mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 09:19:51 +00:00
![Michal Hocko](/assets/img/avatar_default.png)
__GFP_REPEAT was designed to allow retry-but-eventually-fail semantic to the page allocator. This has been true but only for allocations requests larger than PAGE_ALLOC_COSTLY_ORDER. It has been always ignored for smaller sizes. This is a bit unfortunate because there is no way to express the same semantic for those requests and they are considered too important to fail so they might end up looping in the page allocator for ever, similarly to GFP_NOFAIL requests. Now that the whole tree has been cleaned up and accidental or misled usage of __GFP_REPEAT flag has been removed for !costly requests we can give the original flag a better name and more importantly a more useful semantic. Let's rename it to __GFP_RETRY_MAYFAIL which tells the user that the allocator would try really hard but there is no promise of a success. This will work independent of the order and overrides the default allocator behavior. Page allocator users have several levels of guarantee vs. cost options (take GFP_KERNEL as an example) - GFP_KERNEL & ~__GFP_RECLAIM - optimistic allocation without _any_ attempt to free memory at all. The most light weight mode which even doesn't kick the background reclaim. Should be used carefully because it might deplete the memory and the next user might hit the more aggressive reclaim - GFP_KERNEL & ~__GFP_DIRECT_RECLAIM (or GFP_NOWAIT)- optimistic allocation without any attempt to free memory from the current context but can wake kswapd to reclaim memory if the zone is below the low watermark. Can be used from either atomic contexts or when the request is a performance optimization and there is another fallback for a slow path. - (GFP_KERNEL|__GFP_HIGH) & ~__GFP_DIRECT_RECLAIM (aka GFP_ATOMIC) - non sleeping allocation with an expensive fallback so it can access some portion of memory reserves. Usually used from interrupt/bh context with an expensive slow path fallback. - GFP_KERNEL - both background and direct reclaim are allowed and the _default_ page allocator behavior is used. That means that !costly allocation requests are basically nofail but there is no guarantee of that behavior so failures have to be checked properly by callers (e.g. OOM killer victim is allowed to fail currently). - GFP_KERNEL | __GFP_NORETRY - overrides the default allocator behavior and all allocation requests fail early rather than cause disruptive reclaim (one round of reclaim in this implementation). The OOM killer is not invoked. - GFP_KERNEL | __GFP_RETRY_MAYFAIL - overrides the default allocator behavior and all allocation requests try really hard. The request will fail if the reclaim cannot make any progress. The OOM killer won't be triggered. - GFP_KERNEL | __GFP_NOFAIL - overrides the default allocator behavior and all allocation requests will loop endlessly until they succeed. This might be really dangerous especially for larger orders. Existing users of __GFP_REPEAT are changed to __GFP_RETRY_MAYFAIL because they already had their semantic. No new users are added. __alloc_pages_slowpath is changed to bail out for __GFP_RETRY_MAYFAIL if there is no progress and we have already passed the OOM point. This means that all the reclaim opportunities have been exhausted except the most disruptive one (the OOM killer) and a user defined fallback behavior is more sensible than keep retrying in the page allocator. [akpm@linux-foundation.org: fix arch/sparc/kernel/mdesc.c] [mhocko@suse.com: semantic fix] Link: http://lkml.kernel.org/r/20170626123847.GM11534@dhcp22.suse.cz [mhocko@kernel.org: address other thing spotted by Vlastimil] Link: http://lkml.kernel.org/r/20170626124233.GN11534@dhcp22.suse.cz Link: http://lkml.kernel.org/r/20170623085345.11304-3-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Alex Belits <alex.belits@cavium.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Darrick J. Wong <darrick.wong@oracle.com> Cc: David Daney <david.daney@cavium.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: NeilBrown <neilb@suse.com> Cc: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
323 lines
8.2 KiB
C
323 lines
8.2 KiB
C
/*
|
|
* Virtual Memory Map support
|
|
*
|
|
* (C) 2007 sgi. Christoph Lameter.
|
|
*
|
|
* Virtual memory maps allow VM primitives pfn_to_page, page_to_pfn,
|
|
* virt_to_page, page_address() to be implemented as a base offset
|
|
* calculation without memory access.
|
|
*
|
|
* However, virtual mappings need a page table and TLBs. Many Linux
|
|
* architectures already map their physical space using 1-1 mappings
|
|
* via TLBs. For those arches the virtual memory map is essentially
|
|
* for free if we use the same page size as the 1-1 mappings. In that
|
|
* case the overhead consists of a few additional pages that are
|
|
* allocated to create a view of memory for vmemmap.
|
|
*
|
|
* The architecture is expected to provide a vmemmap_populate() function
|
|
* to instantiate the mapping.
|
|
*/
|
|
#include <linux/mm.h>
|
|
#include <linux/mmzone.h>
|
|
#include <linux/bootmem.h>
|
|
#include <linux/memremap.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/sched.h>
|
|
#include <asm/dma.h>
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/pgtable.h>
|
|
|
|
/*
|
|
* Allocate a block of memory to be used to back the virtual memory map
|
|
* or to back the page tables that are used to create the mapping.
|
|
* Uses the main allocators if they are available, else bootmem.
|
|
*/
|
|
|
|
static void * __ref __earlyonly_bootmem_alloc(int node,
|
|
unsigned long size,
|
|
unsigned long align,
|
|
unsigned long goal)
|
|
{
|
|
return memblock_virt_alloc_try_nid(size, align, goal,
|
|
BOOTMEM_ALLOC_ACCESSIBLE, node);
|
|
}
|
|
|
|
static void *vmemmap_buf;
|
|
static void *vmemmap_buf_end;
|
|
|
|
void * __meminit vmemmap_alloc_block(unsigned long size, int node)
|
|
{
|
|
/* If the main allocator is up use that, fallback to bootmem. */
|
|
if (slab_is_available()) {
|
|
struct page *page;
|
|
|
|
if (node_state(node, N_HIGH_MEMORY))
|
|
page = alloc_pages_node(
|
|
node, GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL,
|
|
get_order(size));
|
|
else
|
|
page = alloc_pages(
|
|
GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL,
|
|
get_order(size));
|
|
if (page)
|
|
return page_address(page);
|
|
return NULL;
|
|
} else
|
|
return __earlyonly_bootmem_alloc(node, size, size,
|
|
__pa(MAX_DMA_ADDRESS));
|
|
}
|
|
|
|
/* need to make sure size is all the same during early stage */
|
|
static void * __meminit alloc_block_buf(unsigned long size, int node)
|
|
{
|
|
void *ptr;
|
|
|
|
if (!vmemmap_buf)
|
|
return vmemmap_alloc_block(size, node);
|
|
|
|
/* take the from buf */
|
|
ptr = (void *)ALIGN((unsigned long)vmemmap_buf, size);
|
|
if (ptr + size > vmemmap_buf_end)
|
|
return vmemmap_alloc_block(size, node);
|
|
|
|
vmemmap_buf = ptr + size;
|
|
|
|
return ptr;
|
|
}
|
|
|
|
static unsigned long __meminit vmem_altmap_next_pfn(struct vmem_altmap *altmap)
|
|
{
|
|
return altmap->base_pfn + altmap->reserve + altmap->alloc
|
|
+ altmap->align;
|
|
}
|
|
|
|
static unsigned long __meminit vmem_altmap_nr_free(struct vmem_altmap *altmap)
|
|
{
|
|
unsigned long allocated = altmap->alloc + altmap->align;
|
|
|
|
if (altmap->free > allocated)
|
|
return altmap->free - allocated;
|
|
return 0;
|
|
}
|
|
|
|
/**
|
|
* vmem_altmap_alloc - allocate pages from the vmem_altmap reservation
|
|
* @altmap - reserved page pool for the allocation
|
|
* @nr_pfns - size (in pages) of the allocation
|
|
*
|
|
* Allocations are aligned to the size of the request
|
|
*/
|
|
static unsigned long __meminit vmem_altmap_alloc(struct vmem_altmap *altmap,
|
|
unsigned long nr_pfns)
|
|
{
|
|
unsigned long pfn = vmem_altmap_next_pfn(altmap);
|
|
unsigned long nr_align;
|
|
|
|
nr_align = 1UL << find_first_bit(&nr_pfns, BITS_PER_LONG);
|
|
nr_align = ALIGN(pfn, nr_align) - pfn;
|
|
|
|
if (nr_pfns + nr_align > vmem_altmap_nr_free(altmap))
|
|
return ULONG_MAX;
|
|
altmap->alloc += nr_pfns;
|
|
altmap->align += nr_align;
|
|
return pfn + nr_align;
|
|
}
|
|
|
|
static void * __meminit altmap_alloc_block_buf(unsigned long size,
|
|
struct vmem_altmap *altmap)
|
|
{
|
|
unsigned long pfn, nr_pfns;
|
|
void *ptr;
|
|
|
|
if (size & ~PAGE_MASK) {
|
|
pr_warn_once("%s: allocations must be multiple of PAGE_SIZE (%ld)\n",
|
|
__func__, size);
|
|
return NULL;
|
|
}
|
|
|
|
nr_pfns = size >> PAGE_SHIFT;
|
|
pfn = vmem_altmap_alloc(altmap, nr_pfns);
|
|
if (pfn < ULONG_MAX)
|
|
ptr = __va(__pfn_to_phys(pfn));
|
|
else
|
|
ptr = NULL;
|
|
pr_debug("%s: pfn: %#lx alloc: %ld align: %ld nr: %#lx\n",
|
|
__func__, pfn, altmap->alloc, altmap->align, nr_pfns);
|
|
|
|
return ptr;
|
|
}
|
|
|
|
/* need to make sure size is all the same during early stage */
|
|
void * __meminit __vmemmap_alloc_block_buf(unsigned long size, int node,
|
|
struct vmem_altmap *altmap)
|
|
{
|
|
if (altmap)
|
|
return altmap_alloc_block_buf(size, altmap);
|
|
return alloc_block_buf(size, node);
|
|
}
|
|
|
|
void __meminit vmemmap_verify(pte_t *pte, int node,
|
|
unsigned long start, unsigned long end)
|
|
{
|
|
unsigned long pfn = pte_pfn(*pte);
|
|
int actual_node = early_pfn_to_nid(pfn);
|
|
|
|
if (node_distance(actual_node, node) > LOCAL_DISTANCE)
|
|
pr_warn("[%lx-%lx] potential offnode page_structs\n",
|
|
start, end - 1);
|
|
}
|
|
|
|
pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node)
|
|
{
|
|
pte_t *pte = pte_offset_kernel(pmd, addr);
|
|
if (pte_none(*pte)) {
|
|
pte_t entry;
|
|
void *p = alloc_block_buf(PAGE_SIZE, node);
|
|
if (!p)
|
|
return NULL;
|
|
entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
|
|
set_pte_at(&init_mm, addr, pte, entry);
|
|
}
|
|
return pte;
|
|
}
|
|
|
|
pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node)
|
|
{
|
|
pmd_t *pmd = pmd_offset(pud, addr);
|
|
if (pmd_none(*pmd)) {
|
|
void *p = vmemmap_alloc_block(PAGE_SIZE, node);
|
|
if (!p)
|
|
return NULL;
|
|
pmd_populate_kernel(&init_mm, pmd, p);
|
|
}
|
|
return pmd;
|
|
}
|
|
|
|
pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node)
|
|
{
|
|
pud_t *pud = pud_offset(p4d, addr);
|
|
if (pud_none(*pud)) {
|
|
void *p = vmemmap_alloc_block(PAGE_SIZE, node);
|
|
if (!p)
|
|
return NULL;
|
|
pud_populate(&init_mm, pud, p);
|
|
}
|
|
return pud;
|
|
}
|
|
|
|
p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node)
|
|
{
|
|
p4d_t *p4d = p4d_offset(pgd, addr);
|
|
if (p4d_none(*p4d)) {
|
|
void *p = vmemmap_alloc_block(PAGE_SIZE, node);
|
|
if (!p)
|
|
return NULL;
|
|
p4d_populate(&init_mm, p4d, p);
|
|
}
|
|
return p4d;
|
|
}
|
|
|
|
pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
|
|
{
|
|
pgd_t *pgd = pgd_offset_k(addr);
|
|
if (pgd_none(*pgd)) {
|
|
void *p = vmemmap_alloc_block(PAGE_SIZE, node);
|
|
if (!p)
|
|
return NULL;
|
|
pgd_populate(&init_mm, pgd, p);
|
|
}
|
|
return pgd;
|
|
}
|
|
|
|
int __meminit vmemmap_populate_basepages(unsigned long start,
|
|
unsigned long end, int node)
|
|
{
|
|
unsigned long addr = start;
|
|
pgd_t *pgd;
|
|
p4d_t *p4d;
|
|
pud_t *pud;
|
|
pmd_t *pmd;
|
|
pte_t *pte;
|
|
|
|
for (; addr < end; addr += PAGE_SIZE) {
|
|
pgd = vmemmap_pgd_populate(addr, node);
|
|
if (!pgd)
|
|
return -ENOMEM;
|
|
p4d = vmemmap_p4d_populate(pgd, addr, node);
|
|
if (!p4d)
|
|
return -ENOMEM;
|
|
pud = vmemmap_pud_populate(p4d, addr, node);
|
|
if (!pud)
|
|
return -ENOMEM;
|
|
pmd = vmemmap_pmd_populate(pud, addr, node);
|
|
if (!pmd)
|
|
return -ENOMEM;
|
|
pte = vmemmap_pte_populate(pmd, addr, node);
|
|
if (!pte)
|
|
return -ENOMEM;
|
|
vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
struct page * __meminit sparse_mem_map_populate(unsigned long pnum, int nid)
|
|
{
|
|
unsigned long start;
|
|
unsigned long end;
|
|
struct page *map;
|
|
|
|
map = pfn_to_page(pnum * PAGES_PER_SECTION);
|
|
start = (unsigned long)map;
|
|
end = (unsigned long)(map + PAGES_PER_SECTION);
|
|
|
|
if (vmemmap_populate(start, end, nid))
|
|
return NULL;
|
|
|
|
return map;
|
|
}
|
|
|
|
void __init sparse_mem_maps_populate_node(struct page **map_map,
|
|
unsigned long pnum_begin,
|
|
unsigned long pnum_end,
|
|
unsigned long map_count, int nodeid)
|
|
{
|
|
unsigned long pnum;
|
|
unsigned long size = sizeof(struct page) * PAGES_PER_SECTION;
|
|
void *vmemmap_buf_start;
|
|
|
|
size = ALIGN(size, PMD_SIZE);
|
|
vmemmap_buf_start = __earlyonly_bootmem_alloc(nodeid, size * map_count,
|
|
PMD_SIZE, __pa(MAX_DMA_ADDRESS));
|
|
|
|
if (vmemmap_buf_start) {
|
|
vmemmap_buf = vmemmap_buf_start;
|
|
vmemmap_buf_end = vmemmap_buf_start + size * map_count;
|
|
}
|
|
|
|
for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
|
|
struct mem_section *ms;
|
|
|
|
if (!present_section_nr(pnum))
|
|
continue;
|
|
|
|
map_map[pnum] = sparse_mem_map_populate(pnum, nodeid);
|
|
if (map_map[pnum])
|
|
continue;
|
|
ms = __nr_to_section(pnum);
|
|
pr_err("%s: sparsemem memory map backing failed some memory will not be available\n",
|
|
__func__);
|
|
ms->section_mem_map = 0;
|
|
}
|
|
|
|
if (vmemmap_buf_start) {
|
|
/* need to free left buf */
|
|
memblock_free_early(__pa(vmemmap_buf),
|
|
vmemmap_buf_end - vmemmap_buf);
|
|
vmemmap_buf = NULL;
|
|
vmemmap_buf_end = NULL;
|
|
}
|
|
}
|