The Linux Kernel Mailing List
 help / color / mirror / Atom feed
From: Brendan Jackman <jackmanb@google.com>
To: Andrew Morton <akpm@linux-foundation.org>,
	Vlastimil Babka <vbabka@kernel.org>,
	 Suren Baghdasaryan <surenb@google.com>,
	Michal Hocko <mhocko@suse.com>,
	 Johannes Weiner <hannes@cmpxchg.org>, Zi Yan <ziy@nvidia.com>,
	Muchun Song <muchun.song@linux.dev>,
	 Oscar Salvador <osalvador@suse.de>,
	David Hildenbrand <david@kernel.org>,
	Lorenzo Stoakes <ljs@kernel.org>,
	 "Liam R. Howlett" <liam@infradead.org>,
	Mike Rapoport <rppt@kernel.org>,
	 Matthew Brost <matthew.brost@intel.com>,
	Joshua Hahn <joshua.hahnjy@gmail.com>,
	 Rakie Kim <rakie.kim@sk.com>, Byungchul Park <byungchul@sk.com>,
	 Ying Huang <ying.huang@linux.alibaba.com>,
	Alistair Popple <apopple@nvidia.com>,  Hao Li <hao.li@linux.dev>,
	Christoph Lameter <cl@gentwo.org>,
	David Rientjes <rientjes@google.com>,
	 Roman Gushchin <roman.gushchin@linux.dev>,
	 Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	Clark Williams <clrkwllms@kernel.org>,
	 Steven Rostedt <rostedt@goodmis.org>
Cc: "Harry Yoo (Oracle)" <harry@kernel.org>,
	Gregory Price <gourry@gourry.net>,
	 Johannes Weiner <hannes@cmpxchg.org>,
	Alexei Starovoitov <ast@kernel.org>,
	 Matthew Wilcox <willy@infradead.org>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	 linux-rt-devel@lists.linux.dev,
	Brendan Jackman <jackmanb@google.com>
Subject: [PATCH v2 13/13] mm: remove __GFP_NO_CODETAG
Date: Mon, 22 Jun 2026 10:01:40 +0000	[thread overview]
Message-ID: <20260622-alloc-trylock-v2-13-31f31367d420@google.com> (raw)
In-Reply-To: <20260622-alloc-trylock-v2-0-31f31367d420@google.com>

Now that alloc_pages has an entrypoint that allows passing alloc_flags,
we can take advantage of this to start removing GFP flags that are only
used for mm-internal stuff.

This requires also plumbing the alloc_flags into some more of the
allocator code, in particular __alloc_pages[_noprof]() gets an
alloc_flags arg to go along with its callees, and we now need to pass
those flags deeper into the allocator so they can reach the alloc_tag
code.

To try and keep the new ALLOC_NO_CODETAG's scope nice and narrow, don't
define it in mm/internal.h, instead just define a "reserved bit" and
then use that in places that don't care about what it means.

Signed-off-by: Brendan Jackman <jackmanb@google.com>
---
 mm/alloc_tag.c       | 18 ++++++++++--------
 mm/compaction.c      |  4 ++--
 mm/internal.h        |  8 ++++++--
 mm/page_alloc.c      | 42 ++++++++++++++++++++++++------------------
 mm/page_frag_cache.c |  4 ++--
 5 files changed, 44 insertions(+), 32 deletions(-)

diff --git a/mm/alloc_tag.c b/mm/alloc_tag.c
index d9be1cf5187d9..61a6cba32ff35 100644
--- a/mm/alloc_tag.c
+++ b/mm/alloc_tag.c
@@ -15,6 +15,8 @@
 #include <linux/vmalloc.h>
 #include <linux/kmemleak.h>
 
+#include "internal.h"
+
 #define ALLOCINFO_FILE_NAME		"allocinfo"
 #define MODULE_ALLOC_TAG_VMAP_SIZE	(100000UL * sizeof(struct alloc_tag))
 #define SECTION_START(NAME)		(CODETAG_SECTION_START_PREFIX NAME)
@@ -785,16 +787,15 @@ struct pfn_pool {
 					 sizeof(unsigned long))
 
 /*
- * Skip early PFN recording for a page allocation.  Reuses the
- * %__GFP_NO_OBJ_EXT bit.  Used by __alloc_tag_add_early_pfn() to avoid
- * recursion when allocating pages for the early PFN tracking list
- * itself.
+ * Skip early PFN recording for a page allocation.  Used by
+ * __alloc_tag_add_early_pfn() to avoid recursion when allocating pages for the
+ * early PFN tracking list itself.
  *
  * Codetags of the pages allocated with __GFP_NO_CODETAG should be
  * cleared (via clear_page_tag_ref()) before freeing the pages to prevent
  * alloc_tag_sub_check() from triggering a warning.
  */
-#define __GFP_NO_CODETAG		__GFP_NO_OBJ_EXT
+#define ALLOC_NO_CODETAG		__ALLOC_ALLOC_TAG
 
 static struct pfn_pool *current_pfn_pool __initdata;
 
@@ -806,7 +807,8 @@ static void __init __alloc_tag_add_early_pfn(unsigned long pfn)
 	do {
 		pool = READ_ONCE(current_pfn_pool);
 		if (!pool || atomic_read(&pool->count) >= PFN_POOL_SIZE) {
-			struct page *new_page = alloc_page(__GFP_HIGH | __GFP_NO_CODETAG);
+			struct page *new_page = __alloc_pages(__GFP_HIGH, 0, numa_mem_id(),
+							      NULL, ALLOC_NO_CODETAG);
 			struct pfn_pool *new;
 
 			if (!new_page) {
@@ -837,7 +839,7 @@ typedef void alloc_tag_add_func(unsigned long pfn);
 static alloc_tag_add_func __rcu *alloc_tag_add_early_pfn_ptr __refdata =
 	RCU_INITIALIZER(__alloc_tag_add_early_pfn);
 
-void alloc_tag_add_early_pfn(unsigned long pfn, gfp_t gfp_flags)
+void alloc_tag_add_early_pfn(unsigned long pfn, unsigned int alloc_flags)
 {
 	alloc_tag_add_func *alloc_tag_add;
 
@@ -845,7 +847,7 @@ void alloc_tag_add_early_pfn(unsigned long pfn, gfp_t gfp_flags)
 		return;
 
 	/* Skip allocations for the tracking list itself to avoid recursion. */
-	if (gfp_flags & __GFP_NO_CODETAG)
+	if (alloc_flags & ALLOC_NO_CODETAG)
 		return;
 
 	rcu_read_lock();
diff --git a/mm/compaction.c b/mm/compaction.c
index b776f35ad0200..e90ebd2c54f48 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, ALLOC_DEFAULT);
 	set_page_refcounted(page);
 	return page;
 }
@@ -1850,7 +1850,7 @@ static struct folio *compaction_alloc_noprof(struct folio *src, unsigned long da
 	}
 	dst = (struct folio *)freepage;
 
-	post_alloc_hook(&dst->page, order, __GFP_MOVABLE);
+	post_alloc_hook(&dst->page, order, __GFP_MOVABLE, ALLOC_DEFAULT);
 	set_page_refcounted(&dst->page);
 	if (order)
 		prep_compound_page(&dst->page, order);
diff --git a/mm/internal.h b/mm/internal.h
index 0847b55bfc147..a45bedb9ada5f 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -684,6 +684,8 @@ struct alloc_context {
 	 */
 	enum zone_type highest_zoneidx;
 	bool spread_dirty_pages;
+	/* Only flags that are global to the whole allocation go here. */
+	unsigned int alloc_flags;
 };
 
 /*
@@ -907,7 +909,8 @@ 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 int alloc_flags);
 extern bool free_pages_prepare(struct page *page, unsigned int order);
 
 extern int user_min_free_kbytes;
@@ -1481,6 +1484,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
 #define ALLOC_HIGHATOMIC	0x200 /* Allows access to MIGRATE_HIGHATOMIC */
 #define ALLOC_NOLOCK		0x400 /* Only use spin_trylock in allocation path */
 #define ALLOC_KSWAPD		0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */
+#define __ALLOC_ALLOC_TAG      0x1000 /* Reserved bit for use by alloc_tag code */
 
 /* Flags that allow allocations below the min watermark. */
 #define ALLOC_RESERVES (ALLOC_NON_BLOCK|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM)
@@ -1956,7 +1960,7 @@ bool may_expand_vm(struct mm_struct *mm, const vma_flags_t *vma_flags,
 		   unsigned long npages);
 
 struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, int preferred_nid,
-		nodemask_t *nodemask);
+		nodemask_t *nodemask, unsigned int alloc_flags);
 #define __alloc_pages(...)			alloc_hooks(__alloc_pages_noprof(__VA_ARGS__))
 
 #endif	/* __MM_INTERNAL_H */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d99e4ea8307ea..d50fd9c77a2e8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1246,7 +1246,7 @@ void __clear_page_tag_ref(struct page *page)
 /* Should be called only if mem_alloc_profiling_enabled() */
 static noinline
 void __pgalloc_tag_add(struct page *page, struct task_struct *task,
-		       unsigned int nr, gfp_t gfp_flags)
+		       unsigned int nr, unsigned int alloc_flags)
 {
 	union pgtag_ref_handle handle;
 	union codetag_ref ref;
@@ -1260,17 +1260,17 @@ void __pgalloc_tag_add(struct page *page, struct task_struct *task,
 		 * page_ext is not available yet, record the pfn so we can
 		 * clear the tag ref later when page_ext is initialized.
 		 */
-		alloc_tag_add_early_pfn(page_to_pfn(page), gfp_flags);
+		alloc_tag_add_early_pfn(page_to_pfn(page), alloc_flags);
 		if (task->alloc_tag)
 			alloc_tag_set_inaccurate(task->alloc_tag);
 	}
 }
 
 static inline void pgalloc_tag_add(struct page *page, struct task_struct *task,
-				   unsigned int nr, gfp_t gfp_flags)
+				   unsigned int nr, unsigned int alloc_flags)
 {
 	if (mem_alloc_profiling_enabled())
-		__pgalloc_tag_add(page, task, nr, gfp_flags);
+		__pgalloc_tag_add(page, task, nr, alloc_flags);
 }
 
 /* Should be called only if mem_alloc_profiling_enabled() */
@@ -1807,7 +1807,7 @@ 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 int alloc_flags)
 {
 	const bool zero_tags = gfp_flags & __GFP_ZEROTAGS;
 	bool init = !want_init_on_free() && want_init_on_alloc(gfp_flags) &&
@@ -1858,13 +1858,13 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
 
 	set_page_owner(page, order, gfp_flags);
 	page_table_check_alloc(page, order);
-	pgalloc_tag_add(page, current, 1 << order, gfp_flags);
+	pgalloc_tag_add(page, current, 1 << order, alloc_flags);
 }
 
 static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
 							unsigned int alloc_flags)
 {
-	post_alloc_hook(page, order, gfp_flags);
+	post_alloc_hook(page, order, gfp_flags, alloc_flags);
 
 	if (order && (gfp_flags & __GFP_COMP))
 		prep_compound_page(page, order);
@@ -4773,8 +4773,12 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	 * The fast path uses conservative alloc_flags to succeed only until
 	 * kswapd needs to be woken up, and to avoid the cost of setting up
 	 * alloc_flags precisely. So we do that now.
+	 *
+	 * Can't just or alloc_flags if it contains WMARK bits, but those flags
+	 * shouldn't be set in ac->alloc_flags.
 	 */
-	alloc_flags = slowpath_alloc_flags(gfp_mask, order);
+	VM_WARN_ON(ac->alloc_flags & ALLOC_WMARK_MASK);
+	alloc_flags = ac->alloc_flags | slowpath_alloc_flags(gfp_mask, order);
 
 	/*
 	 * We need to recalculate the starting point for the zonelist iterator
@@ -4816,7 +4820,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	reserve_flags = __gfp_pfmemalloc_flags(gfp_mask);
 	if (reserve_flags)
 		alloc_flags = cma_alloc_flags(gfp_mask, reserve_flags) |
-					  (alloc_flags & ALLOC_KSWAPD);
+				ac->alloc_flags | (alloc_flags & ALLOC_KSWAPD);
 
 	/*
 	 * Reset the nodemask and zonelist iterators if memory policies can be
@@ -5218,7 +5222,7 @@ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid,
 	return nr_populated;
 
 failed:
-	page = __alloc_pages_noprof(gfp, 0, preferred_nid, nodemask);
+	page = __alloc_pages_noprof(gfp, 0, preferred_nid, nodemask, ALLOC_DEFAULT);
 	if (page)
 		page_array[nr_populated++] = page;
 	goto out;
@@ -5326,11 +5330,13 @@ struct page *__alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order,
 {
 	struct page *page;
 	gfp_t alloc_gfp; /* The gfp_t that was actually used for allocation */
-	struct alloc_context ac = { };
+	struct alloc_context ac = {
+		.alloc_flags = alloc_flags,
+	};
 	unsigned int fastpath_alloc_flags = alloc_flags;
 
 	/* Other flags could be supported later if needed. */
-	if (WARN_ON(alloc_flags & ~ALLOC_NOLOCK))
+	if (WARN_ON(alloc_flags & ~(ALLOC_NOLOCK | __ALLOC_ALLOC_TAG)))
 		return NULL;
 
 	if (!alloc_order_allowed(gfp, order, alloc_flags))
@@ -5398,12 +5404,12 @@ struct page *__alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order,
 EXPORT_SYMBOL(__alloc_frozen_pages_noprof);
 
 struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order,
-		int preferred_nid, nodemask_t *nodemask)
+		int preferred_nid, nodemask_t *nodemask, unsigned int alloc_flags)
 {
 	struct page *page;
 
 	page = __alloc_frozen_pages_noprof(gfp, order, preferred_nid, nodemask,
-					   ALLOC_DEFAULT);
+					   alloc_flags);
 	if (page)
 		set_page_refcounted(page);
 	return page;
@@ -5418,14 +5424,14 @@ struct page *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);
+	return __alloc_pages_noprof(gfp_mask, order, nid, NULL, ALLOC_DEFAULT);
 }
 
 struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_nid,
 		nodemask_t *nodemask)
 {
 	struct page *page = __alloc_pages_noprof(gfp | __GFP_COMP, order,
-					preferred_nid, nodemask);
+					preferred_nid, nodemask, ALLOC_DEFAULT);
 	return page_rmappable_folio(page);
 }
 EXPORT_SYMBOL(__folio_alloc_noprof);
@@ -7107,7 +7113,7 @@ 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, ALLOC_DEFAULT);
 			if (!order)
 				continue;
 
@@ -7312,7 +7318,7 @@ 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, ALLOC_DEFAULT);
 	} else {
 		ret = -EINVAL;
 		WARN(true, "PFN range: requested [%lu, %lu), allocated [%lu, %lu)\n",
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index d2423f30577e4..d9573170e0719 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -57,10 +57,10 @@ static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
 	gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) |  __GFP_COMP |
 		   __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC;
 	page = __alloc_pages(gfp_mask, PAGE_FRAG_CACHE_MAX_ORDER,
-			     numa_mem_id(), NULL);
+			     numa_mem_id(), NULL, ALLOC_DEFAULT);
 #endif
 	if (unlikely(!page)) {
-		page = __alloc_pages(gfp, 0, numa_mem_id(), NULL);
+		page = __alloc_pages(gfp, 0, numa_mem_id(), NULL, ALLOC_DEFAULT);
 		order = 0;
 	}
 

-- 
2.54.0


  parent reply	other threads:[~2026-06-22 10:02 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-22 10:01 [PATCH v2 00/13] mm: Some cleanups for page allocator APIs Brendan Jackman
2026-06-22 10:01 ` [PATCH v2 01/13] mm/page_alloc: rename ALLOC_TRYLOCK -> ALLOC_NOLOCK Brendan Jackman
2026-06-22 10:01 ` [PATCH v2 02/13] mm/page_alloc: some renames to clarify alloc_flags scopes Brendan Jackman
2026-06-22 10:01 ` [PATCH v2 03/13] mm/page_alloc: unify __alloc_frozen_pages[_nolock]_noprof() Brendan Jackman
2026-06-22 10:01 ` [PATCH v2 04/13] mm/page_alloc: relax GFP WARN in nolock allocs Brendan Jackman
2026-06-22 10:01 ` [PATCH v2 05/13] perf/x86/intel: Use higher-level allocator Brendan Jackman
2026-06-22 10:10   ` sashiko-bot
2026-06-22 10:19     ` Brendan Jackman
2026-06-22 10:01 ` [PATCH v2 06/13] KVM: VMX: " Brendan Jackman
2026-06-22 10:10   ` sashiko-bot
2026-06-22 10:21     ` Brendan Jackman
2026-06-22 10:01 ` [PATCH v2 07/13] x86/virt: " Brendan Jackman
2026-06-22 10:12   ` sashiko-bot
2026-06-22 10:22     ` Brendan Jackman
2026-06-22 10:01 ` [PATCH v2 08/13] sgi-xp: " Brendan Jackman
2026-06-22 10:15   ` sashiko-bot
2026-06-22 10:20   ` Greg Kroah-Hartman
2026-06-22 10:01 ` [PATCH v2 09/13] net/funeth: Switch to " Brendan Jackman
2026-06-22 10:11   ` sashiko-bot
2026-06-22 10:22     ` Brendan Jackman
2026-06-22 10:01 ` [PATCH v2 10/13] mm: Remove __alloc_pages_node() Brendan Jackman
2026-06-22 10:17   ` sashiko-bot
2026-06-22 10:28     ` Brendan Jackman
2026-06-22 10:01 ` [PATCH v2 11/13] alloc_tag: Move to mm/ Brendan Jackman
2026-06-22 10:01 ` [PATCH v2 12/13] mm: Move __alloc_pages() to mm/internal.h Brendan Jackman
2026-06-22 10:21   ` sashiko-bot
2026-06-22 11:14     ` Brendan Jackman
2026-06-22 12:24   ` David Hildenbrand (Arm)
2026-06-22 13:05     ` Lorenzo Stoakes
2026-06-22 13:07     ` Brendan Jackman
2026-06-22 14:30       ` David Hildenbrand (Arm)
2026-06-22 10:01 ` Brendan Jackman [this message]
2026-06-22 10:05 ` [PATCH v2 00/13] mm: Some cleanups for page allocator APIs Vlastimil Babka (SUSE)
2026-06-22 13:08 ` Lorenzo Stoakes
2026-06-22 13:15   ` Brendan Jackman

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260622-alloc-trylock-v2-13-31f31367d420@google.com \
    --to=jackmanb@google.com \
    --cc=akpm@linux-foundation.org \
    --cc=apopple@nvidia.com \
    --cc=ast@kernel.org \
    --cc=bigeasy@linutronix.de \
    --cc=byungchul@sk.com \
    --cc=cl@gentwo.org \
    --cc=clrkwllms@kernel.org \
    --cc=david@kernel.org \
    --cc=gourry@gourry.net \
    --cc=hannes@cmpxchg.org \
    --cc=hao.li@linux.dev \
    --cc=harry@kernel.org \
    --cc=joshua.hahnjy@gmail.com \
    --cc=liam@infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-rt-devel@lists.linux.dev \
    --cc=ljs@kernel.org \
    --cc=matthew.brost@intel.com \
    --cc=mhocko@suse.com \
    --cc=muchun.song@linux.dev \
    --cc=osalvador@suse.de \
    --cc=rakie.kim@sk.com \
    --cc=rientjes@google.com \
    --cc=roman.gushchin@linux.dev \
    --cc=rostedt@goodmis.org \
    --cc=rppt@kernel.org \
    --cc=surenb@google.com \
    --cc=vbabka@kernel.org \
    --cc=willy@infradead.org \
    --cc=ying.huang@linux.alibaba.com \
    --cc=ziy@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox