From df127725783f45e0f7681f7def2ca259ee9ef4ae Mon Sep 17 00:00:00 2001 From: Michal Nazarewicz Date: Fri, 15 Jan 2016 16:57:58 -0800 Subject: include/linux/kernel.h: change abs() macro so it uses consistent return type commit 8f57e4d930d48217268315898212518d4d3e0773 upstream. Rewrite abs() so that its return type does not depend on the architecture and no unexpected type conversion happen inside of it. The only conversion is from unsigned to signed type. char is left as a return type but treated as a signed type regradless of it's actual signedness. With the old version, int arguments were promoted to long and depending on architecture a long argument might result in s64 or long return type (which may or may not be the same). This came after some back and forth with Nicolas. The current macro has different return type (for the same input type) depending on architecture which might be midly iritating. An alternative version would promote to int like so: #define abs(x) __abs_choose_expr(x, long long, \ __abs_choose_expr(x, long, \ __builtin_choose_expr( \ sizeof(x) <= sizeof(int), \ ({ int __x = (x); __x<0?-__x:__x; }), \ ((void)0)))) I have no preference but imagine Linus might. :] Nicolas argument against is that promoting to int causes iconsistent behaviour: int main(void) { unsigned short a = 0, b = 1, c = a - b; unsigned short d = abs(a - b); unsigned short e = abs(c); printf("%u %u\n", d, e); // prints: 1 65535 } Then again, no sane person expects consistent behaviour from C integer arithmetic. ;) Note: __builtin_types_compatible_p(unsigned char, char) is always false, and __builtin_types_compatible_p(signed char, char) is also always false. Signed-off-by: Michal Nazarewicz Reviewed-by: Nicolas Pitre Cc: Srinivas Pandruvada Cc: Wey-Yi Guy Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Cc: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- include/linux/kernel.h | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 924853d33a13..e571e592e53a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -202,26 +202,26 @@ extern int _cond_resched(void); /** * abs - return absolute value of an argument - * @x: the value. If it is unsigned type, it is converted to signed type first - * (s64, long or int depending on its size). + * @x: the value. If it is unsigned type, it is converted to signed type first. + * char is treated as if it was signed (regardless of whether it really is) + * but the macro's return type is preserved as char. * - * Return: an absolute value of x. If x is 64-bit, macro's return type is s64, - * otherwise it is signed long. + * Return: an absolute value of x. */ -#define abs(x) __builtin_choose_expr(sizeof(x) == sizeof(s64), ({ \ - s64 __x = (x); \ - (__x < 0) ? -__x : __x; \ - }), ({ \ - long ret; \ - if (sizeof(x) == sizeof(long)) { \ - long __x = (x); \ - ret = (__x < 0) ? -__x : __x; \ - } else { \ - int __x = (x); \ - ret = (__x < 0) ? -__x : __x; \ - } \ - ret; \ - })) +#define abs(x) __abs_choose_expr(x, long long, \ + __abs_choose_expr(x, long, \ + __abs_choose_expr(x, int, \ + __abs_choose_expr(x, short, \ + __abs_choose_expr(x, char, \ + __builtin_choose_expr( \ + __builtin_types_compatible_p(typeof(x), char), \ + (char)({ signed char __x = (x); __x<0?-__x:__x; }), \ + ((void)0))))))) + +#define __abs_choose_expr(x, type, other) __builtin_choose_expr( \ + __builtin_types_compatible_p(typeof(x), signed type) || \ + __builtin_types_compatible_p(typeof(x), unsigned type), \ + ({ signed type __x = (x); __x < 0 ? -__x : __x; }), other) /** * reciprocal_scale - "scale" a value into range [0, ep_ro) -- cgit v1.2.3 From f357a79839f95f5ea7baf1c1366d64796d833bca Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Thu, 1 Sep 2016 22:18:34 -0700 Subject: bonding: Fix bonding crash [ Upstream commit 24b27fc4cdf9e10c5e79e5923b6b7c2c5c95096c ] 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 Signed-off-by: Greg Kroah-Hartman --- 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 b97d6823ef3c..4e9c75226f07 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3036,6 +3036,7 @@ 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 8c945f5aac28a81f20f6a5208a6ccab43b8e7a89 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 27 Aug 2016 17:33:03 +0100 Subject: net: smc91x: fix SMC accesses [ Upstream commit 2fb04fdf30192ff1e2b5834e9b7745889ea8bbcb ] Commit b70661c70830 ("net: smc91x: use run-time configuration on all ARM machines") broke some ARM platforms through several mistakes. Firstly, the access size must correspond to the following rule: (a) at least one of 16-bit or 8-bit access size must be supported (b) 32-bit accesses are optional, and may be enabled in addition to the above. Secondly, it provides no emulation of 16-bit accesses, instead blindly making 16-bit accesses even when the platform specifies that only 8-bit is supported. Reorganise smc91x.h so we can make use of the existing 16-bit access emulation already provided - if 16-bit accesses are supported, use 16-bit accesses directly, otherwise if 8-bit accesses are supported, use the provided 16-bit access emulation. If neither, BUG(). This exactly reflects the driver behaviour prior to the commit being fixed. Since the conversion incorrectly cut down the available access sizes on several platforms, we also need to go through every platform and fix up the overly-restrictive access size: Arnd assumed that if a platform can perform 32-bit, 16-bit and 8-bit accesses, then only a 32-bit access size needed to be specified - not so, all available access sizes must be specified. This likely fixes some performance regressions in doing this: if a platform does not support 8-bit accesses, 8-bit accesses have been emulated by performing a 16-bit read-modify-write access. Tested on the Intel Assabet/Neponset platform, which supports only 8-bit accesses, which was broken by the original commit. Fixes: b70661c70830 ("net: smc91x: use run-time configuration on all ARM machines") Signed-off-by: Russell King Tested-by: Robert Jarzmik Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/linux/smc91x.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/smc91x.h b/include/linux/smc91x.h index 76199b75d584..e302c447e057 100644 --- a/include/linux/smc91x.h +++ b/include/linux/smc91x.h @@ -1,6 +1,16 @@ #ifndef __SMC91X_H__ #define __SMC91X_H__ +/* + * These bits define which access sizes a platform can support, rather + * than the maximal access size. So, if your platform can do 16-bit + * and 32-bit accesses to the SMC91x device, but not 8-bit, set both + * SMC91X_USE_16BIT and SMC91X_USE_32BIT. + * + * The SMC91x driver requires at least one of SMC91X_USE_8BIT or + * SMC91X_USE_16BIT to be supported - just setting SMC91X_USE_32BIT is + * an invalid configuration. + */ #define SMC91X_USE_8BIT (1 << 0) #define SMC91X_USE_16BIT (1 << 1) #define SMC91X_USE_32BIT (1 << 2) -- cgit v1.2.3 From af426ec184a38d257457a22554542d4f9bb7eecd 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 commit 12703dbfeb15402260e7554d32a34ac40c233990 upstream. 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 Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/fsnotify_backend.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 533c4408529a..5dfba9a8a7be 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 */ @@ -308,6 +309,8 @@ 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 6e67de3922f25ae43fc86be362d740d88167ae7f 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() commit 96d41019e3ac55f6f0115b0ce97e4f24a3d636d2 upstream. 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 Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/fsnotify_backend.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 5dfba9a8a7be..850d8822e8ff 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; @@ -323,8 +322,6 @@ 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 3f5d8326a870729ae21aa0a6b132cf8d9e9fcc1e 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() commit e23d4159b109167126e5bcd7f3775c95de7fee47 upstream. 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 Signed-off-by: Al Viro Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- 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 26eabf5ec718..fbfadba81c5a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -601,56 +601,56 @@ 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