page *page = NULL;
|
|
pgd_t *pgd = pgd_offset_k(addr);
|
|
|
|
/*
|
|
* XXX we might need to change this if we add VIRTUAL_BUG_ON for
|
|
* architectures that do not vmalloc module space
|
|
*/
|
|
VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr));
|
|
|
|
if (!pgd_none(*pgd)) {
|
|
pud_t *pud = pud_offset(pgd, addr);
|
|
if (!pud_none(*pud)) {
|
|
pmd_t *pmd = pmd_offset(pud, addr);
|
|
if (!pmd_none(*pmd)) {
|
|
pte_t *ptep, pte;
|
|
|
|
ptep = pte_offset_map(pmd, addr);
|
|
pte = *ptep;
|
|
if (pte_present(pte))
|
|
page = pte_page(pte);
|
|
pte_unmap(ptep);
|
|
}
|
|
}
|
|
}
|
|
return page;
|
|
}
|
|
EXPORT_SYMBOL(vmalloc_to_page);
|
|
|
|
/*
|
|
* Map a vmalloc()-space virtual address to the physical page frame number.
|
|
*/
|
|
unsigned long vmalloc_to_pfn(const void *vmalloc_addr)
|
|
{
|
|
return page_to_pfn(vmalloc_to_page(vmalloc_addr));
|
|
}
|
|
EXPORT_SYMBOL(vmalloc_to_pfn);
|
|
|
|
|
|
/*** Global kva allocator ***/
|
|
|
|
#define VM_LAZY_FREE 0x01
|
|
#define VM_LAZY_FREEING 0x02
|
|
#define VM_VM_AREA 0x04
|
|
|
|
static DEFINE_SPINLOCK(vmap_area_lock);
|
|
/* Export for kexec only */
|
|
LIST_HEAD(vmap_area_list);
|
|
static struct rb_root vmap_area_root = RB_ROOT;
|
|
|
|
/* The vmap cache globals are protected by vmap_area_lock */
|
|
static struct rb_node *free_vmap_cache;
|
|
static unsigned long cached_hole_size;
|
|
static unsigned long cached_vstart;
|
|
static unsigned long cached_align;
|
|
|
|
static unsigned long vmap_area_pcpu_hole;
|
|
|
|
static struct vmap_area *__find_vmap_area(unsigned long addr)
|
|
{
|
|
struct rb_node *n = vmap_area_root.rb_node;
|
|
|
|
while (n) {
|
|
struct vmap_area *va;
|
|
|
|
va = rb_entry(n, struct vmap_area, rb_node);
|
|
if (addr < va->va_start)
|
|
n = n->rb_left;
|
|
else if (addr >= va->va_end)
|
|
n = n->rb_right;
|
|
else
|
|
return va;
|
|
}
|
|
|
|
return NULL;
|
|
}
|
|
|
|
static void __insert_vmap_area(struct vmap_area *va)
|
|
{
|
|
struct rb_node **p = &vmap_area_root.rb_node;
|
|
struct rb_node *parent = NULL;
|
|
struct rb_node *tmp;
|
|
|
|
while (*p) {
|
|
struct vmap_area *tmp_va;
|
|
|
|
parent = *p;
|
|
tmp_va = rb_entry(parent, struct vmap_area, rb_node);
|
|
if (va->va_start < tmp_va->va_end)
|
|
p = &(*p)->rb_left;
|
|
else if (va->va_end > tmp_va->va_start)
|
|
p = &(*p)->rb_right;
|
|
else
|
|
BUG();
|
|
}
|
|
|
|
rb_link_node(&va->rb_node, parent, p);
|
|
rb_insert_color(&va->rb_node, &vmap_area_root);
|
|
|
|
/* address-sort this list */
|
|
tmp = rb_prev(&va->rb_node);
|
|
if (tmp) {
|
|
struct vmap_area *prev;
|
|
prev = rb_entry(tmp, struct vmap_area, rb_node);
|
|
list_add_rcu(&va->list, &prev->list);
|
|
} else
|
|
list_add_rcu(&va->list, &vmap_area_list);
|
|
}
|
|
|
|
static void purge_vmap_area_lazy(void);
|
|
|
|
/*
|
|
* Allocate a region of KVA of the specified size and alignment, within the
|
|
* vstart and vend.
|
|
*/
|
|
static struct vmap_area *alloc_vmap_area(unsigned long size,
|
|
unsigned long align,
|
|
unsigned long vstart, unsigned long vend,
|
|
int node, gfp_t gfp_mask)
|
|
{
|
|
struct vmap_area *va;
|
|
struct rb_node *n;
|
|
unsigned long addr;
|
|
int purged = 0;
|
|
struct vmap_area *first;
|
|
|
|
BUG_ON(!size);
|
|
BUG_ON(size & ~PAGE_MASK);
|
|
BUG_ON(!is_power_of_2(align));
|
|
|
|
va = kmalloc_node(sizeof(struct vmap_area),
|
|
gfp_mask & GFP_RECLAIM_MASK, node);
|
|
if (unlikely(!va))
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
/*
|
|
* Only scan the relevant parts containing pointers to other objects
|
|
* to avoid false negatives.
|
|
*/
|
|
kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask & GFP_RECLAIM_MASK);
|
|
|
|
retry:
|
|
spin_lock(&vmap_area_lock);
|
|
/*
|
|
* Invalidate cache if we have more permissive parameters.
|
|
* cached_hole_size notes the largest hole noticed _below_
|
|
* the vmap_area cached in free_vmap_cache: if size fits
|
|
* into that hole, we want to scan from vstart to reuse
|
|
* the hole instead of allocating above free_vmap_cache.
|
|
* Note that __free_vmap_area may update free_vmap_cache
|
|
* without updating cached_hole_size or cached_align.
|
|
*/
|
|
if (!free_vmap_cache ||
|
|
size < cached_hole_size ||
|
|
vstart < cached_vstart ||
|
|
align < cached_align) {
|
|
nocache:
|
|
cached_hole_size = 0;
|
|
free_vmap_cache = NULL;
|
|
}
|
|
/* record if we encounter less permissive parameters */
|
|
cached_vstart = vstart;
|
|
cached_align = align;
|
|
|
|
/* find starting point for our search */
|
|
if (free_vmap_cache) {
|
|
first = rb_entry(free_vmap_cache, struct vmap_area, rb_node);
|
|
addr = ALIGN(first->va_end, align);
|
|
if (addr < vstart)
|
|
goto nocache;
|
|
if (addr + size < addr)
|
|
goto overflow;
|
|
|
|
} else {
|
|
addr = ALIGN(vstart, align);
|
|
if (addr + size < addr)
|
|
goto overflow;
|
|
|
|
n = vmap_area_root.rb_node;
|
|
first = NULL;
|
|
|
|
while (n) {
|
|
struct vmap_area *tmp;
|
|
tmp = rb_entry(n, struct vmap_area, rb_node);
|
|
if (tmp->va_end >= addr) {
|
|
first = tmp;
|
|
if (tmp->va_start <= addr)
|
|
break;
|
|
n = n->rb_left;
|
|
} else
|
|
n = n->rb_right;
|
|
}
|
|
|
|
if (!first)
|
|
goto found;
|
|
}
|
|
|
|
/* from the starting point, walk areas until a suitable hole is found */
|
|
while (addr + size > first->va_start && addr + size <= vend) {
|
|
if (addr + cached_hole_size < first->va_start)
|
|
cached_hole_size = first->va_start - addr;
|
|
addr = ALIGN(first->va_end, align);
|
|
if (addr + size < addr)
|
|
goto overflow;
|
|
|
|
if (list_is_last(&first->list, &vmap_area_list))
|
|
goto found;
|
|
|
|
first = list_entry(first->list.next,
|
|
struct vmap_area, list);
|
|
}
|
|
|
|
found:
|
|
if (addr + size > vend)
|
|
goto overflow;
|
|
|
|
va->va_start = addr;
|
|
va->va_end = addr + size;
|
|
va->flags = 0;
|
|
__insert_vmap_area(va);
|
|
free_vmap_cache = &va->rb_node;
|
|
spin_unlock(&vmap_area_lock);
|
|
|
|
BUG_ON(va->va_start & (align-1));
|
|
BUG_ON(va->va_start < vstart);
|
|
BUG_ON(va->va_end > vend);
|
|
|
|
return va;
|
|
|
|
overflow:
|
|
spin_unlock(&vmap_area_lock);
|
|
if (!purged) {
|
|
purge_vmap_area_lazy();
|
|
purged = 1;
|
|
goto retry;
|
|
}
|
|
if (printk_ratelimit())
|
|
pr_warn("vmap allocation for size %lu failed: "
|
|
"use vmalloc=<size> to increase size.\n", size);
|
|
kfree(va);
|
|
return ERR_PTR(-EBUSY);
|
|
}
|
|
|
|
static void __free_vmap_area(struct vmap_area *va)
|
|
{
|
|
BUG_ON(RB_EMPTY_NODE(&va->rb_node));
|
|
|
|
if (free_vmap_cache) {
|
|
if (va->va_end < cached_vstart) {
|
|
free_vmap_cache = NULL;
|
|
} else {
|
|
struct vmap_area *cache;
|
|
cache = rb_entry(free_vmap_cache, struct vmap_area, rb_node);
|
|
if (va->va_start <= cache->va_start) {
|
|
free_vmap_cache = rb_prev(&va->rb_node);
|
|
/*
|
|
* We don't try to update cached_hole_size or
|
|
* cached_align, but it won't go very wrong.
|
|
*/
|
|
}
|
|
}
|
|
}
|
|
rb_erase(&va->rb_node, &vmap_area_root);
|
|
RB_CLEAR_NODE(&va->rb_node);
|
|
list_del_rcu(&va->list);
|
|
|
|
/*
|
|
* Track the highest possible candidate for pcpu area
|
|
* allocation. Areas outside of vmalloc area can be returned
|
|
* here too, consider only end addresses which fall inside
|
|
* vmalloc area proper.
|
|
*/
|
|
if (va->va_end > VMALLOC_START && va->va_end <= VMALLOC_END)
|
|
vmap_area_pcpu_hole = max(vmap_area_pcpu_hole, va->va_end);
|
|
|
|
kfree_rcu(va, rcu_head);
|
|
}
|
|
|
|
/*
|
|
* Free a region of KVA allocated by alloc_vmap_area
|
|
*/
|
|
static void free_vmap_area(struct vmap_area *va)
|
|
{
|
|
spin_lock(&vmap_area_lock);
|
|
__free_vmap_area(va);
|
|
spin_unlock(&vmap_area_lock);
|
|
}
|
|
|
|
/*
|
|
* Clear the pagetable entries of a given vmap_area
|
|
*/
|
|
static void unmap_vmap_area(struct vmap_area *va)
|
|
{
|
|
vunmap_page_range(va->va_start, va->va_end);
|
|
}
|
|
|
|
static void vmap_debug_free_range(unsigned long start, unsigned long end)
|
|
{
|
|
/*
|
|
* Unmap page tables and force a TLB flush immediately if
|
|
* CONFIG_DEBUG_PAGEALLOC is set. This catches use after free
|
|
* bugs similarly to those in linear kernel virtual address
|
|
* space after a page has been freed.
|
|
*
|
|
* All the lazy freeing logic is still retained, in order to
|
|
* minimise intrusiveness of this debugging feature.
|
|
*
|
|
* This is going to be *slow* (linear kernel virtual address
|
|
* debugging doesn't do a broadcast TLB flush so it is a lot
|
|
* faster).
|
|
*/
|
|
#ifdef CONFIG_DEBUG_PAGEALLOC
|
|
vunmap_page_range(start, end);
|
|
flush_tlb_kernel_range(start, end);
|
|
#endif
|
|
}
|
|
|
|
/*
|
|
* lazy_max_pages is the maximum amount of virtual address space we gather up
|
|
* before attempting to purge with a TLB flush.
|
|
*
|
|
* There is a tradeoff here: a larger number will cover more kernel page tables
|
|
* and take slightly longer to purge, but it will linearly reduce the number of
|
|
* global TLB flushes that must be performed. It would seem natural to scale
|
|
* this number up linearly with the number of CPUs (because vmapping activity
|
|
* could also scale linearly with the number of CPUs), however it is likely
|
|
* that in practice, workloads might be constrained in other ways that mean
|
|
* vmap activity will not scale linearly with CPUs. Also, I want to be
|
|
* conservative and not introduce a big latency on huge systems, so go with
|
|
* a less aggressive log scale. It will still be an improvement over the old
|
|
* code, and it will be simple to change the scale factor if we find that it
|
|
* becomes a problem on bigger systems.
|
|
*/
|
|
static unsigned long lazy_max_pages(void)
|
|
{
|
|
unsigned int log;
|
|
|
|
log = fls(num_online_cpus());
|
|
|
|
return log * (32UL * 1024 * 1024 / PAGE_SIZE);
|
|
}
|
|
|
|
static atomic_t vmap_lazy_nr = ATOMIC_INIT(0);
|
|
|
|
/* for per-CPU blocks */
|
|
static void purge_fragmented_blocks_allcpus(void);
|
|
|
|
/*
|
|
* called before a call to iounmap() if the caller wants vm_area_struct's
|
|
* immediately freed.
|
|
*/
|
|
void set_iounmap_nonlazy(void)
|
|
{
|
|
atomic_set(&vmap_lazy_nr, lazy_max_pages()+1);
|
|
}
|
|
|
|
/*
|
|
* Purges all lazily-freed vmap areas.
|
|
*
|
|
* If sync is 0 then don't purge if there is already a purge in progress.
|
|
* If force_flush is 1, then flush kernel TLBs between *start and *end even
|
|
* if we found no lazy vmap areas to unmap (callers can use this to optimise
|
|
* their own TLB flushing).
|
|
* Returns with *start = min(*start, lowest purged address)
|
|
* *end = max(*end, highest purged address)
|
|
*/
|
|
static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end,
|
|
int sync, int force_flush)
|
|
{
|
|
static DEFINE_SPINLOCK(purge_lock);
|
|
LIST_HEAD(valist);
|
|
struct vmap_area *va;
|
|
struct vmap_area *n_va;
|
|
int nr = 0;
|
|
|
|
/*
|
|
* If sync is 0 but force_flush is 1, we'll go sync anyway but callers
|
|
* should not expect such behaviour. This just simplifies locking for
|
|
* the case that isn't actually used at the moment anyway.
|
|
*/
|
|
if (!sync && !force_flush) {
|
|
if (!spin_trylock(&purge_lock))
|
|
return;
|
|
} else
|
|
spin_lock(&purge_lock);
|
|
|
|
if (sync)
|
|
purge_fragmented_blocks_allcpus();
|
|
|
|
rcu_read_lock();
|
|
list_for_each_entry_rcu(va, &vmap_area_list, list) {
|
|
if (va->flags & VM_LAZY_FREE) {
|
|
if (va->va_start < *start)
|
|
*start = va->va_start;
|
|
if (va->va_end > *end)
|
|
*end = va->va_end;
|
|
nr += (va->va_end - va->va_start) >> PAGE_SHIFT;
|
|
list_add_tail(&va->purge_list, &valist);
|
|
va->flags |= VM_LAZY_FREEING;
|
|
va->flags &= ~VM_LAZY_FREE;
|
|
}
|
|
}
|
|
rcu_read_unlock();
|
|
|
|
if (nr)
|
|
atomic_sub(nr, &vmap_lazy_nr);
|
|
|
|
if (nr || force_flush)
|
|
flush_tlb_kernel_range(*start, *end);
|
|
|
|
if (nr) {
|
|
spin_lock(&vmap_area_lock);
|
|
list_for_each_entry_safe(va, n_va, &valist, purge_list)
|
|
__free_vmap_area(va);
|
|
spin_unlock(&vmap_area_lock);
|
|
}
|
|
spin_unlock(&purge_lock);
|
|
}
|
|
|
|
/*
|
|
* Kick off a purge of the outstanding lazy areas. Don't bother if somebody
|
|
* is already purging.
|
|
*/
|
|
static void try_purge_vmap_area_lazy(void)
|
|
{
|
|
unsigned long start = ULONG_MAX, end = 0;
|
|
|
|
__purge_vmap_area_lazy(&start, &end, 0, 0);
|
|
}
|
|
|
|
/*
|
|
* Kick off a purge of the outstanding lazy areas.
|
|
*/
|
|
static void purge_vmap_area_lazy(void)
|
|
{
|
|
unsigned long start = ULONG_MAX, end = 0;
|
|
|
|
__purge_vmap_area_lazy(&start, &end, 1, 0);
|
|
}
|
|
|
|
/*
|
|
* Free a vmap area, caller ensuring that the area has been unmapped
|
|
* and flush_cache_vunmap had been called for the correct range
|
|
* previously.
|
|
*/
|
|
static void free_vmap_area_noflush(struct vmap_area *va)
|
|
{
|
|
va->flags |= VM_LAZY_FREE;
|
|
atomic_add((va->va_end - va->va_start) >> PAGE_SHIFT, &vmap_lazy_nr);
|
|
if (unlikely(atomic_read(&vmap_lazy_nr) > lazy_max_pages()))
|
|
try_purge_vmap_area_lazy();
|
|
}
|
|
|
|
/*
|
|
* Free and unmap a vmap area, caller ensuring flush_cache_vunmap had been
|
|
* called for the correct range previously.
|
|
*/
|
|
static void free_unmap_vmap_area_noflush(struct vmap_area *va)
|
|
{
|
|
unmap_vmap_area(va);
|
|
free_vmap_area_noflush(va);
|
|
}
|
|
|
|
/*
|
|
* Free and unmap a vmap area
|
|
*/
|
|
static void free_unmap_vmap_area(struct vmap_area *va)
|
|
{
|
|
flush_cache_vunmap(va->va_start, va->va_end);
|
|
free_unmap_vmap_area_noflush(va);
|
|
}
|
|
|
|
static struct vmap_area *find_vmap_area(unsigned long addr)
|
|
{
|
|
struct vmap_area *va;
|
|
|
|
spin_lock(&vmap_area_lock);
|
|
va = __find_vmap_area(addr);
|
|
spin_unlock(&vmap_area_lock);
|
|
|
|
return va;
|
|
}
|
|
|
|
static void free_unmap_vmap_area_addr(unsigned long addr)
|
|
{
|
|
struct vmap_area *va;
|
|
|
|
va = find_vmap_area(addr);
|
|
BUG_ON(!va);
|
|
free_unmap_vmap_area(va);
|
|
}
|
|
|
|
|
|
/*** Per cpu kva allocator ***/
|
|
|
|
/*
|
|
* vmap space is limited especially on 32 bit architectures. Ensure there is
|
|
* room for at least 16 percpu vmap blocks per CPU.
|
|
*/
|
|
/*
|
|
* If we had a constant VMALLOC_START and VMALLOC_END, we'd like to be able
|
|
* to #define VMALLOC_SPACE (VMALLOC_END-VMALLOC_START). Guess
|
|
* instead (we just need a rough idea)
|
|
*/
|
|
#if BITS_PER_LONG == 32
|
|
#define VMALLOC_SPACE (128UL*1024*1024)
|
|
#else
|
|
#define VMALLOC_SPACE (128UL*1024*1024*1024)
|
|
#endif
|
|
|
|
#define VMALLOC_PAGES (VMALLOC_SPACE / PAGE_SIZE)
|
|
#define VMAP_MAX_ALLOC BITS_PER_LONG /* 256K with 4K pages */
|
|
#define VMAP_BBMAP_BITS_MAX 1024 /* 4MB with 4K pages */
|
|
#define VMAP_BBMAP_BITS_MIN (VMAP_MAX_ALLOC*2)
|
|
#define VMAP_MIN(x, y) ((x) < (y) ? (x) : (y)) /* can't use min() */
|
|
#define VMAP_MAX(x, y) ((x) > (y) ? (x) : (y)) /* can't use max() */
|
|
#define VMAP_BBMAP_BITS \
|
|
VMAP_MIN(VMAP_BBMAP_BITS_MAX, \
|
|
VMAP_MAX(VMAP_BBMAP_BITS_MIN, \
|
|
VMALLOC_PAGES / roundup_pow_of_two(NR_CPUS) / 16))
|
|
|
|
#define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE)
|
|
|
|
static bool vmap_initialized __read_mostly = false;
|
|
|
|
struct vmap_block_queue {
|
|
spinlock_t lock;
|
|
struct list_head free;
|
|
};
|
|
|
|
struct vmap_block {
|
|
spinlock_t lock;
|
|
struct vmap_area *va;
|
|
unsigned long free, dirty;
|
|
DECLARE_BITMAP(dirty_map, VMAP_BBMAP_BITS);
|
|
struct list_head free_list;
|
|
struct rcu_head rcu_head;
|
|
struct list_head purge;
|
|
};
|
|
|
|
/* Queue of free and dirty vmap blocks, for allocation and flushing purposes */
|
|
static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue);
|
|
|
|
/*
|
|
* Radix tree of vmap blocks, indexed by address, to quickly find a vmap block
|
|
* in the free path. Could get rid of this if we change the API to return a
|
|
* "cookie" from alloc, to be passed to free. But no big deal yet.
|
|
*/
|
|
static DEFINE_SPINLOCK(vmap_block_tree_lock);
|
|
static RADIX_TREE(vmap_block_tree, GFP_ATOMIC);
|
|
|
|
/*
|
|
* We should probably have a fallback mechanism to allocate virtual memory
|
|
* out of partially filled vmap blocks. However vmap block sizing should be
|
|
* fairly reasonable according to the vmalloc size, so it shouldn't be a
|
|
* big problem.
|
|
*/
|
|
|
|
static unsigned long addr_to_vb_idx(unsigned long addr)
|
|
{
|
|
addr -= VMALLOC_START & ~(VMAP_BLOCK_SIZE-1);
|
|
addr /= VMAP_BLOCK_SIZE;
|
|
return addr;
|
|
}
|
|
|
|
static struct vmap_block *new_vmap_block(gfp_t gfp_mask)
|
|
{
|
|
struct vmap_block_queue *vbq;
|
|
struct vmap_block *vb;
|
|
struct vmap_area *va;
|
|
unsigned long vb_idx;
|
|
int node, err;
|
|
|
|
node = numa_node_id();
|
|
|
|
vb = kmalloc_node(sizeof(struct vmap_block),
|
|
gfp_mask & GFP_RECLAIM_MASK, node);
|
|
if (unlikely(!vb))
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE,
|
|
VMALLOC_START, VMALLOC_END,
|
|
node, gfp_mask);
|
|
if (IS_ERR(va)) {
|
|
kfree(vb);
|
|
return ERR_CAST(va);
|
|
}
|
|
|
|
err = radix_tree_preload(gfp_mask);
|
|
if (unlikely(err)) {
|
|
kfree(vb);
|
|
free_vmap_area(va);
|
|
return ERR_PTR(err);
|
|
}
|
|
|
|
spin_lock_init(&vb->lock);
|
|
vb->va = va;
|
|
vb->free = VMAP_BBMAP_BITS;
|
|
vb->dirty = 0;
|
|
bitmap_zero(vb->dirty_map, VMAP_BBMAP_BITS);
|
|
INIT_LIST_HEAD(&vb->free_list);
|
|
|
|
vb_idx = addr_to_vb_idx(va->va_start);
|
|
spin_lock(&vmap_block_tree_lock);
|
|
err = radix_tree_insert(&vmap_block_tree, vb_idx, vb);
|
|
spin_unlock(&vmap_block_tree_lock);
|
|
BUG_ON(err);
|
|
radix_tree_preload_end();
|
|
|
|
vbq = &get_cpu_var(vmap_block_queue);
|
|
spin_lock(&vbq->lock);
|
|
list_add_tail_rcu(&vb->free_list, &vbq->free);
|
|
spin_unlock(&vbq->lock);
|
|
put_cpu_var(vmap_block_queue);
|
|
|
|
return vb;
|
|
}
|
|
|
|
static void free_vmap_block(struct vmap_block *vb)
|
|
{
|
|
struct vmap_block *tmp;
|
|
unsigned long vb_idx;
|
|
|
|
vb_idx = addr_to_vb_idx(vb->va->va_start);
|
|
spin_lock(&vmap_block_tree_lock);
|
|
tmp = radix_tree_delete(&vmap_block_tree, vb_idx);
|
|
spin_unlock(&vmap_block_tree_lock);
|
|
BUG_ON(tmp != vb);
|
|
|
|
free_vmap_area_noflush(vb->va);
|
|
kfree_rcu(vb, rcu_head);
|
|
}
|
|
|
|
static void purge_fragmented_blocks(int cpu)
|
|
{
|
|
LIST_HEAD(purge);
|
|
struct vmap_block *vb;
|
|
struct vmap_block *n_vb;
|
|
struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu);
|
|
|
|
rcu_read_lock();
|
|
list_for_each_entry_rcu(vb, &vbq->free, free_list) {
|
|
|
|
if (!(vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS))
|
|
continue;
|
|
|
|
spin_lock(&vb->lock);
|
|
if (vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS) {
|
|
vb->free = 0; /* prevent further allocs after releasing lock */
|
|
vb->dirty = VMAP_BBMAP_BITS; /* prevent purging it again */
|
|
bitmap_fill(vb->dirty_map, VMAP_BBMAP_BITS);
|
|
spin_lock(&vbq->lock);
|
|
list_del_rcu(&vb->free_list);
|
|
spin_unlock(&vbq->lock);
|
|
spin_unlock(&vb->lock);
|
|
list_add_tail(&vb->purge, &purge);
|
|
} else
|
|
spin_unlock(&vb->lock);
|
|
}
|
|
rcu_read_unlock();
|
|
|
|
list_for_each_entry_safe(vb, n_vb, &purge, purge) {
|
|
list_del(&vb->purge);
|
|
free_vmap_block(vb);
|
|
}
|
|
}
|
|
|
|
static void purge_fragmented_blocks_allcpus(void)
|
|
{
|
|
int cpu;
|
|
|
|
for_each_possible_cpu(cpu)
|
|
purge_fragmented_blocks(cpu);
|
|
}
|
|
|
|
static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
|
|
{
|
|
struct vmap_block_queue *vbq;
|
|
struct vmap_block *vb;
|
|
unsigned long addr = 0;
|
|
unsigned int order;
|
|
|
|
BUG_ON(size & ~PAGE_MASK);
|
|
BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
|
|
if (WARN_ON(size == 0)) {
|
|
/*
|
|
* Allocating 0 bytes isn't what caller wants since
|
|
* get_order(0) returns funny result. Just warn and terminate
|
|
* early.
|
|
*/
|
|
return NULL;
|
|
}
|
|
order = get_order(size);
|
|
|
|
again:
|
|
rcu_read_lock();
|
|
vbq = &get_cpu_var(vmap_block_queue);
|
|
list_for_each_entry_rcu(vb, &vbq->free, free_list) {
|
|
int i;
|
|
|
|
spin_lock(&vb->lock);
|
|
if (vb->free < 1UL << order)
|
|
goto next;
|
|
|
|
i = VMAP_BBMAP_BITS - vb->free;
|
|
addr = vb->va->va_start + (i << PAGE_SHIFT);
|
|
BUG_ON(addr_to_vb_idx(addr) !=
|
|
addr_to_vb_idx(vb->va->va_start));
|
|
vb->free -= 1UL << order;
|
|
if (vb->free == 0) {
|
|
spin_lock(&vbq->lock);
|
|
list_del_rcu(&vb->free_list);
|
|
spin_unlock(&vbq->lock);
|
|
}
|
|
spin_unlock(&vb->lock);
|
|
break;
|
|
next:
|
|
spin_unlock(&vb->lock);
|
|
}
|
|
|
|
put_cpu_var(vmap_block_queue);
|
|
rcu_read_unlock();
|
|
|
|
if (!addr) {
|
|
vb = new_vmap_block(gfp_mask);
|
|
if (IS_ERR(vb))
|
|
return vb;
|
|
goto again;
|
|
}
|
|
|
|
return (void *)addr;
|
|
}
|
|
|
|
static void vb_free(const void *addr, unsigned long size)
|
|
{
|
|
unsigned long offset;
|
|
unsigned long vb_idx;
|
|
unsigned int order;
|
|
struct vmap_block *vb;
|
|
|
|
BUG_ON(size & ~PAGE_MASK);
|
|
BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
|
|
|
|
flush_cache_vunmap((unsigned long)addr, (unsigned long)addr + size);
|
|
|
|
order = get_order(size);
|
|
|
|
offset = (unsigned long)addr & (VMAP_BLOCK_SIZE - 1);
|
|
|
|
vb_idx = addr_to_vb_idx((unsigned long)addr);
|
|
rcu_read_lock();
|
|
vb = radix_tree_lookup(&vmap_block_tree, vb_idx);
|
|
rcu_read_unlock();
|
|
BUG_ON(!vb);
|
|
|
|
vunmap_page_range((unsigned long)addr, (unsigned long)addr + size);
|
|
|
|
spin_lock(&vb->lock);
|
|
BUG_ON(bitmap_allocate_region(vb->dirty_map, offset >> PAGE_SHIFT, order));
|
|
|
|
vb->dirty += 1UL << order;
|
|
if (vb->dirty == VMAP_BBMAP_BITS) {
|
|
BUG_ON(vb->free);
|
|
spin_unlock(&vb->lock);
|
|
free_vmap_block(vb);
|
|
} else
|
|
spin_unlock(&vb->lock);
|
|
}
|
|
|
|
/**
|
|
* vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer
|
|
*
|
|
* The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily
|
|
* to amortize TLB flushing overheads. What this means is that any page you
|
|
* have now, may, in a former life, have been mapped into kernel virtual
|
|
* address by the vmap layer and so there might be some CPUs with TLB entries
|
|
* still referencing that page (additional to the regular 1:1 kernel mapping).
|
|
*
|
|
* vm_unmap_aliases flushes all such lazy mappings. After it returns, we can
|
|
* be sure that none of the pages we have control over will have any aliases
|
|
* from the vmap layer.
|
|
*/
|
|
void vm_unmap_aliases(void)
|
|
{
|
|
unsigned long start = ULONG_MAX, end = 0;
|
|
int cpu;
|
|
int flush = 0;
|
|
|
|
if (unlikely(!vmap_initialized))
|
|
return;
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu);
|
|
struct vmap_block *vb;
|
|
|
|
rcu_read_lock();
|
|
list_for_each_entry_rcu(vb, &vbq->free, free_list) {
|
|
int i, j;
|
|
|
|
spin_lock(&vb->lock);
|
|
i = find_first_bit(vb->dirty_map, VMAP_BBMAP_BITS);
|
|
if (i < VMAP_BBMAP_BITS) {
|
|
unsigned long s, e;
|
|
|
|
j = find_last_bit(vb->dirty_map,
|
|
VMAP_BBMAP_BITS);
|
|
j = j + 1; /* need exclusive index */
|
|
|
|
s = vb->va->va_start + (i << PAGE_SHIFT);
|
|
e = vb->va->va_start + (j << PAGE_SHIFT);
|
|
flush = 1;
|
|
|
|
if (s < start)
|
|
start = s;
|
|
if (e > end)
|
|
end = e;
|
|
}
|
|
spin_unlock(&vb->lock);
|
|
}
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
__purge_vmap_area_lazy(&start, &end, 1, flush);
|
|
}
|
|
EXPORT_SYMBOL_GPL(vm_unmap_aliases);
|
|
|
|
/**
|
|
* vm_unmap_ram - unmap linear kernel address space set up by vm_map_ram
|
|
* @mem: the pointer returned by vm_map_ram
|
|
* @count: the count passed to that vm_map_ram call (cannot unmap partial)
|
|
*/
|
|
void vm_unmap_ram(const void *mem, unsigned int count)
|
|
{
|
|
unsigned long size = count << PAGE_SHIFT;
|
|
unsigned long addr = (unsigned long)mem;
|
|
|
|
BUG_ON(!addr);
|
|
BUG_ON(addr < VMALLOC_START);
|
|
BUG_ON(addr > VMALLOC_END);
|
|
BUG_ON(addr & (PAGE_SIZE-1));
|
|
|
|
debug_check_no_locks_freed(mem, size);
|
|
vmap_debug_free_range(addr, addr+size);
|
|
|
|
if (likely(count <= VMAP_MAX_ALLOC))
|
|
vb_free(mem, size);
|
|
else
|
|
free_unmap_vmap_area_addr(addr);
|
|
}
|
|
EXPORT_SYMBOL(vm_unmap_ram);
|
|
|
|
/**
|
|
* vm_map_ram - map pages linearly into kernel virtual address (vmalloc space)
|
|
* @pages: an array of pointers to the pages to be mapped
|
|
* @count: number of pages
|
|
* @node: prefer to allocate data structures on this node
|
|
* @prot: memory protection to use. PAGE_KERNEL for regular RAM
|
|
*
|
|
* If you use this function for less than VMAP_MAX_ALLOC pages, it could be
|
|
* faster than vmap so it's good. But if you mix long-life and short-life
|
|
* objects with vm_map_ram(), it could consume lots of address space through
|
|
* fragmentation (especially on a 32bit machine). You could see failures in
|
|
* the end. Please use this function for short-lived objects.
|
|
*
|
|
* Returns: a pointer to the address that has been mapped, or %NULL on failure
|
|
*/
|
|
void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot)
|
|
{
|
|
unsigned long size = count << PAGE_SHIFT;
|
|
unsigned long addr;
|
|
void *mem;
|
|
|
|
if (likely(count <= VMAP_MAX_ALLOC)) {
|
|
mem = vb_alloc(size, GFP_KERNEL);
|
|
if (IS_ERR(mem))
|
|
return NULL;
|
|
addr = (unsigned long)mem;
|
|
} else {
|
|
struct vmap_area *va;
|
|
va = alloc_vmap_area(size, PAGE_SIZE,
|
|
VMALLOC_START, VMALLOC_END, node, GFP_KERNEL);
|
|
if (IS_ERR(va))
|
|
return NULL;
|
|
|
|
addr = va->va_start;
|
|
mem = (void *)addr;
|
|
}
|
|
if (vmap_page_range(addr, addr + size, prot, pages) < 0) {
|
|
vm_unmap_ram(mem, count);
|
|
return NULL;
|
|
}
|
|
return mem;
|
|
}
|
|
EXPORT_SYMBOL(vm_map_ram);
|
|
|
|
static struct vm_struct *vmlist __initdata;
|
|
/**
|
|
* vm_area_add_early - add vmap area early during boot
|
|
* @vm: vm_struct to add
|
|
*
|
|
* This function is used to add fixed kernel vm area to vmlist before
|
|
* vmalloc_init() is called. @vm->addr, @vm->size, and @vm->flags
|
|
* should contain proper values and the other fields should be zero.
|
|
*
|
|
* DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING.
|
|
*/
|
|
void __init vm_area_add_early(struct vm_struct *vm)
|
|
{
|
|
struct vm_struct *tmp, **p;
|
|
|
|
BUG_ON(vmap_initialized);
|
|
for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) {
|
|
if (tmp->addr >= vm->addr) {
|
|
BUG_ON(tmp->addr < vm->addr + vm->size);
|
|
break;
|
|
} else
|
|
BUG_ON(tmp->addr + tmp->size > vm->addr);
|
|
}
|
|
vm->next = *p;
|
|
*p = vm;
|
|
}
|
|
|
|
/**
|
|
* vm_area_register_early - register vmap area early during boot
|
|
* @vm: vm_struct to register
|
|
* @align: requested alignment
|
|
*
|
|
* This function is used to register kernel vm area before
|
|
* vmalloc_init() is called. @vm->size and @vm->flags should contain
|
|
* proper values on entry and other fields should be zero. On return,
|
|
* vm->addr contains the allocated address.
|
|
*
|
|
* DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING.
|
|
*/
|
|
void __init vm_area_register_early(struct vm_struct *vm, size_t align)
|
|
{
|
|
static size_t vm_init_off __initdata;
|
|
unsigned long addr;
|
|
|
|
addr = ALIGN(VMALLOC_START + vm_init_off, align);
|
|
vm_init_off = PFN_ALIGN(addr + vm->size) - VMALLOC_START;
|
|
|
|
vm->addr = (void *)addr;
|
|
|
|
vm_area_add_early(vm);
|
|
}
|
|
|
|
void __init vmalloc_init(void)
|
|
{
|
|
struct vmap_area *va;
|
|
struct vm_struct *tmp;
|
|
int i;
|
|
|
|
for_each_possible_cpu(i) {
|
|
struct vmap_block_queue *vbq;
|
|
struct vfree_deferred *p;
|
|
|
|
vbq = &per_cpu(vmap_block_queue, i);
|
|
spin_lock_init(&vbq->lock);
|
|
INIT_LIST_HEAD(&vbq->free);
|
|
p = &per_cpu(vfree_deferred, i);
|
|
init_llist_head(&p->list);
|
|
INIT_WORK(&p->wq, free_work);
|
|
}
|
|
|
|
/* Import existing vmlist entries. */
|
|
for (tmp = vmlist; tmp; tmp = tmp->next) {
|
|
va = kzalloc(sizeof(struct vmap_area), GFP_NOWAIT);
|
|
va->flags = VM_VM_AREA;
|
|
va->va_start = (unsigned long)tmp->addr;
|
|
va->va_end = va->va_start + tmp->size;
|
|
va->vm = tmp;
|
|
__insert_vmap_area(va);
|
|
}
|
|
|
|
vmap_area_pcpu_hole = VMALLOC_END;
|
|
|
|
vmap_initialized = true;
|
|
}
|
|
|
|
/**
|
|
* map_kernel_range_noflush - map kernel VM area with the specified pages
|
|
* @addr: start of the VM area to map
|
|
* @size: size of the VM area to map
|
|
* @prot: page protection flags to use
|
|
* @pages: pages to map
|
|
*
|
|
* Map PFN_UP(@size) pages at @addr. The VM area @addr and @size
|
|
* specify should have been allocated using get_vm_area() and its
|
|
* friends.
|
|
*
|
|
* NOTE:
|
|
* This function does NOT do any cache flushing. The caller is
|
|
* responsible for calling flush_cache_vmap() on to-be-mapped areas
|
|
* before calling this function.
|
|
*
|
|
* RETURNS:
|
|
* The number of pages mapped on success, -errno on failure.
|
|
*/
|
|
int map_kernel_range_noflush(unsigned long addr, unsigned long size,
|
|
pgprot_t prot, struct page **pages)
|
|
{
|
|
return vmap_page_range_noflush(addr, addr + size, prot, pages);
|
|
}
|
|
|
|
/**
|
|
* unmap_kernel_range_noflush - unmap kernel VM area
|
|
* @addr: start of the VM area to unmap
|
|
* @size: size of the VM area to unmap
|
|
*
|
|
* Unmap PFN_UP(@size) pages at @addr. The VM area @addr and @size
|
|
* specify should have been allocated using get_vm_area() and its
|
|
* friends.
|
|
*
|
|
* NOTE:
|
|
* This function does NOT do any cache flushing. The caller is
|
|
* responsible for calling flush_cache_vunmap() on to-be-mapped areas
|
|
* before calling this function and flush_tlb_kernel_range() after.
|
|
*/
|
|
void unmap_kernel_range_noflush(unsigned long addr, unsigned long size)
|
|
{
|
|
vunmap_page_range(addr, addr + size);
|
|
}
|
|
EXPORT_SYMBOL_GPL(unmap_kernel_range_noflush);
|
|
|
|
/**
|
|
* unmap_kernel_range - unmap kernel VM area and flush cache and TLB
|
|
* @addr: start of the VM area to unmap
|
|
* @size: size of the VM area to unmap
|
|
*
|
|
* Similar to unmap_kernel_range_noflush() but flushes vcache before
|
|
* the unmapping and tlb after.
|
|
*/
|
|
void unmap_kernel_range(unsigned long addr, unsigned long size)
|
|
{
|
|
unsigned long end = addr + size;
|
|
|
|
flush_cache_vunmap(addr, end);
|
|
vunmap_page_range(addr, end);
|
|
flush_tlb_kernel_range(addr, end);
|
|
}
|
|
EXPORT_SYMBOL_GPL(unmap_kernel_range);
|
|
|
|
int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page **pages)
|
|
{
|
|
unsigned long addr = (unsigned long)area->addr;
|
|
unsigned long end = addr + get_vm_area_size(area);
|
|
int err;
|
|
|
|
err = vmap_page_range(addr, end, prot, pages);
|
|
|
|
return err > 0 ? 0 : err;
|
|
}
|
|
EXPORT_SYMBOL_GPL(map_vm_area);
|
|
|
|
static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,
|
|
unsigned long flags, const void *caller)
|
|
{
|
|
spin_lock(&vmap_area_lock);
|
|
vm->flags = flags;
|
|
vm->addr = (void *)va->va_start;
|
|
vm->size = va->va_end - va->va_start;
|
|
vm->caller = caller;
|
|
va->vm = vm;
|
|
va->flags |= VM_VM_AREA;
|
|
spin_unlock(&vmap_area_lock);
|
|
}
|
|
|
|
static void clear_vm_uninitialized_flag(struct vm_struct *vm)
|
|
{
|
|
/*
|
|
* Before removing VM_UNINITIALIZED,
|
|
* we should make sure that vm has proper values.
|
|
* Pair with smp_rmb() in show_numa_info().
|
|
*/
|
|
smp_wmb();
|
|
vm->flags &= ~VM_UNINITIALIZED;
|
|
}
|
|
|
|
static struct vm_struct *__get_vm_area_node(unsigned long size,
|
|
unsigned long align, unsigned long flags, unsigned long start,
|
|
unsigned long end, int node, gfp_t gfp_mask, const void *caller)
|
|
{
|
|
struct vmap_area *va;
|
|
struct vm_struct *area;
|
|
|
|
BUG_ON(in_interrupt());
|
|
if (flags & VM_IOREMAP)
|
|
align = 1ul << clamp_t(int, fls_long(size),
|
|
PAGE_SHIFT, IOREMAP_MAX_ORDER);
|
|
|
|
size = PAGE_ALIGN(size);
|
|
if (unlikely(!size))
|
|
return NULL;
|
|
|
|
area = kzalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node);
|
|
if (unlikely(!area))
|
|
return NULL;
|
|
|
|
if (!(flags & VM_NO_GUARD))
|
|
size += PAGE_SIZE;
|
|
|
|
va = alloc_vmap_area(size, align, start, end, node, gfp_mask);
|
|
if (IS_ERR(va)) {
|
|
kfree(area);
|
|
return NULL;
|
|
}
|
|
|
|
setup_vmalloc_vm(area, va, flags, caller);
|
|
|
|
return area;
|
|
}
|
|
|
|
struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
|
|
unsigned long start, unsigned long end)
|
|
{
|
|
return __get_vm_area_node(size, 1, flags, start, end, NUMA_NO_NODE,
|
|
GFP_KERNEL, __builtin_return_address(0));
|
|
}
|
|
EXPORT_SYMBOL_GPL(__get_vm_area);
|
|
|
|
struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags,
|
|
unsigned long start, unsigned long end,
|
|
const void *caller)
|
|
{
|
|
return __get_vm_area_node(size, 1, flags, start, end, NUMA_NO_NODE,
|
|
GFP_KERNEL, caller);
|
|
}
|
|
|
|
/**
|
|
* get_vm_area - reserve a contiguous kernel virtual area
|
|
* @size: size of the area
|
|
* @flags: %VM_IOREMAP for I/O mappings or VM_ALLOC
|
|
*
|
|
* Search an area of @size in the kernel virtual mapping area,
|
|
* and reserved it for out purposes. Returns the area descriptor
|
|
* on success or %NULL on failure.
|
|
*/
|
|
struct vm_struct *get_vm_area(unsigned long size, unsigned long flags)
|
|
{
|
|
return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
|
|
NUMA_NO_NODE, GFP_KERNEL,
|
|
__builtin_return_address(0));
|
|
}
|
|
|
|
struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags,
|
|
const void *caller)
|
|
{
|
|
return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
|
|
NUMA_NO_NODE, GFP_KERNEL, caller);
|
|
}
|
|
|
|
/**
|
|
* find_vm_area - find a continuous kernel virtual area
|
|
* @addr: base address
|
|
*
|
|
* Search for the kernel VM area starting at @addr, and return it.
|
|
* It is up to the caller to do all required locking to keep the returned
|
|
* pointer valid.
|
|
*/
|
|
struct vm_struct *find_vm_area(const void *addr)
|
|
{
|
|
struct vmap_area *va;
|
|
|
|
va = find_vmap_area((unsigned long)addr);
|
|
if (va && va->flags & VM_VM_AREA)
|
|
return va->vm;
|
|
|
|
return NULL;
|
|
}
|
|
|
|
/**
|
|
* remove_vm_area - find and remove a continuous kernel virtual area
|
|
* @addr: base address
|
|
*
|
|
* Search for the kernel VM area starting at @addr, and remove it.
|
|
* This function returns the found VM area, but using it is NOT safe
|
|
* on SMP machines, except for its size or flags.
|
|
*/
|
|
struct vm_struct *remove_vm_area(const void *addr)
|
|
{
|
|
struct vmap_area *va;
|
|
|
|
va = find_vmap_area((unsigned long)addr);
|
|
if (va && va->flags & VM_VM_AREA) {
|
|
struct vm_struct *vm = va->vm;
|
|
|
|
spin_lock(&vmap_area_lock);
|
|
va->vm = NULL;
|
|
va->flags &= ~VM_VM_AREA;
|
|
spin_unlock(&vmap_area_lock);
|
|
|
|
vmap_debug_free_range(va->va_start, va->va_end);
|
|
kasan_free_shadow(vm);
|
|
free_unmap_vmap_area(va);
|
|
vm->size -= PAGE_SIZE;
|
|
|
|
return vm;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
static void __vunmap(const void *addr, int deallocate_pages)
|
|
{
|
|
struct vm_struct *area;
|
|
|
|
if (!addr)
|
|
return;
|
|
|
|
if (WARN(!PAGE_ALIGNED(addr), "Trying to vfree() bad address (%p)\n",
|
|
addr))
|
|
return;
|
|
|
|
area = remove_vm_area(addr);
|
|
if (unlikely(!area)) {
|
|
WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n",
|
|
addr);
|
|
return;
|
|
}
|
|
|
|
debug_check_no_locks_freed(addr, area->size);
|
|
debug_check_no_obj_freed(addr, area->size);
|
|
|
|
if (deallocate_pages) {
|
|
int i;
|
|
|
|
for (i = 0; i < area->nr_pages; i++) {
|
|
struct page *page = area->pages[i];
|
|
|
|
BUG_ON(!page);
|
|
__free_page(page);
|
|
}
|
|
|
|
if (area->flags & VM_VPAGES)
|
|
vfree(area->pages);
|
|
else
|
|
kfree(area->pages);
|
|
}
|
|
|
|
kfree(area);
|
|
return;
|
|
}
|
|
|
|
/**
|
|
* vfree - release memory allocated by vmalloc()
|
|
* @addr: memory base address
|
|
*
|
|
* Free the virtually continuous memory area starting at @addr, as
|
|
* obtained from vmalloc(), vmalloc_32() or __vmalloc(). If @addr is
|
|
* NULL, no operation is performed.
|
|
*
|
|
* Must not be called in NMI context (strictly speaking, only if we don't
|
|
* have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling
|
|
* conventions for vfree() arch-depenedent would be a really bad idea)
|
|
*
|
|
* NOTE: assumes that the object at *addr has a size >= sizeof(llist_node)
|
|
*/
|
|
void vfree(const void *addr)
|
|
{
|
|
BUG_ON(in_nmi());
|
|
|
|
kmemleak_free(addr);
|
|
|
|
if (!addr)
|
|
return;
|
|
if (unlikely(in_interrupt())) {
|
|
struct vfree_deferred *p = this_cpu_ptr(&vfree_deferred);
|
|
if (llist_add((struct llist_node *)addr, &p->list))
|
|
schedule_work(&p->wq);
|
|
} else
|
|
__vunmap(addr, 1);
|
|
}
|
|
EXPORT_SYMBOL(vfree);
|
|
|
|
/**
|
|
* vunmap - release virtual mapping obtained by vmap()
|
|
* @addr: memory base address
|
|
*
|
|
* Free the virtually contiguous memory area starting at @addr,
|
|
* which was created from the page array passed to vmap().
|
|
*
|
|
* Must not be called in interrupt context.
|
|
*/
|
|
void vunmap(const void *addr)
|
|
{
|
|
BUG_ON(in_interrupt());
|
|
might_sleep();
|
|
if (addr)
|
|
__vunmap(addr, 0);
|
|
}
|
|
EXPORT_SYMBOL(vunmap);
|
|
|
|
/**
|
|
* vmap - map an array of pages into virtually contiguous space
|
|
* @pages: array of page pointers
|
|
* @count: number of pages to map
|
|
* @flags: vm_area->flags
|
|
* @prot: page protection for the mapping
|
|
*
|
|
* Maps @count pages from @pages into contiguous kernel virtual
|
|
* space.
|
|
*/
|
|
void *vmap(struct page **pages, unsigned int count,
|
|
unsigned long flags, pgprot_t prot)
|
|
{
|
|
struct vm_struct *area;
|
|
|
|
might_sleep();
|
|
|
|
if (count > totalram_pages)
|
|
return NULL;
|
|
|
|
area = get_vm_area_caller((count << PAGE_SHIFT), flags,
|
|
__builtin_return_address(0));
|
|
if (!area)
|
|
return NULL;
|
|
|
|
if (map_vm_area(area, prot, pages)) {
|
|
vunmap(area->addr);
|
|
return NULL;
|
|
}
|
|
|
|
return area->addr;
|
|
}
|
|
EXPORT_SYMBOL(vmap);
|
|
|
|
static void *__vmalloc_node(unsigned long size, unsigned long align,
|
|
gfp_t gfp_mask, pgprot_t prot,
|
|
int node, const void *caller);
|
|
static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
|
|
pgprot_t prot, int node)
|
|
{
|
|
const int order = 0;
|
|
struct page **pages;
|
|
unsigned int nr_pages, array_size, i;
|
|
const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
|
|
const gfp_t alloc_mask = gfp_mask | __GFP_NOWARN;
|
|
|
|
nr_pages = get_vm_area_size(area) >> PAGE_SHIFT;
|
|
array_size = (nr_pages * sizeof(struct page *));
|
|
|
|
area->nr_pages = nr_pages;
|
|
/* Please note that the recursion is strictly bounded. */
|
|
if (array_size > PAGE_SIZE) {
|
|
pages = __vmalloc_node(array_size, 1, nested_gfp|__GFP_HIGHMEM,
|
|
PAGE_KERNEL, node, area->caller);
|
|
area->flags |= VM_VPAGES;
|
|
} else {
|
|
pages = kmalloc_node(array_size, nested_gfp, node);
|
|
}
|
|
area->pages = pages;
|
|
if (!area->pages) {
|
|
remove_vm_area(area->addr);
|
|
kfree(area);
|
|
return NULL;
|
|
}
|
|
|
|
for (i = 0; i < area->nr_pages; i++) {
|
|
struct page *page;
|
|
|
|
if (node == NUMA_NO_NODE)
|
|
page = alloc_page(alloc_mask);
|
|
else
|
|
page = alloc_pages_node(node, alloc_mask, order);
|
|
|
|
if (unlikely(!page)) {
|
|
/* Successfully allocated i pages, free them in __vunmap() */
|
|
area->nr_pages = i;
|
|
goto fail;
|
|
}
|
|
area->pages[i] = page;
|
|
if (gfp_mask & __GFP_WAIT)
|
|
cond_resched();
|
|
}
|
|
|
|
if (map_vm_area(area, prot, pages))
|
|
goto fail;
|
|
return area->addr;
|
|
|
|
fail:
|
|
warn_alloc_failed(gfp_mask, order,
|
|
"vmalloc: allocation failure, allocated %ld of %ld bytes\n",
|
|
(area->nr_pages*PAGE_SIZE), area->size);
|
|
vfree(area->addr);
|
|
return NULL;
|
|
}
|
|
|
|
/**
|
|
* __vmalloc_node_range - allocate virtually contiguous memory
|
|
* @size: allocation size
|
|
* @align: desired alignment
|
|
* @start: vm area range start
|
|
* @end: vm area range end
|
|
* @gfp_mask: flags for the page level allocator
|
|
* @prot: protection mask for the allocated pages
|
|
* @vm_flags: additional vm area flags (e.g. %VM_NO_GUARD)
|
|
* @node: node to use for allocation or NUMA_NO_NODE
|
|
* @caller: caller's return address
|
|
*
|
|
* 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.
|
|
*/
|
|
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)
|
|
{
|
|
struct vm_struct *area;
|
|
void *addr;
|
|
unsigned long real_size = size;
|
|
|
|
size = PAGE_ALIGN(size);
|
|
if (!size || (size >> PAGE_SHIFT) > totalram_pages)
|
|
goto fail;
|
|
|
|
area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED |
|
|
vm_flags, start, end, node, gfp_mask, caller);
|
|
if (!area)
|
|
goto fail;
|
|
|
|
addr = __vmalloc_area_node(area, gfp_mask, prot, node);
|
|
if (!addr)
|
|
return NULL;
|
|
|
|
/*
|
|
* In this function, newly allocated vm_struct has VM_UNINITIALIZED
|
|
* flag. It means that vm_struct is not fully initialized.
|
|
* Now, it is fully initialized, so remove this flag here.
|
|
*/
|
|
clear_vm_uninitialized_flag(area);
|
|
|
|
/*
|
|
* A ref_count = 2 is needed because vm_struct allocated in
|
|
* __get_vm_area_node() contains a reference to the virtual address of
|
|
* the vmalloc'ed block.
|
|
*/
|
|
kmemleak_alloc(addr, real_size, 2, gfp_mask);
|
|
|
|
return addr;
|
|
|
|
fail:
|
|
warn_alloc_failed(gfp_mask, 0,
|
|
"vmalloc: allocation failure: %lu bytes\n",
|
|
real_size);
|
|
return NULL;
|
|
}
|
|
|
|
/**
|
|
* __vmalloc_node - allocate virtually contiguous memory
|
|
* @size: allocation size
|
|
* @align: desired alignment
|
|
* @gfp_mask: flags for the page level allocator
|
|
* @prot: protection mask for the allocated pages
|
|
* @node: node to use for allocation or NUMA_NO_NODE
|
|
* @caller: caller's return address
|
|
*
|
|
* 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.
|
|
*/
|
|
static void *__vmalloc_node(unsigned long size, unsigned long align,
|
|
gfp_t gfp_mask, pgprot_t prot,
|
|
int node, const void *caller)
|
|
{
|
|
return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END,
|
|
gfp_mask, prot, 0, node, caller);
|
|
}
|
|
|
|
void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
|
|
{
|
|
return __vmalloc_node(size, 1, gfp_mask, prot, NUMA_NO_NODE,
|
|
__builtin_return_address(0));
|
|
}
|
|
EXPORT_SYMBOL(__vmalloc);
|
|
|
|
static inline void *__vmalloc_node_flags(unsigned long size,
|
|
int node, gfp_t flags)
|
|
{
|
|
return __vmalloc_node(size, 1, flags, PAGE_KERNEL,
|
|
node, __builtin_return_address(0));
|
|
}
|
|
|
|
/**
|
|
* vmalloc - allocate virtually contiguous memory
|
|
* @size: allocation size
|
|
* Allocate enough pages to cover @size from the page level
|
|
* allocator and map them into contiguous kernel virtual space.
|
|
*
|
|
* For tight control over page level allocator and protection flags
|
|
* use __vmalloc() instead.
|
|
*/
|
|
void *vmalloc(unsigned long size)
|
|
{
|
|
return __vmalloc_node_flags(size, NUMA_NO_NODE,
|
|
GFP_KERNEL | __GFP_HIGHMEM);
|
|
}
|
|
EXPORT_SYMBOL(vmalloc);
|
|
|
|
/**
|
|
* vzalloc - allocate virtually contiguous memory with zero fill
|
|
* @size: allocation size
|
|
* Allocate enough pages to cover @size from the page level
|
|
* allocator and map them into contiguous kernel virtual space.
|
|
* The memory allocated is set to zero.
|
|
*
|
|
* For tight control over page level allocator and protection flags
|
|
* use __vmalloc() instead.
|
|
*/
|
|
void *vzalloc(unsigned long size)
|
|
{
|
|
return __vmalloc_node_flags(size, NUMA_NO_NODE,
|
|
GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
|
|
}
|
|
EXPORT_SYMBOL(vzalloc);
|
|
|
|
/**
|
|
* vmalloc_user - allocate zeroed virtually contiguous memory for userspace
|
|
* @size: allocation size
|
|
*
|
|
* The resulting memory area is zeroed so it can be mapped to userspace
|
|
* without leaking data.
|
|
*/
|
|
void *vmalloc_user(unsigned long size)
|
|
{
|
|
struct vm_struct *area;
|
|
void *ret;
|
|
|
|
ret = __vmalloc_node(size, SHMLBA,
|
|
GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
|
|
PAGE_KERNEL, NUMA_NO_NODE,
|
|
__builtin_return_address(0));
|
|
if (ret) {
|
|
area = find_vm_area(ret);
|
|
area->flags |= VM_USERMAP;
|
|
}
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(vmalloc_user);
|
|
|
|
/**
|
|
* vmalloc_node - allocate memory on a specific node
|
|
* @size: allocation size
|
|
* @node: numa node
|
|
*
|
|
* Allocate enough pages to cover @size from the page level
|
|
* allocator and map them into contiguous kernel virtual space.
|
|
*
|
|
* For tight control over page level allocator and protection flags
|
|
* use __vmalloc() instead.
|
|
*/
|
|
void *vmalloc_node(unsigned long size, int node)
|
|
{
|
|
return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
|
|
node, __builtin_return_address(0));
|
|
}
|
|
EXPORT_SYMBOL(vmalloc_node);
|
|
|
|
/**
|
|
* vzalloc_node - allocate memory on a specific node with zero fill
|
|
* @size: allocation size
|
|
* @node: numa node
|
|
*
|
|
* Allocate enough pages to cover @size from the page level
|
|
* allocator and map them into contiguous kernel virtual space.
|
|
* The memory allocated is set to zero.
|
|
*
|
|
* For tight control over page level allocator and protection flags
|
|
* use __vmalloc_node() instead.
|
|
*/
|
|
void *vzalloc_node(unsigned long size, int node)
|
|
{
|
|
return __vmalloc_node_flags(size, node,
|
|
GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
|
|
}
|
|
EXPORT_SYMBOL(vzalloc_node);
|
|
|
|
#ifndef PAGE_KERNEL_EXEC
|
|
# define PAGE_KERNEL_EXEC PAGE_KERNEL
|
|
#endif
|
|
|
|
/**
|
|
* vmalloc_exec - allocate virtually contiguous, executable memory
|
|
* @size: allocation size
|
|
*
|
|
* Kernel-internal function to allocate enough pages to cover @size
|
|
* the page level allocator and map them into contiguous and
|
|
* executable kernel virtual space.
|
|
*
|
|
* For tight control over page level allocator and protection flags
|
|
* use __vmalloc() instead.
|
|
*/
|
|
|
|
void *vmalloc_exec(unsigned long size)
|
|
{
|
|
return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC,
|
|
NUMA_NO_NODE, __builtin_return_address(0));
|
|
}
|
|
|
|
#if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)
|
|
#define GFP_VMALLOC32 GFP_DMA32 | GFP_KERNEL
|
|
#elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA)
|
|
#define GFP_VMALLOC32 GFP_DMA | GFP_KERNEL
|
|
#else
|
|
#define GFP_VMALLOC32 GFP_KERNEL
|
|
#endif
|
|
|
|
/**
|
|
* vmalloc_32 - allocate virtually contiguous memory (32bit addressable)
|
|
* @size: allocation size
|
|
*
|
|
* Allocate enough 32bit PA addressable pages to cover @size from the
|
|
* page level allocator and map them into contiguous kernel virtual space.
|
|
*/
|
|
void *vmalloc_32(unsigned long size)
|
|
{
|
|
return __vmalloc_node(size, 1, GFP_VMALLOC32, PAGE_KERNEL,
|
|
NUMA_NO_NODE, __builtin_return_address(0));
|
|
}
|
|
EXPORT_SYMBOL(vmalloc_32);
|
|
|
|
/**
|
|
* vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory
|
|
* @size: allocation size
|
|
*
|
|
* The resulting memory area is 32bit addressable and zeroed so it can be
|
|
* mapped to userspace without leaking data.
|
|
*/
|
|
void *vmalloc_32_user(unsigned long size)
|
|
{
|
|
struct vm_struct *area;
|
|
void *ret;
|
|
|
|
ret = __vmalloc_node(size, 1, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL,
|
|
NUMA_NO_NODE, __builtin_return_address(0));
|
|
if (ret) {
|
|
area = find_vm_area(ret);
|
|
area->flags |= VM_USERMAP;
|
|
}
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(vmalloc_32_user);
|
|
|
|
/*
|
|
* small helper routine , copy contents to buf from addr.
|
|
* If the page is not present, fill zero.
|
|
*/
|
|
|
|
static int aligned_vread(char *buf, char *addr, unsigned long count)
|
|
{
|
|
struct page *p;
|
|
int copied = 0;
|
|
|
|
while (count) {
|
|
unsigned long offset, length;
|
|
|
|
offset = (unsigned long)addr & ~PAGE_MASK;
|
|
length = PAGE_SIZE - offset;
|
|
if (length > count)
|
|
length = count;
|
|
p = vmalloc_to_page(addr);
|
|
/*
|
|
* To do safe access to this _mapped_ area, we need
|
|
* lock. But adding lock here means that we need to add
|
|
* overhead of vmalloc()/vfree() calles for this _debug_
|
|
* interface, rarely used. Instead of that, we'll use
|
|
* kmap() and get small overhead in this access function.
|
|
*/
|
|
if (p) {
|
|
/*
|
|
* we can expect USER0 is not used (see vread/vwrite's
|
|
* function description)
|
|
*/
|
|
void *map = kmap_atomic(p);
|
|
memcpy(buf, map + offset, length);
|
|
kunmap_atomic(map);
|
|
} else
|
|
memset(buf, 0, length);
|
|
|
|
addr += length;
|
|
buf += length;
|
|
copied += length;
|
|
count -= length;
|
|
}
|
|
return copied;
|
|
}
|
|
|
|
static int aligned_vwrite(char *buf, char *addr, unsigned long count)
|
|
{
|
|
struct page *p;
|
|
int copied = 0;
|
|
|
|
while (count) {
|
|
unsigned long offset, length;
|
|
|
|
offset = (unsigned long)addr & ~PAGE_MASK;
|
|
length = PAGE_SIZE - offset;
|
|
if (length > count)
|
|
length = count;
|
|
p = vmalloc_to_page(addr);
|
|
/*
|
|
* To do safe access to this _mapped_ area, we need
|
|
* lock. But adding lock here means that we need to add
|
|
* overhead of vmalloc()/vfree() calles for this _debug_
|
|
* interface, rarely used. Instead of that, we'll use
|
|
* kmap() and get small overhead in this access function.
|
|
*/
|
|
if (p) {
|
|
/*
|
|
* we can expect USER0 is not used (see vread/vwrite's
|
|
* function description)
|
|
*/
|
|
void *map = kmap_atomic(p);
|
|
memcpy(map + offset, buf, length);
|
|
kunmap_atomic(map);
|
|
}
|
|
addr += length;
|
|
buf += length;
|
|
copied += length;
|
|
count -= length;
|
|
}
|
|
return copied;
|
|
}
|
|
|
|
/**
|
|
* vread() - read vmalloc area in a safe way.
|
|
* @buf: buffer for reading data
|
|
* @addr: vm address.
|
|
* @count: number of bytes to be read.
|
|
*
|
|
* Returns # of bytes which addr and buf should be increased.
|
|
* (same number to @count). Returns 0 if [addr...addr+count) doesn't
|
|
* includes any intersect with alive vmalloc area.
|
|
*
|
|
* This function checks that addr is a valid vmalloc'ed area, and
|
|
* copy data from that area to a given buffer. If the given memory range
|
|
* of [addr...addr+count) includes some valid address, data is copied to
|
|
* proper area of @buf. If there are memory holes, they'll be zero-filled.
|
|
* IOREMAP area is treated as memory hole and no copy is done.
|
|
*
|
|
* If [addr...addr+count) doesn't includes any intersects with alive
|
|
* vm_struct area, returns 0. @buf should be kernel's buffer.
|
|
*
|
|
* Note: In usual ops, vread() is never necessary because the caller
|
|
* should know vmalloc() area is valid and can use memcpy().
|
|
* This is for routines which have to access vmalloc area without
|
|
* any informaion, as /dev/kmem.
|
|
*
|
|
*/
|
|
|
|
long vread(char *buf, char *addr, unsigned long count)
|
|
{
|
|
struct vmap_area *va;
|
|
struct vm_struct *vm;
|
|
char *vaddr, *buf_start = buf;
|
|
unsigned long buflen = count;
|
|
unsigned long n;
|
|
|
|
/* Don't allow overflow */
|
|
if ((unsigned long) addr + count < count)
|
|
count = -(unsigned long) addr;
|
|
|
|
spin_lock(&vmap_area_lock);
|
|
list_for_each_entry(va, &vmap_area_list, list) {
|
|
if (!count)
|
|
break;
|
|
|
|
if (!(va->flags & VM_VM_AREA))
|
|
continue;
|
|
|
|
vm = va->vm;
|
|
vaddr = (char *) vm->addr;
|
|
if (addr >= vaddr + get_vm_area_size(vm))
|
|
continue;
|
|
while (addr < vaddr) {
|
|
if (count == 0)
|
|
goto finished;
|
|
*buf = '\0';
|
|
buf++;
|
|
addr++;
|
|
count--;
|
|
}
|
|
n = vaddr + get_vm_area_size(vm) - addr;
|
|
if (n > count)
|
|
n = count;
|
|
if (!(vm->flags & VM_IOREMAP))
|
|
aligned_vread(buf, addr, n);
|
|
else /* IOREMAP area is treated as memory hole */
|
|
memset(buf, 0, n);
|
|
buf += n;
|
|
addr += n;
|
|
count -= n;
|
|
}
|
|
finished:
|
|
spin_unlock(&vmap_area_lock);
|
|
|
|
if (buf == buf_start)
|
|
return 0;
|
|
/* zero-fill memory holes */
|
|
if (buf != buf_start + buflen)
|
|
memset(buf, 0, buflen - (buf - buf_start));
|
|
|
|
return buflen;
|
|
}
|
|
|
|
/**
|
|
* vwrite() - write vmalloc area in a safe way.
|
|
* @buf: buffer for source data
|
|
* @addr: vm address.
|
|
* @count: number of bytes to be read.
|
|
*
|
|
* Returns # of bytes which addr and buf should be incresed.
|
|
* (same number to @count).
|
|
* If [addr...addr+count) doesn't includes any intersect with valid
|
|
* vmalloc area, returns 0.
|
|
*
|
|
* This function checks that addr is a valid vmalloc'ed area, and
|
|
* copy data from a buffer to the given addr. If specified range of
|
|
* [addr...addr+count) includes some valid address, data is copied from
|
|
* proper area of @buf. If there are memory holes, no copy to hole.
|
|
* IOREMAP area is treated as memory hole and no copy is done.
|
|
*
|
|
* If [addr...addr+count) doesn't includes any intersects with alive
|
|
* vm_struct area, returns 0. @buf should be kernel's buffer.
|
|
*
|
|
* Note: In usual ops, vwrite() is never necessary because the caller
|
|
* should know vmalloc() area is valid and can use memcpy().
|
|
* This is for routines which have to access vmalloc area without
|
|
* any informaion, as /dev/kmem.
|
|
*/
|
|
|
|
long vwrite(char *buf, char *addr, unsigned long count)
|
|
{
|
|
struct vmap_area *va;
|
|
struct vm_struct *vm;
|
|
char *vaddr;
|
|
unsigned long n, buflen;
|
|
int copied = 0;
|
|
|
|
/* Don't allow overflow */
|
|
if ((unsigned long) addr + count < count)
|
|
count = -(unsigned long) addr;
|
|
buflen = count;
|
|
|
|
spin_lock(&vmap_area_lock);
|
|
list_for_each_entry(va, &vmap_area_list, list) {
|
|
if (!count)
|
|
break;
|
|
|
|
if (!(va->flags & VM_VM_AREA))
|
|
continue;
|
|
|
|
vm = va->vm;
|
|
vaddr = (char *) vm->addr;
|
|
if (addr >= vaddr + get_vm_area_size(vm))
|
|
continue;
|
|
while (addr < vaddr) {
|
|
if (count == 0)
|
|
goto finished;
|
|
buf++;
|
|
addr++;
|
|
count--;
|
|
}
|
|
n = vaddr + get_vm_area_size(vm) - addr;
|
|
if (n > count)
|
|
n = count;
|
|
if (!(vm->flags & VM_IOREMAP)) {
|
|
aligned_vwrite(buf, addr, n);
|
|
copied++;
|
|
}
|
|
buf += n;
|
|
addr += n;
|
|
count -= n;
|
|
}
|
|
finished:
|
|
spin_unlock(&vmap_area_lock);
|
|
if (!copied)
|
|
return 0;
|
|
return buflen;
|
|
}
|
|
|
|
/**
|
|
* remap_vmalloc_range_partial - map vmalloc pages to userspace
|
|
* @vma: vma to cover
|
|
* @uaddr: target user address to start at
|
|
* @kaddr: virtual address of vmalloc kernel memory
|
|
* @size: size of map area
|
|
*
|
|
* Returns: 0 for success, -Exxx on failure
|
|
*
|
|
* This function checks that @kaddr is a valid vmalloc'ed area,
|
|
* and that it is big enough to cover the range starting at
|
|
* @uaddr in @vma. Will return failure if that criteria isn't
|
|
* met.
|
|
*
|
|
* Similar to remap_pfn_range() (see mm/memory.c)
|
|
*/
|
|
int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr,
|
|
void *kaddr, unsigned long size)
|
|
{
|
|
struct vm_struct *area;
|
|
|
|
size = PAGE_ALIGN(size);
|
|
|
|
if (!PAGE_ALIGNED(uaddr) || !PAGE_ALIGNED(kaddr))
|
|
return -EINVAL;
|
|
|
|
area = find_vm_area(kaddr);
|
|
if (!area)
|
|
return -EINVAL;
|
|
|
|
if (!(area->flags & VM_USERMAP))
|
|
return -EINVAL;
|
|
|
|
if (kaddr + size > area->addr + area->size)
|
|
return -EINVAL;
|
|
|
|
do {
|
|
struct page *page = vmalloc_to_page(kaddr);
|
|
int ret;
|
|
|
|
ret = vm_insert_page(vma, uaddr, page);
|
|
if (ret)
|
|
return ret;
|
|
|
|
uaddr += PAGE_SIZE;
|
|
kaddr += PAGE_SIZE;
|
|
size -= PAGE_SIZE;
|
|
} while (size > 0);
|
|
|
|
vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(remap_vmalloc_range_partial);
|
|
|
|
/**
|
|
* remap_vmalloc_range - map vmalloc pages to userspace
|
|
* @vma: vma to cover (map full range of vma)
|
|
* @addr: vmalloc memory
|
|
* @pgoff: number of pages into addr before first page to map
|
|
*
|
|
* Returns: 0 for success, -Exxx on failure
|
|
*
|
|
* This function checks that addr is a valid vmalloc'ed area, and
|
|
* that it is big enough to cover the vma. Will return failure if
|
|
* that criteria isn't met.
|
|
*
|
|
* Similar to remap_pfn_range() (see mm/memory.c)
|
|
*/
|
|
int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
|
|
unsigned long pgoff)
|
|
{
|
|
return remap_vmalloc_range_partial(vma, vma->vm_start,
|
|
addr + (pgoff << PAGE_SHIFT),
|
|
vma->vm_end - vma->vm_start);
|
|
}
|
|
EXPORT_SYMBOL(remap_vmalloc_range);
|
|
|
|
/*
|
|
* Implement a stub for vmalloc_sync_all() if the architecture chose not to
|
|
* have one.
|
|
*/
|
|
void __weak vmalloc_sync_all(void)
|
|
{
|
|
}
|
|
|
|
|
|
static int f(pte_t *pte, pgtable_t table, unsigned long addr, void *data)
|
|
{
|
|
pte_t ***p = data;
|
|
|
|
if (p) {
|
|
*(*p) = pte;
|
|
(*p)++;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/**
|
|
* alloc_vm_area - allocate a range of kernel address space
|
|
* @size: size of the area
|
|
* @ptes: returns the PTEs for the address space
|
|
*
|
|
* Returns: NULL on failure, vm_struct on success
|
|
*
|
|
* This function reserves a range of kernel address space, and
|
|
* allocates pagetables to map that range. No actual mappings
|
|
* are created.
|
|
*
|
|
* If @ptes is non-NULL, pointers to the PTEs (in init_mm)
|
|
* allocated for the VM area are returned.
|
|
*/
|
|
struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
|
|
{
|
|
struct vm_struct *area;
|
|
|
|
area = get_vm_area_caller(size, VM_IOREMAP,
|
|
__builtin_return_address(0));
|
|
if (area == NULL)
|
|
return NULL;
|
|
|
|
/*
|
|
* This ensures that page tables are constructed for this region
|
|
* of kernel virtual address space and mapped into init_mm.
|
|
*/
|
|
if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
|
|
size, f, ptes ? &ptes : NULL)) {
|
|
free_vm_area(area);
|
|
return NULL;
|
|
}
|
|
|
|
return area;
|
|
}
|
|
EXPORT_SYMBOL_GPL(alloc_vm_area);
|
|
|
|
void free_vm_area(struct vm_struct *area)
|
|
{
|
|
struct vm_struct *ret;
|
|
ret = remove_vm_area(area->addr);
|
|
BUG_ON(ret != area);
|
|
kfree(area);
|
|
}
|
|
EXPORT_SYMBOL_GPL(free_vm_area);
|
|
|
|
#ifdef CONFIG_SMP
|
|
static struct vmap_area *node_to_va(struct rb_node *n)
|
|
{
|
|
return n ? rb_entry(n, struct vmap_area, rb_node) : NULL;
|
|
}
|
|
|
|
/**
|
|
* pvm_find_next_prev - find the next and prev vmap_area surrounding @end
|
|
* @end: target address
|
|
* @pnext: out arg for the next vmap_area
|
|
* @pprev: out arg for the previous vmap_area
|
|
*
|
|
* Returns: %true if either or both of next and prev are found,
|
|
* %false if no vmap_area exists
|
|
*
|
|
* Find vmap_areas end addresses of which enclose @end. ie. if not
|
|
* NULL, *pnext->va_end > @end and *pprev->va_end <= @end.
|
|
*/
|
|
static bool pvm_find_next_prev(unsigned long end,
|
|
struct vmap_area **pnext,
|
|
struct vmap_area **pprev)
|
|
{
|
|
struct rb_node *n = vmap_area_root.rb_node;
|
|
struct vmap_area *va = NULL;
|
|
|
|
while (n) {
|
|
va = rb_entry(n, struct vmap_area, rb_node);
|
|
if (end < va->va_end)
|
|
n = n->rb_left;
|
|
else if (end > va->va_end)
|
|
n = n->rb_right;
|
|
else
|
|
break;
|
|
}
|
|
|
|
if (!va)
|
|
return false;
|
|
|
|
if (va->va_end > end) {
|
|
*pnext = va;
|
|
*pprev = node_to_va(rb_prev(&(*pnext)->rb_node));
|
|
} else {
|
|
*pprev = va;
|
|
*pnext = node_to_va(rb_next(&(*pprev)->rb_node));
|
|
}
|
|
return true;
|
|
}
|
|
|
|
/**
|
|
* pvm_determine_end - find the highest aligned address between two vmap_areas
|
|
* @pnext: in/out arg for the next vmap_area
|
|
* @pprev: in/out arg for the previous vmap_area
|
|
* @align: alignment
|
|
*
|
|
* Returns: determined end address
|
|
*
|
|
* Find the highest aligned address between *@pnext and *@pprev below
|
|
* VMALLOC_END. *@pnext and *@pprev are adjusted so that the aligned
|
|
* down address is between the end addresses of the two vmap_areas.
|
|
*
|
|
* Please note that the address returned by this function may fall
|
|
* inside *@pnext vmap_area. The caller is responsible for checking
|
|
* that.
|
|
*/
|
|
static unsigned long pvm_determine_end(struct vmap_area **pnext,
|
|
struct vmap_area **pprev,
|
|
unsigned long align)
|
|
{
|
|
const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1);
|
|
unsigned long addr;
|
|
|
|
if (*pnext)
|
|
addr = min((*pnext)->va_start & ~(align - 1), vmalloc_end);
|
|
else
|
|
addr = vmalloc_end;
|
|
|
|
while (*pprev && (*pprev)->va_end > addr) {
|
|
*pnext = *pprev;
|
|
*pprev = node_to_va(rb_prev(&(*pnext)->rb_node));
|
|
}
|
|
|
|
return addr;
|
|
}
|
|
|
|
/**
|
|
* pcpu_get_vm_areas - allocate vmalloc areas for percpu allocator
|
|
* @offsets: array containing offset of each area
|
|
* @sizes: array containing size of each area
|
|
* @nr_vms: the number of areas to allocate
|
|
* @align: alignment, all entries in @offsets and @sizes must be aligned to this
|
|
*
|
|
* Returns: kmalloc'd vm_struct pointer array pointing to allocated
|
|
* vm_structs on success, %NULL on failure
|
|
*
|
|
* Percpu allocator wants to use congruent vm areas so that it can
|
|
* maintain the offsets among percpu areas. This function allocates
|
|
* congruent vmalloc areas for it with GFP_KERNEL. These areas tend to
|
|
* be scattered pretty far, distance between two areas easily going up
|
|
* to gigabytes. To avoid interacting with regular vmallocs, these
|
|
* areas are allocated from top.
|
|
*
|
|
* Despite its complicated look, this allocator is rather simple. It
|
|
* does everything top-down and scans areas from the end looking for
|
|
* matching slot. While scanning, if any of the areas overlaps with
|
|
* existing vmap_area, the base address is pulled down to fit the
|
|
* area. Scanning is repeated till all the areas fit and then all
|
|
* necessary data structres are inserted and the result is returned.
|
|
*/
|
|
struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
|
|
const size_t *sizes, int nr_vms,
|
|
size_t align)
|
|
{
|
|
const unsigned long vmalloc_start = ALIGN(VMALLOC_START, align);
|
|
const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1);
|
|
struct vmap_area **vas, *prev, *next;
|
|
struct vm_struct **vms;
|
|
int area, area2, last_area, term_area;
|
|
unsigned long base, start, end, last_end;
|
|
bool purged = false;
|
|
|
|
/* verify parameters and allocate data structures */
|
|
BUG_ON(align & ~PAGE_MASK || !is_power_of_2(align));
|
|
for (last_area = 0, area = 0; area < nr_vms; area++) {
|
|
start = offsets[area];
|
|
end = start + sizes[area];
|
|
|
|
/* is everything aligned properly? */
|
|
BUG_ON(!IS_ALIGNED(offsets[area], align));
|
|
BUG_ON(!IS_ALIGNED(sizes[area], align));
|
|
|
|
/* detect the area with the highest address */
|
|
if (start > offsets[last_area])
|
|
last_area = area;
|
|
|
|
for (area2 = 0; area2 < nr_vms; area2++) {
|
|
unsigned long start2 = offsets[area2];
|
|
unsigned long end2 = start2 + sizes[area2];
|
|
|
|
if (area2 == area)
|
|
continue;
|
|
|
|
BUG_ON(start2 >= start && start2 < end);
|
|
BUG_ON(end2 <= end && end2 > start);
|
|
}
|
|
}
|
|
last_end = offsets[last_area] + sizes[last_area];
|
|
|
|
if (vmalloc_end - vmalloc_start < last_end) {
|
|
WARN_ON(true);
|
|
return NULL;
|
|
}
|
|
|
|
vms = kcalloc(nr_vms, sizeof(vms[0]), GFP_KERNEL);
|
|
vas = kcalloc(nr_vms, sizeof(vas[0]), GFP_KERNEL);
|
|
if (!vas || !vms)
|
|
goto err_free2;
|
|
|
|
for (area = 0; area < nr_vms; area++) {
|
|
vas[area] = kzalloc(sizeof(struct vmap_area), GFP_KERNEL);
|
|
vms[area] = kzalloc(sizeof(struct vm_struct), GFP_KERNEL);
|
|
if (!vas[area] || !vms[area])
|
|
goto err_free;
|
|
}
|
|
retry:
|
|
spin_lock(&vmap_area_lock);
|
|
|
|
/* start scanning - we scan from the top, begin with the last area */
|
|
area = term_area = last_area;
|
|
start = offsets[area];
|
|
end = start + sizes[area];
|
|
|
|
if (!pvm_find_next_prev(vmap_area_pcpu_hole, &next, &prev)) {
|
|
base = vmalloc_end - last_end;
|
|
goto found;
|
|
}
|
|
base = pvm_determine_end(&next, &prev, align) - end;
|
|
|
|
while (true) {
|
|
BUG_ON(next && next->va_end <= base + end);
|
|
BUG_ON(prev && prev->va_end > base + end);
|
|
|
|
/*
|
|
* base might have underflowed, add last_end before
|
|
* comparing.
|
|
*/
|
|
if (base + last_end < vmalloc_start + last_end) {
|
|
spin_unlock(&vmap_area_lock);
|
|
if (!purged) {
|
|
purge_vmap_area_lazy();
|
|
purged = true;
|
|
goto retry;
|
|
}
|
|
goto err_free;
|
|
}
|
|
|
|
/*
|
|
* If next overlaps, move base downwards so that it's
|
|
* right below next and then recheck.
|
|
*/
|
|
if (next && next->va_start < base + end) {
|
|
base = pvm_determine_end(&next, &prev, align) - end;
|
|
term_area = area;
|
|
continue;
|
|
}
|
|
|
|
/*
|
|
* If prev overlaps, shift down next and prev and move
|
|
* base so that it's right below new next and then
|
|
* recheck.
|
|
*/
|
|
if (prev && prev->va_end > base + start) {
|
|
next = prev;
|
|
prev = node_to_va(rb_prev(&next->rb_node));
|
|
base = pvm_determine_end(&next, &prev, align) - end;
|
|
term_area = area;
|
|
continue;
|
|
}
|
|
|
|
/*
|
|
* This area fits, move on to the previous one. If
|
|
* the previous one is the terminal one, we're done.
|
|
*/
|
|
area = (area + nr_vms - 1) % nr_vms;
|
|
if (area == term_area)
|
|
break;
|
|
start = offsets[area];
|
|
end = start + sizes[area];
|
|
pvm_find_next_prev(base + end, &next, &prev);
|
|
}
|
|
found:
|
|
/* we've found a fitting base, insert all va's */
|
|
for (area = 0; area < nr_vms; area++) {
|
|
struct vmap_area *va = vas[area];
|
|
|
|
va->va_start = base + offsets[area];
|
|
va->va_end = va->va_start + sizes[area];
|
|
__insert_vmap_area(va);
|
|
}
|
|
|
|
vmap_area_pcpu_hole = base + offsets[last_area];
|
|
|
|
spin_unlock(&vmap_area_lock);
|
|
|
|
/* insert all vm's */
|
|
for (area = 0; area < nr_vms; area++)
|
|
setup_vmalloc_vm(vms[area], vas[area], VM_ALLOC,
|
|
pcpu_get_vm_areas);
|
|
|
|
kfree(vas);
|
|
return vms;
|
|
|
|
err_free:
|
|
for (area = 0; area < nr_vms; area++) {
|
|
kfree(vas[area]);
|
|
kfree(vms[area]);
|
|
}
|
|
err_free2:
|
|
kfree(vas);
|
|
kfree(vms);
|
|
return NULL;
|
|
}
|
|
|
|
/**
|
|
* pcpu_free_vm_areas - free vmalloc areas for percpu allocator
|
|
* @vms: vm_struct pointer array returned by pcpu_get_vm_areas()
|
|
* @nr_vms: the number of allocated areas
|
|
*
|
|
* Free vm_structs and the array allocated by pcpu_get_vm_areas().
|
|
*/
|
|
void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < nr_vms; i++)
|
|
free_vm_area(vms[i]);
|
|
kfree(vms);
|
|
}
|
|
#endif /* CONFIG_SMP */
|
|
|
|
#ifdef CONFIG_PROC_FS
|
|
static void *s_start(struct seq_file *m, loff_t *pos)
|
|
__acquires(&vmap_area_lock)
|
|
{
|
|
loff_t n = *pos;
|
|
struct vmap_area *va;
|
|
|
|
spin_lock(&vmap_area_lock);
|
|
va = list_entry((&vmap_area_list)->next, typeof(*va), list);
|
|
while (n > 0 && &va->list != &vmap_area_list) {
|
|
n--;
|
|
va = list_entry(va->list.next, typeof(*va), list);
|
|
}
|
|
if (!n && &va->list != &vmap_area_list)
|
|
return va;
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
static void *s_next(struct seq_file *m, void *p, loff_t *pos)
|
|
{
|
|
struct vmap_area *va = p, *next;
|
|
|
|
++*pos;
|
|
next = list_entry(va->list.next, typeof(*va), list);
|
|
if (&next->list != &vmap_area_list)
|
|
return next;
|
|
|
|
return NULL;
|
|
}
|
|
|
|
static void s_stop(struct seq_file *m, void *p)
|
|
__releases(&vmap_area_lock)
|
|
{
|
|
spin_unlock(&vmap_area_lock);
|
|
}
|
|
|
|
static void show_numa_info(struct seq_file *m, struct vm_struct *v)
|
|
{
|
|
if (IS_ENABLED(CONFIG_NUMA)) {
|
|
unsigned int nr, *counters = m->private;
|
|
|
|
if (!counters)
|
|
return;
|
|
|
|
if (v->flags & VM_UNINITIALIZED)
|
|
return;
|
|
/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
|
|
smp_rmb();
|
|
|
|
memset(counters, 0, nr_node_ids * sizeof(unsigned int));
|
|
|
|
for (nr = 0; nr < v->nr_pages; nr++)
|
|
counters[page_to_nid(v->pages[nr])]++;
|
|
|
|
for_each_node_state(nr, N_HIGH_MEMORY)
|
|
if (counters[nr])
|
|
seq_printf(m, " N%u=%u", nr, counters[nr]);
|
|
}
|
|
}
|
|
|
|
static int s_show(struct seq_file *m, void *p)
|
|
{
|
|
struct vmap_area *va = p;
|
|
struct vm_struct *v;
|
|
|
|
/*
|
|
* s_show can encounter race with remove_vm_area, !VM_VM_AREA on
|
|
* behalf of vmap area is being tear down or vm_map_ram allocation.
|
|
*/
|
|
if (!(va->flags & VM_VM_AREA))
|
|
return 0;
|
|
|
|
v = va->vm;
|
|
|
|
seq_printf(m, "0x%pK-0x%pK %7ld",
|
|
v->addr, v->addr + v->size, v->size);
|
|
|
|
if (v->caller)
|
|
seq_printf(m, " %pS", v->caller);
|
|
|
|
if (v->nr_pages)
|
|
seq_printf(m, " pages=%d", v->nr_pages);
|
|
|
|
if (v->phys_addr)
|
|
seq_printf(m, " phys=%llx", (unsigned long long)v->phys_addr);
|
|
|
|
if (v->flags & VM_IOREMAP)
|
|
seq_puts(m, " ioremap");
|
|
|
|
if (v->flags & VM_ALLOC)
|
|
seq_puts(m, " vmalloc");
|
|
|
|
if (v->flags & VM_MAP)
|
|
seq_puts(m, " vmap");
|
|
|
|
if (v->flags & VM_USERMAP)
|
|
seq_puts(m, " user");
|
|
|
|
if (v->flags & VM_VPAGES)
|
|
seq_puts(m, " vpages");
|
|
|
|
show_numa_info(m, v);
|
|
seq_putc(m, '\n');
|
|
return 0;
|
|
}
|
|
|
|
static const struct seq_operations vmalloc_op = {
|
|
.start = s_start,
|
|
.next = s_next,
|
|
.stop = s_stop,
|
|
.show = s_show,
|
|
};
|
|
|
|
static int vmalloc_open(struct inode *inode, struct file *file)
|
|
{
|
|
if (IS_ENABLED(CONFIG_NUMA))
|
|
return seq_open_private(file, &vmalloc_op,
|
|
nr_node_ids * sizeof(unsigned int));
|
|
else
|
|
return seq_open(file, &vmalloc_op);
|
|
}
|
|
|
|
static const struct file_operations proc_vmalloc_operations = {
|
|
.open = vmalloc_open,
|
|
.read = seq_read,
|
|
.llseek = seq_lseek,
|
|
.release = seq_release_private,
|
|
};
|
|
|
|
static int __init proc_vmalloc_init(void)
|
|
{
|
|
proc_create("vmallocinfo", S_IRUSR, NULL, &proc_vmalloc_operations);
|
|
return 0;
|
|
}
|
|
module_init(proc_vmalloc_init);
|
|
|
|
void get_vmalloc_info(struct vmalloc_info *vmi)
|
|
{
|
|
struct vmap_area *va;
|
|
unsigned long free_area_size;
|
|
unsigned long prev_end;
|
|
|
|
vmi->used = 0;
|
|
vmi->largest_chunk = 0;
|
|
|
|
prev_end = VMALLOC_START;
|
|
|
|
rcu_read_lock();
|
|
|
|
if (list_empty(&vmap_area_list)) {
|
|
vmi->largest_chunk = VMALLOC_TOTAL;
|
|
goto out;
|
|
}
|
|
|
|
list_for_each_entry_rcu(va, &vmap_area_list, list) {
|
|
unsigned long addr = va->va_start;
|
|
|
|
/*
|
|
* Some archs keep another range for modules in vmalloc space
|
|
*/
|
|
if (addr < VMALLOC_START)
|
|
continue;
|
|
if (addr >= VMALLOC_END)
|
|
break;
|
|
|
|
if (va->flags & (VM_LAZY_FREE | VM_LAZY_FREEING))
|
|
continue;
|
|
|
|
vmi->used += (va->va_end - va->va_start);
|
|
|
|
free_area_size = addr - prev_end;
|
|
if (vmi->largest_chunk < free_area_size)
|
|
vmi->largest_chunk = free_area_size;
|
|
|
|
prev_end = va->va_end;
|
|
}
|
|
|
|
if (VMALLOC_END - prev_end > vmi->largest_chunk)
|
|
vmi->largest_chunk = VMALLOC_END - prev_end;
|
|
|
|
out:
|
|
rcu_read_unlock();
|
|
}
|
|
#endif
|
|
|