lib: add allocation tagging support for memory allocation profiling

Introduce CONFIG_MEM_ALLOC_PROFILING which provides definitions to easily
instrument memory allocators.  It registers an "alloc_tags" codetag type
with /proc/allocinfo interface to output allocation tag information when
the feature is enabled.

CONFIG_MEM_ALLOC_PROFILING_DEBUG is provided for debugging the memory
allocation profiling instrumentation.

Memory allocation profiling can be enabled or disabled at runtime using
/proc/sys/vm/mem_profiling sysctl when CONFIG_MEM_ALLOC_PROFILING_DEBUG=n.
CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT enables memory allocation
profiling by default.

[surenb@google.com: Documentation/filesystems/proc.rst: fix allocinfo title]
  Link: https://lkml.kernel.org/r/20240326073813.727090-1-surenb@google.com
[surenb@google.com: do limited memory accounting for modules with ARCH_NEEDS_WEAK_PER_CPU]
  Link: https://lkml.kernel.org/r/20240402180933.1663992-2-surenb@google.com
[klarasmodin@gmail.com: explicitly include irqflags.h in alloc_tag.h]
  Link: https://lkml.kernel.org/r/20240407133252.173636-1-klarasmodin@gmail.com
[surenb@google.com: fix alloc_tag_init() to prevent passing NULL to PTR_ERR()]
  Link: https://lkml.kernel.org/r/20240417003349.2520094-1-surenb@google.com
Link: https://lkml.kernel.org/r/20240321163705.3067592-14-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>
Signed-off-by: Klara Modin <klarasmodin@gmail.com>
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: Vlastimil Babka <vbabka@suse.cz>
Cc: Wedson Almeida Filho <wedsonaf@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 179 insertions, 0 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 015fc6ee9849..fa7aa32ba11a 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -972,6 +972,31 @@ config CODE_TAGGING
 	bool
 	select KALLSYMS
 
+config MEM_ALLOC_PROFILING
+	bool "Enable memory allocation profiling"
+	default n
+	depends on PROC_FS
+	depends on !DEBUG_FORCE_WEAK_PER_CPU
+	select CODE_TAGGING
+	help
+	  Track allocation source code and record total allocation size
+	  initiated at that code location. The mechanism can be used to track
+	  memory leaks with a low performance and memory impact.
+
+config MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT
+	bool "Enable memory allocation profiling by default"
+	default y
+	depends on MEM_ALLOC_PROFILING
+
+config MEM_ALLOC_PROFILING_DEBUG
+	bool "Memory allocation profiler debugging"
+	default n
+	depends on MEM_ALLOC_PROFILING
+	select MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT
+	help
+	  Adds warnings with helpful error messages for memory allocation
+	  profiling.
+
 source "lib/Kconfig.kasan"
 source "lib/Kconfig.kfence"
 source "lib/Kconfig.kmsan"
diff --git a/lib/Makefile b/lib/Makefile
index 910335da8f13..2f4e17bfb299 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -234,6 +234,8 @@ obj-$(CONFIG_OF_RECONFIG_NOTIFIER_ERROR_INJECT) += \
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
 
 obj-$(CONFIG_CODE_TAGGING) += codetag.o
+obj-$(CONFIG_MEM_ALLOC_PROFILING) += alloc_tag.o
+
 lib-$(CONFIG_GENERIC_BUG) += bug.o
 
 obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o
diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c
new file mode 100644
index 000000000000..331dd17650f3
--- /dev/null
+++ b/lib/alloc_tag.c
@@ -0,0 +1,152 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/alloc_tag.h>
+#include <linux/fs.h>
+#include <linux/gfp.h>
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_buf.h>
+#include <linux/seq_file.h>
+
+static struct codetag_type *alloc_tag_cttype;
+
+DEFINE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag);
+EXPORT_SYMBOL(_shared_alloc_tag);
+
+DEFINE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT,
+			mem_alloc_profiling_key);
+
+static void *allocinfo_start(struct seq_file *m, loff_t *pos)
+{
+	struct codetag_iterator *iter;
+	struct codetag *ct;
+	loff_t node = *pos;
+
+	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
+	m->private = iter;
+	if (!iter)
+		return NULL;
+
+	codetag_lock_module_list(alloc_tag_cttype, true);
+	*iter = codetag_get_ct_iter(alloc_tag_cttype);
+	while ((ct = codetag_next_ct(iter)) != NULL && node)
+		node--;
+
+	return ct ? iter : NULL;
+}
+
+static void *allocinfo_next(struct seq_file *m, void *arg, loff_t *pos)
+{
+	struct codetag_iterator *iter = (struct codetag_iterator *)arg;
+	struct codetag *ct = codetag_next_ct(iter);
+
+	(*pos)++;
+	if (!ct)
+		return NULL;
+
+	return iter;
+}
+
+static void allocinfo_stop(struct seq_file *m, void *arg)
+{
+	struct codetag_iterator *iter = (struct codetag_iterator *)m->private;
+
+	if (iter) {
+		codetag_lock_module_list(alloc_tag_cttype, false);
+		kfree(iter);
+	}
+}
+
+static void alloc_tag_to_text(struct seq_buf *out, struct codetag *ct)
+{
+	struct alloc_tag *tag = ct_to_alloc_tag(ct);
+	struct alloc_tag_counters counter = alloc_tag_read(tag);
+	s64 bytes = counter.bytes;
+
+	seq_buf_printf(out, "%12lli %8llu ", bytes, counter.calls);
+	codetag_to_text(out, ct);
+	seq_buf_putc(out, ' ');
+	seq_buf_putc(out, '\n');
+}
+
+static int allocinfo_show(struct seq_file *m, void *arg)
+{
+	struct codetag_iterator *iter = (struct codetag_iterator *)arg;
+	char *bufp;
+	size_t n = seq_get_buf(m, &bufp);
+	struct seq_buf buf;
+
+	seq_buf_init(&buf, bufp, n);
+	alloc_tag_to_text(&buf, iter->ct);
+	seq_commit(m, seq_buf_used(&buf));
+	return 0;
+}
+
+static const struct seq_operations allocinfo_seq_op = {
+	.start	= allocinfo_start,
+	.next	= allocinfo_next,
+	.stop	= allocinfo_stop,
+	.show	= allocinfo_show,
+};
+
+static void __init procfs_init(void)
+{
+	proc_create_seq("allocinfo", 0444, NULL, &allocinfo_seq_op);
+}
+
+static bool alloc_tag_module_unload(struct codetag_type *cttype,
+				    struct codetag_module *cmod)
+{
+	struct codetag_iterator iter = codetag_get_ct_iter(cttype);
+	struct alloc_tag_counters counter;
+	bool module_unused = true;
+	struct alloc_tag *tag;
+	struct codetag *ct;
+
+	for (ct = codetag_next_ct(&iter); ct; ct = codetag_next_ct(&iter)) {
+		if (iter.cmod != cmod)
+			continue;
+
+		tag = ct_to_alloc_tag(ct);
+		counter = alloc_tag_read(tag);
+
+		if (WARN(counter.bytes,
+			 "%s:%u module %s func:%s has %llu allocated at module unload",
+			 ct->filename, ct->lineno, ct->modname, ct->function, counter.bytes))
+			module_unused = false;
+	}
+
+	return module_unused;
+}
+
+static struct ctl_table memory_allocation_profiling_sysctls[] = {
+	{
+		.procname	= "mem_profiling",
+		.data		= &mem_alloc_profiling_key,
+#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG
+		.mode		= 0444,
+#else
+		.mode		= 0644,
+#endif
+		.proc_handler	= proc_do_static_key,
+	},
+	{ }
+};
+
+static int __init alloc_tag_init(void)
+{
+	const struct codetag_type_desc desc = {
+		.section	= "alloc_tags",
+		.tag_size	= sizeof(struct alloc_tag),
+		.module_unload	= alloc_tag_module_unload,
+	};
+
+	alloc_tag_cttype = codetag_register_type(&desc);
+	if (IS_ERR(alloc_tag_cttype))
+		return PTR_ERR(alloc_tag_cttype);
+
+	register_sysctl_init("vm", memory_allocation_profiling_sysctls);
+	procfs_init();
+
+	return 0;
+}
+module_init(alloc_tag_init);