From 24b27fc4cdf9e10c5e79e5923b6b7c2c5c95096c Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Thu, 1 Sep 2016 22:18:34 -0700 Subject: bonding: Fix bonding crash Following few steps will crash kernel - (a) Create bonding master > modprobe bonding miimon=50 (b) Create macvlan bridge on eth2 > ip link add link eth2 dev mvl0 address aa:0:0:0:0:01 \ type macvlan (c) Now try adding eth2 into the bond > echo +eth2 > /sys/class/net/bond0/bonding/slaves Bonding does lots of things before checking if the device enslaved is busy or not. In this case when the notifier call-chain sends notifications, the bond_netdev_event() assumes that the rx_handler /rx_handler_data is registered while the bond_enslave() hasn't progressed far enough to register rx_handler for the new slave. This patch adds a rx_handler check that can be performed right at the beginning of the enslave code to avoid getting into this situation. Signed-off-by: Mahesh Bandewar Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3a788bf0affd..e8d79d4ebcfe 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3267,6 +3267,7 @@ static inline void napi_free_frags(struct napi_struct *napi) napi->skb = NULL; } +bool netdev_is_rx_handler_busy(struct net_device *dev); int netdev_rx_handler_register(struct net_device *dev, rx_handler_func_t *rx_handler, void *rx_handler_data); -- cgit v1.2.3 From d7127b5e5fa0551be21b86640f1648b224e36d43 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 26 Aug 2016 08:16:00 +0200 Subject: locking/barriers: Don't use sizeof(void) in lockless_dereference() My previous commit: 112dc0c8069e ("locking/barriers: Suppress sparse warnings in lockless_dereference()") caused sparse to complain that (in radix-tree.h) we use sizeof(void) since that rcu_dereference()s a void *. Really, all we need is to have the expression *p in here somewhere to make sure p is a pointer type, and sizeof(*p) was the thing that came to my mind first to make sure that's done without really doing anything at runtime. Another thing I had considered was using typeof(*p), but obviously we can't just declare a typeof(*p) variable either, since that may end up being void. Declaring a variable as typeof(*p)* gets around that, and still checks that typeof(*p) is valid, so do that. This type construction can't be done for _________p1 because that will actually be used and causes sparse address space warnings, so keep a separate unused variable for it. Reported-by: Fengguang Wu Signed-off-by: Johannes Berg Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Paul E . McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: kbuild-all@01.org Fixes: 112dc0c8069e ("locking/barriers: Suppress sparse warnings in lockless_dereference()") Link: http://lkml.kernel.org/r/1472192160-4049-1-git-send-email-johannes@sipsolutions.net Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 436aa4e42221..668569844d37 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -527,13 +527,14 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * object's lifetime is managed by something other than RCU. That * "something other" might be reference counting or simple immortality. * - * The seemingly unused size_t variable is to validate @p is indeed a pointer - * type by making sure it can be dereferenced. + * The seemingly unused variable ___typecheck_p validates that @p is + * indeed a pointer type by using a pointer to typeof(*p) as the type. + * Taking a pointer to typeof(*p) again is needed in case p is void *. */ #define lockless_dereference(p) \ ({ \ typeof(p) _________p1 = READ_ONCE(p); \ - size_t __maybe_unused __size_of_ptr = sizeof(*(p)); \ + typeof(*(p)) *___typecheck_p __maybe_unused; \ smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ (_________p1); \ }) -- cgit v1.2.3 From d4c4fed08f31f3746000c46cb1b20bed2959547a Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 15 Aug 2016 09:05:45 -0600 Subject: efi: Make for_each_efi_memory_desc_in_map() cope with running on Xen While commit 55f1ea15216 ("efi: Fix for_each_efi_memory_desc_in_map() for empty memmaps") made an attempt to deal with empty memory maps, it didn't address the case where the map field never gets set, as is apparently the case when running under Xen. Reported-by: Tested-by: Cc: Vitaly Kuznetsov Cc: Jiri Slaby Cc: Mark Rutland Cc: # v4.7+ Signed-off-by: Jan Beulich [ Guard the loop with a NULL check instead of pointer underflow ] Signed-off-by: Matt Fleming --- include/linux/efi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 7f5a58225385..23cd3ced8c1a 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -946,7 +946,7 @@ extern int efi_memattr_apply_permissions(struct mm_struct *mm, /* Iterate through an efi_memory_map */ #define for_each_efi_memory_desc_in_map(m, md) \ for ((md) = (m)->map; \ - ((void *)(md) + (m)->desc_size) <= (m)->map_end; \ + (md) && ((void *)(md) + (m)->desc_size) <= (m)->map_end; \ (md) = (void *)(md) + (m)->desc_size) /** -- cgit v1.2.3 From dadb57abc37499f565b23933dbf49b435c3ba8af Mon Sep 17 00:00:00 2001 From: Jeffrey Hugo Date: Mon, 29 Aug 2016 14:38:51 -0600 Subject: efi/libstub: Allocate headspace in efi_get_memory_map() efi_get_memory_map() allocates a buffer to store the memory map that it retrieves. This buffer may need to be reused by the client after ExitBootServices() is called, at which point allocations are not longer permitted. To support this usecase, provide the allocated buffer size back to the client, and allocate some additional headroom to account for any reasonable growth in the map that is likely to happen between the call to efi_get_memory_map() and the client reusing the buffer. Signed-off-by: Jeffrey Hugo Cc: Ard Biesheuvel Cc: Mark Rutland Cc: Leif Lindholm Cc: Ingo Molnar Cc: Signed-off-by: Matt Fleming --- arch/x86/boot/compressed/eboot.c | 20 ++++-- drivers/firmware/efi/libstub/efi-stub-helper.c | 96 ++++++++++++++++++-------- drivers/firmware/efi/libstub/fdt.c | 17 +++-- drivers/firmware/efi/libstub/random.c | 12 +++- include/linux/efi.h | 15 ++-- 5 files changed, 111 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index ff574dad95cc..c5b7c7b4f0d7 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -1008,7 +1008,7 @@ static efi_status_t exit_boot(struct boot_params *boot_params, void *handle, bool is64) { struct efi_info *efi = &boot_params->efi_info; - unsigned long map_sz, key, desc_size; + unsigned long map_sz, key, desc_size, buff_size; efi_memory_desc_t *mem_map; struct setup_data *e820ext; const char *signature; @@ -1019,14 +1019,20 @@ static efi_status_t exit_boot(struct boot_params *boot_params, bool called_exit = false; u8 nr_entries; int i; - - nr_desc = 0; - e820ext = NULL; - e820ext_size = 0; + struct efi_boot_memmap map; + + nr_desc = 0; + e820ext = NULL; + e820ext_size = 0; + map.map = &mem_map; + map.map_size = &map_sz; + map.desc_size = &desc_size; + map.desc_ver = &desc_version; + map.key_ptr = &key; + map.buff_size = &buff_size; get_map: - status = efi_get_memory_map(sys_table, &mem_map, &map_sz, &desc_size, - &desc_version, &key); + status = efi_get_memory_map(sys_table, &map); if (status != EFI_SUCCESS) return status; diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 3bd127f95315..29368ac69221 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -41,6 +41,8 @@ static unsigned long __chunk_size = EFI_READ_CHUNK_SIZE; #define EFI_ALLOC_ALIGN EFI_PAGE_SIZE #endif +#define EFI_MMAP_NR_SLACK_SLOTS 8 + struct file_info { efi_file_handle_t *handle; u64 size; @@ -63,49 +65,62 @@ void efi_printk(efi_system_table_t *sys_table_arg, char *str) } } +static inline bool mmap_has_headroom(unsigned long buff_size, + unsigned long map_size, + unsigned long desc_size) +{ + unsigned long slack = buff_size - map_size; + + return slack / desc_size >= EFI_MMAP_NR_SLACK_SLOTS; +} + efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg, - efi_memory_desc_t **map, - unsigned long *map_size, - unsigned long *desc_size, - u32 *desc_ver, - unsigned long *key_ptr) + struct efi_boot_memmap *map) { efi_memory_desc_t *m = NULL; efi_status_t status; unsigned long key; u32 desc_version; - *map_size = sizeof(*m) * 32; + *map->desc_size = sizeof(*m); + *map->map_size = *map->desc_size * 32; + *map->buff_size = *map->map_size; again: - /* - * Add an additional efi_memory_desc_t because we're doing an - * allocation which may be in a new descriptor region. - */ - *map_size += sizeof(*m); status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - *map_size, (void **)&m); + *map->map_size, (void **)&m); if (status != EFI_SUCCESS) goto fail; - *desc_size = 0; + *map->desc_size = 0; key = 0; - status = efi_call_early(get_memory_map, map_size, m, - &key, desc_size, &desc_version); - if (status == EFI_BUFFER_TOO_SMALL) { + status = efi_call_early(get_memory_map, map->map_size, m, + &key, map->desc_size, &desc_version); + if (status == EFI_BUFFER_TOO_SMALL || + !mmap_has_headroom(*map->buff_size, *map->map_size, + *map->desc_size)) { efi_call_early(free_pool, m); + /* + * Make sure there is some entries of headroom so that the + * buffer can be reused for a new map after allocations are + * no longer permitted. Its unlikely that the map will grow to + * exceed this headroom once we are ready to trigger + * ExitBootServices() + */ + *map->map_size += *map->desc_size * EFI_MMAP_NR_SLACK_SLOTS; + *map->buff_size = *map->map_size; goto again; } if (status != EFI_SUCCESS) efi_call_early(free_pool, m); - if (key_ptr && status == EFI_SUCCESS) - *key_ptr = key; - if (desc_ver && status == EFI_SUCCESS) - *desc_ver = desc_version; + if (map->key_ptr && status == EFI_SUCCESS) + *map->key_ptr = key; + if (map->desc_ver && status == EFI_SUCCESS) + *map->desc_ver = desc_version; fail: - *map = m; + *map->map = m; return status; } @@ -113,13 +128,20 @@ fail: unsigned long get_dram_base(efi_system_table_t *sys_table_arg) { efi_status_t status; - unsigned long map_size; + unsigned long map_size, buff_size; unsigned long membase = EFI_ERROR; struct efi_memory_map map; efi_memory_desc_t *md; + struct efi_boot_memmap boot_map; - status = efi_get_memory_map(sys_table_arg, (efi_memory_desc_t **)&map.map, - &map_size, &map.desc_size, NULL, NULL); + boot_map.map = (efi_memory_desc_t **)&map.map; + boot_map.map_size = &map_size; + boot_map.desc_size = &map.desc_size; + boot_map.desc_ver = NULL; + boot_map.key_ptr = NULL; + boot_map.buff_size = &buff_size; + + status = efi_get_memory_map(sys_table_arg, &boot_map); if (status != EFI_SUCCESS) return membase; @@ -144,15 +166,22 @@ efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg, unsigned long size, unsigned long align, unsigned long *addr, unsigned long max) { - unsigned long map_size, desc_size; + unsigned long map_size, desc_size, buff_size; efi_memory_desc_t *map; efi_status_t status; unsigned long nr_pages; u64 max_addr = 0; int i; + struct efi_boot_memmap boot_map; + + boot_map.map = ↦ + boot_map.map_size = &map_size; + boot_map.desc_size = &desc_size; + boot_map.desc_ver = NULL; + boot_map.key_ptr = NULL; + boot_map.buff_size = &buff_size; - status = efi_get_memory_map(sys_table_arg, &map, &map_size, &desc_size, - NULL, NULL); + status = efi_get_memory_map(sys_table_arg, &boot_map); if (status != EFI_SUCCESS) goto fail; @@ -230,14 +259,21 @@ efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg, unsigned long size, unsigned long align, unsigned long *addr) { - unsigned long map_size, desc_size; + unsigned long map_size, desc_size, buff_size; efi_memory_desc_t *map; efi_status_t status; unsigned long nr_pages; int i; + struct efi_boot_memmap boot_map; + + boot_map.map = ↦ + boot_map.map_size = &map_size; + boot_map.desc_size = &desc_size; + boot_map.desc_ver = NULL; + boot_map.key_ptr = NULL; + boot_map.buff_size = &buff_size; - status = efi_get_memory_map(sys_table_arg, &map, &map_size, &desc_size, - NULL, NULL); + status = efi_get_memory_map(sys_table_arg, &boot_map); if (status != EFI_SUCCESS) goto fail; diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c index e58abfa953cc..bec0fa8d8746 100644 --- a/drivers/firmware/efi/libstub/fdt.c +++ b/drivers/firmware/efi/libstub/fdt.c @@ -175,13 +175,21 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, unsigned long fdt_addr, unsigned long fdt_size) { - unsigned long map_size, desc_size; + unsigned long map_size, desc_size, buff_size; u32 desc_ver; unsigned long mmap_key; efi_memory_desc_t *memory_map, *runtime_map; unsigned long new_fdt_size; efi_status_t status; int runtime_entry_count = 0; + struct efi_boot_memmap map; + + map.map = &runtime_map; + map.map_size = &map_size; + map.desc_size = &desc_size; + map.desc_ver = &desc_ver; + map.key_ptr = &mmap_key; + map.buff_size = &buff_size; /* * Get a copy of the current memory map that we will use to prepare @@ -189,8 +197,7 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, * subsequent allocations adding entries, since they could not affect * the number of EFI_MEMORY_RUNTIME regions. */ - status = efi_get_memory_map(sys_table, &runtime_map, &map_size, - &desc_size, &desc_ver, &mmap_key); + status = efi_get_memory_map(sys_table, &map); if (status != EFI_SUCCESS) { pr_efi_err(sys_table, "Unable to retrieve UEFI memory map.\n"); return status; @@ -199,6 +206,7 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, pr_efi(sys_table, "Exiting boot services and installing virtual address map...\n"); + map.map = &memory_map; /* * Estimate size of new FDT, and allocate memory for it. We * will allocate a bigger buffer if this ends up being too @@ -218,8 +226,7 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, * we can get the memory map key needed for * exit_boot_services(). */ - status = efi_get_memory_map(sys_table, &memory_map, &map_size, - &desc_size, &desc_ver, &mmap_key); + status = efi_get_memory_map(sys_table, &map); if (status != EFI_SUCCESS) goto fail_free_new_fdt; diff --git a/drivers/firmware/efi/libstub/random.c b/drivers/firmware/efi/libstub/random.c index 53f6d3fe6d86..0c9f58c5ba50 100644 --- a/drivers/firmware/efi/libstub/random.c +++ b/drivers/firmware/efi/libstub/random.c @@ -73,12 +73,20 @@ efi_status_t efi_random_alloc(efi_system_table_t *sys_table_arg, unsigned long random_seed) { unsigned long map_size, desc_size, total_slots = 0, target_slot; + unsigned long buff_size; efi_status_t status; efi_memory_desc_t *memory_map; int map_offset; + struct efi_boot_memmap map; - status = efi_get_memory_map(sys_table_arg, &memory_map, &map_size, - &desc_size, NULL, NULL); + map.map = &memory_map; + map.map_size = &map_size; + map.desc_size = &desc_size; + map.desc_ver = NULL; + map.key_ptr = NULL; + map.buff_size = &buff_size; + + status = efi_get_memory_map(sys_table_arg, &map); if (status != EFI_SUCCESS) return status; diff --git a/include/linux/efi.h b/include/linux/efi.h index 23cd3ced8c1a..943fee524176 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -118,6 +118,15 @@ typedef struct { u32 imagesize; } efi_capsule_header_t; +struct efi_boot_memmap { + efi_memory_desc_t **map; + unsigned long *map_size; + unsigned long *desc_size; + u32 *desc_ver; + unsigned long *key_ptr; + unsigned long *buff_size; +}; + /* * EFI capsule flags */ @@ -1371,11 +1380,7 @@ char *efi_convert_cmdline(efi_system_table_t *sys_table_arg, efi_loaded_image_t *image, int *cmd_line_len); efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg, - efi_memory_desc_t **map, - unsigned long *map_size, - unsigned long *desc_size, - u32 *desc_ver, - unsigned long *key_ptr); + struct efi_boot_memmap *map); efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg, unsigned long size, unsigned long align, -- cgit v1.2.3 From fc07716ba803483be91bc4b2344f9c84985e6f07 Mon Sep 17 00:00:00 2001 From: Jeffrey Hugo Date: Mon, 29 Aug 2016 14:38:52 -0600 Subject: efi/libstub: Introduce ExitBootServices helper The spec allows ExitBootServices to fail with EFI_INVALID_PARAMETER if a race condition has occurred where the EFI has updated the memory map after the stub grabbed a reference to the map. The spec defines a retry proceedure with specific requirements to handle this scenario. This scenario was previously observed on x86 - commit d3768d885c6c ("x86, efi: retry ExitBootServices() on failure") but the current fix is not spec compliant and the scenario is now observed on the Qualcomm Technologies QDF2432 via the FDT stub which does not handle the error and thus causes boot failures. The user will notice the boot failure as the kernel is not executed and the system may drop back to a UEFI shell, but will be unresponsive to input and the system will require a power cycle to recover. Add a helper to the stub library that correctly adheres to the spec in the case of EFI_INVALID_PARAMETER from ExitBootServices and can be universally used across all stub implementations. Signed-off-by: Jeffrey Hugo Cc: Ard Biesheuvel Cc: Mark Rutland Cc: Leif Lindholm Cc: Ingo Molnar Cc: Signed-off-by: Matt Fleming --- drivers/firmware/efi/libstub/efi-stub-helper.c | 73 ++++++++++++++++++++++++++ include/linux/efi.h | 10 ++++ 2 files changed, 83 insertions(+) (limited to 'include/linux') diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 29368ac69221..aded10662020 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -740,3 +740,76 @@ char *efi_convert_cmdline(efi_system_table_t *sys_table_arg, *cmd_line_len = options_bytes; return (char *)cmdline_addr; } + +/* + * Handle calling ExitBootServices according to the requirements set out by the + * spec. Obtains the current memory map, and returns that info after calling + * ExitBootServices. The client must specify a function to perform any + * processing of the memory map data prior to ExitBootServices. A client + * specific structure may be passed to the function via priv. The client + * function may be called multiple times. + */ +efi_status_t efi_exit_boot_services(efi_system_table_t *sys_table_arg, + void *handle, + struct efi_boot_memmap *map, + void *priv, + efi_exit_boot_map_processing priv_func) +{ + efi_status_t status; + + status = efi_get_memory_map(sys_table_arg, map); + + if (status != EFI_SUCCESS) + goto fail; + + status = priv_func(sys_table_arg, map, priv); + if (status != EFI_SUCCESS) + goto free_map; + + status = efi_call_early(exit_boot_services, handle, *map->key_ptr); + + if (status == EFI_INVALID_PARAMETER) { + /* + * The memory map changed between efi_get_memory_map() and + * exit_boot_services(). Per the UEFI Spec v2.6, Section 6.4: + * EFI_BOOT_SERVICES.ExitBootServices we need to get the + * updated map, and try again. The spec implies one retry + * should be sufficent, which is confirmed against the EDK2 + * implementation. Per the spec, we can only invoke + * get_memory_map() and exit_boot_services() - we cannot alloc + * so efi_get_memory_map() cannot be used, and we must reuse + * the buffer. For all practical purposes, the headroom in the + * buffer should account for any changes in the map so the call + * to get_memory_map() is expected to succeed here. + */ + *map->map_size = *map->buff_size; + status = efi_call_early(get_memory_map, + map->map_size, + *map->map, + map->key_ptr, + map->desc_size, + map->desc_ver); + + /* exit_boot_services() was called, thus cannot free */ + if (status != EFI_SUCCESS) + goto fail; + + status = priv_func(sys_table_arg, map, priv); + /* exit_boot_services() was called, thus cannot free */ + if (status != EFI_SUCCESS) + goto fail; + + status = efi_call_early(exit_boot_services, handle, *map->key_ptr); + } + + /* exit_boot_services() was called, thus cannot free */ + if (status != EFI_SUCCESS) + goto fail; + + return EFI_SUCCESS; + +free_map: + efi_call_early(free_pool, *map->map); +fail: + return status; +} diff --git a/include/linux/efi.h b/include/linux/efi.h index 943fee524176..0148a3046b48 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1462,4 +1462,14 @@ extern void efi_call_virt_check_flags(unsigned long flags, const char *call); arch_efi_call_virt_teardown(); \ }) +typedef efi_status_t (*efi_exit_boot_map_processing)( + efi_system_table_t *sys_table_arg, + struct efi_boot_memmap *map, + void *priv); + +efi_status_t efi_exit_boot_services(efi_system_table_t *sys_table, + void *handle, + struct efi_boot_memmap *map, + void *priv, + efi_exit_boot_map_processing priv_func); #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From 81409e9e28058811c9ea865345e1753f8f677e44 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 31 Aug 2016 16:04:21 -0700 Subject: usercopy: fold builtin_const check into inline function Instead of having each caller of check_object_size() need to remember to check for a const size parameter, move the check into check_object_size() itself. This actually matches the original implementation in PaX, though this commit cleans up the now-redundant builtin_const() calls in the various architectures. Signed-off-by: Kees Cook --- arch/ia64/include/asm/uaccess.h | 12 ++++-------- arch/powerpc/include/asm/uaccess.h | 19 +++++++------------ arch/sparc/include/asm/uaccess_32.h | 9 +++------ arch/sparc/include/asm/uaccess_64.h | 7 +++---- include/linux/thread_info.h | 3 ++- 5 files changed, 19 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h index 465c70982f40..0472927ebb9b 100644 --- a/arch/ia64/include/asm/uaccess.h +++ b/arch/ia64/include/asm/uaccess.h @@ -241,8 +241,7 @@ extern unsigned long __must_check __copy_user (void __user *to, const void __use static inline unsigned long __copy_to_user (void __user *to, const void *from, unsigned long count) { - if (!__builtin_constant_p(count)) - check_object_size(from, count, true); + check_object_size(from, count, true); return __copy_user(to, (__force void __user *) from, count); } @@ -250,8 +249,7 @@ __copy_to_user (void __user *to, const void *from, unsigned long count) static inline unsigned long __copy_from_user (void *to, const void __user *from, unsigned long count) { - if (!__builtin_constant_p(count)) - check_object_size(to, count, false); + check_object_size(to, count, false); return __copy_user((__force void __user *) to, from, count); } @@ -265,8 +263,7 @@ __copy_from_user (void *to, const void __user *from, unsigned long count) long __cu_len = (n); \ \ if (__access_ok(__cu_to, __cu_len, get_fs())) { \ - if (!__builtin_constant_p(n)) \ - check_object_size(__cu_from, __cu_len, true); \ + check_object_size(__cu_from, __cu_len, true); \ __cu_len = __copy_user(__cu_to, (__force void __user *) __cu_from, __cu_len); \ } \ __cu_len; \ @@ -280,8 +277,7 @@ __copy_from_user (void *to, const void __user *from, unsigned long count) \ __chk_user_ptr(__cu_from); \ if (__access_ok(__cu_from, __cu_len, get_fs())) { \ - if (!__builtin_constant_p(n)) \ - check_object_size(__cu_to, __cu_len, false); \ + check_object_size(__cu_to, __cu_len, false); \ __cu_len = __copy_user((__force void __user *) __cu_to, __cu_from, __cu_len); \ } \ __cu_len; \ diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index c1dc6c14deb8..f1e382498bbb 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -311,14 +311,12 @@ static inline unsigned long copy_from_user(void *to, unsigned long over; if (access_ok(VERIFY_READ, from, n)) { - if (!__builtin_constant_p(n)) - check_object_size(to, n, false); + check_object_size(to, n, false); return __copy_tofrom_user((__force void __user *)to, from, n); } if ((unsigned long)from < TASK_SIZE) { over = (unsigned long)from + n - TASK_SIZE; - if (!__builtin_constant_p(n - over)) - check_object_size(to, n - over, false); + check_object_size(to, n - over, false); return __copy_tofrom_user((__force void __user *)to, from, n - over) + over; } @@ -331,14 +329,12 @@ static inline unsigned long copy_to_user(void __user *to, unsigned long over; if (access_ok(VERIFY_WRITE, to, n)) { - if (!__builtin_constant_p(n)) - check_object_size(from, n, true); + check_object_size(from, n, true); return __copy_tofrom_user(to, (__force void __user *)from, n); } if ((unsigned long)to < TASK_SIZE) { over = (unsigned long)to + n - TASK_SIZE; - if (!__builtin_constant_p(n)) - check_object_size(from, n - over, true); + check_object_size(from, n - over, true); return __copy_tofrom_user(to, (__force void __user *)from, n - over) + over; } @@ -383,8 +379,7 @@ static inline unsigned long __copy_from_user_inatomic(void *to, return 0; } - if (!__builtin_constant_p(n)) - check_object_size(to, n, false); + check_object_size(to, n, false); return __copy_tofrom_user((__force void __user *)to, from, n); } @@ -412,8 +407,8 @@ static inline unsigned long __copy_to_user_inatomic(void __user *to, if (ret == 0) return 0; } - if (!__builtin_constant_p(n)) - check_object_size(from, n, true); + + check_object_size(from, n, true); return __copy_tofrom_user(to, (__force const void __user *)from, n); } diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h index 341a5a133f48..e722c510bb1b 100644 --- a/arch/sparc/include/asm/uaccess_32.h +++ b/arch/sparc/include/asm/uaccess_32.h @@ -249,8 +249,7 @@ unsigned long __copy_user(void __user *to, const void __user *from, unsigned lon static inline unsigned long copy_to_user(void __user *to, const void *from, unsigned long n) { if (n && __access_ok((unsigned long) to, n)) { - if (!__builtin_constant_p(n)) - check_object_size(from, n, true); + check_object_size(from, n, true); return __copy_user(to, (__force void __user *) from, n); } else return n; @@ -258,16 +257,14 @@ static inline unsigned long copy_to_user(void __user *to, const void *from, unsi static inline unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { - if (!__builtin_constant_p(n)) - check_object_size(from, n, true); + check_object_size(from, n, true); return __copy_user(to, (__force void __user *) from, n); } static inline unsigned long copy_from_user(void *to, const void __user *from, unsigned long n) { if (n && __access_ok((unsigned long) from, n)) { - if (!__builtin_constant_p(n)) - check_object_size(to, n, false); + check_object_size(to, n, false); return __copy_user((__force void __user *) to, from, n); } else return n; diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h index 8bda94fab8e8..37a315d0ddd4 100644 --- a/arch/sparc/include/asm/uaccess_64.h +++ b/arch/sparc/include/asm/uaccess_64.h @@ -212,8 +212,7 @@ copy_from_user(void *to, const void __user *from, unsigned long size) { unsigned long ret; - if (!__builtin_constant_p(size)) - check_object_size(to, size, false); + check_object_size(to, size, false); ret = ___copy_from_user(to, from, size); if (unlikely(ret)) @@ -233,8 +232,8 @@ copy_to_user(void __user *to, const void *from, unsigned long size) { unsigned long ret; - if (!__builtin_constant_p(size)) - check_object_size(from, size, true); + check_object_size(from, size, true); + ret = ___copy_to_user(to, from, size); if (unlikely(ret)) ret = copy_to_user_fixup(to, from, size); diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index cbd8990e2e77..10c9e601398b 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -121,7 +121,8 @@ extern void __check_object_size(const void *ptr, unsigned long n, static inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { - __check_object_size(ptr, n, to_user); + if (!__builtin_constant_p(n)) + __check_object_size(ptr, n, to_user); } #else static inline void check_object_size(const void *ptr, unsigned long n, -- cgit v1.2.3 From a85d6b8242dc78ef3f4542a0f979aebcbe77fc4e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 7 Sep 2016 09:39:32 -0700 Subject: usercopy: force check_object_size() inline Just for good measure, make sure that check_object_size() is always inlined too, as already done for copy_*_user() and __copy_*_user(). Suggested-by: Linus Torvalds Signed-off-by: Kees Cook --- include/linux/thread_info.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 10c9e601398b..2b5b10eed74f 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -118,8 +118,8 @@ static inline int arch_within_stack_frames(const void * const stack, extern void __check_object_size(const void *ptr, unsigned long n, bool to_user); -static inline void check_object_size(const void *ptr, unsigned long n, - bool to_user) +static __always_inline void check_object_size(const void *ptr, unsigned long n, + bool to_user) { if (!__builtin_constant_p(n)) __check_object_size(ptr, n, to_user); -- cgit v1.2.3 From e7e31ca43d6bedf1c551b1f9c7e78d51c9a45790 Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Wed, 7 Sep 2016 19:07:58 +0300 Subject: net/mlx5e: Move an_disable_cap bit to a new position Previous an_disable_cap position bit31 is deprecated to be use in driver with newer firmware. New firmware will advertise the same capability in bit29. Old capability didn't allow setting more than one protocol for a specific speed when autoneg is off, while newer firmware will allow this and it is indicated in the new capability location. Signed-off-by: Bodong Wang Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 21bc4557b67a..d1f9a581aca8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -6710,9 +6710,10 @@ struct mlx5_ifc_pude_reg_bits { }; struct mlx5_ifc_ptys_reg_bits { - u8 an_disable_cap[0x1]; + u8 reserved_at_0[0x1]; u8 an_disable_admin[0x1]; - u8 reserved_at_2[0x6]; + u8 an_disable_cap[0x1]; + u8 reserved_at_3[0x5]; u8 local_port[0x8]; u8 reserved_at_10[0xd]; u8 proto_mask[0x3]; -- cgit v1.2.3 From ba63f23d69a3a10e7e527a02702023da68ef8a6d Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 8 Sep 2016 14:20:38 -0700 Subject: fscrypto: require write access to mount to set encryption policy Since setting an encryption policy requires writing metadata to the filesystem, it should be guarded by mnt_want_write/mnt_drop_write. Otherwise, a user could cause a write to a frozen or readonly filesystem. This was handled correctly by f2fs but not by ext4. Make fscrypt_process_policy() handle it rather than relying on the filesystem to get it right. Signed-off-by: Eric Biggers Cc: stable@vger.kernel.org # 4.1+; check fs/{ext4,f2fs} Signed-off-by: Theodore Ts'o Acked-by: Jaegeuk Kim --- fs/crypto/policy.c | 38 +++++++++++++++++++++++++------------- fs/ext4/ioctl.c | 2 +- fs/f2fs/file.c | 9 +-------- include/linux/fscrypto.h | 5 ++--- 4 files changed, 29 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index f96547f83cab..ed115acb5dee 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -11,6 +11,7 @@ #include #include #include +#include static int inode_has_encryption_context(struct inode *inode) { @@ -92,31 +93,42 @@ static int create_encryption_context_from_policy(struct inode *inode, return inode->i_sb->s_cop->set_context(inode, &ctx, sizeof(ctx), NULL); } -int fscrypt_process_policy(struct inode *inode, +int fscrypt_process_policy(struct file *filp, const struct fscrypt_policy *policy) { + struct inode *inode = file_inode(filp); + int ret; + if (!inode_owner_or_capable(inode)) return -EACCES; if (policy->version != 0) return -EINVAL; + ret = mnt_want_write_file(filp); + if (ret) + return ret; + if (!inode_has_encryption_context(inode)) { if (!S_ISDIR(inode->i_mode)) - return -EINVAL; - if (!inode->i_sb->s_cop->empty_dir) - return -EOPNOTSUPP; - if (!inode->i_sb->s_cop->empty_dir(inode)) - return -ENOTEMPTY; - return create_encryption_context_from_policy(inode, policy); + ret = -EINVAL; + else if (!inode->i_sb->s_cop->empty_dir) + ret = -EOPNOTSUPP; + else if (!inode->i_sb->s_cop->empty_dir(inode)) + ret = -ENOTEMPTY; + else + ret = create_encryption_context_from_policy(inode, + policy); + } else if (!is_encryption_context_consistent_with_policy(inode, + policy)) { + printk(KERN_WARNING + "%s: Policy inconsistent with encryption context\n", + __func__); + ret = -EINVAL; } - if (is_encryption_context_consistent_with_policy(inode, policy)) - return 0; - - printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n", - __func__); - return -EINVAL; + mnt_drop_write_file(filp); + return ret; } EXPORT_SYMBOL(fscrypt_process_policy); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 10686fd67fb4..1bb7df5e4536 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -776,7 +776,7 @@ resizefs_out: (struct fscrypt_policy __user *)arg, sizeof(policy))) return -EFAULT; - return fscrypt_process_policy(inode, &policy); + return fscrypt_process_policy(filp, &policy); #else return -EOPNOTSUPP; #endif diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 47abb96098e4..28f4f4cbb8d8 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1757,21 +1757,14 @@ static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg) { struct fscrypt_policy policy; struct inode *inode = file_inode(filp); - int ret; if (copy_from_user(&policy, (struct fscrypt_policy __user *)arg, sizeof(policy))) return -EFAULT; - ret = mnt_want_write_file(filp); - if (ret) - return ret; - f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); - ret = fscrypt_process_policy(inode, &policy); - mnt_drop_write_file(filp); - return ret; + return fscrypt_process_policy(filp, &policy); } static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg) diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index cfa6cde25f8e..76cff18bb032 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -274,8 +274,7 @@ extern void fscrypt_restore_control_page(struct page *); extern int fscrypt_zeroout_range(struct inode *, pgoff_t, sector_t, unsigned int); /* policy.c */ -extern int fscrypt_process_policy(struct inode *, - const struct fscrypt_policy *); +extern int fscrypt_process_policy(struct file *, const struct fscrypt_policy *); extern int fscrypt_get_policy(struct inode *, struct fscrypt_policy *); extern int fscrypt_has_permitted_context(struct inode *, struct inode *); extern int fscrypt_inherit_context(struct inode *, struct inode *, @@ -345,7 +344,7 @@ static inline int fscrypt_notsupp_zeroout_range(struct inode *i, pgoff_t p, } /* policy.c */ -static inline int fscrypt_notsupp_process_policy(struct inode *i, +static inline int fscrypt_notsupp_process_policy(struct file *f, const struct fscrypt_policy *p) { return -EOPNOTSUPP; -- cgit v1.2.3 From ebf9ff753c041b296241990aef76163bbb2cc9c8 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 13 Sep 2016 15:58:28 +0200 Subject: genirq: Provide irq_gc_{lock_irqsave,unlock_irqrestore}() helpers Some irqchip drivers need to take the generic chip lock outside of the irq context. Provide the irq_gc_{lock_irqsave,unlock_irqrestore}() helpers to allow one to disable irqs while entering a critical section protected by gc->lock. Note that we do not provide optimized version of these helpers for !SMP, because they are not called from the hot-path. [ tglx: Added a comment when these helpers should be [not] used ] Signed-off-by: Boris Brezillon Cc: Jason Cooper Cc: Marc Zyngier Cc: Nicolas Ferre Cc: stable@vger.kernel.org Cc: Alexandre Belloni Link: http://lkml.kernel.org/r/1473775109-4192-1-git-send-email-boris.brezillon@free-electrons.com Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index b52424eaa0ed..0ac26c892fe2 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -945,6 +945,16 @@ static inline void irq_gc_lock(struct irq_chip_generic *gc) { } static inline void irq_gc_unlock(struct irq_chip_generic *gc) { } #endif +/* + * The irqsave variants are for usage in non interrupt code. Do not use + * them in irq_chip callbacks. Use irq_gc_lock() instead. + */ +#define irq_gc_lock_irqsave(gc, flags) \ + raw_spin_lock_irqsave(&(gc)->lock, flags) + +#define irq_gc_unlock_irqrestore(gc, flags) \ + raw_spin_unlock_irqrestore(&(gc)->lock, flags) + static inline void irq_reg_writel(struct irq_chip_generic *gc, u32 val, int reg_offset) { -- cgit v1.2.3 From 6cfeaf5125d425043d44002d0a1a8a147be582bf Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Wed, 14 Sep 2016 11:00:26 +0100 Subject: cpu/hotplug: Include linux/types.h in linux/cpuhotplug.h The linux/cpuhotplug.h header makes use of the bool type, but wasn't including linux/types.h to ensure that type has been defined. Fix this by including linux/types.h in preparation for including linux/cpuhotplug.h in a file that doesn't do so already. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Cc: Richard Cochran Cc: Sebastian Andrzej Siewior Cc: Ralf Baechle Cc: Anna-Maria Gleixner Link: http://lkml.kernel.org/r/20160914100027.20945-1-paul.burton@imgtec.com Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 242bf530edfc..34bd80512a0c 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -1,6 +1,8 @@ #ifndef __CPUHOTPLUG_H #define __CPUHOTPLUG_H +#include + enum cpuhp_state { CPUHP_OFFLINE, CPUHP_CREATE_THREADS, -- cgit v1.2.3 From d4690f1e1cdabb4d61207b6787b1605a0dc0aeab Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 16 Sep 2016 00:11:45 +0100 Subject: fix iov_iter_fault_in_readable() ... by turning it into what used to be multipages counterpart Cc: stable@vger.kernel.org Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/uio.h | 2 +- lib/iov_iter.c | 24 ++---------------------- 2 files changed, 3 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 1b5d1cd796e2..75b4aaf31a9d 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -76,7 +76,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes); void iov_iter_advance(struct iov_iter *i, size_t bytes); int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes); -int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes); +#define iov_iter_fault_in_multipages_readable iov_iter_fault_in_readable size_t iov_iter_single_seg_count(const struct iov_iter *i); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 9e8c7386b3a0..7e3138cfc8c9 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -290,26 +290,6 @@ done: return wanted - bytes; } -/* - * Fault in the first iovec of the given iov_iter, to a maximum length - * of bytes. Returns 0 on success, or non-zero if the memory could not be - * accessed (ie. because it is an invalid address). - * - * writev-intensive code may want this to prefault several iovecs -- that - * would be possible (callers must not rely on the fact that _only_ the - * first iovec will be faulted with the current implementation). - */ -int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) -{ - if (!(i->type & (ITER_BVEC|ITER_KVEC))) { - char __user *buf = i->iov->iov_base + i->iov_offset; - bytes = min(bytes, i->iov->iov_len - i->iov_offset); - return fault_in_pages_readable(buf, bytes); - } - return 0; -} -EXPORT_SYMBOL(iov_iter_fault_in_readable); - /* * Fault in one or more iovecs of the given iov_iter, to a maximum length of * bytes. For each iovec, fault in each page that constitutes the iovec. @@ -317,7 +297,7 @@ EXPORT_SYMBOL(iov_iter_fault_in_readable); * Return 0 on success, or non-zero if the memory could not be accessed (i.e. * because it is an invalid address). */ -int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes) +int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) { size_t skip = i->iov_offset; const struct iovec *iov; @@ -334,7 +314,7 @@ int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes) } return 0; } -EXPORT_SYMBOL(iov_iter_fault_in_multipages_readable); +EXPORT_SYMBOL(iov_iter_fault_in_readable); void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov, unsigned long nr_segs, -- cgit v1.2.3 From 12703dbfeb15402260e7554d32a34ac40c233990 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 19 Sep 2016 14:44:27 -0700 Subject: fsnotify: add a way to stop queueing events on group shutdown Implement a function that can be called when a group is being shutdown to stop queueing new events to the group. Fanotify will use this. Fixes: 5838d4442bd5 ("fanotify: fix double free of pending permission events") Link: http://lkml.kernel.org/r/1473797711-14111-2-git-send-email-jack@suse.cz Signed-off-by: Jan Kara Reviewed-by: Miklos Szeredi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/group.c | 19 +++++++++++++++++++ fs/notify/notification.c | 8 +++++++- include/linux/fsnotify_backend.h | 3 +++ 3 files changed, 29 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/notify/group.c b/fs/notify/group.c index 3e2dd85be5dd..b47f7cfdcaa4 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -39,6 +39,17 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group) kfree(group); } +/* + * Stop queueing new events for this group. Once this function returns + * fsnotify_add_event() will not add any new events to the group's queue. + */ +void fsnotify_group_stop_queueing(struct fsnotify_group *group) +{ + mutex_lock(&group->notification_mutex); + group->shutdown = true; + mutex_unlock(&group->notification_mutex); +} + /* * Trying to get rid of a group. Remove all marks, flush all events and release * the group reference. @@ -47,6 +58,14 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group) */ void fsnotify_destroy_group(struct fsnotify_group *group) { + /* + * Stop queueing new events. The code below is careful enough to not + * require this but fanotify needs to stop queuing events even before + * fsnotify_destroy_group() is called and this makes the other callers + * of fsnotify_destroy_group() to see the same behavior. + */ + fsnotify_group_stop_queueing(group); + /* clear all inode marks for this group, attach them to destroy_list */ fsnotify_detach_group_marks(group); diff --git a/fs/notify/notification.c b/fs/notify/notification.c index a95d8e037aeb..3d76e65ff84f 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -82,7 +82,8 @@ void fsnotify_destroy_event(struct fsnotify_group *group, * Add an event to the group notification queue. The group can later pull this * event off the queue to deal with. The function returns 0 if the event was * added to the queue, 1 if the event was merged with some other queued event, - * 2 if the queue of events has overflown. + * 2 if the event was not queued - either the queue of events has overflown + * or the group is shutting down. */ int fsnotify_add_event(struct fsnotify_group *group, struct fsnotify_event *event, @@ -96,6 +97,11 @@ int fsnotify_add_event(struct fsnotify_group *group, mutex_lock(&group->notification_mutex); + if (group->shutdown) { + mutex_unlock(&group->notification_mutex); + return 2; + } + if (group->q_len >= group->max_events) { ret = 2; /* Queue overflow event only if it isn't already queued */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 58205f33af02..40a9e99de703 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -148,6 +148,7 @@ struct fsnotify_group { #define FS_PRIO_1 1 /* fanotify content based access control */ #define FS_PRIO_2 2 /* fanotify pre-content access */ unsigned int priority; + bool shutdown; /* group is being shut down, don't queue more events */ /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ struct mutex mark_mutex; /* protect marks_list */ @@ -292,6 +293,8 @@ extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *op extern void fsnotify_get_group(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ extern void fsnotify_put_group(struct fsnotify_group *group); +/* group destruction begins, stop queuing new events */ +extern void fsnotify_group_stop_queueing(struct fsnotify_group *group); /* destroy group */ extern void fsnotify_destroy_group(struct fsnotify_group *group); /* fasync handler function */ -- cgit v1.2.3 From 96d41019e3ac55f6f0115b0ce97e4f24a3d636d2 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 19 Sep 2016 14:44:30 -0700 Subject: fanotify: fix list corruption in fanotify_get_response() fanotify_get_response() calls fsnotify_remove_event() when it finds that group is being released from fanotify_release() (bypass_perm is set). However the event it removes need not be only in the group's notification queue but it can have already moved to access_list (userspace read the event before closing the fanotify instance fd) which is protected by a different lock. Thus when fsnotify_remove_event() races with fanotify_release() operating on access_list, the list can get corrupted. Fix the problem by moving all the logic removing permission events from the lists to one place - fanotify_release(). Fixes: 5838d4442bd5 ("fanotify: fix double free of pending permission events") Link: http://lkml.kernel.org/r/1473797711-14111-3-git-send-email-jack@suse.cz Signed-off-by: Jan Kara Reported-by: Miklos Szeredi Tested-by: Miklos Szeredi Reviewed-by: Miklos Szeredi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/fanotify/fanotify.c | 13 +------------ fs/notify/fanotify/fanotify_user.c | 36 ++++++++++++++++++++++++------------ fs/notify/notification.c | 15 --------------- include/linux/fsnotify_backend.h | 3 --- 4 files changed, 25 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index d2f97ecca6a5..e0e5f7c3c99f 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -67,18 +67,7 @@ static int fanotify_get_response(struct fsnotify_group *group, pr_debug("%s: group=%p event=%p\n", __func__, group, event); - wait_event(group->fanotify_data.access_waitq, event->response || - atomic_read(&group->fanotify_data.bypass_perm)); - - if (!event->response) { /* bypass_perm set */ - /* - * Event was canceled because group is being destroyed. Remove - * it from group's event list because we are responsible for - * freeing the permission event. - */ - fsnotify_remove_event(group, &event->fae.fse); - return 0; - } + wait_event(group->fanotify_data.access_waitq, event->response); /* userspace responded, convert to something usable */ switch (event->response) { diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 8e8e6bcd1d43..a64313868d3a 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -358,16 +358,20 @@ static int fanotify_release(struct inode *ignored, struct file *file) #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS struct fanotify_perm_event_info *event, *next; + struct fsnotify_event *fsn_event; /* - * There may be still new events arriving in the notification queue - * but since userspace cannot use fanotify fd anymore, no event can - * enter or leave access_list by now. + * Stop new events from arriving in the notification queue. since + * userspace cannot use fanotify fd anymore, no event can enter or + * leave access_list by now either. */ - spin_lock(&group->fanotify_data.access_lock); - - atomic_inc(&group->fanotify_data.bypass_perm); + fsnotify_group_stop_queueing(group); + /* + * Process all permission events on access_list and notification queue + * and simulate reply from userspace. + */ + spin_lock(&group->fanotify_data.access_lock); list_for_each_entry_safe(event, next, &group->fanotify_data.access_list, fae.fse.list) { pr_debug("%s: found group=%p event=%p\n", __func__, group, @@ -379,12 +383,21 @@ static int fanotify_release(struct inode *ignored, struct file *file) spin_unlock(&group->fanotify_data.access_lock); /* - * Since bypass_perm is set, newly queued events will not wait for - * access response. Wake up the already sleeping ones now. - * synchronize_srcu() in fsnotify_destroy_group() will wait for all - * processes sleeping in fanotify_handle_event() waiting for access - * response and thus also for all permission events to be freed. + * Destroy all non-permission events. For permission events just + * dequeue them and set the response. They will be freed once the + * response is consumed and fanotify_get_response() returns. */ + mutex_lock(&group->notification_mutex); + while (!fsnotify_notify_queue_is_empty(group)) { + fsn_event = fsnotify_remove_first_event(group); + if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS)) + fsnotify_destroy_event(group, fsn_event); + else + FANOTIFY_PE(fsn_event)->response = FAN_ALLOW; + } + mutex_unlock(&group->notification_mutex); + + /* Response for all permission events it set, wakeup waiters */ wake_up(&group->fanotify_data.access_waitq); #endif @@ -755,7 +768,6 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) spin_lock_init(&group->fanotify_data.access_lock); init_waitqueue_head(&group->fanotify_data.access_waitq); INIT_LIST_HEAD(&group->fanotify_data.access_list); - atomic_set(&group->fanotify_data.bypass_perm, 0); #endif switch (flags & FAN_ALL_CLASS_BITS) { case FAN_CLASS_NOTIF: diff --git a/fs/notify/notification.c b/fs/notify/notification.c index 3d76e65ff84f..e455e83ceeeb 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -131,21 +131,6 @@ queue: return ret; } -/* - * Remove @event from group's notification queue. It is the responsibility of - * the caller to destroy the event. - */ -void fsnotify_remove_event(struct fsnotify_group *group, - struct fsnotify_event *event) -{ - mutex_lock(&group->notification_mutex); - if (!list_empty(&event->list)) { - list_del_init(&event->list); - group->q_len--; - } - mutex_unlock(&group->notification_mutex); -} - /* * Remove and return the first event from the notification list. It is the * responsibility of the caller to destroy the obtained event diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 40a9e99de703..7268ed076be8 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -180,7 +180,6 @@ struct fsnotify_group { spinlock_t access_lock; struct list_head access_list; wait_queue_head_t access_waitq; - atomic_t bypass_perm; #endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */ int f_flags; unsigned int max_marks; @@ -307,8 +306,6 @@ extern int fsnotify_add_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct list_head *, struct fsnotify_event *)); -/* Remove passed event from groups notification queue */ -extern void fsnotify_remove_event(struct fsnotify_group *group, struct fsnotify_event *event); /* true if the group notification queue is empty */ extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group); /* return, but do not dequeue the first event on the notification queue */ -- cgit v1.2.3 From e23d4159b109167126e5bcd7f3775c95de7fee47 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 20 Sep 2016 20:07:42 +0100 Subject: fix fault_in_multipages_...() on architectures with no-op access_ok() Switching iov_iter fault-in to multipages variants has exposed an old bug in underlying fault_in_multipages_...(); they break if the range passed to them wraps around. Normally access_ok() done by callers will prevent such (and it's a guaranteed EFAULT - ERR_PTR() values fall into such a range and they should not point to any valid objects). However, on architectures where userland and kernel live in different MMU contexts (e.g. s390) access_ok() is a no-op and on those a range with a wraparound can reach fault_in_multipages_...(). Since any wraparound means EFAULT there, the fix is trivial - turn those while (uaddr <= end) ... into if (unlikely(uaddr > end)) return -EFAULT; do ... while (uaddr <= end); Reported-by: Jan Stancek Tested-by: Jan Stancek Cc: stable@vger.kernel.org # v3.5+ Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 66a1260b33de..7e3d53753612 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -571,56 +571,56 @@ static inline int fault_in_pages_readable(const char __user *uaddr, int size) */ static inline int fault_in_multipages_writeable(char __user *uaddr, int size) { - int ret = 0; char __user *end = uaddr + size - 1; if (unlikely(size == 0)) - return ret; + return 0; + if (unlikely(uaddr > end)) + return -EFAULT; /* * Writing zeroes into userspace here is OK, because we know that if * the zero gets there, we'll be overwriting it. */ - while (uaddr <= end) { - ret = __put_user(0, uaddr); - if (ret != 0) - return ret; + do { + if (unlikely(__put_user(0, uaddr) != 0)) + return -EFAULT; uaddr += PAGE_SIZE; - } + } while (uaddr <= end); /* Check whether the range spilled into the next page. */ if (((unsigned long)uaddr & PAGE_MASK) == ((unsigned long)end & PAGE_MASK)) - ret = __put_user(0, end); + return __put_user(0, end); - return ret; + return 0; } static inline int fault_in_multipages_readable(const char __user *uaddr, int size) { volatile char c; - int ret = 0; const char __user *end = uaddr + size - 1; if (unlikely(size == 0)) - return ret; + return 0; - while (uaddr <= end) { - ret = __get_user(c, uaddr); - if (ret != 0) - return ret; + if (unlikely(uaddr > end)) + return -EFAULT; + + do { + if (unlikely(__get_user(c, uaddr) != 0)) + return -EFAULT; uaddr += PAGE_SIZE; - } + } while (uaddr <= end); /* Check whether the range spilled into the next page. */ if (((unsigned long)uaddr & PAGE_MASK) == ((unsigned long)end & PAGE_MASK)) { - ret = __get_user(c, end); - (void)c; + return __get_user(c, end); } - return ret; + return 0; } int add_to_page_cache_locked(struct page *page, struct address_space *mapping, -- cgit v1.2.3