From d253eee20195b25e298bf162a6e72f14bf4803e5 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Wed, 3 Dec 2008 15:52:35 -0800 Subject: can: Fix CAN_(EFF|RTR)_FLAG handling in can_filter Due to a wrong safety check in af_can.c it was not possible to filter for SFF frames with a specific CAN identifier without getting the same selected CAN identifier from a received EFF frame also. This fix has a minimum (but user visible) impact on the CAN filter API and therefore the CAN version is set to a new date. Indeed the 'old' API is still working as-is. But when now setting CAN_(EFF|RTR)_FLAG in can_filter.can_mask you might get less traffic than before - but still the stuff that you expected to get for your defined filter ... Thanks to Kurt Van Dijck for pointing at this issue and for the review. Signed-off-by: Oliver Hartkopp Acked-by: Kurt Van Dijck Signed-off-by: David S. Miller --- include/linux/can/core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/can/core.h b/include/linux/can/core.h index e9ca210ffa5b..f50785ad4781 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -19,7 +19,7 @@ #include #include -#define CAN_VERSION "20071116" +#define CAN_VERSION "20081130" /* increment this number each time you change some user-space interface */ #define CAN_ABI_VERSION "8" -- cgit v1.2.3 From fd4ce1acd0f8558033b1a6968001552bd7671e6d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 5 Nov 2008 14:58:42 +0100 Subject: [PATCH 1/2] kill FMODE_NDELAY_NOW Update FMODE_NDELAY before each ioctl call so that we can kill the magic FMODE_NDELAY_NOW. It would be even better to do this directly in setfl(), but for that we'd need to have FMODE_NDELAY for all files, not just block special files. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 0dcdd9458f4b..b3345a90e11a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -79,7 +79,6 @@ extern int dir_notify_enable; #define FMODE_NDELAY ((__force fmode_t)32) #define FMODE_EXCL ((__force fmode_t)64) #define FMODE_WRITE_IOCTL ((__force fmode_t)128) -#define FMODE_NDELAY_NOW ((__force fmode_t)256) #define RW_MASK 1 #define RWA_MASK 2 -- cgit v1.2.3 From fc9161e54d0dbf799beff9692ea1cc6237162b85 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 5 Nov 2008 14:58:46 +0100 Subject: [PATCH 2/2] documnt FMODE_ constants Make sure all FMODE_ constants are documents, and ensure a coherent style for the already existing comments. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 32 +++++++++++++++++--------------- 1 file changed, 17 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index b3345a90e11a..4a853ef6fd35 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -63,21 +63,23 @@ extern int dir_notify_enable; #define MAY_ACCESS 16 #define MAY_OPEN 32 -#define FMODE_READ ((__force fmode_t)1) -#define FMODE_WRITE ((__force fmode_t)2) - -/* Internal kernel extensions */ -#define FMODE_LSEEK ((__force fmode_t)4) -#define FMODE_PREAD ((__force fmode_t)8) -#define FMODE_PWRITE FMODE_PREAD /* These go hand in hand */ - -/* File is being opened for execution. Primary users of this flag are - distributed filesystems that can use it to achieve correct ETXTBUSY - behavior for cross-node execution/opening_for_writing of files */ -#define FMODE_EXEC ((__force fmode_t)16) - -#define FMODE_NDELAY ((__force fmode_t)32) -#define FMODE_EXCL ((__force fmode_t)64) +/* file is open for reading */ +#define FMODE_READ ((__force fmode_t)1) +/* file is open for writing */ +#define FMODE_WRITE ((__force fmode_t)2) +/* file is seekable */ +#define FMODE_LSEEK ((__force fmode_t)4) +/* file can be accessed using pread/pwrite */ +#define FMODE_PREAD ((__force fmode_t)8) +#define FMODE_PWRITE FMODE_PREAD /* These go hand in hand */ +/* File is opened for execution with sys_execve / sys_uselib */ +#define FMODE_EXEC ((__force fmode_t)16) +/* File is opened with O_NDELAY (only set for block devices) */ +#define FMODE_NDELAY ((__force fmode_t)32) +/* File is opened with O_EXCL (only set for block devices) */ +#define FMODE_EXCL ((__force fmode_t)64) +/* File is opened using open(.., 3, ..) and is writeable only for ioctls + (specialy hack for floppy.c) */ #define FMODE_WRITE_IOCTL ((__force fmode_t)128) #define RW_MASK 1 -- cgit v1.2.3 From f2f1fa78a155524b849edf359e42a3001ea652c0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 5 Dec 2008 14:49:18 -0800 Subject: Enforce a minimum SG_IO timeout There's no point in having too short SG_IO timeouts, since if the command does end up timing out, we'll end up through the reset sequence that is several seconds long in order to abort the command that timed out. As a result, shorter timeouts than a few seconds simply do not make sense, as the recovery would be longer than the timeout itself. Add a BLK_MIN_SG_TIMEOUT to match the existign BLK_DEFAULT_SG_TIMEOUT. Suggested-by: Alan Cox Acked-by: Tejun Heo Acked-by: Jens Axboe Cc: Jeff Garzik Signed-off-by: Linus Torvalds --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6dcd30d806cd..031a315c0509 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -662,6 +662,7 @@ extern unsigned long blk_max_low_pfn, blk_max_pfn; * default timeout for SG_IO if none specified */ #define BLK_DEFAULT_SG_TIMEOUT (60 * HZ) +#define BLK_MIN_SG_TIMEOUT (7 * HZ) #ifdef CONFIG_BOUNCE extern int init_emergency_isa_pool(void); -- cgit v1.2.3 From a64e64944f4b8ce3288519555dbaa0232414b8ac Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 12 Nov 2008 18:37:41 -0500 Subject: [PATCH] return records for fork() both to child and parent Signed-off-by: Al Viro --- include/linux/audit.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 6272a395d43c..1b2a6a5c1876 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -391,6 +391,7 @@ extern int audit_classify_arch(int arch); #ifdef CONFIG_AUDITSYSCALL /* These are defined in auditsc.c */ /* Public API */ +extern void audit_finish_fork(struct task_struct *child); extern int audit_alloc(struct task_struct *task); extern void audit_free(struct task_struct *task); extern void audit_syscall_entry(int arch, @@ -504,6 +505,7 @@ static inline int audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) extern int audit_n_rules; extern int audit_signals; #else +#define audit_finish_fork(t) #define audit_alloc(t) ({ 0; }) #define audit_free(t) do { ; } while (0) #define audit_syscall_entry(ta,a,b,c,d,e) do { ; } while (0) -- cgit v1.2.3 From 48887e63d6e057543067327da6b091297f7fe645 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 6 Dec 2008 01:05:50 -0500 Subject: [PATCH] fix broken timestamps in AVC generated by kernel threads Timestamp in audit_context is valid only if ->in_syscall is set. Signed-off-by: Al Viro --- include/linux/audit.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 1b2a6a5c1876..8f0672d13eb1 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -435,7 +435,7 @@ static inline void audit_ptrace(struct task_struct *t) /* Private API (for audit.c only) */ extern unsigned int audit_serial(void); -extern void auditsc_get_stamp(struct audit_context *ctx, +extern int auditsc_get_stamp(struct audit_context *ctx, struct timespec *t, unsigned int *serial); extern int audit_set_loginuid(struct task_struct *task, uid_t loginuid); #define audit_get_loginuid(t) ((t)->loginuid) @@ -518,7 +518,7 @@ extern int audit_signals; #define audit_inode(n,d) do { ; } while (0) #define audit_inode_child(d,i,p) do { ; } while (0) #define audit_core_dumps(i) do { ; } while (0) -#define auditsc_get_stamp(c,t,s) do { BUG(); } while (0) +#define auditsc_get_stamp(c,t,s) (0) #define audit_get_loginuid(t) (-1) #define audit_get_sessionid(t) (-1) #define audit_log_task_context(b) do { ; } while (0) -- cgit v1.2.3 From 7b363e440021a1cf9ed76944b2685f48dacefb3e Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Tue, 9 Dec 2008 23:22:26 -0800 Subject: netpoll: fix race on poll_list resulting in garbage entry A few months back a race was discused between the netpoll napi service path, and the fast path through net_rx_action: http://kerneltrap.org/mailarchive/linux-netdev/2007/10/16/345470 A patch was submitted for that bug, but I think we missed a case. Consider the following scenario: INITIAL STATE CPU0 has one napi_struct A on its poll_list CPU1 is calling netpoll_send_skb and needs to call poll_napi on the same napi_struct A that CPU0 has on its list CPU0 CPU1 net_rx_action poll_napi !list_empty (returns true) locks poll_lock for A poll_one_napi napi->poll netif_rx_complete __napi_complete (removes A from poll_list) list_entry(list->next) In the above scenario, net_rx_action assumes that the per-cpu poll_list is exclusive to that cpu. netpoll of course violates that, and because the netpoll path can dequeue from the poll list, its possible for CPU0 to detect a non-empty list at the top of the while loop in net_rx_action, but have it become empty by the time it calls list_entry. Since the poll_list isn't surrounded by any other structure, the returned data from that list_entry call in this situation is garbage, and any number of crashes can result based on what exactly that garbage is. Given that its not fasible for performance reasons to place exclusive locks arround each cpus poll list to provide that mutal exclusion, I think the best solution is modify the netpoll path in such a way that we continue to guarantee that the poll_list for a cpu is in fact exclusive to that cpu. To do this I've implemented the patch below. It adds an additional bit to the state field in the napi_struct. When executing napi->poll from the netpoll_path, this bit will be set. When a driver calls netif_rx_complete, if that bit is set, it will not remove the napi_struct from the poll_list. That work will be saved for the next iteration of net_rx_action. I've tested this and it seems to work well. About the biggest drawback I can see to it is the fact that it might result in an extra loop through net_rx_action in the event that the device is actually contended for (i.e. the netpoll path actually preforms all the needed work no the device, and the call to net_rx_action winds up doing nothing, except removing the napi_struct from the poll_list. However I think this is probably a small price to pay, given that the alternative is a crash. Signed-off-by: Neil Horman Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9d77b1d7dca8..e26f54952892 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -319,6 +319,7 @@ enum { NAPI_STATE_SCHED, /* Poll is scheduled */ NAPI_STATE_DISABLE, /* Disable pending */ + NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ }; extern void __napi_schedule(struct napi_struct *n); @@ -1497,6 +1498,12 @@ static inline void netif_rx_complete(struct net_device *dev, { unsigned long flags; + /* + * don't let napi dequeue from the cpu poll list + * just in case its running on a different cpu + */ + if (unlikely(test_bit(NAPI_STATE_NPSVC, &napi->state))) + return; local_irq_save(flags); __netif_rx_complete(dev, napi); local_irq_restore(flags); -- cgit v1.2.3 From 71c5576fbd809f2015f4eddf72e501e298720cf3 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 9 Dec 2008 13:14:13 -0800 Subject: revert "percpu counter: clean up percpu_counter_sum_and_set()" Revert commit 1f7c14c62ce63805f9574664a6c6de3633d4a354 Author: Mingming Cao Date: Thu Oct 9 12:50:59 2008 -0400 percpu counter: clean up percpu_counter_sum_and_set() Before this patch we had the following: percpu_counter_sum(): return the percpu_counter's value percpu_counter_sum_and_set(): return the percpu_counter's value, copying that value into the central value and zeroing the per-cpu counters before returning. After this patch, percpu_counter_sum_and_set() has gone, and percpu_counter_sum() gets the old percpu_counter_sum_and_set() functionality. Problem is, as Eric points out, the old percpu_counter_sum_and_set() functionality was racy and wrong. It zeroes out counters on "other" cpus, without holding any locks which will prevent races agaist updates from those other CPUS. This patch reverts 1f7c14c62ce63805f9574664a6c6de3633d4a354. This means that percpu_counter_sum_and_set() still has the race, but percpu_counter_sum() does not. Note that this is not a simple revert - ext4 has since started using percpu_counter_sum() for its dirty_blocks counter as well. Note that this revert patch changes percpu_counter_sum() semantics. Before the patch, a call to percpu_counter_sum() will bring the counter's central counter mostly up-to-date, so a following percpu_counter_read() will return a close value. After this patch, a call to percpu_counter_sum() will leave the counter's central accumulator unaltered, so a subsequent call to percpu_counter_read() can now return a significantly inaccurate result. If there is any code in the tree which was introduced after e8ced39d5e8911c662d4d69a342b9d053eaaac4e was merged, and which depends upon the new percpu_counter_sum() semantics, that code will break. Reported-by: Eric Dumazet Cc: "David S. Miller" Cc: Peter Zijlstra Cc: Mingming Cao Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/percpu_counter.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 9007ccdfc112..208388835357 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -35,7 +35,7 @@ int percpu_counter_init_irq(struct percpu_counter *fbc, s64 amount); void percpu_counter_destroy(struct percpu_counter *fbc); void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch); -s64 __percpu_counter_sum(struct percpu_counter *fbc); +s64 __percpu_counter_sum(struct percpu_counter *fbc, int set); static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { @@ -44,13 +44,19 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { - s64 ret = __percpu_counter_sum(fbc); + s64 ret = __percpu_counter_sum(fbc, 0); return ret < 0 ? 0 : ret; } +static inline s64 percpu_counter_sum_and_set(struct percpu_counter *fbc) +{ + return __percpu_counter_sum(fbc, 1); +} + + static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { - return __percpu_counter_sum(fbc); + return __percpu_counter_sum(fbc, 0); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) -- cgit v1.2.3 From 02d211688727ad02bb4555b1aa8ae2de16b21b39 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 9 Dec 2008 13:14:14 -0800 Subject: revert "percpu_counter: new function percpu_counter_sum_and_set" Revert commit e8ced39d5e8911c662d4d69a342b9d053eaaac4e Author: Mingming Cao Date: Fri Jul 11 19:27:31 2008 -0400 percpu_counter: new function percpu_counter_sum_and_set As described in revert "percpu counter: clean up percpu_counter_sum_and_set()" the new percpu_counter_sum_and_set() is racy against updates to the cpu-local accumulators on other CPUs. Revert that change. This means that ext4 will be slow again. But correct. Reported-by: Eric Dumazet Cc: "David S. Miller" Cc: Peter Zijlstra Cc: Mingming Cao Cc: Cc: [2.6.27.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/percpu_counter.h | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 208388835357..9007ccdfc112 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -35,7 +35,7 @@ int percpu_counter_init_irq(struct percpu_counter *fbc, s64 amount); void percpu_counter_destroy(struct percpu_counter *fbc); void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch); -s64 __percpu_counter_sum(struct percpu_counter *fbc, int set); +s64 __percpu_counter_sum(struct percpu_counter *fbc); static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { @@ -44,19 +44,13 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { - s64 ret = __percpu_counter_sum(fbc, 0); + s64 ret = __percpu_counter_sum(fbc); return ret < 0 ? 0 : ret; } -static inline s64 percpu_counter_sum_and_set(struct percpu_counter *fbc) -{ - return __percpu_counter_sum(fbc, 1); -} - - static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { - return __percpu_counter_sum(fbc, 0); + return __percpu_counter_sum(fbc); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) -- cgit v1.2.3 From 9c24624727f6d6c460e45762a408ca5f5b9b8ef2 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 9 Dec 2008 13:14:27 -0800 Subject: KSYM_SYMBOL_LEN fixes Miles Lane tailing /sys files hit a BUG which Pekka Enberg has tracked to my 966c8c12dc9e77f931e2281ba25d2f0244b06949 sprint_symbol(): use less stack exposing a bug in slub's list_locations() - kallsyms_lookup() writes a 0 to namebuf[KSYM_NAME_LEN-1], but that was beyond the end of page provided. The 100 slop which list_locations() allows at end of page looks roughly enough for all the other stuff it might print after the symbol before it checks again: break out KSYM_SYMBOL_LEN earlier than before. Latencytop and ftrace and are using KSYM_NAME_LEN buffers where they need KSYM_SYMBOL_LEN buffers, and vmallocinfo a 2*KSYM_NAME_LEN buffer where it wants a KSYM_SYMBOL_LEN buffer: fix those before anyone copies them. [akpm@linux-foundation.org: ftrace.h needs module.h] Signed-off-by: Hugh Dickins Cc: Christoph Lameter Cc Miles Lane Acked-by: Pekka Enberg Acked-by: Steven Rostedt Acked-by: Frederic Weisbecker Cc: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ftrace.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 703eb53cfa2b..9c5bc6be2b09 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -6,6 +6,7 @@ #include #include #include +#include #include #ifdef CONFIG_FUNCTION_TRACER @@ -231,7 +232,7 @@ ftrace_init_module(unsigned long *start, unsigned long *end) { } struct boot_trace { pid_t caller; - char func[KSYM_NAME_LEN]; + char func[KSYM_SYMBOL_LEN]; int result; unsigned long long duration; /* usecs */ ktime_t calltime; -- cgit v1.2.3 From d2ff911882b6bc693d86ca9566daac70aacbb2b3 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 15 Dec 2008 19:04:35 +1030 Subject: Define smp_call_function_many for UP Otherwise those using it in transition patches (eg. kvm) can't compile with CONFIG_SMP=n: arch/x86/kvm/../../../virt/kvm/kvm_main.c: In function 'make_all_cpus_request': arch/x86/kvm/../../../virt/kvm/kvm_main.c:380: error: implicit declaration of function 'smp_call_function_many' Signed-off-by: Rusty Russell Signed-off-by: Linus Torvalds --- include/linux/smp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index 3f9a60043a97..6e7ba16ff454 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -146,6 +146,8 @@ static inline void smp_send_reschedule(int cpu) { } }) #define smp_call_function_mask(mask, func, info, wait) \ (up_smp_call_function(func, info)) +#define smp_call_function_many(mask, func, info, wait) \ + (up_smp_call_function(func, info)) static inline void init_call_single_data(void) { } -- cgit v1.2.3 From 9a9fafb89433c5fd1331bac0c84c4b321e358b42 Mon Sep 17 00:00:00 2001 From: Phil Endecott Date: Mon, 1 Dec 2008 10:22:33 -0500 Subject: USB: fix comment about endianness of descriptors This patch fixes a comment and clarifies the documentation about the endianness of descriptors. The current policy is that descriptors will be little-endian at the API even on big-endian systems; however the /proc/bus/usb API predates this policy and presents descriptors with some multibyte fields byte-swapped. Signed-off-by: Phil Endecott Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ch9.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h index 73a2f4eb1f7a..9b42baed3900 100644 --- a/include/linux/usb/ch9.h +++ b/include/linux/usb/ch9.h @@ -158,8 +158,12 @@ struct usb_ctrlrequest { * (rarely) accepted by SET_DESCRIPTOR. * * Note that all multi-byte values here are encoded in little endian - * byte order "on the wire". But when exposed through Linux-USB APIs, - * they've been converted to cpu byte order. + * byte order "on the wire". Within the kernel and when exposed + * through the Linux-USB APIs, they are not converted to cpu byte + * order; it is the responsibility of the client code to do this. + * The single exception is when device and configuration descriptors (but + * not other descriptors) are read from usbfs (i.e. /proc/bus/usb/BBB/DDD); + * in this case the fields are converted to host endianness by the kernel. */ /* -- cgit v1.2.3