mm: defer kmemleak object creation of module_alloc()

[ Upstream commit 60115fa54a ]

Yongqiang reports a kmemleak panic when module insmod/rmmod with KASAN
enabled(without KASAN_VMALLOC) on x86[1].

When the module area allocates memory, it's kmemleak_object is created
successfully, but the KASAN shadow memory of module allocation is not
ready, so when kmemleak scan the module's pointer, it will panic due to
no shadow memory with KASAN check.

  module_alloc
    __vmalloc_node_range
      kmemleak_vmalloc
				kmemleak_scan
				  update_checksum
    kasan_module_alloc
      kmemleak_ignore

Note, there is no problem if KASAN_VMALLOC enabled, the modules area
entire shadow memory is preallocated.  Thus, the bug only exits on ARCH
which supports dynamic allocation of module area per module load, for
now, only x86/arm64/s390 are involved.

Add a VM_DEFER_KMEMLEAK flags, defer vmalloc'ed object register of
kmemleak in module_alloc() to fix this issue.

[1] https://lore.kernel.org/all/6d41e2b9-4692-5ec4-b1cd-cbe29ae89739@huawei.com/

[wangkefeng.wang@huawei.com: fix build]
  Link: https://lkml.kernel.org/r/20211125080307.27225-1-wangkefeng.wang@huawei.com
[akpm@linux-foundation.org: simplify ifdefs, per Andrey]
  Link: https://lkml.kernel.org/r/CA+fCnZcnwJHUQq34VuRxpdoY6_XbJCDJ-jopksS5Eia4PijPzw@mail.gmail.com

Link: https://lkml.kernel.org/r/20211124142034.192078-1-wangkefeng.wang@huawei.com
Fixes: 793213a82d ("s390/kasan: dynamic shadow mem allocation for modules")
Fixes: 39d114ddc6 ("arm64: add KASAN support")
Fixes: bebf56a1b1 ("kasan: enable instrumentation of global variables")
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Reported-by: Yongqiang Liu <liuyongqiang13@huawei.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>

arch/arm64/kernel/module.c

@@ -36,7 +36,7 @@ void *module_alloc(unsigned long size)
 		module_alloc_end = MODULES_END;
 
 	p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base,
-				module_alloc_end, gfp_mask, PAGE_KERNEL, 0,
+				module_alloc_end, gfp_mask, PAGE_KERNEL, VM_DEFER_KMEMLEAK,
 				NUMA_NO_NODE, __builtin_return_address(0));
 
 	if (!p && IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) &&
@@ -58,7 +58,7 @@ void *module_alloc(unsigned long size)
 				PAGE_KERNEL, 0, NUMA_NO_NODE,
 				__builtin_return_address(0));
 
-	if (p && (kasan_module_alloc(p, size) < 0)) {
+	if (p && (kasan_module_alloc(p, size, gfp_mask) < 0)) {
 		vfree(p);
 		return NULL;
 	}

arch/s390/kernel/module.c

@@ -37,14 +37,15 @@
 
 void *module_alloc(unsigned long size)
 {
+	gfp_t gfp_mask = GFP_KERNEL;
 	void *p;
 
 	if (PAGE_ALIGN(size) > MODULES_LEN)
 		return NULL;
 	p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR, MODULES_END,
-				 GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+				 gfp_mask, PAGE_KERNEL_EXEC, VM_DEFER_KMEMLEAK, NUMA_NO_NODE,
 				 __builtin_return_address(0));
-	if (p && (kasan_module_alloc(p, size) < 0)) {
+	if (p && (kasan_module_alloc(p, size, gfp_mask) < 0)) {
 		vfree(p);
 		return NULL;
 	}

arch/x86/kernel/module.c

@@ -67,6 +67,7 @@ static unsigned long int get_module_load_offset(void)
 
 void *module_alloc(unsigned long size)
 {
+	gfp_t gfp_mask = GFP_KERNEL;
 	void *p;
 
 	if (PAGE_ALIGN(size) > MODULES_LEN)
@@ -74,10 +75,10 @@ void *module_alloc(unsigned long size)
 
 	p = __vmalloc_node_range(size, MODULE_ALIGN,
 				    MODULES_VADDR + get_module_load_offset(),
-				    MODULES_END, GFP_KERNEL,
-				    PAGE_KERNEL, 0, NUMA_NO_NODE,
+				    MODULES_END, gfp_mask,
+				    PAGE_KERNEL, VM_DEFER_KMEMLEAK, NUMA_NO_NODE,
 				    __builtin_return_address(0));
-	if (p && (kasan_module_alloc(p, size) < 0)) {
+	if (p && (kasan_module_alloc(p, size, gfp_mask) < 0)) {
 		vfree(p);
 		return NULL;
 	}

include/linux/kasan.h

@@ -461,12 +461,12 @@ static inline void kasan_release_vmalloc(unsigned long start,
  * allocations with real shadow memory. With KASAN vmalloc, the special
  * case is unnecessary, as the work is handled in the generic case.
  */
-int kasan_module_alloc(void *addr, size_t size);
+int kasan_module_alloc(void *addr, size_t size, gfp_t gfp_mask);
 void kasan_free_shadow(const struct vm_struct *vm);
 
 #else /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */
 
-static inline int kasan_module_alloc(void *addr, size_t size) { return 0; }
+static inline int kasan_module_alloc(void *addr, size_t size, gfp_t gfp_mask) { return 0; }
 static inline void kasan_free_shadow(const struct vm_struct *vm) {}
 
 #endif /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */

include/linux/vmalloc.h

@@ -28,6 +28,13 @@ struct notifier_block;		/* in notifier.h */
 #define VM_MAP_PUT_PAGES	0x00000200	/* put pages and free array in vfree */
 #define VM_NO_HUGE_VMAP		0x00000400	/* force PAGE_SIZE pte mapping */
 
+#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
+	!defined(CONFIG_KASAN_VMALLOC)
+#define VM_DEFER_KMEMLEAK	0x00000800	/* defer kmemleak object creation */
+#else
+#define VM_DEFER_KMEMLEAK	0
+#endif
+
 /*
  * VM_KASAN is used slightly differently depending on CONFIG_KASAN_VMALLOC.
  *

mm/kasan/shadow.c

@@ -493,7 +493,7 @@ void kasan_release_vmalloc(unsigned long start, unsigned long end,
 
 #else /* CONFIG_KASAN_VMALLOC */
 
-int kasan_module_alloc(void *addr, size_t size)
+int kasan_module_alloc(void *addr, size_t size, gfp_t gfp_mask)
 {
 	void *ret;
 	size_t scaled_size;
@@ -515,9 +515,14 @@ int kasan_module_alloc(void *addr, size_t size)
 			__builtin_return_address(0));
 
 	if (ret) {
+		struct vm_struct *vm = find_vm_area(addr);
 		__memset(ret, KASAN_SHADOW_INIT, shadow_size);
-		find_vm_area(addr)->flags |= VM_KASAN;
+		vm->flags |= VM_KASAN;
 		kmemleak_ignore(ret);
+
+		if (vm->flags & VM_DEFER_KMEMLEAK)
+			kmemleak_vmalloc(vm, size, gfp_mask);
+
 		return 0;
 	}
 

mm/vmalloc.c

@@ -3032,6 +3032,7 @@ again:
 	clear_vm_uninitialized_flag(area);
 
 	size = PAGE_ALIGN(size);
+	if (!(vm_flags & VM_DEFER_KMEMLEAK))
 		kmemleak_vmalloc(area, size, gfp_mask);
 
 	return addr;