lib: introduce support for page allocation tagging

Introduce helper functions to easily instrument page allocators by storing
a pointer to the allocation tag associated with the code that allocated
the page in a page_ext field.

Link: https://lkml.kernel.org/r/20240321163705.3067592-15-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Co-developed-by: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Kees Cook <keescook@chromium.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alex Gaynor <alex.gaynor@gmail.com>
Cc: Alice Ryhl <aliceryhl@google.com>
Cc: Andreas Hindborg <a.hindborg@samsung.com>
Cc: Benno Lossin <benno.lossin@proton.me>
Cc: "Björn Roy Baron" <bjorn3_gh@protonmail.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Gary Guo <gary@garyguo.net>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Wedson Almeida Filho <wedsonaf@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

7 files changed, 105 insertions, 1 deletions

diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index be98564191e6..07e0656898f9 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -4,7 +4,6 @@
 
 #include <linux/types.h>
 #include <linux/stacktrace.h>
-#include <linux/stackdepot.h>
 
 struct pglist_data;
 
diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h
new file mode 100644
index 000000000000..66bd021eb46e
--- /dev/null
+++ b/include/linux/pgalloc_tag.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * page allocation tagging
+ */
+#ifndef _LINUX_PGALLOC_TAG_H
+#define _LINUX_PGALLOC_TAG_H
+
+#include <linux/alloc_tag.h>
+
+#ifdef CONFIG_MEM_ALLOC_PROFILING
+
+#include <linux/page_ext.h>
+
+extern struct page_ext_operations page_alloc_tagging_ops;
+extern struct page_ext *page_ext_get(struct page *page);
+extern void page_ext_put(struct page_ext *page_ext);
+
+static inline union codetag_ref *codetag_ref_from_page_ext(struct page_ext *page_ext)
+{
+	return (void *)page_ext + page_alloc_tagging_ops.offset;
+}
+
+static inline struct page_ext *page_ext_from_codetag_ref(union codetag_ref *ref)
+{
+	return (void *)ref - page_alloc_tagging_ops.offset;
+}
+
+/* Should be called only if mem_alloc_profiling_enabled() */
+static inline union codetag_ref *get_page_tag_ref(struct page *page)
+{
+	if (page) {
+		struct page_ext *page_ext = page_ext_get(page);
+
+		if (page_ext)
+			return codetag_ref_from_page_ext(page_ext);
+	}
+	return NULL;
+}
+
+static inline void put_page_tag_ref(union codetag_ref *ref)
+{
+	page_ext_put(page_ext_from_codetag_ref(ref));
+}
+
+static inline void pgalloc_tag_add(struct page *page, struct task_struct *task,
+				   unsigned int nr)
+{
+	if (mem_alloc_profiling_enabled()) {
+		union codetag_ref *ref = get_page_tag_ref(page);
+
+		if (ref) {
+			alloc_tag_add(ref, task->alloc_tag, PAGE_SIZE * nr);
+			put_page_tag_ref(ref);
+		}
+	}
+}
+
+static inline void pgalloc_tag_sub(struct page *page, unsigned int nr)
+{
+	if (mem_alloc_profiling_enabled()) {
+		union codetag_ref *ref = get_page_tag_ref(page);
+
+		if (ref) {
+			alloc_tag_sub(ref, PAGE_SIZE * nr);
+			put_page_tag_ref(ref);
+		}
+	}
+}
+
+#else /* CONFIG_MEM_ALLOC_PROFILING */
+
+static inline void pgalloc_tag_add(struct page *page, struct task_struct *task,
+				   unsigned int nr) {}
+static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {}
+
+#endif /* CONFIG_MEM_ALLOC_PROFILING */
+
+#endif /* _LINUX_PGALLOC_TAG_H */
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index fa7aa32ba11a..a8f77de5e8ea 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -978,6 +978,7 @@ config MEM_ALLOC_PROFILING
 	depends on PROC_FS
 	depends on !DEBUG_FORCE_WEAK_PER_CPU
 	select CODE_TAGGING
+	select PAGE_EXTENSION
 	help
 	  Track allocation source code and record total allocation size
 	  initiated at that code location. The mechanism can be used to track
diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c
index 331dd17650f3..59bb71036837 100644
--- a/lib/alloc_tag.c
+++ b/lib/alloc_tag.c
@@ -3,6 +3,7 @@
 #include <linux/fs.h>
 #include <linux/gfp.h>
 #include <linux/module.h>
+#include <linux/page_ext.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_buf.h>
 #include <linux/seq_file.h>
@@ -118,6 +119,22 @@ static bool alloc_tag_module_unload(struct codetag_type *cttype,
 	return module_unused;
 }
 
+static __init bool need_page_alloc_tagging(void)
+{
+	return true;
+}
+
+static __init void init_page_alloc_tagging(void)
+{
+}
+
+struct page_ext_operations page_alloc_tagging_ops = {
+	.size = sizeof(union codetag_ref),
+	.need = need_page_alloc_tagging,
+	.init = init_page_alloc_tagging,
+};
+EXPORT_SYMBOL(page_alloc_tagging_ops);
+
 static struct ctl_table memory_allocation_profiling_sysctls[] = {
 	{
 		.procname	= "mem_profiling",
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 549e76af8f82..2fd9bf044a79 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -24,6 +24,7 @@
 #include <linux/page_ext.h>
 #include <linux/pti.h>
 #include <linux/pgtable.h>
+#include <linux/stackdepot.h>
 #include <linux/swap.h>
 #include <linux/cma.h>
 #include <linux/crash_dump.h>
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5083ac034d26..3fd273c22749 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -54,6 +54,7 @@
 #include <linux/khugepaged.h>
 #include <linux/delayacct.h>
 #include <linux/cacheinfo.h>
+#include <linux/pgalloc_tag.h>
 #include <asm/div64.h>
 #include "internal.h"
 #include "shuffle.h"
@@ -1101,6 +1102,7 @@ __always_inline bool free_pages_prepare(struct page *page,
 		/* Do not let hwpoison pages hit pcplists/buddy */
 		reset_page_owner(page, order);
 		page_table_check_free(page, order);
+		pgalloc_tag_sub(page, 1 << order);
 		return false;
 	}
 
@@ -1140,6 +1142,7 @@ __always_inline bool free_pages_prepare(struct page *page,
 	page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 	reset_page_owner(page, order);
 	page_table_check_free(page, order);
+	pgalloc_tag_sub(page, 1 << order);
 
 	if (!PageHighMem(page)) {
 		debug_check_no_locks_freed(page_address(page),
@@ -1533,6 +1536,7 @@ 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);
 }
 
 static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
diff --git a/mm/page_ext.c b/mm/page_ext.c
index 4548fcc66d74..3c58fe8a24df 100644
--- a/mm/page_ext.c
+++ b/mm/page_ext.c
@@ -10,6 +10,7 @@
 #include <linux/page_idle.h>
 #include <linux/page_table_check.h>
 #include <linux/rcupdate.h>
+#include <linux/pgalloc_tag.h>
 
 /*
  * struct page extension
@@ -82,6 +83,9 @@ static struct page_ext_operations *page_ext_ops[] __initdata = {
 #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT)
 	&page_idle_ops,
 #endif
+#ifdef CONFIG_MEM_ALLOC_PROFILING
+	&page_alloc_tagging_ops,
+#endif
 #ifdef CONFIG_PAGE_TABLE_CHECK
 	&page_table_check_ops,
 #endif