[PATCH v2 01/51] alloc_tag: don't remove /proc/allocinfo under the codetag module lock

[Christian Brauner <brauner@kernel.org>]

codetag_alloc_module_section() takes the codetag type's mod_lock for
writing and calls reserve_module_tags() with it held. When that can't
reserve the tags, because the section's alignment doesn't fit, because
there are too many tags for the page flag bits or because the memory
for them can't be allocated, it shuts memory allocation profiling down
and removes /proc/allocinfo, still with mod_lock held.

remove_proc_entry() waits until every reader of the entry has let go of
it, and a reader of /proc/allocinfo takes mod_lock for reading in
allocinfo_start() while it holds the entry. So a module load that hits
one of those paths while /proc/allocinfo is being read waits for the
reader and the reader waits for the module load, for good.

Let a work item remove the entry in that case. The profiling is shut
down right away like before, the file just goes a moment later.

Fixes: 4835f747d3ed ("alloc_tag: support for page allocation tag compression")
Cc: stable@vger.kernel.org
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>
---
 mm/alloc_tag.c | 27 ++++++++++++++++++++++++---
 1 file changed, 24 insertions(+), 3 deletions(-)

diff --git a/mm/alloc_tag.c b/mm/alloc_tag.c
index 82e2c3448dcf..7d7ad6704953 100644
--- a/mm/alloc_tag.c
+++ b/mm/alloc_tag.c
@@ -15,6 +15,7 @@
 #include <linux/seq_file.h>
 #include <linux/string_choices.h>
 #include <linux/vmalloc.h>
+#include <linux/workqueue.h>
 #include <linux/kmemleak.h>
 #include <uapi/linux/alloc_tag.h>
 
@@ -604,6 +605,26 @@ static void shutdown_mem_profiling(bool remove_file)
 	mem_profiling_support = false;
 }
 
+static void remove_allocinfo_file(struct work_struct *work)
+{
+	remove_proc_entry(ALLOCINFO_FILE_NAME, NULL);
+}
+static DECLARE_WORK(remove_allocinfo_work, remove_allocinfo_file);
+
+/*
+ * A module's tags are reserved with the codetag module lock held for
+ * writing, and a reader of /proc/allocinfo takes that lock with the entry
+ * pinned. Removing the entry there would wait for that reader for good, so
+ * let a work item do it.
+ */
+static void shutdown_mem_profiling_async(void)
+{
+	if (!mem_profiling_support)
+		return;
+	shutdown_mem_profiling(false);
+	schedule_work(&remove_allocinfo_work);
+}
+
 void __init alloc_tag_sec_init(void)
 {
 	struct alloc_tag *last_codetag;
@@ -855,7 +876,7 @@ static void *reserve_module_tags(struct module *mod, unsigned long size,
 		align = 1;
 
 	if (!ensure_alignment(align, &prepend)) {
-		shutdown_mem_profiling(true);
+		shutdown_mem_profiling_async();
 		pr_err("%s: alignment %lu is incompatible with allocation tag indexing. Memory allocation profiling is disabled!\n",
 			mod->name, align);
 		return ERR_PTR(-EINVAL);
@@ -905,14 +926,14 @@ unlock:
 
 		module_tags.size = offset + size;
 		if (mem_alloc_profiling_enabled() && !tags_addressable()) {
-			shutdown_mem_profiling(true);
+			shutdown_mem_profiling_async();
 			pr_warn("With module %s there are too many tags to fit in %d page flag bits. Memory allocation profiling is disabled!\n",
 				mod->name, NR_UNUSED_PAGEFLAG_BITS);
 		}
 
 		grow_res = vm_module_tags_populate();
 		if (grow_res) {
-			shutdown_mem_profiling(true);
+			shutdown_mem_profiling_async();
 			pr_err("Failed to allocate memory for allocation tags in the module %s. Memory allocation profiling is disabled!\n",
 			       mod->name);
 			return ERR_PTR(grow_res);

-- 
2.53.0