summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorStephen Rothwell <sfr@canb.auug.org.au>2017-12-08 14:51:32 +1100
committerStephen Rothwell <sfr@canb.auug.org.au>2017-12-08 14:51:32 +1100
commit0d30821ca64f0b47e3767148075f1d47a5b98c99 (patch)
tree4a65f8fc491ad9aa63e7d9e51d13251b4e53e536
parent644cd3e39dc6ce95a4ce5a35c2a2b1698f3e6f03 (diff)
parent589cde432c02376f863fca98c3e7549f64d78559 (diff)
downloadlinux-next-0d30821ca64f0b47e3767148075f1d47a5b98c99.tar.gz
Merge remote-tracking branch 'kspp/for-next/kspp'
-rw-r--r--arch/Kconfig11
-rw-r--r--arch/arm/Kconfig1
-rw-r--r--arch/arm/include/asm/processor.h7
-rw-r--r--arch/arm64/Kconfig1
-rw-r--r--arch/arm64/include/asm/processor.h8
-rw-r--r--arch/x86/Kconfig1
-rw-r--r--arch/x86/include/asm/processor.h8
-rw-r--r--arch/x86/kvm/x86.c7
-rw-r--r--drivers/misc/lkdtm.h4
-rw-r--r--drivers/misc/lkdtm_core.c4
-rw-r--r--drivers/misc/lkdtm_usercopy.c88
-rw-r--r--drivers/scsi/scsi_lib.c9
-rw-r--r--fs/befs/linuxvfs.c14
-rw-r--r--fs/cifs/cifsfs.c10
-rw-r--r--fs/dcache.c9
-rw-r--r--fs/exofs/super.c7
-rw-r--r--fs/ext2/super.c12
-rw-r--r--fs/ext4/super.c12
-rw-r--r--fs/fhandle.c3
-rw-r--r--fs/freevxfs/vxfs_super.c8
-rw-r--r--fs/jfs/super.c8
-rw-r--r--fs/orangefs/super.c15
-rw-r--r--fs/ufs/super.c13
-rw-r--r--include/linux/sched/task.h14
-rw-r--r--include/linux/slab.h29
-rw-r--r--include/linux/slab_def.h3
-rw-r--r--include/linux/slub_def.h3
-rw-r--r--include/linux/stddef.h2
-rw-r--r--include/net/sctp/structs.h9
-rw-r--r--include/net/sock.h2
-rw-r--r--kernel/fork.c31
-rw-r--r--mm/slab.c34
-rw-r--r--mm/slab.h8
-rw-r--r--mm/slab_common.c62
-rw-r--r--mm/slub.c44
-rw-r--r--mm/usercopy.c12
-rw-r--r--net/caif/caif_socket.c2
-rw-r--r--net/core/sock.c4
-rw-r--r--net/ipv4/raw.c2
-rw-r--r--net/ipv6/raw.c2
-rw-r--r--net/sctp/socket.c10
-rw-r--r--security/Kconfig14
-rw-r--r--virt/kvm/kvm_main.c8
43 files changed, 417 insertions, 138 deletions
diff --git a/arch/Kconfig b/arch/Kconfig
index 400b9e1b2f27..8911ff37335a 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -242,6 +242,17 @@ config ARCH_INIT_TASK
config ARCH_TASK_STRUCT_ALLOCATOR
bool
+config HAVE_ARCH_THREAD_STRUCT_WHITELIST
+ bool
+ depends on !ARCH_TASK_STRUCT_ALLOCATOR
+ help
+ An architecture should select this to provide hardened usercopy
+ knowledge about what region of the thread_struct should be
+ whitelisted for copying to userspace. Normally this is only the
+ FPU registers. Specifically, arch_thread_struct_whitelist()
+ should be implemented. Without this, the entire thread_struct
+ field in task_struct will be left whitelisted.
+
# Select if arch has its private alloc_thread_stack() function
config ARCH_THREAD_STACK_ALLOCATOR
bool
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 438231500510..5abdd9906a3c 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -50,6 +50,7 @@ config ARM
select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
select HAVE_ARCH_MMAP_RND_BITS if MMU
select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT)
+ select HAVE_ARCH_THREAD_STRUCT_WHITELIST
select HAVE_ARCH_TRACEHOOK
select HAVE_ARM_SMCCC if CPU_V7
select HAVE_EBPF_JIT if !CPU_ENDIAN_BE32
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index 338cbe0a18ef..01a41be58d43 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -45,6 +45,13 @@ struct thread_struct {
struct debug_info debug;
};
+/* Nothing needs to be usercopy-whitelisted from thread_struct. */
+static inline void arch_thread_struct_whitelist(unsigned long *offset,
+ unsigned long *size)
+{
+ *offset = *size = 0;
+}
+
#define INIT_THREAD { }
#define start_thread(regs,pc,sp) \
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a93339f5178f..c84477e6a884 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -90,6 +90,7 @@ config ARM64
select HAVE_ARCH_MMAP_RND_BITS
select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
select HAVE_ARCH_SECCOMP_FILTER
+ select HAVE_ARCH_THREAD_STRUCT_WHITELIST
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
select HAVE_ARCH_VMAP_STACK
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 023cacb946c3..e58a5864ec89 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -113,6 +113,14 @@ struct thread_struct {
struct debug_info debug; /* debugging */
};
+/* Whitelist the fpsimd_state for copying to userspace. */
+static inline void arch_thread_struct_whitelist(unsigned long *offset,
+ unsigned long *size)
+{
+ *offset = offsetof(struct thread_struct, fpsimd_state);
+ *size = sizeof(struct fpsimd_state);
+}
+
#ifdef CONFIG_COMPAT
#define task_user_tls(t) \
({ \
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e412670ee550..a5667e42b33e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -116,6 +116,7 @@ config X86
select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT
select HAVE_ARCH_COMPAT_MMAP_BASES if MMU && COMPAT
select HAVE_ARCH_SECCOMP_FILTER
+ select HAVE_ARCH_THREAD_STRUCT_WHITELIST
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index cad8dab266bc..f6814925ca63 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -507,6 +507,14 @@ struct thread_struct {
*/
};
+/* Whitelist the FPU state from the task_struct for hardened usercopy. */
+static inline void arch_thread_struct_whitelist(unsigned long *offset,
+ unsigned long *size)
+{
+ *offset = offsetof(struct thread_struct, fpu.state);
+ *size = fpu_kernel_xstate_size;
+}
+
/*
* Thread-synchronous status.
*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6ca747abfa2f..1e1e617cf81d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4237,13 +4237,14 @@ set_identity_unlock:
mutex_unlock(&kvm->lock);
break;
case KVM_XEN_HVM_CONFIG: {
+ struct kvm_xen_hvm_config xhc;
r = -EFAULT;
- if (copy_from_user(&kvm->arch.xen_hvm_config, argp,
- sizeof(struct kvm_xen_hvm_config)))
+ if (copy_from_user(&xhc, argp, sizeof(xhc)))
goto out;
r = -EINVAL;
- if (kvm->arch.xen_hvm_config.flags)
+ if (xhc.flags)
goto out;
+ memcpy(&kvm->arch.xen_hvm_config, &xhc, sizeof(xhc));
r = 0;
break;
}
diff --git a/drivers/misc/lkdtm.h b/drivers/misc/lkdtm.h
index 687a0dbbe199..9e513dcfd809 100644
--- a/drivers/misc/lkdtm.h
+++ b/drivers/misc/lkdtm.h
@@ -76,8 +76,8 @@ void __init lkdtm_usercopy_init(void);
void __exit lkdtm_usercopy_exit(void);
void lkdtm_USERCOPY_HEAP_SIZE_TO(void);
void lkdtm_USERCOPY_HEAP_SIZE_FROM(void);
-void lkdtm_USERCOPY_HEAP_FLAG_TO(void);
-void lkdtm_USERCOPY_HEAP_FLAG_FROM(void);
+void lkdtm_USERCOPY_HEAP_WHITELIST_TO(void);
+void lkdtm_USERCOPY_HEAP_WHITELIST_FROM(void);
void lkdtm_USERCOPY_STACK_FRAME_TO(void);
void lkdtm_USERCOPY_STACK_FRAME_FROM(void);
void lkdtm_USERCOPY_STACK_BEYOND(void);
diff --git a/drivers/misc/lkdtm_core.c b/drivers/misc/lkdtm_core.c
index ba92291508dc..e3f2bac4b245 100644
--- a/drivers/misc/lkdtm_core.c
+++ b/drivers/misc/lkdtm_core.c
@@ -177,8 +177,8 @@ static const struct crashtype crashtypes[] = {
CRASHTYPE(ATOMIC_TIMING),
CRASHTYPE(USERCOPY_HEAP_SIZE_TO),
CRASHTYPE(USERCOPY_HEAP_SIZE_FROM),
- CRASHTYPE(USERCOPY_HEAP_FLAG_TO),
- CRASHTYPE(USERCOPY_HEAP_FLAG_FROM),
+ CRASHTYPE(USERCOPY_HEAP_WHITELIST_TO),
+ CRASHTYPE(USERCOPY_HEAP_WHITELIST_FROM),
CRASHTYPE(USERCOPY_STACK_FRAME_TO),
CRASHTYPE(USERCOPY_STACK_FRAME_FROM),
CRASHTYPE(USERCOPY_STACK_BEYOND),
diff --git a/drivers/misc/lkdtm_usercopy.c b/drivers/misc/lkdtm_usercopy.c
index a64372cc148d..a2fca01d643b 100644
--- a/drivers/misc/lkdtm_usercopy.c
+++ b/drivers/misc/lkdtm_usercopy.c
@@ -20,7 +20,7 @@
*/
static volatile size_t unconst = 0;
static volatile size_t cache_size = 1024;
-static struct kmem_cache *bad_cache;
+static struct kmem_cache *whitelist_cache;
static const unsigned char test_text[] = "This is a test.\n";
@@ -115,6 +115,10 @@ free_user:
vm_munmap(user_addr, PAGE_SIZE);
}
+/*
+ * This checks for whole-object size validation with hardened usercopy,
+ * with or without usercopy whitelisting.
+ */
static void do_usercopy_heap_size(bool to_user)
{
unsigned long user_addr;
@@ -172,77 +176,79 @@ free_kernel:
kfree(two);
}
-static void do_usercopy_heap_flag(bool to_user)
+/*
+ * This checks for the specific whitelist window within an object. If this
+ * test passes, then do_usercopy_heap_size() tests will pass too.
+ */
+static void do_usercopy_heap_whitelist(bool to_user)
{
- unsigned long user_addr;
- unsigned char *good_buf = NULL;
- unsigned char *bad_buf = NULL;
+ unsigned long user_alloc;
+ unsigned char *buf = NULL;
+ unsigned char __user *user_addr;
+ size_t offset, size;
/* Make sure cache was prepared. */
- if (!bad_cache) {
+ if (!whitelist_cache) {
pr_warn("Failed to allocate kernel cache\n");
return;
}
/*
- * Allocate one buffer from each cache (kmalloc will have the
- * SLAB_USERCOPY flag already, but "bad_cache" won't).
+ * Allocate a buffer with a whitelisted window in the buffer.
*/
- good_buf = kmalloc(cache_size, GFP_KERNEL);
- bad_buf = kmem_cache_alloc(bad_cache, GFP_KERNEL);
- if (!good_buf || !bad_buf) {
- pr_warn("Failed to allocate buffers from caches\n");
+ buf = kmem_cache_alloc(whitelist_cache, GFP_KERNEL);
+ if (!buf) {
+ pr_warn("Failed to allocate buffer from whitelist cache\n");
goto free_alloc;
}
/* Allocate user memory we'll poke at. */
- user_addr = vm_mmap(NULL, 0, PAGE_SIZE,
+ user_alloc = vm_mmap(NULL, 0, PAGE_SIZE,
PROT_READ | PROT_WRITE | PROT_EXEC,
MAP_ANONYMOUS | MAP_PRIVATE, 0);
- if (user_addr >= TASK_SIZE) {
+ if (user_alloc >= TASK_SIZE) {
pr_warn("Failed to allocate user memory\n");
goto free_alloc;
}
+ user_addr = (void __user *)user_alloc;
- memset(good_buf, 'A', cache_size);
- memset(bad_buf, 'B', cache_size);
+ memset(buf, 'B', cache_size);
+
+ /* Whitelisted window in buffer, from kmem_cache_create_usercopy. */
+ offset = (cache_size / 4) + unconst;
+ size = (cache_size / 16) + unconst;
if (to_user) {
- pr_info("attempting good copy_to_user with SLAB_USERCOPY\n");
- if (copy_to_user((void __user *)user_addr, good_buf,
- cache_size)) {
+ pr_info("attempting good copy_to_user inside whitelist\n");
+ if (copy_to_user(user_addr, buf + offset, size)) {
pr_warn("copy_to_user failed unexpectedly?!\n");
goto free_user;
}
- pr_info("attempting bad copy_to_user w/o SLAB_USERCOPY\n");
- if (copy_to_user((void __user *)user_addr, bad_buf,
- cache_size)) {
+ pr_info("attempting bad copy_to_user outside whitelist\n");
+ if (copy_to_user(user_addr, buf + offset - 1, size)) {
pr_warn("copy_to_user failed, but lacked Oops\n");
goto free_user;
}
} else {
- pr_info("attempting good copy_from_user with SLAB_USERCOPY\n");
- if (copy_from_user(good_buf, (void __user *)user_addr,
- cache_size)) {
+ pr_info("attempting good copy_from_user inside whitelist\n");
+ if (copy_from_user(buf + offset, user_addr, size)) {
pr_warn("copy_from_user failed unexpectedly?!\n");
goto free_user;
}
- pr_info("attempting bad copy_from_user w/o SLAB_USERCOPY\n");
- if (copy_from_user(bad_buf, (void __user *)user_addr,
- cache_size)) {
+ pr_info("attempting bad copy_from_user outside whitelist\n");
+ if (copy_from_user(buf + offset - 1, user_addr, size)) {
pr_warn("copy_from_user failed, but lacked Oops\n");
goto free_user;
}
}
free_user:
- vm_munmap(user_addr, PAGE_SIZE);
+ vm_munmap(user_alloc, PAGE_SIZE);
free_alloc:
- if (bad_buf)
- kmem_cache_free(bad_cache, bad_buf);
- kfree(good_buf);
+ if (buf)
+ kmem_cache_free(whitelist_cache, buf);
}
/* Callable tests. */
@@ -256,14 +262,14 @@ void lkdtm_USERCOPY_HEAP_SIZE_FROM(void)
do_usercopy_heap_size(false);
}
-void lkdtm_USERCOPY_HEAP_FLAG_TO(void)
+void lkdtm_USERCOPY_HEAP_WHITELIST_TO(void)
{
- do_usercopy_heap_flag(true);
+ do_usercopy_heap_whitelist(true);
}
-void lkdtm_USERCOPY_HEAP_FLAG_FROM(void)
+void lkdtm_USERCOPY_HEAP_WHITELIST_FROM(void)
{
- do_usercopy_heap_flag(false);
+ do_usercopy_heap_whitelist(false);
}
void lkdtm_USERCOPY_STACK_FRAME_TO(void)
@@ -314,11 +320,15 @@ free_user:
void __init lkdtm_usercopy_init(void)
{
/* Prepare cache that lacks SLAB_USERCOPY flag. */
- bad_cache = kmem_cache_create("lkdtm-no-usercopy", cache_size, 0,
- 0, NULL);
+ whitelist_cache =
+ kmem_cache_create_usercopy("lkdtm-usercopy", cache_size,
+ 0, 0,
+ cache_size / 4,
+ cache_size / 16,
+ NULL);
}
void __exit lkdtm_usercopy_exit(void)
{
- kmem_cache_destroy(bad_cache);
+ kmem_cache_destroy(whitelist_cache);
}
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index b0541d786850..b10cf469e55d 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -79,14 +79,15 @@ int scsi_init_sense_cache(struct Scsi_Host *shost)
if (shost->unchecked_isa_dma) {
scsi_sense_isadma_cache =
kmem_cache_create("scsi_sense_cache(DMA)",
- SCSI_SENSE_BUFFERSIZE, 0,
- SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA, NULL);
+ SCSI_SENSE_BUFFERSIZE, 0,
+ SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA, NULL);
if (!scsi_sense_isadma_cache)
ret = -ENOMEM;
} else {
scsi_sense_cache =
- kmem_cache_create("scsi_sense_cache",
- SCSI_SENSE_BUFFERSIZE, 0, SLAB_HWCACHE_ALIGN, NULL);
+ kmem_cache_create_usercopy("scsi_sense_cache",
+ SCSI_SENSE_BUFFERSIZE, 0, SLAB_HWCACHE_ALIGN,
+ 0, SCSI_SENSE_BUFFERSIZE, NULL);
if (!scsi_sense_cache)
ret = -ENOMEM;
}
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index ee236231cafa..af2832aaeec5 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -444,11 +444,15 @@ unacquire_none:
static int __init
befs_init_inodecache(void)
{
- befs_inode_cachep = kmem_cache_create("befs_inode_cache",
- sizeof (struct befs_inode_info),
- 0, (SLAB_RECLAIM_ACCOUNT|
- SLAB_MEM_SPREAD|SLAB_ACCOUNT),
- init_once);
+ befs_inode_cachep = kmem_cache_create_usercopy("befs_inode_cache",
+ sizeof(struct befs_inode_info), 0,
+ (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|
+ SLAB_ACCOUNT),
+ offsetof(struct befs_inode_info,
+ i_data.symlink),
+ sizeof_field(struct befs_inode_info,
+ i_data.symlink),
+ init_once);
if (befs_inode_cachep == NULL)
return -ENOMEM;
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 31b7565b1617..29f4b0290fbd 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -1231,9 +1231,11 @@ cifs_init_request_bufs(void)
cifs_dbg(VFS, "CIFSMaxBufSize %d 0x%x\n",
CIFSMaxBufSize, CIFSMaxBufSize);
*/
- cifs_req_cachep = kmem_cache_create("cifs_request",
+ cifs_req_cachep = kmem_cache_create_usercopy("cifs_request",
CIFSMaxBufSize + max_hdr_size, 0,
- SLAB_HWCACHE_ALIGN, NULL);
+ SLAB_HWCACHE_ALIGN, 0,
+ CIFSMaxBufSize + max_hdr_size,
+ NULL);
if (cifs_req_cachep == NULL)
return -ENOMEM;
@@ -1259,9 +1261,9 @@ cifs_init_request_bufs(void)
more SMBs to use small buffer alloc and is still much more
efficient to alloc 1 per page off the slab compared to 17K (5page)
alloc of large cifs buffers even when page debugging is on */
- cifs_sm_req_cachep = kmem_cache_create("cifs_small_rq",
+ cifs_sm_req_cachep = kmem_cache_create_usercopy("cifs_small_rq",
MAX_CIFS_SMALL_BUFFER_SIZE, 0, SLAB_HWCACHE_ALIGN,
- NULL);
+ 0, MAX_CIFS_SMALL_BUFFER_SIZE, NULL);
if (cifs_sm_req_cachep == NULL) {
mempool_destroy(cifs_req_poolp);
kmem_cache_destroy(cifs_req_cachep);
diff --git a/fs/dcache.c b/fs/dcache.c
index 379dce86f001..d90bbc641a70 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -3597,8 +3597,9 @@ static void __init dcache_init(void)
* but it is probably not worth it because of the cache nature
* of the dcache.
*/
- dentry_cache = KMEM_CACHE(dentry,
- SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD|SLAB_ACCOUNT);
+ dentry_cache = KMEM_CACHE_USERCOPY(dentry,
+ SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD|SLAB_ACCOUNT,
+ d_iname);
/* Hash may have been set up in dcache_init_early */
if (!hashdist)
@@ -3635,8 +3636,8 @@ void __init vfs_caches_init_early(void)
void __init vfs_caches_init(void)
{
- names_cachep = kmem_cache_create("names_cache", PATH_MAX, 0,
- SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+ names_cachep = kmem_cache_create_usercopy("names_cache", PATH_MAX, 0,
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC, 0, PATH_MAX, NULL);
dcache_init();
inode_init();
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 819624cfc8da..e5c532875bb7 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -192,10 +192,13 @@ static void exofs_init_once(void *foo)
*/
static int init_inodecache(void)
{
- exofs_inode_cachep = kmem_cache_create("exofs_inode_cache",
+ exofs_inode_cachep = kmem_cache_create_usercopy("exofs_inode_cache",
sizeof(struct exofs_i_info), 0,
SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD |
- SLAB_ACCOUNT, exofs_init_once);
+ SLAB_ACCOUNT,
+ offsetof(struct exofs_i_info, i_data),
+ sizeof_field(struct exofs_i_info, i_data),
+ exofs_init_once);
if (exofs_inode_cachep == NULL)
return -ENOMEM;
return 0;
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 7646818ab266..50b8946c3d1a 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -220,11 +220,13 @@ static void init_once(void *foo)
static int __init init_inodecache(void)
{
- ext2_inode_cachep = kmem_cache_create("ext2_inode_cache",
- sizeof(struct ext2_inode_info),
- 0, (SLAB_RECLAIM_ACCOUNT|
- SLAB_MEM_SPREAD|SLAB_ACCOUNT),
- init_once);
+ ext2_inode_cachep = kmem_cache_create_usercopy("ext2_inode_cache",
+ sizeof(struct ext2_inode_info), 0,
+ (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|
+ SLAB_ACCOUNT),
+ offsetof(struct ext2_inode_info, i_data),
+ sizeof_field(struct ext2_inode_info, i_data),
+ init_once);
if (ext2_inode_cachep == NULL)
return -ENOMEM;
return 0;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 7c46693a14d7..57a8fa451d3e 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1036,11 +1036,13 @@ static void init_once(void *foo)
static int __init init_inodecache(void)
{
- ext4_inode_cachep = kmem_cache_create("ext4_inode_cache",
- sizeof(struct ext4_inode_info),
- 0, (SLAB_RECLAIM_ACCOUNT|
- SLAB_MEM_SPREAD|SLAB_ACCOUNT),
- init_once);
+ ext4_inode_cachep = kmem_cache_create_usercopy("ext4_inode_cache",
+ sizeof(struct ext4_inode_info), 0,
+ (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|
+ SLAB_ACCOUNT),
+ offsetof(struct ext4_inode_info, i_data),
+ sizeof_field(struct ext4_inode_info, i_data),
+ init_once);
if (ext4_inode_cachep == NULL)
return -ENOMEM;
return 0;
diff --git a/fs/fhandle.c b/fs/fhandle.c
index 0ace128f5d23..0ee727485615 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -69,8 +69,7 @@ static long do_sys_name_to_handle(struct path *path,
} else
retval = 0;
/* copy the mount id */
- if (copy_to_user(mnt_id, &real_mount(path->mnt)->mnt_id,
- sizeof(*mnt_id)) ||
+ if (put_user(real_mount(path->mnt)->mnt_id, mnt_id) ||
copy_to_user(ufh, handle,
sizeof(struct file_handle) + handle_bytes))
retval = -EFAULT;
diff --git a/fs/freevxfs/vxfs_super.c b/fs/freevxfs/vxfs_super.c
index f989efa051a0..48b24bb50d02 100644
--- a/fs/freevxfs/vxfs_super.c
+++ b/fs/freevxfs/vxfs_super.c
@@ -332,9 +332,13 @@ vxfs_init(void)
{
int rv;
- vxfs_inode_cachep = kmem_cache_create("vxfs_inode",
+ vxfs_inode_cachep = kmem_cache_create_usercopy("vxfs_inode",
sizeof(struct vxfs_inode_info), 0,
- SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
+ SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD,
+ offsetof(struct vxfs_inode_info, vii_immed.vi_immed),
+ sizeof_field(struct vxfs_inode_info,
+ vii_immed.vi_immed),
+ NULL);
if (!vxfs_inode_cachep)
return -ENOMEM;
rv = register_filesystem(&vxfs_fs_type);
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 90373aebfdca..1b9264fd54b6 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -965,9 +965,11 @@ static int __init init_jfs_fs(void)
int rc;
jfs_inode_cachep =
- kmem_cache_create("jfs_ip", sizeof(struct jfs_inode_info), 0,
- SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT,
- init_once);
+ kmem_cache_create_usercopy("jfs_ip", sizeof(struct jfs_inode_info),
+ 0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT,
+ offsetof(struct jfs_inode_info, i_inline),
+ sizeof_field(struct jfs_inode_info, i_inline),
+ init_once);
if (jfs_inode_cachep == NULL)
return -ENOMEM;
diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c
index 36f1390b5ed7..62d49e53061c 100644
--- a/fs/orangefs/super.c
+++ b/fs/orangefs/super.c
@@ -610,11 +610,16 @@ void orangefs_kill_sb(struct super_block *sb)
int orangefs_inode_cache_initialize(void)
{
- orangefs_inode_cache = kmem_cache_create("orangefs_inode_cache",
- sizeof(struct orangefs_inode_s),
- 0,
- ORANGEFS_CACHE_CREATE_FLAGS,
- orangefs_inode_cache_ctor);
+ orangefs_inode_cache = kmem_cache_create_usercopy(
+ "orangefs_inode_cache",
+ sizeof(struct orangefs_inode_s),
+ 0,
+ ORANGEFS_CACHE_CREATE_FLAGS,
+ offsetof(struct orangefs_inode_s,
+ link_target),
+ sizeof_field(struct orangefs_inode_s,
+ link_target),
+ orangefs_inode_cache_ctor);
if (!orangefs_inode_cache) {
gossip_err("Cannot create orangefs_inode_cache\n");
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 4d497e9c6883..652a77702aec 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -1466,11 +1466,14 @@ static void init_once(void *foo)
static int __init init_inodecache(void)
{
- ufs_inode_cachep = kmem_cache_create("ufs_inode_cache",
- sizeof(struct ufs_inode_info),
- 0, (SLAB_RECLAIM_ACCOUNT|
- SLAB_MEM_SPREAD|SLAB_ACCOUNT),
- init_once);
+ ufs_inode_cachep = kmem_cache_create_usercopy("ufs_inode_cache",
+ sizeof(struct ufs_inode_info), 0,
+ (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|
+ SLAB_ACCOUNT),
+ offsetof(struct ufs_inode_info, i_u1.i_symlink),
+ sizeof_field(struct ufs_inode_info,
+ i_u1.i_symlink),
+ init_once);
if (ufs_inode_cachep == NULL)
return -ENOMEM;
return 0;
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 05b8650f06f5..5be31eb7b266 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -104,6 +104,20 @@ extern int arch_task_struct_size __read_mostly;
# define arch_task_struct_size (sizeof(struct task_struct))
#endif
+#ifndef CONFIG_HAVE_ARCH_THREAD_STRUCT_WHITELIST
+/*
+ * If an architecture has not declared a thread_struct whitelist we
+ * must assume something there may need to be copied to userspace.
+ */
+static inline void arch_thread_struct_whitelist(unsigned long *offset,
+ unsigned long *size)
+{
+ *offset = 0;
+ /* Handle dynamically sized thread_struct. */
+ *size = arch_task_struct_size - offsetof(struct task_struct, thread);
+}
+#endif
+
#ifdef CONFIG_VMAP_STACK
static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
{
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 50697a1d6621..a614e2fc4a89 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -135,9 +135,15 @@ struct mem_cgroup;
void __init kmem_cache_init(void);
bool slab_is_available(void);
-struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
- slab_flags_t,
- void (*)(void *));
+extern bool usercopy_fallback;
+
+struct kmem_cache *kmem_cache_create(const char *name, size_t size,
+ size_t align, slab_flags_t flags,
+ void (*ctor)(void *));
+struct kmem_cache *kmem_cache_create_usercopy(const char *name,
+ size_t size, size_t align, slab_flags_t flags,
+ size_t useroffset, size_t usersize,
+ void (*ctor)(void *));
void kmem_cache_destroy(struct kmem_cache *);
int kmem_cache_shrink(struct kmem_cache *);
@@ -153,9 +159,20 @@ void memcg_destroy_kmem_caches(struct mem_cgroup *);
* f.e. add ____cacheline_aligned_in_smp to the struct declaration
* then the objects will be properly aligned in SMP configurations.
*/
-#define KMEM_CACHE(__struct, __flags) kmem_cache_create(#__struct,\
- sizeof(struct __struct), __alignof__(struct __struct),\
- (__flags), NULL)
+#define KMEM_CACHE(__struct, __flags) \
+ kmem_cache_create(#__struct, sizeof(struct __struct), \
+ __alignof__(struct __struct), (__flags), NULL)
+
+/*
+ * To whitelist a single field for copying to/from usercopy, use this
+ * macro instead for KMEM_CACHE() above.
+ */
+#define KMEM_CACHE_USERCOPY(__struct, __flags, __field) \
+ kmem_cache_create_usercopy(#__struct, \
+ sizeof(struct __struct), \
+ __alignof__(struct __struct), (__flags), \
+ offsetof(struct __struct, __field), \
+ sizeof_field(struct __struct, __field), NULL)
/*
* Common kmalloc functions provided by all allocators
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 072e46e9e1d5..7385547c04b1 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -85,6 +85,9 @@ struct kmem_cache {
unsigned int *random_seq;
#endif
+ size_t useroffset; /* Usercopy region offset */
+ size_t usersize; /* Usercopy region size */
+
struct kmem_cache_node *node[MAX_NUMNODES];
};
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 0adae162dc8f..8ad99c47b19c 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -135,6 +135,9 @@ struct kmem_cache {
struct kasan_cache kasan_info;
#endif
+ size_t useroffset; /* Usercopy region offset */
+ size_t usersize; /* Usercopy region size */
+
struct kmem_cache_node *node[MAX_NUMNODES];
};
diff --git a/include/linux/stddef.h b/include/linux/stddef.h
index 2181719fd907..70c4b4bb4d1f 100644
--- a/include/linux/stddef.h
+++ b/include/linux/stddef.h
@@ -19,6 +19,8 @@ enum {
#define offsetof(TYPE, MEMBER) ((size_t)&((TYPE *)0)->MEMBER)
#endif
+#define sizeof_field(structure, field) sizeof((((structure *)0)->field))
+
/**
* offsetofend(TYPE, MEMBER)
*
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 2f8f93da5dc2..7a59a6c948c1 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -202,12 +202,17 @@ struct sctp_sock {
/* Flags controlling Heartbeat, SACK delay, and Path MTU Discovery. */
__u32 param_flags;
- struct sctp_initmsg initmsg;
struct sctp_rtoinfo rtoinfo;
struct sctp_paddrparams paddrparam;
- struct sctp_event_subscribe subscribe;
struct sctp_assocparams assocparams;
+ /*
+ * These two structures must be grouped together for the usercopy
+ * whitelist region.
+ */
+ struct sctp_event_subscribe subscribe;
+ struct sctp_initmsg initmsg;
+
int user_frag;
__u32 autoclose;
diff --git a/include/net/sock.h b/include/net/sock.h
index f90685441143..c28b282790b5 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1108,6 +1108,8 @@ struct proto {
struct kmem_cache *slab;
unsigned int obj_size;
slab_flags_t slab_flags;
+ size_t useroffset; /* Usercopy region offset */
+ size_t usersize; /* Usercopy region size */
struct percpu_counter *orphan_count;
diff --git a/kernel/fork.c b/kernel/fork.c
index 432eadf6b58c..5977e691c754 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -282,8 +282,9 @@ static void free_thread_stack(struct task_struct *tsk)
void thread_stack_cache_init(void)
{
- thread_stack_cache = kmem_cache_create("thread_stack", THREAD_SIZE,
- THREAD_SIZE, 0, NULL);
+ thread_stack_cache = kmem_cache_create_usercopy("thread_stack",
+ THREAD_SIZE, THREAD_SIZE, 0, 0,
+ THREAD_SIZE, NULL);
BUG_ON(thread_stack_cache == NULL);
}
# endif
@@ -457,6 +458,21 @@ static void set_max_threads(unsigned int max_threads_suggested)
int arch_task_struct_size __read_mostly;
#endif
+static void task_struct_whitelist(unsigned long *offset, unsigned long *size)
+{
+ /* Fetch thread_struct whitelist for the architecture. */
+ arch_thread_struct_whitelist(offset, size);
+
+ /*
+ * Handle zero-sized whitelist or empty thread_struct, otherwise
+ * adjust offset to position of thread_struct in task_struct.
+ */
+ if (unlikely(*size == 0))
+ *offset = 0;
+ else
+ *offset += offsetof(struct task_struct, thread);
+}
+
void __init fork_init(void)
{
int i;
@@ -465,11 +481,14 @@ void __init fork_init(void)
#define ARCH_MIN_TASKALIGN 0
#endif
int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN);
+ unsigned long useroffset, usersize;
/* create a slab on which task_structs can be allocated */
- task_struct_cachep = kmem_cache_create("task_struct",
+ task_struct_whitelist(&useroffset, &usersize);
+ task_struct_cachep = kmem_cache_create_usercopy("task_struct",
arch_task_struct_size, align,
- SLAB_PANIC|SLAB_ACCOUNT, NULL);
+ SLAB_PANIC|SLAB_ACCOUNT,
+ useroffset, usersize, NULL);
#endif
/* do the arch specific task caches init */
@@ -2225,9 +2244,11 @@ void __init proc_caches_init(void)
* maximum number of CPU's we can ever have. The cpumask_allocation
* is at the end of the structure, exactly for that reason.
*/
- mm_cachep = kmem_cache_create("mm_struct",
+ mm_cachep = kmem_cache_create_usercopy("mm_struct",
sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
+ offsetof(struct mm_struct, saved_auxv),
+ sizeof_field(struct mm_struct, saved_auxv),
NULL);
vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT);
mmap_init();
diff --git a/mm/slab.c b/mm/slab.c
index 183e996dde5f..9ed5c54e9d3c 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1281,7 +1281,7 @@ void __init kmem_cache_init(void)
create_boot_cache(kmem_cache, "kmem_cache",
offsetof(struct kmem_cache, node) +
nr_node_ids * sizeof(struct kmem_cache_node *),
- SLAB_HWCACHE_ALIGN);
+ SLAB_HWCACHE_ALIGN, 0, 0);
list_add(&kmem_cache->list, &slab_caches);
slab_state = PARTIAL;
@@ -1291,7 +1291,8 @@ void __init kmem_cache_init(void)
*/
kmalloc_caches[INDEX_NODE] = create_kmalloc_cache(
kmalloc_info[INDEX_NODE].name,
- kmalloc_size(INDEX_NODE), ARCH_KMALLOC_FLAGS);
+ kmalloc_size(INDEX_NODE), ARCH_KMALLOC_FLAGS,
+ 0, kmalloc_size(INDEX_NODE));
slab_state = PARTIAL_NODE;
setup_kmalloc_cache_index_table();
@@ -4392,7 +4393,9 @@ module_init(slab_proc_init);
#ifdef CONFIG_HARDENED_USERCOPY
/*
- * Rejects objects that are incorrectly sized.
+ * Rejects incorrectly sized objects and objects that are to be copied
+ * to/from userspace but do not fall entirely within the containing slab
+ * cache's usercopy region.
*
* Returns NULL if check passes, otherwise const char * to name of cache
* to indicate an error.
@@ -4412,11 +4415,28 @@ const char *__check_heap_object(const void *ptr, unsigned long n,
/* Find offset within object. */
offset = ptr - index_to_obj(cachep, page, objnr) - obj_offset(cachep);
- /* Allow address range falling entirely within object size. */
- if (offset <= cachep->object_size && n <= cachep->object_size - offset)
- return NULL;
+ /* Make sure object falls entirely within cache's usercopy region. */
+ if (offset < cachep->useroffset ||
+ offset - cachep->useroffset > cachep->usersize ||
+ n > cachep->useroffset - offset + cachep->usersize) {
+ /*
+ * If the copy is still within the allocated object, produce
+ * a warning instead of rejecting the copy. This is intended
+ * to be a temporary method to find any missing usercopy
+ * whitelists.
+ */
+ if (usercopy_fallback &&
+ offset <= cachep->object_size &&
+ n <= cachep->object_size - offset) {
+ WARN_ONCE(1, "unexpected usercopy with bad or missing whitelist from %s offset %lu size %lu",
+ cachep->name, offset, n);
+ return NULL;
+ }
+
+ return cachep->name;
+ }
- return cachep->name;
+ return NULL;
}
#endif /* CONFIG_HARDENED_USERCOPY */
diff --git a/mm/slab.h b/mm/slab.h
index ad657ffa44e5..1f013f7795c6 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -22,6 +22,8 @@ struct kmem_cache {
unsigned int size; /* The aligned/padded/added on size */
unsigned int align; /* Alignment as calculated */
slab_flags_t flags; /* Active flags on the slab */
+ size_t useroffset; /* Usercopy region offset */
+ size_t usersize; /* Usercopy region size */
const char *name; /* Slab name for sysfs */
int refcount; /* Use counter */
void (*ctor)(void *); /* Called on object slot creation */
@@ -95,9 +97,11 @@ struct kmem_cache *kmalloc_slab(size_t, gfp_t);
int __kmem_cache_create(struct kmem_cache *, slab_flags_t flags);
extern struct kmem_cache *create_kmalloc_cache(const char *name, size_t size,
- slab_flags_t flags);
+ slab_flags_t flags, size_t useroffset,
+ size_t usersize);
extern void create_boot_cache(struct kmem_cache *, const char *name,
- size_t size, slab_flags_t flags);
+ size_t size, slab_flags_t flags, size_t useroffset,
+ size_t usersize);
int slab_unmergeable(struct kmem_cache *s);
struct kmem_cache *find_mergeable(size_t size, size_t align,
diff --git a/mm/slab_common.c b/mm/slab_common.c
index c8cb36774ba1..d00cd3f0f8ac 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -31,6 +31,14 @@ LIST_HEAD(slab_caches);
DEFINE_MUTEX(slab_mutex);
struct kmem_cache *kmem_cache;
+#ifdef CONFIG_HARDENED_USERCOPY
+bool usercopy_fallback __ro_after_init =
+ IS_ENABLED(CONFIG_HARDENED_USERCOPY_FALLBACK);
+module_param(usercopy_fallback, bool, 0400);
+MODULE_PARM_DESC(usercopy_fallback,
+ "WARN instead of reject usercopy whitelist violations");
+#endif
+
static LIST_HEAD(slab_caches_to_rcu_destroy);
static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work);
static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
@@ -281,6 +289,9 @@ int slab_unmergeable(struct kmem_cache *s)
if (s->ctor)
return 1;
+ if (s->usersize)
+ return 1;
+
/*
* We may have set a slab to be unmergeable during bootstrap.
*/
@@ -366,12 +377,16 @@ unsigned long calculate_alignment(slab_flags_t flags,
static struct kmem_cache *create_cache(const char *name,
size_t object_size, size_t size, size_t align,
- slab_flags_t flags, void (*ctor)(void *),
+ slab_flags_t flags, size_t useroffset,
+ size_t usersize, void (*ctor)(void *),
struct mem_cgroup *memcg, struct kmem_cache *root_cache)
{
struct kmem_cache *s;
int err;
+ if (WARN_ON(useroffset + usersize > object_size))
+ useroffset = usersize = 0;
+
err = -ENOMEM;
s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL);
if (!s)
@@ -382,6 +397,8 @@ static struct kmem_cache *create_cache(const char *name,
s->size = size;
s->align = align;
s->ctor = ctor;
+ s->useroffset = useroffset;
+ s->usersize = usersize;
err = init_memcg_params(s, memcg, root_cache);
if (err)
@@ -406,11 +423,13 @@ out_free_cache:
}
/*
- * kmem_cache_create - Create a cache.
+ * kmem_cache_create_usercopy - Create a cache.
* @name: A string which is used in /proc/slabinfo to identify this cache.
* @size: The size of objects to be created in this cache.
* @align: The required alignment for the objects.
* @flags: SLAB flags
+ * @useroffset: Usercopy region offset
+ * @usersize: Usercopy region size
* @ctor: A constructor for the objects.
*
* Returns a ptr to the cache on success, NULL on failure.
@@ -430,8 +449,9 @@ out_free_cache:
* as davem.
*/
struct kmem_cache *
-kmem_cache_create(const char *name, size_t size, size_t align,
- slab_flags_t flags, void (*ctor)(void *))
+kmem_cache_create_usercopy(const char *name, size_t size, size_t align,
+ slab_flags_t flags, size_t useroffset, size_t usersize,
+ void (*ctor)(void *))
{
struct kmem_cache *s = NULL;
const char *cache_name;
@@ -462,7 +482,13 @@ kmem_cache_create(const char *name, size_t size, size_t align,
*/
flags &= CACHE_CREATE_MASK;
- s = __kmem_cache_alias(name, size, align, flags, ctor);
+ /* Fail closed on bad usersize of useroffset values. */
+ if (WARN_ON(!usersize && useroffset) ||
+ WARN_ON(size < usersize || size - usersize < useroffset))
+ usersize = useroffset = 0;
+
+ if (!usersize)
+ s = __kmem_cache_alias(name, size, align, flags, ctor);
if (s)
goto out_unlock;
@@ -474,7 +500,7 @@ kmem_cache_create(const char *name, size_t size, size_t align,
s = create_cache(cache_name, size, size,
calculate_alignment(flags, align, size),
- flags, ctor, NULL, NULL);
+ flags, useroffset, usersize, ctor, NULL, NULL);
if (IS_ERR(s)) {
err = PTR_ERR(s);
kfree_const(cache_name);
@@ -500,6 +526,15 @@ out_unlock:
}
return s;
}
+EXPORT_SYMBOL(kmem_cache_create_usercopy);
+
+struct kmem_cache *
+kmem_cache_create(const char *name, size_t size, size_t align,
+ slab_flags_t flags, void (*ctor)(void *))
+{
+ return kmem_cache_create_usercopy(name, size, align, flags, 0, 0,
+ ctor);
+}
EXPORT_SYMBOL(kmem_cache_create);
static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work)
@@ -612,6 +647,7 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
s = create_cache(cache_name, root_cache->object_size,
root_cache->size, root_cache->align,
root_cache->flags & CACHE_CREATE_MASK,
+ root_cache->useroffset, root_cache->usersize,
root_cache->ctor, memcg, root_cache);
/*
* If we could not create a memcg cache, do not complain, because
@@ -879,13 +915,15 @@ bool slab_is_available(void)
#ifndef CONFIG_SLOB
/* Create a cache during boot when no slab services are available yet */
void __init create_boot_cache(struct kmem_cache *s, const char *name, size_t size,
- slab_flags_t flags)
+ slab_flags_t flags, size_t useroffset, size_t usersize)
{
int err;
s->name = name;
s->size = s->object_size = size;
s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size);
+ s->useroffset = useroffset;
+ s->usersize = usersize;
slab_init_memcg_params(s);
@@ -899,14 +937,15 @@ void __init create_boot_cache(struct kmem_cache *s, const char *name, size_t siz
}
struct kmem_cache *__init create_kmalloc_cache(const char *name, size_t size,
- slab_flags_t flags)
+ slab_flags_t flags, size_t useroffset,
+ size_t usersize)
{
struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);
if (!s)
panic("Out of memory when creating slab %s\n", name);
- create_boot_cache(s, name, size, flags);
+ create_boot_cache(s, name, size, flags, useroffset, usersize);
list_add(&s->list, &slab_caches);
memcg_link_cache(s);
s->refcount = 1;
@@ -1060,7 +1099,8 @@ void __init setup_kmalloc_cache_index_table(void)
static void __init new_kmalloc_cache(int idx, slab_flags_t flags)
{
kmalloc_caches[idx] = create_kmalloc_cache(kmalloc_info[idx].name,
- kmalloc_info[idx].size, flags);
+ kmalloc_info[idx].size, flags, 0,
+ kmalloc_info[idx].size);
}
/*
@@ -1101,7 +1141,7 @@ void __init create_kmalloc_caches(slab_flags_t flags)
BUG_ON(!n);
kmalloc_dma_caches[i] = create_kmalloc_cache(n,
- size, SLAB_CACHE_DMA | flags);
+ size, SLAB_CACHE_DMA | flags, 0, 0);
}
}
#endif
diff --git a/mm/slub.c b/mm/slub.c
index cfd56e5a35fb..3530b3c60ad6 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3813,7 +3813,9 @@ EXPORT_SYMBOL(__kmalloc_node);
#ifdef CONFIG_HARDENED_USERCOPY
/*
- * Rejects objects that are incorrectly sized.
+ * Rejects incorrectly sized objects and objects that are to be copied
+ * to/from userspace but do not fall entirely within the containing slab
+ * cache's usercopy region.
*
* Returns NULL if check passes, otherwise const char * to name of cache
* to indicate an error.
@@ -3823,11 +3825,9 @@ const char *__check_heap_object(const void *ptr, unsigned long n,
{
struct kmem_cache *s;
unsigned long offset;
- size_t object_size;
/* Find object and usable object size. */
s = page->slab_cache;
- object_size = slab_ksize(s);
/* Reject impossible pointers. */
if (ptr < page_address(page))
@@ -3843,11 +3843,30 @@ const char *__check_heap_object(const void *ptr, unsigned long n,
offset -= s->red_left_pad;
}
- /* Allow address range falling entirely within object size. */
- if (offset <= object_size && n <= object_size - offset)
- return NULL;
+ /* Make sure object falls entirely within cache's usercopy region. */
+ if (offset < s->useroffset ||
+ offset - s->useroffset > s->usersize ||
+ n > s->useroffset - offset + s->usersize) {
+ size_t object_size;
+
+ /*
+ * If the copy is still within the allocated object, produce
+ * a warning instead of rejecting the copy. This is intended
+ * to be a temporary method to find any missing usercopy
+ * whitelists.
+ */
+ object_size = slab_ksize(s);
+ if (usercopy_fallback &&
+ (offset <= object_size && n <= object_size - offset)) {
+ WARN_ONCE(1, "unexpected usercopy with bad or missing whitelist from %s offset %lu size %lu",
+ s->name, offset, n);
+ return NULL;
+ }
+
+ return s->name;
+ }
- return s->name;
+ return NULL;
}
#endif /* CONFIG_HARDENED_USERCOPY */
@@ -4181,7 +4200,7 @@ void __init kmem_cache_init(void)
kmem_cache = &boot_kmem_cache;
create_boot_cache(kmem_cache_node, "kmem_cache_node",
- sizeof(struct kmem_cache_node), SLAB_HWCACHE_ALIGN);
+ sizeof(struct kmem_cache_node), SLAB_HWCACHE_ALIGN, 0, 0);
register_hotmemory_notifier(&slab_memory_callback_nb);
@@ -4191,7 +4210,7 @@ void __init kmem_cache_init(void)
create_boot_cache(kmem_cache, "kmem_cache",
offsetof(struct kmem_cache, node) +
nr_node_ids * sizeof(struct kmem_cache_node *),
- SLAB_HWCACHE_ALIGN);
+ SLAB_HWCACHE_ALIGN, 0, 0);
kmem_cache = bootstrap(&boot_kmem_cache);
@@ -5061,6 +5080,12 @@ static ssize_t cache_dma_show(struct kmem_cache *s, char *buf)
SLAB_ATTR_RO(cache_dma);
#endif
+static ssize_t usersize_show(struct kmem_cache *s, char *buf)
+{
+ return sprintf(buf, "%zu\n", s->usersize);
+}
+SLAB_ATTR_RO(usersize);
+
static ssize_t destroy_by_rcu_show(struct kmem_cache *s, char *buf)
{
return sprintf(buf, "%d\n", !!(s->flags & SLAB_TYPESAFE_BY_RCU));
@@ -5435,6 +5460,7 @@ static struct attribute *slab_attrs[] = {
#ifdef CONFIG_FAILSLAB
&failslab_attr.attr,
#endif
+ &usersize_attr.attr,
NULL
};
diff --git a/mm/usercopy.c b/mm/usercopy.c
index a9852b24715d..cbffde670c49 100644
--- a/mm/usercopy.c
+++ b/mm/usercopy.c
@@ -58,6 +58,18 @@ static noinline int check_stack_object(const void *obj, unsigned long len)
return GOOD_STACK;
}
+/*
+ * If this function is reached, then CONFIG_HARDENED_USERCOPY has found an
+ * unexpected state during a copy_from_user() or copy_to_user() call.
+ * There are several checks being performed on the buffer by the
+ * __check_object_size() function. Normal stack buffer usage should never
+ * trip the checks, and kernel text addressing will always trip the check.
+ * For cache objects, it is checking that only the whitelisted range of
+ * bytes for a given cache is being accessed (via the cache's usersize and
+ * useroffset fields). To adjust a cache whitelist, use the usercopy-aware
+ * kmem_cache_create_usercopy() function to create the cache (and
+ * carefully audit the whitelist range).
+ */
static void report_usercopy(const void *ptr, unsigned long len,
bool to_user, const char *type)
{
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 64048cec41e0..b109445a1df9 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -1032,6 +1032,8 @@ static int caif_create(struct net *net, struct socket *sock, int protocol,
static struct proto prot = {.name = "PF_CAIF",
.owner = THIS_MODULE,
.obj_size = sizeof(struct caifsock),
+ .useroffset = offsetof(struct caifsock, conn_req.param),
+ .usersize = sizeof_field(struct caifsock, conn_req.param)
};
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_NET_ADMIN))
diff --git a/net/core/sock.c b/net/core/sock.c
index 1211159718ad..8e097dbcfe34 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3151,8 +3151,10 @@ static int req_prot_init(const struct proto *prot)
int proto_register(struct proto *prot, int alloc_slab)
{
if (alloc_slab) {
- prot->slab = kmem_cache_create(prot->name, prot->obj_size, 0,
+ prot->slab = kmem_cache_create_usercopy(prot->name,
+ prot->obj_size, 0,
SLAB_HWCACHE_ALIGN | prot->slab_flags,
+ prot->useroffset, prot->usersize,
NULL);
if (prot->slab == NULL) {
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 33b70bfd1122..1b6fa4195ac9 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -970,6 +970,8 @@ struct proto raw_prot = {
.hash = raw_hash_sk,
.unhash = raw_unhash_sk,
.obj_size = sizeof(struct raw_sock),
+ .useroffset = offsetof(struct raw_sock, filter),
+ .usersize = sizeof_field(struct raw_sock, filter),
.h.raw_hash = &raw_v4_hashinfo,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_raw_setsockopt,
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 761a473a07c5..08a85fabdfd1 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1272,6 +1272,8 @@ struct proto rawv6_prot = {
.hash = raw_hash_sk,
.unhash = raw_unhash_sk,
.obj_size = sizeof(struct raw6_sock),
+ .useroffset = offsetof(struct raw6_sock, filter),
+ .usersize = sizeof_field(struct raw6_sock, filter),
.h.raw_hash = &raw_v6_hashinfo,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_rawv6_setsockopt,
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9297482e527a..73341cc4b059 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5011,7 +5011,7 @@ static int sctp_getsockopt_autoclose(struct sock *sk, int len, char __user *optv
len = sizeof(int);
if (put_user(len, optlen))
return -EFAULT;
- if (copy_to_user(optval, &sctp_sk(sk)->autoclose, sizeof(int)))
+ if (put_user(sctp_sk(sk)->autoclose, (int __user *)optval))
return -EFAULT;
return 0;
}
@@ -8469,6 +8469,10 @@ struct proto sctp_prot = {
.unhash = sctp_unhash,
.get_port = sctp_get_port,
.obj_size = sizeof(struct sctp_sock),
+ .useroffset = offsetof(struct sctp_sock, subscribe),
+ .usersize = offsetof(struct sctp_sock, initmsg) -
+ offsetof(struct sctp_sock, subscribe) +
+ sizeof_field(struct sctp_sock, initmsg),
.sysctl_mem = sysctl_sctp_mem,
.sysctl_rmem = sysctl_sctp_rmem,
.sysctl_wmem = sysctl_sctp_wmem,
@@ -8508,6 +8512,10 @@ struct proto sctpv6_prot = {
.unhash = sctp_unhash,
.get_port = sctp_get_port,
.obj_size = sizeof(struct sctp6_sock),
+ .useroffset = offsetof(struct sctp6_sock, sctp.subscribe),
+ .usersize = offsetof(struct sctp6_sock, sctp.initmsg) -
+ offsetof(struct sctp6_sock, sctp.subscribe) +
+ sizeof_field(struct sctp6_sock, sctp.initmsg),
.sysctl_mem = sysctl_sctp_mem,
.sysctl_rmem = sysctl_sctp_rmem,
.sysctl_wmem = sysctl_sctp_wmem,
diff --git a/security/Kconfig b/security/Kconfig
index 3eca040e951f..bdaa2059392b 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -162,6 +162,20 @@ config HARDENED_USERCOPY
or are part of the kernel text. This kills entire classes
of heap overflow exploits and similar kernel memory exposures.
+config HARDENED_USERCOPY_FALLBACK
+ bool "Allow usercopy whitelist violations to fallback to object size"
+ depends on HARDENED_USERCOPY
+ default y
+ help
+ This is a temporary option that allows missing usercopy whitelists
+ to be discovered via a WARN() to the kernel log, instead of
+ rejecting the copy, falling back to non-whitelisted hardened
+ usercopy that checks the slab allocation size instead of the
+ whitelist size. This option will be removed once it seems like
+ all missing usercopy whitelists have been identified and fixed.
+ Booting with "slab_common.usercopy_fallback=Y/N" can change
+ this setting.
+
config HARDENED_USERCOPY_PAGESPAN
bool "Refuse to copy allocations that span multiple pages"
depends on HARDENED_USERCOPY
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7b4d46432c85..f3834b7af23a 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4010,8 +4010,12 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
/* A kmem cache lets us meet the alignment requirements of fx_save. */
if (!vcpu_align)
vcpu_align = __alignof__(struct kvm_vcpu);
- kvm_vcpu_cache = kmem_cache_create("kvm_vcpu", vcpu_size, vcpu_align,
- SLAB_ACCOUNT, NULL);
+ kvm_vcpu_cache =
+ kmem_cache_create_usercopy("kvm_vcpu", vcpu_size, vcpu_align,
+ SLAB_ACCOUNT,
+ offsetof(struct kvm_vcpu, arch),
+ sizeof_field(struct kvm_vcpu, arch),
+ NULL);
if (!kvm_vcpu_cache) {
r = -ENOMEM;
goto out_free_3;