Thread a user virtual address from vma_alloc_folio() down through the page allocator to post_alloc_hook(). This is plumbing preparation for a subsequent patch that will use user_addr to call folio_zero_user() for cache-friendly zeroing of user pages.
The user_addr is stored in struct alloc_context and flows through: vma_alloc_folio -> folio_alloc_mpol -> __alloc_pages_mpol -> __alloc_frozen_pages -> get_page_from_freelist -> prep_new_page -> post_alloc_hook user_addr is threaded through internal APIs only (__alloc_frozen_pages_noprof, __alloc_pages_mpol). Public APIs (__alloc_pages, __folio_alloc, folio_alloc_mpol) are unchanged. USER_ADDR_NONE ((unsigned long)-1) is used for non-user allocations, since address 0 is a valid userspace mapping. Signed-off-by: Michael S. Tsirkin <[email protected]> Assisted-by: Claude:claude-opus-4-6 Assisted-by: cursor-agent:GPT-5.4-xhigh --- include/linux/gfp.h | 8 +++++++- mm/compaction.c | 5 ++--- mm/hugetlb.c | 36 ++++++++++++++++++++---------------- mm/internal.h | 12 +++++++++--- mm/mempolicy.c | 42 +++++++++++++++++++++++++++++++----------- mm/page_alloc.c | 44 +++++++++++++++++++++++++++++--------------- mm/slub.c | 4 ++-- 7 files changed, 100 insertions(+), 51 deletions(-) diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 7069b810f171..e275cc80e19e 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -226,6 +226,12 @@ static inline void arch_free_page(struct page *page, int order) { } static inline void arch_alloc_page(struct page *page, int order) { } #endif +/* + * Sentinel for user_addr: indicates a non-user allocation. + * Cannot use 0 because address 0 is a valid userspace mapping. + */ +#define USER_ADDR_NONE ((unsigned long)-1) + 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__)) @@ -340,7 +346,7 @@ static inline struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid) { - return folio_alloc_noprof(gfp, order); + return __folio_alloc_noprof(gfp, order, numa_node_id(), NULL); } #endif diff --git a/mm/compaction.c b/mm/compaction.c index 1e8f8eca318c..c1039a9373e5 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -82,7 +82,7 @@ static inline bool is_via_compact_memory(int order) { return false; } static struct page *mark_allocated_noprof(struct page *page, unsigned int order, gfp_t gfp_flags) { - post_alloc_hook(page, order, __GFP_MOVABLE); + post_alloc_hook(page, order, __GFP_MOVABLE, USER_ADDR_NONE); set_page_refcounted(page); return page; } @@ -1832,8 +1832,7 @@ static struct folio *compaction_alloc_noprof(struct folio *src, unsigned long da set_page_private(&freepage[size], start_order); } dst = (struct folio *)freepage; - - post_alloc_hook(&dst->page, order, __GFP_MOVABLE); + post_alloc_hook(&dst->page, order, __GFP_MOVABLE, USER_ADDR_NONE); set_page_refcounted(&dst->page); if (order) prep_compound_page(&dst->page, order); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0beb6e22bc26..de8361b503d2 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1842,7 +1842,8 @@ struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio) } static struct folio *alloc_buddy_frozen_folio(int order, gfp_t gfp_mask, - int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) + int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry, + unsigned long addr) { struct folio *folio; bool alloc_try_hard = true; @@ -1859,7 +1860,7 @@ 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, addr); /* * If we did not specify __GFP_RETRY_MAYFAIL, but still got a @@ -1888,7 +1889,7 @@ static struct folio *alloc_buddy_frozen_folio(int order, gfp_t gfp_mask, static struct folio *only_alloc_fresh_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, - nodemask_t *node_alloc_noretry) + nodemask_t *node_alloc_noretry, unsigned long addr) { struct folio *folio; int order = huge_page_order(h); @@ -1900,7 +1901,7 @@ static struct folio *only_alloc_fresh_hugetlb_folio(struct hstate *h, folio = alloc_gigantic_frozen_folio(order, gfp_mask, nid, nmask); else folio = alloc_buddy_frozen_folio(order, gfp_mask, nid, nmask, - node_alloc_noretry); + node_alloc_noretry, addr); if (folio) init_new_hugetlb_folio(folio); return folio; @@ -1914,11 +1915,12 @@ static struct folio *only_alloc_fresh_hugetlb_folio(struct hstate *h, * pages is zero, and the accounting must be done in the caller. */ static struct folio *alloc_fresh_hugetlb_folio(struct hstate *h, - gfp_t gfp_mask, int nid, nodemask_t *nmask) + gfp_t gfp_mask, int nid, nodemask_t *nmask, + unsigned long addr) { struct folio *folio; - folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, NULL); + folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, NULL, addr); if (folio) hugetlb_vmemmap_optimize_folio(h, folio); return folio; @@ -1958,7 +1960,7 @@ static struct folio *alloc_pool_huge_folio(struct hstate *h, struct folio *folio; folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, node, - nodes_allowed, node_alloc_noretry); + nodes_allowed, node_alloc_noretry, USER_ADDR_NONE); if (folio) return folio; } @@ -2127,7 +2129,8 @@ int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn) * Allocates a fresh surplus page from the page allocator. */ static struct folio *alloc_surplus_hugetlb_folio(struct hstate *h, - gfp_t gfp_mask, int nid, nodemask_t *nmask) + gfp_t gfp_mask, int nid, nodemask_t *nmask, + unsigned long addr) { struct folio *folio = NULL; @@ -2139,7 +2142,7 @@ static struct folio *alloc_surplus_hugetlb_folio(struct hstate *h, goto out_unlock; spin_unlock_irq(&hugetlb_lock); - folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask); + folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, addr); if (!folio) return NULL; @@ -2182,7 +2185,7 @@ static struct folio *alloc_migrate_hugetlb_folio(struct hstate *h, gfp_t gfp_mas if (hstate_is_gigantic(h)) return NULL; - folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask); + folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, USER_ADDR_NONE); if (!folio) return NULL; @@ -2218,14 +2221,14 @@ struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h, if (mpol_is_preferred_many(mpol)) { gfp_t gfp = gfp_mask & ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); - folio = alloc_surplus_hugetlb_folio(h, gfp, nid, nodemask); + folio = alloc_surplus_hugetlb_folio(h, gfp, nid, nodemask, addr); /* Fallback to all nodes if page==NULL */ nodemask = NULL; } if (!folio) - folio = alloc_surplus_hugetlb_folio(h, gfp_mask, nid, nodemask); + folio = alloc_surplus_hugetlb_folio(h, gfp_mask, nid, nodemask, addr); mpol_cond_put(mpol); return folio; } @@ -2332,7 +2335,8 @@ static int gather_surplus_pages(struct hstate *h, long delta) * down the road to pick the current node if that is the case. */ folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h), - NUMA_NO_NODE, &alloc_nodemask); + NUMA_NO_NODE, &alloc_nodemask, + USER_ADDR_NONE); if (!folio) { alloc_ok = false; break; @@ -2738,7 +2742,7 @@ static int alloc_and_dissolve_hugetlb_folio(struct folio *old_folio, spin_unlock_irq(&hugetlb_lock); gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; new_folio = alloc_fresh_hugetlb_folio(h, gfp_mask, - nid, NULL); + nid, NULL, USER_ADDR_NONE); if (!new_folio) return -ENOMEM; goto retry; @@ -3434,13 +3438,13 @@ static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, nid, - &node_states[N_MEMORY], NULL); + &node_states[N_MEMORY], NULL, USER_ADDR_NONE); if (!folio && !list_empty(&folio_list) && hugetlb_vmemmap_optimizable_size(h)) { prep_and_add_allocated_folios(h, &folio_list); INIT_LIST_HEAD(&folio_list); folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, nid, - &node_states[N_MEMORY], NULL); + &node_states[N_MEMORY], NULL, USER_ADDR_NONE); } if (!folio) break; diff --git a/mm/internal.h b/mm/internal.h index cb0af847d7d9..8e4616e42b4a 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -672,6 +672,7 @@ struct alloc_context { */ enum zone_type highest_zoneidx; bool spread_dirty_pages; + unsigned long user_addr; }; /* @@ -887,24 +888,29 @@ static inline void prep_compound_tail(struct page *head, int tail_idx) set_page_private(p, 0); } -void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); +void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags, + unsigned long user_addr); 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, unsigned int order, int nid, - nodemask_t *); + nodemask_t *, unsigned long user_addr); #define __alloc_frozen_pages(...) \ alloc_hooks(__alloc_frozen_pages_noprof(__VA_ARGS__)) void free_frozen_pages(struct page *page, unsigned int order); +void free_frozen_pages_zeroed(struct page *page, unsigned int order); void free_unref_folios(struct folio_batch *fbatch); #ifdef CONFIG_NUMA struct page *alloc_frozen_pages_noprof(gfp_t, unsigned int order); +struct folio *folio_alloc_mpol_user_noprof(gfp_t gfp, unsigned int order, + struct mempolicy *pol, pgoff_t ilx, int nid, + unsigned long user_addr); #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, USER_ADDR_NONE); } #endif diff --git a/mm/mempolicy.c b/mm/mempolicy.c index f0f85c89da82..06403a3812b4 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2406,7 +2406,8 @@ bool mempolicy_in_oom_domain(struct task_struct *tsk, } static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, - int nid, nodemask_t *nodemask) + int nid, nodemask_t *nodemask, + unsigned long user_addr) { struct page *page; gfp_t preferred_gfp; @@ -2419,9 +2420,11 @@ 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, user_addr); if (!page) - page = __alloc_frozen_pages_noprof(gfp, order, nid, NULL); + page = __alloc_frozen_pages_noprof(gfp, order, nid, NULL, + user_addr); return page; } @@ -2436,8 +2439,9 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, * * Return: The page on success or NULL if allocation fails. */ -static struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, - struct mempolicy *pol, pgoff_t ilx, int nid) +static struct page *__alloc_pages_mpol(gfp_t gfp, unsigned int order, + struct mempolicy *pol, pgoff_t ilx, int nid, + unsigned long user_addr) { nodemask_t *nodemask; struct page *page; @@ -2445,7 +2449,8 @@ static struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, nodemask = policy_nodemask(gfp, pol, ilx, &nid); if (pol->mode == MPOL_PREFERRED_MANY) - return alloc_pages_preferred_many(gfp, order, nid, nodemask); + return alloc_pages_preferred_many(gfp, order, nid, nodemask, + user_addr); if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && /* filter "hugepage" allocation, unless from alloc_pages() */ @@ -2469,7 +2474,7 @@ 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, user_addr); if (page || !(gfp & __GFP_DIRECT_RECLAIM)) return page; /* @@ -2481,7 +2486,7 @@ 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, user_addr); if (unlikely(pol->mode == MPOL_INTERLEAVE || pol->mode == MPOL_WEIGHTED_INTERLEAVE) && page) { @@ -2497,11 +2502,18 @@ static struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, return page; } -struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, +static struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { - struct page *page = alloc_pages_mpol(gfp | __GFP_COMP, order, pol, - ilx, nid); + return __alloc_pages_mpol(gfp, order, pol, ilx, nid, USER_ADDR_NONE); +} + +struct folio *folio_alloc_mpol_user_noprof(gfp_t gfp, unsigned int order, + struct mempolicy *pol, pgoff_t ilx, int nid, + unsigned long user_addr) +{ + struct page *page = __alloc_pages_mpol(gfp | __GFP_COMP, order, pol, + ilx, nid, user_addr); if (!page) return NULL; @@ -2509,6 +2521,14 @@ struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, return page_rmappable_folio(page); } +struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, + struct mempolicy *pol, pgoff_t ilx, int nid) +{ + return folio_alloc_mpol_user_noprof(gfp, order, pol, ilx, nid, + USER_ADDR_NONE); +} +EXPORT_SYMBOL(folio_alloc_mpol_noprof); + /** * vma_alloc_folio - Allocate a folio for a VMA. * @gfp: GFP flags. diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6d31a5c99e93..c19eaf76607c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1837,7 +1837,7 @@ static inline bool should_skip_init(gfp_t flags) } inline void post_alloc_hook(struct page *page, unsigned int order, - gfp_t gfp_flags) + gfp_t gfp_flags, unsigned long user_addr) { bool init = !want_init_on_free() && want_init_on_alloc(gfp_flags) && !should_skip_init(gfp_flags); @@ -1892,9 +1892,10 @@ inline void post_alloc_hook(struct page *page, unsigned int order, } static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, - unsigned int alloc_flags) + unsigned int alloc_flags, + unsigned long user_addr) { - post_alloc_hook(page, order, gfp_flags); + post_alloc_hook(page, order, gfp_flags, user_addr); if (order && (gfp_flags & __GFP_COMP)) prep_compound_page(page, order); @@ -3959,7 +3960,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, page = rmqueue(zonelist_zone(ac->preferred_zoneref), zone, order, gfp_mask, alloc_flags, ac->migratetype); if (page) { - prep_new_page(page, order, gfp_mask, alloc_flags); + prep_new_page(page, order, gfp_mask, alloc_flags, + ac->user_addr); /* * If this is a high-order atomic allocation then check @@ -4194,7 +4196,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, /* Prep a captured page if available */ if (page) - prep_new_page(page, order, gfp_mask, alloc_flags); + prep_new_page(page, order, gfp_mask, alloc_flags, + ac->user_addr); /* Try get a page from the freelist if available */ if (!page) @@ -5072,7 +5075,7 @@ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, struct zoneref *z; struct per_cpu_pages *pcp; struct list_head *pcp_list; - struct alloc_context ac; + struct alloc_context ac = { .user_addr = USER_ADDR_NONE }; gfp_t alloc_gfp; unsigned int alloc_flags = ALLOC_WMARK_LOW; int nr_populated = 0, nr_account = 0; @@ -5187,7 +5190,7 @@ 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, 0, USER_ADDR_NONE); set_page_refcounted(page); page_array[nr_populated++] = page; } @@ -5212,12 +5215,13 @@ EXPORT_SYMBOL_GPL(alloc_pages_bulk_noprof); * 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) + int preferred_nid, nodemask_t *nodemask, + unsigned long user_addr) { struct page *page; unsigned int alloc_flags = ALLOC_WMARK_LOW; gfp_t alloc_gfp; /* The gfp_t that was actually used for allocation */ - struct alloc_context ac = { }; + struct alloc_context ac = { .user_addr = user_addr }; /* * There are several places where we assume that the order value is sane @@ -5278,10 +5282,12 @@ EXPORT_SYMBOL(__alloc_frozen_pages_noprof); struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask) + { struct page *page; - page = __alloc_frozen_pages_noprof(gfp, order, preferred_nid, nodemask); + page = __alloc_frozen_pages_noprof(gfp, order, preferred_nid, + nodemask, USER_ADDR_NONE); if (page) set_page_refcounted(page); return page; @@ -5310,7 +5316,8 @@ struct folio *vma_alloc_folio_user_addr_noprof(gfp_t gfp, int order, gfp |= __GFP_NOWARN; pol = get_vma_policy(vma, addr, order, &ilx); - folio = folio_alloc_mpol_noprof(gfp, order, pol, ilx, numa_node_id()); + folio = folio_alloc_mpol_user_noprof(gfp, order, pol, ilx, + numa_node_id(), user_addr); mpol_cond_put(pol); return folio; } @@ -5319,10 +5326,17 @@ struct folio *vma_alloc_folio_user_addr_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, unsigned long user_addr) { + struct page *page; + if (vma->vm_flags & VM_DROPPABLE) gfp |= __GFP_NOWARN; - return folio_alloc_noprof(gfp, order); + page = __alloc_frozen_pages_noprof(gfp | __GFP_COMP, order, + numa_node_id(), NULL, user_addr); + if (!page) + return NULL; + set_page_refcounted(page); + return page_rmappable_folio(page); } #endif EXPORT_SYMBOL(vma_alloc_folio_user_addr_noprof); @@ -6947,7 +6961,7 @@ static void split_free_frozen_pages(struct list_head *list, gfp_t gfp_mask) list_for_each_entry_safe(page, next, &list[order], lru) { int i; - post_alloc_hook(page, order, gfp_mask); + post_alloc_hook(page, order, gfp_mask, USER_ADDR_NONE); if (!order) continue; @@ -7153,7 +7167,7 @@ int alloc_contig_frozen_range_noprof(unsigned long start, unsigned long end, struct page *head = pfn_to_page(start); check_new_pages(head, order); - prep_new_page(head, order, gfp_mask, 0); + prep_new_page(head, order, gfp_mask, 0, USER_ADDR_NONE); } else { ret = -EINVAL; WARN(true, "PFN range: requested [%lu, %lu), allocated [%lu, %lu)\n", @@ -7818,7 +7832,7 @@ struct page *alloc_frozen_pages_nolock_noprof(gfp_t gfp_flags, int nid, unsigned gfp_t alloc_gfp = __GFP_NOWARN | __GFP_ZERO | __GFP_NOMEMALLOC | __GFP_COMP | gfp_flags; unsigned int alloc_flags = ALLOC_TRYLOCK; - struct alloc_context ac = { }; + struct alloc_context ac = { .user_addr = USER_ADDR_NONE }; struct page *page; VM_WARN_ON_ONCE(gfp_flags & ~__GFP_ACCOUNT); diff --git a/mm/slub.c b/mm/slub.c index 0c906fefc31b..fc8f998a0fe1 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3266,7 +3266,7 @@ 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, USER_ADDR_NONE); if (!page) return NULL; @@ -5178,7 +5178,7 @@ 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, USER_ADDR_NONE); if (page) { ptr = page_address(page); -- MST
