alloc_tag: allocate percpu counters for module tags dynamically

When a module gets unloaded it checks whether any of its tags are still in
use and if so, we keep the memory containing module's allocation tags
alive until all tags are unused.  However percpu counters referenced by
the tags are freed by free_module().  This will lead to UAF if the memory
allocated by a module is accessed after module was unloaded.

To fix this we allocate percpu counters for module allocation tags
dynamically and we keep it alive for tags which are still in use after
module unloading.  This also removes the requirement of a larger
PERCPU_MODULE_RESERVE when memory allocation profiling is enabled because
percpu memory for counters does not need to be reserved anymore.

Link: https://lkml.kernel.org/r/[email protected]
Fixes: 0db6f8d7820a ("alloc_tag: load module tags into separate contiguous memory")
Signed-off-by: Suren Baghdasaryan <[email protected]>
Reported-by: David Wang <[email protected]>
Closes: https://lore.kernel.org/all/[email protected]/
Tested-by: David Wang <[email protected]>
Cc: Christoph Lameter (Ampere) <[email protected]>
Cc: Dennis Zhou <[email protected]>
Cc: Kent Overstreet <[email protected]>
Cc: Pasha Tatashin <[email protected]>
Cc: Tejun Heo <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

1 files changed, 69 insertions, 18 deletions

diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c
index 25ecc1334b67..c7f602fa7b23 100644
--- a/lib/alloc_tag.c
+++ b/lib/alloc_tag.c
@@ -350,18 +350,28 @@ static bool needs_section_mem(struct module *mod, unsigned long size)
 	return size >= sizeof(struct alloc_tag);
 }
 
-static struct alloc_tag *find_used_tag(struct alloc_tag *from, struct alloc_tag *to)
+static bool clean_unused_counters(struct alloc_tag *start_tag,
+				  struct alloc_tag *end_tag)
 {
-	while (from <= to) {
+	struct alloc_tag *tag;
+	bool ret = true;
+
+	for (tag = start_tag; tag <= end_tag; tag++) {
 		struct alloc_tag_counters counter;
 
-		counter = alloc_tag_read(from);
-		if (counter.bytes)
-			return from;
-		from++;
+		if (!tag->counters)
+			continue;
+
+		counter = alloc_tag_read(tag);
+		if (!counter.bytes) {
+			free_percpu(tag->counters);
+			tag->counters = NULL;
+		} else {
+			ret = false;
+		}
 	}
 
-	return NULL;
+	return ret;
 }
 
 /* Called with mod_area_mt locked */
@@ -371,12 +381,16 @@ static void clean_unused_module_areas_locked(void)
 	struct module *val;
 
 	mas_for_each(&mas, val, module_tags.size) {
+		struct alloc_tag *start_tag;
+		struct alloc_tag *end_tag;
+
 		if (val != &unloaded_mod)
 			continue;
 
 		/* Release area if all tags are unused */
-		if (!find_used_tag((struct alloc_tag *)(module_tags.start_addr + mas.index),
-				   (struct alloc_tag *)(module_tags.start_addr + mas.last)))
+		start_tag = (struct alloc_tag *)(module_tags.start_addr + mas.index);
+		end_tag = (struct alloc_tag *)(module_tags.start_addr + mas.last);
+		if (clean_unused_counters(start_tag, end_tag))
 			mas_erase(&mas);
 	}
 }
@@ -561,7 +575,8 @@ unlock:
 static void release_module_tags(struct module *mod, bool used)
 {
 	MA_STATE(mas, &mod_area_mt, module_tags.size, module_tags.size);
-	struct alloc_tag *tag;
+	struct alloc_tag *start_tag;
+	struct alloc_tag *end_tag;
 	struct module *val;
 
 	mas_lock(&mas);
@@ -575,15 +590,22 @@ static void release_module_tags(struct module *mod, bool used)
 	if (!used)
 		goto release_area;
 
-	/* Find out if the area is used */
-	tag = find_used_tag((struct alloc_tag *)(module_tags.start_addr + mas.index),
-			    (struct alloc_tag *)(module_tags.start_addr + mas.last));
-	if (tag) {
-		struct alloc_tag_counters counter = alloc_tag_read(tag);
+	start_tag = (struct alloc_tag *)(module_tags.start_addr + mas.index);
+	end_tag = (struct alloc_tag *)(module_tags.start_addr + mas.last);
+	if (!clean_unused_counters(start_tag, end_tag)) {
+		struct alloc_tag *tag;
+
+		for (tag = start_tag; tag <= end_tag; tag++) {
+			struct alloc_tag_counters counter;
+
+			if (!tag->counters)
+				continue;
 
-		pr_info("%s:%u module %s func:%s has %llu allocated at module unload\n",
-			tag->ct.filename, tag->ct.lineno, tag->ct.modname,
-			tag->ct.function, counter.bytes);
+			counter = alloc_tag_read(tag);
+			pr_info("%s:%u module %s func:%s has %llu allocated at module unload\n",
+				tag->ct.filename, tag->ct.lineno, tag->ct.modname,
+				tag->ct.function, counter.bytes);
+		}
 	} else {
 		used = false;
 	}
@@ -596,6 +618,34 @@ out:
 	mas_unlock(&mas);
 }
 
+static void load_module(struct module *mod, struct codetag *start, struct codetag *stop)
+{
+	/* Allocate module alloc_tag percpu counters */
+	struct alloc_tag *start_tag;
+	struct alloc_tag *stop_tag;
+	struct alloc_tag *tag;
+
+	if (!mod)
+		return;
+
+	start_tag = ct_to_alloc_tag(start);
+	stop_tag = ct_to_alloc_tag(stop);
+	for (tag = start_tag; tag < stop_tag; tag++) {
+		WARN_ON(tag->counters);
+		tag->counters = alloc_percpu(struct alloc_tag_counters);
+		if (!tag->counters) {
+			while (--tag >= start_tag) {
+				free_percpu(tag->counters);
+				tag->counters = NULL;
+			}
+			shutdown_mem_profiling(true);
+			pr_err("Failed to allocate memory for allocation tag percpu counters in the module %s. Memory allocation profiling is disabled!\n",
+			       mod->name);
+			break;
+		}
+	}
+}
+
 static void replace_module(struct module *mod, struct module *new_mod)
 {
 	MA_STATE(mas, &mod_area_mt, 0, module_tags.size);
@@ -757,6 +807,7 @@ static int __init alloc_tag_init(void)
 		.needs_section_mem	= needs_section_mem,
 		.alloc_section_mem	= reserve_module_tags,
 		.free_section_mem	= release_module_tags,
+		.module_load		= load_module,
 		.module_replaced	= replace_module,
 #endif
 	};