From 27fed4175acf81ddd91d9a4ee2fd298981f60295 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Mon, 27 Jul 2009 18:39:45 -0700 Subject: ip: fix logic of reverse path filter sysctl Even though reverse path filter was changed from simple boolean to trinary control, the loose mode only works if both all and device are configured because of this logic error. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index acef2a770b6b..ad27c7da8798 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -82,7 +82,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) #define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING) -#define IN_DEV_RPFILTER(in_dev) IN_DEV_ANDCONF((in_dev), RP_FILTER) +#define IN_DEV_RPFILTER(in_dev) IN_DEV_MAXCONF((in_dev), RP_FILTER) #define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \ ACCEPT_SOURCE_ROUTE) #define IN_DEV_BOOTP_RELAY(in_dev) IN_DEV_ANDCONF((in_dev), BOOTP_RELAY) -- cgit v1.2.3 From 7c958e32649e0c35801762878fb0b6da8c55a515 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 31 Jul 2009 11:49:11 -0400 Subject: block: Add a wrapper for setting minimum request size without a queue Introduce blk_limits_io_min() and make blk_queue_io_min() call it. Signed-off-by: Mike Snitzer Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- 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 e7cb5dbf6c26..69103e053c92 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -913,6 +913,7 @@ extern void blk_queue_logical_block_size(struct request_queue *, unsigned short) extern void blk_queue_physical_block_size(struct request_queue *, unsigned short); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); +extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt); extern void blk_set_default_limits(struct queue_limits *lim); -- cgit v1.2.3 From 9f498cc5be7e013d8d6e4c616980ed0ffc8680d2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 23 Jul 2009 14:46:33 +0200 Subject: perf_counter: Full task tracing In order to be able to distinguish between no samples due to inactivity and no samples due to task ended, Arjan asked for PERF_EVENT_EXIT events. This is useful to the boot delay instrumentation (bootchart) app. This patch changes the PERF_EVENT_FORK to be emitted on every clone, and adds PERF_EVENT_EXIT to be emitted on task exit, after the task's counters have been closed. This task tracing is controlled through: attr.comm || attr.mmap and through the new attr.task field. Suggested-by: Arjan van de Ven Cc: Paul Mackerras Cc: Anton Blanchard Signed-off-by: Peter Zijlstra [ cleaned up perf_counter.h a bit ] Signed-off-by: Ingo Molnar --- include/linux/perf_counter.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h index bd15d7a5f5ce..e604e6ef72dd 100644 --- a/include/linux/perf_counter.h +++ b/include/linux/perf_counter.h @@ -181,8 +181,9 @@ struct perf_counter_attr { freq : 1, /* use freq, not period */ inherit_stat : 1, /* per task counts */ enable_on_exec : 1, /* next exec enables */ + task : 1, /* trace fork/exit */ - __reserved_1 : 51; + __reserved_1 : 50; __u32 wakeup_events; /* wakeup every n events */ __u32 __reserved_2; @@ -308,6 +309,15 @@ enum perf_event_type { */ PERF_EVENT_COMM = 3, + /* + * struct { + * struct perf_event_header header; + * u32 pid, ppid; + * u32 tid, ptid; + * }; + */ + PERF_EVENT_EXIT = 4, + /* * struct { * struct perf_event_header header; @@ -323,6 +333,7 @@ enum perf_event_type { * struct { * struct perf_event_header header; * u32 pid, ppid; + * u32 tid, ptid; * }; */ PERF_EVENT_FORK = 7, -- cgit v1.2.3 From 7699ad35ed06044c4fc1be162553880f98658616 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Mon, 15 Jun 2009 01:10:18 -0400 Subject: mtd: let include/linux/mtd/partitions.h stand on its own When declaring static MTD partitions in board specific code, only including should suffice without gcc nagging us with: In file included from arch/arm/mach-kirkwood/sheevaplug-setup.c:14: include/linux/mtd/partitions.h:50: warning: 'struct mtd_info' declared inside parameter list include/linux/mtd/partitions.h:50: warning: its scope is only this definition or declaration, which is probably not what you want include/linux/mtd/partitions.h:51: warning: 'struct mtd_info' declared inside parameter list include/linux/mtd/partitions.h:61: warning: 'struct mtd_info' declared inside parameter list include/linux/mtd/partitions.h:67: warning: 'struct mtd_info' declared inside parameter list Signed-off-by: Nicolas Pitre Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/partitions.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index af6dcb992bc3..b70313d33ff8 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -47,6 +47,8 @@ struct mtd_partition { #define MTDPART_SIZ_FULL (0) +struct mtd_info; + int add_mtd_partitions(struct mtd_info *, const struct mtd_partition *, int); int del_mtd_partitions(struct mtd_info *); -- cgit v1.2.3 From 6afc4fdb3e94ba60cd566cb878b60c6c01979277 Mon Sep 17 00:00:00 2001 From: Saeed Bishara Date: Tue, 28 Jul 2009 04:56:43 -0700 Subject: mtd: fix the conversion from dev to mtd_info The patch fixes a bug when converting dev to mtd_info by using the drvdata of the dev, the previous code used container_of(dev, struct mtd_info, dev), but won't work for the mtdXro devices as they created without being contained inside mtd_info structure. Signed-off-by: Saeed Bishara Signed-off-by: David Woodhouse --- include/linux/mtd/mtd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 5675b63a0631..0f32a9b6ff55 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -251,7 +251,7 @@ struct mtd_info { static inline struct mtd_info *dev_to_mtd(struct device *dev) { - return dev ? container_of(dev, struct mtd_info, dev) : NULL; + return dev ? dev_get_drvdata(dev) : NULL; } static inline uint32_t mtd_div_by_eb(uint64_t sz, struct mtd_info *mtd) -- cgit v1.2.3 From 18eac1cc100fa2afd5f39085aae6b694e417734b Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 3 Aug 2009 10:58:29 -0700 Subject: tty-ldisc: make refcount be atomic_t 'users' count This is pure preparation of changing the ldisc reference counting to be a true refcount that defines the lifetime of the ldisc. But this is a purely syntactic change for now to make the next steps easier. This patch should make no semantic changes at all. But I wanted to make the ldisc refcount be an atomic (I will be touching it without locks soon enough), and I wanted to rename it so that there isn't quite as much confusion between 'ldo->refcount' (ldisk operations refcount) and 'ld->refcount' (ldisc refcount itself) in the same file. So it's now an atomic 'ld->users' count. It still starts at zero, despite having a reference from 'tty->ldisc', but that will change once we turn it into a _real_ refcount. Signed-off-by: Linus Torvalds Tested-by: OGAWA Hirofumi Tested-by: Sergey Senozhatsky Acked-by: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_ldisc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 40f38d896777..0c4ee9b88f85 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -144,7 +144,7 @@ struct tty_ldisc_ops { struct tty_ldisc { struct tty_ldisc_ops *ops; - int refcount; + atomic_t users; }; #define TTY_LDISC_MAGIC 0x5403 -- cgit v1.2.3 From 5116d8f6b977970ebefc1932c0f313163a6ec91f Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Sun, 26 Jul 2009 17:10:01 +0300 Subject: KVM: fix ack not being delivered when msi present kvm_notify_acked_irq does not check irq type, so that it sometimes interprets msi vector as irq. As a result, ack notifiers are not called, which typially hangs the guest. The fix is to track and check irq type. Signed-off-by: Michael S. Tsirkin Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 16713dc672e4..3060bdc35ffe 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -110,6 +110,7 @@ struct kvm_memory_slot { struct kvm_kernel_irq_routing_entry { u32 gsi; + u32 type; int (*set)(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int level); union { -- cgit v1.2.3 From af6af30c0fcd77e621638e53ef8b176bca8bd3b4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 5 Aug 2009 20:41:04 +0200 Subject: ftrace: Fix perf-tracepoint OOPS Not all tracepoints are created equal, in specific the ftrace tracepoints are created with TRACE_EVENT_FORMAT() which does not generate the needed bits to tie them into perf counters. For those events, don't create the 'id' file and fail ->profile_enable when their ID is specified through other means. Reported-by: Chris Mason Signed-off-by: Peter Zijlstra Cc: Steven Rostedt LKML-Reference: <1249497664.5890.4.camel@laptop> [ v2: fix build error in the !CONFIG_EVENT_PROFILE case ] Signed-off-by: Ingo Molnar --- include/linux/ftrace_event.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 5c093ffc655b..d7cd193c2277 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -119,11 +119,9 @@ struct ftrace_event_call { void *filter; void *mod; -#ifdef CONFIG_EVENT_PROFILE - atomic_t profile_count; - int (*profile_enable)(struct ftrace_event_call *); - void (*profile_disable)(struct ftrace_event_call *); -#endif + atomic_t profile_count; + int (*profile_enable)(struct ftrace_event_call *); + void (*profile_disable)(struct ftrace_event_call *); }; #define MAX_FILTER_PRED 32 -- cgit v1.2.3 From d82f1c35348cebe2fb2d4a4d31ce0ab0769e3d93 Mon Sep 17 00:00:00 2001 From: Eric Miao Date: Wed, 5 Aug 2009 01:24:41 -0700 Subject: Input: matrix_keypad - make matrix keymap size dynamic Remove assumption on the shift and size of rows/columns form matrix_keypad driver. Signed-off-by: Eric Miao Signed-off-by: Dmitry Torokhov --- include/linux/input/matrix_keypad.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/input/matrix_keypad.h b/include/linux/input/matrix_keypad.h index 7964516c6954..15d5903af2dd 100644 --- a/include/linux/input/matrix_keypad.h +++ b/include/linux/input/matrix_keypad.h @@ -15,12 +15,13 @@ #define KEY_COL(k) (((k) >> 16) & 0xff) #define KEY_VAL(k) ((k) & 0xffff) +#define MATRIX_SCAN_CODE(row, col, row_shift) (((row) << (row_shift)) + (col)) + /** * struct matrix_keymap_data - keymap for matrix keyboards * @keymap: pointer to array of uint32 values encoded with KEY() macro * representing keymap * @keymap_size: number of entries (initialized) in this keymap - * @max_keymap_size: maximum size of keymap supported by the device * * This structure is supposed to be used by platform code to supply * keymaps to drivers that implement matrix-like keypads/keyboards. @@ -28,14 +29,13 @@ struct matrix_keymap_data { const uint32_t *keymap; unsigned int keymap_size; - unsigned int max_keymap_size; }; /** * struct matrix_keypad_platform_data - platform-dependent keypad data * @keymap_data: pointer to &matrix_keymap_data - * @row_gpios: array of gpio numbers reporesenting rows - * @col_gpios: array of gpio numbers reporesenting colums + * @row_gpios: pointer to array of gpio numbers representing rows + * @col_gpios: pointer to array of gpio numbers reporesenting colums * @num_row_gpios: actual number of row gpios used by device * @num_col_gpios: actual number of col gpios used by device * @col_scan_delay_us: delay, measured in microseconds, that is @@ -48,8 +48,9 @@ struct matrix_keymap_data { struct matrix_keypad_platform_data { const struct matrix_keymap_data *keymap_data; - unsigned int row_gpios[MATRIX_MAX_ROWS]; - unsigned int col_gpios[MATRIX_MAX_COLS]; + const unsigned int *row_gpios; + const unsigned int *col_gpios; + unsigned int num_row_gpios; unsigned int num_col_gpios; -- cgit v1.2.3 From 54e346215e4fe2ca8c94c54e546cc61902060510 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 7 Aug 2009 14:38:25 -0300 Subject: vfs: fix inode_init_always calling convention Currently inode_init_always calls into ->destroy_inode if the additional initialization fails. That's not only counter-intuitive because inode_init_always did not allocate the inode structure, but in case of XFS it's actively harmful as ->destroy_inode might delete the inode from a radix-tree that has never been added. This in turn might end up deleting the inode for the same inum that has been instanciated by another process and cause lots of cause subtile problems. Also in the case of re-initializing a reclaimable inode in XFS it would free an inode we still want to keep alive. Signed-off-by: Christoph Hellwig Reviewed-by: Eric Sandeen --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index a36ffa5a77a4..0c3b5e58a986 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2137,7 +2137,7 @@ extern loff_t default_llseek(struct file *file, loff_t offset, int origin); extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin); -extern struct inode * inode_init_always(struct super_block *, struct inode *); +extern int inode_init_always(struct super_block *, struct inode *); extern void inode_init_once(struct inode *); extern void inode_add_to_lists(struct super_block *, struct inode *); extern void iput(struct inode *); -- cgit v1.2.3 From 2e00c97e2c1d2ffc9e26252ca26b237678b0b772 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 7 Aug 2009 14:38:29 -0300 Subject: vfs: add __destroy_inode When we want to tear down an inode that lost the add to the cache race in XFS we must not call into ->destroy_inode because that would delete the inode that won the race from the inode cache radix tree. This patch provides the __destroy_inode helper needed to fix this, the actual fix will be in th next patch. As XFS was the only reason destroy_inode was exported we shift the export to the new __destroy_inode. Signed-off-by: Christoph Hellwig Reviewed-by: Eric Sandeen --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 0c3b5e58a986..67888a9e0655 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2164,6 +2164,7 @@ extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); extern void destroy_inode(struct inode *); +extern void __destroy_inode(struct inode *); extern struct inode *new_inode(struct super_block *); extern int should_remove_suid(struct dentry *); extern int file_remove_suid(struct file *); -- cgit v1.2.3 From 4bfc44958e499af9a73f62201543b3a1f617cfeb Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Thu, 6 Aug 2009 15:07:33 -0700 Subject: mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware At first, init_task's mems_allowed is initialized as this. init_task->mems_allowed == node_state[N_POSSIBLE] And cpuset's top_cpuset mask is initialized as this top_cpuset->mems_allowed = node_state[N_HIGH_MEMORY] Before 2.6.29: policy's mems_allowed is initialized as this. 1. update tasks->mems_allowed by its cpuset->mems_allowed. 2. policy->mems_allowed = nodes_and(tasks->mems_allowed, user's mask) Updating task's mems_allowed in reference to top_cpuset's one. cpuset's mems_allowed is aware of N_HIGH_MEMORY, always. In 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c ("cpuset,mm: update tasks' mems_allowed in time"), policy's mems_allowed is initialized as this. 1. policy->mems_allowd = nodes_and(task->mems_allowed, user's mask) Here, if task is in top_cpuset, task->mems_allowed is not updated from init's one. Assume user excutes command as #numactrl --interleave=all ,.... policy->mems_allowd = nodes_and(N_POSSIBLE, ALL_SET_MASK) Then, policy's mems_allowd can includes a possible node, which has no pgdat. MPOL's INTERLEAVE just scans nodemask of task->mems_allowd and access this directly. NODE_DATA(nid)->zonelist even if NODE_DATA(nid)==NULL Then, what's we need is making policy->mems_allowed be aware of N_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will be on statck. Because I know cpumask has a new interface of CPUMASK_ALLOC(), I added it to node. This patch stands on old behavior. But I feel this fix itself is just a Band-Aid. But to do fundametal fix, we have to take care of memory hotplug and it takes time. (task->mems_allowd should be N_HIGH_MEMORY, I think.) mpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy's nodemask should be includes only online nodes. In old behavior, this is guaranteed by frequent reference to cpuset's code. Now, most of them are removed and mempolicy has to check it by itself. To do check, a few nodemask_t will be used for calculating nodemask. But, size of nodemask_t can be big and it's not good to allocate them on stack. Now, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area. NODEMASK_ALLOC/FREE shoudl be there. [akpm@linux-foundation.org: cleanups & tweaks] Tested-by: KOSAKI Motohiro Signed-off-by: KAMEZAWA Hiroyuki Cc: Miao Xie Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Christoph Lameter Cc: Paul Menage Cc: Nick Piggin Cc: Yasunori Goto Cc: Pekka Enberg Cc: David Rientjes Cc: Lee Schermerhorn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nodemask.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 829b94b156f2..b359c4a9ec9e 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -82,6 +82,12 @@ * to generate slightly worse code. So use a simple one-line #define * for node_isset(), instead of wrapping an inline inside a macro, the * way we do the other calls. + * + * NODEMASK_SCRATCH + * When doing above logical AND, OR, XOR, Remap operations the callers tend to + * need temporary nodemask_t's on the stack. But if NODES_SHIFT is large, + * nodemask_t's consume too much stack space. NODEMASK_SCRATCH is a helper + * for such situations. See below and CPUMASK_ALLOC also. */ #include @@ -473,4 +479,26 @@ static inline int num_node_state(enum node_states state) #define for_each_node(node) for_each_node_state(node, N_POSSIBLE) #define for_each_online_node(node) for_each_node_state(node, N_ONLINE) +/* + * For nodemask scrach area.(See CPUMASK_ALLOC() in cpumask.h) + */ + +#if NODES_SHIFT > 8 /* nodemask_t > 64 bytes */ +#define NODEMASK_ALLOC(x, m) struct x *m = kmalloc(sizeof(*m), GFP_KERNEL) +#define NODEMASK_FREE(m) kfree(m) +#else +#define NODEMASK_ALLOC(x, m) struct x _m, *m = &_m +#define NODEMASK_FREE(m) +#endif + +/* A example struture for using NODEMASK_ALLOC, used in mempolicy. */ +struct nodemask_scratch { + nodemask_t mask1; + nodemask_t mask2; +}; + +#define NODEMASK_SCRATCH(x) NODEMASK_ALLOC(nodemask_scratch, x) +#define NODEMASK_SCRATCH_FREE(x) NODEMASK_FREE(x) + + #endif /* __LINUX_NODEMASK_H */ -- cgit v1.2.3 From daeb6b6fbe27049f465c48a7d0ee5555c3b84064 Mon Sep 17 00:00:00 2001 From: Phillip Lougher Date: Thu, 6 Aug 2009 15:09:30 -0700 Subject: bzip2/lzma/gzip: fix comments describing decompressor API Fix and improve comments in decompress/generic.h that describe the decompressor API. Also remove an unused definition, and rename INBUF_LEN in lib/decompress_inflate.c to conform to bzip2/lzma naming. Signed-off-by: Phillip Lougher Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/decompress/generic.h | 32 +++++++++++++++++++------------- 1 file changed, 19 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/decompress/generic.h b/include/linux/decompress/generic.h index 6dfb856327bb..0c7111a55a1a 100644 --- a/include/linux/decompress/generic.h +++ b/include/linux/decompress/generic.h @@ -1,31 +1,37 @@ #ifndef DECOMPRESS_GENERIC_H #define DECOMPRESS_GENERIC_H -/* Minimal chunksize to be read. - *Bzip2 prefers at least 4096 - *Lzma prefers 0x10000 */ -#define COMPR_IOBUF_SIZE 4096 - typedef int (*decompress_fn) (unsigned char *inbuf, int len, int(*fill)(void*, unsigned int), - int(*writebb)(void*, unsigned int), - unsigned char *output, + int(*flush)(void*, unsigned int), + unsigned char *outbuf, int *posp, void(*error)(char *x)); /* inbuf - input buffer *len - len of pre-read data in inbuf - *fill - function to fill inbuf if empty - *writebb - function to write out outbug + *fill - function to fill inbuf when empty + *flush - function to write out outbuf + *outbuf - output buffer *posp - if non-null, input position (number of bytes read) will be * returned here * - *If len != 0, the inbuf is initialized (with as much data), and fill - *should not be called - *If len = 0, the inbuf is allocated, but empty. Its size is IOBUF_SIZE - *fill should be called (repeatedly...) to read data, at most IOBUF_SIZE + *If len != 0, inbuf should contain all the necessary input data, and fill + *should be NULL + *If len = 0, inbuf can be NULL, in which case the decompressor will allocate + *the input buffer. If inbuf != NULL it must be at least XXX_IOBUF_SIZE bytes. + *fill will be called (repeatedly...) to read data, at most XXX_IOBUF_SIZE + *bytes should be read per call. Replace XXX with the appropriate decompressor + *name, i.e. LZMA_IOBUF_SIZE. + * + *If flush = NULL, outbuf must be large enough to buffer all the expected + *output. If flush != NULL, the output buffer will be allocated by the + *decompressor (outbuf = NULL), and the flush function will be called to + *flush the output buffer at the appropriate time (decompressor and stream + *dependent). */ + /* Utility routine to detect the decompression method */ decompress_fn decompress_method(const unsigned char *inbuf, int len, const char **name); -- cgit v1.2.3 From f413cdb80ce00ec1a4d0ab949b5d96c81cae7f75 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 7 Aug 2009 01:25:54 +0200 Subject: perf_counter: Fix/complete ftrace event records sampling This patch implements the kernel side support for ftrace event record sampling. A new counter sampling attribute is added: PERF_SAMPLE_TP_RECORD which requests ftrace events record sampling. In this case if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint fires, we emit the tracepoint binary record to the perfcounter event buffer, as a sample. Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf record: perf record -f -F 1 -a -e workqueue:workqueue_execution perf report -D 0x21e18 [0x48]: event: 9 . . ... raw event: size 72 bytes . 0000: 09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff ......H........ . 0010: 0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00 ........!...... . 0020: 2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e +...........eve . 0030: 74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00 ts/1........... . 0040: e0 b1 31 81 ff ff ff ff ....... . 0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33 The raw ftrace binary record starts at offset 0020. Translation: struct trace_entry { type = 0x2b = 43; flags = 1; preempt_count = 2; pid = 0xa = 10; tgid = 0xa = 10; } thread_comm = "events/1" thread_pid = 0xa = 10; func = 0xffffffff8131b1e0 = flush_to_ldisc() What will come next? - Userspace support ('perf trace'), 'flight data recorder' mode for perf trace, etc. - The unconditional copy from the profiling callback brings some costs however if someone wants no such sampling to occur, and needs to be fixed in the future. For that we need to have an instant access to the perf counter attribute. This is a matter of a flag to add in the struct ftrace_event. - Take care of the events recursivity! Don't ever try to record a lock event for example, it seems some locking is used in the profiling fast path and lead to a tracing recursivity. That will be fixed using raw spinlock or recursivity protection. - [...] - Profit! :-) Signed-off-by: Frederic Weisbecker Cc: Li Zefan Cc: Tom Zanussi Cc: Arnaldo Carvalho de Melo Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Steven Rostedt Cc: Paul Mackerras Cc: Pekka Enberg Cc: Gabriel Munteanu Cc: Lai Jiangshan Signed-off-by: Ingo Molnar --- include/linux/ftrace_event.h | 4 +++- include/linux/perf_counter.h | 9 ++++++++- 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index d7cd193c2277..a81170de7f6b 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -89,7 +89,9 @@ enum print_line_t { TRACE_TYPE_NO_CONSUME = 3 /* Handled but ask to not consume */ }; - +void tracing_generic_entry_update(struct trace_entry *entry, + unsigned long flags, + int pc); struct ring_buffer_event * trace_current_buffer_lock_reserve(int type, unsigned long len, unsigned long flags, int pc); diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h index e604e6ef72dd..a67dd5c5b6d3 100644 --- a/include/linux/perf_counter.h +++ b/include/linux/perf_counter.h @@ -121,8 +121,9 @@ enum perf_counter_sample_format { PERF_SAMPLE_CPU = 1U << 7, PERF_SAMPLE_PERIOD = 1U << 8, PERF_SAMPLE_STREAM_ID = 1U << 9, + PERF_SAMPLE_TP_RECORD = 1U << 10, - PERF_SAMPLE_MAX = 1U << 10, /* non-ABI */ + PERF_SAMPLE_MAX = 1U << 11, /* non-ABI */ }; /* @@ -413,6 +414,11 @@ struct perf_callchain_entry { __u64 ip[PERF_MAX_STACK_DEPTH]; }; +struct perf_tracepoint_record { + int size; + char *record; +}; + struct task_struct; /** @@ -681,6 +687,7 @@ struct perf_sample_data { struct pt_regs *regs; u64 addr; u64 period; + void *private; }; extern int perf_counter_overflow(struct perf_counter *counter, int nmi, -- cgit v1.2.3 From 3a43ce68ae1758fa6a839386025ef45acb6baa22 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 8 Aug 2009 04:26:37 +0200 Subject: perf_counter: Fix tracepoint sampling to be part of generic sampling Based on Peter's comments, make tracepoint sampling generic just like all the other sampling bits are. This is a rename with no code changes: - PERF_SAMPLE_TP_RECORD to PERF_SAMPLE_RAW - struct perf_tracepoint_record to perf_raw_record We want the system in place that transport tracepoints raw samples events into the perf ring buffer to be generalized and usable by any type of counter. Reported-by; Peter Zijlstra Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Mike Galbraith Cc: Paul Mackerras LKML-Reference: <1249698400-5441-4-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- include/linux/perf_counter.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h index a67dd5c5b6d3..2aabe43c1d04 100644 --- a/include/linux/perf_counter.h +++ b/include/linux/perf_counter.h @@ -121,7 +121,7 @@ enum perf_counter_sample_format { PERF_SAMPLE_CPU = 1U << 7, PERF_SAMPLE_PERIOD = 1U << 8, PERF_SAMPLE_STREAM_ID = 1U << 9, - PERF_SAMPLE_TP_RECORD = 1U << 10, + PERF_SAMPLE_RAW = 1U << 10, PERF_SAMPLE_MAX = 1U << 11, /* non-ABI */ }; @@ -414,9 +414,9 @@ struct perf_callchain_entry { __u64 ip[PERF_MAX_STACK_DEPTH]; }; -struct perf_tracepoint_record { - int size; - char *record; +struct perf_raw_record { + u32 size; + void *data; }; struct task_struct; @@ -687,7 +687,7 @@ struct perf_sample_data { struct pt_regs *regs; u64 addr; u64 period; - void *private; + struct perf_raw_record *raw; }; extern int perf_counter_overflow(struct perf_counter *counter, int nmi, -- cgit v1.2.3 From a044560c3a1f0ad75ce685c1ed7604820b9ed319 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 10 Aug 2009 11:16:52 +0200 Subject: perf_counter: Correct PERF_SAMPLE_RAW output PERF_SAMPLE_* output switches should unconditionally output the correct format, as they are the only way to unambiguously parse the PERF_EVENT_SAMPLE data. Signed-off-by: Peter Zijlstra Acked-by: Frederic Weisbecker Cc: Arnaldo Carvalho de Melo Cc: Mike Galbraith Cc: Paul Mackerras LKML-Reference: <1249896447.17467.74.camel@twins> Signed-off-by: Ingo Molnar --- include/linux/perf_counter.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h index 2aabe43c1d04..a9d823a93fe8 100644 --- a/include/linux/perf_counter.h +++ b/include/linux/perf_counter.h @@ -369,6 +369,8 @@ enum perf_event_type { * * { u64 nr, * u64 ips[nr]; } && PERF_SAMPLE_CALLCHAIN + * { u32 size; + * char data[size];}&& PERF_SAMPLE_RAW * }; */ PERF_EVENT_SAMPLE = 9, -- cgit v1.2.3 From 2fc391112fb6f3424435a3aa2fda887497b5f807 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 10 Aug 2009 12:33:05 +0100 Subject: locking, sched: Give waitqueue spinlocks their own lockdep classes Give waitqueue spinlocks their own lockdep classes when they are initialised from init_waitqueue_head(). This means that struct wait_queue::func functions can operate other waitqueues. This is used by CacheFiles to catch the page from a backing fs being unlocked and to wake up another thread to take a copy of it. Signed-off-by: Peter Zijlstra Signed-off-by: David Howells Tested-by: Takashi Iwai Cc: linux-cachefs@redhat.com Cc: torvalds@osdl.org Cc: akpm@linux-foundation.org LKML-Reference: <20090810113305.17284.81508.stgit@warthog.procyon.org.uk> Signed-off-by: Ingo Molnar --- include/linux/wait.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 6788e1a4d4ca..cf3c2f5dba51 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -77,7 +77,14 @@ struct task_struct; #define __WAIT_BIT_KEY_INITIALIZER(word, bit) \ { .flags = word, .bit_nr = bit, } -extern void init_waitqueue_head(wait_queue_head_t *q); +extern void __init_waitqueue_head(wait_queue_head_t *q, struct lock_class_key *); + +#define init_waitqueue_head(q) \ + do { \ + static struct lock_class_key __key; \ + \ + __init_waitqueue_head((q), &__key); \ + } while (0) #ifdef CONFIG_LOCKDEP # define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \ -- cgit v1.2.3 From 1ae88b2e446261c038f2c0c3150ffae142b227a2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 12 Aug 2009 09:12:30 -0400 Subject: NFS: Fix an O_DIRECT Oops... We can't call nfs_readdata_release()/nfs_writedata_release() without first initialising and referencing args.context. Doing so inside nfs_direct_read_schedule_segment()/nfs_direct_write_schedule_segment() causes an Oops. We should rather be calling nfs_readdata_free()/nfs_writedata_free() in those cases. Looking at the O_DIRECT code, the "struct nfs_direct_req" is already referencing the nfs_open_context for us. Since the readdata and writedata structures carry a reference to that, we can simplify things by getting rid of the extra nfs_open_context references, so that we can replace all instances of nfs_readdata_release()/nfs_writedata_release(). Reported-by: Catalin Marinas Signed-off-by: Trond Myklebust Tested-by: Catalin Marinas Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/linux/nfs_fs.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index fdffb413b192..f6b90240dd41 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -473,7 +473,6 @@ extern int nfs_writepages(struct address_space *, struct writeback_control *); extern int nfs_flush_incompatible(struct file *file, struct page *page); extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned int); extern int nfs_writeback_done(struct rpc_task *, struct nfs_write_data *); -extern void nfs_writedata_release(void *); /* * Try to write back everything synchronously (but check the @@ -488,7 +487,6 @@ extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_write_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_write_data *wdata); -extern void nfs_commitdata_release(void *wdata); #else static inline int nfs_commit_inode(struct inode *inode, int how) @@ -507,6 +505,7 @@ nfs_have_writebacks(struct inode *inode) * Allocate nfs_write_data structures */ extern struct nfs_write_data *nfs_writedata_alloc(unsigned int npages); +extern void nfs_writedata_free(struct nfs_write_data *); /* * linux/fs/nfs/read.c @@ -515,7 +514,6 @@ extern int nfs_readpage(struct file *, struct page *); extern int nfs_readpages(struct file *, struct address_space *, struct list_head *, unsigned); extern int nfs_readpage_result(struct rpc_task *, struct nfs_read_data *); -extern void nfs_readdata_release(void *data); extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, struct page *); @@ -523,6 +521,7 @@ extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, * Allocate nfs_read_data structures */ extern struct nfs_read_data *nfs_readdata_alloc(unsigned int npages); +extern void nfs_readdata_free(struct nfs_read_data *); /* * linux/fs/nfs3proc.c -- cgit v1.2.3 From 28402971d869e26271b25301011f667d3a5640c3 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 13 Aug 2009 10:13:22 +0200 Subject: perf_counter: Provide hw_perf_counter_setup_online() APIs Provide weak aliases for hw_perf_counter_setup_online(). This is used by the BTS patches (for v2.6.32), but it interacts with fixes so propagate this upstream. (it has no effect as of yet) Also export perf_counter_output() to architecture code. Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Frederic Weisbecker LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/perf_counter.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h index a9d823a93fe8..2b36afe6ae0f 100644 --- a/include/linux/perf_counter.h +++ b/include/linux/perf_counter.h @@ -694,6 +694,8 @@ struct perf_sample_data { extern int perf_counter_overflow(struct perf_counter *counter, int nmi, struct perf_sample_data *data); +extern void perf_counter_output(struct perf_counter *counter, int nmi, + struct perf_sample_data *data); /* * Return 1 for a software counter, 0 for a hardware counter -- cgit v1.2.3 From 3dab77fb1bf89664bb1c9544607159dcab6f7d57 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 13 Aug 2009 11:47:53 +0200 Subject: perf: Rework/fix the whole read vs group stuff Replace PERF_SAMPLE_GROUP with PERF_SAMPLE_READ and introduce PERF_FORMAT_GROUP to deal with group reads in a more generic way. This allows you to get group reads out of read() as well. Signed-off-by: Peter Zijlstra Cc: Corey J Ashford Cc: Paul Mackerras Cc: stephane eranian LKML-Reference: <20090813103655.117411814@chello.nl> Signed-off-by: Ingo Molnar --- include/linux/perf_counter.h | 47 +++++++++++++++++++++++++++++++++----------- 1 file changed, 36 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h index 2b36afe6ae0f..b53f7006cc4e 100644 --- a/include/linux/perf_counter.h +++ b/include/linux/perf_counter.h @@ -115,7 +115,7 @@ enum perf_counter_sample_format { PERF_SAMPLE_TID = 1U << 1, PERF_SAMPLE_TIME = 1U << 2, PERF_SAMPLE_ADDR = 1U << 3, - PERF_SAMPLE_GROUP = 1U << 4, + PERF_SAMPLE_READ = 1U << 4, PERF_SAMPLE_CALLCHAIN = 1U << 5, PERF_SAMPLE_ID = 1U << 6, PERF_SAMPLE_CPU = 1U << 7, @@ -127,16 +127,32 @@ enum perf_counter_sample_format { }; /* - * Bits that can be set in attr.read_format to request that - * reads on the counter should return the indicated quantities, - * in increasing order of bit value, after the counter value. + * The format of the data returned by read() on a perf counter fd, + * as specified by attr.read_format: + * + * struct read_format { + * { u64 value; + * { u64 time_enabled; } && PERF_FORMAT_ENABLED + * { u64 time_running; } && PERF_FORMAT_RUNNING + * { u64 id; } && PERF_FORMAT_ID + * } && !PERF_FORMAT_GROUP + * + * { u64 nr; + * { u64 time_enabled; } && PERF_FORMAT_ENABLED + * { u64 time_running; } && PERF_FORMAT_RUNNING + * { u64 value; + * { u64 id; } && PERF_FORMAT_ID + * } cntr[nr]; + * } && PERF_FORMAT_GROUP + * }; */ enum perf_counter_read_format { PERF_FORMAT_TOTAL_TIME_ENABLED = 1U << 0, PERF_FORMAT_TOTAL_TIME_RUNNING = 1U << 1, PERF_FORMAT_ID = 1U << 2, + PERF_FORMAT_GROUP = 1U << 3, - PERF_FORMAT_MAX = 1U << 3, /* non-ABI */ + PERF_FORMAT_MAX = 1U << 4, /* non-ABI */ }; #define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */ @@ -343,10 +359,8 @@ enum perf_event_type { * struct { * struct perf_event_header header; * u32 pid, tid; - * u64 value; - * { u64 time_enabled; } && PERF_FORMAT_ENABLED - * { u64 time_running; } && PERF_FORMAT_RUNNING - * { u64 parent_id; } && PERF_FORMAT_ID + * + * struct read_format values; * }; */ PERF_EVENT_READ = 8, @@ -364,11 +378,22 @@ enum perf_event_type { * { u32 cpu, res; } && PERF_SAMPLE_CPU * { u64 period; } && PERF_SAMPLE_PERIOD * - * { u64 nr; - * { u64 id, val; } cnt[nr]; } && PERF_SAMPLE_GROUP + * { struct read_format values; } && PERF_SAMPLE_READ * * { u64 nr, * u64 ips[nr]; } && PERF_SAMPLE_CALLCHAIN + * + * # + * # The RAW record below is opaque data wrt the ABI + * # + * # That is, the ABI doesn't make any promises wrt to + * # the stability of its content, it may vary depending + * # on event, hardware, kernel version and phase of + * # the moon. + * # + * # In other words, PERF_SAMPLE_RAW contents are not an ABI. + * # + * * { u32 size; * char data[size];}&& PERF_SAMPLE_RAW * }; -- cgit v1.2.3 From 9c0d90103c7e0eb6e638e5b649e9f6d8d9c1b4b3 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 31 Jul 2009 12:53:58 -0400 Subject: Capabilities: move cap_file_mmap to commoncap.c Currently we duplicate the mmap_min_addr test in cap_file_mmap and in security_file_mmap if !CONFIG_SECURITY. This patch moves cap_file_mmap into commoncap.c and then calls that function directly from security_file_mmap ifndef CONFIG_SECURITY like all of the other capability checks are done. Signed-off-by: Eric Paris Acked-by: Serge Hallyn Signed-off-by: James Morris --- include/linux/security.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 5eff459b3833..ac4bc3760b46 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -66,6 +66,9 @@ extern int cap_inode_setxattr(struct dentry *dentry, const char *name, extern int cap_inode_removexattr(struct dentry *dentry, const char *name); extern int cap_inode_need_killpriv(struct dentry *dentry); extern int cap_inode_killpriv(struct dentry *dentry); +extern int cap_file_mmap(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags, + unsigned long addr, unsigned long addr_only); extern int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags); extern int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5); @@ -2197,9 +2200,7 @@ static inline int security_file_mmap(struct file *file, unsigned long reqprot, unsigned long addr, unsigned long addr_only) { - if ((addr < mmap_min_addr) && !capable(CAP_SYS_RAWIO)) - return -EACCES; - return 0; + return cap_file_mmap(file, reqprot, prot, flags, addr, addr_only); } static inline int security_file_mprotect(struct vm_area_struct *vma, -- cgit v1.2.3 From 788084aba2ab7348257597496befcbccabdc98a3 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 31 Jul 2009 12:54:11 -0400 Subject: Security/SELinux: seperate lsm specific mmap_min_addr Currently SELinux enforcement of controls on the ability to map low memory is determined by the mmap_min_addr tunable. This patch causes SELinux to ignore the tunable and instead use a seperate Kconfig option specific to how much space the LSM should protect. The tunable will now only control the need for CAP_SYS_RAWIO and SELinux permissions will always protect the amount of low memory designated by CONFIG_LSM_MMAP_MIN_ADDR. This allows users who need to disable the mmap_min_addr controls (usual reason being they run WINE as a non-root user) to do so and still have SELinux controls preventing confined domains (like a web server) from being able to map some area of low memory. Signed-off-by: Eric Paris Signed-off-by: James Morris --- include/linux/mm.h | 15 --------------- include/linux/security.h | 17 +++++++++++++++++ 2 files changed, 17 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ba3a7cb1eaa0..9a72cc78e6b8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -34,8 +34,6 @@ extern int sysctl_legacy_va_layout; #define sysctl_legacy_va_layout 0 #endif -extern unsigned long mmap_min_addr; - #include #include #include @@ -574,19 +572,6 @@ static inline void set_page_links(struct page *page, enum zone_type zone, set_page_section(page, pfn_to_section_nr(pfn)); } -/* - * If a hint addr is less than mmap_min_addr change hint to be as - * low as possible but still greater than mmap_min_addr - */ -static inline unsigned long round_hint_to_min(unsigned long hint) -{ - hint &= PAGE_MASK; - if (((void *)hint != NULL) && - (hint < mmap_min_addr)) - return PAGE_ALIGN(mmap_min_addr); - return hint; -} - /* * Some inline functions in vmstat.h depend on page_zone() */ diff --git a/include/linux/security.h b/include/linux/security.h index ac4bc3760b46..dc3472c1f781 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -28,6 +28,7 @@ #include #include #include +#include /* PAGE_ALIGN */ #include #include #include @@ -95,6 +96,7 @@ extern int cap_netlink_send(struct sock *sk, struct sk_buff *skb); extern int cap_netlink_recv(struct sk_buff *skb, int cap); extern unsigned long mmap_min_addr; +extern unsigned long dac_mmap_min_addr; /* * Values used in the task_security_ops calls */ @@ -147,6 +149,21 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) opts->num_mnt_opts = 0; } +/* + * If a hint addr is less than mmap_min_addr change hint to be as + * low as possible but still greater than mmap_min_addr + */ +static inline unsigned long round_hint_to_min(unsigned long hint) +{ + hint &= PAGE_MASK; + if (((void *)hint != NULL) && + (hint < mmap_min_addr)) + return PAGE_ALIGN(mmap_min_addr); + return hint; +} + +extern int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos); /** * struct security_operations - main security structure * -- cgit v1.2.3 From 1d9959734a1949ea4f2427bd2d8b21ede6b2441c Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 7 Aug 2009 14:53:57 -0400 Subject: security: define round_hint_to_min in !CONFIG_SECURITY Fix the header files to define round_hint_to_min() and to define mmap_min_addr_handler() in the !CONFIG_SECURITY case. Built and tested with !CONFIG_SECURITY Signed-off-by: Eric Paris Signed-off-by: James Morris --- include/linux/security.h | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index dc3472c1f781..1f16eea2017b 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -121,6 +121,21 @@ struct request_sock; #define LSM_UNSAFE_PTRACE 2 #define LSM_UNSAFE_PTRACE_CAP 4 +/* + * If a hint addr is less than mmap_min_addr change hint to be as + * low as possible but still greater than mmap_min_addr + */ +static inline unsigned long round_hint_to_min(unsigned long hint) +{ + hint &= PAGE_MASK; + if (((void *)hint != NULL) && + (hint < mmap_min_addr)) + return PAGE_ALIGN(mmap_min_addr); + return hint; +} +extern int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos); + #ifdef CONFIG_SECURITY struct security_mnt_opts { @@ -149,21 +164,6 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) opts->num_mnt_opts = 0; } -/* - * If a hint addr is less than mmap_min_addr change hint to be as - * low as possible but still greater than mmap_min_addr - */ -static inline unsigned long round_hint_to_min(unsigned long hint) -{ - hint &= PAGE_MASK; - if (((void *)hint != NULL) && - (hint < mmap_min_addr)) - return PAGE_ALIGN(mmap_min_addr); - return hint; -} - -extern int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos); /** * struct security_operations - main security structure * -- cgit v1.2.3 From c1a8f1f1c8e01eab5862c8db39b49ace814e6c66 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 16 Aug 2009 09:36:49 +0000 Subject: net: restore gnet_stats_basic to previous definition In 5e140dfc1fe87eae27846f193086724806b33c7d "net: reorder struct Qdisc for better SMP performance" the definition of struct gnet_stats_basic changed incompatibly, as copies of this struct are shipped to userland via netlink. Restoring old behavior is not welcome, for performance reason. Fix is to use a private structure for kernel, and teach gnet_stats_copy_basic() to convert from kernel to user land, using legacy structure (struct gnet_stats_basic) Based on a report and initial patch from Michael Spang. Reported-by: Michael Spang Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/gen_stats.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gen_stats.h b/include/linux/gen_stats.h index 0ffa41df0ee8..710e901085d0 100644 --- a/include/linux/gen_stats.h +++ b/include/linux/gen_stats.h @@ -19,6 +19,11 @@ enum { * @packets: number of seen packets */ struct gnet_stats_basic +{ + __u64 bytes; + __u32 packets; +}; +struct gnet_stats_basic_packed { __u64 bytes; __u32 packets; -- cgit v1.2.3 From 0753ba01e126020bf0f8150934903b48935b697d Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Tue, 18 Aug 2009 14:11:10 -0700 Subject: mm: revert "oom: move oom_adj value" The commit 2ff05b2b (oom: move oom_adj value) moveed the oom_adj value to the mm_struct. It was a very good first step for sanitize OOM. However Paul Menage reported the commit makes regression to his job scheduler. Current OOM logic can kill OOM_DISABLED process. Why? His program has the code of similar to the following. ... set_oom_adj(OOM_DISABLE); /* The job scheduler never killed by oom */ ... if (vfork() == 0) { set_oom_adj(0); /* Invoked child can be killed */ execve("foo-bar-cmd"); } .... vfork() parent and child are shared the same mm_struct. then above set_oom_adj(0) doesn't only change oom_adj for vfork() child, it's also change oom_adj for vfork() parent. Then, vfork() parent (job scheduler) lost OOM immune and it was killed. Actually, fork-setting-exec idiom is very frequently used in userland program. We must not break this assumption. Then, this patch revert commit 2ff05b2b and related commit. Reverted commit list --------------------- - commit 2ff05b2b4e (oom: move oom_adj value from task_struct to mm_struct) - commit 4d8b9135c3 (oom: avoid unnecessary mm locking and scanning for OOM_DISABLE) - commit 8123681022 (oom: only oom kill exiting tasks with attached memory) - commit 933b787b57 (mm: copy over oom_adj value at fork time) Signed-off-by: KOSAKI Motohiro Cc: Paul Menage Cc: David Rientjes Cc: KAMEZAWA Hiroyuki Cc: Rik van Riel Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Nick Piggin Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 -- include/linux/sched.h | 1 + 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7acc8439d9b3..0042090a4d70 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -240,8 +240,6 @@ struct mm_struct { unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ - s8 oom_adj; /* OOM kill score adjustment (bit shift) */ - cpumask_t cpu_vm_mask; /* Architecture-specific MM context */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 3ab08e4bb6b8..0f1ea4a66957 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1198,6 +1198,7 @@ struct task_struct { * a short time */ unsigned char fpu_counter; + s8 oomkilladj; /* OOM kill score adjustment (bit shift). */ #ifdef CONFIG_BLK_DEV_IO_TRACE unsigned int btrace_seq; #endif -- cgit v1.2.3 From 1700f5fde88f9a251037bc86bde538ee32c59905 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 20 Aug 2009 22:05:53 -0700 Subject: Input: ucb1400_ts - enable ADC Filter This patch enables ADC filtering on UCB1400 codec by default. The benefit from this change is mostly on some Colibri boards where the ADCSYNC pin of the UCB1400 codec isn't connected causing the touchscreen to jitter very badly. This change has no visible effect on boards where the ADCSYNC pin is connected. Signed-off-by: Marek Vasut Tested-by: Palo Revak Signed-off-by: Dmitry Torokhov --- include/linux/ucb1400.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ucb1400.h b/include/linux/ucb1400.h index ed889f4168f3..ae779bb8cc0f 100644 --- a/include/linux/ucb1400.h +++ b/include/linux/ucb1400.h @@ -73,6 +73,10 @@ #define UCB_ADC_DATA 0x68 #define UCB_ADC_DAT_VALID (1 << 15) + +#define UCB_FCSR 0x6c +#define UCB_FCSR_AVE (1 << 12) + #define UCB_ADC_DAT_MASK 0x3ff #define UCB_ID 0x7e -- cgit v1.2.3 From f4b0373b26567cafd421d91101852ed7a34e9e94 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 21 Aug 2009 09:26:15 -0700 Subject: Make bitmask 'and' operators return a result code When 'and'ing two bitmasks (where 'andnot' is a variation on it), some cases want to know whether the result is the empty set or not. In particular, the TLB IPI sending code wants to do cpumask operations and determine if there are any CPU's left in the final set. So this just makes the bitmask (and cpumask) functions return a boolean for whether the result has any bits set. Cc: stable@kernel.org (2.6.30, needed by TLB shootdown fix) Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 18 ++++++++---------- include/linux/cpumask.h | 20 ++++++++++---------- 2 files changed, 18 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 2878811c6134..756d78b8c1c5 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -94,13 +94,13 @@ extern void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, int shift, int bits); extern void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, int shift, int bits); -extern void __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, +extern int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); extern void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); extern void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); -extern void __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, +extern int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); extern int __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); @@ -171,13 +171,12 @@ static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, } } -static inline void bitmap_and(unsigned long *dst, const unsigned long *src1, +static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, int nbits) { if (small_const_nbits(nbits)) - *dst = *src1 & *src2; - else - __bitmap_and(dst, src1, src2, nbits); + return (*dst = *src1 & *src2) != 0; + return __bitmap_and(dst, src1, src2, nbits); } static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, @@ -198,13 +197,12 @@ static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, __bitmap_xor(dst, src1, src2, nbits); } -static inline void bitmap_andnot(unsigned long *dst, const unsigned long *src1, +static inline int bitmap_andnot(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, int nbits) { if (small_const_nbits(nbits)) - *dst = *src1 & ~(*src2); - else - __bitmap_andnot(dst, src1, src2, nbits); + return (*dst = *src1 & ~(*src2)) != 0; + return __bitmap_andnot(dst, src1, src2, nbits); } static inline void bitmap_complement(unsigned long *dst, const unsigned long *src, diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index c5ac87ca7bc6..796df12091b7 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -43,10 +43,10 @@ * int cpu_isset(cpu, mask) true iff bit 'cpu' set in mask * int cpu_test_and_set(cpu, mask) test and set bit 'cpu' in mask * - * void cpus_and(dst, src1, src2) dst = src1 & src2 [intersection] + * int cpus_and(dst, src1, src2) dst = src1 & src2 [intersection] * void cpus_or(dst, src1, src2) dst = src1 | src2 [union] * void cpus_xor(dst, src1, src2) dst = src1 ^ src2 - * void cpus_andnot(dst, src1, src2) dst = src1 & ~src2 + * int cpus_andnot(dst, src1, src2) dst = src1 & ~src2 * void cpus_complement(dst, src) dst = ~src * * int cpus_equal(mask1, mask2) Does mask1 == mask2? @@ -179,10 +179,10 @@ static inline int __cpu_test_and_set(int cpu, cpumask_t *addr) } #define cpus_and(dst, src1, src2) __cpus_and(&(dst), &(src1), &(src2), NR_CPUS) -static inline void __cpus_and(cpumask_t *dstp, const cpumask_t *src1p, +static inline int __cpus_and(cpumask_t *dstp, const cpumask_t *src1p, const cpumask_t *src2p, int nbits) { - bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); + return bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); } #define cpus_or(dst, src1, src2) __cpus_or(&(dst), &(src1), &(src2), NR_CPUS) @@ -201,10 +201,10 @@ static inline void __cpus_xor(cpumask_t *dstp, const cpumask_t *src1p, #define cpus_andnot(dst, src1, src2) \ __cpus_andnot(&(dst), &(src1), &(src2), NR_CPUS) -static inline void __cpus_andnot(cpumask_t *dstp, const cpumask_t *src1p, +static inline int __cpus_andnot(cpumask_t *dstp, const cpumask_t *src1p, const cpumask_t *src2p, int nbits) { - bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); + return bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); } #define cpus_complement(dst, src) __cpus_complement(&(dst), &(src), NR_CPUS) @@ -738,11 +738,11 @@ static inline void cpumask_clear(struct cpumask *dstp) * @src1p: the first input * @src2p: the second input */ -static inline void cpumask_and(struct cpumask *dstp, +static inline int cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { - bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), + return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } @@ -779,11 +779,11 @@ static inline void cpumask_xor(struct cpumask *dstp, * @src1p: the first input * @src2p: the second input */ -static inline void cpumask_andnot(struct cpumask *dstp, +static inline int cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { - bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), + return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } -- cgit v1.2.3 From 6777d773a463ac045d333b989d4e44660f8d92ad Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Fri, 21 Aug 2009 14:32:48 -0400 Subject: kernel_read: redefine offset type vfs_read() offset is defined as loff_t, but kernel_read() offset is only defined as unsigned long. Redefine kernel_read() offset as loff_t. Cc: stable@kernel.org Signed-off-by: Mimi Zohar Signed-off-by: James Morris --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 67888a9e0655..73e9b643e455 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2123,7 +2123,7 @@ extern struct file *do_filp_open(int dfd, const char *pathname, int open_flag, int mode, int acc_mode); extern int may_open(struct path *, int, int); -extern int kernel_read(struct file *, unsigned long, char *, unsigned long); +extern int kernel_read(struct file *, loff_t, char *, unsigned long); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ -- cgit v1.2.3 From 353d5c30c666580347515da609dd74a2b8e9b828 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 24 Aug 2009 16:30:28 +0100 Subject: mm: fix hugetlb bug due to user_shm_unlock call 2.6.30's commit 8a0bdec194c21c8fdef840989d0d7b742bb5d4bc removed user_shm_lock() calls in hugetlb_file_setup() but left the user_shm_unlock call in shm_destroy(). In detail: Assume that can_do_hugetlb_shm() returns true and hence user_shm_lock() is not called in hugetlb_file_setup(). However, user_shm_unlock() is called in any case in shm_destroy() and in the following atomic_dec_and_lock(&up->__count) in free_uid() is executed and if up->__count gets zero, also cleanup_user_struct() is scheduled. Note that sched_destroy_user() is empty if CONFIG_USER_SCHED is not set. However, the ref counter up->__count gets unexpectedly non-positive and the corresponding structs are freed even though there are live references to them, resulting in a kernel oops after a lots of shmget(SHM_HUGETLB)/shmctl(IPC_RMID) cycles and CONFIG_USER_SCHED set. Hugh changed Stefan's suggested patch: can_do_hugetlb_shm() at the time of shm_destroy() may give a different answer from at the time of hugetlb_file_setup(). And fixed newseg()'s no_id error path, which has missed user_shm_unlock() ever since it came in 2.6.9. Reported-by: Stefan Huber Signed-off-by: Hugh Dickins Tested-by: Stefan Huber Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 2723513a5651..5cbc620bdfe0 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -10,6 +10,7 @@ #include struct ctl_table; +struct user_struct; int PageHuge(struct page *page); @@ -146,7 +147,8 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) extern const struct file_operations hugetlbfs_file_operations; extern struct vm_operations_struct hugetlb_vm_ops; -struct file *hugetlb_file_setup(const char *name, size_t, int); +struct file *hugetlb_file_setup(const char *name, size_t size, int acct, + struct user_struct **user); int hugetlb_get_quota(struct address_space *mapping, long delta); void hugetlb_put_quota(struct address_space *mapping, long delta); @@ -168,7 +170,7 @@ static inline void set_file_hugepages(struct file *file) #define is_file_hugepages(file) 0 #define set_file_hugepages(file) BUG() -#define hugetlb_file_setup(name,size,acctflag) ERR_PTR(-ENOSYS) +#define hugetlb_file_setup(name,size,acct,user) ERR_PTR(-ENOSYS) #endif /* !CONFIG_HUGETLBFS */ -- cgit v1.2.3 From 8e7ee27095aee87b5db1b0061e2ceea5878a1bbd Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Wed, 26 Aug 2009 14:29:21 -0700 Subject: flex_array: declare parts member to have incomplete type The `parts' member of struct flex_array should evaluate to an incomplete type so that sizeof() cannot be used and C99 does not require the zero-length specification. Signed-off-by: David Rientjes Acked-by: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/flex_array.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/flex_array.h b/include/linux/flex_array.h index 23c1ec79a31b..603160db7c98 100644 --- a/include/linux/flex_array.h +++ b/include/linux/flex_array.h @@ -21,7 +21,7 @@ struct flex_array { struct { int element_size; int total_nr_elements; - struct flex_array_part *parts[0]; + struct flex_array_part *parts[]; }; /* * This little trick makes sure that -- cgit v1.2.3 From b62e408c05228f40e69bb38a48db8961cac6cd23 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Wed, 26 Aug 2009 14:29:22 -0700 Subject: flex_array: convert element_nr formals to unsigned It's problematic to allow signed element_nr's or total's to be passed as part of the flex array API. flex_array_alloc() allows total_nr_elements to be set to a negative quantity, which is obviously erroneous. flex_array_get() and flex_array_put() allows negative array indices in dereferencing an array part, which could address memory mapped before struct flex_array. The fix is to convert all existing element_nr formals to be qualified as unsigned. Existing checks to compare it to total_nr_elements or the max array size based on element_size need not be changed. Signed-off-by: David Rientjes Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/flex_array.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/flex_array.h b/include/linux/flex_array.h index 603160db7c98..45ff18491514 100644 --- a/include/linux/flex_array.h +++ b/include/linux/flex_array.h @@ -36,12 +36,14 @@ struct flex_array { .total_nr_elements = (total), \ } } } -struct flex_array *flex_array_alloc(int element_size, int total, gfp_t flags); -int flex_array_prealloc(struct flex_array *fa, int start, int end, gfp_t flags); +struct flex_array *flex_array_alloc(int element_size, unsigned int total, + gfp_t flags); +int flex_array_prealloc(struct flex_array *fa, unsigned int start, + unsigned int end, gfp_t flags); void flex_array_free(struct flex_array *fa); void flex_array_free_parts(struct flex_array *fa); -int flex_array_put(struct flex_array *fa, int element_nr, void *src, +int flex_array_put(struct flex_array *fa, unsigned int element_nr, void *src, gfp_t flags); -void *flex_array_get(struct flex_array *fa, int element_nr); +void *flex_array_get(struct flex_array *fa, unsigned int element_nr); #endif /* _FLEX_ARRAY_H */ -- cgit v1.2.3