From 37fb3a30b46237f23cfdf7ee09d49f9888dd13bf Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 8 Aug 2011 16:08:08 +0200 Subject: fuse: fix flock Commit a9ff4f87 "fuse: support BSD locking semantics" overlooked a number of issues with supporing flock locks over existing POSIX locking infrastructure: - it's not backward compatible, passing flock(2) calls to userspace unconditionally (if userspace sets FUSE_POSIX_LOCKS) - it doesn't cater for the fact that flock locks are automatically unlocked on file release - it doesn't take into account the fact that flock exclusive locks (write locks) don't need an fd opened for write. The last one invalidates the original premise of the patch that flock locks can be emulated with POSIX locks. This patch fixes the first two issues. The last one needs to be fixed in userspace if the filesystem assumed that a write lock will happen only on a file operned for write (as in the case of the current fuse library). Reported-by: Sebastian Pipping Signed-off-by: Miklos Szeredi --- include/linux/fuse.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index d464de53db43..464cff526860 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -47,6 +47,9 @@ * - FUSE_IOCTL_UNRESTRICTED shall now return with array of 'struct * fuse_ioctl_iovec' instead of ambiguous 'struct iovec' * - add FUSE_IOCTL_32BIT flag + * + * 7.17 + * - add FUSE_FLOCK_LOCKS and FUSE_RELEASE_FLOCK_UNLOCK */ #ifndef _LINUX_FUSE_H @@ -78,7 +81,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 16 +#define FUSE_KERNEL_MINOR_VERSION 17 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -153,8 +156,10 @@ struct fuse_file_lock { /** * INIT request/reply flags * + * FUSE_POSIX_LOCKS: remote locking for POSIX file locks * FUSE_EXPORT_SUPPORT: filesystem handles lookups of "." and ".." * FUSE_DONT_MASK: don't apply umask to file mode on create operations + * FUSE_FLOCK_LOCKS: remote locking for BSD style file locks */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -163,6 +168,7 @@ struct fuse_file_lock { #define FUSE_EXPORT_SUPPORT (1 << 4) #define FUSE_BIG_WRITES (1 << 5) #define FUSE_DONT_MASK (1 << 6) +#define FUSE_FLOCK_LOCKS (1 << 10) /** * CUSE INIT request/reply flags @@ -175,6 +181,7 @@ struct fuse_file_lock { * Release flags */ #define FUSE_RELEASE_FLUSH (1 << 0) +#define FUSE_RELEASE_FLOCK_UNLOCK (1 << 1) /** * Getattr flags -- cgit v1.2.3 From bb0822954aab7d23a3f902c2a103ee0242f6046e Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Tue, 16 Aug 2011 13:37:14 -0600 Subject: squeeze max-pause area and drop pass-good area Revert the pass-good area introduced in ffd1f609ab10 ("writeback: introduce max-pause and pass-good dirty limits") and make the max-pause area smaller and safe. This fixes ~30% performance regression in the ext3 data=writeback fio_mmap_randwrite_64k/fio_mmap_randrw_64k test cases, where there are 12 JBOD disks, on each disk runs 8 concurrent tasks doing reads+writes. Using deadline scheduler also has a regression, but not that big as CFQ, so this suggests we have some write starvation. The test logs show that - the disks are sometimes under utilized - global dirty pages sometimes rush high to the pass-good area for several hundred seconds, while in the mean time some bdi dirty pages drop to very low value (bdi_dirty << bdi_thresh). Then suddenly the global dirty pages dropped under global dirty threshold and bdi_dirty rush very high (for example, 2 times higher than bdi_thresh). During which time balance_dirty_pages() is not called at all. So the problems are 1) The random writes progress so slow that they break the assumption of the max-pause logic that "8 pages per 200ms is typically more than enough to curb heavy dirtiers". 2) The max-pause logic ignored task_bdi_thresh and thus opens the possibility for some bdi's to over dirty pages, leading to (bdi_dirty >> bdi_thresh) and then (bdi_thresh >> bdi_dirty) for others. 3) The higher max-pause/pass-good thresholds somehow leads to the bad swing of dirty pages. The fix is to allow the task to slightly dirty over task_bdi_thresh, but no way to exceed bdi_dirty and/or global dirty_thresh. Tests show that it fixed the JBOD regression completely (both behavior and performance), while still being able to cut down large pause times in balance_dirty_pages() for single-disk cases. Reported-by: Li Shaohua Tested-by: Li Shaohua Acked-by: Jan Kara Signed-off-by: Wu Fengguang --- include/linux/writeback.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index f1bfa12ea246..2b8963ff0f35 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -12,15 +12,6 @@ * * (thresh - thresh/DIRTY_FULL_SCOPE, thresh) * - * The 1/16 region above the global dirty limit will be put to maximum pauses: - * - * (limit, limit + limit/DIRTY_MAXPAUSE_AREA) - * - * The 1/16 region above the max-pause region, dirty exceeded bdi's will be put - * to loops: - * - * (limit + limit/DIRTY_MAXPAUSE_AREA, limit + limit/DIRTY_PASSGOOD_AREA) - * * Further beyond, all dirtier tasks will enter a loop waiting (possibly long * time) for the dirty pages to drop, unless written enough pages. * @@ -31,8 +22,6 @@ */ #define DIRTY_SCOPE 8 #define DIRTY_FULL_SCOPE (DIRTY_SCOPE / 2) -#define DIRTY_MAXPAUSE_AREA 16 -#define DIRTY_PASSGOOD_AREA 8 /* * 4MB minimal write chunk size -- cgit v1.2.3 From 0d7c5f2572ccfa7bf83292b1506926663f2d164a Mon Sep 17 00:00:00 2001 From: Pavan Savoy Date: Wed, 10 Aug 2011 10:18:31 -0500 Subject: drivers:misc:ti-st: platform hooks for chip states Certain platform specific or Host-WiLink Interface specific actions would be required to be taken when the chip is being enabled and after the chip is disabled such as configuration of the mux modes for the GPIO of host connected to the nshutdown of the chip or relinquishing UART after the chip is disabled. Similar actions can also be taken when the chip is in deep sleep or when the chip is awake. Performance enhancements such as configuring the host to run faster when chip is awake and slower when chip is asleep can also be made here. Signed-off-by: Pavan Savoy Signed-off-by: Greg Kroah-Hartman --- include/linux/ti_wilink_st.h | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ti_wilink_st.h b/include/linux/ti_wilink_st.h index b004e557caa9..2ef4385da6bf 100644 --- a/include/linux/ti_wilink_st.h +++ b/include/linux/ti_wilink_st.h @@ -410,7 +410,28 @@ struct gps_event_hdr { u16 plen; } __attribute__ ((packed)); -/* platform data */ +/** + * struct ti_st_plat_data - platform data shared between ST driver and + * platform specific board file which adds the ST device. + * @nshutdown_gpio: Host's GPIO line to which chip's BT_EN is connected. + * @dev_name: The UART/TTY name to which chip is interfaced. (eg: /dev/ttyS1) + * @flow_cntrl: Should always be 1, since UART's CTS/RTS is used for PM + * purposes. + * @baud_rate: The baud rate supported by the Host UART controller, this will + * be shared across with the chip via a HCI VS command from User-Space Init + * Mgr application. + * @suspend: + * @resume: legacy PM routines hooked to platform specific board file, so as + * to take chip-host interface specific action. + * @chip_enable: + * @chip_disable: Platform/Interface specific mux mode setting, GPIO + * configuring, Host side PM disabling etc.. can be done here. + * @chip_asleep: + * @chip_awake: Chip specific deep sleep states is communicated to Host + * specific board-xx.c to take actions such as cut UART clocks when chip + * asleep or run host faster when chip awake etc.. + * + */ struct ti_st_plat_data { long nshutdown_gpio; unsigned char dev_name[UART_DEV_NAME_LEN]; /* uart name */ @@ -418,6 +439,10 @@ struct ti_st_plat_data { unsigned long baud_rate; int (*suspend)(struct platform_device *, pm_message_t); int (*resume)(struct platform_device *); + int (*chip_enable) (struct kim_data_s *); + int (*chip_disable) (struct kim_data_s *); + int (*chip_asleep) (struct kim_data_s *); + int (*chip_awake) (struct kim_data_s *); }; #endif /* TI_WILINK_ST_H */ -- cgit v1.2.3 From 5dc06c5a70b79a323152bec7e55783e705767e63 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 23 Aug 2011 14:49:55 +0200 Subject: block: remove READ_META and WRITE_META Replace all occurnanced of the undocumented READ_META with READ | REQ_META and remove the unused WRITE_META define. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 178cdb4f1d4a..eae44c981173 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -162,10 +162,8 @@ struct inodes_stat_t { #define READA RWA_MASK #define READ_SYNC (READ | REQ_SYNC) -#define READ_META (READ | REQ_META) #define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE) #define WRITE_ODIRECT (WRITE | REQ_SYNC) -#define WRITE_META (WRITE | REQ_META) #define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH) #define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA) #define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA) -- cgit v1.2.3 From 65299a3b788bd274bed92f9fa3232082c9f3ea70 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 23 Aug 2011 14:50:29 +0200 Subject: block: separate priority boosting from REQ_META Add a new REQ_PRIO to let requests preempt others in the cfq I/O schedule, and lave REQ_META purely for marking requests as metadata in blktrace. All existing callers of REQ_META except for XFS are updated to also set REQ_PRIO for now. Signed-off-by: Christoph Hellwig Reviewed-by: Namhyung Kim Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 32f0076e844b..71fc53bb8f1c 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -124,6 +124,7 @@ enum rq_flag_bits { __REQ_SYNC, /* request is sync (sync write or read) */ __REQ_META, /* metadata io request */ + __REQ_PRIO, /* boost priority in cfq */ __REQ_DISCARD, /* request to discard sectors */ __REQ_SECURE, /* secure discard (used with __REQ_DISCARD) */ @@ -161,14 +162,15 @@ enum rq_flag_bits { #define REQ_FAILFAST_DRIVER (1 << __REQ_FAILFAST_DRIVER) #define REQ_SYNC (1 << __REQ_SYNC) #define REQ_META (1 << __REQ_META) +#define REQ_PRIO (1 << __REQ_PRIO) #define REQ_DISCARD (1 << __REQ_DISCARD) #define REQ_NOIDLE (1 << __REQ_NOIDLE) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_COMMON_MASK \ - (REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_DISCARD | \ - REQ_NOIDLE | REQ_FLUSH | REQ_FUA | REQ_SECURE) + (REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | \ + REQ_DISCARD | REQ_NOIDLE | REQ_FLUSH | REQ_FUA | REQ_SECURE) #define REQ_CLONE_MASK REQ_COMMON_MASK #define REQ_RAHEAD (1 << __REQ_RAHEAD) -- cgit v1.2.3 From 24d406a6bf736f7aebdc8fa0f0ec86e0890c6d24 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 10 Aug 2011 14:59:28 +0200 Subject: TTY: pty, fix pty counting tty_operations->remove is normally called like: queue_release_one_tty ->tty_shutdown ->tty_driver_remove_tty ->tty_operations->remove However tty_shutdown() is called from queue_release_one_tty() only if tty_operations->shutdown is NULL. But for pty, it is not. pty_unix98_shutdown() is used there as ->shutdown. So tty_operations->remove of pty (i.e. pty_unix98_remove()) is never called. This results in invalid pty_count. I.e. what can be seen in /proc/sys/kernel/pty/nr. I see this was already reported at: https://lkml.org/lkml/2009/11/5/370 But it was not fixed since then. This patch is kind of a hackish way. The problem lies in ->install. We allocate there another tty (so-called tty->link). So ->install is called once, but ->remove twice, for both tty and tty->link. The fix here is to count both tty and tty->link and divide the count by 2 for user. And to have ->remove called, let's make tty_driver_remove_tty() global and call that from pty_unix98_shutdown() (tty_operations->shutdown). While at it, let's document that when ->shutdown is defined, tty_shutdown() is not called. Signed-off-by: Jiri Slaby Cc: Alan Cox Cc: "H. Peter Anvin" Cc: stable Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 ++ include/linux/tty_driver.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 44bc0c5617e1..5f2ede82b3d6 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -421,6 +421,8 @@ extern void tty_driver_flush_buffer(struct tty_struct *tty); extern void tty_throttle(struct tty_struct *tty); extern void tty_unthrottle(struct tty_struct *tty); extern int tty_do_resize(struct tty_struct *tty, struct winsize *ws); +extern void tty_driver_remove_tty(struct tty_driver *driver, + struct tty_struct *tty); extern void tty_shutdown(struct tty_struct *tty); extern void tty_free_termios(struct tty_struct *tty); extern int is_current_pgrp_orphaned(void); diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 9deeac855240..ecdaeb98b293 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -47,6 +47,9 @@ * * This routine is called synchronously when a particular tty device * is closed for the last time freeing up the resources. + * Note that tty_shutdown() is not called if ops->shutdown is defined. + * This means one is responsible to take care of calling ops->remove (e.g. + * via tty_driver_remove_tty) and releasing tty->termios. * * * void (*cleanup)(struct tty_struct * tty); -- cgit v1.2.3 From 56ebdaf2fa3c5276be201c5d1aff1490b682ecf2 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 24 Aug 2011 16:04:34 +0200 Subject: block: simplify force plug flush code a little bit Cleaning up the code a little bit. attempt_plug_merge() traverses the plug list anyway, we can do the request counting there, so stack size is reduced a little bit. The motivation here is I suspect if we should count the requests for each queue (task could handle multiple disks in the meantime), but my test doesn't show it's worthy doing. If somebody proves we should do it, below change will make that more easier. Signed-off-by: Shaohua Li Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 84b15d54f8c2..7fbaa9103344 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -873,7 +873,6 @@ struct blk_plug { struct list_head list; struct list_head cb_list; unsigned int should_sort; - unsigned int count; }; #define BLK_MAX_REQUEST_COUNT 16 -- cgit v1.2.3 From be27425dcc516fd08245b047ea57f83b8f6f0903 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 19 Aug 2011 16:15:10 -0700 Subject: Add a personality to report 2.6.x version numbers I ran into a couple of programs which broke with the new Linux 3.0 version. Some of those were binary only. I tried to use LD_PRELOAD to work around it, but it was quite difficult and in one case impossible because of a mix of 32bit and 64bit executables. For example, all kind of management software from HP doesnt work, unless we pretend to run a 2.6 kernel. $ uname -a Linux svivoipvnx001 3.0.0-08107-g97cd98f #1062 SMP Fri Aug 12 18:11:45 CEST 2011 i686 i686 i386 GNU/Linux $ hpacucli ctrl all show Error: No controllers detected. $ rpm -qf /usr/sbin/hpacucli hpacucli-8.75-12.0 Another notable case is that Python now reports "linux3" from sys.platform(); which in turn can break things that were checking sys.platform() == "linux2": https://bugzilla.mozilla.org/show_bug.cgi?id=664564 It seems pretty clear to me though it's a bug in the apps that are using '==' instead of .startswith(), but this allows us to unbreak broken programs. This patch adds a UNAME26 personality that makes the kernel report a 2.6.40+x version number instead. The x is the x in 3.x. I know this is somewhat ugly, but I didn't find a better workaround, and compatibility to existing programs is important. Some programs also read /proc/sys/kernel/osrelease. This can be worked around in user space with mount --bind (and a mount namespace) To use: wget ftp://ftp.kernel.org/pub/linux/kernel/people/ak/uname26/uname26.c gcc -o uname26 uname26.c ./uname26 program Signed-off-by: Andi Kleen Signed-off-by: Linus Torvalds --- include/linux/personality.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/personality.h b/include/linux/personality.h index eec3bae164d4..8fc7dd1a57ff 100644 --- a/include/linux/personality.h +++ b/include/linux/personality.h @@ -22,6 +22,7 @@ extern int __set_personality(unsigned int); * These occupy the top three bytes. */ enum { + UNAME26 = 0x0020000, ADDR_NO_RANDOMIZE = 0x0040000, /* disable randomization of VA space */ FDPIC_FUNCPTRS = 0x0080000, /* userspace function ptrs point to descriptors * (signal handling) -- cgit v1.2.3 From e096d0c7e2e4e5893792db865dd065ac73cf1f00 Mon Sep 17 00:00:00 2001 From: Josh Boyer Date: Thu, 25 Aug 2011 07:48:12 -0400 Subject: lockdep: Add helper function for dir vs file i_mutex annotation Purely in-memory filesystems do not use the inode hash as the dcache tells us if an entry already exists. As a result, they do not call unlock_new_inode, and thus directory inodes do not get put into a different lockdep class for i_sem. We need the different lockdep classes, because the locking order for i_mutex is different for directory inodes and regular inodes. Directory inodes can do "readdir()", which takes i_mutex *before* possibly taking mm->mmap_sem (due to a page fault while copying the directory entry to user space). In contrast, regular inodes can be mmap'ed, which takes mm->mmap_sem before accessing i_mutex. The two cases can never happen for the same inode, so no real deadlock can occur, but without the different lockdep classes, lockdep cannot understand that. As a result, if CONFIG_DEBUG_LOCK_ALLOC is set, this can lead to false positives from lockdep like below: find/645 is trying to acquire lock: (&mm->mmap_sem){++++++}, at: [] might_fault+0x5c/0xac but task is already holding lock: (&sb->s_type->i_mutex_key#15){+.+.+.}, at: [] vfs_readdir+0x5b/0xb4 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&sb->s_type->i_mutex_key#15){+.+.+.}: [] lock_acquire+0xbf/0x103 [] __mutex_lock_common+0x4c/0x361 [] mutex_lock_nested+0x40/0x45 [] hugetlbfs_file_mmap+0x82/0x110 [] mmap_region+0x258/0x432 [] do_mmap_pgoff+0x2ac/0x306 [] sys_mmap_pgoff+0x118/0x16a [] sys_mmap+0x22/0x24 [] system_call_fastpath+0x16/0x1b -> #0 (&mm->mmap_sem){++++++}: [] __lock_acquire+0xa1a/0xcf7 [] lock_acquire+0xbf/0x103 [] might_fault+0x89/0xac [] filldir+0x6f/0xc7 [] dcache_readdir+0x67/0x205 [] vfs_readdir+0x7b/0xb4 [] sys_getdents+0x7e/0xd1 [] system_call_fastpath+0x16/0x1b This patch moves the directory vs file lockdep annotation into a helper function that can be called by in-memory filesystems and has hugetlbfs call it. Signed-off-by: Josh Boyer Acked-by: Peter Zijlstra Signed-off-by: Linus Torvalds --- include/linux/fs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 178cdb4f1d4a..c2bd68f2277a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2318,6 +2318,11 @@ extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*te extern struct inode * iget_locked(struct super_block *, unsigned long); extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *); extern int insert_inode_locked(struct inode *); +#ifdef CONFIG_DEBUG_LOCK_ALLOC +extern void lockdep_annotate_inode_mutex_key(struct inode *inode); +#else +static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { }; +#endif extern void unlock_new_inode(struct inode *); extern unsigned int get_next_ino(void); -- cgit v1.2.3 From a801876638c5ce650223476c4eb8f37cea32dc1c Mon Sep 17 00:00:00 2001 From: Evgeniy Polyakov Date: Thu, 25 Aug 2011 15:59:06 -0700 Subject: MAINTAINERS: Evgeniy has moved Signed-off-by: Evgeniy Polyakov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/connector.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/connector.h b/include/linux/connector.h index 0c69ad825b39..3c9c54fd5690 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -1,7 +1,7 @@ /* * connector.h * - * 2004-2005 Copyright (c) Evgeniy Polyakov + * 2004-2005 Copyright (c) Evgeniy Polyakov * All rights reserved. * * This program is free software; you can redistribute it and/or modify -- cgit v1.2.3 From 284fb68d00c56e971ed01e0b4bac5ddd4d1b74ab Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Thu, 25 Aug 2011 15:59:13 -0700 Subject: rapidio: fix use of non-compatible registers Replace/remove use of RIO v.1.2 registers/bits that are not forward-compatible with newer versions of RapidIO specification. RapidIO specification v.1.3 removed Write Port CSR, Doorbell CSR, Mailbox CSR and Mailbox and Doorbell bits of the PEF CAR. Use of removed (since RIO v.1.3) register bits affects users of currently available 1.3 and 2.x compliant devices who may use not so recent kernel versions. Removing checks for unsupported bits makes corresponding routines compatible with all versions of RapidIO specification. Therefore, backporting makes stable kernel versions compliant with RIO v.1.3 and later as well. Signed-off-by: Alexandre Bounine Cc: Kumar Gala Cc: Matt Porter Cc: Li Yang Cc: Thomas Moll Cc: Chul Kim Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio_regs.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rio_regs.h b/include/linux/rio_regs.h index 9026b30238f3..218168a2b5e9 100644 --- a/include/linux/rio_regs.h +++ b/include/linux/rio_regs.h @@ -36,12 +36,12 @@ #define RIO_PEF_PROCESSOR 0x20000000 /* [I] Processor */ #define RIO_PEF_SWITCH 0x10000000 /* [I] Switch */ #define RIO_PEF_MULTIPORT 0x08000000 /* [VI, 2.1] Multiport */ -#define RIO_PEF_INB_MBOX 0x00f00000 /* [II] Mailboxes */ -#define RIO_PEF_INB_MBOX0 0x00800000 /* [II] Mailbox 0 */ -#define RIO_PEF_INB_MBOX1 0x00400000 /* [II] Mailbox 1 */ -#define RIO_PEF_INB_MBOX2 0x00200000 /* [II] Mailbox 2 */ -#define RIO_PEF_INB_MBOX3 0x00100000 /* [II] Mailbox 3 */ -#define RIO_PEF_INB_DOORBELL 0x00080000 /* [II] Doorbells */ +#define RIO_PEF_INB_MBOX 0x00f00000 /* [II, <= 1.2] Mailboxes */ +#define RIO_PEF_INB_MBOX0 0x00800000 /* [II, <= 1.2] Mailbox 0 */ +#define RIO_PEF_INB_MBOX1 0x00400000 /* [II, <= 1.2] Mailbox 1 */ +#define RIO_PEF_INB_MBOX2 0x00200000 /* [II, <= 1.2] Mailbox 2 */ +#define RIO_PEF_INB_MBOX3 0x00100000 /* [II, <= 1.2] Mailbox 3 */ +#define RIO_PEF_INB_DOORBELL 0x00080000 /* [II, <= 1.2] Doorbells */ #define RIO_PEF_EXT_RT 0x00000200 /* [III, 1.3] Extended route table support */ #define RIO_PEF_STD_RT 0x00000100 /* [III, 1.3] Standard route table support */ #define RIO_PEF_CTLS 0x00000010 /* [III] CTLS */ @@ -102,7 +102,7 @@ #define RIO_SWITCH_RT_LIMIT 0x34 /* [III, 1.3] Switch Route Table Destination ID Limit CAR */ #define RIO_RT_MAX_DESTID 0x0000ffff -#define RIO_MBOX_CSR 0x40 /* [II] Mailbox CSR */ +#define RIO_MBOX_CSR 0x40 /* [II, <= 1.2] Mailbox CSR */ #define RIO_MBOX0_AVAIL 0x80000000 /* [II] Mbox 0 avail */ #define RIO_MBOX0_FULL 0x40000000 /* [II] Mbox 0 full */ #define RIO_MBOX0_EMPTY 0x20000000 /* [II] Mbox 0 empty */ @@ -128,8 +128,8 @@ #define RIO_MBOX3_FAIL 0x00000008 /* [II] Mbox 3 fail */ #define RIO_MBOX3_ERROR 0x00000004 /* [II] Mbox 3 error */ -#define RIO_WRITE_PORT_CSR 0x44 /* [I] Write Port CSR */ -#define RIO_DOORBELL_CSR 0x44 /* [II] Doorbell CSR */ +#define RIO_WRITE_PORT_CSR 0x44 /* [I, <= 1.2] Write Port CSR */ +#define RIO_DOORBELL_CSR 0x44 /* [II, <= 1.2] Doorbell CSR */ #define RIO_DOORBELL_AVAIL 0x80000000 /* [II] Doorbell avail */ #define RIO_DOORBELL_FULL 0x40000000 /* [II] Doorbell full */ #define RIO_DOORBELL_EMPTY 0x20000000 /* [II] Doorbell empty */ -- cgit v1.2.3 From cc7993f6439b49909a8792660c4d0741fec9d584 Mon Sep 17 00:00:00 2001 From: Dilan Lee Date: Thu, 25 Aug 2011 15:59:17 -0700 Subject: backlight: add a callback 'notify_after' for backlight control We need a callback to do some things after pwm_enable, pwm_disable and pwm_config. Signed-off-by: Dilan Lee Reviewed-by: Robert Morell Reviewed-by: Arun Murthy Cc: Richard Purdie Cc: Paul Mundt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pwm_backlight.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pwm_backlight.h b/include/linux/pwm_backlight.h index 5e3e25a3c9c3..63d2df43e61a 100644 --- a/include/linux/pwm_backlight.h +++ b/include/linux/pwm_backlight.h @@ -14,6 +14,7 @@ struct platform_pwm_backlight_data { unsigned int pwm_period_ns; int (*init)(struct device *dev); int (*notify)(struct device *dev, int brightness); + void (*notify_after)(struct device *dev, int brightness); void (*exit)(struct device *dev); int (*check_fb)(struct device *dev, struct fb_info *info); }; -- cgit v1.2.3 From f5b940997397229975ea073679b03967932a541b Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 26 Aug 2011 18:03:11 -0400 Subject: All Arch: remove linkage for sys_nfsservctl system call The nfsservctl system call is now gone, so we should remove all linkage for it. Signed-off-by: NeilBrown Signed-off-by: J. Bruce Fields Signed-off-by: Linus Torvalds --- include/linux/compat.h | 1 - include/linux/syscalls.h | 3 --- 2 files changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 8779405e15a8..c6e7523bf765 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -438,7 +438,6 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, struct compat_timespec __user *tsp, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); -asmlinkage long compat_sys_nfsservctl(int cmd, void *notused, void *notused2); asmlinkage long compat_sys_signalfd4(int ufd, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize, int flags); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 8c03b98df5f9..1ff0ec2a5e8d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -702,9 +702,6 @@ asmlinkage long sys_sysctl(struct __sysctl_args __user *args); asmlinkage long sys_sysinfo(struct sysinfo __user *info); asmlinkage long sys_sysfs(int option, unsigned long arg1, unsigned long arg2); -asmlinkage long sys_nfsservctl(int cmd, - struct nfsctl_arg __user *arg, - void __user *res); asmlinkage long sys_syslog(int type, char __user *buf, int len); asmlinkage long sys_uselib(const char __user *library); asmlinkage long sys_ni_syscall(void); -- cgit v1.2.3 From a8d757ef076f0f95f13a918808824058de25b3eb Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 25 Aug 2011 15:58:03 +0200 Subject: perf events: Fix slow and broken cgroup context switch code The current cgroup context switch code was incorrect leading to bogus counts. Furthermore, as soon as there was an active cgroup event on a CPU, the context switch cost on that CPU would increase by a significant amount as demonstrated by a simple ping/pong example: $ ./pong Both processes pinned to CPU1, running for 10s 10684.51 ctxsw/s Now start a cgroup perf stat: $ perf stat -e cycles,cycles -A -a -G test -C 1 -- sleep 100 $ ./pong Both processes pinned to CPU1, running for 10s 6674.61 ctxsw/s That's a 37% penalty. Note that pong is not even in the monitored cgroup. The results shown by perf stat are bogus: $ perf stat -e cycles,cycles -A -a -G test -C 1 -- sleep 100 Performance counter stats for 'sleep 100': CPU1 cycles test CPU1 16,984,189,138 cycles # 0.000 GHz The second 'cycles' event should report a count @ CPU clock (here 2.4GHz) as it is counting across all cgroups. The patch below fixes the bogus accounting and bypasses any cgroup switches in case the outgoing and incoming tasks are in the same cgroup. With this patch the same test now yields: $ ./pong Both processes pinned to CPU1, running for 10s 10775.30 ctxsw/s Start perf stat with cgroup: $ perf stat -e cycles,cycles -A -a -G test -C 1 -- sleep 10 Run pong outside the cgroup: $ /pong Both processes pinned to CPU1, running for 10s 10687.80 ctxsw/s The penalty is now less than 2%. And the results for perf stat are correct: $ perf stat -e cycles,cycles -A -a -G test -C 1 -- sleep 10 Performance counter stats for 'sleep 10': CPU1 cycles test # 0.000 GHz CPU1 23,933,981,448 cycles # 0.000 GHz Now perf stat reports the correct counts for for the non cgroup event. If we run pong inside the cgroup, then we also get the correct counts: $ perf stat -e cycles,cycles -A -a -G test -C 1 -- sleep 10 Performance counter stats for 'sleep 10': CPU1 22,297,726,205 cycles test # 0.000 GHz CPU1 23,933,981,448 cycles # 0.000 GHz 10.001457237 seconds time elapsed Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110825135803.GA4697@quad Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 245bafdafd5e..c816075c01ce 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -944,8 +944,10 @@ extern void perf_pmu_unregister(struct pmu *pmu); extern int perf_num_counters(void); extern const char *perf_pmu_name(void); -extern void __perf_event_task_sched_in(struct task_struct *task); -extern void __perf_event_task_sched_out(struct task_struct *task, struct task_struct *next); +extern void __perf_event_task_sched_in(struct task_struct *prev, + struct task_struct *task); +extern void __perf_event_task_sched_out(struct task_struct *prev, + struct task_struct *next); extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); @@ -1059,17 +1061,20 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) extern struct jump_label_key perf_sched_events; -static inline void perf_event_task_sched_in(struct task_struct *task) +static inline void perf_event_task_sched_in(struct task_struct *prev, + struct task_struct *task) { if (static_branch(&perf_sched_events)) - __perf_event_task_sched_in(task); + __perf_event_task_sched_in(prev, task); } -static inline void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next) +static inline void perf_event_task_sched_out(struct task_struct *prev, + struct task_struct *next) { perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0); - __perf_event_task_sched_out(task, next); + if (static_branch(&perf_sched_events)) + __perf_event_task_sched_out(prev, next); } extern void perf_event_mmap(struct vm_area_struct *vma); @@ -1139,10 +1144,11 @@ extern void perf_event_disable(struct perf_event *event); extern void perf_event_task_tick(void); #else static inline void -perf_event_task_sched_in(struct task_struct *task) { } +perf_event_task_sched_in(struct task_struct *prev, + struct task_struct *task) { } static inline void -perf_event_task_sched_out(struct task_struct *task, - struct task_struct *next) { } +perf_event_task_sched_out(struct task_struct *prev, + struct task_struct *next) { } static inline int perf_event_init_task(struct task_struct *child) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } -- cgit v1.2.3 From 8efcc57dedfebc99c3cd39564e3fc47cd1a24b75 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 3 Aug 2011 18:04:29 +0900 Subject: mfd: Fix value of WM8994_CONFIGURE_GPIO This needs to be an out of band value for the register and on this device registers are 16 bit so we must shift left one to the 17th bit. Signed-off-by: Mark Brown Cc: stable@kernel.org Signed-off-by: Samuel Ortiz --- include/linux/mfd/wm8994/pdata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/wm8994/pdata.h b/include/linux/mfd/wm8994/pdata.h index d12f8d635a81..97cf4f27d647 100644 --- a/include/linux/mfd/wm8994/pdata.h +++ b/include/linux/mfd/wm8994/pdata.h @@ -26,7 +26,7 @@ struct wm8994_ldo_pdata { struct regulator_init_data *init_data; }; -#define WM8994_CONFIGURE_GPIO 0x8000 +#define WM8994_CONFIGURE_GPIO 0x10000 #define WM8994_DRC_REGS 5 #define WM8994_EQ_REGS 20 -- cgit v1.2.3 From bff747c58cf97bf4fc8b499ee0f419b59d6b226d Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 8 Sep 2011 10:16:47 -0700 Subject: regulator: fix kernel-doc warning in consumer.h Fix kernel-doc warning about internal/private data by marking it as "private:" so that kernel-doc will ignore it. Warning(include/linux/regulator/consumer.h:128): No description found for parameter 'ret' Signed-off-by: Randy Dunlap Acked-by: Mark Brown Signed-off-by: Linus Torvalds --- include/linux/regulator/consumer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 26f6ea4444e3..b47771aa5718 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -123,7 +123,7 @@ struct regulator_bulk_data { const char *supply; struct regulator *consumer; - /* Internal use */ + /* private: Internal use */ int ret; }; -- cgit v1.2.3 From 185efc0f9a1f2d6ad6d4782c5d9e529f3290567f Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 14 Sep 2011 16:21:58 -0700 Subject: memcg: Revert "memcg: add memory.vmscan_stat" Revert the post-3.0 commit 82f9d486e59f5 ("memcg: add memory.vmscan_stat"). The implementation of per-memcg reclaim statistics violates how memcg hierarchies usually behave: hierarchically. The reclaim statistics are accounted to child memcgs and the parent hitting the limit, but not to hierarchy levels in between. Usually, hierarchical statistics are perfectly recursive, with each level representing the sum of itself and all its children. Since this exports statistics to userspace, this may lead to confusion and problems with changing things after the release, so revert it now, we can try again later. Signed-off-by: Johannes Weiner Acked-by: KAMEZAWA Hiroyuki Cc: Daisuke Nishimura Cc: Michal Hocko Cc: Ying Han Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 19 ------------------- include/linux/swap.h | 6 ++++++ 2 files changed, 6 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 3b535db00a94..343bd7661f2a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -39,16 +39,6 @@ extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, struct mem_cgroup *mem_cont, int active, int file); -struct memcg_scanrecord { - struct mem_cgroup *mem; /* scanend memory cgroup */ - struct mem_cgroup *root; /* scan target hierarchy root */ - int context; /* scanning context (see memcontrol.c) */ - unsigned long nr_scanned[2]; /* the number of scanned pages */ - unsigned long nr_rotated[2]; /* the number of rotated pages */ - unsigned long nr_freed[2]; /* the number of freed pages */ - unsigned long elapsed; /* nsec of time elapsed while scanning */ -}; - #ifdef CONFIG_CGROUP_MEM_RES_CTLR /* * All "charge" functions with gfp_mask should use GFP_KERNEL or @@ -127,15 +117,6 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page); extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p); -extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem, - gfp_t gfp_mask, bool noswap, - struct memcg_scanrecord *rec); -extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, - gfp_t gfp_mask, bool noswap, - struct zone *zone, - struct memcg_scanrecord *rec, - unsigned long *nr_scanned); - #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP extern int do_swap_account; #endif diff --git a/include/linux/swap.h b/include/linux/swap.h index 14d62490922e..c71f84bb62ec 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -252,6 +252,12 @@ static inline void lru_cache_add_file(struct page *page) extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); extern int __isolate_lru_page(struct page *page, int mode, int file); +extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem, + gfp_t gfp_mask, bool noswap); +extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, + gfp_t gfp_mask, bool noswap, + struct zone *zone, + unsigned long *nr_scanned); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; extern int remove_mapping(struct address_space *mapping, struct page *page); -- cgit v1.2.3 From 4f5b04800a224aadb6cffcbbc3d3fa26e2367c7f Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 14 Sep 2011 16:22:29 -0700 Subject: drivers/gpio/gpio-generic.c: fix build errors Building a kernel with hotplug disabled results in a link failure: `bgpio_remove' referenced in section `___ksymtab_gpl+bgpio_remove' of drivers/built-in.o: defined in discarded section `.devexit.text' of drivers/built-in.o This is because of bgpio_remove() is exported. It is illegal to export symbols which are discarded either at link time or as part of an init/exit section. Fix this by dropping the __devexit attributation from bgpio_remove(). Also drop the __devinit attributation from bgpio_init(). Signed-off-by: Russell King Cc: Grant Likely Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/basic_mmio_gpio.h | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/basic_mmio_gpio.h b/include/linux/basic_mmio_gpio.h index 98999cf107ce..feb912196745 100644 --- a/include/linux/basic_mmio_gpio.h +++ b/include/linux/basic_mmio_gpio.h @@ -63,15 +63,10 @@ static inline struct bgpio_chip *to_bgpio_chip(struct gpio_chip *gc) return container_of(gc, struct bgpio_chip, gc); } -int __devexit bgpio_remove(struct bgpio_chip *bgc); -int __devinit bgpio_init(struct bgpio_chip *bgc, - struct device *dev, - unsigned long sz, - void __iomem *dat, - void __iomem *set, - void __iomem *clr, - void __iomem *dirout, - void __iomem *dirin, - bool big_endian); +int bgpio_remove(struct bgpio_chip *bgc); +int bgpio_init(struct bgpio_chip *bgc, struct device *dev, + unsigned long sz, void __iomem *dat, void __iomem *set, + void __iomem *clr, void __iomem *dirout, void __iomem *dirin, + bool big_endian); #endif /* __BASIC_MMIO_GPIO_H */ -- cgit v1.2.3 From 946cedccbd7387488d2cee5da92cdfeb28d2e670 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 30 Aug 2011 03:21:44 +0000 Subject: tcp: Change possible SYN flooding messages "Possible SYN flooding on port xxxx " messages can fill logs on servers. Change logic to log the message only once per listener, and add two new SNMP counters to track : TCPReqQFullDoCookies : number of times a SYNCOOKIE was replied to client TCPReqQFullDrop : number of times a SYN request was dropped because syncookies were not enabled. Based on a prior patch from Tom Herbert, and suggestions from David. Signed-off-by: Eric Dumazet CC: Tom Herbert Signed-off-by: David S. Miller --- include/linux/snmp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/snmp.h b/include/linux/snmp.h index 12b2b18e50c1..e16557a357e5 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -231,6 +231,8 @@ enum LINUX_MIB_TCPDEFERACCEPTDROP, LINUX_MIB_IPRPFILTER, /* IP Reverse Path Filter (rp_filter) */ LINUX_MIB_TCPTIMEWAITOVERFLOW, /* TCPTimeWaitOverflow */ + LINUX_MIB_TCPREQQFULLDOCOOKIES, /* TCPReqQFullDoCookies */ + LINUX_MIB_TCPREQQFULLDROP, /* TCPReqQFullDrop */ __LINUX_MIB_MAX }; -- cgit v1.2.3 From 48c830120f2a20b44220aa26feda9ed15f49eaab Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 31 Aug 2011 08:03:29 +0000 Subject: net: copy userspace buffers on device forwarding dev_forward_skb loops an skb back into host networking stack which might hang on the memory indefinitely. In particular, this can happen in macvtap in bridged mode. Copy the userspace fragments to avoid blocking the sender in that case. As this patch makes skb_copy_ubufs extern now, I also added some documentation and made it clear the SKBTX_DEV_ZEROCOPY flag automatically instead of doing it in all callers. This can be made into a separate patch if people feel it's worth it. Signed-off-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7b996ed86d5b..8bd383caa363 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -524,6 +524,7 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, extern bool skb_recycle_check(struct sk_buff *skb, int skb_size); extern struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); +extern int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); extern struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); extern struct sk_buff *skb_copy(const struct sk_buff *skb, -- cgit v1.2.3 From 5bd078dda4d4fbdb4bd138a6bd5b6e274c019ed2 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 14 Sep 2011 11:31:36 -0500 Subject: irq: Add declaration of irq_domain_simple_ops to irqdomain.h irq_domain_simple_ops is exported, but is not declared in irqdomain.h, so add it. Signed-off-by: Rob Herring Cc: Grant Likely Cc: marc.zyngier@arm.com Cc: thomas.abraham@linaro.org Cc: jamie@jamieiles.com Cc: b-cousson@ti.com Cc: shawn.guo@linaro.org Cc: linux-arm-kernel@lists.infradead.org Cc: devicetree-discuss@lists.ozlabs.org Link: http://lkml.kernel.org/r/1316017900-19918-2-git-send-email-robherring2@gmail.com Signed-off-by: Thomas Gleixner --- include/linux/irqdomain.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index e807ad687a07..3ad553e8eae2 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -80,6 +80,7 @@ extern void irq_domain_del(struct irq_domain *domain); #endif /* CONFIG_IRQ_DOMAIN */ #if defined(CONFIG_IRQ_DOMAIN) && defined(CONFIG_OF_IRQ) +extern struct irq_domain_ops irq_domain_simple_ops; extern void irq_domain_add_simple(struct device_node *controller, int irq_base); extern void irq_domain_generate_simple(const struct of_device_id *match, u64 phys_base, unsigned int irq_start); -- cgit v1.2.3 From b6cf8788a3382c2000743a0e393bcc8aeb0601cb Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 20 Sep 2011 17:07:29 +0200 Subject: [S390] kvm: extension capability for new address space layout 598841ca9919d008b520114d8a4378c4ce4e40a1 ([S390] use gmap address spaces for kvm guest images) changed kvm on s390 to use a separate address space for kvm guests. We can now put KVM guests anywhere in the user address mode with a size up to 8PB - as long as the memory is 1MB-aligned. This change was done without KVM extension capability bit. The change was added after 3.0, but we still have a chance to add a feature bit before 3.1 (keeping the releases in a sane state). We use number 71 to avoid collisions with other pending kvm patches as requested by Alexander Graf. Signed-off-by: Christian Borntraeger Acked-by: Avi Kivity Cc: Alexander Graf Signed-off-by: Heiko Carstens --- include/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 2c366b52f505..aace6b8691a2 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -553,6 +553,7 @@ struct kvm_ppc_pvinfo { #define KVM_CAP_SPAPR_TCE 63 #define KVM_CAP_PPC_SMT 64 #define KVM_CAP_PPC_RMA 65 +#define KVM_CAP_S390_GMAP 71 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From d94c177beeb4469cd4f6e83354ab0223353e98ed Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 26 Sep 2011 17:44:55 -0700 Subject: vfs pathname lookup: Add LOOKUP_AUTOMOUNT flag Since we've now turned around and made LOOKUP_FOLLOW *not* force an automount, we want to add the ability to force an automount event on lookup even if we don't happen to have one of the other flags that force it implicitly (LOOKUP_OPEN, LOOKUP_DIRECTORY, LOOKUP_PARENT..) Most cases will never want to use this, since you'd normally want to delay automounting as long as possible, which usually implies LOOKUP_OPEN (when we open a file or directory, we really cannot avoid the automount any more). But Trond argued sufficiently forcefully that at a minimum bind mounting a file and quotactl will want to force the automount lookup. Some other cases (like nfs_follow_remote_path()) could use it too, although LOOKUP_DIRECTORY would work there as well. This commit just adds the flag and logic, no users yet, though. It also doesn't actually touch the LOOKUP_NO_AUTOMOUNT flag that is related, and was made irrelevant by the same change that made us not follow on LOOKUP_FOLLOW. Cc: Trond Myklebust Cc: Ian Kent Cc: Jeff Layton Cc: Miklos Szeredi Cc: David Howells Cc: Al Viro Cc: Greg KH Signed-off-by: Linus Torvalds --- include/linux/namei.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index 76fe2c62ae71..e13dac7caab2 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -48,6 +48,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; */ #define LOOKUP_FOLLOW 0x0001 #define LOOKUP_DIRECTORY 0x0002 +#define LOOKUP_AUTOMOUNT 0x0004 #define LOOKUP_PARENT 0x0010 #define LOOKUP_REVAL 0x0020 -- cgit v1.2.3 From b6c8069d3577481390b3f24a8434ad72a3235594 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 27 Sep 2011 08:12:33 -0700 Subject: vfs: remove LOOKUP_NO_AUTOMOUNT flag That flag no longer makes sense, since we don't look up automount points as eagerly any more. Additionally, it turns out that the NO_AUTOMOUNT handling was buggy to begin with: it would avoid automounting even for cases where we really *needed* to do the automount handling, and could return ENOENT for autofs entries that hadn't been instantiated yet. With our new non-eager automount semantics, one discussion has been about adding a AT_AUTOMOUNT flag to vfs_fstatat (and thus the newfstatat() and fstatat64() system calls), but it's probably not worth it: you can always force at least directory automounting by simply adding the final '/' to the filename, which works for *all* of the stat family system calls, old and new. So AT_NO_AUTOMOUNT (and thus LOOKUP_NO_AUTOMOUNT) really were just a result of our bad default behavior. Acked-by: Ian Kent Acked-by: Trond Myklebust Signed-off-by: Linus Torvalds --- include/linux/namei.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index e13dac7caab2..409328d1cbbb 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -53,7 +53,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_PARENT 0x0010 #define LOOKUP_REVAL 0x0020 #define LOOKUP_RCU 0x0040 -#define LOOKUP_NO_AUTOMOUNT 0x0080 + /* * Intent data */ -- cgit v1.2.3 From f75159e9936143177b442afc78150b7a7ad8aa07 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Tue, 20 Sep 2011 01:25:41 +0000 Subject: ptp: fix L2 event message recognition The IEEE 1588 standard defines two kinds of messages, event and general messages. Event messages require time stamping, and general do not. When using UDP transport, two separate ports are used for the two message types. The BPF designed to recognize event messages incorrectly classifies L2 general messages as event messages. This commit fixes the issue by extending the filter to check the message type field for L2 PTP packets. Event messages are be distinguished from general messages by testing the "general" bit. Signed-off-by: Richard Cochran Cc: Signed-off-by: David S. Miller --- include/linux/ptp_classify.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index e07e2742a865..1dc420ba213a 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -51,6 +51,7 @@ #define PTP_CLASS_V2_VLAN (PTP_CLASS_V2 | PTP_CLASS_VLAN) #define PTP_EV_PORT 319 +#define PTP_GEN_BIT 0x08 /* indicates general message, if set in message type */ #define OFF_ETYPE 12 #define OFF_IHL 14 @@ -116,14 +117,20 @@ static inline int ptp_filter_init(struct sock_filter *f, int len) {OP_OR, 0, 0, PTP_CLASS_IPV6 }, /* */ \ {OP_RETA, 0, 0, 0 }, /* */ \ /*L3x*/ {OP_RETK, 0, 0, PTP_CLASS_NONE }, /* */ \ -/*L40*/ {OP_JEQ, 0, 6, ETH_P_8021Q }, /* f goto L50 */ \ +/*L40*/ {OP_JEQ, 0, 9, ETH_P_8021Q }, /* f goto L50 */ \ {OP_LDH, 0, 0, OFF_ETYPE + 4 }, /* */ \ - {OP_JEQ, 0, 9, ETH_P_1588 }, /* f goto L60 */ \ + {OP_JEQ, 0, 15, ETH_P_1588 }, /* f goto L60 */ \ + {OP_LDB, 0, 0, ETH_HLEN + VLAN_HLEN }, /* */ \ + {OP_AND, 0, 0, PTP_GEN_BIT }, /* */ \ + {OP_JEQ, 0, 12, 0 }, /* f goto L6x */ \ {OP_LDH, 0, 0, ETH_HLEN + VLAN_HLEN }, /* */ \ {OP_AND, 0, 0, PTP_CLASS_VMASK }, /* */ \ {OP_OR, 0, 0, PTP_CLASS_VLAN }, /* */ \ {OP_RETA, 0, 0, 0 }, /* */ \ -/*L50*/ {OP_JEQ, 0, 4, ETH_P_1588 }, /* f goto L61 */ \ +/*L50*/ {OP_JEQ, 0, 7, ETH_P_1588 }, /* f goto L61 */ \ + {OP_LDB, 0, 0, ETH_HLEN }, /* */ \ + {OP_AND, 0, 0, PTP_GEN_BIT }, /* */ \ + {OP_JEQ, 0, 4, 0 }, /* f goto L6x */ \ {OP_LDH, 0, 0, ETH_HLEN }, /* */ \ {OP_AND, 0, 0, PTP_CLASS_VMASK }, /* */ \ {OP_OR, 0, 0, PTP_CLASS_L2 }, /* */ \ -- cgit v1.2.3 From d670ec13178d0fd8680e6742a2bc6e04f28f87d8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 1 Sep 2011 12:42:04 +0200 Subject: posix-cpu-timers: Cure SMP wobbles David reported: Attached below is a watered-down version of rt/tst-cpuclock2.c from GLIBC. Just build it with "gcc -o test test.c -lpthread -lrt" or similar. Run it several times, and you will see cases where the main thread will measure a process clock difference before and after the nanosleep which is smaller than the cpu-burner thread's individual thread clock difference. This doesn't make any sense since the cpu-burner thread is part of the top-level process's thread group. I've reproduced this on both x86-64 and sparc64 (using both 32-bit and 64-bit binaries). For example: [davem@boricha build-x86_64-linux]$ ./test process: before(0.001221967) after(0.498624371) diff(497402404) thread: before(0.000081692) after(0.498316431) diff(498234739) self: before(0.001223521) after(0.001240219) diff(16698) [davem@boricha build-x86_64-linux]$ The diff of 'process' should always be >= the diff of 'thread'. I make sure to wrap the 'thread' clock measurements the most tightly around the nanosleep() call, and that the 'process' clock measurements are the outer-most ones. --- #include #include #include #include #include #include #include #include static pthread_barrier_t barrier; static void *chew_cpu(void *arg) { pthread_barrier_wait(&barrier); while (1) __asm__ __volatile__("" : : : "memory"); return NULL; } int main(void) { clockid_t process_clock, my_thread_clock, th_clock; struct timespec process_before, process_after; struct timespec me_before, me_after; struct timespec th_before, th_after; struct timespec sleeptime; unsigned long diff; pthread_t th; int err; err = clock_getcpuclockid(0, &process_clock); if (err) return 1; err = pthread_getcpuclockid(pthread_self(), &my_thread_clock); if (err) return 1; pthread_barrier_init(&barrier, NULL, 2); err = pthread_create(&th, NULL, chew_cpu, NULL); if (err) return 1; err = pthread_getcpuclockid(th, &th_clock); if (err) return 1; pthread_barrier_wait(&barrier); err = clock_gettime(process_clock, &process_before); if (err) return 1; err = clock_gettime(my_thread_clock, &me_before); if (err) return 1; err = clock_gettime(th_clock, &th_before); if (err) return 1; sleeptime.tv_sec = 0; sleeptime.tv_nsec = 500000000; nanosleep(&sleeptime, NULL); err = clock_gettime(th_clock, &th_after); if (err) return 1; err = clock_gettime(my_thread_clock, &me_after); if (err) return 1; err = clock_gettime(process_clock, &process_after); if (err) return 1; diff = process_after.tv_nsec - process_before.tv_nsec; printf("process: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n", process_before.tv_sec, process_before.tv_nsec, process_after.tv_sec, process_after.tv_nsec, diff); diff = th_after.tv_nsec - th_before.tv_nsec; printf("thread: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n", th_before.tv_sec, th_before.tv_nsec, th_after.tv_sec, th_after.tv_nsec, diff); diff = me_after.tv_nsec - me_before.tv_nsec; printf("self: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n", me_before.tv_sec, me_before.tv_nsec, me_after.tv_sec, me_after.tv_nsec, diff); return 0; } This is due to us using p->se.sum_exec_runtime in thread_group_cputime() where we iterate the thread group and sum all data. This does not take time since the last schedule operation (tick or otherwise) into account. We can cure this by using task_sched_runtime() at the cost of having to take locks. This also means we can (and must) do away with thread_group_sched_runtime() since the modified thread_group_cputime() is now more accurate and would deadlock when called from thread_group_sched_runtime(). Aside of that it makes the function safe on 32 bit systems. The old code added t->se.sum_exec_runtime unprotected. sum_exec_runtime is a 64bit value and could be changed on another cpu at the same time. Reported-by: David Miller Signed-off-by: Peter Zijlstra Cc: stable@kernel.org Link: http://lkml.kernel.org/r/1314874459.7945.22.camel@twins Tested-by: David Miller Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4ac2c0578e0f..41d0237fd449 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1956,7 +1956,6 @@ static inline void disable_sched_clock_irqtime(void) {} extern unsigned long long task_sched_runtime(struct task_struct *task); -extern unsigned long long thread_group_sched_runtime(struct task_struct *task); /* sched_exec is called by processes performing an exec */ #ifdef CONFIG_SMP -- cgit v1.2.3 From 5f39e6705faade2e89d119958a8c51b9b6e2c53c Mon Sep 17 00:00:00 2001 From: Jon Mason Date: Mon, 3 Oct 2011 09:50:20 -0500 Subject: PCI: Disable MPS configuration by default Add the ability to disable PCI-E MPS turning and using the BIOS configured MPS defaults. Due to the number of issues recently discovered on some x86 chipsets, make this the default behavior. Also, add the option for peer to peer DMA MPS configuration. Peer to peer DMA is outside the scope of this patch, but MPS configuration could prevent it from working by having the MPS on one root port different than the MPS on another. To work around this, simply make the system wide MPS the smallest possible value (128B). Signed-off-by: Jon Mason Acked-by: Benjamin Herrenschmidt Signed-off-by: Linus Torvalds --- include/linux/pci.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 8c230cbcbb48..9fc01226055b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -621,8 +621,9 @@ struct pci_driver { extern void pcie_bus_configure_settings(struct pci_bus *bus, u8 smpss); enum pcie_bus_config_types { - PCIE_BUS_PERFORMANCE, + PCIE_BUS_TUNE_OFF, PCIE_BUS_SAFE, + PCIE_BUS_PERFORMANCE, PCIE_BUS_PEER2PEER, }; -- cgit v1.2.3