Currently the core allocator code is controlled by ALLOC_NOLOCK, but the main entry point function is significantly different from the normal __alloc_frozen_pages_nolock(), this is tiring when reading the code. Plumb the ALLOC_NOLOCK control one layer up in the call stack: create an alloc_flags argument to __alloc_frozen_pages_nolock() (which is only exposed to mm/) and then turn the nolock variant into a thin wrapper that just sets that flag (as well as handling NUMA_NO_NODE, similar to how some of the wrappers in gfp.h do). Rationale that this doesn't change anything: 1. Simple bits: A bunch of the nolock-specific handling is just moved to the new alloc_order_allowed(), alloc_trylock_allowed() and gfp_trylock. 2. __alloc_frozen_pages_noprof() has some extra logic that wasn't previously in the nolock variant: a. Application of gfp_allowed_mask; this only affects early boot, and only flags that affect the slowpath get changed here. b. Application of current_gfp_context() - also only affects the slowpath 3. The slowpath itself: this is now just explicitly skipped under !ALLOC_TRYLOCK. Ulterior motive: adding an alloc_flags arg to the allocator's mm-internal entrypoint can later be used to do more allocation customisation without needing to create new GFP flags. While adding this flag to a bunch of places, create ALLOC_DEFAULT to avoid a mysterious literal 0 in most places. alloc_frozen_pages_noprof() is defined above the alloc flags so just leave that as a slightly messy exception instead of trying to fully reorder mm/internal.h for that one case. No functional change intended. Signed-off-by: Brendan Jackman --- mm/hugetlb.c | 3 +- mm/mempolicy.c | 10 ++-- mm/page_alloc.c | 178 +++++++++++++++++++++++++++++--------------------------- mm/page_alloc.h | 6 +- mm/slub.c | 6 +- 5 files changed, 108 insertions(+), 95 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f7925624c4d2e..dfcfcfa4715bf 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1806,7 +1806,8 @@ static struct folio *alloc_buddy_frozen_folio(int order, gfp_t gfp_mask, if (alloc_try_hard) gfp_mask |= __GFP_RETRY_MAYFAIL; - folio = (struct folio *)__alloc_frozen_pages(gfp_mask, order, nid, nmask); + folio = (struct folio *)__alloc_frozen_pages(gfp_mask, order, nid, nmask, + ALLOC_DEFAULT); /* * If we did not specify __GFP_RETRY_MAYFAIL, but still got a diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 9c740324f9160..41d630f0ea821 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2426,9 +2426,11 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, */ preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); - page = __alloc_frozen_pages_noprof(preferred_gfp, order, nid, nodemask); + page = __alloc_frozen_pages_noprof(preferred_gfp, order, nid, nodemask, + ALLOC_DEFAULT); if (!page) - page = __alloc_frozen_pages_noprof(gfp, order, nid, NULL); + page = __alloc_frozen_pages_noprof(gfp, order, nid, NULL, + ALLOC_DEFAULT); return page; } @@ -2476,7 +2478,7 @@ static struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, */ page = __alloc_frozen_pages_noprof( gfp | __GFP_THISNODE | __GFP_NORETRY, order, - nid, NULL); + nid, NULL, ALLOC_DEFAULT); if (page || !(gfp & __GFP_DIRECT_RECLAIM)) return page; /* @@ -2488,7 +2490,7 @@ static struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, } } - page = __alloc_frozen_pages_noprof(gfp, order, nid, nodemask); + page = __alloc_frozen_pages_noprof(gfp, order, nid, nodemask, ALLOC_DEFAULT); if (unlikely(pol->mode == MPOL_INTERLEAVE || pol->mode == MPOL_WEIGHTED_INTERLEAVE) && page) { diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a3ba63c7f9199..8d409d075e3e9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5222,7 +5222,7 @@ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, } nr_account++; - prep_new_page(page, 0, gfp, 0); + prep_new_page(page, 0, gfp, ALLOC_DEFAULT); set_page_refcounted(page); page_array[nr_populated++] = page; } @@ -5271,24 +5271,98 @@ void free_pages_bulk(struct page **page_array, unsigned long nr_pages) } } -/* - * This is the 'heart' of the zoned buddy allocator. - */ -struct page *__alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order, - int preferred_nid, nodemask_t *nodemask) +static inline bool alloc_order_allowed(gfp_t gfp, unsigned int order, + unsigned int alloc_flags) { - struct page *page; - unsigned int fastpath_alloc_flags = ALLOC_WMARK_LOW; - gfp_t alloc_gfp; /* The gfp_t that was actually used for allocation */ - struct alloc_context ac = { }; + if (alloc_flags & ALLOC_NOLOCK) + return pcp_allowed_order(order); /* * There are several places where we assume that the order value is sane * so bail out early if the request is out of bound. */ - if (WARN_ON_ONCE_GFP(order > MAX_PAGE_ORDER, gfp)) + return !(WARN_ON_ONCE_GFP(order > MAX_PAGE_ORDER, gfp)); +} + +static inline bool alloc_trylock_allowed(void) +{ + /* + * In PREEMPT_RT spin_trylock() will call raw_spin_lock() which is + * unsafe in NMI. If spin_trylock() is called from hard IRQ the current + * task may be waiting for one rt_spin_lock, but rt_spin_trylock() will + * mark the task as the owner of another rt_spin_lock which will + * confuse PI logic, so return immediately if called from hard IRQ or + * NMI. + * + * Note, irqs_disabled() case is ok. This function can be called + * from raw_spin_lock_irqsave region. + */ + if (IS_ENABLED(CONFIG_PREEMPT_RT) && (in_nmi() || in_hardirq())) + return false; + + /* On UP, spin_trylock() always succeeds even when it is locked */ + if (!IS_ENABLED(CONFIG_SMP) && in_nmi()) + return false; + + /* Bailout, since _deferred_grow_zone() needs to take a lock */ + if (deferred_pages_enabled()) + return false; + + return true; +} + +/* + * GFP flags to set for ALLOC_NOLOCK i.e. alloc_pages_nolock(). + * + * Do not specify __GFP_DIRECT_RECLAIM, since direct claim is not allowed. + * Do not specify __GFP_KSWAPD_RECLAIM either, since wake up of kswapd + * is not safe in arbitrary context. + * + * These two are the conditions for gfpflags_allow_spinning() being true. + * + * Specify __GFP_NOWARN since failing alloc_pages_nolock() is not a reason + * to warn. Also warn would trigger printk() which is unsafe from + * various contexts. We cannot use printk_deferred_enter() to mitigate, + * since the running context is unknown. + * + * Specify __GFP_ZERO to make sure that call to kmsan_alloc_page() below + * is safe in any context. Also zeroing the page is mandatory for + * BPF use cases. + * + * Though __GFP_NOMEMALLOC is not checked in the code path below, + * specify it here to highlight that alloc_pages_nolock() + * doesn't want to deplete reserves. + */ +static const gfp_t gfp_nolock = __GFP_NOWARN | __GFP_ZERO | __GFP_NOMEMALLOC | + __GFP_COMP; + +/* + * This is the 'heart' of the zoned buddy allocator. + */ +struct page *__alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order, + int preferred_nid, nodemask_t *nodemask, unsigned int alloc_flags) +{ + struct page *page; + gfp_t alloc_gfp; /* The gfp_t that was actually used for allocation */ + struct alloc_context ac = { }; + unsigned int fastpath_alloc_flags = alloc_flags; + + /* Other flags could be supported later if needed. */ + if (WARN_ON(alloc_flags & ~ALLOC_NOLOCK)) return NULL; + if (!alloc_order_allowed(gfp, order, alloc_flags)) + return NULL; + + if (alloc_flags & ALLOC_NOLOCK) { + VM_WARN_ON_ONCE(gfp & ~__GFP_ACCOUNT); + if (!alloc_trylock_allowed()) + return NULL; + gfp |= gfp_nolock; + } else { + fastpath_alloc_flags |= ALLOC_WMARK_LOW; + } + gfp &= gfp_allowed_mask; /* * Apply scoped allocation constraints. This is mainly about GFP_NOFS @@ -5310,9 +5384,9 @@ struct page *__alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order, fastpath_alloc_flags |= alloc_flags_nofragment(zonelist_zone(ac.preferred_zoneref), gfp); fastpath_alloc_flags |= alloc_flags_nonblocking(gfp, order) & ALLOC_HIGHATOMIC; - /* First allocation attempt */ + /* First allocation attempt (or, for nolock, only attempt) */ page = get_page_from_freelist(alloc_gfp, order, fastpath_alloc_flags, &ac); - if (likely(page)) + if (likely(page) || (alloc_flags & ALLOC_NOLOCK)) goto out; alloc_gfp = gfp; @@ -5329,7 +5403,8 @@ struct page *__alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order, out: if (memcg_kmem_online() && (gfp & __GFP_ACCOUNT) && page && unlikely(__memcg_kmem_charge_page(page, gfp, order) != 0)) { - free_frozen_pages(page, order); + __free_frozen_pages(page, order, + alloc_flags & ALLOC_NOLOCK ? FPI_TRYLOCK : 0); page = NULL; } @@ -5345,7 +5420,8 @@ struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, { struct page *page; - page = __alloc_frozen_pages_noprof(gfp, order, preferred_nid, nodemask); + page = __alloc_frozen_pages_noprof(gfp, order, preferred_nid, nodemask, + ALLOC_DEFAULT); if (page) set_page_refcounted(page); return page; @@ -7875,80 +7951,10 @@ static bool __free_unaccepted(struct page *page) struct page *alloc_frozen_pages_nolock_noprof(gfp_t gfp_flags, int nid, unsigned int order) { - /* - * Do not specify __GFP_DIRECT_RECLAIM, since direct claim is not allowed. - * Do not specify __GFP_KSWAPD_RECLAIM either, since wake up of kswapd - * is not safe in arbitrary context. - * - * These two are the conditions for gfpflags_allow_spinning() being true. - * - * Specify __GFP_NOWARN since failing alloc_pages_nolock() is not a reason - * to warn. Also warn would trigger printk() which is unsafe from - * various contexts. We cannot use printk_deferred_enter() to mitigate, - * since the running context is unknown. - * - * Specify __GFP_ZERO to make sure that call to kmsan_alloc_page() below - * is safe in any context. Also zeroing the page is mandatory for - * BPF use cases. - * - * Though __GFP_NOMEMALLOC is not checked in the code path below, - * specify it here to highlight that alloc_pages_nolock() - * doesn't want to deplete reserves. - */ - gfp_t alloc_gfp = __GFP_NOWARN | __GFP_ZERO | __GFP_NOMEMALLOC | __GFP_COMP - | gfp_flags; - unsigned int alloc_flags = ALLOC_NOLOCK; - struct alloc_context ac = { }; - struct page *page; - - VM_WARN_ON_ONCE(gfp_flags & ~__GFP_ACCOUNT); - /* - * In PREEMPT_RT spin_trylock() will call raw_spin_lock() which is - * unsafe in NMI. If spin_trylock() is called from hard IRQ the current - * task may be waiting for one rt_spin_lock, but rt_spin_trylock() will - * mark the task as the owner of another rt_spin_lock which will - * confuse PI logic, so return immediately if called from hard IRQ or - * NMI. - * - * Note, irqs_disabled() case is ok. This function can be called - * from raw_spin_lock_irqsave region. - */ - if (IS_ENABLED(CONFIG_PREEMPT_RT) && (in_nmi() || in_hardirq())) - return NULL; - - /* On UP, spin_trylock() always succeeds even when it is locked */ - if (!IS_ENABLED(CONFIG_SMP) && in_nmi()) - return NULL; - - if (!pcp_allowed_order(order)) - return NULL; - - /* Bailout, since _deferred_grow_zone() needs to take a lock */ - if (deferred_pages_enabled()) - return NULL; - if (nid == NUMA_NO_NODE) nid = numa_node_id(); - prepare_alloc_pages(alloc_gfp, order, nid, NULL, &ac, - &alloc_gfp, &alloc_flags); - - /* - * Best effort allocation from percpu free list. - * If it's empty attempt to spin_trylock zone->lock. - */ - page = get_page_from_freelist(alloc_gfp, order, alloc_flags, &ac); - - /* Unlike regular alloc_pages() there is no __alloc_pages_slowpath(). */ - - if (memcg_kmem_online() && page && (gfp_flags & __GFP_ACCOUNT) && - unlikely(__memcg_kmem_charge_page(page, alloc_gfp, order) != 0)) { - __free_frozen_pages(page, order, FPI_TRYLOCK); - page = NULL; - } - trace_mm_page_alloc(page, order, alloc_gfp, ac.migratetype); - kmsan_alloc_page(page, order, alloc_gfp); - return page; + return __alloc_frozen_pages_noprof(gfp_flags, order, nid, NULL, ALLOC_NOLOCK); } /** * alloc_pages_nolock - opportunistic reentrant allocation from any context diff --git a/mm/page_alloc.h b/mm/page_alloc.h index 3250d44f96457..e16f905f859a7 100644 --- a/mm/page_alloc.h +++ b/mm/page_alloc.h @@ -11,6 +11,7 @@ #include #include +#define ALLOC_DEFAULT 0 /* The ALLOC_WMARK bits are used as an index to zone->watermark */ #define ALLOC_WMARK_MIN WMARK_MIN #define ALLOC_WMARK_LOW WMARK_LOW @@ -219,7 +220,7 @@ extern bool free_pages_prepare(struct page *page, unsigned int order); extern int user_min_free_kbytes; struct page *__alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order, int nid, - nodemask_t *nodemask); + nodemask_t *nodemask, unsigned int alloc_flags); #define __alloc_frozen_pages(...) \ alloc_hooks(__alloc_frozen_pages_noprof(__VA_ARGS__)) void free_frozen_pages(struct page *page, unsigned int order); @@ -230,7 +231,8 @@ struct page *alloc_frozen_pages_noprof(gfp_t, unsigned int order); #else static inline struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order) { - return __alloc_frozen_pages_noprof(gfp, order, numa_node_id(), NULL); + return __alloc_frozen_pages_noprof(gfp, order, numa_node_id(), NULL, + 0 /* ALLOC_DEFAULT */); } #endif diff --git a/mm/slub.c b/mm/slub.c index 877021e69cc41..3989b4758ae0a 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3292,7 +3292,8 @@ static inline struct slab *alloc_slab_page(gfp_t flags, int node, else if (node == NUMA_NO_NODE) page = alloc_frozen_pages(flags, order); else - page = __alloc_frozen_pages(flags, order, node, NULL); + page = __alloc_frozen_pages(flags, order, node, NULL, + ALLOC_DEFAULT); if (!page) return NULL; @@ -5302,7 +5303,8 @@ static void *___kmalloc_large_node(size_t size, gfp_t flags, int node) if (node == NUMA_NO_NODE) page = alloc_frozen_pages_noprof(flags, order); else - page = __alloc_frozen_pages_noprof(flags, order, node, NULL); + page = __alloc_frozen_pages_noprof(flags, order, node, NULL, + ALLOC_DEFAULT); if (page) { ptr = page_address(page); -- 2.54.0