From a5cdc030030ef5a16e48aebeb65067bdc3120899 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 23 Mar 2006 01:16:06 -0800 Subject: [IPV4]: Add fib rule netlink notifications To really make sense of route notifications in the presence of multiple tables, userspace also needs to be notified about routing rule updates. Notifications are sent to the so far unused RTNLGRP_NOP1 (now RTNLGRP_RULE) group. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index d572d5376319..df0cdd41085c 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -839,6 +839,7 @@ enum #define RTMGRP_IPV4_IFADDR 0x10 #define RTMGRP_IPV4_MROUTE 0x20 #define RTMGRP_IPV4_ROUTE 0x40 +#define RTMGRP_IPV4_RULE 0x80 #define RTMGRP_IPV6_IFADDR 0x100 #define RTMGRP_IPV6_MROUTE 0x200 @@ -869,7 +870,8 @@ enum rtnetlink_groups { #define RTNLGRP_IPV4_MROUTE RTNLGRP_IPV4_MROUTE RTNLGRP_IPV4_ROUTE, #define RTNLGRP_IPV4_ROUTE RTNLGRP_IPV4_ROUTE - RTNLGRP_NOP1, + RTNLGRP_IPV4_RULE, +#define RTNLGRP_IPV4_RULE RTNLGRP_IPV4_RULE RTNLGRP_IPV6_IFADDR, #define RTNLGRP_IPV6_IFADDR RTNLGRP_IPV6_IFADDR RTNLGRP_IPV6_MROUTE, -- cgit v1.2.1 From af36e6b6d7f4ad7a5ccfd14dfa71ec941255f93d Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Thu, 23 Mar 2006 01:28:06 -0800 Subject: [TG3]: Add 5755 support Add support for new chip 5755 which is very similar to 5787. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index ec3c32932620..989a9d00dec1 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1864,11 +1864,13 @@ #define PCI_DEVICE_ID_TIGON3_5780S 0x166b #define PCI_DEVICE_ID_TIGON3_5705F 0x166e #define PCI_DEVICE_ID_TIGON3_5754M 0x1672 +#define PCI_DEVICE_ID_TIGON3_5755M 0x1673 #define PCI_DEVICE_ID_TIGON3_5750 0x1676 #define PCI_DEVICE_ID_TIGON3_5751 0x1677 #define PCI_DEVICE_ID_TIGON3_5715 0x1678 #define PCI_DEVICE_ID_TIGON3_5715S 0x1679 #define PCI_DEVICE_ID_TIGON3_5754 0x167a +#define PCI_DEVICE_ID_TIGON3_5755 0x167b #define PCI_DEVICE_ID_TIGON3_5750M 0x167c #define PCI_DEVICE_ID_TIGON3_5751M 0x167d #define PCI_DEVICE_ID_TIGON3_5751F 0x167e -- cgit v1.2.1 From 711e2c33ac9221a419a9e28d05dd78a6a9c5fd4d Mon Sep 17 00:00:00 2001 From: Jean Tourrilhes Date: Wed, 22 Feb 2006 15:10:56 -0800 Subject: [PATCH] WE-20 for kernel 2.6.16 This is version 20 of the Wireless Extensions. This is the completion of the RtNetlink work I started early 2004, it enables the full Wireless Extension API over RtNetlink. Few comments on the patch : o totally driver transparent, no change in drivers needed. o iwevent were already RtNetlink based since they were created (around 2.5.7). This adds all the regular SET and GET requests over RtNetlink, using the exact same mechanism and data format as iwevents. o This is a Kconfig option, as currently most people have no need for it. Surprisingly, patch is actually small and well encapsulated. o Tested on SMP, attention as been paid to make it 64 bits clean. o Code do probably too many checks and could be further optimised, but better safe than sorry. o RtNetlink based version of the Wireless Tools available on my web page for people inclined to try out this stuff. I would also like to thank Alexey Kuznetsov for his helpful suggestions to make this patch better. Signed-off-by: Jean Tourrilhes Signed-off-by: John W. Linville --- include/linux/wireless.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wireless.h b/include/linux/wireless.h index a555a0f7a7b4..13588564b42b 100644 --- a/include/linux/wireless.h +++ b/include/linux/wireless.h @@ -1,10 +1,10 @@ /* * This file define a set of standard wireless extensions * - * Version : 19 18.3.05 + * Version : 20 17.2.06 * * Authors : Jean Tourrilhes - HPL - - * Copyright (c) 1997-2005 Jean Tourrilhes, All Rights Reserved. + * Copyright (c) 1997-2006 Jean Tourrilhes, All Rights Reserved. */ #ifndef _LINUX_WIRELESS_H @@ -80,7 +80,7 @@ * (there is some stuff that will be added in the future...) * I just plan to increment with each new version. */ -#define WIRELESS_EXT 19 +#define WIRELESS_EXT 20 /* * Changes : @@ -204,6 +204,10 @@ * - Add IW_QUAL_ALL_UPDATED and IW_QUAL_ALL_INVALID macros * - Add explicit flag to tell stats are in dBm : IW_QUAL_DBM * - Add IW_IOCTL_IDX() and IW_EVENT_IDX() macros + * + * V19 to V20 + * ---------- + * - RtNetlink requests support (SET/GET) */ /**************************** CONSTANTS ****************************/ -- cgit v1.2.1 From 9e71f9c848e669f003b1319da52f03cb8e7d7403 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 23 Mar 2006 02:59:22 -0800 Subject: [PATCH] DM: Fix bug: BIO_RW_BARRIER requests to md/raid1 hang. Both R1BIO_Barrier and R1BIO_Returned are 4 !!!! This means that barrier requests don't get returned (i.e. b_endio called) because it looks like they already have been. Signed-off-by: Neil Brown Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/raid1.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/raid/raid1.h b/include/linux/raid/raid1.h index 9d5494aaac0f..3009c813d83d 100644 --- a/include/linux/raid/raid1.h +++ b/include/linux/raid/raid1.h @@ -130,6 +130,6 @@ struct r1bio_s { * with failure when last write completes (and all failed). * Record that bi_end_io was called with this flag... */ -#define R1BIO_Returned 4 +#define R1BIO_Returned 6 #endif -- cgit v1.2.1 From f577eb30afdc68233f25d4d82b04102129262365 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 23 Mar 2006 02:59:59 -0800 Subject: [PATCH] swsusp: low level interface Introduce the low level interface that can be used for handling the snapshot of the system memory by the in-kernel swap-writing/reading code of swsusp and the userland interface code (to be introduced shortly). Also change the way in which swsusp records the allocated swap pages and, consequently, simplifies the in-kernel swap-writing/reading code (this is necessary for the userland interface too). To this end, it introduces two helper functions in mm/swapfile.c, so that the swsusp code does not refer directly to the swap internals. Signed-off-by: Rafael J. Wysocki Acked-by: Pavel Machek Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 12415dd94451..54eac8a39a4c 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -234,14 +234,15 @@ extern struct page * read_swap_cache_async(swp_entry_t, struct vm_area_struct *v /* linux/mm/swapfile.c */ extern long total_swap_pages; extern unsigned int nr_swapfiles; -extern struct swap_info_struct swap_info[]; extern void si_swapinfo(struct sysinfo *); extern swp_entry_t get_swap_page(void); -extern swp_entry_t get_swap_page_of_type(int type); +extern swp_entry_t get_swap_page_of_type(int); extern int swap_duplicate(swp_entry_t); extern int valid_swaphandles(swp_entry_t, unsigned long *); extern void swap_free(swp_entry_t); extern void free_swap_and_cache(swp_entry_t); +extern int swap_type_of(dev_t); +extern unsigned int count_swap_pages(int, int); extern sector_t map_swap_page(struct swap_info_struct *, pgoff_t); extern struct swap_info_struct *get_swap_info_struct(unsigned); extern int can_share_swap_page(struct page *); -- cgit v1.2.1 From 74c7e2efbe37378026f00ad9e7253796d7b2fc99 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 23 Mar 2006 03:00:01 -0800 Subject: [PATCH] kernel/power: move externs to header files Move externs from C source files to header files. Signed-off-by: Randy Dunlap Cc: "Rafael J. Wysocki" Cc: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 5be87ba3b7ac..6df2585c0169 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -188,6 +188,8 @@ extern void device_power_up(void); extern void device_resume(void); #ifdef CONFIG_PM +extern suspend_disk_method_t pm_disk_mode; + extern int device_suspend(pm_message_t state); #define device_set_wakeup_enable(dev,val) \ @@ -215,7 +217,6 @@ static inline int dpm_runtime_suspend(struct device * dev, pm_message_t state) static inline void dpm_runtime_resume(struct device * dev) { - } #endif -- cgit v1.2.1 From ff4da2e262d2509fe1bacff70dd00934be569c66 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 23 Mar 2006 03:00:07 -0800 Subject: [PATCH] swsusp: add check for suspension of X-controlled devices It is unsafe to suspend devices if the hardware is controlled by X. Add an extra check to prevent this from happening. Signed-off-by: Rafael J. Wysocki Cc: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vt_kern.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index fab5aed8ca31..530ae3f4248c 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -73,6 +73,11 @@ int con_copy_unimap(struct vc_data *dst_vc, struct vc_data *src_vc); int vt_waitactive(int vt); void change_console(struct vc_data *new_vc); void reset_vc(struct vc_data *vc); +#ifdef CONFIG_VT +int is_console_suspend_safe(void); +#else +static inline int is_console_suspend_safe(void) { return 1; } +#endif /* * vc_screen.c shares this temporary buffer with the console write code so that -- cgit v1.2.1 From d8733c2956968a01394a4d2a9e97a8b431a78776 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 23 Mar 2006 03:00:11 -0800 Subject: [PATCH] ext3_readdir: use generic readahead Linus points out that ext3_readdir's readahead only cuts in when ext3_readdir() is operating at the very start of the directory. So for large directories we end up performing no readahead at all and we suck. So take it all out and use the core VM's page_cache_readahead(). This means that ext3 directory reads will use all of readahead's dynamic sizing goop. Note that we're using the directory's filp->f_ra to hold the readahead state, but readahead is actually being performed against the underlying blockdev's address_space. Fortunately the readahead code is all set up to handle this. Tested with printk. It works. I was struggling to find a real workload which actually cared. (The patch also exports page_cache_readahead() to GPL modules) Cc: "Stephen C. Tweedie" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext3_fs.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index c0272d73ab20..e7239f2f97a1 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -772,9 +772,12 @@ extern unsigned long ext3_count_free (struct buffer_head *, unsigned); /* inode.c */ -extern int ext3_forget(handle_t *, int, struct inode *, struct buffer_head *, int); -extern struct buffer_head * ext3_getblk (handle_t *, struct inode *, long, int, int *); -extern struct buffer_head * ext3_bread (handle_t *, struct inode *, int, int, int *); +int ext3_forget(handle_t *, int, struct inode *, struct buffer_head *, int); +struct buffer_head * ext3_getblk (handle_t *, struct inode *, long, int, int *); +struct buffer_head * ext3_bread (handle_t *, struct inode *, int, int, int *); +int ext3_get_block_handle(handle_t *handle, struct inode *inode, + sector_t iblock, struct buffer_head *bh_result, int create, + int extend_disksize); extern void ext3_read_inode (struct inode *); extern int ext3_write_inode (struct inode *, int); -- cgit v1.2.1 From 0c9e63fd38a2fb2181668a0cdd622a3c23cfd567 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 23 Mar 2006 03:00:12 -0800 Subject: [PATCH] Shrinks sizeof(files_struct) and better layout 1) Reduce the size of (struct fdtable) to exactly 64 bytes on 32bits platforms, lowering kmalloc() allocated space by 50%. 2) Reduce the size of (files_struct), using a special 32 bits (or 64bits) embedded_fd_set, instead of a 1024 bits fd_set for the close_on_exec_init and open_fds_init fields. This save some ram (248 bytes per task) as most tasks dont open more than 32 files. D-Cache footprint for such tasks is also reduced to the minimum. 3) Reduce size of allocated fdset. Currently two full pages are allocated, that is 32768 bits on x86 for example, and way too much. The minimum is now L1_CACHE_BYTES. UP and SMP should benefit from this patch, because most tasks will touch only one cache line when open()/close() stdin/stdout/stderr (0/1/2), (next_fd, close_on_exec_init, open_fds_init, fd_array[0 .. 2] being in the same cache line) Signed-off-by: Eric Dumazet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/file.h | 28 ++++++++++++++++++++++++---- include/linux/init_task.h | 10 +++++----- 2 files changed, 29 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 9901b850f2e4..9f7c2513866f 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -10,6 +10,7 @@ #include #include #include +#include /* * The default fd array needs to be at least BITS_PER_LONG, @@ -17,10 +18,22 @@ */ #define NR_OPEN_DEFAULT BITS_PER_LONG +/* + * The embedded_fd_set is a small fd_set, + * suitable for most tasks (which open <= BITS_PER_LONG files) + */ +struct embedded_fd_set { + unsigned long fds_bits[1]; +}; + +/* + * More than this number of fds: we use a separately allocated fd_set + */ +#define EMBEDDED_FD_SET_SIZE (BITS_PER_BYTE * sizeof(struct embedded_fd_set)) + struct fdtable { unsigned int max_fds; int max_fdset; - int next_fd; struct file ** fd; /* current fd array */ fd_set *close_on_exec; fd_set *open_fds; @@ -33,13 +46,20 @@ struct fdtable { * Open file table structure */ struct files_struct { + /* + * read mostly part + */ atomic_t count; struct fdtable *fdt; struct fdtable fdtab; - fd_set close_on_exec_init; - fd_set open_fds_init; + /* + * written part on a separate cache line in SMP + */ + spinlock_t file_lock ____cacheline_aligned_in_smp; + int next_fd; + struct embedded_fd_set close_on_exec_init; + struct embedded_fd_set open_fds_init; struct file * fd_array[NR_OPEN_DEFAULT]; - spinlock_t file_lock; /* Protects concurrent writers. Nests inside tsk->alloc_lock */ }; #define files_fdtable(files) (rcu_dereference((files)->fdt)) diff --git a/include/linux/init_task.h b/include/linux/init_task.h index dcfd2ecccb5d..92146f3b7423 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -7,11 +7,10 @@ #define INIT_FDTABLE \ { \ .max_fds = NR_OPEN_DEFAULT, \ - .max_fdset = __FD_SETSIZE, \ - .next_fd = 0, \ + .max_fdset = EMBEDDED_FD_SET_SIZE, \ .fd = &init_files.fd_array[0], \ - .close_on_exec = &init_files.close_on_exec_init, \ - .open_fds = &init_files.open_fds_init, \ + .close_on_exec = (fd_set *)&init_files.close_on_exec_init, \ + .open_fds = (fd_set *)&init_files.open_fds_init, \ .rcu = RCU_HEAD_INIT, \ .free_files = NULL, \ .next = NULL, \ @@ -20,9 +19,10 @@ #define INIT_FILES \ { \ .count = ATOMIC_INIT(1), \ - .file_lock = SPIN_LOCK_UNLOCKED, \ .fdt = &init_files.fdtab, \ .fdtab = INIT_FDTABLE, \ + .file_lock = SPIN_LOCK_UNLOCKED, \ + .next_fd = 0, \ .close_on_exec_init = { { 0, } }, \ .open_fds_init = { { 0, } }, \ .fd_array = { NULL, } \ -- cgit v1.2.1 From 6a2900b67652421b51fe25e4b86ecfec742b1f30 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Mar 2006 03:00:15 -0800 Subject: [PATCH] kill cdrom ->dev_ioctl method Since early 2.4.x all cdrom drivers implement the block_device methods themselves, so they can handle additional ioctls directly instead of going through the cdrom layer. Signed-off-by: Christoph Hellwig Acked-by: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cdrom.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index b68fdf1f3156..3c9b0bc05123 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -378,7 +378,6 @@ struct cdrom_generic_command #define CDC_MEDIA_CHANGED 0x80 /* media changed */ #define CDC_PLAY_AUDIO 0x100 /* audio functions */ #define CDC_RESET 0x200 /* hard reset device */ -#define CDC_IOCTLS 0x400 /* driver has non-standard ioctls */ #define CDC_DRIVE_STATUS 0x800 /* driver implements drive status */ #define CDC_GENERIC_PACKET 0x1000 /* driver implements generic packets */ #define CDC_CD_R 0x2000 /* drive is a CD-R */ @@ -974,9 +973,7 @@ struct cdrom_device_ops { int (*reset) (struct cdrom_device_info *); /* play stuff */ int (*audio_ioctl) (struct cdrom_device_info *,unsigned int, void *); - /* dev-specific */ - int (*dev_ioctl) (struct cdrom_device_info *, - unsigned int, unsigned long); + /* driver specifications */ const int capability; /* capability flags */ int n_minors; /* number of active minor devices */ -- cgit v1.2.1 From 804f1594cc3deb161e531a43d90c501f0db2635a Mon Sep 17 00:00:00 2001 From: Kyle McMartin Date: Thu, 23 Mar 2006 03:00:16 -0800 Subject: [PATCH] Move read_mostly definition to asm/cache.h Seems like needless clutter having a bunch of #if defined(CONFIG_$ARCH) in include/linux/cache.h. Move the per architecture section definition to asm/cache.h, and keep the if-not-defined dummy case in linux/cache.h to catch architectures which don't implement the section. Verified that symbols still go in .data.read_mostly on parisc, and the compile doesn't break. Signed-off-by: Kyle McMartin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cache.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cache.h b/include/linux/cache.h index d22e632f41fb..cc4b3aafad9a 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -13,9 +13,7 @@ #define SMP_CACHE_BYTES L1_CACHE_BYTES #endif -#if defined(CONFIG_X86) || defined(CONFIG_SPARC64) || defined(CONFIG_IA64) || defined(CONFIG_PARISC) -#define __read_mostly __attribute__((__section__(".data.read_mostly"))) -#else +#ifndef __read_mostly #define __read_mostly #endif -- cgit v1.2.1 From c039e3134ae62863bbc8e8429b29e3c43cf21b2a Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Thu, 23 Mar 2006 03:00:28 -0800 Subject: [PATCH] sem2mutex: blockdev #2 Semaphore to mutex conversion. The conversion was generated via scripts, and the result was validated automatically via a script as well. Signed-off-by: Arjan van de Ven Signed-off-by: Ingo Molnar Acked-by: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 128d0082522c..009ac96053fe 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -397,8 +397,8 @@ struct block_device { dev_t bd_dev; /* not a kdev_t - it's a search key */ struct inode * bd_inode; /* will die */ int bd_openers; - struct semaphore bd_sem; /* open/close mutex */ - struct semaphore bd_mount_sem; /* mount mutex */ + struct mutex bd_mutex; /* open/close mutex */ + struct mutex bd_mount_mutex; /* mount mutex */ struct list_head bd_inodes; void * bd_holder; int bd_holders; -- cgit v1.2.1 From d3be915fc5e7d19a2283ad9b0fe0782a74675d0a Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 23 Mar 2006 03:00:29 -0800 Subject: [PATCH] sem2mutex: quota Semaphore to mutex conversion. The conversion was generated via scripts, and the result was validated automatically via a script as well. Signed-off-by: Ingo Molnar Cc: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/quota.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index f33aeb22c26a..8dc2d04a103f 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -38,6 +38,7 @@ #include #include #include +#include #define __DQUOT_VERSION__ "dquot_6.5.1" #define __DQUOT_NUM_VERSION__ 6*10000+5*100+1 @@ -215,7 +216,7 @@ struct dquot { struct list_head dq_inuse; /* List of all quotas */ struct list_head dq_free; /* Free list element */ struct list_head dq_dirty; /* List of dirty dquots */ - struct semaphore dq_lock; /* dquot IO lock */ + struct mutex dq_lock; /* dquot IO lock */ atomic_t dq_count; /* Use count */ wait_queue_head_t dq_wait_unused; /* Wait queue for dquot to become unused */ struct super_block *dq_sb; /* superblock this applies to */ @@ -285,8 +286,8 @@ struct quota_format_type { struct quota_info { unsigned int flags; /* Flags for diskquotas on this device */ - struct semaphore dqio_sem; /* lock device while I/O in progress */ - struct semaphore dqonoff_sem; /* Serialize quotaon & quotaoff */ + struct mutex dqio_mutex; /* lock device while I/O in progress */ + struct mutex dqonoff_mutex; /* Serialize quotaon & quotaoff */ struct rw_semaphore dqptr_sem; /* serialize ops using quota_info struct, pointers from inode to dquots */ struct inode *files[MAXQUOTAS]; /* inodes of quotafiles */ struct mem_dqinfo info[MAXQUOTAS]; /* Information for each quota type */ -- cgit v1.2.1 From d4f9af9dac4ecb75818f909168f87b441cc95653 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 23 Mar 2006 03:00:30 -0800 Subject: [PATCH] sem2mutex: inotify Semaphore to mutex conversion. The conversion was generated via scripts, and the result was validated automatically via a script as well. Signed-off-by: Ingo Molnar Cc: John McCutchan Signed-off-by: Andrew Morton Acked-by: Robert Love Signed-off-by: Linus Torvalds --- 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 009ac96053fe..9ed1f36b6d54 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -509,7 +509,7 @@ struct inode { #ifdef CONFIG_INOTIFY struct list_head inotify_watches; /* watches on this inode */ - struct semaphore inotify_sem; /* protects the watches list */ + struct mutex inotify_mutex; /* protects the watches list */ #endif unsigned long i_state; -- cgit v1.2.1 From 70522e121a521aa09bd0f4e62e1aa68708b798e1 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 23 Mar 2006 03:00:31 -0800 Subject: [PATCH] sem2mutex: tty Semaphore to mutex conversion. The conversion was generated via scripts, and the result was validated automatically via a script as well. Signed-off-by: Ingo Molnar Cc: Alan Cox Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tty.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index f45cd74e6f24..f13f49afe198 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -24,6 +24,7 @@ #include #include #include +#include #include @@ -231,8 +232,8 @@ struct tty_struct { int canon_data; unsigned long canon_head; unsigned int canon_column; - struct semaphore atomic_read; - struct semaphore atomic_write; + struct mutex atomic_read_lock; + struct mutex atomic_write_lock; unsigned char *write_buf; int write_cnt; spinlock_t read_lock; @@ -319,8 +320,7 @@ extern void tty_ldisc_put(int); extern void tty_wakeup(struct tty_struct *tty); extern void tty_ldisc_flush(struct tty_struct *tty); -struct semaphore; -extern struct semaphore tty_sem; +extern struct mutex tty_mutex; /* n_tty.c */ extern struct tty_ldisc tty_ldisc_N_TTY; -- cgit v1.2.1 From a11f3a0574a5734db3e5de38922430d005d35118 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Thu, 23 Mar 2006 03:00:33 -0800 Subject: [PATCH] sem2mutex: vfs_rename_mutex Semaphore to mutex conversion. The conversion was generated via scripts, and the result was validated automatically via a script as well. Signed-off-by: Arjan van de Ven Signed-off-by: Ingo Molnar Cc: Al Viro Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 9ed1f36b6d54..0f71ee730127 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -847,7 +847,7 @@ struct super_block { * The next field is for VFS *only*. No filesystems have any business * even looking at it. You had been warned. */ - struct semaphore s_vfs_rename_sem; /* Kludge */ + struct mutex s_vfs_rename_mutex; /* Kludge */ /* Granuality of c/m/atime in ns. Cannot be worse than a second */ -- cgit v1.2.1 From f24075bd0c1cd1cc2cf86d394f960aa0401de573 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 23 Mar 2006 03:00:34 -0800 Subject: [PATCH] sem2mutex: iprune Semaphore to mutex conversion. The conversion was generated via scripts, and the result was validated automatically via a script as well. Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 0f71ee730127..8fd8d9b90b00 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1534,7 +1534,7 @@ extern void destroy_inode(struct inode *); extern struct inode *new_inode(struct super_block *); extern int remove_suid(struct dentry *); extern void remove_dquot_ref(struct super_block *, int, struct list_head *); -extern struct semaphore iprune_sem; +extern struct mutex iprune_mutex; extern void __insert_inode_hash(struct inode *, unsigned long hashval); extern void remove_inode_hash(struct inode *); -- cgit v1.2.1 From 2c68ee754c40099c59828e59618a54726f76126a Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Thu, 23 Mar 2006 03:00:35 -0800 Subject: [PATCH] sem2mutex: jbd, j_checkpoint_mutex Semaphore to mutex conversion. The conversion was generated via scripts, and the result was validated automatically via a script as well. Signed-off-by: Arjan van de Ven Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/jbd.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 41ee79962bb2..2ccbfb6340ba 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -28,6 +28,7 @@ #include #include #include +#include #include #endif @@ -575,7 +576,7 @@ struct transaction_s * @j_wait_checkpoint: Wait queue to trigger checkpointing * @j_wait_commit: Wait queue to trigger commit * @j_wait_updates: Wait queue to wait for updates to complete - * @j_checkpoint_sem: Semaphore for locking against concurrent checkpoints + * @j_checkpoint_mutex: Mutex for locking against concurrent checkpoints * @j_head: Journal head - identifies the first unused block in the journal * @j_tail: Journal tail - identifies the oldest still-used block in the * journal. @@ -645,7 +646,7 @@ struct journal_s int j_barrier_count; /* The barrier lock itself */ - struct semaphore j_barrier; + struct mutex j_barrier; /* * Transactions: The current running transaction... @@ -687,7 +688,7 @@ struct journal_s wait_queue_head_t j_wait_updates; /* Semaphore for locking against concurrent checkpoints */ - struct semaphore j_checkpoint_sem; + struct mutex j_checkpoint_mutex; /* * Journal head: identifies the first unused block in the journal. -- cgit v1.2.1 From 7a7d1cf95408863a657035701606b13644c9f55e Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 23 Mar 2006 03:00:35 -0800 Subject: [PATCH] sem2mutex: kprobes Semaphore to mutex conversion. The conversion was generated via scripts, and the result was validated automatically via a script as well. Signed-off-by: Ingo Molnar Acked-by: Anil S Keshavamurthy Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kprobes.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 669756bc20a2..778adc0fa640 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -36,6 +36,7 @@ #include #include #include +#include #ifdef CONFIG_KPROBES #include @@ -152,7 +153,7 @@ struct kretprobe_instance { }; extern spinlock_t kretprobe_lock; -extern struct semaphore kprobe_mutex; +extern struct mutex kprobe_mutex; extern int arch_prepare_kprobe(struct kprobe *p); extern void arch_arm_kprobe(struct kprobe *p); extern void arch_disarm_kprobe(struct kprobe *p); -- cgit v1.2.1 From 0ac1759abc69fb62438c30a7e422f628a1120d67 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 23 Mar 2006 03:00:37 -0800 Subject: [PATCH] sem2mutex: fs/seq_file.c Semaphore to mutex conversion. The conversion was generated via scripts, and the result was validated automatically via a script as well. Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/seq_file.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 850a974ee505..b95f6eb7254c 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -4,7 +4,7 @@ #include #include -#include +#include struct seq_operations; struct file; @@ -19,7 +19,7 @@ struct seq_file { size_t count; loff_t index; loff_t version; - struct semaphore sem; + struct mutex lock; struct seq_operations *op; void *private; }; -- cgit v1.2.1 From f85221dd74f2708b78a2aa54de59944e44206d0e Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 23 Mar 2006 03:00:38 -0800 Subject: [PATCH] sem2mutex: drivers/block/loop.c Semaphore to mutex conversion. The conversion was generated via scripts, and the result was validated automatically via a script as well. Signed-off-by: Ingo Molnar Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/loop.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/loop.h b/include/linux/loop.h index f96506782ebe..e76c7611d6cc 100644 --- a/include/linux/loop.h +++ b/include/linux/loop.h @@ -17,6 +17,7 @@ #include #include #include +#include /* Possible states of device */ enum { @@ -60,7 +61,7 @@ struct loop_device { int lo_state; struct completion lo_done; struct completion lo_bh_done; - struct semaphore lo_ctl_mutex; + struct mutex lo_ctl_mutex; int lo_pending; request_queue_t *lo_queue; -- cgit v1.2.1 From 82d4dc5adb0055393248ad4ab8de392fac708a12 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 23 Mar 2006 03:00:38 -0800 Subject: [PATCH] sem2mutex: drivers/block/nbd.c Semaphore to mutex conversion. The conversion was generated via scripts, and the result was validated automatically via a script as well. Signed-off-by: Ingo Molnar Cc: Paul Clements Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nbd.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nbd.h b/include/linux/nbd.h index f95d51fae733..a6ce409ec6fc 100644 --- a/include/linux/nbd.h +++ b/include/linux/nbd.h @@ -38,6 +38,7 @@ enum { #ifdef __KERNEL__ #include +#include /* values for flags field */ #define NBD_READ_ONLY 0x0001 @@ -57,7 +58,7 @@ struct nbd_device { struct request *active_req; wait_queue_head_t active_wq; - struct semaphore tx_lock; + struct mutex tx_lock; struct gendisk *disk; int blksize; u64 bytesize; -- cgit v1.2.1 From 97461518610fb1679f67333bb699bb81136e49fe Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Thu, 23 Mar 2006 03:00:42 -0800 Subject: [PATCH] convert ext3's truncate_sem to a mutex ext3's truncate_sem is always released in the same function it's taken and it otherwise is a mutex as well.. Signed-off-by: Arjan van de Ven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext3_fs_i.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext3_fs_i.h b/include/linux/ext3_fs_i.h index e71dd98dbcae..7abf90147180 100644 --- a/include/linux/ext3_fs_i.h +++ b/include/linux/ext3_fs_i.h @@ -19,6 +19,7 @@ #include #include #include +#include struct ext3_reserve_window { __u32 _rsv_start; /* First byte reserved */ @@ -122,16 +123,16 @@ struct ext3_inode_info { __u16 i_extra_isize; /* - * truncate_sem is for serialising ext3_truncate() against + * truncate_mutex is for serialising ext3_truncate() against * ext3_getblock(). In the 2.4 ext2 design, great chunks of inode's * data tree are chopped off during truncate. We can't do that in * ext3 because whenever we perform intermediate commits during * truncate, the inode and all the metadata blocks *must* be in a * consistent state which allows truncation of the orphans to restart * during recovery. Hence we must fix the get_block-vs-truncate race - * by other means, so we have truncate_sem. + * by other means, so we have truncate_mutex. */ - struct semaphore truncate_sem; + struct mutex truncate_mutex; struct inode vfs_inode; }; -- cgit v1.2.1 From 8e3f90459b7052c31a9669417b837fb14aa6d313 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 23 Mar 2006 03:00:43 -0800 Subject: [PATCH] sem2mutex: NCPFS Semaphore to mutex conversion. The conversion was generated via scripts, and the result was validated automatically via a script as well. Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ncp_fs_i.h | 2 +- include/linux/ncp_fs_sb.h | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ncp_fs_i.h b/include/linux/ncp_fs_i.h index 415be1ec6f98..bdb4c8ae6924 100644 --- a/include/linux/ncp_fs_i.h +++ b/include/linux/ncp_fs_i.h @@ -19,7 +19,7 @@ struct ncp_inode_info { __le32 DosDirNum; __u8 volNumber; __le32 nwattr; - struct semaphore open_sem; + struct mutex open_mutex; atomic_t opened; int access; int flags; diff --git a/include/linux/ncp_fs_sb.h b/include/linux/ncp_fs_sb.h index cf858eb80f0b..b089d9506283 100644 --- a/include/linux/ncp_fs_sb.h +++ b/include/linux/ncp_fs_sb.h @@ -11,6 +11,7 @@ #include #include #include +#include #ifdef __KERNEL__ @@ -51,7 +52,7 @@ struct ncp_server { receive replies */ int lock; /* To prevent mismatch in protocols. */ - struct semaphore sem; + struct mutex mutex; int current_size; /* for packet preparation */ int has_subfunction; @@ -96,7 +97,7 @@ struct ncp_server { struct { struct work_struct tq; /* STREAM/DGRAM: data/error ready */ struct ncp_request_reply* creq; /* STREAM/DGRAM: awaiting reply from this request */ - struct semaphore creq_sem; /* DGRAM only: lock accesses to rcv.creq */ + struct mutex creq_mutex; /* DGRAM only: lock accesses to rcv.creq */ unsigned int state; /* STREAM only: receiver state */ struct { -- cgit v1.2.1 From 1e7933defd0fce79b2d8ecdbc7ca37fed0c188ed Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 23 Mar 2006 03:00:44 -0800 Subject: [PATCH] sem2mutex: UDF Semaphore to mutex conversion. The conversion was generated via scripts, and the result was validated automatically via a script as well. Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/udf_fs_sb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/udf_fs_sb.h b/include/linux/udf_fs_sb.h index b15ff2e99c91..80ae9ef940dc 100644 --- a/include/linux/udf_fs_sb.h +++ b/include/linux/udf_fs_sb.h @@ -13,7 +13,7 @@ #ifndef _UDF_FS_SB_H #define _UDF_FS_SB_H 1 -#include +#include #pragma pack(1) @@ -111,7 +111,7 @@ struct udf_sb_info /* VAT inode */ struct inode *s_vat; - struct semaphore s_alloc_sem; + struct mutex s_alloc_mutex; }; #endif /* _UDF_FS_SB_H */ -- cgit v1.2.1 From 81861d78c9edf9a9b03a9ba1f5b242d658f16832 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 23 Mar 2006 03:00:44 -0800 Subject: [PATCH] sem2mutex: serial ->port_write_mutex Semaphore to mutex conversion. The conversion was generated via scripts, and the result was validated automatically via a script as well. Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/generic_serial.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/generic_serial.h b/include/linux/generic_serial.h index 0abe9d9a0069..652611a4bdcd 100644 --- a/include/linux/generic_serial.h +++ b/include/linux/generic_serial.h @@ -12,6 +12,8 @@ #ifndef GENERIC_SERIAL_H #define GENERIC_SERIAL_H +#include + struct real_driver { void (*disable_tx_interrupts) (void *); void (*enable_tx_interrupts) (void *); @@ -34,7 +36,7 @@ struct gs_port { int xmit_head; int xmit_tail; int xmit_cnt; - struct semaphore port_write_sem; + struct mutex port_write_mutex; int flags; wait_queue_head_t open_wait; wait_queue_head_t close_wait; -- cgit v1.2.1 From 6b9438e1323a2be10dcc039f6321e7ca18b9459e Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Thu, 23 Mar 2006 03:00:48 -0800 Subject: [PATCH] fat_lock is used as a mutex, convert it to using the new mutex primitive The fat code uses the fat_lock always in a mutex way (taking and releasing the lock in the same function), the patch below converts it into the new mutex primitive. Please consider this patch for the code. Signed-off-by: Arjan van de Ven Acked-by: OGAWA Hirofumi Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/msdos_fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/msdos_fs.h b/include/linux/msdos_fs.h index 8bcd9450d926..779e6a5744c7 100644 --- a/include/linux/msdos_fs.h +++ b/include/linux/msdos_fs.h @@ -184,6 +184,7 @@ struct fat_slot_info { #include #include #include +#include struct fat_mount_options { uid_t fs_uid; @@ -226,7 +227,7 @@ struct msdos_sb_info { unsigned long max_cluster; /* maximum cluster number */ unsigned long root_cluster; /* first cluster of the root directory */ unsigned long fsinfo_sector; /* sector number of FAT32 fsinfo */ - struct semaphore fat_lock; + struct mutex fat_lock; unsigned int prev_free; /* previously allocated cluster number */ unsigned int free_clusters; /* -1 if undefined */ struct fat_mount_options options; -- cgit v1.2.1 From 66d2173053f64121f8dc69a1cf85972e37e1ee75 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 23 Mar 2006 03:00:51 -0800 Subject: [PATCH] Extract inode_inc_link_count(), inode_dec_link_count() Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 8fd8d9b90b00..f9c9dea636d0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1115,6 +1115,18 @@ static inline void mark_inode_dirty_sync(struct inode *inode) __mark_inode_dirty(inode, I_DIRTY_SYNC); } +static inline void inode_inc_link_count(struct inode *inode) +{ + inode->i_nlink++; + mark_inode_dirty(inode); +} + +static inline void inode_dec_link_count(struct inode *inode) +{ + inode->i_nlink--; + mark_inode_dirty(inode); +} + extern void touch_atime(struct vfsmount *mnt, struct dentry *dentry); static inline void file_accessed(struct file *file) { -- cgit v1.2.1 From 772a0dc5d2103baff2f15c2668930bcd37add777 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 23 Mar 2006 03:00:55 -0800 Subject: [PATCH] notifier: profile.h forward decl fix Declarations use struct notifier_block on both legs of the ifdef, so move the notifier_block forward declaration outside the ifdef. Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/profile.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/profile.h b/include/linux/profile.h index 026969a5595c..1f2fea6640a4 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -14,6 +14,7 @@ struct proc_dir_entry; struct pt_regs; +struct notifier_block; /* init basic kernel profiler */ void __init profile_init(void); @@ -32,7 +33,6 @@ enum profile_type { #ifdef CONFIG_PROFILING -struct notifier_block; struct task_struct; struct mm_struct; -- cgit v1.2.1 From 41c28ff1635e71af072c4711ff5fadd5855d48e7 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Thu, 23 Mar 2006 03:00:56 -0800 Subject: [PATCH] kill _INLINE_ This patch removes all occurances of _INLINE_ in the kernel. With the exception of tty_flip.h, I've simply removed the inline's since gcc should know best which functions to be inlined. Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tty_flip.h | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index 222faf97d5f9..0c6169fff366 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -7,14 +7,8 @@ extern int tty_insert_flip_string_flags(struct tty_struct *tty, unsigned char *c extern int tty_prepare_flip_string(struct tty_struct *tty, unsigned char **chars, size_t size); extern int tty_prepare_flip_string_flags(struct tty_struct *tty, unsigned char **chars, char **flags, size_t size); -#ifdef INCLUDE_INLINE_FUNCS -#define _INLINE_ extern -#else -#define _INLINE_ static __inline__ -#endif - -_INLINE_ int tty_insert_flip_char(struct tty_struct *tty, - unsigned char ch, char flag) +static inline int tty_insert_flip_char(struct tty_struct *tty, + unsigned char ch, char flag) { struct tty_buffer *tb = tty->buf.tail; if (tb && tb->active && tb->used < tb->size) { @@ -25,7 +19,7 @@ _INLINE_ int tty_insert_flip_char(struct tty_struct *tty, return tty_insert_flip_string_flags(tty, &ch, &flag, 1); } -_INLINE_ void tty_schedule_flip(struct tty_struct *tty) +static inline void tty_schedule_flip(struct tty_struct *tty) { unsigned long flags; spin_lock_irqsave(&tty->buf.lock, flags); -- cgit v1.2.1 From dd287796d608fcdc3fe5e8fdb5bf762a8f1bc32a Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 23 Mar 2006 03:00:57 -0800 Subject: [PATCH] pause_on_oops command line option Attempt to fix the problem wherein people's oops reports scroll off the screen due to repeated oopsing or to oopses on other CPUs. If this happens the user can reboot with the `pause_on_oops=' option. It will allow the first oopsing CPU to print an oops record just a single time. Second oopsing attempts, or oopses on other CPUs will cause those CPUs to enter a tight loop until the specified number of seconds have elapsed. The patch implements the infrastructure generically in the expectation that architectures other than x86 will find it useful. Cc: Dave Jones Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 3b507bf05d09..bb6e7ddee2fd 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -91,6 +91,9 @@ extern struct notifier_block *panic_notifier_list; extern long (*panic_blink)(long time); NORET_TYPE void panic(const char * fmt, ...) __attribute__ ((NORET_AND format (printf, 1, 2))); +extern void oops_enter(void); +extern void oops_exit(void); +extern int oops_may_print(void); fastcall NORET_TYPE void do_exit(long error_code) ATTRIB_NORET; NORET_TYPE void complete_and_exit(struct completion *, long) -- cgit v1.2.1 From 2178426d26661ed6e18a8d6ea0bc05c98d73600d Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Thu, 23 Mar 2006 03:01:00 -0800 Subject: [PATCH] kernel/rcupdate.c: make two structs static This patch makes two needlessly global structs static. Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rcupdate.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index c2ec6c77874e..5673008b61e1 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -113,8 +113,6 @@ struct rcu_data { DECLARE_PER_CPU(struct rcu_data, rcu_data); DECLARE_PER_CPU(struct rcu_data, rcu_bh_data); -extern struct rcu_ctrlblk rcu_ctrlblk; -extern struct rcu_ctrlblk rcu_bh_ctrlblk; /* * Increment the quiescent state counter. -- cgit v1.2.1 From 5a6b7951bfcca7f45f44269ea87417c74558daf8 Mon Sep 17 00:00:00 2001 From: Benjamin LaHaise Date: Thu, 23 Mar 2006 03:01:03 -0800 Subject: [PATCH] get_empty_filp tweaks, inline epoll_init_file() Eliminate a handful of cache references by keeping current in a register instead of reloading (helps x86) and avoiding the overhead of a function call. Inlining eventpoll_init_file() saves 24 bytes. Also reorder file initialization to make writes occur more sequentially. Signed-off-by: Benjamin LaHaise Cc: Davide Libenzi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/eventpoll.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 1289f0ec4c00..1e4bdfcf83a2 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -52,7 +52,12 @@ struct file; #ifdef CONFIG_EPOLL /* Used to initialize the epoll bits inside the "struct file" */ -void eventpoll_init_file(struct file *file); +static inline void eventpoll_init_file(struct file *file) +{ + INIT_LIST_HEAD(&file->f_ep_links); + spin_lock_init(&file->f_ep_lock); +} + /* Used to release the epoll bits inside the "struct file" */ void eventpoll_release_file(struct file *file); @@ -85,7 +90,6 @@ static inline void eventpoll_release(struct file *file) eventpoll_release_file(file); } - #else static inline void eventpoll_init_file(struct file *file) {} -- cgit v1.2.1 From 394e3902c55e667945f6f1c2bdbc59842cce70f7 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 23 Mar 2006 03:01:05 -0800 Subject: [PATCH] more for_each_cpu() conversions When we stop allocating percpu memory for not-possible CPUs we must not touch the percpu data for not-possible CPUs at all. The correct way of doing this is to test cpu_possible() or to use for_each_cpu(). This patch is a kernel-wide sweep of all instances of NR_CPUS. I found very few instances of this bug, if any. But the patch converts lots of open-coded test to use the preferred helper macros. Cc: Mikael Starvik Cc: David Howells Acked-by: Kyle McMartin Cc: Anton Blanchard Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Paul Mundt Cc: "David S. Miller" Cc: William Lee Irwin III Cc: Andi Kleen Cc: Christian Zankel Cc: Philippe Elie Cc: Nathan Scott Cc: Jens Axboe Cc: Eric Dumazet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/genhd.h | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index eef5ccdcd731..fd647fde5ec1 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -149,22 +149,16 @@ struct disk_attribute { ({ \ typeof(gendiskp->dkstats->field) res = 0; \ int i; \ - for (i=0; i < NR_CPUS; i++) { \ - if (!cpu_possible(i)) \ - continue; \ + for_each_cpu(i) \ res += per_cpu_ptr(gendiskp->dkstats, i)->field; \ - } \ res; \ }) static inline void disk_stat_set_all(struct gendisk *gendiskp, int value) { int i; - for (i=0; i < NR_CPUS; i++) { - if (cpu_possible(i)) { - memset(per_cpu_ptr(gendiskp->dkstats, i), value, - sizeof (struct disk_stats)); - } - } + for_each_cpu(i) + memset(per_cpu_ptr(gendiskp->dkstats, i), value, + sizeof (struct disk_stats)); } #else -- cgit v1.2.1 From b86ff981a8252d83d6a7719ae09f3a05307e3592 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 23 Mar 2006 19:56:55 +0100 Subject: [PATCH] relay: migrate from relayfs to a generic relay API Original patch from Paul Mundt, sysfs parts removed by me since they were broken. Signed-off-by: Jens Axboe --- include/linux/relay.h | 281 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 281 insertions(+) create mode 100644 include/linux/relay.h (limited to 'include/linux') diff --git a/include/linux/relay.h b/include/linux/relay.h new file mode 100644 index 000000000000..4bcc1531d6a9 --- /dev/null +++ b/include/linux/relay.h @@ -0,0 +1,281 @@ +/* + * linux/include/linux/relay.h + * + * Copyright (C) 2002, 2003 - Tom Zanussi (zanussi@us.ibm.com), IBM Corp + * Copyright (C) 1999, 2000, 2001, 2002 - Karim Yaghmour (karim@opersys.com) + * + * CONFIG_RELAY definitions and declarations + */ + +#ifndef _LINUX_RELAY_H +#define _LINUX_RELAY_H + +#include +#include +#include +#include +#include +#include +#include +#include + +/* Needs a _much_ better name... */ +#define FIX_SIZE(x) ((((x) - 1) & PAGE_MASK) + PAGE_SIZE) + +/* + * Tracks changes to rchan/rchan_buf structs + */ +#define RELAYFS_CHANNEL_VERSION 6 + +/* + * Per-cpu relay channel buffer + */ +struct rchan_buf +{ + void *start; /* start of channel buffer */ + void *data; /* start of current sub-buffer */ + size_t offset; /* current offset into sub-buffer */ + size_t subbufs_produced; /* count of sub-buffers produced */ + size_t subbufs_consumed; /* count of sub-buffers consumed */ + struct rchan *chan; /* associated channel */ + wait_queue_head_t read_wait; /* reader wait queue */ + struct work_struct wake_readers; /* reader wake-up work struct */ + struct dentry *dentry; /* channel file dentry */ + struct kref kref; /* channel buffer refcount */ + struct page **page_array; /* array of current buffer pages */ + unsigned int page_count; /* number of current buffer pages */ + unsigned int finalized; /* buffer has been finalized */ + size_t *padding; /* padding counts per sub-buffer */ + size_t prev_padding; /* temporary variable */ + size_t bytes_consumed; /* bytes consumed in cur read subbuf */ + unsigned int cpu; /* this buf's cpu */ +} ____cacheline_aligned; + +/* + * Relay channel data structure + */ +struct rchan +{ + u32 version; /* the version of this struct */ + size_t subbuf_size; /* sub-buffer size */ + size_t n_subbufs; /* number of sub-buffers per buffer */ + size_t alloc_size; /* total buffer size allocated */ + struct rchan_callbacks *cb; /* client callbacks */ + struct kref kref; /* channel refcount */ + void *private_data; /* for user-defined data */ + size_t last_toobig; /* tried to log event > subbuf size */ + struct rchan_buf *buf[NR_CPUS]; /* per-cpu channel buffers */ +}; + +/* + * Relay channel client callbacks + */ +struct rchan_callbacks +{ + /* + * subbuf_start - called on buffer-switch to a new sub-buffer + * @buf: the channel buffer containing the new sub-buffer + * @subbuf: the start of the new sub-buffer + * @prev_subbuf: the start of the previous sub-buffer + * @prev_padding: unused space at the end of previous sub-buffer + * + * The client should return 1 to continue logging, 0 to stop + * logging. + * + * NOTE: subbuf_start will also be invoked when the buffer is + * created, so that the first sub-buffer can be initialized + * if necessary. In this case, prev_subbuf will be NULL. + * + * NOTE: the client can reserve bytes at the beginning of the new + * sub-buffer by calling subbuf_start_reserve() in this callback. + */ + int (*subbuf_start) (struct rchan_buf *buf, + void *subbuf, + void *prev_subbuf, + size_t prev_padding); + + /* + * buf_mapped - relay buffer mmap notification + * @buf: the channel buffer + * @filp: relay file pointer + * + * Called when a relay file is successfully mmapped + */ + void (*buf_mapped)(struct rchan_buf *buf, + struct file *filp); + + /* + * buf_unmapped - relay buffer unmap notification + * @buf: the channel buffer + * @filp: relay file pointer + * + * Called when a relay file is successfully unmapped + */ + void (*buf_unmapped)(struct rchan_buf *buf, + struct file *filp); + /* + * create_buf_file - create file to represent a relay channel buffer + * @filename: the name of the file to create + * @parent: the parent of the file to create + * @mode: the mode of the file to create + * @buf: the channel buffer + * @is_global: outparam - set non-zero if the buffer should be global + * + * Called during relay_open(), once for each per-cpu buffer, + * to allow the client to create a file to be used to + * represent the corresponding channel buffer. If the file is + * created outside of relay, the parent must also exist in + * that filesystem. + * + * The callback should return the dentry of the file created + * to represent the relay buffer. + * + * Setting the is_global outparam to a non-zero value will + * cause relay_open() to create a single global buffer rather + * than the default set of per-cpu buffers. + * + * See Documentation/filesystems/relayfs.txt for more info. + */ + struct dentry *(*create_buf_file)(const char *filename, + struct dentry *parent, + int mode, + struct rchan_buf *buf, + int *is_global); + + /* + * remove_buf_file - remove file representing a relay channel buffer + * @dentry: the dentry of the file to remove + * + * Called during relay_close(), once for each per-cpu buffer, + * to allow the client to remove a file used to represent a + * channel buffer. + * + * The callback should return 0 if successful, negative if not. + */ + int (*remove_buf_file)(struct dentry *dentry); +}; + +/* + * CONFIG_RELAY kernel API, kernel/relay.c + */ + +struct rchan *relay_open(const char *base_filename, + struct dentry *parent, + size_t subbuf_size, + size_t n_subbufs, + struct rchan_callbacks *cb); +extern void relay_close(struct rchan *chan); +extern void relay_flush(struct rchan *chan); +extern void relay_subbufs_consumed(struct rchan *chan, + unsigned int cpu, + size_t consumed); +extern void relay_reset(struct rchan *chan); +extern int relay_buf_full(struct rchan_buf *buf); + +extern size_t relay_switch_subbuf(struct rchan_buf *buf, + size_t length); + +/** + * relay_write - write data into the channel + * @chan: relay channel + * @data: data to be written + * @length: number of bytes to write + * + * Writes data into the current cpu's channel buffer. + * + * Protects the buffer by disabling interrupts. Use this + * if you might be logging from interrupt context. Try + * __relay_write() if you know you won't be logging from + * interrupt context. + */ +static inline void relay_write(struct rchan *chan, + const void *data, + size_t length) +{ + unsigned long flags; + struct rchan_buf *buf; + + local_irq_save(flags); + buf = chan->buf[smp_processor_id()]; + if (unlikely(buf->offset + length > chan->subbuf_size)) + length = relay_switch_subbuf(buf, length); + memcpy(buf->data + buf->offset, data, length); + buf->offset += length; + local_irq_restore(flags); +} + +/** + * __relay_write - write data into the channel + * @chan: relay channel + * @data: data to be written + * @length: number of bytes to write + * + * Writes data into the current cpu's channel buffer. + * + * Protects the buffer by disabling preemption. Use + * relay_write() if you might be logging from interrupt + * context. + */ +static inline void __relay_write(struct rchan *chan, + const void *data, + size_t length) +{ + struct rchan_buf *buf; + + buf = chan->buf[get_cpu()]; + if (unlikely(buf->offset + length > buf->chan->subbuf_size)) + length = relay_switch_subbuf(buf, length); + memcpy(buf->data + buf->offset, data, length); + buf->offset += length; + put_cpu(); +} + +/** + * relay_reserve - reserve slot in channel buffer + * @chan: relay channel + * @length: number of bytes to reserve + * + * Returns pointer to reserved slot, NULL if full. + * + * Reserves a slot in the current cpu's channel buffer. + * Does not protect the buffer at all - caller must provide + * appropriate synchronization. + */ +static inline void *relay_reserve(struct rchan *chan, size_t length) +{ + void *reserved; + struct rchan_buf *buf = chan->buf[smp_processor_id()]; + + if (unlikely(buf->offset + length > buf->chan->subbuf_size)) { + length = relay_switch_subbuf(buf, length); + if (!length) + return NULL; + } + reserved = buf->data + buf->offset; + buf->offset += length; + + return reserved; +} + +/** + * subbuf_start_reserve - reserve bytes at the start of a sub-buffer + * @buf: relay channel buffer + * @length: number of bytes to reserve + * + * Helper function used to reserve bytes at the beginning of + * a sub-buffer in the subbuf_start() callback. + */ +static inline void subbuf_start_reserve(struct rchan_buf *buf, + size_t length) +{ + BUG_ON(length >= buf->chan->subbuf_size - 1); + buf->offset = length; +} + +/* + * exported relay file operations, kernel/relay.c + */ +extern struct file_operations relay_file_operations; + +#endif /* _LINUX_RELAY_H */ + -- cgit v1.2.1 From 2056a782f8e7e65fd4bfd027506b4ce1c5e9ccd4 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 23 Mar 2006 20:00:26 +0100 Subject: [PATCH] Block queue IO tracing support (blktrace) as of 2006-03-23 Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 + include/linux/blktrace_api.h | 277 +++++++++++++++++++++++++++++++++++++++++++ include/linux/compat_ioctl.h | 4 + include/linux/fs.h | 4 + include/linux/sched.h | 1 + 5 files changed, 289 insertions(+) create mode 100644 include/linux/blktrace_api.h (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 56bb6a4e15f3..c179966f1a2f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -22,6 +22,7 @@ typedef struct request_queue request_queue_t; struct elevator_queue; typedef struct elevator_queue elevator_t; struct request_pm_state; +struct blk_trace; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ @@ -416,6 +417,8 @@ struct request_queue unsigned int sg_reserved_size; int node; + struct blk_trace *blk_trace; + /* * reserved for flush operations */ diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h new file mode 100644 index 000000000000..b34d3e73d5ea --- /dev/null +++ b/include/linux/blktrace_api.h @@ -0,0 +1,277 @@ +#ifndef BLKTRACE_H +#define BLKTRACE_H + +#include +#include +#include + +/* + * Trace categories + */ +enum blktrace_cat { + BLK_TC_READ = 1 << 0, /* reads */ + BLK_TC_WRITE = 1 << 1, /* writes */ + BLK_TC_BARRIER = 1 << 2, /* barrier */ + BLK_TC_SYNC = 1 << 3, /* barrier */ + BLK_TC_QUEUE = 1 << 4, /* queueing/merging */ + BLK_TC_REQUEUE = 1 << 5, /* requeueing */ + BLK_TC_ISSUE = 1 << 6, /* issue */ + BLK_TC_COMPLETE = 1 << 7, /* completions */ + BLK_TC_FS = 1 << 8, /* fs requests */ + BLK_TC_PC = 1 << 9, /* pc requests */ + BLK_TC_NOTIFY = 1 << 10, /* special message */ + + BLK_TC_END = 1 << 15, /* only 16-bits, reminder */ +}; + +#define BLK_TC_SHIFT (16) +#define BLK_TC_ACT(act) ((act) << BLK_TC_SHIFT) + +/* + * Basic trace actions + */ +enum blktrace_act { + __BLK_TA_QUEUE = 1, /* queued */ + __BLK_TA_BACKMERGE, /* back merged to existing rq */ + __BLK_TA_FRONTMERGE, /* front merge to existing rq */ + __BLK_TA_GETRQ, /* allocated new request */ + __BLK_TA_SLEEPRQ, /* sleeping on rq allocation */ + __BLK_TA_REQUEUE, /* request requeued */ + __BLK_TA_ISSUE, /* sent to driver */ + __BLK_TA_COMPLETE, /* completed by driver */ + __BLK_TA_PLUG, /* queue was plugged */ + __BLK_TA_UNPLUG_IO, /* queue was unplugged by io */ + __BLK_TA_UNPLUG_TIMER, /* queue was unplugged by timer */ + __BLK_TA_INSERT, /* insert request */ + __BLK_TA_SPLIT, /* bio was split */ + __BLK_TA_BOUNCE, /* bio was bounced */ + __BLK_TA_REMAP, /* bio was remapped */ +}; + +/* + * Trace actions in full. Additionally, read or write is masked + */ +#define BLK_TA_QUEUE (__BLK_TA_QUEUE | BLK_TC_ACT(BLK_TC_QUEUE)) +#define BLK_TA_BACKMERGE (__BLK_TA_BACKMERGE | BLK_TC_ACT(BLK_TC_QUEUE)) +#define BLK_TA_FRONTMERGE (__BLK_TA_FRONTMERGE | BLK_TC_ACT(BLK_TC_QUEUE)) +#define BLK_TA_GETRQ (__BLK_TA_GETRQ | BLK_TC_ACT(BLK_TC_QUEUE)) +#define BLK_TA_SLEEPRQ (__BLK_TA_SLEEPRQ | BLK_TC_ACT(BLK_TC_QUEUE)) +#define BLK_TA_REQUEUE (__BLK_TA_REQUEUE | BLK_TC_ACT(BLK_TC_REQUEUE)) +#define BLK_TA_ISSUE (__BLK_TA_ISSUE | BLK_TC_ACT(BLK_TC_ISSUE)) +#define BLK_TA_COMPLETE (__BLK_TA_COMPLETE| BLK_TC_ACT(BLK_TC_COMPLETE)) +#define BLK_TA_PLUG (__BLK_TA_PLUG | BLK_TC_ACT(BLK_TC_QUEUE)) +#define BLK_TA_UNPLUG_IO (__BLK_TA_UNPLUG_IO | BLK_TC_ACT(BLK_TC_QUEUE)) +#define BLK_TA_UNPLUG_TIMER (__BLK_TA_UNPLUG_TIMER | BLK_TC_ACT(BLK_TC_QUEUE)) +#define BLK_TA_INSERT (__BLK_TA_INSERT | BLK_TC_ACT(BLK_TC_QUEUE)) +#define BLK_TA_SPLIT (__BLK_TA_SPLIT) +#define BLK_TA_BOUNCE (__BLK_TA_BOUNCE) +#define BLK_TA_REMAP (__BLK_TA_REMAP | BLK_TC_ACT(BLK_TC_QUEUE)) + +#define BLK_IO_TRACE_MAGIC 0x65617400 +#define BLK_IO_TRACE_VERSION 0x07 + +/* + * The trace itself + */ +struct blk_io_trace { + u32 magic; /* MAGIC << 8 | version */ + u32 sequence; /* event number */ + u64 time; /* in microseconds */ + u64 sector; /* disk offset */ + u32 bytes; /* transfer length */ + u32 action; /* what happened */ + u32 pid; /* who did it */ + u32 device; /* device number */ + u32 cpu; /* on what cpu did it happen */ + u16 error; /* completion error */ + u16 pdu_len; /* length of data after this trace */ +}; + +/* + * The remap event + */ +struct blk_io_trace_remap { + u32 device; + u32 __pad; + u64 sector; +}; + +enum { + Blktrace_setup = 1, + Blktrace_running, + Blktrace_stopped, +}; + +struct blk_trace { + int trace_state; + struct rchan *rchan; + unsigned long *sequence; + u16 act_mask; + u64 start_lba; + u64 end_lba; + u32 pid; + u32 dev; + struct dentry *dir; + struct dentry *dropped_file; + atomic_t dropped; +}; + +/* + * User setup structure passed with BLKTRACESTART + */ +struct blk_user_trace_setup { + char name[BDEVNAME_SIZE]; /* output */ + u16 act_mask; /* input */ + u32 buf_size; /* input */ + u32 buf_nr; /* input */ + u64 start_lba; + u64 end_lba; + u32 pid; +}; + +#if defined(CONFIG_BLK_DEV_IO_TRACE) +extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *); +extern void blk_trace_shutdown(request_queue_t *); +extern void __blk_add_trace(struct blk_trace *, sector_t, int, int, u32, int, int, void *); + +/** + * blk_add_trace_rq - Add a trace for a request oriented action + * @q: queue the io is for + * @rq: the source request + * @what: the action + * + * Description: + * Records an action against a request. Will log the bio offset + size. + * + **/ +static inline void blk_add_trace_rq(struct request_queue *q, struct request *rq, + u32 what) +{ + struct blk_trace *bt = q->blk_trace; + int rw = rq->flags & 0x07; + + if (likely(!bt)) + return; + + if (blk_pc_request(rq)) { + what |= BLK_TC_ACT(BLK_TC_PC); + __blk_add_trace(bt, 0, rq->data_len, rw, what, rq->errors, sizeof(rq->cmd), rq->cmd); + } else { + what |= BLK_TC_ACT(BLK_TC_FS); + __blk_add_trace(bt, rq->hard_sector, rq->hard_nr_sectors << 9, rw, what, rq->errors, 0, NULL); + } +} + +/** + * blk_add_trace_bio - Add a trace for a bio oriented action + * @q: queue the io is for + * @bio: the source bio + * @what: the action + * + * Description: + * Records an action against a bio. Will log the bio offset + size. + * + **/ +static inline void blk_add_trace_bio(struct request_queue *q, struct bio *bio, + u32 what) +{ + struct blk_trace *bt = q->blk_trace; + + if (likely(!bt)) + return; + + __blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw, what, !bio_flagged(bio, BIO_UPTODATE), 0, NULL); +} + +/** + * blk_add_trace_generic - Add a trace for a generic action + * @q: queue the io is for + * @bio: the source bio + * @rw: the data direction + * @what: the action + * + * Description: + * Records a simple trace + * + **/ +static inline void blk_add_trace_generic(struct request_queue *q, + struct bio *bio, int rw, u32 what) +{ + struct blk_trace *bt = q->blk_trace; + + if (likely(!bt)) + return; + + if (bio) + blk_add_trace_bio(q, bio, what); + else + __blk_add_trace(bt, 0, 0, rw, what, 0, 0, NULL); +} + +/** + * blk_add_trace_pdu_int - Add a trace for a bio with an integer payload + * @q: queue the io is for + * @what: the action + * @bio: the source bio + * @pdu: the integer payload + * + * Description: + * Adds a trace with some integer payload. This might be an unplug + * option given as the action, with the depth at unplug time given + * as the payload + * + **/ +static inline void blk_add_trace_pdu_int(struct request_queue *q, u32 what, + struct bio *bio, unsigned int pdu) +{ + struct blk_trace *bt = q->blk_trace; + u64 rpdu = cpu_to_be64(pdu); + + if (likely(!bt)) + return; + + if (bio) + __blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw, what, !bio_flagged(bio, BIO_UPTODATE), sizeof(rpdu), &rpdu); + else + __blk_add_trace(bt, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu); +} + +/** + * blk_add_trace_remap - Add a trace for a remap operation + * @q: queue the io is for + * @bio: the source bio + * @dev: target device + * @from: source sector + * @to: target sector + * + * Description: + * Device mapper or raid target sometimes need to split a bio because + * it spans a stripe (or similar). Add a trace for that action. + * + **/ +static inline void blk_add_trace_remap(struct request_queue *q, struct bio *bio, + dev_t dev, sector_t from, sector_t to) +{ + struct blk_trace *bt = q->blk_trace; + struct blk_io_trace_remap r; + + if (likely(!bt)) + return; + + r.device = cpu_to_be32(dev); + r.sector = cpu_to_be64(to); + + __blk_add_trace(bt, from, bio->bi_size, bio->bi_rw, BLK_TA_REMAP, !bio_flagged(bio, BIO_UPTODATE), sizeof(r), &r); +} + +#else /* !CONFIG_BLK_DEV_IO_TRACE */ +#define blk_trace_ioctl(bdev, cmd, arg) (-ENOTTY) +#define blk_trace_shutdown(q) do { } while (0) +#define blk_add_trace_rq(q, rq, what) do { } while (0) +#define blk_add_trace_bio(q, rq, what) do { } while (0) +#define blk_add_trace_generic(q, rq, rw, what) do { } while (0) +#define blk_add_trace_pdu_int(q, what, bio, pdu) do { } while (0) +#define blk_add_trace_remap(q, bio, dev, f, t) do {} while (0) +#endif /* CONFIG_BLK_DEV_IO_TRACE */ + +#endif diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h index ae7dfb790df3..efb518f16bb3 100644 --- a/include/linux/compat_ioctl.h +++ b/include/linux/compat_ioctl.h @@ -97,6 +97,10 @@ COMPATIBLE_IOCTL(BLKRRPART) COMPATIBLE_IOCTL(BLKFLSBUF) COMPATIBLE_IOCTL(BLKSECTSET) COMPATIBLE_IOCTL(BLKSSZGET) +COMPATIBLE_IOCTL(BLKTRACESTART) +COMPATIBLE_IOCTL(BLKTRACESTOP) +COMPATIBLE_IOCTL(BLKTRACESETUP) +COMPATIBLE_IOCTL(BLKTRACETEARDOWN) ULONG_IOCTL(BLKRASET) ULONG_IOCTL(BLKFRASET) /* RAID */ diff --git a/include/linux/fs.h b/include/linux/fs.h index f9c9dea636d0..9b34a1b03455 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -197,6 +197,10 @@ extern int dir_notify_enable; #define BLKBSZGET _IOR(0x12,112,size_t) #define BLKBSZSET _IOW(0x12,113,size_t) #define BLKGETSIZE64 _IOR(0x12,114,size_t) /* return device size in bytes (u64 *arg) */ +#define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup) +#define BLKTRACESTART _IO(0x12,116) +#define BLKTRACESTOP _IO(0x12,117) +#define BLKTRACETEARDOWN _IO(0x12,118) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 62e6314382f0..e60a91d5b369 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -706,6 +706,7 @@ struct task_struct { prio_array_t *array; unsigned short ioprio; + unsigned int btrace_seq; unsigned long sleep_avg; unsigned long long timestamp, last_ran; -- cgit v1.2.1 From 42d3b83fecb7b576d477244347982baa02fa4f44 Mon Sep 17 00:00:00 2001 From: Jim Cromie Date: Mon, 9 Jan 2006 23:22:24 +0100 Subject: [PATCH] hwmon: Allow sensor attributes arrays This patch refactors SENSOR_DEVICE_ATTR macro. First it creates a new macro SENSOR_ATTR() which expands to an initialization expression, then it uses that in SENSOR_DEVICE_ATTR, which declares and initializes a struct sensor_device_attribute. IOW, SENSOR_ATTR() imitates __ATTR() in include/linux/device.h. Signed-off-by: Jim Cromie Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/hwmon-sysfs.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hwmon-sysfs.h b/include/linux/hwmon-sysfs.h index 7eb4004b3601..dedca6a516b4 100644 --- a/include/linux/hwmon-sysfs.h +++ b/include/linux/hwmon-sysfs.h @@ -27,11 +27,13 @@ struct sensor_device_attribute{ #define to_sensor_dev_attr(_dev_attr) \ container_of(_dev_attr, struct sensor_device_attribute, dev_attr) -#define SENSOR_DEVICE_ATTR(_name,_mode,_show,_store,_index) \ -struct sensor_device_attribute sensor_dev_attr_##_name = { \ - .dev_attr = __ATTR(_name,_mode,_show,_store), \ - .index = _index, \ -} +#define SENSOR_ATTR(_name, _mode, _show, _store, _index) \ + { .dev_attr = __ATTR(_name, _mode, _show, _store), \ + .index = _index } + +#define SENSOR_DEVICE_ATTR(_name, _mode, _show, _store, _index) \ +struct sensor_device_attribute sensor_dev_attr_##_name \ + = SENSOR_ATTR(_name, _mode, _show, _store, _index) struct sensor_device_attribute_2 { struct device_attribute dev_attr; -- cgit v1.2.1 From 70adca5a9f506942ec88fb2d9d6e71ef271888b7 Mon Sep 17 00:00:00 2001 From: Jim Cromie Date: Wed, 18 Jan 2006 23:10:49 +0100 Subject: [PATCH] hwmon: Refactor SENSOR_DEVICE_ATTR_2 This patch refactors SENSOR_DEVICE_ATTR_2 macro, following pattern set by SENSOR_ATTR. First it creates a new macro SENSOR_ATTR_2() which expands to an initialization expression, then it uses that in SENSOR_DEVICE_ATTR_2, which declares and initializes a struct sensor_device_attribute_2. Signed-off-by: Jim Cromie Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/hwmon-sysfs.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hwmon-sysfs.h b/include/linux/hwmon-sysfs.h index dedca6a516b4..a90c09d331c1 100644 --- a/include/linux/hwmon-sysfs.h +++ b/include/linux/hwmon-sysfs.h @@ -43,11 +43,13 @@ struct sensor_device_attribute_2 { #define to_sensor_dev_attr_2(_dev_attr) \ container_of(_dev_attr, struct sensor_device_attribute_2, dev_attr) +#define SENSOR_ATTR_2(_name, _mode, _show, _store, _nr, _index) \ + { .dev_attr = __ATTR(_name, _mode, _show, _store), \ + .index = _index, \ + .nr = _nr } + #define SENSOR_DEVICE_ATTR_2(_name,_mode,_show,_store,_nr,_index) \ -struct sensor_device_attribute_2 sensor_dev_attr_##_name = { \ - .dev_attr = __ATTR(_name,_mode,_show,_store), \ - .index = _index, \ - .nr = _nr, \ -} +struct sensor_device_attribute_2 sensor_dev_attr_##_name \ + = SENSOR_ATTR_2(_name, _mode, _show, _store, _nr, _index) #endif /* _LINUX_HWMON_SYSFS_H */ -- cgit v1.2.1 From 5c085d369c2c4f18942ec8951466e186366d5c78 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 18 Jan 2006 23:16:04 +0100 Subject: [PATCH] i2c: Semaphore to mutex conversions, part 2 semaphore to mutex conversion. the conversion was generated via scripts, and the result was validated automatically via a script as well. build tested. Signed-off-by: Ingo Molnar Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 63f1d63cc1d8..1635ee25918f 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -32,7 +32,7 @@ #include #include /* for struct device */ #include /* for completion */ -#include +#include /* --- For i2c-isa ---------------------------------------------------- */ @@ -225,8 +225,8 @@ struct i2c_adapter { int (*client_unregister)(struct i2c_client *); /* data fields that are valid for all devices */ - struct semaphore bus_lock; - struct semaphore clist_lock; + struct mutex bus_lock; + struct mutex clist_lock; int timeout; int retries; -- cgit v1.2.1 From 2f27f46c49c096d86e7e63acd43cad3bc42f2383 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 5 Feb 2006 23:29:18 +0100 Subject: [PATCH] i2c: Drop the i2c-frodo bus driver Drop the i2c-frodo bus driver. It isn't referenced by the build system, and depends on code which was never included in 2.6 kernels. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c-id.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index 474c8f4f5d4f..ec311bc89439 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -172,7 +172,6 @@ #define I2C_HW_B_RIVA 0x010010 /* Riva based graphics cards */ #define I2C_HW_B_IOC 0x010011 /* IOC bit-wiggling */ #define I2C_HW_B_TSUNA 0x010012 /* DEC Tsunami chipset */ -#define I2C_HW_B_FRODO 0x010013 /* 2d3D SA-1110 Development Board */ #define I2C_HW_B_OMAHA 0x010014 /* Omaha I2C interface (ARM) */ #define I2C_HW_B_GUIDE 0x010015 /* Guide bit-basher */ #define I2C_HW_B_IXP2000 0x010016 /* GPIO on IXP2000 systems */ -- cgit v1.2.1 From 5f7ea3c58c9aa571617a9d77dd2fbd4bd81cc50a Mon Sep 17 00:00:00 2001 From: Martin Devera Date: Mon, 27 Feb 2006 23:11:45 +0100 Subject: [PATCH] I2C: i2c-piix4: Add Broadcom HT-1000 support Add Broadcom HT-1000 south bridge's PCI ID to i2c-piix driver. Note that at least on Supermicro H8SSL it uses non-standard SMBHSTCFG = 3 and standard values like 0 or 9 causes hangup. Signed-off-by: Martin Devera Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index ec3c32932620..f5a724fbf094 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1371,6 +1371,7 @@ #define PCI_DEVICE_ID_SERVERWORKS_OSB4 0x0200 #define PCI_DEVICE_ID_SERVERWORKS_CSB5 0x0201 #define PCI_DEVICE_ID_SERVERWORKS_CSB6 0x0203 +#define PCI_DEVICE_ID_SERVERWORKS_HT1000SB 0x0205 #define PCI_DEVICE_ID_SERVERWORKS_OSB4IDE 0x0211 #define PCI_DEVICE_ID_SERVERWORKS_CSB5IDE 0x0212 #define PCI_DEVICE_ID_SERVERWORKS_CSB6IDE 0x0213 -- cgit v1.2.1 From b82db5cedf78bfeb4a1c8a28ae284dc671d26eb3 Mon Sep 17 00:00:00 2001 From: Kristen Accardi Date: Tue, 17 Jan 2006 16:56:56 -0800 Subject: [PATCH] PCI: return max reserved busnr Change the semantics of this call to return the max reserved bus number instead of just the max assigned bus number. Signed-off-by: Kristen Carlson Accardi Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index fe1a2b02fc55..2039da1f3672 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -516,6 +516,7 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev * dev, int max, int pass void pci_walk_bus(struct pci_bus *top, void (*cb)(struct pci_dev *, void *), void *userdata); int pci_cfg_space_size(struct pci_dev *dev); +unsigned char pci_bus_max_busnr(struct pci_bus* bus); /* kmem_cache style wrapper around pci_alloc_consistent() */ -- cgit v1.2.1 From 6e325a62a0a228cd0222783802b53cce04551776 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 14 Feb 2006 18:52:22 +0200 Subject: [PATCH] PCI: make MSI quirk inheritable from the pci bus It turns out AMD 8131 quirk only affects MSI for devices behind the 8131 bridge. Handle this by adding a flags field in pci_bus, inherited from parent to child. Signed-off-by: Michael S. Tsirkin Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 2039da1f3672..d4d533fa5d30 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -95,6 +95,11 @@ enum pci_channel_state { pci_channel_io_perm_failure = (__force pci_channel_state_t) 3, }; +typedef unsigned short __bitwise pci_bus_flags_t; +enum pci_bus_flags { + PCI_BUS_FLAGS_NO_MSI = (pci_bus_flags_t) 1, +}; + /* * The pci_dev structure is used to describe PCI devices. */ @@ -203,7 +208,7 @@ struct pci_bus { char name[48]; unsigned short bridge_ctl; /* manage NO_ISA/FBB/et al behaviors */ - unsigned short pad2; + pci_bus_flags_t bus_flags; /* Inherited by child busses */ struct device *bridge; struct class_device class_dev; struct bin_attribute *legacy_io; /* legacy I/O for this bus */ -- cgit v1.2.1 From 3c990e9219ea0b0aee588473ce6c8a66cdee3ff5 Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Sat, 4 Mar 2006 21:52:42 -0500 Subject: [PATCH] PCI: fix pci_request_region[s] arg Add missing 'const' to pci_request_region[s] 'res_name' arg, since we pass it directly to __request_region(), whose 'name' arg is also const. Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index d4d533fa5d30..0aad5a378e95 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -490,9 +490,9 @@ void pdev_sort_resources(struct pci_dev *, struct resource_list *); void pci_fixup_irqs(u8 (*)(struct pci_dev *, u8 *), int (*)(struct pci_dev *, u8, u8)); #define HAVE_PCI_REQ_REGIONS 2 -int pci_request_regions(struct pci_dev *, char *); +int pci_request_regions(struct pci_dev *, const char *); void pci_release_regions(struct pci_dev *); -int pci_request_region(struct pci_dev *, int, char *); +int pci_request_region(struct pci_dev *, int, const char *); void pci_release_region(struct pci_dev *, int); /* drivers/pci/bus.c */ -- cgit v1.2.1 From acf356b12d13c8b43c486e53e8ee12f1f435ecc8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 24 Mar 2006 14:07:50 +0900 Subject: [PATCH] libata: add per-dev pio/mwdma/udma_mask Add per-dev pio/mwdma/udma_mask. All transfer mode limits used to be applied to ap->*_mask which unnecessarily restricted other devices sharing the port. This change will also benefit later EH speed down and hotplug. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 7a54244d30aa..fbe8ba212598 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -358,6 +358,11 @@ struct ata_device { unsigned int max_sectors; /* per-device max sectors */ unsigned int cdb_len; + /* per-dev xfer mask */ + unsigned int pio_mask; + unsigned int mwdma_mask; + unsigned int udma_mask; + /* for CHS addressing */ u16 cylinders; /* Number of cylinders */ u16 heads; /* Number of heads */ -- cgit v1.2.1 From 082776e4be791736c32baf818e50f501a7f83819 Mon Sep 17 00:00:00 2001 From: Nigel Cunningham Date: Thu, 23 Mar 2006 23:22:16 +1000 Subject: [PATCH] Make libata not powerdown drivers on PM_EVENT_FREEZE. At the moment libata doesn't pass pm_message_t down ata_device_suspend. This causes drives to be powered down when we just want a freeze, causing unnecessary wear and tear. This patch gets pm_message_t passed down so that it can be used to determine whether to power down the drive. Signed-off-by: Nigel Cunningham drivers/scsi/libata-core.c | 5 +++-- drivers/scsi/libata-scsi.c | 4 ++-- drivers/scsi/scsi_sysfs.c | 2 +- include/linux/libata.h | 4 ++-- include/scsi/scsi_host.h | 2 +- 5 files changed, 9 insertions(+), 8 deletions(-) Signed-off-by: Jeff Garzik --- include/linux/libata.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index fbe8ba212598..c52f13498556 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -520,9 +520,9 @@ extern void ata_eh_qc_retry(struct ata_queued_cmd *qc); extern int ata_scsi_release(struct Scsi_Host *host); extern unsigned int ata_host_intr(struct ata_port *ap, struct ata_queued_cmd *qc); extern int ata_scsi_device_resume(struct scsi_device *); -extern int ata_scsi_device_suspend(struct scsi_device *); +extern int ata_scsi_device_suspend(struct scsi_device *, pm_message_t state); extern int ata_device_resume(struct ata_port *, struct ata_device *); -extern int ata_device_suspend(struct ata_port *, struct ata_device *); +extern int ata_device_suspend(struct ata_port *, struct ata_device *, pm_message_t state); extern int ata_ratelimit(void); extern unsigned int ata_busy_sleep(struct ata_port *ap, unsigned long timeout_pat, -- cgit v1.2.1 From ebdfca6eb1b755d3bfe9a81339ecdafd92038c1a Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Thu, 23 Mar 2006 15:38:34 +0000 Subject: [PATCH] libata: add ata_dev_pair helper Signed-off-by: Alan Cox Signed-off-by: Jeff Garzik --- include/linux/libata.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index c52f13498556..80c2339da67d 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -573,6 +573,8 @@ extern int ata_std_bios_param(struct scsi_device *sdev, struct block_device *bdev, sector_t capacity, int geom[]); extern int ata_scsi_slave_config(struct scsi_device *sdev); +extern struct ata_device *ata_dev_pair(struct ata_port *ap, + struct ata_device *adev); /* * Timing helpers -- cgit v1.2.1 From 2f1f610b62bce36d6d50857859091b8989c70267 Mon Sep 17 00:00:00 2001 From: Brian King Date: Thu, 23 Mar 2006 17:30:15 -0600 Subject: [PATCH] libata: Remove dependence on host_set->dev for SAS Remove some of the dependence on the host_set struct in preparation for supporting SAS HBAs. Adds a struct device pointer to the ata_port struct. Signed-off-by: Brian King Signed-off-by: Jeff Garzik --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 80c2339da67d..047192253c3a 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -400,6 +400,7 @@ struct ata_port { struct ata_host_stats stats; struct ata_host_set *host_set; + struct device *dev; struct work_struct port_task; -- cgit v1.2.1 From 6961ec8267d08e21011457b05d2263ec06bdcfe1 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 24 Mar 2006 03:15:08 -0800 Subject: [PATCH] add sys_unshare to syscalls.h All architecture independent system calls should be declared in syscalls.h, add the one that is missing. Signed-off-by: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b9ea44ac0ddb..e487e3b60f60 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -568,5 +568,6 @@ asmlinkage long compat_sys_newfstatat(unsigned int dfd, char __user * filename, int flag); asmlinkage long compat_sys_openat(unsigned int dfd, const char __user *filename, int flags, int mode); +asmlinkage long sys_unshare(unsigned long unshare_flags); #endif -- cgit v1.2.1 From 9b04c997b1120feefa1e6ee8e2902270bc055cd2 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 24 Mar 2006 03:15:10 -0800 Subject: [PATCH] vfs: MS_VERBOSE should be MS_SILENT The meaning of MS_VERBOSE is backwards; if the bit is set, it really means, "don't be verbose". This is confusing and counter-intuitive. In addition, there is also no way to set the MS_VERBOSE flag in the mount(8) program in util-linux, but interesting, it does define options which would do the right thing if MS_SILENT were defined, which unfortunately we do not: #ifdef MS_SILENT { "quiet", 0, 0, MS_SILENT }, /* be quiet */ { "loud", 0, 1, MS_SILENT }, /* print out messages. */ #endif So the obvious fix is to deprecate the use of MS_VERBOSE and replace it with MS_SILENT. Signed-off-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9b34a1b03455..65e6df247ea5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -103,7 +103,9 @@ extern int dir_notify_enable; #define MS_BIND 4096 #define MS_MOVE 8192 #define MS_REC 16384 -#define MS_VERBOSE 32768 +#define MS_VERBOSE 32768 /* War is peace. Verbosity is silence. + MS_VERBOSE is deprecated. */ +#define MS_SILENT 32768 #define MS_POSIXACL (1<<16) /* VFS does not apply the umask */ #define MS_UNBINDABLE (1<<17) /* change to unbindable */ #define MS_PRIVATE (1<<18) /* change to private */ -- cgit v1.2.1 From 87e24802586333fa861861f6493c76039872755b Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Fri, 24 Mar 2006 03:15:44 -0800 Subject: [PATCH] bitmap: region cleanup Paul Mundt says: This patch set implements a number of patches to clean up and restructure the bitmap region code, in addition to extending the interface to support multiword spanning allocations. The current implementation (before this patch set) is limited by only being able to allocate pages <= BITS_PER_LONG, as noted by the strategically positioned BUG_ON() at lib/bitmap.c:752: /* We don't do regions of pages > BITS_PER_LONG. The * algorithm would be a simple look for multiple zeros in the * array, but there's no driver today that needs this. If you * trip this BUG(), you get to code it... */ BUG_ON(pages > BITS_PER_LONG); As I seem to have been the first person to trigger this, the result ends up being the following patch set with the help of Paul Jackson. The final patch in the series eliminates quite a bit of code duplication, so the bitmap code size ends up being smaller than the current implementation as an added bonus. After these are applied, it should already be possible to do multiword allocations with dma_alloc_coherent() out of ranges established by dma_declare_coherent_memory() on x86 without having to change any of the code, and the SH store queue API will follow up on this as the other user that needs support for this. This patch: Some code cleanup on the lib/bitmap.c bitmap_*_region() routines: * spacing * variable names * comments Has no change to code function. Signed-off-by: Paul Mundt Signed-off-by: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 7d8ff97b3e92..d9ed27969855 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -46,6 +46,9 @@ * bitmap_parse(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf * bitmap_scnlistprintf(buf, len, src, nbits) Print bitmap src as list to buf * bitmap_parselist(buf, dst, nbits) Parse bitmap dst from list + * bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region + * bitmap_release_region(bitmap, pos, order) Free specified bit region + * bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region */ /* -- cgit v1.2.1 From f6ef943813ac3085ece7252ea101d663581219f6 Mon Sep 17 00:00:00 2001 From: Bart Samwel Date: Fri, 24 Mar 2006 03:15:48 -0800 Subject: [PATCH] Represent dirty_*_centisecs as jiffies internally Make that the internal values for: /proc/sys/vm/dirty_writeback_centisecs /proc/sys/vm/dirty_expire_centisecs are stored as jiffies instead of centiseconds. Let the sysctl interface do the conversions with full precision using clock_t_to_jiffies, instead of doing overflow-sensitive on-the-fly conversions every time the values are used. Cons: apparent precision loss if HZ is not a multiple of 100, because of conversion back and forth. This is a common problem for all sysctl values that use proc_dointvec_userhz_jiffies. (There is only one other in-tree use, in net/core/neighbour.c.) Signed-off-by: Bart Samwel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/writeback.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index beaef5c7a0ea..609565961494 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -88,8 +88,8 @@ void throttle_vm_writeout(void); /* These are exported to sysctl. */ extern int dirty_background_ratio; extern int vm_dirty_ratio; -extern int dirty_writeback_centisecs; -extern int dirty_expire_centisecs; +extern int dirty_writeback_interval; +extern int dirty_expire_interval; extern int block_dump; extern int laptop_mode; -- cgit v1.2.1 From cdb0452789d365695b5b173542af9c7e3d24f185 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 24 Mar 2006 03:15:57 -0800 Subject: [PATCH] kill include/linux/platform.h, default_idle() cleanup include/linux/platform.h contained nothing that was actually used except the default_idle() prototype, and is therefore removed by this patch. This patch does the following with the platform specific default_idle() functions on different architectures: - remove the unused function: - parisc - sparc64 - make the needlessly global function static: - arm - h8300 - m68k - m68knommu - s390 - v850 - x86_64 - add a prototype in asm/system.h: - cris - i386 - ia64 Signed-off-by: Adrian Bunk Acked-by: Patrick Mochel Acked-by: Kyle McMartin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/platform.h | 43 ------------------------------------------- 1 file changed, 43 deletions(-) delete mode 100644 include/linux/platform.h (limited to 'include/linux') diff --git a/include/linux/platform.h b/include/linux/platform.h deleted file mode 100644 index 3c33084a6ec2..000000000000 --- a/include/linux/platform.h +++ /dev/null @@ -1,43 +0,0 @@ -/* - * include/linux/platform.h - platform driver definitions - * - * Because of the prolific consumerism of the average American, - * and the dominant marketing budgets of PC OEMs, we have been - * blessed with frequent updates of the PC architecture. - * - * While most of these calls are singular per architecture, they - * require an extra layer of abstraction on the x86 so the right - * subsystem gets the right call. - * - * Basically, this consolidates the power off and reboot callbacks - * into one structure, as well as adding power management hooks. - * - * When adding a platform driver, please make sure all callbacks are - * filled. There are defaults defined below that do nothing; use those - * if you do not support that callback. - */ - -#ifndef _PLATFORM_H_ -#define _PLATFORM_H_ -#ifdef __KERNEL__ - -#include - -struct platform_t { - char * name; - u32 suspend_states; - void (*reboot)(char * cmd); - void (*halt)(void); - void (*power_off)(void); - int (*suspend)(int state, int flags); - void (*idle)(void); -}; - -extern struct platform_t * platform; -extern void default_reboot(char * cmd); -extern void default_halt(void); -extern int default_suspend(int state, int flags); -extern void default_idle(void); - -#endif /* __KERNEL__ */ -#endif /* _PLATFORM_H */ -- cgit v1.2.1 From 825a46af5ac171f9f41f794a0a00165588ba1589 Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Fri, 24 Mar 2006 03:16:03 -0800 Subject: [PATCH] cpuset memory spread basic implementation This patch provides the implementation and cpuset interface for an alternative memory allocation policy that can be applied to certain kinds of memory allocations, such as the page cache (file system buffers) and some slab caches (such as inode caches). The policy is called "memory spreading." If enabled, it spreads out these kinds of memory allocations over all the nodes allowed to a task, instead of preferring to place them on the node where the task is executing. All other kinds of allocations, including anonymous pages for a tasks stack and data regions, are not affected by this policy choice, and continue to be allocated preferring the node local to execution, as modified by the NUMA mempolicy. There are two boolean flag files per cpuset that control where the kernel allocates pages for the file system buffers and related in kernel data structures. They are called 'memory_spread_page' and 'memory_spread_slab'. If the per-cpuset boolean flag file 'memory_spread_page' is set, then the kernel will spread the file system buffers (page cache) evenly over all the nodes that the faulting task is allowed to use, instead of preferring to put those pages on the node where the task is running. If the per-cpuset boolean flag file 'memory_spread_slab' is set, then the kernel will spread some file system related slab caches, such as for inodes and dentries evenly over all the nodes that the faulting task is allowed to use, instead of preferring to put those pages on the node where the task is running. The implementation is simple. Setting the cpuset flags 'memory_spread_page' or 'memory_spread_cache' turns on the per-process flags PF_SPREAD_PAGE or PF_SPREAD_SLAB, respectively, for each task that is in the cpuset or subsequently joins that cpuset. In subsequent patches, the page allocation calls for the affected page cache and slab caches are modified to perform an inline check for these flags, and if set, a call to a new routine cpuset_mem_spread_node() returns the node to prefer for the allocation. The cpuset_mem_spread_node() routine is also simple. It uses the value of a per-task rotor cpuset_mem_spread_rotor to select the next node in the current tasks mems_allowed to prefer for the allocation. This policy can provide substantial improvements for jobs that need to place thread local data on the corresponding node, but that need to access large file system data sets that need to be spread across the several nodes in the jobs cpuset in order to fit. Without this patch, especially for jobs that might have one thread reading in the data set, the memory allocation across the nodes in the jobs cpuset can become very uneven. A couple of Copyright year ranges are updated as well. And a couple of email addresses that can be found in the MAINTAINERS file are removed. Signed-off-by: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuset.h | 29 ++++++++++++++++++++++++++++- include/linux/sched.h | 3 +++ 2 files changed, 31 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 3bc606927116..9354722a9217 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -4,7 +4,7 @@ * cpuset interface * * Copyright (C) 2003 BULL SA - * Copyright (C) 2004 Silicon Graphics, Inc. + * Copyright (C) 2004-2006 Silicon Graphics, Inc. * */ @@ -51,6 +51,18 @@ extern char *cpuset_task_status_allowed(struct task_struct *task, char *buffer); extern void cpuset_lock(void); extern void cpuset_unlock(void); +extern int cpuset_mem_spread_node(void); + +static inline int cpuset_do_page_mem_spread(void) +{ + return current->flags & PF_SPREAD_PAGE; +} + +static inline int cpuset_do_slab_mem_spread(void) +{ + return current->flags & PF_SPREAD_SLAB; +} + #else /* !CONFIG_CPUSETS */ static inline int cpuset_init_early(void) { return 0; } @@ -99,6 +111,21 @@ static inline char *cpuset_task_status_allowed(struct task_struct *task, static inline void cpuset_lock(void) {} static inline void cpuset_unlock(void) {} +static inline int cpuset_mem_spread_node(void) +{ + return 0; +} + +static inline int cpuset_do_page_mem_spread(void) +{ + return 0; +} + +static inline int cpuset_do_slab_mem_spread(void) +{ + return 0; +} + #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index e60a91d5b369..b0e37cfa09f5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -869,6 +869,7 @@ struct task_struct { struct cpuset *cpuset; nodemask_t mems_allowed; int cpuset_mems_generation; + int cpuset_mem_spread_rotor; #endif atomic_t fs_excl; /* holding fs exclusive resources */ struct rcu_head rcu; @@ -929,6 +930,8 @@ static inline void put_task_struct(struct task_struct *t) #define PF_BORROWED_MM 0x00400000 /* I am a kthread doing use_mm */ #define PF_RANDOMIZE 0x00800000 /* randomize virtual address space */ #define PF_SWAPWRITE 0x01000000 /* Allowed to write to swap */ +#define PF_SPREAD_PAGE 0x04000000 /* Spread page cache over cpuset */ +#define PF_SPREAD_SLAB 0x08000000 /* Spread some slab caches over cpuset */ /* * Only the _current_ task can read/write to tsk->flags, but other -- cgit v1.2.1 From 44110fe385af23ca5eee8a6ad4ff55d50339097a Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Fri, 24 Mar 2006 03:16:04 -0800 Subject: [PATCH] cpuset memory spread page cache implementation and hooks Change the page cache allocation calls to support cpuset memory spreading. See the previous patch, cpuset_mem_spread, for an explanation of cpuset memory spreading. On systems without cpusets configured in the kernel, this is no change. On systems with cpusets configured in the kernel, but the "memory_spread" cpuset option not enabled for the current tasks cpuset, this adds a call to a cpuset routine and failed bit test of the processor state flag PF_SPREAD_PAGE. On tasks in cpusets with "memory_spread" enabled, this adds a call to a cpuset routine that computes which of the tasks mems_allowed nodes should be preferred for this allocation. If memory spreading applies to a particular allocation, then any other NUMA mempolicy does not apply. Signed-off-by: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ee700c6eb442..839f0b3c23aa 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -51,6 +51,10 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) #define page_cache_release(page) put_page(page) void release_pages(struct page **pages, int nr, int cold); +#ifdef CONFIG_NUMA +extern struct page *page_cache_alloc(struct address_space *x); +extern struct page *page_cache_alloc_cold(struct address_space *x); +#else static inline struct page *page_cache_alloc(struct address_space *x) { return alloc_pages(mapping_gfp_mask(x), 0); @@ -60,6 +64,7 @@ static inline struct page *page_cache_alloc_cold(struct address_space *x) { return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD, 0); } +#endif typedef int filler_t(void *, struct page *); -- cgit v1.2.1 From 101a50019ae5e370d73984ee05d56dd3b08f330a Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Fri, 24 Mar 2006 03:16:07 -0800 Subject: [PATCH] cpuset memory spread slab cache implementation Provide the slab cache infrastructure to support cpuset memory spreading. See the previous patches, cpuset_mem_spread, for an explanation of cpuset memory spreading. This patch provides a slab cache SLAB_MEM_SPREAD flag. If set in the kmem_cache_create() call defining a slab cache, then any task marked with the process state flag PF_MEMSPREAD will spread memory page allocations for that cache over all the allowed nodes, instead of preferring the local (faulting) node. On systems not configured with CONFIG_NUMA, this results in no change to the page allocation code path for slab caches. On systems with cpusets configured in the kernel, but the "memory_spread" cpuset option not enabled for the current tasks cpuset, this adds a call to a cpuset routine and failed bit test of the processor state flag PF_SPREAD_SLAB. For tasks so marked, a second inline test is done for the slab cache flag SLAB_MEM_SPREAD, and if that is set and if the allocation is not in_interrupt(), this adds a call to to a cpuset routine that computes which of the tasks mems_allowed nodes should be preferred for this allocation. ==> This patch adds another hook into the performance critical code path to allocating objects from the slab cache, in the ____cache_alloc() chunk, below. The next patch optimizes this hook, reducing the impact of the combined mempolicy plus memory spreading hooks on this critical code path to a single check against the tasks task_struct flags word. This patch provides the generic slab flags and logic needed to apply memory spreading to a particular slab. A subsequent patch will mark a few specific slab caches for this placement policy. Signed-off-by: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 2b28c849d75a..e2ee5b268797 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -46,6 +46,7 @@ typedef struct kmem_cache kmem_cache_t; what is reclaimable later*/ #define SLAB_PANIC 0x00040000UL /* panic if kmem_cache_create() fails */ #define SLAB_DESTROY_BY_RCU 0x00080000UL /* defer freeing pages to RCU */ +#define SLAB_MEM_SPREAD 0x00100000UL /* Spread some memory over cpuset */ /* flags passed to a constructor func */ #define SLAB_CTOR_CONSTRUCTOR 0x001UL /* if not set, then deconstructor */ -- cgit v1.2.1 From c61afb181c649754ea221f104e268cbacfc993e3 Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Fri, 24 Mar 2006 03:16:08 -0800 Subject: [PATCH] cpuset memory spread slab cache optimizations The hooks in the slab cache allocator code path for support of NUMA mempolicies and cpuset memory spreading are in an important code path. Many systems will use neither feature. This patch optimizes those hooks down to a single check of some bits in the current tasks task_struct flags. For non NUMA systems, this hook and related code is already ifdef'd out. The optimization is done by using another task flag, set if the task is using a non-default NUMA mempolicy. Taking this flag bit along with the PF_SPREAD_PAGE and PF_SPREAD_SLAB flag bits added earlier in this 'cpuset memory spreading' patch set, one can check for the combination of any of these special case memory placement mechanisms with a single test of the current tasks task_struct flags. This patch also tightens up the code, to save a few bytes of kernel text space, and moves some of it out of line. Due to the nested inlines called from multiple places, we were ending up with three copies of this code, which once we get off the main code path (for local node allocation) seems a bit wasteful of instruction memory. Signed-off-by: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 5 +++++ include/linux/sched.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index bbd2221923c3..6a7621b2b12b 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -147,6 +147,7 @@ extern void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *new); extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new); extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new); +extern void mpol_fix_fork_child_flag(struct task_struct *p); #define set_cpuset_being_rebound(x) (cpuset_being_rebound = (x)) #ifdef CONFIG_CPUSET @@ -248,6 +249,10 @@ static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { } +static inline void mpol_fix_fork_child_flag(struct task_struct *p) +{ +} + #define set_cpuset_being_rebound(x) do {} while (0) static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma, diff --git a/include/linux/sched.h b/include/linux/sched.h index b0e37cfa09f5..2cda439ece43 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -932,6 +932,7 @@ static inline void put_task_struct(struct task_struct *t) #define PF_SWAPWRITE 0x01000000 /* Allowed to write to swap */ #define PF_SPREAD_PAGE 0x04000000 /* Spread page cache over cpuset */ #define PF_SPREAD_SLAB 0x08000000 /* Spread some slab caches over cpuset */ +#define PF_MEMPOLICY 0x10000000 /* Non-default NUMA mempolicy */ /* * Only the _current_ task can read/write to tsk->flags, but other -- cgit v1.2.1 From ab7efcc97ebc92e03c0474dfd38f9c7b84b84115 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Fri, 24 Mar 2006 03:16:17 -0800 Subject: [PATCH] abstract type/size specification for assembly Provide abstraction for generating type and size information of assembly routines and data, while permitting architectures to override these defaults. Signed-off-by: Jan Beulich Cc: "Russell King" Cc: Ralf Baechle Cc: "Andi Kleen" Cc: "Luck, Tony" Cc: Miles Bader Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/linkage.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 147eb01e0d4b..c08c9983e840 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -28,17 +28,27 @@ #define ALIGN __ALIGN #define ALIGN_STR __ALIGN_STR +#ifndef ENTRY #define ENTRY(name) \ .globl name; \ ALIGN; \ name: +#endif #define KPROBE_ENTRY(name) \ .section .kprobes.text, "ax"; \ - .globl name; \ - ALIGN; \ - name: + ENTRY(name) +#ifndef END +#define END(name) \ + .size name, .-name +#endif + +#ifndef ENDPROC +#define ENDPROC(name) \ + .type name, @function; \ + END(name) +#endif #endif -- cgit v1.2.1 From ebcf28e1c7a295f3321249dd235ad2e45938fdd9 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 24 Mar 2006 03:18:04 -0800 Subject: [PATCH] fadvise(): write commands Add two new linux-specific fadvise extensions(): LINUX_FADV_ASYNC_WRITE: start async writeout of any dirty pages between file offsets `offset' and `offset+len'. Any pages which are currently under writeout are skipped, whether or not they are dirty. LINUX_FADV_WRITE_WAIT: wait upon writeout of any dirty pages between file offsets `offset' and `offset+len'. By combining these two operations the application may do several things: LINUX_FADV_ASYNC_WRITE: push some or all of the dirty pages at the disk. LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE: push all of the currently dirty pages at the disk. LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE, LINUX_FADV_WRITE_WAIT: push all of the currently dirty pages at the disk, wait until they have been written. It should be noted that none of these operations write out the file's metadata. So unless the application is strictly performing overwrites of already-instantiated disk blocks, there are no guarantees here that the data will be available after a crash. To complete this suite of operations I guess we should have a "sync file metadata only" operation. This gives applications access to all the building blocks needed for all sorts of sync operations. But sync-metadata doesn't fit well with the fadvise() interface. Probably it should be a new syscall: sys_fmetadatasync(). The patch also diddles with the meaning of `endbyte' in sys_fadvise64_64(). It is made to represent that last affected byte in the file (ie: it is inclusive). Generally, all these byterange and pagerange functions are inclusive so we can easily represent EOF with -1. As Ulrich notes, these two functions are somewhat abusive of the fadvise() concept, which appears to be "set the future policy for this fd". But these commands are a perfect fit with the fadvise() impementation, and several of the existing fadvise() commands are synchronous and don't affect future policy either. I think we can live with the slight incongruity. Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fadvise.h | 6 ++++++ include/linux/fs.h | 5 +++++ 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fadvise.h b/include/linux/fadvise.h index e8e747139b9a..b2913bba35d8 100644 --- a/include/linux/fadvise.h +++ b/include/linux/fadvise.h @@ -18,4 +18,10 @@ #define POSIX_FADV_NOREUSE 5 /* Data will be accessed once. */ #endif +/* + * Linux-specific fadvise() extensions: + */ +#define LINUX_FADV_ASYNC_WRITE 32 /* Start writeout on range */ +#define LINUX_FADV_WRITE_WAIT 33 /* Wait upon writeout to range */ + #endif /* FADVISE_H_INCLUDED */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 65e6df247ea5..0ad70c1e5e55 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1473,6 +1473,11 @@ extern int filemap_fdatawait(struct address_space *); extern int filemap_write_and_wait(struct address_space *mapping); extern int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); +extern int wait_on_page_writeback_range(struct address_space *mapping, + pgoff_t start, pgoff_t end); +extern int __filemap_fdatawrite_range(struct address_space *mapping, + loff_t start, loff_t end, int sync_mode); + extern void sync_supers(void); extern void sync_filesystems(int wait); extern void emergency_sync(void); -- cgit v1.2.1 From fa5a734e406b53761fcc5ee22366006f71112c2d Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 24 Mar 2006 03:18:10 -0800 Subject: [PATCH] balance_dirty_pages_ratelimited: take nr_pages arg Modify balance_dirty_pages_ratelimited() so that it can take a number-of-pages-which-I-just-dirtied argument. For msync(). Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/writeback.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 609565961494..56f92fcbe94a 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -99,7 +99,15 @@ int dirty_writeback_centisecs_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); void page_writeback_init(void); -void balance_dirty_pages_ratelimited(struct address_space *mapping); +void balance_dirty_pages_ratelimited_nr(struct address_space *mapping, + unsigned long nr_pages_dirtied); + +static inline void +balance_dirty_pages_ratelimited(struct address_space *mapping) +{ + balance_dirty_pages_ratelimited_nr(mapping, 1); +} + int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0); int do_writepages(struct address_space *mapping, struct writeback_control *wbc); int sync_page_range(struct inode *inode, struct address_space *mapping, -- cgit v1.2.1 From 4741c9fd36b3bcadd37238321c469049da94a4b9 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 24 Mar 2006 03:18:11 -0800 Subject: [PATCH] set_page_dirty() return value fixes We need set_page_dirty() to return true if it actually transitioned the page from a clean to dirty state. This wasn't right in a couple of places. Do a kernel-wide audit, fix things up. This leaves open the possibility of returning a negative errno from set_page_dirty() sometime in the future. But we don't do that at present. Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 0ad70c1e5e55..092cfaee0cd2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -350,7 +350,7 @@ struct address_space_operations { /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); - /* Set a page dirty */ + /* Set a page dirty. Return true if this dirtied it */ int (*set_page_dirty)(struct page *page); int (*readpages)(struct file *filp, struct address_space *mapping, -- cgit v1.2.1 From 18e79b40ed9c5223b88771f805c69f5993fc131b Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 24 Mar 2006 03:18:14 -0800 Subject: [PATCH] fsync: extract internal code Pull the guts out of do_fsync() - we can use it elsewhere. Cc: Hugh Dickins Cc: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 092cfaee0cd2..215696a0f16f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1478,6 +1478,7 @@ extern int wait_on_page_writeback_range(struct address_space *mapping, extern int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode); +extern long do_fsync(struct file *file, int datasync); extern void sync_supers(void); extern void sync_filesystems(int wait); extern void emergency_sync(void); -- cgit v1.2.1 From 97f2478db161714d0e3e864f38f5789c66f98b81 Mon Sep 17 00:00:00 2001 From: Pierre Ossman Date: Fri, 24 Mar 2006 03:18:16 -0800 Subject: [PATCH] Secure Digital Host Controller id and regs Class code and register definitions for the Secure Digital Host Controller standard. Signed-off-by: Pierre Ossman Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index f3dcf89d5232..6f080ae59286 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -69,6 +69,7 @@ #define PCI_CLASS_SYSTEM_TIMER 0x0802 #define PCI_CLASS_SYSTEM_RTC 0x0803 #define PCI_CLASS_SYSTEM_PCI_HOTPLUG 0x0804 +#define PCI_CLASS_SYSTEM_SDHCI 0x0805 #define PCI_CLASS_SYSTEM_OTHER 0x0880 #define PCI_BASE_CLASS_INPUT 0x09 -- cgit v1.2.1 From 208a08f7cc2a8932ed76162d9844f9ae7d7fc015 Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Fri, 24 Mar 2006 03:18:21 -0800 Subject: [PATCH] ide: Allow IDE interface to specify its not capable of 32-bit operations In some embedded systems the IDE hardware interface may only support 16-bit or smaller accesses. Allow the interface to specify if this is the case and don't allow the drive or user to override the setting. Signed-off-by: Kumar Gala Acked-by: Bartlomiej Zolnierkiewicz Cc: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ide.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index a7fc4cc79b23..8d2db412ba9c 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -792,6 +792,7 @@ typedef struct hwif_s { unsigned no_dsc : 1; /* 0 default, 1 dsc_overlap disabled */ unsigned auto_poll : 1; /* supports nop auto-poll */ unsigned sg_mapped : 1; /* sg_table and sg_nents are ready */ + unsigned no_io_32bit : 1; /* 1 = can not do 32-bit IO ops */ struct device gendev; struct completion gendev_rel_comp; /* To deal with device release() */ -- cgit v1.2.1 From 6687a97d4041f996f725902d2990e5de6ef5cbe5 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 24 Mar 2006 03:18:41 -0800 Subject: [PATCH] timer-irq-driven soft-watchdog, cleanups Make the softlockup detector purely timer-interrupt driven, removing softirq-context (timer) dependencies. This means that if the softlockup watchdog triggers, it has truly observed a longer than 10 seconds scheduling delay of a SCHED_FIFO prio 99 task. (the patch also turns off the softlockup detector during the initial bootup phase and does small style fixes) Signed-off-by: Ingo Molnar Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2cda439ece43..e0054c1b9a09 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -206,11 +206,11 @@ extern void update_process_times(int user); extern void scheduler_tick(void); #ifdef CONFIG_DETECT_SOFTLOCKUP -extern void softlockup_tick(struct pt_regs *regs); +extern void softlockup_tick(void); extern void spawn_softlockup_task(void); extern void touch_softlockup_watchdog(void); #else -static inline void softlockup_tick(struct pt_regs *regs) +static inline void softlockup_tick(void) { } static inline void spawn_softlockup_task(void) -- cgit v1.2.1 From 96840aa00a031069a136ec4c55d0bdd09ac6d3a7 Mon Sep 17 00:00:00 2001 From: Davi Arnaut Date: Fri, 24 Mar 2006 03:18:42 -0800 Subject: [PATCH] strndup_user() This patch series creates a strndup_user() function to easy copying C strings from userspace. Also we avoid common pitfalls like userspace modifying the final \0 after the strlen_user(). Signed-off-by: Davi Arnaut Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index 369be3264a55..dee221429ad0 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -18,6 +18,8 @@ extern char * strsep(char **,const char *); extern __kernel_size_t strspn(const char *,const char *); extern __kernel_size_t strcspn(const char *,const char *); +extern char *strndup_user(const char __user *, long); + /* * Include machine specific inline routines */ -- cgit v1.2.1 From aec5c3c1a929d7d79a420e943285cf3ba26a7c0d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 25 Mar 2006 01:33:34 +0900 Subject: [PATCH] libata: kill E.D.D. E.D.D. has no user in-tree and mostly useless. Kill it. For possible out-of-tree users, add a nice warning message and error handling if LLDD doesn't report any useable reset mechanism (and thus tries to use E.D.D.). Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 047192253c3a..9fcc061e3adf 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -161,7 +161,6 @@ enum { ATA_QCFLAG_EH_SCHEDULED = (1 << 5), /* EH scheduled */ /* various lengths of time */ - ATA_TMOUT_EDD = 5 * HZ, /* heuristic */ ATA_TMOUT_PIO = 30 * HZ, ATA_TMOUT_BOOT = 30 * HZ, /* heuristic */ ATA_TMOUT_BOOT_QUICK = 7 * HZ, /* heuristic */ -- cgit v1.2.1