diff options
Diffstat (limited to 'include/linux/gfp.h')
| -rw-r--r-- | include/linux/gfp.h | 609 |
1 files changed, 215 insertions, 394 deletions
diff --git a/include/linux/gfp.h b/include/linux/gfp.h index c603237e006c..be160e8d8bcb 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -2,313 +2,15 @@ #ifndef __LINUX_GFP_H #define __LINUX_GFP_H -#include <linux/mmdebug.h> +#include <linux/gfp_types.h> + #include <linux/mmzone.h> -#include <linux/stddef.h> -#include <linux/linkage.h> #include <linux/topology.h> +#include <linux/alloc_tag.h> +#include <linux/sched.h> struct vm_area_struct; - -/* - * In case of changes, please don't forget to update - * include/trace/events/mmflags.h and tools/perf/builtin-kmem.c - */ - -/* Plain integer GFP bitmasks. Do not use this directly. */ -#define ___GFP_DMA 0x01u -#define ___GFP_HIGHMEM 0x02u -#define ___GFP_DMA32 0x04u -#define ___GFP_MOVABLE 0x08u -#define ___GFP_RECLAIMABLE 0x10u -#define ___GFP_HIGH 0x20u -#define ___GFP_IO 0x40u -#define ___GFP_FS 0x80u -#define ___GFP_ZERO 0x100u -#define ___GFP_ATOMIC 0x200u -#define ___GFP_DIRECT_RECLAIM 0x400u -#define ___GFP_KSWAPD_RECLAIM 0x800u -#define ___GFP_WRITE 0x1000u -#define ___GFP_NOWARN 0x2000u -#define ___GFP_RETRY_MAYFAIL 0x4000u -#define ___GFP_NOFAIL 0x8000u -#define ___GFP_NORETRY 0x10000u -#define ___GFP_MEMALLOC 0x20000u -#define ___GFP_COMP 0x40000u -#define ___GFP_NOMEMALLOC 0x80000u -#define ___GFP_HARDWALL 0x100000u -#define ___GFP_THISNODE 0x200000u -#define ___GFP_ACCOUNT 0x400000u -#ifdef CONFIG_LOCKDEP -#define ___GFP_NOLOCKDEP 0x800000u -#else -#define ___GFP_NOLOCKDEP 0 -#endif -/* If the above are modified, __GFP_BITS_SHIFT may need updating */ - -/* - * Physical address zone modifiers (see linux/mmzone.h - low four bits) - * - * Do not put any conditional on these. If necessary modify the definitions - * without the underscores and use them consistently. The definitions here may - * be used in bit comparisons. - */ -#define __GFP_DMA ((__force gfp_t)___GFP_DMA) -#define __GFP_HIGHMEM ((__force gfp_t)___GFP_HIGHMEM) -#define __GFP_DMA32 ((__force gfp_t)___GFP_DMA32) -#define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* ZONE_MOVABLE allowed */ -#define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE) - -/** - * DOC: Page mobility and placement hints - * - * Page mobility and placement hints - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * These flags provide hints about how mobile the page is. Pages with similar - * mobility are placed within the same pageblocks to minimise problems due - * to external fragmentation. - * - * %__GFP_MOVABLE (also a zone modifier) indicates that the page can be - * moved by page migration during memory compaction or can be reclaimed. - * - * %__GFP_RECLAIMABLE is used for slab allocations that specify - * SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers. - * - * %__GFP_WRITE indicates the caller intends to dirty the page. Where possible, - * these pages will be spread between local zones to avoid all the dirty - * pages being in one zone (fair zone allocation policy). - * - * %__GFP_HARDWALL enforces the cpuset memory allocation policy. - * - * %__GFP_THISNODE forces the allocation to be satisfied from the requested - * node with no fallbacks or placement policy enforcements. - * - * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg. - */ -#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) -#define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) -#define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) -#define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE) -#define __GFP_ACCOUNT ((__force gfp_t)___GFP_ACCOUNT) - -/** - * DOC: Watermark modifiers - * - * Watermark modifiers -- controls access to emergency reserves - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * %__GFP_HIGH indicates that the caller is high-priority and that granting - * the request is necessary before the system can make forward progress. - * For example, creating an IO context to clean pages. - * - * %__GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is - * high priority. Users are typically interrupt handlers. This may be - * used in conjunction with %__GFP_HIGH - * - * %__GFP_MEMALLOC allows access to all memory. This should only be used when - * the caller guarantees the allocation will allow more memory to be freed - * very shortly e.g. process exiting or swapping. Users either should - * be the MM or co-ordinating closely with the VM (e.g. swap over NFS). - * Users of this flag have to be extremely careful to not deplete the reserve - * completely and implement a throttling mechanism which controls the - * consumption of the reserve based on the amount of freed memory. - * Usage of a pre-allocated pool (e.g. mempool) should be always considered - * before using this flag. - * - * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves. - * This takes precedence over the %__GFP_MEMALLOC flag if both are set. - */ -#define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC) -#define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) -#define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC) -#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) - -/** - * DOC: Reclaim modifiers - * - * Reclaim modifiers - * ~~~~~~~~~~~~~~~~~ - * Please note that all the following flags are only applicable to sleepable - * allocations (e.g. %GFP_NOWAIT and %GFP_ATOMIC will ignore them). - * - * %__GFP_IO can start physical IO. - * - * %__GFP_FS can call down to the low-level FS. Clearing the flag avoids the - * allocator recursing into the filesystem which might already be holding - * locks. - * - * %__GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim. - * This flag can be cleared to avoid unnecessary delays when a fallback - * option is available. - * - * %__GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when - * the low watermark is reached and have it reclaim pages until the high - * watermark is reached. A caller may wish to clear this flag when fallback - * options are available and the reclaim is likely to disrupt the system. The - * canonical example is THP allocation where a fallback is cheap but - * reclaim/compaction may cause indirect stalls. - * - * %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim. - * - * The default allocator behavior depends on the request size. We have a concept - * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER). - * !costly allocations are too essential to fail so they are implicitly - * non-failing by default (with some exceptions like OOM victims might fail so - * the caller still has to check for failures) while costly requests try to be - * not disruptive and back off even without invoking the OOM killer. - * The following three modifiers might be used to override some of these - * implicit rules - * - * %__GFP_NORETRY: The VM implementation will try only very lightweight - * memory direct reclaim to get some memory under memory pressure (thus - * it can sleep). It will avoid disruptive actions like OOM killer. The - * caller must handle the failure which is quite likely to happen under - * heavy memory pressure. The flag is suitable when failure can easily be - * handled at small cost, such as reduced throughput - * - * %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim - * procedures that have previously failed if there is some indication - * that progress has been made else where. It can wait for other - * tasks to attempt high level approaches to freeing memory such as - * compaction (which removes fragmentation) and page-out. - * There is still a definite limit to the number of retries, but it is - * a larger limit than with %__GFP_NORETRY. - * Allocations with this flag may fail, but only when there is - * genuinely little unused memory. While these allocations do not - * directly trigger the OOM killer, their failure indicates that - * the system is likely to need to use the OOM killer soon. The - * caller must handle failure, but can reasonably do so by failing - * a higher-level request, or completing it only in a much less - * efficient manner. - * If the allocation does fail, and the caller is in a position to - * free some non-essential memory, doing so could benefit the system - * as a whole. - * - * %__GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller - * cannot handle allocation failures. The allocation could block - * indefinitely but will never return with failure. Testing for - * failure is pointless. - * New users should be evaluated carefully (and the flag should be - * used only when there is no reasonable failure policy) but it is - * definitely preferable to use the flag rather than opencode endless - * loop around allocator. - * Using this flag for costly allocations is _highly_ discouraged. - */ -#define __GFP_IO ((__force gfp_t)___GFP_IO) -#define __GFP_FS ((__force gfp_t)___GFP_FS) -#define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */ -#define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */ -#define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) -#define __GFP_RETRY_MAYFAIL ((__force gfp_t)___GFP_RETRY_MAYFAIL) -#define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) -#define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) - -/** - * DOC: Action modifiers - * - * Action modifiers - * ~~~~~~~~~~~~~~~~ - * - * %__GFP_NOWARN suppresses allocation failure reports. - * - * %__GFP_COMP address compound page metadata. - * - * %__GFP_ZERO returns a zeroed page on success. - */ -#define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) -#define __GFP_COMP ((__force gfp_t)___GFP_COMP) -#define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) - -/* Disable lockdep for GFP context tracking */ -#define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) - -/* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT (23 + IS_ENABLED(CONFIG_LOCKDEP)) -#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) - -/** - * DOC: Useful GFP flag combinations - * - * Useful GFP flag combinations - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * Useful GFP flag combinations that are commonly used. It is recommended - * that subsystems start with one of these combinations and then set/clear - * %__GFP_FOO flags as necessary. - * - * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower - * watermark is applied to allow access to "atomic reserves". - * The current implementation doesn't support NMI and few other strict - * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT. - * - * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires - * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim. - * - * %GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is - * accounted to kmemcg. - * - * %GFP_NOWAIT is for kernel allocations that should not stall for direct - * reclaim, start physical IO or use any filesystem callback. - * - * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages - * that do not require the starting of any physical IO. - * Please try to avoid using this flag directly and instead use - * memalloc_noio_{save,restore} to mark the whole scope which cannot - * perform any IO with a short explanation why. All allocation requests - * will inherit GFP_NOIO implicitly. - * - * %GFP_NOFS will use direct reclaim but will not use any filesystem interfaces. - * Please try to avoid using this flag directly and instead use - * memalloc_nofs_{save,restore} to mark the whole scope which cannot/shouldn't - * recurse into the FS layer with a short explanation why. All allocation - * requests will inherit GFP_NOFS implicitly. - * - * %GFP_USER is for userspace allocations that also need to be directly - * accessibly by the kernel or hardware. It is typically used by hardware - * for buffers that are mapped to userspace (e.g. graphics) that hardware - * still must DMA to. cpuset limits are enforced for these allocations. - * - * %GFP_DMA exists for historical reasons and should be avoided where possible. - * The flags indicates that the caller requires that the lowest zone be - * used (%ZONE_DMA or 16M on x86-64). Ideally, this would be removed but - * it would require careful auditing as some users really require it and - * others use the flag to avoid lowmem reserves in %ZONE_DMA and treat the - * lowest zone as a type of emergency reserve. - * - * %GFP_DMA32 is similar to %GFP_DMA except that the caller requires a 32-bit - * address. - * - * %GFP_HIGHUSER is for userspace allocations that may be mapped to userspace, - * do not need to be directly accessible by the kernel but that cannot - * move once in use. An example may be a hardware allocation that maps - * data directly into userspace but has no addressing limitations. - * - * %GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not - * need direct access to but can use kmap() when access is required. They - * are expected to be movable via page reclaim or page migration. Typically, - * pages on the LRU would also be allocated with %GFP_HIGHUSER_MOVABLE. - * - * %GFP_TRANSHUGE and %GFP_TRANSHUGE_LIGHT are used for THP allocations. They - * are compound allocations that will generally fail quickly if memory is not - * available and will not wake kswapd/kcompactd on failure. The _LIGHT - * version does not attempt reclaim/compaction at all and is by default used - * in page fault path, while the non-light is used by khugepaged. - */ -#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) -#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) -#define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT) -#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) -#define GFP_NOIO (__GFP_RECLAIM) -#define GFP_NOFS (__GFP_RECLAIM | __GFP_IO) -#define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL) -#define GFP_DMA __GFP_DMA -#define GFP_DMA32 __GFP_DMA32 -#define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) -#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE) -#define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ - __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM) -#define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM) +struct mempolicy; /* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) @@ -319,12 +21,15 @@ static inline int gfp_migratetype(const gfp_t gfp_flags) VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE); BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE); + BUILD_BUG_ON((___GFP_RECLAIMABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_RECLAIMABLE); + BUILD_BUG_ON(((___GFP_MOVABLE | ___GFP_RECLAIMABLE) >> + GFP_MOVABLE_SHIFT) != MIGRATE_HIGHATOMIC); if (unlikely(page_group_by_mobility_disabled)) return MIGRATE_UNMOVABLE; /* Group based on mobility */ - return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; + return (__force unsigned long)(gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; } #undef GFP_MOVABLE_MASK #undef GFP_MOVABLE_SHIFT @@ -334,27 +39,23 @@ static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) return !!(gfp_flags & __GFP_DIRECT_RECLAIM); } -/** - * gfpflags_normal_context - is gfp_flags a normal sleepable context? - * @gfp_flags: gfp_flags to test - * - * Test whether @gfp_flags indicates that the allocation is from the - * %current context and allowed to sleep. - * - * An allocation being allowed to block doesn't mean it owns the %current - * context. When direct reclaim path tries to allocate memory, the - * allocation context is nested inside whatever %current was doing at the - * time of the original allocation. The nested allocation may be allowed - * to block but modifying anything %current owns can corrupt the outer - * context's expectations. - * - * %true result from this function indicates that the allocation context - * can sleep and use anything that's associated with %current. - */ -static inline bool gfpflags_normal_context(const gfp_t gfp_flags) +static inline bool gfpflags_allow_spinning(const gfp_t gfp_flags) { - return (gfp_flags & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC)) == - __GFP_DIRECT_RECLAIM; + /* + * !__GFP_DIRECT_RECLAIM -> direct claim is not allowed. + * !__GFP_KSWAPD_RECLAIM -> it's not safe to wake up kswapd. + * All GFP_* flags including GFP_NOWAIT use one or both flags. + * alloc_pages_nolock() is the only API that doesn't specify either flag. + * + * This is stronger than GFP_NOWAIT or GFP_ATOMIC because + * those are guaranteed to never block on a sleeping lock. + * Here we are enforcing that the allocation doesn't ever spin + * on any locks (i.e. only trylocks). There is no high level + * GFP_$FOO flag for this use in alloc_pages_nolock() as the + * regular page allocator doesn't fully support this + * allocation mode. + */ + return !!(gfp_flags & __GFP_RECLAIM); } #ifdef CONFIG_HIGHMEM @@ -475,13 +176,38 @@ static inline int gfp_zonelist(gfp_t flags) } /* + * gfp flag masking for nested internal allocations. + * + * For code that needs to do allocations inside the public allocation API (e.g. + * memory allocation tracking code) the allocations need to obey the caller + * allocation context constrains to prevent allocation context mismatches (e.g. + * GFP_KERNEL allocations in GFP_NOFS contexts) from potential deadlock + * situations. + * + * It is also assumed that these nested allocations are for internal kernel + * object storage purposes only and are not going to be used for DMA, etc. Hence + * we strip out all the zone information and leave just the context information + * intact. + * + * Further, internal allocations must fail before the higher level allocation + * can fail, so we must make them fail faster and fail silently. We also don't + * want them to deplete emergency reserves. Hence nested allocations must be + * prepared for these allocations to fail. + */ +static inline gfp_t gfp_nested_mask(gfp_t flags) +{ + return ((flags & (GFP_KERNEL | GFP_ATOMIC | __GFP_NOLOCKDEP)) | + (__GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN)); +} + +/* * We get the zone list from the current node and the gfp_mask. - * This zone list contains a maximum of MAXNODES*MAX_NR_ZONES zones. + * This zone list contains a maximum of MAX_NUMNODES*MAX_NR_ZONES zones. * There are two zonelists per node, one for all zones with memory and * one containing just zones from the node the zonelist belongs to. * - * For the normal case of non-DISCONTIGMEM systems the NODE_DATA() gets - * optimized to &contig_page_data at compile-time. + * For the case of non-NUMA systems the NODE_DATA() gets optimized to + * &contig_page_data at compile-time. */ static inline struct zonelist *node_zonelist(int nid, gfp_t flags) { @@ -494,21 +220,55 @@ static inline void arch_free_page(struct page *page, int order) { } #ifndef HAVE_ARCH_ALLOC_PAGE static inline void arch_alloc_page(struct page *page, int order) { } #endif -#ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE -static inline int arch_make_page_accessible(struct page *page) + +struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, int preferred_nid, + nodemask_t *nodemask); +#define __alloc_pages(...) alloc_hooks(__alloc_pages_noprof(__VA_ARGS__)) + +struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_nid, + nodemask_t *nodemask); +#define __folio_alloc(...) alloc_hooks(__folio_alloc_noprof(__VA_ARGS__)) + +unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, + nodemask_t *nodemask, int nr_pages, + struct page **page_array); +#define __alloc_pages_bulk(...) alloc_hooks(alloc_pages_bulk_noprof(__VA_ARGS__)) + +unsigned long alloc_pages_bulk_mempolicy_noprof(gfp_t gfp, + unsigned long nr_pages, + struct page **page_array); +#define alloc_pages_bulk_mempolicy(...) \ + alloc_hooks(alloc_pages_bulk_mempolicy_noprof(__VA_ARGS__)) + +/* Bulk allocate order-0 pages */ +#define alloc_pages_bulk(_gfp, _nr_pages, _page_array) \ + __alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, _page_array) + +static inline unsigned long +alloc_pages_bulk_node_noprof(gfp_t gfp, int nid, unsigned long nr_pages, + struct page **page_array) { - return 0; + if (nid == NUMA_NO_NODE) + nid = numa_mem_id(); + + return alloc_pages_bulk_noprof(gfp, nid, NULL, nr_pages, page_array); } -#endif -struct page * -__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid, - nodemask_t *nodemask); +#define alloc_pages_bulk_node(...) \ + alloc_hooks(alloc_pages_bulk_node_noprof(__VA_ARGS__)) -static inline struct page * -__alloc_pages(gfp_t gfp_mask, unsigned int order, int preferred_nid) +static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask) { - return __alloc_pages_nodemask(gfp_mask, order, preferred_nid, NULL); + gfp_t warn_gfp = gfp_mask & (__GFP_THISNODE|__GFP_NOWARN); + + if (warn_gfp != (__GFP_THISNODE|__GFP_NOWARN)) + return; + + if (node_online(this_node)) + return; + + pr_warn("%pGg allocation from offline node %d\n", &gfp_mask, this_node); + dump_stack(); } /* @@ -516,88 +276,123 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order, int preferred_nid) * online. For more general interface, see alloc_pages_node(). */ static inline struct page * -__alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) +__alloc_pages_node_noprof(int nid, gfp_t gfp_mask, unsigned int order) +{ + VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); + warn_if_node_offline(nid, gfp_mask); + + return __alloc_pages_noprof(gfp_mask, order, nid, NULL); +} + +#define __alloc_pages_node(...) alloc_hooks(__alloc_pages_node_noprof(__VA_ARGS__)) + +static inline +struct folio *__folio_alloc_node_noprof(gfp_t gfp, unsigned int order, int nid) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); - VM_WARN_ON((gfp_mask & __GFP_THISNODE) && !node_online(nid)); + warn_if_node_offline(nid, gfp); - return __alloc_pages(gfp_mask, order, nid); + return __folio_alloc_noprof(gfp, order, nid, NULL); } +#define __folio_alloc_node(...) alloc_hooks(__folio_alloc_node_noprof(__VA_ARGS__)) + /* * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE, * prefer the current CPU's closest node. Otherwise node must be valid and * online. */ -static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, - unsigned int order) +static inline struct page *alloc_pages_node_noprof(int nid, gfp_t gfp_mask, + unsigned int order) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); - return __alloc_pages_node(nid, gfp_mask, order); + return __alloc_pages_node_noprof(nid, gfp_mask, order); } -#ifdef CONFIG_NUMA -extern struct page *alloc_pages_current(gfp_t gfp_mask, unsigned order); +#define alloc_pages_node(...) alloc_hooks(alloc_pages_node_noprof(__VA_ARGS__)) -static inline struct page * -alloc_pages(gfp_t gfp_mask, unsigned int order) +#ifdef CONFIG_NUMA +struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order); +struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order); +struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, + struct mempolicy *mpol, pgoff_t ilx, int nid); +struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr); +#else +static inline struct page *alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { - return alloc_pages_current(gfp_mask, order); + return alloc_pages_node_noprof(numa_node_id(), gfp_mask, order); } -extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, - struct vm_area_struct *vma, unsigned long addr, - int node, bool hugepage); -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) -#else -static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) +static inline struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) +{ + return __folio_alloc_node_noprof(gfp, order, numa_node_id()); +} +static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, + struct mempolicy *mpol, pgoff_t ilx, int nid) { - return alloc_pages_node(numa_node_id(), gfp_mask, order); + return folio_alloc_noprof(gfp, order); } -#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ - alloc_pages(gfp_mask, order) -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages(gfp_mask, order) +#define vma_alloc_folio_noprof(gfp, order, vma, addr) \ + folio_alloc_noprof(gfp, order) #endif + +#define alloc_pages(...) alloc_hooks(alloc_pages_noprof(__VA_ARGS__)) +#define folio_alloc(...) alloc_hooks(folio_alloc_noprof(__VA_ARGS__)) +#define folio_alloc_mpol(...) alloc_hooks(folio_alloc_mpol_noprof(__VA_ARGS__)) +#define vma_alloc_folio(...) alloc_hooks(vma_alloc_folio_noprof(__VA_ARGS__)) + #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) -#define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) -extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); -extern unsigned long get_zeroed_page(gfp_t gfp_mask); +static inline struct page *alloc_page_vma_noprof(gfp_t gfp, + struct vm_area_struct *vma, unsigned long addr) +{ + struct folio *folio = vma_alloc_folio_noprof(gfp, 0, vma, addr); + + return &folio->page; +} +#define alloc_page_vma(...) alloc_hooks(alloc_page_vma_noprof(__VA_ARGS__)) + +struct page *alloc_pages_nolock_noprof(int nid, unsigned int order); +#define alloc_pages_nolock(...) alloc_hooks(alloc_pages_nolock_noprof(__VA_ARGS__)) + +extern unsigned long get_free_pages_noprof(gfp_t gfp_mask, unsigned int order); +#define __get_free_pages(...) alloc_hooks(get_free_pages_noprof(__VA_ARGS__)) + +extern unsigned long get_zeroed_page_noprof(gfp_t gfp_mask); +#define get_zeroed_page(...) alloc_hooks(get_zeroed_page_noprof(__VA_ARGS__)) + +void *alloc_pages_exact_noprof(size_t size, gfp_t gfp_mask) __alloc_size(1); +#define alloc_pages_exact(...) alloc_hooks(alloc_pages_exact_noprof(__VA_ARGS__)) -void *alloc_pages_exact(size_t size, gfp_t gfp_mask); void free_pages_exact(void *virt, size_t size); -void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); -#define __get_free_page(gfp_mask) \ - __get_free_pages((gfp_mask), 0) +__meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2); +#define alloc_pages_exact_nid(...) \ + alloc_hooks(alloc_pages_exact_nid_noprof(__VA_ARGS__)) -#define __get_dma_pages(gfp_mask, order) \ - __get_free_pages((gfp_mask) | GFP_DMA, (order)) +#define __get_free_page(gfp_mask) \ + __get_free_pages((gfp_mask), 0) + +#define __get_dma_pages(gfp_mask, order) \ + __get_free_pages((gfp_mask) | GFP_DMA, (order)) extern void __free_pages(struct page *page, unsigned int order); +extern void free_pages_nolock(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); -extern void free_unref_page(struct page *page); -extern void free_unref_page_list(struct list_head *list); - -struct page_frag_cache; -extern void __page_frag_cache_drain(struct page *page, unsigned int count); -extern void *page_frag_alloc(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask); -extern void page_frag_free(void *addr); #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) -void page_alloc_init(void); +void page_alloc_init_cpuhp(void); +int decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp); void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); void page_alloc_init_late(void); +void setup_pcp_cacheinfo(unsigned int cpu); /* * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what @@ -611,30 +406,56 @@ extern gfp_t gfp_allowed_mask; /* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask); -extern void pm_restrict_gfp_mask(void); -extern void pm_restore_gfp_mask(void); +static inline bool gfp_has_io_fs(gfp_t gfp) +{ + return (gfp & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS); +} -#ifdef CONFIG_PM_SLEEP -extern bool pm_suspended_storage(void); -#else -static inline bool pm_suspended_storage(void) +/* + * Check if the gfp flags allow compaction - GFP_NOIO is a really + * tricky context because the migration might require IO. + */ +static inline bool gfp_compaction_allowed(gfp_t gfp_mask) { - return false; + return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO); } -#endif /* CONFIG_PM_SLEEP */ + +extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma); #ifdef CONFIG_CONTIG_ALLOC /* The below functions must be run on a range from a single zone. */ -extern int alloc_contig_range(unsigned long start, unsigned long end, +extern int alloc_contig_range_noprof(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask); -extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, - int nid, nodemask_t *nodemask); +#define alloc_contig_range(...) alloc_hooks(alloc_contig_range_noprof(__VA_ARGS__)) + +extern struct page *alloc_contig_pages_noprof(unsigned long nr_pages, gfp_t gfp_mask, + int nid, nodemask_t *nodemask); +#define alloc_contig_pages(...) alloc_hooks(alloc_contig_pages_noprof(__VA_ARGS__)) + #endif -void free_contig_range(unsigned long pfn, unsigned int nr_pages); +void free_contig_range(unsigned long pfn, unsigned long nr_pages); -#ifdef CONFIG_CMA -/* CMA stuff */ -extern void init_cma_reserved_pageblock(struct page *page); +#ifdef CONFIG_CONTIG_ALLOC +static inline struct folio *folio_alloc_gigantic_noprof(int order, gfp_t gfp, + int nid, nodemask_t *node) +{ + struct page *page; + + if (WARN_ON(!order || !(gfp & __GFP_COMP))) + return NULL; + + page = alloc_contig_pages_noprof(1 << order, gfp, nid, node); + + return page ? page_folio(page) : NULL; +} +#else +static inline struct folio *folio_alloc_gigantic_noprof(int order, gfp_t gfp, + int nid, nodemask_t *node) +{ + return NULL; +} #endif +/* This should be paired with folio_put() rather than free_contig_range(). */ +#define folio_alloc_gigantic(...) alloc_hooks(folio_alloc_gigantic_noprof(__VA_ARGS__)) #endif /* __LINUX_GFP_H */ |