From d1f8297a96b0d70f17704296a6666468f2087ce6 Mon Sep 17 00:00:00 2001 From: Sascha Hlusiak Date: Sat, 26 Sep 2009 20:28:07 -0700 Subject: Revert "sit: stateless autoconf for isatap" This reverts commit 645069299a1c7358cf7330afe293f07552f11a5d. While the code does not actually break anything, it does not completely follow RFC5214 yet. After talking back with Fred L. Templin, I agree that completing the ISATAP specific RS/RA code, would pollute the kernel a lot with code that is better implemented in userspace. The kernel should not send RS packages for ISATAP at all. Signed-off-by: Sascha Hlusiak Acked-by: Fred L. Templin Signed-off-by: David S. Miller --- include/linux/if_tunnel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_tunnel.h b/include/linux/if_tunnel.h index 5eb9b0f857e0..5a9aae4adb44 100644 --- a/include/linux/if_tunnel.h +++ b/include/linux/if_tunnel.h @@ -44,7 +44,7 @@ struct ip_tunnel_prl { __u16 flags; __u16 __reserved; __u32 datalen; - __u32 rs_delay; + __u32 __reserved2; /* data follows */ }; -- cgit v1.2.3 From bf6993276f74d46776f35c45ddef29b981b1d1c6 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 30 Sep 2009 00:32:06 -0400 Subject: jbd2: Use tracepoints for history file The /proc/fs/jbd2//history was maintained manually; by using tracepoints, we can get all of the existing functionality of the /proc file plus extra capabilities thanks to the ftrace infrastructure. We save memory as a bonus. Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 27 +++++++-------------------- 1 file changed, 7 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 52695d3dfd0b..f1011f7f3d41 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -464,9 +464,9 @@ struct handle_s */ struct transaction_chp_stats_s { unsigned long cs_chp_time; - unsigned long cs_forced_to_close; - unsigned long cs_written; - unsigned long cs_dropped; + __u32 cs_forced_to_close; + __u32 cs_written; + __u32 cs_dropped; }; /* The transaction_t type is the guts of the journaling mechanism. It @@ -668,23 +668,16 @@ struct transaction_run_stats_s { unsigned long rs_flushing; unsigned long rs_logging; - unsigned long rs_handle_count; - unsigned long rs_blocks; - unsigned long rs_blocks_logged; + __u32 rs_handle_count; + __u32 rs_blocks; + __u32 rs_blocks_logged; }; struct transaction_stats_s { - int ts_type; unsigned long ts_tid; - union { - struct transaction_run_stats_s run; - struct transaction_chp_stats_s chp; - } u; + struct transaction_run_stats_s run; }; -#define JBD2_STATS_RUN 1 -#define JBD2_STATS_CHECKPOINT 2 - static inline unsigned long jbd2_time_diff(unsigned long start, unsigned long end) { @@ -988,12 +981,6 @@ struct journal_s /* * Journal statistics */ - struct transaction_stats_s *j_history; - int j_history_max; - int j_history_cur; - /* - * Protect the transactions statistics history - */ spinlock_t j_history_lock; struct proc_dir_entry *j_proc_entry; struct transaction_stats_s j_stats; -- cgit v1.2.3 From 9fcd66e572b94974365a9119b073e0a43d496eb7 Mon Sep 17 00:00:00 2001 From: Maxime Bizon Date: Fri, 18 Sep 2009 13:04:58 +0200 Subject: MIPS: BCM63xx: Add serial driver for bcm63xx integrated UART. Signed-off-by: Maxime Bizon Acked-by: Greg Kroah-Hartman Signed-off-by: Ralf Baechle --- include/linux/serial_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index fe661afe0713..db532ce288be 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -176,6 +176,9 @@ /* Qualcomm MSM SoCs */ #define PORT_MSM 88 +/* BCM63xx family SoCs */ +#define PORT_BCM63XX 89 + #ifdef __KERNEL__ #include -- cgit v1.2.3 From b7058842c940ad2c08dd829b21e5c92ebe3b8758 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 30 Sep 2009 16:12:20 -0700 Subject: net: Make setsockopt() optlen be unsigned. This provides safety against negative optlen at the type level instead of depending upon (sometimes non-trivial) checks against this sprinkled all over the the place, in each and every implementation. Based upon work done by Arjan van de Ven and feedback from Linus Torvalds. Signed-off-by: David S. Miller --- include/linux/atmdev.h | 2 +- include/linux/mroute.h | 4 ++-- include/linux/mroute6.h | 4 ++-- include/linux/net.h | 8 ++++---- include/linux/netfilter.h | 4 ++-- 5 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index 086e5c362d3a..817b23705c91 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -397,7 +397,7 @@ struct atmdev_ops { /* only send is required */ int (*getsockopt)(struct atm_vcc *vcc,int level,int optname, void __user *optval,int optlen); int (*setsockopt)(struct atm_vcc *vcc,int level,int optname, - void __user *optval,int optlen); + void __user *optval,unsigned int optlen); int (*send)(struct atm_vcc *vcc,struct sk_buff *skb); int (*send_oam)(struct atm_vcc *vcc,void *cell,int flags); void (*phy_put)(struct atm_dev *dev,unsigned char value, diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 0d45b4e8d367..08bc776d05e2 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -145,14 +145,14 @@ static inline int ip_mroute_opt(int opt) #endif #ifdef CONFIG_IP_MROUTE -extern int ip_mroute_setsockopt(struct sock *, int, char __user *, int); +extern int ip_mroute_setsockopt(struct sock *, int, char __user *, unsigned int); extern int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *); extern int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg); extern int ip_mr_init(void); #else static inline int ip_mroute_setsockopt(struct sock *sock, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { return -ENOPROTOOPT; } diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index 43dc97e32183..b191865a6ca3 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -134,7 +134,7 @@ static inline int ip6_mroute_opt(int opt) struct sock; #ifdef CONFIG_IPV6_MROUTE -extern int ip6_mroute_setsockopt(struct sock *, int, char __user *, int); +extern int ip6_mroute_setsockopt(struct sock *, int, char __user *, unsigned int); extern int ip6_mroute_getsockopt(struct sock *, int, char __user *, int __user *); extern int ip6_mr_input(struct sk_buff *skb); extern int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg); @@ -143,7 +143,7 @@ extern void ip6_mr_cleanup(void); #else static inline int ip6_mroute_setsockopt(struct sock *sock, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { return -ENOPROTOOPT; } diff --git a/include/linux/net.h b/include/linux/net.h index 9040a10584f7..529a0931711d 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -178,11 +178,11 @@ struct proto_ops { int (*listen) (struct socket *sock, int len); int (*shutdown) (struct socket *sock, int flags); int (*setsockopt)(struct socket *sock, int level, - int optname, char __user *optval, int optlen); + int optname, char __user *optval, unsigned int optlen); int (*getsockopt)(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); int (*compat_setsockopt)(struct socket *sock, int level, - int optname, char __user *optval, int optlen); + int optname, char __user *optval, unsigned int optlen); int (*compat_getsockopt)(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); int (*sendmsg) (struct kiocb *iocb, struct socket *sock, @@ -256,7 +256,7 @@ extern int kernel_getpeername(struct socket *sock, struct sockaddr *addr, extern int kernel_getsockopt(struct socket *sock, int level, int optname, char *optval, int *optlen); extern int kernel_setsockopt(struct socket *sock, int level, int optname, - char *optval, int optlen); + char *optval, unsigned int optlen); extern int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); extern int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg); @@ -313,7 +313,7 @@ SOCKCALL_WRAP(name, compat_ioctl, (struct socket *sock, unsigned int cmd, \ SOCKCALL_WRAP(name, listen, (struct socket *sock, int len), (sock, len)) \ SOCKCALL_WRAP(name, shutdown, (struct socket *sock, int flags), (sock, flags)) \ SOCKCALL_WRAP(name, setsockopt, (struct socket *sock, int level, int optname, \ - char __user *optval, int optlen), (sock, level, optname, optval, optlen)) \ + char __user *optval, unsigned int optlen), (sock, level, optname, optval, optlen)) \ SOCKCALL_WRAP(name, getsockopt, (struct socket *sock, int level, int optname, \ char __user *optval, int __user *optlen), (sock, level, optname, optval, optlen)) \ SOCKCALL_WRAP(name, sendmsg, (struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t len), \ diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 48cfe51bfddc..6132b5e6d9d3 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -221,12 +221,12 @@ __ret;}) /* Call setsockopt() */ int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, - int len); + unsigned int len); int nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); int compat_nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, - char __user *opt, int len); + char __user *opt, unsigned int len); int compat_nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); -- cgit v1.2.3 From 48c0d4d4c04dd520c55e0fd756fa4e7c83de3d13 Mon Sep 17 00:00:00 2001 From: Zdenek Kabelac Date: Fri, 25 Sep 2009 06:19:26 +0200 Subject: Add missing blk_trace_remove_sysfs to be in pair with blk_trace_init_sysfs Add missing blk_trace_remove_sysfs to be in pair with blk_trace_init_sysfs introduced in commit 1d54ad6da9192fed5dd3b60224d9f2dfea0dcd82. Release kobject also in case the request_fn is NULL. Problem was noticed via kmemleak backtrace when some sysfs entries were note properly destroyed during device removal: unreferenced object 0xffff88001aa76640 (size 80): comm "lvcreate", pid 2120, jiffies 4294885144 hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 f0 65 a7 1a 00 88 ff ff .........e...... 90 66 a7 1a 00 88 ff ff 86 1d 53 81 ff ff ff ff .f........S..... backtrace: [] kmemleak_alloc+0x26/0x60 [] kmem_cache_alloc+0x133/0x1c0 [] sysfs_new_dirent+0x41/0x120 [] sysfs_add_file_mode+0x3c/0xb0 [] internal_create_group+0xc1/0x1a0 [] sysfs_create_group+0x13/0x20 [] blk_trace_init_sysfs+0x14/0x20 [] blk_register_queue+0x3c/0xf0 [] add_disk+0x94/0x160 [] dm_create+0x598/0x6e0 [dm_mod] [] dev_create+0x51/0x350 [dm_mod] [] ctl_ioctl+0x1a3/0x240 [dm_mod] [] dm_compat_ctl_ioctl+0x12/0x20 [dm_mod] [] compat_sys_ioctl+0xcd/0x4f0 [] sysenter_dispatch+0x7/0x2c [] 0xffffffffffffffff Signed-off-by: Zdenek Kabelac Reviewed-by: Li Zefan Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 7e4350ece0f8..622939a23299 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -198,6 +198,7 @@ extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, char __user *arg); extern int blk_trace_startstop(struct request_queue *q, int start); extern int blk_trace_remove(struct request_queue *q); +extern void blk_trace_remove_sysfs(struct device *dev); extern int blk_trace_init_sysfs(struct device *dev); extern struct attribute_group blk_trace_attr_group; @@ -211,6 +212,7 @@ extern struct attribute_group blk_trace_attr_group; # define blk_trace_startstop(q, start) (-ENOTTY) # define blk_trace_remove(q) (-ENOTTY) # define blk_add_trace_msg(q, fmt, ...) do { } while (0) +# define blk_trace_remove_sysfs(struct device *dev) do { } while (0) static inline int blk_trace_init_sysfs(struct device *dev) { return 0; -- cgit v1.2.3 From c15227de132f1295f3db6b7df9079956b1020fd8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Sep 2009 13:52:12 +0200 Subject: block: use normal I/O path for discard requests prepare_discard_fn() was being called in a place where memory allocation was effectively impossible. This makes it inappropriate for all but the most trivial translations of Linux's DISCARD operation to the block command set. Additionally adding a payload there makes the ownership of the bio backing unclear as it's now allocated by the device driver and not the submitter as usual. It is replaced with QUEUE_FLAG_DISCARD which is used to indicate whether the queue supports discard operations or not. blkdev_issue_discard now allocates a one-page, sector-length payload which is the right thing for the common ATA and SCSI implementations. The mtd implementation of prepare_discard_fn() is replaced with simply checking for the request being a discard. Largely based on a previous patch from Matthew Wilcox which did the prepare_discard_fn but not the different payload allocation yet. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e23a86cae5ac..f62d45e87618 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -82,7 +82,6 @@ enum rq_cmd_type_bits { enum { REQ_LB_OP_EJECT = 0x40, /* eject request */ REQ_LB_OP_FLUSH = 0x41, /* flush request */ - REQ_LB_OP_DISCARD = 0x42, /* discard sectors */ }; /* @@ -261,7 +260,6 @@ typedef void (request_fn_proc) (struct request_queue *q); typedef int (make_request_fn) (struct request_queue *q, struct bio *bio); typedef int (prep_rq_fn) (struct request_queue *, struct request *); typedef void (unplug_fn) (struct request_queue *); -typedef int (prepare_discard_fn) (struct request_queue *, struct request *); struct bio_vec; struct bvec_merge_data { @@ -340,7 +338,6 @@ struct request_queue make_request_fn *make_request_fn; prep_rq_fn *prep_rq_fn; unplug_fn *unplug_fn; - prepare_discard_fn *prepare_discard_fn; merge_bvec_fn *merge_bvec_fn; prepare_flush_fn *prepare_flush_fn; softirq_done_fn *softirq_done_fn; @@ -460,6 +457,7 @@ struct request_queue #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 15 /* do IO stats */ #define QUEUE_FLAG_CQ 16 /* hardware does queuing */ +#define QUEUE_FLAG_DISCARD 17 /* supports DISCARD */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_CLUSTER) | \ @@ -591,6 +589,7 @@ enum { #define blk_queue_flushing(q) ((q)->ordseq) #define blk_queue_stackable(q) \ test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags) +#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_fs_request(rq) ((rq)->cmd_type == REQ_TYPE_FS) #define blk_pc_request(rq) ((rq)->cmd_type == REQ_TYPE_BLOCK_PC) @@ -955,7 +954,6 @@ extern void blk_queue_merge_bvec(struct request_queue *, merge_bvec_fn *); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); -extern void blk_queue_set_discard(struct request_queue *, prepare_discard_fn *); extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); -- cgit v1.2.3 From 67efc9258010da35b27b3854d0880c7e193004ed Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Sep 2009 13:54:20 +0200 Subject: block: allow large discard requests Currently we set the bio size to the byte equivalent of the blocks to be trimmed when submitting the initial DISCARD ioctl. That means it is subject to the max_hw_sectors limitation of the HBA which is much lower than the size of a DISCARD request we can support. Add a separate max_discard_sectors tunable to limit the size for discard requests. We limit the max discard request size in bytes to 32bit as that is the limit for bio->bi_size. This could be much larger if we had a way to pass that information through the block layer. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f62d45e87618..1a03b715dfad 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -311,6 +311,7 @@ struct queue_limits { unsigned int alignment_offset; unsigned int io_min; unsigned int io_opt; + unsigned int max_discard_sectors; unsigned short logical_block_size; unsigned short max_hw_segments; @@ -928,6 +929,8 @@ extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short); extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); +extern void blk_queue_max_discard_sectors(struct request_queue *q, + unsigned int max_discard_sectors); 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, -- cgit v1.2.3 From b0da3f0dada78832c9da03ad2152ae76bd9a2496 Mon Sep 17 00:00:00 2001 From: Jun'ichi Nomura Date: Thu, 1 Oct 2009 21:16:13 +0200 Subject: Add a tracepoint for block request remapping Since 2.6.31 now has request-based device-mapper, it's useful to have a tracepoint for request-remapping as well as bio-remapping. This patch adds a tracepoint for request-remapping, trace_block_rq_remap(). Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Cc: Alasdair G Kergon Cc: Li Zefan Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 622939a23299..3b73b9992b26 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -212,7 +212,7 @@ extern struct attribute_group blk_trace_attr_group; # define blk_trace_startstop(q, start) (-ENOTTY) # define blk_trace_remove(q) (-ENOTTY) # define blk_add_trace_msg(q, fmt, ...) do { } while (0) -# define blk_trace_remove_sysfs(struct device *dev) do { } while (0) +# define blk_trace_remove_sysfs(dev) do { } while (0) static inline int blk_trace_init_sysfs(struct device *dev) { return 0; -- cgit v1.2.3 From 828c09509b9695271bcbdc53e9fc9a6a737148d2 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 1 Oct 2009 15:43:56 -0700 Subject: const: constify remaining file_operations [akpm@linux-foundation.org: fix KVM] Signed-off-by: Alexey Dobriyan Acked-by: Mike Frysinger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 2 +- include/linux/fs.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b62bb9294d0c..0008dee66514 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -37,7 +37,7 @@ extern void cgroup_exit(struct task_struct *p, int run_callbacks); extern int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); -extern struct file_operations proc_cgroup_operations; +extern const struct file_operations proc_cgroup_operations; /* Define the enumeration of all cgroup subsystems */ #define SUBSYS(_x) _x ## _subsys_id, diff --git a/include/linux/fs.h b/include/linux/fs.h index 2adaa2529f18..a1e6899d4b6c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2446,7 +2446,7 @@ static int __fops ## _open(struct inode *inode, struct file *file) \ __simple_attr_check_format(__fmt, 0ull); \ return simple_attr_open(inode, file, __get, __set, __fmt); \ } \ -static struct file_operations __fops = { \ +static const struct file_operations __fops = { \ .owner = THIS_MODULE, \ .open = __fops ## _open, \ .release = simple_attr_release, \ -- cgit v1.2.3 From 4e649152cbaa1aedd01821d200ab9d597fe469e4 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Thu, 1 Oct 2009 15:44:11 -0700 Subject: memcg: some modification to softlimit under hierarchical memory reclaim. This patch clean up/fixes for memcg's uncharge soft limit path. Problems: Now, res_counter_charge()/uncharge() handles softlimit information at charge/uncharge and softlimit-check is done when event counter per memcg goes over limit. Now, event counter per memcg is updated only when memory usage is over soft limit. Here, considering hierarchical memcg management, ancesotors should be taken care of. Now, ancerstors(hierarchy) are handled in charge() but not in uncharge(). This is not good. Prolems: 1. memcg's event counter incremented only when softlimit hits. That's bad. It makes event counter hard to be reused for other purpose. 2. At uncharge, only the lowest level rescounter is handled. This is bug. Because ancesotor's event counter is not incremented, children should take care of them. 3. res_counter_uncharge()'s 3rd argument is NULL in most case. ops under res_counter->lock should be small. No "if" sentense is better. Fixes: * Removed soft_limit_xx poitner and checks in charge and uncharge. Do-check-only-when-necessary scheme works enough well without them. * make event-counter of memcg incremented at every charge/uncharge. (per-cpu area will be accessed soon anyway) * All ancestors are checked at soft-limit-check. This is necessary because ancesotor's event counter may never be modified. Then, they should be checked at the same time. Reviewed-by: Daisuke Nishimura Signed-off-by: KAMEZAWA Hiroyuki Cc: Paul Menage Cc: Li Zefan Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/res_counter.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index 731af71cddc9..fcb9884df618 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -114,8 +114,7 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent); int __must_check res_counter_charge_locked(struct res_counter *counter, unsigned long val); int __must_check res_counter_charge(struct res_counter *counter, - unsigned long val, struct res_counter **limit_fail_at, - struct res_counter **soft_limit_at); + unsigned long val, struct res_counter **limit_fail_at); /* * uncharge - tell that some portion of the resource is released @@ -128,8 +127,7 @@ int __must_check res_counter_charge(struct res_counter *counter, */ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val); -void res_counter_uncharge(struct res_counter *counter, unsigned long val, - bool *was_soft_limit_excess); +void res_counter_uncharge(struct res_counter *counter, unsigned long val); static inline bool res_counter_limit_check_locked(struct res_counter *cnt) { -- cgit v1.2.3 From 293500a23f4b0698cb04abfecfc9a954d8ab2742 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Fri, 2 Oct 2009 02:40:04 +0000 Subject: connector: Keep the skb in cn_callback_data Signed-off-by: Philipp Reisner Acked-by: Lars Ellenberg Acked-by: Evgeniy Polyakov Signed-off-by: David S. Miller --- include/linux/connector.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/connector.h b/include/linux/connector.h index 47ebf416f512..05a7a14126d8 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -134,8 +134,8 @@ struct cn_callback_id { struct cn_callback_data { void (*destruct_data) (void *); void *ddata; - - void *callback_priv; + + struct sk_buff *skb; void (*callback) (struct cn_msg *); void *free; -- cgit v1.2.3 From 7069331dbe7155f23966f5944109f909fea0c7e4 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Fri, 2 Oct 2009 02:40:05 +0000 Subject: connector: Provide the sender's credentials to the callback Signed-off-by: Philipp Reisner Acked-by: Lars Ellenberg Acked-by: Evgeniy Polyakov Signed-off-by: David S. Miller --- include/linux/connector.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/connector.h b/include/linux/connector.h index 05a7a14126d8..545728e20b63 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -136,7 +136,7 @@ struct cn_callback_data { void *ddata; struct sk_buff *skb; - void (*callback) (struct cn_msg *); + void (*callback) (struct cn_msg *, struct netlink_skb_parms *); void *free; }; @@ -167,11 +167,11 @@ struct cn_dev { struct cn_queue_dev *cbdev; }; -int cn_add_callback(struct cb_id *, char *, void (*callback) (struct cn_msg *)); +int cn_add_callback(struct cb_id *, char *, void (*callback) (struct cn_msg *, struct netlink_skb_parms *)); void cn_del_callback(struct cb_id *); int cn_netlink_send(struct cn_msg *, u32, gfp_t); -int cn_queue_add_callback(struct cn_queue_dev *dev, char *name, struct cb_id *id, void (*callback)(struct cn_msg *)); +int cn_queue_add_callback(struct cn_queue_dev *dev, char *name, struct cb_id *id, void (*callback)(struct cn_msg *, struct netlink_skb_parms *)); void cn_queue_del_callback(struct cn_queue_dev *dev, struct cb_id *id); int queue_cn_work(struct cn_callback_entry *cbq, struct work_struct *work); -- cgit v1.2.3 From f1489cfb173509a3c13444b46b6c989bad4f5b16 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Fri, 2 Oct 2009 02:40:07 +0000 Subject: connector: Removed the destruct_data callback since it is always kfree_skb() Signed-off-by: Philipp Reisner Acked-by: Lars Ellenberg Acked-by: Evgeniy Polyakov Signed-off-by: David S. Miller --- include/linux/connector.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/connector.h b/include/linux/connector.h index 545728e20b63..3a14615fd35c 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -132,9 +132,6 @@ struct cn_callback_id { }; struct cn_callback_data { - void (*destruct_data) (void *); - void *ddata; - struct sk_buff *skb; void (*callback) (struct cn_msg *, struct netlink_skb_parms *); -- cgit v1.2.3 From 8e2967555571659d2c8a70dd120710110ed7bba4 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 3 Oct 2009 16:26:03 +0200 Subject: cfq-iosched: implement slower async initiate and queue ramp up This slowly ramps up the async queue depth based on the time passed since the sync IO, and doesn't allow async at all until a sync slice period has passed. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1a03b715dfad..a7323930d2ba 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1147,7 +1147,11 @@ static inline void put_dev_sector(Sector p) } struct work_struct; +struct delayed_work; int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); +int kblockd_schedule_delayed_work(struct request_queue *q, + struct delayed_work *work, + unsigned long delay); #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) -- cgit v1.2.3 From ac481c20ef8f6c6f2be75d581863f40c43874ef7 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Sat, 3 Oct 2009 20:52:01 +0200 Subject: block: Topology ioctls Not all users of the topology information want to use libblkid. Provide the topology information through bdev ioctls. Also clarify sector size comments for existing BLK ioctls. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 35 ++++++++++++++++++++++++++++++----- include/linux/fs.h | 4 ++++ 2 files changed, 34 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a7323930d2ba..25119041e034 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1081,25 +1081,37 @@ static inline unsigned int queue_physical_block_size(struct request_queue *q) return q->limits.physical_block_size; } +static inline int bdev_physical_block_size(struct block_device *bdev) +{ + return queue_physical_block_size(bdev_get_queue(bdev)); +} + static inline unsigned int queue_io_min(struct request_queue *q) { return q->limits.io_min; } +static inline int bdev_io_min(struct block_device *bdev) +{ + return queue_io_min(bdev_get_queue(bdev)); +} + static inline unsigned int queue_io_opt(struct request_queue *q) { return q->limits.io_opt; } +static inline int bdev_io_opt(struct block_device *bdev) +{ + return queue_io_opt(bdev_get_queue(bdev)); +} + static inline int queue_alignment_offset(struct request_queue *q) { - if (q && q->limits.misaligned) + if (q->limits.misaligned) return -1; - if (q && q->limits.alignment_offset) - return q->limits.alignment_offset; - - return 0; + return q->limits.alignment_offset; } static inline int queue_sector_alignment_offset(struct request_queue *q, @@ -1109,6 +1121,19 @@ static inline int queue_sector_alignment_offset(struct request_queue *q, & (q->limits.io_min - 1); } +static inline int bdev_alignment_offset(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (q->limits.misaligned) + return -1; + + if (bdev != bdev->bd_contains) + return bdev->bd_part->alignment_offset; + + return q->limits.alignment_offset; +} + static inline int queue_dma_alignment(struct request_queue *q) { return q ? q->dma_alignment : 511; diff --git a/include/linux/fs.h b/include/linux/fs.h index 2adaa2529f18..883eaacfd924 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -300,6 +300,10 @@ struct inodes_stat_t { #define BLKTRACESTOP _IO(0x12,117) #define BLKTRACETEARDOWN _IO(0x12,118) #define BLKDISCARD _IO(0x12,119) +#define BLKIOMIN _IO(0x12,120) +#define BLKIOOPT _IO(0x12,121) +#define BLKALIGNOFF _IO(0x12,122) +#define BLKPBSZGET _IO(0x12,123) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ -- cgit v1.2.3 From 0f78ab9899e9d6acb09d5465def618704255963b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 4 Oct 2009 21:04:38 +0200 Subject: Revert "Seperate read and write statistics of in_flight requests" This reverts commit a9327cac440be4d8333bba975cbbf76045096275. Corrado Zoccolo reports: "with 2.6.32-rc1 I started getting the following strange output from "iostat -kx 2": Linux 2.6.31bisect (et2) 04/10/2009 _i686_ (2 CPU) avg-cpu: %user %nice %system %iowait %steal %idle 10,70 0,00 3,16 15,75 0,00 70,38 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 18,22 0,00 0,67 0,01 14,77 0,02 43,94 0,01 10,53 39043915,03 2629219,87 sdb 60,89 9,68 50,79 3,04 1724,43 50,52 65,95 0,70 13,06 488437,47 2629219,87 avg-cpu: %user %nice %system %iowait %steal %idle 2,72 0,00 0,74 0,00 0,00 96,53 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 6,68 0,00 0,99 0,00 0,00 92,33 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 4,40 0,00 0,73 1,47 0,00 93,40 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 4,00 0,00 3,00 0,00 28,00 18,67 0,06 19,50 333,33 100,00 Global values for service time and utilization are garbage. For interval values, utilization is always 100%, and service time is higher than normal. I bisected it down to: [a9327cac440be4d8333bba975cbbf76045096275] Seperate read and write statistics of in_flight requests and verified that reverting just that commit indeed solves the issue on 2.6.32-rc1." So until this is debugged, revert the bad commit. Signed-off-by: Jens Axboe --- include/linux/genhd.h | 21 +++++++-------------- 1 file changed, 7 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 297df45ffd0a..7beaa21b3880 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -98,7 +98,7 @@ struct hd_struct { int make_it_fail; #endif unsigned long stamp; - int in_flight[2]; + int in_flight; #ifdef CONFIG_SMP struct disk_stats *dkstats; #else @@ -322,23 +322,18 @@ static inline void free_part_stats(struct hd_struct *part) #define part_stat_sub(cpu, gendiskp, field, subnd) \ part_stat_add(cpu, gendiskp, field, -subnd) -static inline void part_inc_in_flight(struct hd_struct *part, int rw) +static inline void part_inc_in_flight(struct hd_struct *part) { - part->in_flight[rw]++; + part->in_flight++; if (part->partno) - part_to_disk(part)->part0.in_flight[rw]++; + part_to_disk(part)->part0.in_flight++; } -static inline void part_dec_in_flight(struct hd_struct *part, int rw) +static inline void part_dec_in_flight(struct hd_struct *part) { - part->in_flight[rw]--; + part->in_flight--; if (part->partno) - part_to_disk(part)->part0.in_flight[rw]--; -} - -static inline int part_in_flight(struct hd_struct *part) -{ - return part->in_flight[0] + part->in_flight[1]; + part_to_disk(part)->part0.in_flight--; } /* block/blk-core.c */ @@ -551,8 +546,6 @@ extern ssize_t part_size_show(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t part_stat_show(struct device *dev, struct device_attribute *attr, char *buf); -extern ssize_t part_inflight_show(struct device *dev, - struct device_attribute *attr, char *buf); #ifdef CONFIG_FAIL_MAKE_REQUEST extern ssize_t part_fail_show(struct device *dev, struct device_attribute *attr, char *buf); -- cgit v1.2.3 From a99bbaf5ee6bad1aca0c88ea65ec6e5373e86184 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sun, 4 Oct 2009 16:11:37 +0400 Subject: headers: remove sched.h from poll.h Signed-off-by: Alexey Dobriyan Signed-off-by: Linus Torvalds --- include/linux/poll.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/poll.h b/include/linux/poll.h index fa287f25138d..6673743946f7 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -6,10 +6,10 @@ #ifdef __KERNEL__ #include +#include #include #include #include -#include #include /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating -- cgit v1.2.3