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_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 | 2 +- mm/compaction.c | 5 ++--- mm/hugetlb.c | 36 ++++++++++++++++++++---------------- mm/internal.h | 18 +++++++++++++++--- mm/mempolicy.c | 44 ++++++++++++++++++++++++++++++++------------ mm/page_alloc.c | 44 +++++++++++++++++++++++++++++--------------- mm/slub.c | 4 ++-- 7 files changed, 101 insertions(+), 52 deletions(-) diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 7ccbda35b9ad..ee35c5367abc 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -337,7 +337,7 @@ 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 3648ce22c807..72684fe81e83 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; } @@ -1849,8 +1849,7 @@ 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 f24bf49be047..a999f3ead852 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1806,7 +1806,8 @@ 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; @@ -1823,7 +1824,7 @@ 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 @@ -1852,7 +1853,7 @@ 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); @@ -1864,7 +1865,7 @@ 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; @@ -1878,11 +1879,12 @@ 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; @@ -1922,7 +1924,7 @@ 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; } @@ -2091,7 +2093,8 @@ 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; @@ -2103,7 +2106,7 @@ 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; @@ -2146,7 +2149,7 @@ 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; @@ -2182,14 +2185,14 @@ 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; } @@ -2296,7 +2299,8 @@ 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; @@ -2702,7 +2706,7 @@ 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; @@ -3400,13 +3404,13 @@ 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 5a2ddcf68e0b..751ae8911607 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -662,6 +662,12 @@ void calculate_min_free_kbytes(void); int __meminit init_per_zone_wmark_min(void); void page_alloc_sysctl_init(void); +/* + * 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) + /* * Structure for holding the mostly immutable allocation parameters passed * between functions involved in allocations, including the alloc_pages* @@ -693,6 +699,7 @@ struct alloc_context { */ enum zone_type highest_zoneidx; bool spread_dirty_pages; + unsigned long user_addr; }; /* @@ -916,24 +923,29 @@ static inline void init_compound_tail(struct page *tail, prep_compound_tail(tail, head, order); } -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 39e556e3d263..ea3043e0075b 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2413,7 +2413,8 @@ 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; @@ -2426,25 +2427,29 @@ 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; } /** - * alloc_pages_mpol - Allocate pages according to NUMA mempolicy. + * __alloc_pages_mpol - Allocate pages according to NUMA mempolicy. * @gfp: GFP flags. * @order: Order of the page allocation. * @pol: Pointer to the NUMA mempolicy. * @ilx: Index for interleave mempolicy (also distinguishes alloc_pages()). * @nid: Preferred node (usually numa_node_id() but @mpol may override it). + * @user_addr: User fault address for cache-friendly zeroing, or USER_ADDR_NONE. * * 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; @@ -2452,7 +2457,8 @@ 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() */ @@ -2476,7 +2482,7 @@ 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; /* @@ -2488,7 +2494,7 @@ 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) { @@ -2504,11 +2510,18 @@ 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; @@ -2516,6 +2529,13 @@ 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); +} + struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned order) { struct mempolicy *pol = &default_policy; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index fc7327ebdf6c..c3c0f4e2baa7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1806,7 +1806,7 @@ 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); @@ -1861,9 +1861,10 @@ 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); @@ -3943,7 +3944,8 @@ 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); return page; } else { @@ -4171,7 +4173,8 @@ __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) @@ -5048,7 +5051,7 @@ 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; @@ -5163,7 +5166,7 @@ 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; } @@ -5188,12 +5191,13 @@ 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 @@ -5254,10 +5258,12 @@ 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; @@ -5300,7 +5306,8 @@ struct folio *vma_alloc_folio_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(), addr); mpol_cond_put(pol); return folio; } @@ -5308,10 +5315,17 @@ struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long 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, addr); + if (!page) + return NULL; + set_page_refcounted(page); + return page_rmappable_folio(page); } #endif EXPORT_SYMBOL(vma_alloc_folio_noprof); @@ -6892,7 +6906,7 @@ 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; @@ -7098,7 +7112,7 @@ 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", @@ -7763,7 +7777,7 @@ 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 0baa906f39ab..74dd2d96941b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3275,7 +3275,7 @@ 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; @@ -5235,7 +5235,7 @@ 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
