From a29ccf6f823a84d89e1c7aaaf221cf7282022024 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Tue, 3 Jun 2008 14:59:40 +0100 Subject: Make console charset translation optional By turning off the new CONSOLE_TRANSLATIONS option and dropping the associated code and tables from the kernel, we can save about 7KiB. Taken from linux-tiny project by Tim Bird and mangled further by dwmw2. Signed-off-by: Tim Bird Signed-off-by: David Woodhouse --- include/linux/consolemap.h | 14 ++++++++++++++ include/linux/vt_kern.h | 19 +++++++++++++++++++ 2 files changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/consolemap.h b/include/linux/consolemap.h index e2bf7e5db39a..c4811da1338b 100644 --- a/include/linux/consolemap.h +++ b/include/linux/consolemap.h @@ -3,6 +3,9 @@ * * Interface between console.c, selection.c and consolemap.c */ +#ifndef __LINUX_CONSOLEMAP_H__ +#define __LINUX_CONSOLEMAP_H__ + #define LAT1_MAP 0 #define GRAF_MAP 1 #define IBMPC_MAP 2 @@ -10,6 +13,7 @@ #include +#ifdef CONFIG_CONSOLE_TRANSLATIONS struct vc_data; extern u16 inverse_translate(struct vc_data *conp, int glyph, int use_unicode); @@ -18,3 +22,13 @@ extern int conv_uni_to_pc(struct vc_data *conp, long ucs); extern u32 conv_8bit_to_uni(unsigned char c); extern int conv_uni_to_8bit(u32 uni); void console_map_init(void); +#else +#define inverse_translate(conp, glyph, uni) ((uint16_t)glyph) +#define set_translate(m, vc) ((unsigned short *)NULL) +#define conv_uni_to_pc(conp, ucs) ((int) (ucs > 0xff ? -1: ucs)) +#define conv_8bit_to_uni(c) ((uint32_t)(c)) +#define conv_uni_to_8bit(c) ((int) ((c) & 0xff)) +#define console_map_init(c) do { ; } while (0) +#endif /* CONFIG_CONSOLE_TRANSLATIONS */ + +#endif /* __LINUX_CONSOLEMAP_H__ */ diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 9448ffbdcbf6..14c0e91be9b5 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -12,6 +12,7 @@ #include #include #include +#include /* * Presently, a lot of graphics programs do not restore the contents of @@ -54,6 +55,7 @@ void redraw_screen(struct vc_data *vc, int is_switch); struct tty_struct; int tioclinux(struct tty_struct *tty, unsigned long arg); +#ifdef CONFIG_CONSOLE_TRANSLATIONS /* consolemap.c */ struct unimapinit; @@ -71,6 +73,23 @@ void con_free_unimap(struct vc_data *vc); void con_protect_unimap(struct vc_data *vc, int rdonly); int con_copy_unimap(struct vc_data *dst_vc, struct vc_data *src_vc); +#define vc_translate(vc, c) ((vc)->vc_translate[(c) | \ + (vc)->vc_toggle_meta ? 0x80 : 0]) +#else +#define con_set_trans_old(arg) (0) +#define con_get_trans_old(arg) (-EINVAL) +#define con_set_trans_new(arg) (0) +#define con_get_trans_new(arg) (-EINVAL) +#define con_clear_unimap(vc, ui) (0) +#define con_set_unimap(vc, ct, list) (0) +#define con_set_default_unimap(vc) (0) +#define con_copy_unimap(d, s) (0) +#define con_get_unimap(vc, ct, uct, list) (-EINVAL) +#define con_free_unimap(vc) do { ; } while (0) + +#define vc_translate(vc, c) (c) +#endif + /* vt.c */ int vt_waitactive(int vt); void change_console(struct vc_data *new_vc); -- cgit v1.2.3 From b8f8c3cf0a4ac0632ec3f0e15e9dc0c29de917af Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 18 Jul 2008 17:27:28 +0200 Subject: nohz: prevent tick stop outside of the idle loop Jack Ren and Eric Miao tracked down the following long standing problem in the NOHZ code: scheduler switch to idle task enable interrupts Window starts here ----> interrupt happens (does not set NEED_RESCHED) irq_exit() stops the tick ----> interrupt happens (does set NEED_RESCHED) return from schedule() cpu_idle(): preempt_disable(); Window ends here The interrupts can happen at any point inside the race window. The first interrupt stops the tick, the second one causes the scheduler to rerun and switch away from idle again and we end up with the tick disabled. The fact that it needs two interrupts where the first one does not set NEED_RESCHED and the second one does made the bug obscure and extremly hard to reproduce and analyse. Kudos to Jack and Eric. Solution: Limit the NOHZ functionality to the idle loop to make sure that we can not run into such a situation ever again. cpu_idle() { preempt_disable(); while(1) { tick_nohz_stop_sched_tick(1); <- tell NOHZ code that we are in the idle loop while (!need_resched()) halt(); tick_nohz_restart_sched_tick(); <- disables NOHZ mode preempt_enable_no_resched(); schedule(); preempt_disable(); } } In hindsight we should have done this forever, but ... /me grabs a large brown paperbag. Debugged-by: Jack Ren , Debugged-by: eric miao Signed-off-by: Thomas Gleixner --- include/linux/tick.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index a881c652f7e9..d3c02695dc5d 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -49,6 +49,7 @@ struct tick_sched { unsigned long check_clocks; enum tick_nohz_mode nohz_mode; ktime_t idle_tick; + int inidle; int tick_stopped; unsigned long idle_jiffies; unsigned long idle_calls; @@ -105,14 +106,14 @@ static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ # ifdef CONFIG_NO_HZ -extern void tick_nohz_stop_sched_tick(void); +extern void tick_nohz_stop_sched_tick(int inidle); extern void tick_nohz_restart_sched_tick(void); extern void tick_nohz_update_jiffies(void); extern ktime_t tick_nohz_get_sleep_length(void); extern void tick_nohz_stop_idle(int cpu); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); # else -static inline void tick_nohz_stop_sched_tick(void) { } +static inline void tick_nohz_stop_sched_tick(int inidle) { } static inline void tick_nohz_restart_sched_tick(void) { } static inline void tick_nohz_update_jiffies(void) { } static inline ktime_t tick_nohz_get_sleep_length(void) -- cgit v1.2.3 From 47b374752aed1c029f995473c7c463ee3ae5fbaa Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Tue, 22 Jul 2008 14:19:39 -0700 Subject: IB/mlx4: Rename struct mlx4_lso_seg to mlx4_wqe_lso_seg Make the struct name consistent with other WQE segment struct types defined in . Signed-off-by: Roland Dreier --- include/linux/mlx4/qp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 7f128b266faa..f02e9ed36cfa 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -219,7 +219,7 @@ struct mlx4_wqe_datagram_seg { __be32 reservd[2]; }; -struct mlx4_lso_seg { +struct mlx4_wqe_lso_seg { __be32 mss_hdr_size; __be32 header[0]; }; -- cgit v1.2.3 From e5899e1b7d73e67de758a32174a859cc2586c0b9 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 19 Jul 2008 14:39:24 +0200 Subject: PCI PM: make more PCI PM core functionality available to drivers Make more PCI PM core functionality available to drivers * Export pci_pme_capable() so that it can be called directly by drivers (for example, tg3 needs that). * Move the state choosing part of pci_prepare_to_sleep() to a separate function, pci_target_state(), that can be called directly by drivers (for example, tg3 needs that). Signed-off-by: Rafael J. Wysocki Signed-off-by: Jesse Barnes --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index a6a088e1a804..1d296d31abe0 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -638,7 +638,9 @@ int pci_save_state(struct pci_dev *dev); int pci_restore_state(struct pci_dev *dev); int pci_set_power_state(struct pci_dev *dev, pci_power_t state); pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state); +bool pci_pme_capable(struct pci_dev *dev, pci_power_t state); int pci_enable_wake(struct pci_dev *dev, pci_power_t state, int enable); +pci_power_t pci_target_state(struct pci_dev *dev); int pci_prepare_to_sleep(struct pci_dev *dev); int pci_back_from_sleep(struct pci_dev *dev); -- cgit v1.2.3 From e14fa82439d33cef67eaafc1a48960bbfa610c8e Mon Sep 17 00:00:00 2001 From: Riku Voipio Date: Sat, 31 May 2008 14:43:41 +0100 Subject: leds: Add pca9532 led driver NXP pca9532 is a LED dimmer/controller attached to i2c bus. It allows attaching upto 16 leds which can either be on, off or dimmed and/or blinked with the two PWM modulators available. This driver is a "new-style" i2c driver that adheres to the driver model and implements the led framework api. Since the leds connected to the driver are platform specific, it is only useful when platform data is passed to the driver to define what leds are connected to which pins. Signed-off-by: Riku Voipio Signed-off-by: Andrew Morton Signed-off-by: Richard Purdie --- include/linux/leds-pca9532.h | 45 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) create mode 100644 include/linux/leds-pca9532.h (limited to 'include/linux') diff --git a/include/linux/leds-pca9532.h b/include/linux/leds-pca9532.h new file mode 100644 index 000000000000..81b4207deb95 --- /dev/null +++ b/include/linux/leds-pca9532.h @@ -0,0 +1,45 @@ +/* + * pca9532.h - platform data structure for pca9532 led controller + * + * Copyright (C) 2008 Riku Voipio + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * Datasheet: http://www.nxp.com/acrobat/datasheets/PCA9532_3.pdf + * + */ + +#ifndef __LINUX_PCA9532_H +#define __LINUX_PCA9532_H + +#include + +enum pca9532_state { + PCA9532_OFF = 0x0, + PCA9532_ON = 0x1, + PCA9532_PWM0 = 0x2, + PCA9532_PWM1 = 0x3 +}; + +enum pca9532_type { PCA9532_TYPE_NONE, PCA9532_TYPE_LED, + PCA9532_TYPE_N2100_BEEP }; + +struct pca9532_led { + u8 id; + struct i2c_client *client; + char *name; + struct led_classdev ldev; + enum pca9532_type type; + enum pca9532_state state; +}; + +struct pca9532_platform_data { + struct pca9532_led leds[16]; + u8 pwm[2]; + u8 psc[2]; +}; + +#endif /* __LINUX_PCA9532_H */ + -- cgit v1.2.3 From 781a54e7664cc0089287a90d27086e9656ac68a1 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Sat, 31 May 2008 15:23:19 +0100 Subject: leds: mark led_classdev.default_trigger as const LED classdev core doesn't modify memory pointed by the default_trigger, so mark it as const and we'll able to pass const char *s without getting compiler warnings. Signed-off-by: Anton Vorontsov Signed-off-by: Richard Purdie --- include/linux/leds.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 519df72e939d..e7a5e89932fe 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -48,7 +48,7 @@ struct led_classdev { struct device *dev; struct list_head node; /* LED Device list */ - char *default_trigger; /* Trigger to use */ + const char *default_trigger; /* Trigger to use */ #ifdef CONFIG_LEDS_TRIGGERS /* Protects the trigger data below */ -- cgit v1.2.3 From f46e9203d9a100bae216cc06e17f2e77351aa8d8 Mon Sep 17 00:00:00 2001 From: Nate Case Date: Wed, 16 Jul 2008 22:49:55 +0100 Subject: leds: Add support for Philips PCA955x I2C LED drivers This driver supports the PCA9550, PCA9551, PCA9552, and PCA9553 LED driver chips. Signed-off-by: Nate Case Signed-off-by: Andrew Morton Signed-off-by: Richard Purdie --- include/linux/leds.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index e7a5e89932fe..d41ccb56146a 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -118,6 +118,20 @@ extern void ledtrig_ide_activity(void); #define ledtrig_ide_activity() do {} while(0) #endif +/* + * Generic LED platform data for describing LED names and default triggers. + */ +struct led_info { + const char *name; + char *default_trigger; + int flags; +}; + +struct led_platform_data { + int num_leds; + struct led_info *leds; +}; + /* For the leds-gpio driver */ struct gpio_led { const char *name; -- cgit v1.2.3 From 95d04f0735b4fc837bff9aedcc3f3efb20ddc3d1 Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Wed, 23 Jul 2008 08:12:26 -0700 Subject: IB/mlx4: Add support for memory management extensions and local DMA L_Key Add support for the following operations to mlx4 when device firmware supports them: - Send with invalidate and local invalidate send queue work requests; - Allocate/free fast register MRs; - Allocate/free fast register MR page lists; - Fast register MR send queue work requests; - Local DMA L_Key. Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 10 ++++++++++ include/linux/mlx4/qp.h | 16 ++++++++++++---- 2 files changed, 22 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 81b3dd5206e0..655ea0d1ee14 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -68,6 +68,14 @@ enum { MLX4_DEV_CAP_FLAG_UD_MCAST = 1 << 21 }; +enum { + MLX4_BMME_FLAG_LOCAL_INV = 1 << 6, + MLX4_BMME_FLAG_REMOTE_INV = 1 << 7, + MLX4_BMME_FLAG_TYPE_2_WIN = 1 << 9, + MLX4_BMME_FLAG_RESERVED_LKEY = 1 << 10, + MLX4_BMME_FLAG_FAST_REG_WR = 1 << 11, +}; + enum mlx4_event { MLX4_EVENT_TYPE_COMP = 0x00, MLX4_EVENT_TYPE_PATH_MIG = 0x01, @@ -184,6 +192,8 @@ struct mlx4_caps { u32 max_msg_sz; u32 page_size_cap; u32 flags; + u32 bmme_flags; + u32 reserved_lkey; u16 stat_rate_support; u8 port_width_cap[MLX4_MAX_PORTS + 1]; int max_gso_sz; diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index f02e9ed36cfa..e27082cd650e 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -233,6 +233,14 @@ struct mlx4_wqe_bind_seg { __be64 length; }; +enum { + MLX4_WQE_FMR_PERM_LOCAL_READ = 1 << 27, + MLX4_WQE_FMR_PERM_LOCAL_WRITE = 1 << 28, + MLX4_WQE_FMR_PERM_REMOTE_READ = 1 << 29, + MLX4_WQE_FMR_PERM_REMOTE_WRITE = 1 << 30, + MLX4_WQE_FMR_PERM_ATOMIC = 1 << 31 +}; + struct mlx4_wqe_fmr_seg { __be32 flags; __be32 mem_key; @@ -255,11 +263,11 @@ struct mlx4_wqe_fmr_ext_seg { }; struct mlx4_wqe_local_inval_seg { - u8 flags; - u8 reserved1[3]; + __be32 flags; + u32 reserved1; __be32 mem_key; - u8 reserved2[3]; - u8 guest_id; + u32 reserved2[2]; + __be32 guest_id; __be64 pa; }; -- cgit v1.2.3 From a5bf6190417cbbf80443a9f71c65b653e13e9982 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Thu, 10 Jul 2008 18:38:33 +0300 Subject: UBI: add ubi_sync() interface To flush MTD device caches. Signed-off-by: Artem Bityutskiy --- include/linux/mtd/ubi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/ubi.h b/include/linux/mtd/ubi.h index f71201d0f3e7..83302bbbddb4 100644 --- a/include/linux/mtd/ubi.h +++ b/include/linux/mtd/ubi.h @@ -152,6 +152,7 @@ int ubi_leb_erase(struct ubi_volume_desc *desc, int lnum); int ubi_leb_unmap(struct ubi_volume_desc *desc, int lnum); int ubi_leb_map(struct ubi_volume_desc *desc, int lnum, int dtype); int ubi_is_mapped(struct ubi_volume_desc *desc, int lnum); +int ubi_sync(int ubi_num); /* * This function is the same as the 'ubi_leb_read()' function, but it does not -- cgit v1.2.3 From 85c6e6e28259e9b58b8984db536c45bc3161f40c Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 16 Jul 2008 10:25:56 +0300 Subject: UBI: amend commentaries Hch asked not to use "unit" for sub-systems, let it be so. Also some other commentaries modifications. Signed-off-by: Artem Bityutskiy --- include/linux/mtd/ubi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/ubi.h b/include/linux/mtd/ubi.h index 83302bbbddb4..6316fafe5c2a 100644 --- a/include/linux/mtd/ubi.h +++ b/include/linux/mtd/ubi.h @@ -45,13 +45,13 @@ enum { * @size: how many physical eraseblocks are reserved for this volume * @used_bytes: how many bytes of data this volume contains * @used_ebs: how many physical eraseblocks of this volume actually contain any - * data + * data * @vol_type: volume type (%UBI_DYNAMIC_VOLUME or %UBI_STATIC_VOLUME) * @corrupted: non-zero if the volume is corrupted (static volumes only) * @upd_marker: non-zero if the volume has update marker set * @alignment: volume alignment * @usable_leb_size: how many bytes are available in logical eraseblocks of - * this volume + * this volume * @name_len: volume name length * @name: volume name * @cdev: UBI volume character device major and minor numbers -- cgit v1.2.3 From b552068999b0b05087c454e525b30b785c79dc9b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 23 Apr 2008 10:07:27 -0400 Subject: Remove __DECLARE_SEMAPHORE_GENERIC There are no users of __DECLARE_SEMAPHORE_GENERIC in the kernel Signed-off-by: Matthew Wilcox --- include/linux/semaphore.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/semaphore.h b/include/linux/semaphore.h index 9cae64b00d6b..7415839ac890 100644 --- a/include/linux/semaphore.h +++ b/include/linux/semaphore.h @@ -26,10 +26,8 @@ struct semaphore { .wait_list = LIST_HEAD_INIT((name).wait_list), \ } -#define __DECLARE_SEMAPHORE_GENERIC(name, count) \ - struct semaphore name = __SEMAPHORE_INITIALIZER(name, count) - -#define DECLARE_MUTEX(name) __DECLARE_SEMAPHORE_GENERIC(name, 1) +#define DECLARE_MUTEX(name) \ + struct semaphore name = __SEMAPHORE_INITIALIZER(name, 1) static inline void sema_init(struct semaphore *sem, int val) { -- cgit v1.2.3 From e108526e77aa41c89b3be96f75d97615db2b751c Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Wed, 23 Jul 2008 21:26:44 -0700 Subject: move memory_read_from_buffer() from fs.h to string.h James Bottomley warns that inclusion of linux/fs.h in a low level driver was always a danger signal. This patch moves memory_read_from_buffer() from fs.h to string.h and fixes includes in existing memory_read_from_buffer() users. Signed-off-by: Akinobu Mita Cc: James Bottomley Cc: Geert Uytterhoeven Cc: Zhang Rui Cc: Bob Moore Cc: Thomas Renninger Cc: Len Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 -- include/linux/string.h | 3 +++ 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9c2ac5c0ef5c..ff54ae4933f3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2006,8 +2006,6 @@ extern void simple_release_fs(struct vfsmount **mount, int *count); extern ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available); -extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, - const void *from, size_t available); #ifdef CONFIG_MIGRATION extern int buffer_migrate_page(struct address_space *, diff --git a/include/linux/string.h b/include/linux/string.h index efdc44593b52..810d80df0a1d 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -111,5 +111,8 @@ extern void argv_free(char **argv); extern bool sysfs_streq(const char *s1, const char *s2); +extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, + const void *from, size_t available); + #endif #endif /* _LINUX_STRING_H_ */ -- cgit v1.2.3 From 8b05c7e6e159d2f33c9275281b8b909a89eb7c5d Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Wed, 23 Jul 2008 21:26:53 -0700 Subject: add a helper function to test if an object is on the stack lib/debugobjects.c has a function to test if an object is on the stack. The block layer and ide needs it (they need to avoid DMA from/to stack buffers). This patch moves the function to include/linux/sched.h so that everyone can use it. lib/debugobjects.c uses current->stack but this patch uses a task_stack_page() accessor, which is a preferable way to access the stack. Signed-off-by: FUJITA Tomonori Cc: Christoph Lameter Cc: Andy Whitcroft Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index dc7e592c473a..6aca4a16e377 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1983,6 +1983,13 @@ static inline unsigned long *end_of_stack(struct task_struct *p) #endif +static inline int object_is_on_stack(void *obj) +{ + void *stack = task_stack_page(current); + + return (obj >= stack) && (obj < (stack + THREAD_SIZE)); +} + extern void thread_info_cache_init(void); /* set thread flags in other task's structures -- cgit v1.2.3 From b61bfa3c462671c48a51fb5c31af337c5a996a04 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 23 Jul 2008 21:26:55 -0700 Subject: mm: move bootmem descriptors definition to a single place There are a lot of places that define either a single bootmem descriptor or an array of them. Use only one central array with MAX_NUMNODES items instead. Signed-off-by: Johannes Weiner Acked-by: Ralf Baechle Cc: Ingo Molnar Cc: Richard Henderson Cc: Russell King Cc: Tony Luck Cc: Hirokazu Takata Cc: Geert Uytterhoeven Cc: Kyle McMartin Cc: Paul Mackerras Cc: Paul Mundt Cc: David S. Miller Cc: Yinghai Lu Cc: Christoph Lameter Cc: Mel Gorman Cc: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index a1d9b79078ea..2599c741405e 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -38,6 +38,8 @@ typedef struct bootmem_data { struct list_head list; } bootmem_data_t; +extern bootmem_data_t bootmem_node_data[]; + extern unsigned long bootmem_bootmap_pages(unsigned long); extern unsigned long init_bootmem(unsigned long addr, unsigned long memend); extern void free_bootmem(unsigned long addr, unsigned long size); -- cgit v1.2.3 From ffc6421f0720f433b5b35b89ff56e998eabff93b Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 23 Jul 2008 21:26:59 -0700 Subject: mm: unexport __alloc_bootmem_core() This function has no external callers, so unexport it. Also fix its naming inconsistency. Signed-off-by: Johannes Weiner Cc: Ingo Molnar Cc: Yinghai Lu Cc: Christoph Lameter Cc: Mel Gorman Cc: Andy Whitcroft Cc: Mel Gorman Cc: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 2599c741405e..dd8fee6c46d9 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -56,11 +56,6 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal); -extern void *__alloc_bootmem_core(struct bootmem_data *bdata, - unsigned long size, - unsigned long align, - unsigned long goal, - unsigned long limit); /* * flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE, -- cgit v1.2.3 From e4048e5dc4aecec670f48ed007a28779f09cebd6 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Wed, 23 Jul 2008 21:27:01 -0700 Subject: page allocator: inline some __alloc_pages() wrappers Two zonelist patch series rewrote __page_alloc() largely. Now, it is just a wrapper function. Inlining them will save a function call. [akpm@linux-foundation.org: export __alloc_pages_internal] Cc: Lee Schermerhorn Cc: Mel Gorman Signed-off-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index b414be387180..f640ed241422 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -173,11 +173,24 @@ static inline void arch_free_page(struct page *page, int order) { } static inline void arch_alloc_page(struct page *page, int order) { } #endif -extern struct page *__alloc_pages(gfp_t, unsigned int, struct zonelist *); +struct page * +__alloc_pages_internal(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, nodemask_t *nodemask); + +static inline struct page * +__alloc_pages(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist) +{ + return __alloc_pages_internal(gfp_mask, order, zonelist, NULL); +} + +static inline struct page * +__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, nodemask_t *nodemask) +{ + return __alloc_pages_internal(gfp_mask, order, zonelist, nodemask); +} -extern struct page * -__alloc_pages_nodemask(gfp_t, unsigned int, - struct zonelist *, nodemask_t *nodemask); static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) -- cgit v1.2.3 From c748e1340e0de3fa7fed86f8bdf499be9242afff Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 23 Jul 2008 21:27:03 -0700 Subject: mm/vmstat.c: proper externs This patch adds proper extern declarations for five variables in include/linux/vmstat.h Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index e83b69346d23..58334d439516 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -44,6 +44,12 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, NR_VM_EVENT_ITEMS }; +extern const struct seq_operations fragmentation_op; +extern const struct seq_operations pagetypeinfo_op; +extern const struct seq_operations zoneinfo_op; +extern const struct seq_operations vmstat_op; +extern int sysctl_stat_interval; + #ifdef CONFIG_VM_EVENT_COUNTERS /* * Light weight per cpu counter implementation. -- cgit v1.2.3 From 0d71d10a4252a3938e6b70189bc776171c02e076 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 23 Jul 2008 21:27:05 -0700 Subject: mm: remove nopfn There are no users of nopfn in the tree. Remove it. [hugh@veritas.com: fix build error] Signed-off-by: Nick Piggin Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2128ef7780c6..eb815cfc1b35 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -166,8 +166,6 @@ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); void (*close)(struct vm_area_struct * area); int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf); - unsigned long (*nopfn)(struct vm_area_struct *area, - unsigned long address); /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ @@ -674,13 +672,6 @@ static inline int page_mapped(struct page *page) return atomic_read(&(page)->_mapcount) >= 0; } -/* - * Error return values for the *_nopfn functions - */ -#define NOPFN_SIGBUS ((unsigned long) -1) -#define NOPFN_OOM ((unsigned long) -2) -#define NOPFN_REFAULT ((unsigned long) -3) - /* * Different kinds of faults, as returned by handle_mm_fault(). * Used to decide whether a process gets delivered SIGBUS or -- cgit v1.2.3 From 28b2ee20c7cba812b6f2ccf6d722cf86d00a84dc Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 23 Jul 2008 21:27:05 -0700 Subject: access_process_vm device memory infrastructure In order to be able to debug things like the X server and programs using the PPC Cell SPUs, the debugger needs to be able to access device memory through ptrace and /proc/pid/mem. This patch: Add the generic_access_phys access function and put the hooks in place to allow access_process_vm to access device or PPC Cell SPU memory. [riel@redhat.com: Add documentation for the vm_ops->access function] Signed-off-by: Rik van Riel Signed-off-by: Benjamin Herrensmidt Cc: Dave Airlie Cc: Hugh Dickins Cc: Paul Mackerras Cc: Arnd Bergmann Acked-by: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index eb815cfc1b35..5c7f8f64f70e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -170,6 +170,12 @@ struct vm_operations_struct { /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ int (*page_mkwrite)(struct vm_area_struct *vma, struct page *page); + + /* called by access_process_vm when get_user_pages() fails, typically + * for use by special VMAs that can switch between memory and hardware + */ + int (*access)(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write); #ifdef CONFIG_NUMA /* * set_policy() op must add a reference to any non-NULL @new mempolicy @@ -771,6 +777,8 @@ int copy_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); +int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write); static inline void unmap_shared_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen) -- cgit v1.2.3 From 42b7772812d15b86543a23b82bd6070eef9a08b1 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Wed, 23 Jul 2008 21:27:10 -0700 Subject: mm: remove double indirection on tlb parameter to free_pgd_range() & Co The double indirection here is not needed anywhere and hence (at least) confusing. Signed-off-by: Jan Beulich Cc: Hugh Dickins Cc: Nick Piggin Cc: Christoph Lameter Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "Luck, Tony" Cc: Paul Mundt Cc: "David S. Miller" Acked-by: Jeremy Fitzhardinge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5c7f8f64f70e..f8071097302a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -769,10 +769,8 @@ struct mm_walk { int walk_page_range(unsigned long addr, unsigned long end, struct mm_walk *walk); -void free_pgd_range(struct mmu_gather **tlb, unsigned long addr, +void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); -void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *start_vma, - unsigned long floor, unsigned long ceiling); int copy_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma); void unmap_mapping_range(struct address_space *mapping, -- cgit v1.2.3 From da3bbdd4632c0171406b2677e31494afa5bde2f8 Mon Sep 17 00:00:00 2001 From: Kentaro Makita Date: Wed, 23 Jul 2008 21:27:13 -0700 Subject: fix soft lock up at NFS mount via per-SB LRU-list of unused dentries [Summary] Split LRU-list of unused dentries to one per superblock to avoid soft lock up during NFS mounts and remounting of any filesystem. Previously I posted here: http://lkml.org/lkml/2008/3/5/590 [Descriptions] - background dentry_unused is a list of dentries which are not referenced. dentry_unused grows up when references on directories or files are released. This list can be very long if there is huge free memory. - the problem When shrink_dcache_sb() is called, it scans all dentry_unused linearly under spin_lock(), and if dentry->d_sb is differnt from given superblock, scan next dentry. This scan costs very much if there are many entries, and very ineffective if there are many superblocks. IOW, When we need to shrink unused dentries on one dentry, but scans unused dentries on all superblocks in the system. For example, we scan 500 dentries to unmount a filesystem, but scans 1,000,000 or more unused dentries on other superblocks. In our case , At mounting NFS*, shrink_dcache_sb() is called to shrink unused dentries on NFS, but scans 100,000,000 unused dentries on superblocks in the system such as local ext3 filesystems. I hear NFS mounting took 1 min on some system in use. * : NFS uses virtual filesystem in rpc layer, so NFS is affected by this problem. 100,000,000 is possible number on large systems. Per-superblock LRU of unused dentried can reduce the cost in reasonable manner. - How to fix I found this problem is solved by David Chinner's "Per-superblock unused dentry LRU lists V3"(1), so I rebase it and add some fix to reclaim with fairness, which is in Andrew Morton's comments(2). 1) http://lkml.org/lkml/2006/5/25/318 2) http://lkml.org/lkml/2006/5/25/320 Split LRU-list of unused dentries to each superblocks. Then, NFS mounting will check dentries under a superblock instead of all. But this spliting will break LRU of dentry-unused. So, I've attempted to make reclaim unused dentrins with fairness by calculate number of dentries to scan on this sb based on following way number of dentries to scan on this sb = count * (number of dentries on this sb / number of dentries in the machine) - ToDo - I have to measuring performance number and do stress tests. - When unmount occurs during prune_dcache(), scanning on same superblock, It is unable to reach next superblock because it is gone away. We restart scannig superblock from first one, it causes unfairness of reclaim unused dentries on first superblock. But I think this happens very rarely. - Test Results Result on 6GB boxes with excessive unused dentries. Without patch: $ cat /proc/sys/fs/dentry-state 10181835 10180203 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m1.830s user 0m0.001s sys 0m1.653s With this patch: $ cat /proc/sys/fs/dentry-state 10236610 10234751 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m0.106s user 0m0.002s sys 0m0.032s [akpm@linux-foundation.org: fix comments] Signed-off-by: Kentaro Makita Cc: Neil Brown Cc: Trond Myklebust Cc: David Chinner Cc: "J. Bruce Fields" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index ff54ae4933f3..e5e6a244096c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1025,6 +1025,7 @@ extern int send_sigurg(struct fown_struct *fown); extern struct list_head super_blocks; extern spinlock_t sb_lock; +#define sb_entry(list) list_entry((list), struct super_block, s_list) #define S_BIAS (1<<30) struct super_block { struct list_head s_list; /* Keep this first */ @@ -1058,6 +1059,9 @@ struct super_block { struct list_head s_more_io; /* parked for more writeback */ struct hlist_head s_anon; /* anonymous dentries for (nfs) exporting */ struct list_head s_files; + /* s_dentry_lru and s_nr_dentry_unused are protected by dcache_lock */ + struct list_head s_dentry_lru; /* unused dentry lru */ + int s_nr_dentry_unused; /* # of dentry on lru */ struct block_device *s_bdev; struct mtd_info *s_mtd; -- cgit v1.2.3 From 0cad47cf13bc2e9142d3a11d9f50523797d0d4ea Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Wed, 23 Jul 2008 21:27:16 -0700 Subject: page-flags: record page flag overlays explicitly With the recent page flag reorganisation we have a single enum which defines the valid page flags and their values, nice and clear. However there are a number of bits which are overloaded by different subsystems. Firstly there is PG_owner_priv_1 which is used by filesystems and by XEN. Secondly both SLOB and SLUB use a couple of extra page bits to manage internal state for pages they own; both overlay other bits. All of these "aliases" are scattered about the source making it very hard for a reader to know if the bits are safe to rely on in all contexts; confusion here is bad. As we now have a single place where the bits are clearly assigned it makes sense to clarify the reuse of bits by making the aliases explicit and visible with the original bit assignments. This patch creates explicit aliases within the enum itself for the overloaded bits, creates standard bit accessors PageFoo etc. and uses those throughout. This version pulls the bit manipulation out to standard named page bit accessors as suggested by Christoph, it retains the explicit mapping to the overlayed bits. A fusion of both ideas. This has been SLUB and SLOB have been compile tested on x86_64 only, and SLUB boot tested. If people feel this is worth doing then I can run a fuller set of testing. This patch: Some page flags are used for more than one purpose, for example PG_owner_priv_1. Currently there are individual accessors for each user, each built using the common flag name far away from the bit definitions. This makes it hard to see all possible uses of these bits. Now that we have a single enum to generate the bit orders it makes sense to express overlays in the same place. So create per use aliases for this bit in the main page-flags enum and use those in the accessors. [akpm@linux-foundation.org: fix xen] Signed-off-by: Andy Whitcroft Cc: Pekka Enberg Cc: Christoph Lameter Cc: Matt Mackall Cc: Nick Piggin Cc: KAMEZAWA Hiroyuki Reviewed-by: KOSAKI Motohiro Cc: Rik van Riel Cc: Jeremy Fitzhardinge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 0d2a4e7012aa..7d8db1233e44 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -96,7 +96,14 @@ enum pageflags { #ifdef CONFIG_IA64_UNCACHED_ALLOCATOR PG_uncached, /* Page has been mapped as uncached */ #endif - __NR_PAGEFLAGS + __NR_PAGEFLAGS, + + /* Filesystems */ + PG_checked = PG_owner_priv_1, + + /* XEN */ + PG_pinned = PG_owner_priv_1, + PG_savepinned = PG_dirty, }; #ifndef __GENERATING_BOUNDS_H @@ -155,9 +162,9 @@ PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty) PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru) PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active) __PAGEFLAG(Slab, slab) -PAGEFLAG(Checked, owner_priv_1) /* Used by some filesystems */ -PAGEFLAG(Pinned, owner_priv_1) TESTSCFLAG(Pinned, owner_priv_1) /* Xen */ -PAGEFLAG(SavePinned, dirty); /* Xen */ +PAGEFLAG(Checked, checked) /* Used by some filesystems */ +PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned) /* Xen */ +PAGEFLAG(SavePinned, savepinned); /* Xen */ PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private) __SETPAGEFLAG(Private, private) -- cgit v1.2.3 From 8a38082d21cbc5ec961da7dda195e98a9a064dcf Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Wed, 23 Jul 2008 21:27:18 -0700 Subject: slub: record page flag overlays explicitly SLUB reuses two page bits for internal purposes, it overlays PG_active and PG_error. This is hidden away in slub.c. Document these overlays explicitly in the main page-flags enum along with all the others. Signed-off-by: Andy Whitcroft Cc: Pekka Enberg Cc: Christoph Lameter Cc: Matt Mackall Cc: Nick Piggin Tested-by: KOSAKI Motohiro Cc: KOSAKI Motohiro Cc: Rik van Riel Cc: Jeremy Fitzhardinge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 7d8db1233e44..3fc586b7b90b 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -104,6 +104,10 @@ enum pageflags { /* XEN */ PG_pinned = PG_owner_priv_1, PG_savepinned = PG_dirty, + + /* SLUB */ + PG_slub_frozen = PG_active, + PG_slub_debug = PG_error, }; #ifndef __GENERATING_BOUNDS_H @@ -169,6 +173,9 @@ PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private) __SETPAGEFLAG(Private, private) +__PAGEFLAG(SlubFrozen, slub_frozen) +__PAGEFLAG(SlubDebug, slub_debug) + /* * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. -- cgit v1.2.3 From 9023cb7e8564d95a1893f8cb6895a293be9a71fe Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Wed, 23 Jul 2008 21:27:19 -0700 Subject: slob: record page flag overlays explicitly SLOB reuses two page bits for internal purposes, it overlays PG_active and PG_private. This is hidden away in slob.c. Document these overlays explicitly in the main page-flags enum along with all the others. Signed-off-by: Andy Whitcroft Cc: Pekka Enberg Cc: Christoph Lameter Cc: Matt Mackall Cc: Nick Piggin Reviewed-by: KOSAKI Motohiro Cc: KOSAKI Motohiro Cc: Rik van Riel Cc: Jeremy Fitzhardinge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 3fc586b7b90b..54590a9a103e 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -105,6 +105,10 @@ enum pageflags { PG_pinned = PG_owner_priv_1, PG_savepinned = PG_dirty, + /* SLOB */ + PG_slob_page = PG_active, + PG_slob_free = PG_private, + /* SLUB */ PG_slub_frozen = PG_active, PG_slub_debug = PG_error, @@ -173,6 +177,9 @@ PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private) __SETPAGEFLAG(Private, private) +__PAGEFLAG(SlobPage, slob_page) +__PAGEFLAG(SlobFree, slob_free) + __PAGEFLAG(SlubFrozen, slub_frozen) __PAGEFLAG(SlubDebug, slub_debug) -- cgit v1.2.3 From 2185e69f680ae8c8496b6fc15e20c889d5b39b67 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 23 Jul 2008 21:27:19 -0700 Subject: mapping_set_error: add unlikely() This is called on a per-page basis and in the vast majority of cases `error' is zero. Cc: Guillaume Chazarain Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index d2fca802f809..ee1ec2c7723c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -22,7 +22,7 @@ static inline void mapping_set_error(struct address_space *mapping, int error) { - if (error) { + if (unlikely(error)) { if (error == -ENOSPC) set_bit(AS_ENOSPC, &mapping->flags); else -- cgit v1.2.3 From 9109fb7b3520de187ebc3646c209d66a233f7169 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 23 Jul 2008 21:27:20 -0700 Subject: mm: drop unneeded pgdat argument from free_area_init_node() free_area_init_node() gets passed in the node id as well as the node descriptor. This is redundant as the function can trivially get the node descriptor itself by means of NODE_DATA() and the node's id. I checked all the users and NODE_DATA() seems to be usable everywhere from where this function is called. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f8071097302a..196924b657bc 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -962,9 +962,8 @@ static inline void pgtable_page_dtor(struct page *page) NULL: pte_offset_kernel(pmd, address)) extern void free_area_init(unsigned long * zones_size); -extern void free_area_init_node(int nid, pg_data_t *pgdat, - unsigned long * zones_size, unsigned long zone_start_pfn, - unsigned long *zholes_size); +extern void free_area_init_node(int nid, unsigned long * zones_size, + unsigned long zone_start_pfn, unsigned long *zholes_size); #ifdef CONFIG_ARCH_POPULATES_NODE_MAP /* * With CONFIG_ARCH_POPULATES_NODE_MAP set, an architecture may initialise its -- cgit v1.2.3 From a1e78772d72b2616ed20e54896e68e0e7044854e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 23 Jul 2008 21:27:23 -0700 Subject: hugetlb: reserve huge pages for reliable MAP_PRIVATE hugetlbfs mappings until fork() This patch reserves huge pages at mmap() time for MAP_PRIVATE mappings in a similar manner to the reservations taken for MAP_SHARED mappings. The reserve count is accounted both globally and on a per-VMA basis for private mappings. This guarantees that a process that successfully calls mmap() will successfully fault all pages in the future unless fork() is called. The characteristics of private mappings of hugetlbfs files behaviour after this patch are; 1. The process calling mmap() is guaranteed to succeed all future faults until it forks(). 2. On fork(), the parent may die due to SIGKILL on writes to the private mapping if enough pages are not available for the COW. For reasonably reliable behaviour in the face of a small huge page pool, children of hugepage-aware processes should not reference the mappings; such as might occur when fork()ing to exec(). 3. On fork(), the child VMAs inherit no reserves. Reads on pages already faulted by the parent will succeed. Successful writes will depend on enough huge pages being free in the pool. 4. Quotas of the hugetlbfs mount are checked at reserve time for the mapper and at fault time otherwise. Before this patch, all reads or writes in the child potentially needs page allocations that can later lead to the death of the parent. This applies to reads and writes of uninstantiated pages as well as COW. After the patch it is only a write to an instantiated page that causes problems. Signed-off-by: Mel Gorman Acked-by: Adam Litke Cc: Andy Whitcroft Cc: William Lee Irwin III Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index a79e80b689d8..185b14c9f021 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -17,6 +17,7 @@ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) return vma->vm_flags & VM_HUGETLB; } +void reset_vma_resv_huge_pages(struct vm_area_struct *vma); int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); int hugetlb_overcommit_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); int hugetlb_treat_movable_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); @@ -30,7 +31,8 @@ int hugetlb_report_node_meminfo(int, char *); unsigned long hugetlb_total_pages(void); int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, int write_access); -int hugetlb_reserve_pages(struct inode *inode, long from, long to); +int hugetlb_reserve_pages(struct inode *inode, long from, long to, + struct vm_area_struct *vma); void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); extern unsigned long max_huge_pages; @@ -58,6 +60,11 @@ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) { return 0; } + +static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma) +{ +} + static inline unsigned long hugetlb_total_pages(void) { return 0; -- cgit v1.2.3 From 04f2cbe35699d22dbf428373682ead85ca1240f5 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 23 Jul 2008 21:27:25 -0700 Subject: hugetlb: guarantee that COW faults for a process that called mmap(MAP_PRIVATE) on hugetlbfs will succeed After patch 2 in this series, a process that successfully calls mmap() for a MAP_PRIVATE mapping will be guaranteed to successfully fault until a process calls fork(). At that point, the next write fault from the parent could fail due to COW if the child still has a reference. We only reserve pages for the parent but a copy must be made to avoid leaking data from the parent to the child after fork(). Reserves could be taken for both parent and child at fork time to guarantee faults but if the mapping is large it is highly likely we will not have sufficient pages for the reservation, and it is common to fork only to exec() immediatly after. A failure here would be very undesirable. Note that the current behaviour of mainline with MAP_PRIVATE pages is pretty bad. The following situation is allowed to occur today. 1. Process calls mmap(MAP_PRIVATE) 2. Process calls mlock() to fault all pages and makes sure it succeeds 3. Process forks() 4. Process writes to MAP_PRIVATE mapping while child still exists 5. If the COW fails at this point, the process gets SIGKILLed even though it had taken care to ensure the pages existed This patch improves the situation by guaranteeing the reliability of the process that successfully calls mmap(). When the parent performs COW, it will try to satisfy the allocation without using reserves. If that fails the parent will steal the page leaving any children without a page. Faults from the child after that point will result in failure. If the child COW happens first, an attempt will be made to allocate the page without reserves and the child will get SIGKILLed on failure. To summarise the new behaviour: 1. If the original mapper performs COW on a private mapping with multiple references, it will attempt to allocate a hugepage from the pool or the buddy allocator without using the existing reserves. On fail, VMAs mapping the same area are traversed and the page being COW'd is unmapped where found. It will then steal the original page as the last mapper in the normal way. 2. The VMAs the pages were unmapped from are flagged to note that pages with data no longer exist. Future no-page faults on those VMAs will terminate the process as otherwise it would appear that data was corrupted. A warning is printed to the console that this situation occured. 2. If the child performs COW first, it will attempt to satisfy the COW from the pool if there are enough pages or via the buddy allocator if overcommit is allowed and the buddy allocator can satisfy the request. If it fails, the child will be killed. If the pool is large enough, existing applications will not notice that the reserves were a factor. Existing applications depending on the no-reserves been set are unlikely to exist as for much of the history of hugetlbfs, pages were prefaulted at mmap(), allocating the pages at that point or failing the mmap(). [npiggin@suse.de: fix CONFIG_HUGETLB=n build] Signed-off-by: Mel Gorman Acked-by: Adam Litke Cc: Andy Whitcroft Cc: William Lee Irwin III Cc: Hugh Dickins Cc: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 185b14c9f021..abbc187193a1 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -23,8 +23,10 @@ int hugetlb_overcommit_handler(struct ctl_table *, int, struct file *, void __us int hugetlb_treat_movable_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, int *, int, int); -void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long); -void __unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long); +void unmap_hugepage_range(struct vm_area_struct *, + unsigned long, unsigned long, struct page *); +void __unmap_hugepage_range(struct vm_area_struct *, + unsigned long, unsigned long, struct page *); int hugetlb_prefault(struct address_space *, struct vm_area_struct *); int hugetlb_report_meminfo(char *); int hugetlb_report_node_meminfo(int, char *); @@ -74,7 +76,7 @@ static inline unsigned long hugetlb_total_pages(void) #define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL) #define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; }) #define hugetlb_prefault(mapping, vma) ({ BUG(); 0; }) -#define unmap_hugepage_range(vma, start, end) BUG() +#define unmap_hugepage_range(vma, start, end, page) BUG() #define hugetlb_report_meminfo(buf) 0 #define hugetlb_report_node_meminfo(n, buf) 0 #define follow_huge_pmd(mm, addr, pmd, write) NULL -- cgit v1.2.3 From cdfd4325c0d878679bd6a3ba8285b71d9980e3c0 Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Wed, 23 Jul 2008 21:27:28 -0700 Subject: mm: record MAP_NORESERVE status on vmas and fix small page mprotect reservations With Mel's hugetlb private reservation support patches applied, strict overcommit semantics are applied to both shared and private huge page mappings. This can be a problem if an application relied on unlimited overcommit semantics for private mappings. An example of this would be an application which maps a huge area with the intention of using it very sparsely. These application would benefit from being able to opt-out of the strict overcommit. It should be noted that prior to hugetlb supporting demand faulting all mappings were fully populated and so applications of this type should be rare. This patch stack implements the MAP_NORESERVE mmap() flag for huge page mappings. This flag has the same meaning as for small page mappings, suppressing reservations for that mapping. Thanks to Mel Gorman for reviewing a number of early versions of these patches. This patch: When a small page mapping is created with mmap() reservations are created by default for any memory pages required. When the region is read/write the reservation is increased for every page, no reservation is needed for read-only regions (as they implicitly share the zero page). Reservations are tracked via the VM_ACCOUNT vma flag which is present when the region has reservation backing it. When we convert a region from read-only to read-write new reservations are aquired and VM_ACCOUNT is set. However, when a read-only map is created with MAP_NORESERVE it is indistinguishable from a normal mapping. When we then convert that to read/write we are forced to incorrectly create reservations for it as we have no record of the original MAP_NORESERVE. This patch introduces a new vma flag VM_NORESERVE which records the presence of the original MAP_NORESERVE flag. This allows us to distinguish these two circumstances and correctly account the reserve. As well as fixing this FIXME in the code, this makes it much easier to introduce MAP_NORESERVE support for huge pages as this flag is available consistantly for the life of the mapping. VM_ACCOUNT on the other hand is heavily used at the generic level in association with small pages. Signed-off-by: Andy Whitcroft Cc: Mel Gorman Cc: Adam Litke Cc: Johannes Weiner Cc: Andy Whitcroft Cc: William Lee Irwin III Cc: Hugh Dickins Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 196924b657bc..df322fb4df31 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -100,6 +100,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */ #define VM_RESERVED 0x00080000 /* Count as reserved_vm like IO */ #define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */ +#define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ #define VM_MAPPED_COPY 0x01000000 /* T if mapped copy of data (nommu mmap) */ -- cgit v1.2.3 From ff7ea79cf7c3a481851bd4b2185fdeb6ce4afa29 Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Wed, 23 Jul 2008 21:27:39 -0700 Subject: mm: create /sys/kernel/mm Add a kobject to create /sys/kernel/mm when sysfs is mounted. The kobject will exist regardless. This will allow for the hugepage related sysfs directories to exist under the mm "subsystem" directory. Add an ABI file appropriately. [kosaki.motohiro@jp.fujitsu.com: fix build] Signed-off-by: Nishanth Aravamudan Cc: Nick Piggin Cc: Mel Gorman Signed-off-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kobject.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 60f0d418ae32..5437ac0276e2 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -186,6 +186,8 @@ extern struct kobject *kset_find_obj(struct kset *, const char *); /* The global /sys/kernel/ kobject for people to chain off of */ extern struct kobject *kernel_kobj; +/* The global /sys/kernel/mm/ kobject for people to chain off of */ +extern struct kobject *mm_kobj; /* The global /sys/hypervisor/ kobject for people to chain off of */ extern struct kobject *hypervisor_kobj; /* The global /sys/power/ kobject for people to chain off of */ -- cgit v1.2.3 From a5516438959d90b071ff0a484ce4f3f523dc3152 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 23 Jul 2008 21:27:41 -0700 Subject: hugetlb: modular state for hugetlb page size The goal of this patchset is to support multiple hugetlb page sizes. This is achieved by introducing a new struct hstate structure, which encapsulates the important hugetlb state and constants (eg. huge page size, number of huge pages currently allocated, etc). The hstate structure is then passed around the code which requires these fields, they will do the right thing regardless of the exact hstate they are operating on. This patch adds the hstate structure, with a single global instance of it (default_hstate), and does the basic work of converting hugetlb to use the hstate. Future patches will add more hstate structures to allow for different hugetlbfs mounts to have different page sizes. [akpm@linux-foundation.org: coding-style fixes] Acked-by: Adam Litke Acked-by: Nishanth Aravamudan Signed-off-by: Andi Kleen Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 88 ++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 83 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index abbc187193a1..ad2271e11f9b 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -8,7 +8,6 @@ #include #include #include -#include struct ctl_table; @@ -45,7 +44,8 @@ extern int sysctl_hugetlb_shm_group; /* arch callbacks */ -pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr); +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz); pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr); int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, @@ -80,7 +80,7 @@ static inline unsigned long hugetlb_total_pages(void) #define hugetlb_report_meminfo(buf) 0 #define hugetlb_report_node_meminfo(n, buf) 0 #define follow_huge_pmd(mm, addr, pmd, write) NULL -#define prepare_hugepage_range(addr,len) (-EINVAL) +#define prepare_hugepage_range(file, addr, len) (-EINVAL) #define pmd_huge(x) 0 #define is_hugepage_only_range(mm, addr, len) 0 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; }) @@ -134,8 +134,6 @@ struct file *hugetlb_file_setup(const char *name, size_t); int hugetlb_get_quota(struct address_space *mapping, long delta); void hugetlb_put_quota(struct address_space *mapping, long delta); -#define BLOCKS_PER_HUGEPAGE (HPAGE_SIZE / 512) - static inline int is_file_hugepages(struct file *file) { if (file->f_op == &hugetlbfs_file_operations) @@ -164,4 +162,84 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long flags); #endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */ +#ifdef CONFIG_HUGETLB_PAGE + +/* Defines one hugetlb page size */ +struct hstate { + int hugetlb_next_nid; + unsigned int order; + unsigned long mask; + unsigned long max_huge_pages; + unsigned long nr_huge_pages; + unsigned long free_huge_pages; + unsigned long resv_huge_pages; + unsigned long surplus_huge_pages; + unsigned long nr_overcommit_huge_pages; + struct list_head hugepage_freelists[MAX_NUMNODES]; + unsigned int nr_huge_pages_node[MAX_NUMNODES]; + unsigned int free_huge_pages_node[MAX_NUMNODES]; + unsigned int surplus_huge_pages_node[MAX_NUMNODES]; +}; + +extern struct hstate default_hstate; + +static inline struct hstate *hstate_vma(struct vm_area_struct *vma) +{ + return &default_hstate; +} + +static inline struct hstate *hstate_file(struct file *f) +{ + return &default_hstate; +} + +static inline struct hstate *hstate_inode(struct inode *i) +{ + return &default_hstate; +} + +static inline unsigned long huge_page_size(struct hstate *h) +{ + return (unsigned long)PAGE_SIZE << h->order; +} + +static inline unsigned long huge_page_mask(struct hstate *h) +{ + return h->mask; +} + +static inline unsigned int huge_page_order(struct hstate *h) +{ + return h->order; +} + +static inline unsigned huge_page_shift(struct hstate *h) +{ + return h->order + PAGE_SHIFT; +} + +static inline unsigned int pages_per_huge_page(struct hstate *h) +{ + return 1 << h->order; +} + +static inline unsigned int blocks_per_huge_page(struct hstate *h) +{ + return huge_page_size(h) / 512; +} + +#include + +#else +struct hstate {}; +#define hstate_file(f) NULL +#define hstate_vma(v) NULL +#define hstate_inode(i) NULL +#define huge_page_size(h) PAGE_SIZE +#define huge_page_mask(h) PAGE_MASK +#define huge_page_order(h) 0 +#define huge_page_shift(h) PAGE_SHIFT +#define pages_per_huge_page(h) 1 +#endif + #endif /* _LINUX_HUGETLB_H */ -- cgit v1.2.3 From e5ff215941d59f8ae6bf58f6428dc5c26745a612 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 23 Jul 2008 21:27:42 -0700 Subject: hugetlb: multiple hstates for multiple page sizes Add basic support for more than one hstate in hugetlbfs. This is the key to supporting multiple hugetlbfs page sizes at once. - Rather than a single hstate, we now have an array, with an iterator - default_hstate continues to be the struct hstate which we use by default - Add functions for architectures to register new hstates [akpm@linux-foundation.org: coding-style fixes] Acked-by: Adam Litke Acked-by: Nishanth Aravamudan Signed-off-by: Andi Kleen Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ad2271e11f9b..b75bdb4deba3 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -36,8 +36,6 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma); void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); -extern unsigned long max_huge_pages; -extern unsigned long sysctl_overcommit_huge_pages; extern unsigned long hugepages_treat_as_movable; extern const unsigned long hugetlb_zero, hugetlb_infinity; extern int sysctl_hugetlb_shm_group; @@ -181,7 +179,17 @@ struct hstate { unsigned int surplus_huge_pages_node[MAX_NUMNODES]; }; -extern struct hstate default_hstate; +void __init hugetlb_add_hstate(unsigned order); +struct hstate *size_to_hstate(unsigned long size); + +#ifndef HUGE_MAX_HSTATE +#define HUGE_MAX_HSTATE 1 +#endif + +extern struct hstate hstates[HUGE_MAX_HSTATE]; +extern unsigned int default_hstate_idx; + +#define default_hstate (hstates[default_hstate_idx]) static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { @@ -230,6 +238,11 @@ static inline unsigned int blocks_per_huge_page(struct hstate *h) #include +static inline struct hstate *page_hstate(struct page *page) +{ + return size_to_hstate(PAGE_SIZE << compound_order(page)); +} + #else struct hstate {}; #define hstate_file(f) NULL -- cgit v1.2.3 From a137e1cc6d6e7d315fef03962a2a5a113348b13b Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 23 Jul 2008 21:27:43 -0700 Subject: hugetlbfs: per mount huge page sizes Add the ability to configure the hugetlb hstate used on a per mount basis. - Add a new pagesize= option to the hugetlbfs mount that allows setting the page size - This option causes the mount code to find the hstate corresponding to the specified size, and sets up a pointer to the hstate in the mount's superblock. - Change the hstate accessors to use this information rather than the global_hstate they were using (requires a slight change in mm/memory.c so we don't NULL deref in the error-unmap path -- see comments). [np: take hstate out of hugetlbfs inode and vma->vm_private_data] Acked-by: Adam Litke Acked-by: Nishanth Aravamudan Signed-off-by: Andi Kleen Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index b75bdb4deba3..ba9263e631b9 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -100,6 +100,7 @@ struct hugetlbfs_config { umode_t mode; long nr_blocks; long nr_inodes; + struct hstate *hstate; }; struct hugetlbfs_sb_info { @@ -108,6 +109,7 @@ struct hugetlbfs_sb_info { long max_inodes; /* inodes allowed */ long free_inodes; /* inodes free */ spinlock_t stat_lock; + struct hstate *hstate; }; @@ -191,19 +193,21 @@ extern unsigned int default_hstate_idx; #define default_hstate (hstates[default_hstate_idx]) -static inline struct hstate *hstate_vma(struct vm_area_struct *vma) +static inline struct hstate *hstate_inode(struct inode *i) { - return &default_hstate; + struct hugetlbfs_sb_info *hsb; + hsb = HUGETLBFS_SB(i->i_sb); + return hsb->hstate; } static inline struct hstate *hstate_file(struct file *f) { - return &default_hstate; + return hstate_inode(f->f_dentry->d_inode); } -static inline struct hstate *hstate_inode(struct inode *i) +static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { - return &default_hstate; + return hstate_file(vma->vm_file); } static inline unsigned long huge_page_size(struct hstate *h) -- cgit v1.2.3 From a3437870160cf2caaac6bdd76c7377a5a4145a8c Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Wed, 23 Jul 2008 21:27:44 -0700 Subject: hugetlb: new sysfs interface Provide new hugepages user APIs that are more suited to multiple hstates in sysfs. There is a new directory, /sys/kernel/hugepages. Underneath that directory there will be a directory per-supported hugepage size, e.g.: /sys/kernel/hugepages/hugepages-64kB /sys/kernel/hugepages/hugepages-16384kB /sys/kernel/hugepages/hugepages-16777216kB corresponding to 64k, 16m and 16g respectively. Within each hugepages-size directory there are a number of files, corresponding to the tracked counters in the hstate, e.g.: /sys/kernel/hugepages/hugepages-64/nr_hugepages /sys/kernel/hugepages/hugepages-64/nr_overcommit_hugepages /sys/kernel/hugepages/hugepages-64/free_hugepages /sys/kernel/hugepages/hugepages-64/resv_hugepages /sys/kernel/hugepages/hugepages-64/surplus_hugepages Of these files, the first two are read-write and the latter three are read-only. The size of the hugepage being manipulated is trivially deducible from the enclosing directory and is always expressed in kB (to match meminfo). [dave@linux.vnet.ibm.com: fix build] [nacc@us.ibm.com: hugetlb: hang off of /sys/kernel/mm rather than /sys/kernel] [nacc@us.ibm.com: hugetlb: remove CONFIG_SYSFS dependency] Acked-by: Greg Kroah-Hartman Signed-off-by: Nishanth Aravamudan Signed-off-by: Nick Piggin Cc: Dave Hansen Signed-off-by: Nishanth Aravamudan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ba9263e631b9..58c0de32e7f0 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -164,6 +164,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, #ifdef CONFIG_HUGETLB_PAGE +#define HSTATE_NAME_LEN 32 /* Defines one hugetlb page size */ struct hstate { int hugetlb_next_nid; @@ -179,6 +180,7 @@ struct hstate { unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; + char name[HSTATE_NAME_LEN]; }; void __init hugetlb_add_hstate(unsigned order); -- cgit v1.2.3 From b54bbf7b81170f03597c17dd0b559e3006bc9868 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 23 Jul 2008 21:27:45 -0700 Subject: mm: introduce non panic alloc_bootmem Straight forward variant of the existing __alloc_bootmem_node, only subsequent patch when allocating giant hugepages at boot -- don't want to panic if we can't allocate as many as the user asked for. Signed-off-by: Andi Kleen Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index dd8fee6c46d9..f352c5f125b4 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -89,6 +89,10 @@ extern void *__alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal); +extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat, + unsigned long size, + unsigned long align, + unsigned long goal); extern unsigned long init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn, unsigned long startpfn, -- cgit v1.2.3 From ceb868796181dc95ea01a110e123afd391639873 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 23 Jul 2008 21:27:50 -0700 Subject: hugetlb: introduce pud_huge Straight forward extensions for huge pages located in the PUD instead of PMDs. Signed-off-by: Andi Kleen Signed-off-by: Nick Piggin Cc: Martin Schwidefsky Cc: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 58c0de32e7f0..b2c17f62cacb 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -50,7 +50,10 @@ struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int write); struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write); +struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address, + pud_t *pud, int write); int pmd_huge(pmd_t pmd); +int pud_huge(pud_t pmd); void hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot); @@ -78,8 +81,10 @@ static inline unsigned long hugetlb_total_pages(void) #define hugetlb_report_meminfo(buf) 0 #define hugetlb_report_node_meminfo(n, buf) 0 #define follow_huge_pmd(mm, addr, pmd, write) NULL +#define follow_huge_pud(mm, addr, pud, write) NULL #define prepare_hugepage_range(file, addr, len) (-EINVAL) #define pmd_huge(x) 0 +#define pud_huge(x) 0 #define is_hugepage_only_range(mm, addr, len) 0 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; }) #define hugetlb_fault(mm, vma, addr, write) ({ BUG(); 0; }) -- cgit v1.2.3 From 53ba51d21d6e048424ab8aadfebdb1f25ae07b60 Mon Sep 17 00:00:00 2001 From: Jon Tollefson Date: Wed, 23 Jul 2008 21:27:52 -0700 Subject: hugetlb: allow arch overridden hugepage allocation Allow alloc_bootmem_huge_page() to be overridden by architectures that can't always use bootmem. This requires huge_boot_pages to be available for use by this function. This is required for powerpc 16G pages, which have to be reserved prior to boot-time. The location of these pages are indicated in the device tree. Acked-by: Adam Litke Signed-off-by: Jon Tollefson Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index b2c17f62cacb..9a71d4cc88c8 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -39,6 +39,7 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); extern unsigned long hugepages_treat_as_movable; extern const unsigned long hugetlb_zero, hugetlb_infinity; extern int sysctl_hugetlb_shm_group; +extern struct list_head huge_boot_pages; /* arch callbacks */ @@ -188,6 +189,14 @@ struct hstate { char name[HSTATE_NAME_LEN]; }; +struct huge_bootmem_page { + struct list_head list; + struct hstate *hstate; +}; + +/* arch callback */ +int __init alloc_bootmem_huge_page(struct hstate *h); + void __init hugetlb_add_hstate(unsigned order); struct hstate *size_to_hstate(unsigned long size); @@ -256,6 +265,7 @@ static inline struct hstate *page_hstate(struct page *page) #else struct hstate {}; +#define alloc_bootmem_huge_page(h) NULL #define hstate_file(f) NULL #define hstate_vma(v) NULL #define hstate_inode(i) NULL -- cgit v1.2.3 From 223e8dc9249c9e15f6c8b638d73fcad78ccb0a88 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 23 Jul 2008 21:28:00 -0700 Subject: bootmem: reorder code to match new bootmem structure This only reorders functions so that further patches will be easier to read. No code changed. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 86 ++++++++++++++++++++++++++----------------------- 1 file changed, 45 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index f352c5f125b4..5000fd70b04f 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -41,36 +41,62 @@ typedef struct bootmem_data { extern bootmem_data_t bootmem_node_data[]; extern unsigned long bootmem_bootmap_pages(unsigned long); + +extern unsigned long init_bootmem_node(pg_data_t *pgdat, + unsigned long freepfn, + unsigned long startpfn, + unsigned long endpfn); extern unsigned long init_bootmem(unsigned long addr, unsigned long memend); + +extern unsigned long free_all_bootmem_node(pg_data_t *pgdat); +extern unsigned long free_all_bootmem(void); + +extern void free_bootmem_node(pg_data_t *pgdat, + unsigned long addr, + unsigned long size); extern void free_bootmem(unsigned long addr, unsigned long size); -extern void *__alloc_bootmem(unsigned long size, + +/* + * Flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE, + * the architecture-specific code should honor this). + * + * If flags is 0, then the return value is always 0 (success). If + * flags contains BOOTMEM_EXCLUSIVE, then -EBUSY is returned if the + * memory already was reserved. + */ +#define BOOTMEM_DEFAULT 0 +#define BOOTMEM_EXCLUSIVE (1<<0) + +extern int reserve_bootmem_node(pg_data_t *pgdat, + unsigned long physaddr, + unsigned long size, + int flags); +#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE +extern int reserve_bootmem(unsigned long addr, unsigned long size, int flags); +#endif + +extern void *__alloc_bootmem_nopanic(unsigned long size, unsigned long align, unsigned long goal); -extern void *__alloc_bootmem_nopanic(unsigned long size, +extern void *__alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal); extern void *__alloc_bootmem_low(unsigned long size, unsigned long align, unsigned long goal); +extern void *__alloc_bootmem_node(pg_data_t *pgdat, + unsigned long size, + unsigned long align, + unsigned long goal); +extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat, + unsigned long size, + unsigned long align, + unsigned long goal); extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal); - -/* - * flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE, - * the architecture-specific code should honor this) - */ -#define BOOTMEM_DEFAULT 0 -#define BOOTMEM_EXCLUSIVE (1<<0) - #ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE -/* - * If flags is 0, then the return value is always 0 (success). If - * flags contains BOOTMEM_EXCLUSIVE, then -EBUSY is returned if the - * memory already was reserved. - */ -extern int reserve_bootmem(unsigned long addr, unsigned long size, int flags); #define alloc_bootmem(x) \ __alloc_bootmem(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_low(x) \ @@ -83,38 +109,16 @@ extern int reserve_bootmem(unsigned long addr, unsigned long size, int flags); extern int reserve_bootmem_generic(unsigned long addr, unsigned long size, int flags); -extern unsigned long free_all_bootmem(void); -extern unsigned long free_all_bootmem_node(pg_data_t *pgdat); -extern void *__alloc_bootmem_node(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal); -extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal); -extern unsigned long init_bootmem_node(pg_data_t *pgdat, - unsigned long freepfn, - unsigned long startpfn, - unsigned long endpfn); -extern int reserve_bootmem_node(pg_data_t *pgdat, - unsigned long physaddr, - unsigned long size, - int flags); -extern void free_bootmem_node(pg_data_t *pgdat, - unsigned long addr, - unsigned long size); -extern void *alloc_bootmem_section(unsigned long size, - unsigned long section_nr); -#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE #define alloc_bootmem_node(pgdat, x) \ __alloc_bootmem_node(pgdat, x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_pages_node(pgdat, x) \ __alloc_bootmem_node(pgdat, x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_low_pages_node(pgdat, x) \ __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0) -#endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */ + +extern void *alloc_bootmem_section(unsigned long size, + unsigned long section_nr); #ifdef CONFIG_HAVE_ARCH_ALLOC_REMAP extern void *alloc_remap(int nid, unsigned long size); -- cgit v1.2.3 From 5f2809e69c7128f86316048221cf45146f69a4a0 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 23 Jul 2008 21:28:05 -0700 Subject: bootmem: clean up alloc_bootmem_core alloc_bootmem_core has become quite nasty to read over time. This is a clean rewrite that keeps the semantics. bdata->last_pos has been dropped. bdata->last_success has been renamed to hint_idx and it is now an index relative to the node's range. Since further block searching might start at this index, it is now set to the end of a succeeded allocation rather than its beginning. bdata->last_offset has been renamed to last_end_off to be more clear that it represents the ending address of the last allocation relative to the node. [y-goto@jp.fujitsu.com: fix new alloc_bootmem_core()] Signed-off-by: Johannes Weiner Signed-off-by: Yasunori Goto Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 5000fd70b04f..90921d10ffa2 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -31,10 +31,8 @@ typedef struct bootmem_data { unsigned long node_boot_start; unsigned long node_low_pfn; void *node_bootmem_map; - unsigned long last_offset; - unsigned long last_pos; - unsigned long last_success; /* Previous allocation point. To speed - * up searching */ + unsigned long last_end_off; + unsigned long hint_idx; struct list_head list; } bootmem_data_t; -- cgit v1.2.3 From 3560e249abda6bee41a07a7bf0383a6e193e2839 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 23 Jul 2008 21:28:09 -0700 Subject: bootmem: replace node_boot_start in struct bootmem_data Almost all users of this field need a PFN instead of a physical address, so replace node_boot_start with node_min_pfn. [Lee.Schermerhorn@hp.com: fix spurious BUG_ON() in mark_bootmem()] Signed-off-by: Johannes Weiner Cc: Signed-off-by: Lee Schermerhorn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 90921d10ffa2..4ddf2922fc8d 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -28,7 +28,7 @@ extern unsigned long saved_max_pfn; * memory pages (including holes) on the node. */ typedef struct bootmem_data { - unsigned long node_boot_start; + unsigned long node_min_pfn; unsigned long node_low_pfn; void *node_bootmem_map; unsigned long last_end_off; -- cgit v1.2.3 From 2be0ffe2b29bd31d3debd0877797892ff2d91f4c Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Wed, 23 Jul 2008 21:28:11 -0700 Subject: mm: add alloc_pages_exact() and free_pages_exact() alloc_pages_exact() is similar to alloc_pages(), except that it allocates the minimum number of pages to fulfill the request. This is useful if you want to allocate a very large buffer that is slightly larger than an even power-of-two number of pages. In that case, alloc_pages() will waste a lot of memory. I have a video driver that wants to allocate a 5MB buffer. alloc_pages() wiill waste 3MB of physically-contiguous memory. Signed-off-by: Timur Tabi Cc: Andi Kleen Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index f640ed241422..e8003afeffba 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -228,6 +228,9 @@ extern struct page *alloc_page_vma(gfp_t gfp_mask, extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); +void *alloc_pages_exact(size_t size, gfp_t gfp_mask); +void free_pages_exact(void *virt, size_t size); + #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask),0) -- cgit v1.2.3 From 27ac792ca0b0a1e7e65f20342260650516c95864 Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Wed, 23 Jul 2008 21:28:13 -0700 Subject: PAGE_ALIGN(): correctly handle 64-bit values on 32-bit architectures On 32-bit architectures PAGE_ALIGN() truncates 64-bit values to the 32-bit boundary. For example: u64 val = PAGE_ALIGN(size); always returns a value < 4GB even if size is greater than 4GB. The problem resides in PAGE_MASK definition (from include/asm-x86/page.h for example): #define PAGE_SHIFT 12 #define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE-1)) ... #define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) The "~" is performed on a 32-bit value, so everything in "and" with PAGE_MASK greater than 4GB will be truncated to the 32-bit boundary. Using the ALIGN() macro seems to be the right way, because it uses typeof(addr) for the mask. Also move the PAGE_ALIGN() definitions out of include/asm-*/page.h in include/linux/mm.h. See also lkml discussion: http://lkml.org/lkml/2008/6/11/237 [akpm@linux-foundation.org: fix drivers/media/video/uvc/uvc_queue.c] [akpm@linux-foundation.org: fix v850] [akpm@linux-foundation.org: fix powerpc] [akpm@linux-foundation.org: fix arm] [akpm@linux-foundation.org: fix mips] [akpm@linux-foundation.org: fix drivers/media/video/pvrusb2/pvrusb2-dvb.c] [akpm@linux-foundation.org: fix drivers/mtd/maps/uclinux.c] [akpm@linux-foundation.org: fix powerpc] Signed-off-by: Andrea Righi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index df322fb4df31..d87a5a5fe87d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -41,6 +41,9 @@ extern unsigned long mmap_min_addr; #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) +/* to align the pointer to the (next) page boundary */ +#define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) + /* * Linux kernel virtual memory manager primitives. * The idea being to have a "virtual" mm in the same way -- cgit v1.2.3 From af370fb8cb3031f20438f246798d5f0d98089f29 Mon Sep 17 00:00:00 2001 From: Yasunori Goto Date: Wed, 23 Jul 2008 21:28:17 -0700 Subject: memory hotplug: small fixes to bootmem freeing for memory hotremove - Change some naming * Magic -> types * MIX_INFO -> MIX_SECTION_INFO * Change definition of bootmem type from direct hex value - __free_pages_bootmem() becomes __meminit. Signed-off-by: Yasunori Goto Cc: Andy Whitcroft Cc: Badari Pulavarty Cc: Yinghai Lu Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index ea9f5ad9ec8e..3628e5088f64 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -13,12 +13,12 @@ struct mem_section; #ifdef CONFIG_MEMORY_HOTPLUG /* - * Magic number for free bootmem. + * Types for free bootmem. * The normal smallest mapcount is -1. Here is smaller value than it. */ -#define SECTION_INFO 0xfffffffe -#define MIX_INFO 0xfffffffd -#define NODE_INFO 0xfffffffc +#define SECTION_INFO (-1 - 1) +#define MIX_SECTION_INFO (-1 - 2) +#define NODE_INFO (-1 - 3) /* * pgdat resizing functions -- cgit v1.2.3 From 5c755e9fd813810680abd56ec09a5f90143e815b Mon Sep 17 00:00:00 2001 From: Badari Pulavarty Date: Wed, 23 Jul 2008 21:28:19 -0700 Subject: memory-hotplug: add sysfs removable attribute for hotplug memory remove Memory may be hot-removed on a per-memory-block basis, particularly on POWER where the SPARSEMEM section size often matches the memory-block size. A user-level agent must be able to identify which sections of memory are likely to be removable before attempting the potentially expensive operation. This patch adds a file called "removable" to the memory directory in sysfs to help such an agent. In this patch, a memory block is considered removable if; o It contains only MOVABLE pageblocks o It contains only pageblocks with free pages regardless of pageblock type On the other hand, a memory block starting with a PageReserved() page will never be considered removable. Without this patch, the user-agent is forced to choose a memory block to remove randomly. Sample output of the sysfs files: ./memory/memory0/removable: 0 ./memory/memory1/removable: 0 ./memory/memory2/removable: 0 ./memory/memory3/removable: 0 ./memory/memory4/removable: 0 ./memory/memory5/removable: 0 ./memory/memory6/removable: 0 ./memory/memory7/removable: 1 ./memory/memory8/removable: 0 ./memory/memory9/removable: 0 ./memory/memory10/removable: 0 ./memory/memory11/removable: 0 ./memory/memory12/removable: 0 ./memory/memory13/removable: 0 ./memory/memory14/removable: 0 ./memory/memory15/removable: 0 ./memory/memory16/removable: 0 ./memory/memory17/removable: 1 ./memory/memory18/removable: 1 ./memory/memory19/removable: 1 ./memory/memory20/removable: 1 ./memory/memory21/removable: 1 ./memory/memory22/removable: 1 Signed-off-by: Badari Pulavarty Signed-off-by: Mel Gorman Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 3628e5088f64..763ba81fc0f0 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -199,6 +199,18 @@ extern int walk_memory_resource(unsigned long start_pfn, unsigned long nr_pages, void *arg, int (*func)(unsigned long, unsigned long, void *)); +#ifdef CONFIG_MEMORY_HOTREMOVE + +extern int is_mem_section_removable(unsigned long pfn, unsigned long nr_pages); + +#else +static inline int is_mem_section_removable(unsigned long pfn, + unsigned long nr_pages) +{ + return 0; +} +#endif /* CONFIG_MEMORY_HOTREMOVE */ + extern int add_memory(int nid, u64 start, u64 size); extern int arch_add_memory(int nid, u64 start, u64 size); extern int remove_memory(u64 start, u64 size); -- cgit v1.2.3 From 9ca908f47bc784c90e17a553ce33e756c73feac4 Mon Sep 17 00:00:00 2001 From: Milton Miller Date: Wed, 23 Jul 2008 21:28:20 -0700 Subject: kcalloc: remove runtime division While in all cases in the kernel we know the size of the elements to be created, we don't always know the count of elements. By commuting the size and count in the overflow check, the compiler can reduce the runtime division of size_t with a compare to a (unique) constant in these cases. Signed-off-by: Milton Miller Cc: Takashi Iwai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 9aa90a6f20e0..41103910f8a2 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -180,7 +180,7 @@ size_t ksize(const void *); */ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) { - if (n != 0 && size > ULONG_MAX / n) + if (size != 0 && n > ULONG_MAX / size) return NULL; return __kmalloc(n * size, flags | __GFP_ZERO); } -- cgit v1.2.3 From 83d1674a946141c3c59d430e96c224f7937e6158 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Wed, 23 Jul 2008 21:28:22 -0700 Subject: mm: make CONFIG_MIGRATION available w/o CONFIG_NUMA We'd like to support CONFIG_MEMORY_HOTREMOVE on s390, which depends on CONFIG_MIGRATION. So far, CONFIG_MIGRATION is only available with NUMA support. This patch makes CONFIG_MIGRATION selectable for architectures that define ARCH_ENABLE_MEMORY_HOTREMOVE. When MIGRATION is enabled w/o NUMA, the kernel won't compile because migrate_vmas() does not know about vm_ops->migrate() and vma_migratable() does not know about policy_zone. To fix this, those two functions can be restricted to '#ifdef CONFIG_NUMA' because they are not being used w/o NUMA. vma_migratable() is moved over from migrate.h to mempolicy.h. [kosaki.motohiro@jp.fujitsu.com: build fix] Acked-by: Christoph Lameter Signed-off-by: Gerald Schaefer Cc: Martin Schwidefsky Cc: Heiko Carstens Signed-off-by: KOSAKI Motorhiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 19 +++++++++++++++++++ include/linux/migrate.h | 21 --------------------- 2 files changed, 19 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 3a39570b81b8..085c903fe0f1 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -59,6 +59,7 @@ enum { #include #include #include +#include struct mm_struct; @@ -220,6 +221,24 @@ extern int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context); extern int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context); #endif + +/* Check if a vma is migratable */ +static inline int vma_migratable(struct vm_area_struct *vma) +{ + if (vma->vm_flags & (VM_IO|VM_HUGETLB|VM_PFNMAP|VM_RESERVED)) + return 0; + /* + * Migration allocates pages in the highest zone. If we cannot + * do so then migration (at least from node to node) is not + * possible. + */ + if (vma->vm_file && + gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping)) + < policy_zone) + return 0; + return 1; +} + #else struct mempolicy {}; diff --git a/include/linux/migrate.h b/include/linux/migrate.h index e10a90a93b5d..03aea612d284 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -3,28 +3,10 @@ #include #include -#include typedef struct page *new_page_t(struct page *, unsigned long private, int **); #ifdef CONFIG_MIGRATION -/* Check if a vma is migratable */ -static inline int vma_migratable(struct vm_area_struct *vma) -{ - if (vma->vm_flags & (VM_IO|VM_HUGETLB|VM_PFNMAP|VM_RESERVED)) - return 0; - /* - * Migration allocates pages in the highest zone. If we cannot - * do so then migration (at least from node to node) is not - * possible. - */ - if (vma->vm_file && - gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping)) - < policy_zone) - return 0; - return 1; -} - extern int isolate_lru_page(struct page *p, struct list_head *pagelist); extern int putback_lru_pages(struct list_head *l); extern int migrate_page(struct address_space *, @@ -39,9 +21,6 @@ extern int migrate_vmas(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, unsigned long flags); #else -static inline int vma_migratable(struct vm_area_struct *vma) - { return 0; } - static inline int isolate_lru_page(struct page *p, struct list_head *list) { return -ENOSYS; } static inline int putback_lru_pages(struct list_head *l) { return 0; } -- cgit v1.2.3 From 5459c164f0591ee75ed0203bb8f3817f25948e2f Mon Sep 17 00:00:00 2001 From: "Andrew G. Morgan" Date: Wed, 23 Jul 2008 21:28:24 -0700 Subject: security: protect legacy applications from executing with insufficient privilege When cap_bset suppresses some of the forced (fP) capabilities of a file, it is generally only safe to execute the program if it understands how to recognize it doesn't have enough privilege to work correctly. For legacy applications (fE!=0), which have no non-destructive way to determine that they are missing privilege, we fail to execute (EPERM) any executable that requires fP capabilities, but would otherwise get pP' < fP. This is a fail-safe permission check. For some discussion of why it is problematic for (legacy) privileged applications to run with less than the set of capabilities requested for them, see: http://userweb.kernel.org/~morgan/sendmail-capabilities-war-story.html With this iteration of this support, we do not include setuid-0 based privilege protection from the bounding set. That is, the admin can still (ab)use the bounding set to suppress the privileges of a setuid-0 program. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: cleanup] Signed-off-by: Andrew G. Morgan Acked-by: Serge Hallyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/binfmts.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index ee0ed48e8348..826f62350805 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -38,7 +38,7 @@ struct linux_binprm{ misc_bang:1; struct file * file; int e_uid, e_gid; - kernel_cap_t cap_inheritable, cap_permitted; + kernel_cap_t cap_post_exec_permitted; bool cap_effective; void *security; int argc, envc; -- cgit v1.2.3 From 9b3e43a747c74029b0acf6acf4666601f132f471 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 23 Jul 2008 21:28:26 -0700 Subject: security: remove unused forwards Why would linux/security.h need forward declarations for nfsctl_arg and swap_info_struct? It's hard to imagine: remove them. Signed-off-by: Hugh Dickins Acked-by: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/security.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 31c8851ec5d0..f0e9adb22ac2 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -102,9 +102,7 @@ extern unsigned long mmap_min_addr; #define LSM_SETID_FS 8 /* forward declares to avoid warnings */ -struct nfsctl_arg; struct sched_param; -struct swap_info_struct; struct request_sock; /* bprm_apply_creds unsafe reasons */ -- cgit v1.2.3 From d75f65fd247fe85d90a3880d143b1bb22fe13a48 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 23 Jul 2008 21:28:34 -0700 Subject: remove include/linux/pm_legacy.h Remove the obsolete and no longer used include/linux/pm_legacy.h Reviewed-by: Robert P. J. Day Signed-off-by: Adrian Bunk Cc: Pavel Machek Acked-by: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pm_legacy.h | 35 ----------------------------------- 1 file changed, 35 deletions(-) delete mode 100644 include/linux/pm_legacy.h (limited to 'include/linux') diff --git a/include/linux/pm_legacy.h b/include/linux/pm_legacy.h deleted file mode 100644 index 446f4f42b952..000000000000 --- a/include/linux/pm_legacy.h +++ /dev/null @@ -1,35 +0,0 @@ -#ifndef __LINUX_PM_LEGACY_H__ -#define __LINUX_PM_LEGACY_H__ - - -#ifdef CONFIG_PM_LEGACY - -/* - * Register a device with power management - */ -struct pm_dev __deprecated * -pm_register(pm_dev_t type, unsigned long id, pm_callback callback); - -/* - * Send a request to all devices - */ -int __deprecated pm_send_all(pm_request_t rqst, void *data); - -#else /* CONFIG_PM_LEGACY */ - -static inline struct pm_dev *pm_register(pm_dev_t type, - unsigned long id, - pm_callback callback) -{ - return NULL; -} - -static inline int pm_send_all(pm_request_t rqst, void *data) -{ - return 0; -} - -#endif /* CONFIG_PM_LEGACY */ - -#endif /* __LINUX_PM_LEGACY_H__ */ - -- cgit v1.2.3 From 558481f038e587b22d02167af58914c814ce9de5 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 23 Jul 2008 21:28:35 -0700 Subject: pm: remove definition of struct pm_dev Remove the definition of 'struct pm_dev', which is not used any more, along with some related stuff from include/linux/pm.h . Signed-off-by: Rafael J. Wysocki Acked-by: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pm.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 4ad9de94449a..5bf1ce89cfbb 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -68,30 +68,6 @@ enum */ #define PM_PCI_ID(dev) ((dev)->bus->number << 16 | (dev)->devfn) -/* - * Request handler callback - */ -struct pm_dev; - -typedef int (*pm_callback)(struct pm_dev *dev, pm_request_t rqst, void *data); - -/* - * Dynamic device information - */ -struct pm_dev -{ - pm_dev_t type; - unsigned long id; - pm_callback callback; - void *data; - - unsigned long flags; - unsigned long state; - unsigned long prev_state; - - struct list_head entry; -}; - /* Functions above this comment are list-based old-style power * management. Please avoid using them. */ -- cgit v1.2.3 From e7ecb331e11d1f7aa66aeef9170fc20781c9bb55 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 23 Jul 2008 21:28:35 -0700 Subject: pm: remove remaining obsolete definitions from pm.h Remove the remaining obsolete definitions from include/linux/pm.h and move the definitions of PM_SUSPEND and PM_RESUME to the header of h3600 which is the only user of them. Signed-off-by: Rafael J. Wysocki Acked-by: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pm.h | 46 ---------------------------------------------- 1 file changed, 46 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 5bf1ce89cfbb..390dd95a375e 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -25,52 +25,6 @@ #include #include -/* - * Power management requests... these are passed to pm_send_all() and friends. - * - * these functions are old and deprecated, see below. - */ -typedef int __bitwise pm_request_t; - -#define PM_SUSPEND ((__force pm_request_t) 1) /* enter D1-D3 */ -#define PM_RESUME ((__force pm_request_t) 2) /* enter D0 */ - - -/* - * Device types... these are passed to pm_register - */ -typedef int __bitwise pm_dev_t; - -#define PM_UNKNOWN_DEV ((__force pm_dev_t) 0) /* generic */ -#define PM_SYS_DEV ((__force pm_dev_t) 1) /* system device (fan, KB controller, ...) */ -#define PM_PCI_DEV ((__force pm_dev_t) 2) /* PCI device */ -#define PM_USB_DEV ((__force pm_dev_t) 3) /* USB device */ -#define PM_SCSI_DEV ((__force pm_dev_t) 4) /* SCSI device */ -#define PM_ISA_DEV ((__force pm_dev_t) 5) /* ISA device */ -#define PM_MTD_DEV ((__force pm_dev_t) 6) /* Memory Technology Device */ - -/* - * System device hardware ID (PnP) values - */ -enum -{ - PM_SYS_UNKNOWN = 0x00000000, /* generic */ - PM_SYS_KBC = 0x41d00303, /* keyboard controller */ - PM_SYS_COM = 0x41d00500, /* serial port */ - PM_SYS_IRDA = 0x41d00510, /* IRDA controller */ - PM_SYS_FDC = 0x41d00700, /* floppy controller */ - PM_SYS_VGA = 0x41d00900, /* VGA controller */ - PM_SYS_PCMCIA = 0x41d00e00, /* PCMCIA controller */ -}; - -/* - * Device identifier - */ -#define PM_PCI_ID(dev) ((dev)->bus->number << 16 | (dev)->devfn) - -/* Functions above this comment are list-based old-style power - * management. Please avoid using them. */ - /* * Callbacks for platform drivers to implement. */ -- cgit v1.2.3 From 8c363265d57d755e62053e9f69a1f2164e83f7ea Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 23 Jul 2008 21:28:37 -0700 Subject: pm: drop unnecessary includes from pm.h Drop unnecessary includes from include/linux/pm.h . Signed-off-by: Rafael J. Wysocki Acked-by: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 390dd95a375e..ed98d967f9fb 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -22,8 +22,6 @@ #define _LINUX_PM_H #include -#include -#include /* * Callbacks for platform drivers to implement. -- cgit v1.2.3 From 8111d1b552349921aae1acf73e4e8cea98e80970 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Wed, 23 Jul 2008 21:28:37 -0700 Subject: pm: add new PM_EVENT codes for runtime power transitions This patch (as1112) adds some new PM_EVENT_* codes for use by kernel subsystems. They describe runtime power-state transitions of the sort already implemented by the USB subsystem. Signed-off-by: Alan Stern Signed-off-by: Rafael J. Wysocki Acked-by: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pm.h | 37 +++++++++++++++++++++++++++++++++++-- 1 file changed, 35 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index ed98d967f9fb..4dcce54b6d76 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -245,6 +245,21 @@ struct pm_ext_ops { * RECOVER Creation of a hibernation image or restoration of the main * memory contents from a hibernation image has failed, call * ->thaw() and ->complete() for all devices. + * + * The following PM_EVENT_ messages are defined for internal use by + * kernel subsystems. They are never issued by the PM core. + * + * USER_SUSPEND Manual selective suspend was issued by userspace. + * + * USER_RESUME Manual selective resume was issued by userspace. + * + * REMOTE_WAKEUP Remote-wakeup request was received from the device. + * + * AUTO_SUSPEND Automatic (device idle) runtime suspend was + * initiated by the subsystem. + * + * AUTO_RESUME Automatic (device needed) runtime resume was + * requested by a driver. */ #define PM_EVENT_ON 0x0000 @@ -256,9 +271,18 @@ struct pm_ext_ops { #define PM_EVENT_THAW 0x0020 #define PM_EVENT_RESTORE 0x0040 #define PM_EVENT_RECOVER 0x0080 +#define PM_EVENT_USER 0x0100 +#define PM_EVENT_REMOTE 0x0200 +#define PM_EVENT_AUTO 0x0400 -#define PM_EVENT_SLEEP (PM_EVENT_SUSPEND | PM_EVENT_HIBERNATE) +#define PM_EVENT_SLEEP (PM_EVENT_SUSPEND | PM_EVENT_HIBERNATE) +#define PM_EVENT_USER_SUSPEND (PM_EVENT_USER | PM_EVENT_SUSPEND) +#define PM_EVENT_USER_RESUME (PM_EVENT_USER | PM_EVENT_RESUME) +#define PM_EVENT_REMOTE_WAKEUP (PM_EVENT_REMOTE | PM_EVENT_RESUME) +#define PM_EVENT_AUTO_SUSPEND (PM_EVENT_AUTO | PM_EVENT_SUSPEND) +#define PM_EVENT_AUTO_RESUME (PM_EVENT_AUTO | PM_EVENT_RESUME) +#define PMSG_ON ((struct pm_message){ .event = PM_EVENT_ON, }) #define PMSG_FREEZE ((struct pm_message){ .event = PM_EVENT_FREEZE, }) #define PMSG_QUIESCE ((struct pm_message){ .event = PM_EVENT_QUIESCE, }) #define PMSG_SUSPEND ((struct pm_message){ .event = PM_EVENT_SUSPEND, }) @@ -267,7 +291,16 @@ struct pm_ext_ops { #define PMSG_THAW ((struct pm_message){ .event = PM_EVENT_THAW, }) #define PMSG_RESTORE ((struct pm_message){ .event = PM_EVENT_RESTORE, }) #define PMSG_RECOVER ((struct pm_message){ .event = PM_EVENT_RECOVER, }) -#define PMSG_ON ((struct pm_message){ .event = PM_EVENT_ON, }) +#define PMSG_USER_SUSPEND ((struct pm_messge) \ + { .event = PM_EVENT_USER_SUSPEND, }) +#define PMSG_USER_RESUME ((struct pm_messge) \ + { .event = PM_EVENT_USER_RESUME, }) +#define PMSG_REMOTE_RESUME ((struct pm_messge) \ + { .event = PM_EVENT_REMOTE_RESUME, }) +#define PMSG_AUTO_SUSPEND ((struct pm_messge) \ + { .event = PM_EVENT_AUTO_SUSPEND, }) +#define PMSG_AUTO_RESUME ((struct pm_messge) \ + { .event = PM_EVENT_AUTO_RESUME, }) /** * Device power management states -- cgit v1.2.3 From c1a220e7acf8ad2c03504891f4a70cd9c32c904b Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Wed, 23 Jul 2008 21:28:39 -0700 Subject: pm: introduce new interfaces schedule_work_on() and queue_work_on() This interface allows adding a job on a specific cpu. Although a work struct on a cpu will be scheduled to other cpu if the cpu dies, there is a recursion if a work task tries to offline the cpu it's running on. we need to schedule the task to a specific cpu in this case. http://bugzilla.kernel.org/show_bug.cgi?id=10897 [oleg@tv-sign.ru: cleanups] Signed-off-by: Zhang Rui Tested-by: Rus Signed-off-by: Rafael J. Wysocki Acked-by: Pavel Machek Signed-off-by: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/workqueue.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 542526c6e8ef..14d47120682b 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -179,6 +179,8 @@ __create_workqueue_key(const char *name, int singlethread, extern void destroy_workqueue(struct workqueue_struct *wq); extern int queue_work(struct workqueue_struct *wq, struct work_struct *work); +extern int queue_work_on(int cpu, struct workqueue_struct *wq, + struct work_struct *work); extern int queue_delayed_work(struct workqueue_struct *wq, struct delayed_work *work, unsigned long delay); extern int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, @@ -188,6 +190,7 @@ extern void flush_workqueue(struct workqueue_struct *wq); extern void flush_scheduled_work(void); extern int schedule_work(struct work_struct *work); +extern int schedule_work_on(int cpu, struct work_struct *work); extern int schedule_delayed_work(struct delayed_work *work, unsigned long delay); extern int schedule_delayed_work_on(int cpu, struct delayed_work *work, unsigned long delay); -- cgit v1.2.3 From bdfe6b7c681669148dae4db27eb24ee5408ba371 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 23 Jul 2008 21:28:41 -0700 Subject: pm: acpi hibernation: utilize hardware signature ACPI defines a hardware signature. BIOS calculates the signature according to hardware configure and if hardware changes while hibernated, the signature will change. In that case, S4 resume should fail. Still, there may be systems on which this mechanism does not work correctly, so it is better to provide a workaround for them. For this reason, add a new switch to the acpi_sleep= command line argument allowing one to disable hardware signature checking. [shaohua.li@intel.com: build fix] Signed-off-by: Shaohua Li Signed-off-by: Rafael J. Wysocki Cc: Andi Kleen Cc: Len Brown Acked-by: Pavel Machek Cc: Cc: Shaohua Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/acpi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index a17177639376..702f79dad16a 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -236,6 +236,7 @@ int acpi_check_mem_region(resource_size_t start, resource_size_t n, const char *name); #ifdef CONFIG_PM_SLEEP +void __init acpi_no_s4_hw_signature(void); void __init acpi_old_suspend_ordering(void); #endif /* CONFIG_PM_SLEEP */ #else /* CONFIG_ACPI */ -- cgit v1.2.3 From f606ddf42fd4edc558eeb48bfee66d2c591571d2 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 23 Jul 2008 21:28:50 -0700 Subject: remove the v850 port Trying to compile the v850 port brings many compile errors, one of them exists since at least kernel 2.6.19. There also seems to be noone willing to bring this port back into a usable state. This patch therefore removes the v850 port. If anyone ever decides to revive the v850 port the code will still be available from older kernels, and it wouldn't be impossible for the port to reenter the kernel if it would become actively maintained again. Signed-off-by: Adrian Bunk Acked-by: Greg Ungerer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/audit.h | 1 - include/linux/module.h | 2 +- include/linux/serial_core.h | 3 --- include/linux/syscalls.h | 2 +- 4 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 8b82974bdc12..6272a395d43c 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -286,7 +286,6 @@ #define AUDIT_ARCH_SHEL64 (EM_SH|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) #define AUDIT_ARCH_SPARC (EM_SPARC) #define AUDIT_ARCH_SPARC64 (EM_SPARCV9|__AUDIT_ARCH_64BIT) -#define AUDIT_ARCH_V850 (EM_V850|__AUDIT_ARCH_LE) #define AUDIT_ARCH_X86_64 (EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) #define AUDIT_PERM_EXEC 1 diff --git a/include/linux/module.h b/include/linux/module.h index fce15ebd0e1c..68e09557c951 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -23,7 +23,7 @@ /* Not Yet Implemented */ #define MODULE_SUPPORTED_DEVICE(name) -/* v850 toolchain uses a `_' prefix for all user symbols */ +/* some toolchains uses a `_' prefix for all user symbols */ #ifndef MODULE_SYMBOL_PREFIX #define MODULE_SYMBOL_PREFIX "" #endif diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index f3a1c0e45021..3b2f6c04855e 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -59,9 +59,6 @@ #define PORT_SUNZILOG 38 #define PORT_SUNSAB 39 -/* NEC v850. */ -#define PORT_V850E_UART 40 - /* DEC */ #define PORT_DZ 46 #define PORT_ZS 47 diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 0522f368f9d7..4394dadff813 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -443,7 +443,7 @@ asmlinkage long sys_newuname(struct new_utsname __user *name); asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim); -#if defined(COMPAT_RLIM_OLD_INFINITY) || !(defined(CONFIG_IA64) || defined(CONFIG_V850)) +#if defined(COMPAT_RLIM_OLD_INFINITY) || !(defined(CONFIG_IA64)) asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *rlim); #endif asmlinkage long sys_setrlimit(unsigned int resource, -- cgit v1.2.3 From a677a039be7243357d93502bff2b40850c942e2d Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:17 -0700 Subject: flag parameters: socket and socketpair This patch adds support for flag values which are ORed to the type passwd to socket and socketpair. The additional code is minimal. The flag values in this implementation can and must match the O_* flags. This avoids overhead in the conversion. The internal functions sock_alloc_fd and sock_map_fd get a new parameters and all callers are changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #define PORT 57392 /* For Linux these must be the same. */ #define SOCK_CLOEXEC O_CLOEXEC int main (void) { int fd; fd = socket (PF_INET, SOCK_STREAM, 0); if (fd == -1) { puts ("socket(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("socket(0) set close-on-exec flag"); return 1; } close (fd); fd = socket (PF_INET, SOCK_STREAM|SOCK_CLOEXEC, 0); if (fd == -1) { puts ("socket(SOCK_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("socket(SOCK_CLOEXEC) does not set close-on-exec flag"); return 1; } close (fd); int fds[2]; if (socketpair (PF_UNIX, SOCK_STREAM, 0, fds) == -1) { puts ("socketpair(0) failed"); return 1; } for (int i = 0; i < 2; ++i) { coe = fcntl (fds[i], F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { printf ("socketpair(0) set close-on-exec flag for fds[%d]\n", i); return 1; } close (fds[i]); } if (socketpair (PF_UNIX, SOCK_STREAM|SOCK_CLOEXEC, 0, fds) == -1) { puts ("socketpair(SOCK_CLOEXEC) failed"); return 1; } for (int i = 0; i < 2; ++i) { coe = fcntl (fds[i], F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { printf ("socketpair(SOCK_CLOEXEC) does not set close-on-exec flag for fds[%d]\n", i); return 1; } close (fds[i]); } puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: "David S. Miller" Cc: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/net.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 150a48c68d52..8b5383c45b45 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -20,6 +20,7 @@ #include #include +#include /* For O_CLOEXEC */ #include struct poll_table_struct; @@ -94,6 +95,12 @@ enum sock_type { }; #define SOCK_MAX (SOCK_PACKET + 1) +/* Mask which covers at least up to SOCK_MASK-1. The + * remaining bits are used as flags. */ +#define SOCK_TYPE_MASK 0xf + +/* Flags for socket, socketpair, paccept */ +#define SOCK_CLOEXEC O_CLOEXEC #endif /* ARCH_HAS_SOCKET_TYPES */ @@ -208,7 +215,7 @@ extern int sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len); extern int sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags); -extern int sock_map_fd(struct socket *sock); +extern int sock_map_fd(struct socket *sock, int flags); extern struct socket *sockfd_lookup(int fd, int *err); #define sockfd_put(sock) fput(sock->file) extern int net_ratelimit(void); -- cgit v1.2.3 From aaca0bdca573f3f51ea03139f9c7289541e7bca3 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:20 -0700 Subject: flag parameters: paccept This patch is by far the most complex in the series. It adds a new syscall paccept. This syscall differs from accept in that it adds (at the userlevel) two additional parameters: - a signal mask - a flags value The flags parameter can be used to set flag like SOCK_CLOEXEC. This is imlpemented here as well. Some people argued that this is a property which should be inherited from the file desriptor for the server but this is against POSIX. Additionally, we really want the signal mask parameter as well (similar to pselect, ppoll, etc). So an interface change in inevitable. The flag value is the same as for socket and socketpair. I think diverging here will only create confusion. Similar to the filesystem interfaces where the use of the O_* constants differs, it is acceptable here. The signal mask is handled as for pselect etc. The mask is temporarily installed for the thread and removed before the call returns. I modeled the code after pselect. If there is a problem it's likely also in pselect. For architectures which use socketcall I maintained this interface instead of adding a system call. The symmetry shouldn't be broken. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #include #include #include #include #ifndef __NR_paccept # ifdef __x86_64__ # define __NR_paccept 288 # elif defined __i386__ # define SYS_PACCEPT 18 # define USE_SOCKETCALL 1 # else # error "need __NR_paccept" # endif #endif #ifdef USE_SOCKETCALL # define paccept(fd, addr, addrlen, mask, flags) \ ({ long args[6] = { \ (long) fd, (long) addr, (long) addrlen, (long) mask, 8, (long) flags }; \ syscall (__NR_socketcall, SYS_PACCEPT, args); }) #else # define paccept(fd, addr, addrlen, mask, flags) \ syscall (__NR_paccept, fd, addr, addrlen, mask, 8, flags) #endif #define PORT 57392 #define SOCK_CLOEXEC O_CLOEXEC static pthread_barrier_t b; static void * tf (void *arg) { pthread_barrier_wait (&b); int s = socket (AF_INET, SOCK_STREAM, 0); struct sockaddr_in sin; sin.sin_family = AF_INET; sin.sin_addr.s_addr = htonl (INADDR_LOOPBACK); sin.sin_port = htons (PORT); connect (s, (const struct sockaddr *) &sin, sizeof (sin)); close (s); pthread_barrier_wait (&b); s = socket (AF_INET, SOCK_STREAM, 0); sin.sin_port = htons (PORT); connect (s, (const struct sockaddr *) &sin, sizeof (sin)); close (s); pthread_barrier_wait (&b); pthread_barrier_wait (&b); sleep (2); pthread_kill ((pthread_t) arg, SIGUSR1); return NULL; } static void handler (int s) { } int main (void) { pthread_barrier_init (&b, NULL, 2); struct sockaddr_in sin; pthread_t th; if (pthread_create (&th, NULL, tf, (void *) pthread_self ()) != 0) { puts ("pthread_create failed"); return 1; } int s = socket (AF_INET, SOCK_STREAM, 0); int reuse = 1; setsockopt (s, SOL_SOCKET, SO_REUSEADDR, &reuse, sizeof (reuse)); sin.sin_family = AF_INET; sin.sin_addr.s_addr = htonl (INADDR_LOOPBACK); sin.sin_port = htons (PORT); bind (s, (struct sockaddr *) &sin, sizeof (sin)); listen (s, SOMAXCONN); pthread_barrier_wait (&b); int s2 = paccept (s, NULL, 0, NULL, 0); if (s2 < 0) { puts ("paccept(0) failed"); return 1; } int coe = fcntl (s2, F_GETFD); if (coe & FD_CLOEXEC) { puts ("paccept(0) set close-on-exec-flag"); return 1; } close (s2); pthread_barrier_wait (&b); s2 = paccept (s, NULL, 0, NULL, SOCK_CLOEXEC); if (s2 < 0) { puts ("paccept(SOCK_CLOEXEC) failed"); return 1; } coe = fcntl (s2, F_GETFD); if ((coe & FD_CLOEXEC) == 0) { puts ("paccept(SOCK_CLOEXEC) does not set close-on-exec flag"); return 1; } close (s2); pthread_barrier_wait (&b); struct sigaction sa; sa.sa_handler = handler; sa.sa_flags = 0; sigemptyset (&sa.sa_mask); sigaction (SIGUSR1, &sa, NULL); sigset_t ss; pthread_sigmask (SIG_SETMASK, NULL, &ss); sigaddset (&ss, SIGUSR1); pthread_sigmask (SIG_SETMASK, &ss, NULL); sigdelset (&ss, SIGUSR1); alarm (4); pthread_barrier_wait (&b); errno = 0 ; s2 = paccept (s, NULL, 0, &ss, 0); if (s2 != -1 || errno != EINTR) { puts ("paccept did not fail with EINTR"); return 1; } close (s); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: make it compile] [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Cc: "David S. Miller" Cc: Roland McGrath Cc: Kyle McMartin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/net.h | 3 +++ include/linux/syscalls.h | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 8b5383c45b45..3a9b06d4d0fe 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -47,6 +47,7 @@ struct net; #define SYS_GETSOCKOPT 15 /* sys_getsockopt(2) */ #define SYS_SENDMSG 16 /* sys_sendmsg(2) */ #define SYS_RECVMSG 17 /* sys_recvmsg(2) */ +#define SYS_PACCEPT 18 /* sys_paccept(2) */ typedef enum { SS_FREE = 0, /* not allocated */ @@ -219,6 +220,8 @@ extern int sock_map_fd(struct socket *sock, int flags); extern struct socket *sockfd_lookup(int fd, int *err); #define sockfd_put(sock) fput(sock->file) extern int net_ratelimit(void); +extern long do_accept(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags); #define net_random() random32() #define net_srandom(seed) srandom32((__force u32)seed) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 4394dadff813..2a2a40af6b2c 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -409,6 +409,8 @@ asmlinkage long sys_getsockopt(int fd, int level, int optname, asmlinkage long sys_bind(int, struct sockaddr __user *, int); asmlinkage long sys_connect(int, struct sockaddr __user *, int); asmlinkage long sys_accept(int, struct sockaddr __user *, int __user *); +asmlinkage long sys_paccept(int, struct sockaddr __user *, int __user *, + const sigset_t *, size_t, int); asmlinkage long sys_getsockname(int, struct sockaddr __user *, int __user *); asmlinkage long sys_getpeername(int, struct sockaddr __user *, int __user *); asmlinkage long sys_send(int, void __user *, size_t, unsigned); -- cgit v1.2.3 From c019bbc612f6633ede7ed67725cbf68de45ae8a4 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:21 -0700 Subject: flag parameters: paccept w/out set_restore_sigmask Some platforms do not have support to restore the signal mask in the return path from a syscall. For those platforms syscalls like pselect are not defined at all. This is, I think, not a good choice for paccept() since paccept() adds more value on top of accept() than just the signal mask handling. Therefore this patch defines a scaled down version of the sys_paccept function for those platforms. It returns -EINVAL in case the signal mask is non-NULL but behaves the same otherwise. Note that I explicitly included . I saw that it is currently included but indirectly two levels down. There is too much risk in relying on this. The header might change and then suddenly the function definition would change without anyone immediately noticing. Signed-off-by: Ulrich Drepper Cc: Davide Libenzi Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/net.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 3a9b06d4d0fe..39a23af059b4 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -102,6 +102,9 @@ enum sock_type { /* Flags for socket, socketpair, paccept */ #define SOCK_CLOEXEC O_CLOEXEC +#ifndef SOCK_NONBLOCK +#define SOCK_NONBLOCK O_NONBLOCK +#endif #endif /* ARCH_HAS_SOCKET_TYPES */ -- cgit v1.2.3 From 7d9dbca34240ebb6ff88d8a29c6c7bffd098f0c1 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:22 -0700 Subject: flag parameters: anon_inode_getfd extension This patch just extends the anon_inode_getfd interface to take an additional parameter with a flag value. The flag value is passed on to get_unused_fd_flags in anticipation for a use with the O_CLOEXEC flag. No actual semantic changes here, the changed callers all pass 0 for now. [akpm@linux-foundation.org: KVM fix] Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/anon_inodes.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h index 6129e58ca7c9..e0a0cdc2da43 100644 --- a/include/linux/anon_inodes.h +++ b/include/linux/anon_inodes.h @@ -9,7 +9,7 @@ #define _LINUX_ANON_INODES_H int anon_inode_getfd(const char *name, const struct file_operations *fops, - void *priv); + void *priv, int flags); #endif /* _LINUX_ANON_INODES_H */ -- cgit v1.2.3 From 9deb27baedb79759c3ab9435a7d8b841842d56e9 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:24 -0700 Subject: flag parameters: signalfd This patch adds the new signalfd4 syscall. It extends the old signalfd syscall by one parameter which is meant to hold a flag value. In this patch the only flag support is SFD_CLOEXEC which causes the close-on-exec flag for the returned file descriptor to be set. A new name SFD_CLOEXEC is introduced which in this implementation must have the same value as O_CLOEXEC. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #ifndef __NR_signalfd4 # ifdef __x86_64__ # define __NR_signalfd4 289 # elif defined __i386__ # define __NR_signalfd4 327 # else # error "need __NR_signalfd4" # endif #endif #define SFD_CLOEXEC O_CLOEXEC int main (void) { sigset_t ss; sigemptyset (&ss); sigaddset (&ss, SIGUSR1); int fd = syscall (__NR_signalfd4, -1, &ss, 8, 0); if (fd == -1) { puts ("signalfd4(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("signalfd4(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_signalfd4, -1, &ss, 8, SFD_CLOEXEC); if (fd == -1) { puts ("signalfd4(SFD_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("signalfd4(SFD_CLOEXEC) does not set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/signalfd.h | 5 +++++ include/linux/syscalls.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/signalfd.h b/include/linux/signalfd.h index ea037f28df91..8b3f7b7420a1 100644 --- a/include/linux/signalfd.h +++ b/include/linux/signalfd.h @@ -8,6 +8,11 @@ #ifndef _LINUX_SIGNALFD_H #define _LINUX_SIGNALFD_H +/* For O_CLOEXEC */ +#include + +/* Flags for signalfd4. */ +#define SFD_CLOEXEC O_CLOEXEC struct signalfd_siginfo { __u32 ssi_signo; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 2a2a40af6b2c..1c2707797845 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -610,6 +610,7 @@ asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, size_t len); asmlinkage long sys_getcpu(unsigned __user *cpu, unsigned __user *node, struct getcpu_cache __user *cache); asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask); +asmlinkage long sys_signalfd4(int ufd, sigset_t __user *user_mask, size_t sizemask, int flags); asmlinkage long sys_timerfd_create(int clockid, int flags); asmlinkage long sys_timerfd_settime(int ufd, int flags, const struct itimerspec __user *utmr, -- cgit v1.2.3 From b087498eb5605673b0f260a7620d91818cd72304 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:25 -0700 Subject: flag parameters: eventfd This patch adds the new eventfd2 syscall. It extends the old eventfd syscall by one parameter which is meant to hold a flag value. In this patch the only flag support is EFD_CLOEXEC which causes the close-on-exec flag for the returned file descriptor to be set. A new name EFD_CLOEXEC is introduced which in this implementation must have the same value as O_CLOEXEC. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #ifndef __NR_eventfd2 # ifdef __x86_64__ # define __NR_eventfd2 290 # elif defined __i386__ # define __NR_eventfd2 328 # else # error "need __NR_eventfd2" # endif #endif #define EFD_CLOEXEC O_CLOEXEC int main (void) { int fd = syscall (__NR_eventfd2, 1, 0); if (fd == -1) { puts ("eventfd2(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("eventfd2(0) sets close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_eventfd2, 1, EFD_CLOEXEC); if (fd == -1) { puts ("eventfd2(EFD_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("eventfd2(EFD_CLOEXEC) does not set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/eventfd.h | 6 ++++++ include/linux/syscalls.h | 1 + 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index a701399b7fed..a6c0eaedb1b0 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -10,6 +10,12 @@ #ifdef CONFIG_EVENTFD +/* For O_CLOEXEC */ +#include + +/* Flags for eventfd2. */ +#define EFD_CLOEXEC O_CLOEXEC + struct file *eventfd_fget(int fd); int eventfd_signal(struct file *file, int n); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 1c2707797845..9ab09926a7f2 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -617,6 +617,7 @@ asmlinkage long sys_timerfd_settime(int ufd, int flags, struct itimerspec __user *otmr); asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr); asmlinkage long sys_eventfd(unsigned int count); +asmlinkage long sys_eventfd2(unsigned int count, int flags); asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len); int kernel_execve(const char *filename, char *const argv[], char *const envp[]); -- cgit v1.2.3 From 11fcb6c14676023d0bd437841f5dcd670e7990a0 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:26 -0700 Subject: flag parameters: timerfd_create The timerfd_create syscall already has a flags parameter. It just is unused so far. This patch changes this by introducing the TFD_CLOEXEC flag to set the close-on-exec flag for the returned file descriptor. A new name TFD_CLOEXEC is introduced which in this implementation must have the same value as O_CLOEXEC. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #ifndef __NR_timerfd_create # ifdef __x86_64__ # define __NR_timerfd_create 283 # elif defined __i386__ # define __NR_timerfd_create 322 # else # error "need __NR_timerfd_create" # endif #endif #define TFD_CLOEXEC O_CLOEXEC int main (void) { int fd = syscall (__NR_timerfd_create, CLOCK_REALTIME, 0); if (fd == -1) { puts ("timerfd_create(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("timerfd_create(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_timerfd_create, CLOCK_REALTIME, TFD_CLOEXEC); if (fd == -1) { puts ("timerfd_create(TFD_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("timerfd_create(TFD_CLOEXEC) set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/timerfd.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timerfd.h b/include/linux/timerfd.h index cf2b10d75731..96ed97dff00f 100644 --- a/include/linux/timerfd.h +++ b/include/linux/timerfd.h @@ -8,9 +8,14 @@ #ifndef _LINUX_TIMERFD_H #define _LINUX_TIMERFD_H +/* For O_CLOEXEC */ +#include +/* Flags for timerfd_settime. */ #define TFD_TIMER_ABSTIME (1 << 0) +/* Flags for timerfd_create. */ +#define TFD_CLOEXEC O_CLOEXEC #endif /* _LINUX_TIMERFD_H */ -- cgit v1.2.3 From a0998b50c3f0b8fdd265c63e0032f86ebe377dbf Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:27 -0700 Subject: flag parameters: epoll_create This patch adds the new epoll_create2 syscall. It extends the old epoll_create syscall by one parameter which is meant to hold a flag value. In this patch the only flag support is EPOLL_CLOEXEC which causes the close-on-exec flag for the returned file descriptor to be set. A new name EPOLL_CLOEXEC is introduced which in this implementation must have the same value as O_CLOEXEC. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #ifndef __NR_epoll_create2 # ifdef __x86_64__ # define __NR_epoll_create2 291 # elif defined __i386__ # define __NR_epoll_create2 329 # else # error "need __NR_epoll_create2" # endif #endif #define EPOLL_CLOEXEC O_CLOEXEC int main (void) { int fd = syscall (__NR_epoll_create2, 1, 0); if (fd == -1) { puts ("epoll_create2(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("epoll_create2(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_epoll_create2, 1, EPOLL_CLOEXEC); if (fd == -1) { puts ("epoll_create2(EPOLL_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("epoll_create2(EPOLL_CLOEXEC) set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/eventpoll.h | 4 ++++ include/linux/syscalls.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index cf79853967ff..1cfaa40059c8 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -14,8 +14,12 @@ #ifndef _LINUX_EVENTPOLL_H #define _LINUX_EVENTPOLL_H +/* For O_CLOEXEC */ +#include #include +/* Flags for epoll_create2. */ +#define EPOLL_CLOEXEC O_CLOEXEC /* Valid opcodes to issue to sys_epoll_ctl() */ #define EPOLL_CTL_ADD 1 diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 9ab09926a7f2..85953240f28c 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -430,6 +430,7 @@ asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp); asmlinkage long sys_epoll_create(int size); +asmlinkage long sys_epoll_create2(int size, int flags); asmlinkage long sys_epoll_ctl(int epfd, int op, int fd, struct epoll_event __user *event); asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events, -- cgit v1.2.3 From 336dd1f70ff62d7dd8655228caed4c5bfc818c56 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:29 -0700 Subject: flag parameters: dup2 This patch adds the new dup3 syscall. It extends the old dup2 syscall by one parameter which is meant to hold a flag value. Support for the O_CLOEXEC flag is added in this patch. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #ifndef __NR_dup3 # ifdef __x86_64__ # define __NR_dup3 292 # elif defined __i386__ # define __NR_dup3 330 # else # error "need __NR_dup3" # endif #endif int main (void) { int fd = syscall (__NR_dup3, 1, 4, 0); if (fd == -1) { puts ("dup3(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("dup3(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_dup3, 1, 4, O_CLOEXEC); if (fd == -1) { puts ("dup3(O_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("dup3(O_CLOEXEC) set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: 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 85953240f28c..034d3358549e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -305,6 +305,7 @@ asmlinkage long sys_fcntl64(unsigned int fd, #endif asmlinkage long sys_dup(unsigned int fildes); asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd); +asmlinkage long sys_dup3(unsigned int oldfd, unsigned int newfd, int flags); asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int on); asmlinkage long sys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); -- cgit v1.2.3 From ed8cae8ba01348bfd83333f4648dd807b04d7f08 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:30 -0700 Subject: flag parameters: pipe This patch introduces the new syscall pipe2 which is like pipe but it also takes an additional parameter which takes a flag value. This patch implements the handling of O_CLOEXEC for the flag. I did not add support for the new syscall for the architectures which have a special sys_pipe implementation. I think the maintainers of those archs have the chance to go with the unified implementation but that's up to them. The implementation introduces do_pipe_flags. I did that instead of changing all callers of do_pipe because some of the callers are written in assembler. I would probably screw up changing the assembly code. To avoid breaking code do_pipe is now a small wrapper around do_pipe_flags. Once all callers are changed over to do_pipe_flags the old do_pipe function can be removed. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #ifndef __NR_pipe2 # ifdef __x86_64__ # define __NR_pipe2 293 # elif defined __i386__ # define __NR_pipe2 331 # else # error "need __NR_pipe2" # endif #endif int main (void) { int fd[2]; if (syscall (__NR_pipe2, fd, 0) != 0) { puts ("pipe2(0) failed"); return 1; } for (int i = 0; i < 2; ++i) { int coe = fcntl (fd[i], F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { printf ("pipe2(0) set close-on-exit for fd[%d]\n", i); return 1; } } close (fd[0]); close (fd[1]); if (syscall (__NR_pipe2, fd, O_CLOEXEC) != 0) { puts ("pipe2(O_CLOEXEC) failed"); return 1; } for (int i = 0; i < 2; ++i) { int coe = fcntl (fd[i], F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { printf ("pipe2(O_CLOEXEC) does not set close-on-exit for fd[%d]\n", i); return 1; } } close (fd[0]); close (fd[1]); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: 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 e5e6a244096c..0e80cd717d32 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1777,6 +1777,7 @@ static inline void allow_write_access(struct file *file) atomic_inc(&file->f_path.dentry->d_inode->i_writecount); } extern int do_pipe(int *); +extern int do_pipe_flags(int *, int); extern struct file *create_read_pipe(struct file *f); extern struct file *create_write_pipe(void); extern void free_write_pipe(struct file *); -- cgit v1.2.3 From 4006553b06306b34054529477b06b68a1c66249b Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:32 -0700 Subject: flag parameters: inotify_init This patch introduces the new syscall inotify_init1 (note: the 1 stands for the one parameter the syscall takes, as opposed to no parameter before). The values accepted for this parameter are function-specific and defined in the inotify.h header. Here the values must match the O_* flags, though. In this patch CLOEXEC support is introduced. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #ifndef __NR_inotify_init1 # ifdef __x86_64__ # define __NR_inotify_init1 294 # elif defined __i386__ # define __NR_inotify_init1 332 # else # error "need __NR_inotify_init1" # endif #endif #define IN_CLOEXEC O_CLOEXEC int main (void) { int fd; fd = syscall (__NR_inotify_init1, 0); if (fd == -1) { puts ("inotify_init1(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("inotify_init1(0) set close-on-exit"); return 1; } close (fd); fd = syscall (__NR_inotify_init1, IN_CLOEXEC); if (fd == -1) { puts ("inotify_init1(IN_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("inotify_init1(O_CLOEXEC) does not set close-on-exit"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/inotify.h | 5 +++++ include/linux/syscalls.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/inotify.h b/include/linux/inotify.h index 742b917e7d1b..72ef82120512 100644 --- a/include/linux/inotify.h +++ b/include/linux/inotify.h @@ -7,6 +7,8 @@ #ifndef _LINUX_INOTIFY_H #define _LINUX_INOTIFY_H +/* For O_CLOEXEC */ +#include #include /* @@ -63,6 +65,9 @@ struct inotify_event { IN_MOVED_TO | IN_DELETE | IN_CREATE | IN_DELETE_SELF | \ IN_MOVE_SELF) +/* Flags for sys_inotify_init1. */ +#define IN_CLOEXEC O_CLOEXEC + #ifdef __KERNEL__ #include diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 034d3358549e..93a7e7f017a6 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -547,6 +547,7 @@ asmlinkage long sys_get_mempolicy(int __user *policy, unsigned long addr, unsigned long flags); asmlinkage long sys_inotify_init(void); +asmlinkage long sys_inotify_init1(int flags); asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask); asmlinkage long sys_inotify_rm_watch(int fd, u32 wd); -- cgit v1.2.3 From 77d2720059618b9b6e827a8b73831eb6c6fad63c Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:35 -0700 Subject: flag parameters: NONBLOCK in socket and socketpair This patch introduces support for the SOCK_NONBLOCK flag in socket, socketpair, and paccept. To do this the internal function sock_attach_fd gets an additional parameter which it uses to set the appropriate flag for the file descriptor. Given that in modern, scalable programs almost all socket connections are non-blocking and the minimal additional cost for the new functionality I see no reason not to add this code. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #include #include #ifndef __NR_paccept # ifdef __x86_64__ # define __NR_paccept 288 # elif defined __i386__ # define SYS_PACCEPT 18 # define USE_SOCKETCALL 1 # else # error "need __NR_paccept" # endif #endif #ifdef USE_SOCKETCALL # define paccept(fd, addr, addrlen, mask, flags) \ ({ long args[6] = { \ (long) fd, (long) addr, (long) addrlen, (long) mask, 8, (long) flags }; \ syscall (__NR_socketcall, SYS_PACCEPT, args); }) #else # define paccept(fd, addr, addrlen, mask, flags) \ syscall (__NR_paccept, fd, addr, addrlen, mask, 8, flags) #endif #define PORT 57392 #define SOCK_NONBLOCK O_NONBLOCK static pthread_barrier_t b; static void * tf (void *arg) { pthread_barrier_wait (&b); int s = socket (AF_INET, SOCK_STREAM, 0); struct sockaddr_in sin; sin.sin_family = AF_INET; sin.sin_addr.s_addr = htonl (INADDR_LOOPBACK); sin.sin_port = htons (PORT); connect (s, (const struct sockaddr *) &sin, sizeof (sin)); close (s); pthread_barrier_wait (&b); pthread_barrier_wait (&b); s = socket (AF_INET, SOCK_STREAM, 0); sin.sin_port = htons (PORT); connect (s, (const struct sockaddr *) &sin, sizeof (sin)); close (s); pthread_barrier_wait (&b); return NULL; } int main (void) { int fd; fd = socket (PF_INET, SOCK_STREAM, 0); if (fd == -1) { puts ("socket(0) failed"); return 1; } int fl = fcntl (fd, F_GETFL); if (fl == -1) { puts ("fcntl failed"); return 1; } if (fl & O_NONBLOCK) { puts ("socket(0) set non-blocking mode"); return 1; } close (fd); fd = socket (PF_INET, SOCK_STREAM|SOCK_NONBLOCK, 0); if (fd == -1) { puts ("socket(SOCK_NONBLOCK) failed"); return 1; } fl = fcntl (fd, F_GETFL); if (fl == -1) { puts ("fcntl failed"); return 1; } if ((fl & O_NONBLOCK) == 0) { puts ("socket(SOCK_NONBLOCK) does not set non-blocking mode"); return 1; } close (fd); int fds[2]; if (socketpair (PF_UNIX, SOCK_STREAM, 0, fds) == -1) { puts ("socketpair(0) failed"); return 1; } for (int i = 0; i < 2; ++i) { fl = fcntl (fds[i], F_GETFL); if (fl == -1) { puts ("fcntl failed"); return 1; } if (fl & O_NONBLOCK) { printf ("socketpair(0) set non-blocking mode for fds[%d]\n", i); return 1; } close (fds[i]); } if (socketpair (PF_UNIX, SOCK_STREAM|SOCK_NONBLOCK, 0, fds) == -1) { puts ("socketpair(SOCK_NONBLOCK) failed"); return 1; } for (int i = 0; i < 2; ++i) { fl = fcntl (fds[i], F_GETFL); if (fl == -1) { puts ("fcntl failed"); return 1; } if ((fl & O_NONBLOCK) == 0) { printf ("socketpair(SOCK_NONBLOCK) does not set non-blocking mode for fds[%d]\n", i); return 1; } close (fds[i]); } pthread_barrier_init (&b, NULL, 2); struct sockaddr_in sin; pthread_t th; if (pthread_create (&th, NULL, tf, NULL) != 0) { puts ("pthread_create failed"); return 1; } int s = socket (AF_INET, SOCK_STREAM, 0); int reuse = 1; setsockopt (s, SOL_SOCKET, SO_REUSEADDR, &reuse, sizeof (reuse)); sin.sin_family = AF_INET; sin.sin_addr.s_addr = htonl (INADDR_LOOPBACK); sin.sin_port = htons (PORT); bind (s, (struct sockaddr *) &sin, sizeof (sin)); listen (s, SOMAXCONN); pthread_barrier_wait (&b); int s2 = paccept (s, NULL, 0, NULL, 0); if (s2 < 0) { puts ("paccept(0) failed"); return 1; } fl = fcntl (s2, F_GETFL); if (fl & O_NONBLOCK) { puts ("paccept(0) set non-blocking mode"); return 1; } close (s2); close (s); pthread_barrier_wait (&b); s = socket (AF_INET, SOCK_STREAM, 0); sin.sin_port = htons (PORT); setsockopt (s, SOL_SOCKET, SO_REUSEADDR, &reuse, sizeof (reuse)); bind (s, (struct sockaddr *) &sin, sizeof (sin)); listen (s, SOMAXCONN); pthread_barrier_wait (&b); s2 = paccept (s, NULL, 0, NULL, SOCK_NONBLOCK); if (s2 < 0) { puts ("paccept(SOCK_NONBLOCK) failed"); return 1; } fl = fcntl (s2, F_GETFL); if ((fl & O_NONBLOCK) == 0) { puts ("paccept(SOCK_NONBLOCK) does not set non-blocking mode"); return 1; } close (s2); close (s); pthread_barrier_wait (&b); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/net.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 39a23af059b4..2f999fbb188d 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -20,7 +20,7 @@ #include #include -#include /* For O_CLOEXEC */ +#include /* For O_CLOEXEC and O_NONBLOCK */ #include struct poll_table_struct; -- cgit v1.2.3 From 5fb5e04926a54bc1c22bba7ca166840f4476196f Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:37 -0700 Subject: flag parameters: NONBLOCK in signalfd This patch adds support for the SFD_NONBLOCK flag to signalfd4. The additional changes needed are minimal. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #ifndef __NR_signalfd4 # ifdef __x86_64__ # define __NR_signalfd4 289 # elif defined __i386__ # define __NR_signalfd4 327 # else # error "need __NR_signalfd4" # endif #endif #define SFD_NONBLOCK O_NONBLOCK int main (void) { sigset_t ss; sigemptyset (&ss); sigaddset (&ss, SIGUSR1); int fd = syscall (__NR_signalfd4, -1, &ss, 8, 0); if (fd == -1) { puts ("signalfd4(0) failed"); return 1; } int fl = fcntl (fd, F_GETFL); if (fl == -1) { puts ("fcntl failed"); return 1; } if (fl & O_NONBLOCK) { puts ("signalfd4(0) set non-blocking mode"); return 1; } close (fd); fd = syscall (__NR_signalfd4, -1, &ss, 8, SFD_NONBLOCK); if (fd == -1) { puts ("signalfd4(SFD_NONBLOCK) failed"); return 1; } fl = fcntl (fd, F_GETFL); if (fl == -1) { puts ("fcntl failed"); return 1; } if ((fl & O_NONBLOCK) == 0) { puts ("signalfd4(SFD_NONBLOCK) does not set non-blocking mode"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/signalfd.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/signalfd.h b/include/linux/signalfd.h index 8b3f7b7420a1..bef0c46d4713 100644 --- a/include/linux/signalfd.h +++ b/include/linux/signalfd.h @@ -8,11 +8,12 @@ #ifndef _LINUX_SIGNALFD_H #define _LINUX_SIGNALFD_H -/* For O_CLOEXEC */ +/* For O_CLOEXEC and O_NONBLOCK */ #include /* Flags for signalfd4. */ #define SFD_CLOEXEC O_CLOEXEC +#define SFD_NONBLOCK O_NONBLOCK struct signalfd_siginfo { __u32 ssi_signo; -- cgit v1.2.3 From e7d476dfdf0bcfed478a207aecfdc84f81efecaf Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:38 -0700 Subject: flag parameters: NONBLOCK in eventfd This patch adds support for the EFD_NONBLOCK flag to eventfd2. The additional changes needed are minimal. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #ifndef __NR_eventfd2 # ifdef __x86_64__ # define __NR_eventfd2 290 # elif defined __i386__ # define __NR_eventfd2 328 # else # error "need __NR_eventfd2" # endif #endif #define EFD_NONBLOCK O_NONBLOCK int main (void) { int fd = syscall (__NR_eventfd2, 1, 0); if (fd == -1) { puts ("eventfd2(0) failed"); return 1; } int fl = fcntl (fd, F_GETFL); if (fl == -1) { puts ("fcntl failed"); return 1; } if (fl & O_NONBLOCK) { puts ("eventfd2(0) sets non-blocking mode"); return 1; } close (fd); fd = syscall (__NR_eventfd2, 1, EFD_NONBLOCK); if (fd == -1) { puts ("eventfd2(EFD_NONBLOCK) failed"); return 1; } fl = fcntl (fd, F_GETFL); if (fl == -1) { puts ("fcntl failed"); return 1; } if ((fl & O_NONBLOCK) == 0) { puts ("eventfd2(EFD_NONBLOCK) does not set non-blocking mode"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/eventfd.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index a6c0eaedb1b0..a667637b54e3 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -10,11 +10,12 @@ #ifdef CONFIG_EVENTFD -/* For O_CLOEXEC */ +/* For O_CLOEXEC and O_NONBLOCK */ #include /* Flags for eventfd2. */ #define EFD_CLOEXEC O_CLOEXEC +#define EFD_NONBLOCK O_NONBLOCK struct file *eventfd_fget(int fd); int eventfd_signal(struct file *file, int n); -- cgit v1.2.3 From 6b1ef0e60d42f2fdaec26baee8327eb156347b4f Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:39 -0700 Subject: flag parameters: NONBLOCK in timerfd_create This patch adds support for the TFD_NONBLOCK flag to timerfd_create. The additional changes needed are minimal. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #ifndef __NR_timerfd_create # ifdef __x86_64__ # define __NR_timerfd_create 283 # elif defined __i386__ # define __NR_timerfd_create 322 # else # error "need __NR_timerfd_create" # endif #endif #define TFD_NONBLOCK O_NONBLOCK int main (void) { int fd = syscall (__NR_timerfd_create, CLOCK_REALTIME, 0); if (fd == -1) { puts ("timerfd_create(0) failed"); return 1; } int fl = fcntl (fd, F_GETFL); if (fl == -1) { puts ("fcntl failed"); return 1; } if (fl & O_NONBLOCK) { puts ("timerfd_create(0) set non-blocking mode"); return 1; } close (fd); fd = syscall (__NR_timerfd_create, CLOCK_REALTIME, TFD_NONBLOCK); if (fd == -1) { puts ("timerfd_create(TFD_NONBLOCK) failed"); return 1; } fl = fcntl (fd, F_GETFL); if (fl == -1) { puts ("fcntl failed"); return 1; } if ((fl & O_NONBLOCK) == 0) { puts ("timerfd_create(TFD_NONBLOCK) set non-blocking mode"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/timerfd.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/timerfd.h b/include/linux/timerfd.h index 96ed97dff00f..86cb0501d3e2 100644 --- a/include/linux/timerfd.h +++ b/include/linux/timerfd.h @@ -8,7 +8,7 @@ #ifndef _LINUX_TIMERFD_H #define _LINUX_TIMERFD_H -/* For O_CLOEXEC */ +/* For O_CLOEXEC and O_NONBLOCK */ #include /* Flags for timerfd_settime. */ @@ -16,6 +16,7 @@ /* Flags for timerfd_create. */ #define TFD_CLOEXEC O_CLOEXEC +#define TFD_NONBLOCK O_NONBLOCK #endif /* _LINUX_TIMERFD_H */ -- cgit v1.2.3 From be61a86d7237dd80510615f38ae21d6e1e98660c Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:40 -0700 Subject: flag parameters: NONBLOCK in pipe This patch adds O_NONBLOCK support to pipe2. It is minimally more involved than the patches for eventfd et.al but still trivial. The interfaces of the create_write_pipe and create_read_pipe helper functions were changed and the one other caller as well. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #ifndef __NR_pipe2 # ifdef __x86_64__ # define __NR_pipe2 293 # elif defined __i386__ # define __NR_pipe2 331 # else # error "need __NR_pipe2" # endif #endif int main (void) { int fds[2]; if (syscall (__NR_pipe2, fds, 0) == -1) { puts ("pipe2(0) failed"); return 1; } for (int i = 0; i < 2; ++i) { int fl = fcntl (fds[i], F_GETFL); if (fl == -1) { puts ("fcntl failed"); return 1; } if (fl & O_NONBLOCK) { printf ("pipe2(0) set non-blocking mode for fds[%d]\n", i); return 1; } close (fds[i]); } if (syscall (__NR_pipe2, fds, O_NONBLOCK) == -1) { puts ("pipe2(O_NONBLOCK) failed"); return 1; } for (int i = 0; i < 2; ++i) { int fl = fcntl (fds[i], F_GETFL); if (fl == -1) { puts ("fcntl failed"); return 1; } if ((fl & O_NONBLOCK) == 0) { printf ("pipe2(O_NONBLOCK) does not set non-blocking mode for fds[%d]\n", i); return 1; } close (fds[i]); } puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk 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 0e80cd717d32..4b86f806014c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1778,8 +1778,8 @@ static inline void allow_write_access(struct file *file) } extern int do_pipe(int *); extern int do_pipe_flags(int *, int); -extern struct file *create_read_pipe(struct file *f); -extern struct file *create_write_pipe(void); +extern struct file *create_read_pipe(struct file *f, int flags); +extern struct file *create_write_pipe(int flags); extern void free_write_pipe(struct file *); extern struct file *do_filp_open(int dfd, const char *pathname, -- cgit v1.2.3 From 510df2dd482496083e1c3b1a8c9b6afd5fa4c7d7 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:41 -0700 Subject: flag parameters: NONBLOCK in inotify_init This patch adds non-blocking support for inotify_init1. The additional changes needed are minimal. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #ifndef __NR_inotify_init1 # ifdef __x86_64__ # define __NR_inotify_init1 294 # elif defined __i386__ # define __NR_inotify_init1 332 # else # error "need __NR_inotify_init1" # endif #endif #define IN_NONBLOCK O_NONBLOCK int main (void) { int fd = syscall (__NR_inotify_init1, 0); if (fd == -1) { puts ("inotify_init1(0) failed"); return 1; } int fl = fcntl (fd, F_GETFL); if (fl == -1) { puts ("fcntl failed"); return 1; } if (fl & O_NONBLOCK) { puts ("inotify_init1(0) set non-blocking mode"); return 1; } close (fd); fd = syscall (__NR_inotify_init1, IN_NONBLOCK); if (fd == -1) { puts ("inotify_init1(IN_NONBLOCK) failed"); return 1; } fl = fcntl (fd, F_GETFL); if (fl == -1) { puts ("fcntl failed"); return 1; } if ((fl & O_NONBLOCK) == 0) { puts ("inotify_init1(IN_NONBLOCK) set non-blocking mode"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/inotify.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/inotify.h b/include/linux/inotify.h index 72ef82120512..bd578578a8b9 100644 --- a/include/linux/inotify.h +++ b/include/linux/inotify.h @@ -7,7 +7,7 @@ #ifndef _LINUX_INOTIFY_H #define _LINUX_INOTIFY_H -/* For O_CLOEXEC */ +/* For O_CLOEXEC and O_NONBLOCK */ #include #include @@ -67,6 +67,7 @@ struct inotify_event { /* Flags for sys_inotify_init1. */ #define IN_CLOEXEC O_CLOEXEC +#define IN_NONBLOCK O_NONBLOCK #ifdef __KERNEL__ -- cgit v1.2.3 From 9fe5ad9c8cef9ad5873d8ee55d1cf00d9b607df0 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:43 -0700 Subject: flag parameters add-on: remove epoll_create size param Remove the size parameter from the new epoll_create syscall and renames the syscall itself. The updated test program follows. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #ifndef __NR_epoll_create2 # ifdef __x86_64__ # define __NR_epoll_create2 291 # elif defined __i386__ # define __NR_epoll_create2 329 # else # error "need __NR_epoll_create2" # endif #endif #define EPOLL_CLOEXEC O_CLOEXEC int main (void) { int fd = syscall (__NR_epoll_create2, 0); if (fd == -1) { puts ("epoll_create2(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("epoll_create2(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_epoll_create2, EPOLL_CLOEXEC); if (fd == -1) { puts ("epoll_create2(EPOLL_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("epoll_create2(EPOLL_CLOEXEC) set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/eventpoll.h | 2 +- include/linux/syscalls.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 1cfaa40059c8..f1e1d3c47125 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -18,7 +18,7 @@ #include #include -/* Flags for epoll_create2. */ +/* Flags for epoll_create1. */ #define EPOLL_CLOEXEC O_CLOEXEC /* Valid opcodes to issue to sys_epoll_ctl() */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 93a7e7f017a6..06f2bf76c030 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -431,7 +431,7 @@ asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp); asmlinkage long sys_epoll_create(int size); -asmlinkage long sys_epoll_create2(int size, int flags); +asmlinkage long sys_epoll_create1(int flags); asmlinkage long sys_epoll_ctl(int epfd, int op, int fd, struct epoll_event __user *event); asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events, -- cgit v1.2.3 From 102eb97564c73ea73645b38599c5cbe6f54b030c Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Wed, 23 Jul 2008 21:29:55 -0700 Subject: spi: make spi_board_info.modalias a char array Currently, 'modalias' in the spi_device structure is a 'const char *'. The spi_new_device() function fills in the modalias value from a passed in spi_board_info data block. Since it is a pointer copy, the new spi_device remains dependent on the spi_board_info structure after the new spi_device is registered (no other fields in spi_device directly depend on the spi_board_info structure; all of the other data is copied). This causes a problem when dynamically propulating the list of attached SPI devices. For example, in arch/powerpc, the list of SPI devices can be populated from data in the device tree. With the current code, the device tree adapter must kmalloc() a new spi_board_info structure for each new SPI device it finds in the device tree, and there is no simple mechanism in place for keeping track of these allocations. This patch changes modalias from a 'const char *' to a fixed char array. By copying the modalias string instead of referencing it, the dependency on the spi_board_info structure is eliminated and an outside caller does not need to maintain a separate spi_board_info allocation for each device. If searched through the code to the best of my ability for any references to modalias which may be affected by this change and haven't found anything. It has been tested with the lite5200b platform in arch/powerpc. [dbrownell@users.sourceforge.net: cope with linux-next changes: KOBJ_NAME_LEN obliterated, etc] Signed-off-by: Grant Likely Signed-off-by: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/spi/spi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index b9a76c972084..a9cc29d46653 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -82,7 +82,7 @@ struct spi_device { int irq; void *controller_state; void *controller_data; - const char *modalias; + char modalias[32]; /* * likely need more hooks for more protocol options affecting how -- cgit v1.2.3 From aa55ddf340c9fa3f303ee16bbf35887e42c50304 Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Wed, 23 Jul 2008 21:30:29 -0700 Subject: autofs4: remove unused ioctls The ioctls AUTOFS_IOC_TOGGLEREGHOST and AUTOFS_IOC_ASKREGHOST were added several years ago but what they were intended for has never been implemented (as far as I'm aware noone uses them) so remove them. Signed-off-by: Ian Kent Reviewed-by: Jeff Moyer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/auto_fs4.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/auto_fs4.h b/include/linux/auto_fs4.h index 31a29541b504..b785c6f8644d 100644 --- a/include/linux/auto_fs4.h +++ b/include/linux/auto_fs4.h @@ -98,8 +98,6 @@ union autofs_v5_packet_union { #define AUTOFS_IOC_EXPIRE_INDIRECT AUTOFS_IOC_EXPIRE_MULTI #define AUTOFS_IOC_EXPIRE_DIRECT AUTOFS_IOC_EXPIRE_MULTI #define AUTOFS_IOC_PROTOSUBVER _IOR(0x93,0x67,int) -#define AUTOFS_IOC_ASKREGHOST _IOR(0x93,0x68,int) -#define AUTOFS_IOC_TOGGLEREGHOST _IOR(0x93,0x69,int) #define AUTOFS_IOC_ASKUMOUNT _IOR(0x93,0x70,int) -- cgit v1.2.3 From 5ad31a575157147b43fa84ef1e21471661653878 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Wed, 23 Jul 2008 21:30:33 -0700 Subject: rtc: remove BKL for ioctl() Remove implicit use of BKL in ioctl() from the RTC framework. Instead, the rtc->ops_lock is used. That's the same lock that already protects the RTC operations when they're issued through the exported rtc_*() calls in drivers/rtc/interface.c ... making this a bugfix, not just a cleanup, since both ioctl calls and set_alarm() need to update IRQ enable flags and that implies a common lock (which RTC drivers as a rule do not provide on their own). A new comment at the declaration of "struct rtc_class_ops" summarizes current locking rules. It's not clear to me that the exceptions listed there should exist ... if not, those are pre-existing problems which can be fixed in a patch that doesn't relate to BKL removal. Signed-off-by: David Brownell Cc: Alan Cox Cc: Jonathan Corbet Acked-by: Alessandro Zummo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rtc.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index f2d0d1527721..b01fe004cb5e 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -115,6 +115,23 @@ extern void rtc_time_to_tm(unsigned long time, struct rtc_time *tm); extern struct class *rtc_class; +/* + * For these RTC methods the device parameter is the physical device + * on whatever bus holds the hardware (I2C, Platform, SPI, etc), which + * was passed to rtc_device_register(). Its driver_data normally holds + * device state, including the rtc_device pointer for the RTC. + * + * Most of these methods are called with rtc_device.ops_lock held, + * through the rtc_*(struct rtc_device *, ...) calls. + * + * The (current) exceptions are mostly filesystem hooks: + * - the proc() hook for procfs + * - non-ioctl() chardev hooks: open(), release(), read_callback() + * - periodic irq calls: irq_set_state(), irq_set_freq() + * + * REVISIT those periodic irq calls *do* have ops_lock when they're + * issued through ioctl() ... + */ struct rtc_class_ops { int (*open)(struct device *); void (*release)(struct device *); -- cgit v1.2.3 From 53e84b672c1a8190af2b376c35c7a39cf1214f59 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Wed, 23 Jul 2008 21:30:36 -0700 Subject: rtc: ds1305/ds1306 driver Support the Dallas/Maxim DS1305 and DS1306 RTC chips. These use SPI, and support alarms, NVRAM, and a trickle charger for use when their backup power supply is a supercap or rechargeable cell. This basic driver doesn't yet support suspend/resume or wakealarms. Signed-off-by: David Brownell Cc: Alessandro Zummo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/spi/ds1305.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 include/linux/spi/ds1305.h (limited to 'include/linux') diff --git a/include/linux/spi/ds1305.h b/include/linux/spi/ds1305.h new file mode 100644 index 000000000000..287ec830eab7 --- /dev/null +++ b/include/linux/spi/ds1305.h @@ -0,0 +1,35 @@ +#ifndef __LINUX_SPI_DS1305_H +#define __LINUX_SPI_DS1305_H + +/* + * One-time configuration for ds1305 and ds1306 RTC chips. + * + * Put a pointer to this in spi_board_info.platform_data if you want to + * be sure that Linux (re)initializes this as needed ... after losing + * backup power, and potentially on the first boot. + */ +struct ds1305_platform_data { + + /* Trickle charge configuration: it's OK to leave out the MAGIC + * bitmask; mask in either DS1 or DS2, and then one of 2K/4k/8K. + */ +#define DS1305_TRICKLE_MAGIC 0xa0 +#define DS1305_TRICKLE_DS2 0x08 /* two diodes */ +#define DS1305_TRICKLE_DS1 0x04 /* one diode */ +#define DS1305_TRICKLE_2K 0x01 /* 2 KOhm resistance */ +#define DS1305_TRICKLE_4K 0x02 /* 4 KOhm resistance */ +#define DS1305_TRICKLE_8K 0x03 /* 8 KOhm resistance */ + u8 trickle; + + /* set only on ds1306 parts */ + bool is_ds1306; + + /* ds1306 only: enable 1 Hz output */ + bool en_1hz; + + /* REVISIT: the driver currently expects nINT0 to be wired + * as the alarm IRQ. ALM1 may also need to be set up ... + */ +}; + +#endif /* __LINUX_SPI_DS1305_H */ -- cgit v1.2.3 From d3de851a445123f24ad8ece18662014b5e8a8b4e Mon Sep 17 00:00:00 2001 From: David Brownell Date: Wed, 23 Jul 2008 21:30:37 -0700 Subject: rtc: BCD codeshrink This updates to define the key routines as constant functions, which the macros will then call. Newer code can now call bcd2bin() instead of SCREAMING BCD2BIN() TO THE FOUR WINDS. This lets each driver shrink their codespace by using N function calls to a single (global) copy of those routines, instead of N inlined copies of these functions per driver. These routines aren't used in speed-critical code. Almost all callers are in the RTC framework. Typical per-driver savings is near 300 bytes. Signed-off-by: David Brownell Acked-by: Adrian Bunk Cc: Alessandro Zummo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bcd.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bcd.h b/include/linux/bcd.h index c545308125b0..7ac518e3c152 100644 --- a/include/linux/bcd.h +++ b/include/linux/bcd.h @@ -10,8 +10,13 @@ #ifndef _BCD_H #define _BCD_H -#define BCD2BIN(val) (((val) & 0x0f) + ((val)>>4)*10) -#define BIN2BCD(val) ((((val)/10)<<4) + (val)%10) +#include + +unsigned bcd2bin(unsigned char val) __attribute_const__; +unsigned char bin2bcd(unsigned val) __attribute_const__; + +#define BCD2BIN(val) bcd2bin(val) +#define BIN2BCD(val) bin2bcd(val) /* backwards compat */ #define BCD_TO_BIN(val) ((val)=BCD2BIN(val)) -- cgit v1.2.3 From 01a2d9ed85c945fc8a672622780533a1a0b7caf5 Mon Sep 17 00:00:00 2001 From: Krzysztof Helt Date: Wed, 23 Jul 2008 21:31:04 -0700 Subject: tridentfb: acceleration constants change This patch replaces deprecated constant FB_ACCELF_TEXT with FBINFO_HWACCEL_DISABLED and adds constants for Trident families of accelerators. The FBINFO_HWACCEL_DISABLED is correctly used so noaccel parameter works now. Signed-off-by: Krzysztof Helt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 72295b099228..a084d1335869 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -120,6 +120,10 @@ struct dentry; #define FB_ACCEL_XGI_VOLARI_V 47 /* XGI Volari V3XT, V5, V8 */ #define FB_ACCEL_XGI_VOLARI_Z 48 /* XGI Volari Z7 */ #define FB_ACCEL_OMAP1610 49 /* TI OMAP16xx */ +#define FB_ACCEL_TRIDENT_TGUI 50 /* Trident TGUI */ +#define FB_ACCEL_TRIDENT_3DIMAGE 51 /* Trident 3DImage */ +#define FB_ACCEL_TRIDENT_BLADE3D 52 /* Trident Blade3D */ +#define FB_ACCEL_TRIDENT_BLADEXP 53 /* Trident BladeXP */ #define FB_ACCEL_NEOMAGIC_NM2070 90 /* NeoMagic NM2070 */ #define FB_ACCEL_NEOMAGIC_NM2090 91 /* NeoMagic NM2090 */ #define FB_ACCEL_NEOMAGIC_NM2093 92 /* NeoMagic NM2093 */ -- cgit v1.2.3 From 206c5d69d0540024faffd423fc703f1e457332d7 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Wed, 23 Jul 2008 21:31:35 -0700 Subject: sm501: add inversion controls for VBIASEN and FPEN Add flags to allow the driver to invert the sense of both VBIASEN and FPEN signals comming from the SM501. Signed-off-by: Ben Dooks Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sm501.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sm501.h b/include/linux/sm501.h index 95c1c39ba445..b530fa6a1d34 100644 --- a/include/linux/sm501.h +++ b/include/linux/sm501.h @@ -73,6 +73,8 @@ extern unsigned long sm501_gpio_get(struct device *dev, #define SM501FB_FLAG_USE_HWACCEL (1<<3) #define SM501FB_FLAG_PANEL_NO_FPEN (1<<4) #define SM501FB_FLAG_PANEL_NO_VBIASEN (1<<5) +#define SM501FB_FLAG_PANEL_INV_FPEN (1<<6) +#define SM501FB_FLAG_PANEL_INV_VBIASEN (1<<7) struct sm501_platdata_fbsub { struct fb_videomode *def_mode; -- cgit v1.2.3 From 0c531360ed504aa0ce995fcb8ef08e82b6534d0b Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Wed, 23 Jul 2008 21:31:38 -0700 Subject: lcd: add lcd_device to check_fb() entry in lcd_ops Add the lcd_device being checked to the check_fb entry of lcd_ops. This ensures that any driver using this to check against it's own state can do so, and also makes all the calls in lcd_ops more orthogonal in their arguments. Signed-off-by: Ben Dooks Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lcd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lcd.h b/include/linux/lcd.h index 1d379787f2e7..173febac6656 100644 --- a/include/linux/lcd.h +++ b/include/linux/lcd.h @@ -47,7 +47,7 @@ struct lcd_ops { int (*set_contrast)(struct lcd_device *, int contrast); /* Check if given framebuffer device is the one LCD is bound to; return 0 if not, !=0 if it is. If NULL, lcd always matches the fb. */ - int (*check_fb)(struct fb_info *); + int (*check_fb)(struct lcd_device *, struct fb_info *); }; struct lcd_device { -- cgit v1.2.3 From 3e074058d72486676f6fdf6fe803200c62dcb403 Mon Sep 17 00:00:00 2001 From: Hans-Christian Egtvedt Date: Wed, 23 Jul 2008 21:31:48 -0700 Subject: fbdev: LCD backlight driver using Atmel PWM driver This patch adds a platform driver using the ATMEL PWM driver to control a backlight which requires a PWM signal and optional GPIO signal for discrete on/off signal. It has been tested on Favr-32 board from EarthLCD. The driver is configurable by supplying a struct with the platform data. See the include/linux/atmel-pwm-bl.h for details. The board code for Favr-32 will be submitted to the AVR32 kernel list. Signed-off-by: Hans-Christian Egtvedt Cc: Krzysztof Helt Cc: Haavard Skinnemoen Cc: Richard Purdie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/atmel-pwm-bl.h | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) create mode 100644 include/linux/atmel-pwm-bl.h (limited to 'include/linux') diff --git a/include/linux/atmel-pwm-bl.h b/include/linux/atmel-pwm-bl.h new file mode 100644 index 000000000000..0153a47806c2 --- /dev/null +++ b/include/linux/atmel-pwm-bl.h @@ -0,0 +1,43 @@ +/* + * Copyright (C) 2007 Atmel Corporation + * + * Driver for the AT32AP700X PS/2 controller (PSIF). + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + */ + +#ifndef __INCLUDE_ATMEL_PWM_BL_H +#define __INCLUDE_ATMEL_PWM_BL_H + +/** + * struct atmel_pwm_bl_platform_data + * @pwm_channel: which PWM channel in the PWM module to use. + * @pwm_frequency: PWM frequency to generate, the driver will try to be as + * close as the prescaler allows. + * @pwm_compare_max: value to use in the PWM channel compare register. + * @pwm_duty_max: maximum duty cycle value, must be less than or equal to + * pwm_compare_max. + * @pwm_duty_min: minimum duty cycle value, must be less than pwm_duty_max. + * @pwm_active_low: set to one if the low part of the PWM signal increases the + * brightness of the backlight. + * @gpio_on: GPIO line to control the backlight on/off, set to -1 if not used. + * @on_active_low: set to one if the on/off signal is on when GPIO is low. + * + * This struct must be added to the platform device in the board code. It is + * used by the atmel-pwm-bl driver to setup the GPIO to control on/off and the + * PWM device. + */ +struct atmel_pwm_bl_platform_data { + unsigned int pwm_channel; + unsigned int pwm_frequency; + unsigned int pwm_compare_max; + unsigned int pwm_duty_max; + unsigned int pwm_duty_min; + unsigned int pwm_active_low; + int gpio_on; + unsigned int on_active_low; +}; + +#endif /* __INCLUDE_ATMEL_PWM_BL_H */ -- cgit v1.2.3 From 5bb49fcd501aa9fd3d321a22b7c01d9b0db7ab36 Mon Sep 17 00:00:00 2001 From: Philippe De Muyter Date: Wed, 23 Jul 2008 21:31:50 -0700 Subject: video/fb: cleanup FB_MAJOR usage Currently, linux/major.h defines a GRAPHDEV_MAJOR (29) that nobody uses, and linux/fb.h defines the real FB_MAJOR (also 29), that only fbmem.c needs. Drop GRAPHDEV_MAJOR from major.h, move FB_MAJOR definition from fb.h to major.h, and fix fbmem.c to use major.h's definition. Signed-off-by: Philippe De Muyter Cc: Krzysztof Helt Cc: "Antonino A. Daplas" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fb.h | 1 - include/linux/major.h | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index a084d1335869..3b8870e32afd 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -8,7 +8,6 @@ struct dentry; /* Definitions of frame buffers */ -#define FB_MAJOR 29 #define FB_MAX 32 /* sufficient for now */ /* ioctls diff --git a/include/linux/major.h b/include/linux/major.h index 0cb98053537a..53d5fafd85c3 100644 --- a/include/linux/major.h +++ b/include/linux/major.h @@ -53,7 +53,7 @@ #define STL_SIOMEMMAJOR 28 #define ACSI_MAJOR 28 #define AZTECH_CDROM_MAJOR 29 -#define GRAPHDEV_MAJOR 29 /* SparcLinux & Linux/68k /dev/fb */ +#define FB_MAJOR 29 /* /dev/fb* framebuffers */ #define CM206_CDROM_MAJOR 32 #define IDE2_MAJOR 33 #define IDE3_MAJOR 34 -- cgit v1.2.3 From f9247273cb69ba101877e946d2d83044409cc8c5 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Thu, 24 Jul 2008 17:22:13 +0100 Subject: UFS: add const to parser token table This patch adds a "const" to the parser token table. I've done an allmodconfig build to see if this produces any warnings/failures and the patch includes a fix for the only warning that was produced. Signed-off-by: Steven Whitehouse Acked-by: Alexander Viro Acked-by: Evgeniy Dushistov Signed-off-by: Linus Torvalds --- include/linux/parser.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/parser.h b/include/linux/parser.h index 7dcd05075756..cc554ca8bc78 100644 --- a/include/linux/parser.h +++ b/include/linux/parser.h @@ -14,7 +14,7 @@ struct match_token { const char *pattern; }; -typedef struct match_token match_table_t[]; +typedef const struct match_token match_table_t[]; /* Maximum number of arguments that match_token will find in a pattern */ enum {MAX_OPT_ARGS = 3}; -- cgit v1.2.3 From 6cdf6eb357c2681596b7b1672b92396ba82333d4 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Thu, 24 Jul 2008 22:53:14 +0200 Subject: ide: add ->dev and ->host_priv fields to struct ide_host * Add 'struct device *dev[2]' and 'void *host_priv' fields to struct ide_host. * Set ->dev[] in ide_host_alloc_all()/ide_setup_pci_device[s](). * Pass 'void *priv' argument to ide_setup_pci_device[s]() and use it to set ->host_priv. * Set PCI dev's ->driver_data to point to the struct ide_host instance if PCI host driver wants to use ->host_priv. * Rename ide_setup_pci_device[s]() to ide_pci_init_{one,two}(). Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index d67ccca2b964..776c574c9640 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -626,6 +626,8 @@ typedef struct hwif_s { struct ide_host { ide_hwif_t *ports[MAX_HWIFS]; unsigned int n_ports; + struct device *dev[2]; + void *host_priv; }; /* @@ -1201,8 +1203,9 @@ struct ide_port_info { u8 udma_mask; }; -int ide_setup_pci_device(struct pci_dev *, const struct ide_port_info *); -int ide_setup_pci_devices(struct pci_dev *, struct pci_dev *, const struct ide_port_info *); +int ide_pci_init_one(struct pci_dev *, const struct ide_port_info *, void *); +int ide_pci_init_two(struct pci_dev *, struct pci_dev *, + const struct ide_port_info *, void *); void ide_map_sg(ide_drive_t *, struct request *); void ide_init_sg_cmd(ide_drive_t *, struct request *); -- cgit v1.2.3 From 08da591e14cf87247ec09b17c350235157a92fc3 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Thu, 24 Jul 2008 22:53:15 +0200 Subject: ide: add ide_device_{get,put}() helpers * Add 'struct ide_host *host' field to ide_hwif_t and set it in ide_host_alloc_all(). * Add ide_device_{get,put}() helpers loosely based on SCSI's scsi_device_{get,put}() ones. * Convert IDE device drivers to use ide_device_{get,put}(). Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 776c574c9640..3eccac0a2a36 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -532,12 +532,16 @@ struct ide_dma_ops { void (*dma_timeout)(struct ide_drive_s *); }; +struct ide_host; + typedef struct hwif_s { struct hwif_s *next; /* for linked-list in ide_hwgroup_t */ struct hwif_s *mate; /* other hwif from same PCI chip */ struct hwgroup_s *hwgroup; /* actually (ide_hwgroup_t *) */ struct proc_dir_entry *proc; /* /proc/ide/ directory entry */ + struct ide_host *host; + char name[6]; /* name of interface, eg. "ide0" */ struct ide_io_ports io_ports; @@ -876,6 +880,9 @@ struct ide_driver_s { #define to_ide_driver(drv) container_of(drv, ide_driver_t, gen_driver) +int ide_device_get(ide_drive_t *); +void ide_device_put(ide_drive_t *); + int generic_ide_ioctl(ide_drive_t *, struct file *, struct block_device *, unsigned, unsigned long); extern int ide_vlb_clk; -- cgit v1.2.3 From ef0b04276d8f719d754c092434fbd62c2aeb5307 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Thu, 24 Jul 2008 22:53:19 +0200 Subject: ide: add ide_pci_remove() helper * Add 'unsigned long host_flags' field to struct ide_host. * Set ->host_flags in ide_host_alloc_all(). * Always set PCI dev's ->driver_data in ide_pci_init_{one,two}(). * Add ide_pci_remove() helper (the default implementation for struct pci_driver's ->remove method). Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 3eccac0a2a36..dbd0aeb3a56d 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -631,6 +631,7 @@ struct ide_host { ide_hwif_t *ports[MAX_HWIFS]; unsigned int n_ports; struct device *dev[2]; + unsigned long host_flags; void *host_priv; }; @@ -1213,6 +1214,7 @@ struct ide_port_info { int ide_pci_init_one(struct pci_dev *, const struct ide_port_info *, void *); int ide_pci_init_two(struct pci_dev *, struct pci_dev *, const struct ide_port_info *, void *); +void ide_pci_remove(struct pci_dev *); void ide_map_sg(ide_drive_t *, struct request *); void ide_init_sg_cmd(ide_drive_t *, struct request *); -- cgit v1.2.3 From d83b8b85cd56a083d30df73f3fd5e4714591b910 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Thu, 24 Jul 2008 22:53:30 +0200 Subject: ide: define MAX_HWIFS in * Now that ide_hwif_t instances are allocated dynamically the difference between MAX_HWIFS == 2 and MAX_HWIFS == 10 is ~100 bytes (x86-32) so use MAX_HWIFS == 10 on all archs except these ones that use MAX_HWIFS == 1. * Define MAX_HWIFS in instead of . [ Please note that avr32/cris/v850 have no and alpha/ia64/sh always define CONFIG_IDE_MAX_HWIFS. ] Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index dbd0aeb3a56d..76fe00b24b51 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -213,6 +213,14 @@ static inline int __ide_default_irq(unsigned long base) #include +#ifndef MAX_HWIFS +#if defined(CONFIG_BLACKFIN) || defined(CONFIG_H8300) || defined(CONFIG_XTENSA) +# define MAX_HWIFS 1 +#else +# define MAX_HWIFS 10 +#endif +#endif + #if !defined(MAX_HWIFS) || defined(CONFIG_EMBEDDED) #undef MAX_HWIFS #define MAX_HWIFS CONFIG_IDE_MAX_HWIFS -- cgit v1.2.3 From 2a8f7450f828eaee49d66f41f99ac2e54f1160a6 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Thu, 24 Jul 2008 22:53:31 +0200 Subject: ide: remove for some archs * Remove include from ( includes which is enough). * Remove for alpha/blackfin/h8300/ia64/m32r/sh/x86/xtensa (this leaves us with arm/frv/m68k/mips/mn10300/parisc/powerpc/sparc[64]). There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 76fe00b24b51..fd78b401b036 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -211,7 +211,13 @@ static inline int __ide_default_irq(unsigned long base) return 0; } +#if defined(CONFIG_ARM) || defined(CONFIG_FRV) || defined(CONFIG_M68K) || \ + defined(CONFIG_MIPS) || defined(CONFIG_MN10300) || defined(CONFIG_PARISC) \ + || defined(CONFIG_PPC) || defined(CONFIG_SPARC) || defined(CONFIG_SPARC64) #include +#else +#include +#endif #ifndef MAX_HWIFS #if defined(CONFIG_BLACKFIN) || defined(CONFIG_H8300) || defined(CONFIG_XTENSA) -- cgit v1.2.3 From a326b02b0c576001353dbc489154959b0889c6bf Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Thu, 24 Jul 2008 22:53:33 +0200 Subject: ide: drop 'name' parameter from ->init_chipset method There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index fd78b401b036..b846bc44a27e 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1206,7 +1206,7 @@ enum { struct ide_port_info { char *name; - unsigned int (*init_chipset)(struct pci_dev *, const char *); + unsigned int (*init_chipset)(struct pci_dev *); void (*init_iops)(ide_hwif_t *); void (*init_hwif)(ide_hwif_t *); int (*init_dma)(ide_hwif_t *, -- cgit v1.2.3 From 674bfc23c585b34c42263d73fb51710d49762a23 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 25 Jul 2008 12:06:03 -0500 Subject: virtio: clarify that ABI is usable by any implementations We want others to implement and use virtio, so it makes sense to BSD license the non-__KERNEL__ parts of the headers to make this crystal clear. Signed-off-by: Rusty Russell Acked-by: Christian Borntraeger Acked-by: Mark McLoughlin Acked-by: Ryan Harper Acked-by: Eric Van Hensbergen Acked-by: Anthony Liguori --- include/linux/virtio_9p.h | 2 ++ include/linux/virtio_balloon.h | 2 ++ include/linux/virtio_blk.h | 2 ++ include/linux/virtio_config.h | 3 +++ include/linux/virtio_console.h | 2 ++ include/linux/virtio_net.h | 2 ++ include/linux/virtio_pci.h | 5 ++--- include/linux/virtio_rng.h | 2 ++ 8 files changed, 17 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_9p.h b/include/linux/virtio_9p.h index 8eff0b53910b..b3c4a60ceeb3 100644 --- a/include/linux/virtio_9p.h +++ b/include/linux/virtio_9p.h @@ -1,5 +1,7 @@ #ifndef _LINUX_VIRTIO_9P_H #define _LINUX_VIRTIO_9P_H +/* This header is BSD licensed so anyone can use the definitions to implement + * compatible drivers/servers. */ #include /* The ID for virtio console */ diff --git a/include/linux/virtio_balloon.h b/include/linux/virtio_balloon.h index 979524ee75b7..c30c7bfbf39b 100644 --- a/include/linux/virtio_balloon.h +++ b/include/linux/virtio_balloon.h @@ -1,5 +1,7 @@ #ifndef _LINUX_VIRTIO_BALLOON_H #define _LINUX_VIRTIO_BALLOON_H +/* This header is BSD licensed so anyone can use the definitions to implement + * compatible drivers/servers. */ #include /* The ID for virtio_balloon */ diff --git a/include/linux/virtio_blk.h b/include/linux/virtio_blk.h index 5f79a5f9de79..6a66c7f30bcb 100644 --- a/include/linux/virtio_blk.h +++ b/include/linux/virtio_blk.h @@ -1,5 +1,7 @@ #ifndef _LINUX_VIRTIO_BLK_H #define _LINUX_VIRTIO_BLK_H +/* This header is BSD licensed so anyone can use the definitions to implement + * compatible drivers/servers. */ #include /* The ID for virtio_block */ diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index f364bbf63c34..7eb4b34d13bb 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -1,5 +1,8 @@ #ifndef _LINUX_VIRTIO_CONFIG_H #define _LINUX_VIRTIO_CONFIG_H +/* This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so + * anyone can use the definitions to implement compatible drivers/servers. */ + /* Virtio devices use a standardized configuration space to define their * features and pass configuration information, but each implementation can * store and access that space differently. */ diff --git a/include/linux/virtio_console.h b/include/linux/virtio_console.h index ed2d4ead7eb7..19a0da0dba41 100644 --- a/include/linux/virtio_console.h +++ b/include/linux/virtio_console.h @@ -1,6 +1,8 @@ #ifndef _LINUX_VIRTIO_CONSOLE_H #define _LINUX_VIRTIO_CONSOLE_H #include +/* This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so + * anyone can use the definitions to implement compatible drivers/servers. */ /* The ID for virtio console */ #define VIRTIO_ID_CONSOLE 3 diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 38c0571820fb..5e33761b9b8a 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -1,5 +1,7 @@ #ifndef _LINUX_VIRTIO_NET_H #define _LINUX_VIRTIO_NET_H +/* This header is BSD licensed so anyone can use the definitions to implement + * compatible drivers/servers. */ #include /* The ID for virtio_net */ diff --git a/include/linux/virtio_pci.h b/include/linux/virtio_pci.h index b3151659cf49..cdef35742932 100644 --- a/include/linux/virtio_pci.h +++ b/include/linux/virtio_pci.h @@ -9,9 +9,8 @@ * Authors: * Anthony Liguori * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * + * This header is BSD licensed so anyone can use the definitions to implement + * compatible drivers/servers. */ #ifndef _LINUX_VIRTIO_PCI_H diff --git a/include/linux/virtio_rng.h b/include/linux/virtio_rng.h index 331afb6c9f62..1a85dab8a940 100644 --- a/include/linux/virtio_rng.h +++ b/include/linux/virtio_rng.h @@ -1,5 +1,7 @@ #ifndef _LINUX_VIRTIO_RNG_H #define _LINUX_VIRTIO_RNG_H +/* This header is BSD licensed so anyone can use the definitions to implement + * compatible drivers/servers. */ #include /* The ID for virtio_rng */ -- cgit v1.2.3 From 066f4d82a67f621ddd547bfa4b9c94631d8457b0 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 29 May 2008 11:08:26 +0200 Subject: virtio_blk: check for hardsector size from host Currently virtio_blk assumes a 512 byte hard sector size. This can cause trouble / performance issues if the backing has a different block size (like a file on an ext3 file system formatted with 4k block size or a dasd). Lets add a feature flag that tells the guest to use a different hard sector size than 512 byte. Signed-off-by: Christian Borntraeger Signed-off-by: Rusty Russell --- include/linux/virtio_blk.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_blk.h b/include/linux/virtio_blk.h index 6a66c7f30bcb..c1aef85243bf 100644 --- a/include/linux/virtio_blk.h +++ b/include/linux/virtio_blk.h @@ -13,6 +13,7 @@ #define VIRTIO_BLK_F_SEG_MAX 2 /* Indicates maximum # of segments */ #define VIRTIO_BLK_F_GEOMETRY 4 /* Legacy geometry available */ #define VIRTIO_BLK_F_RO 5 /* Disk is read-only */ +#define VIRTIO_BLK_F_BLK_SIZE 6 /* Block size of disk is available*/ struct virtio_blk_config { @@ -28,6 +29,8 @@ struct virtio_blk_config __u8 heads; __u8 sectors; } geometry; + /* block size of device (if VIRTIO_BLK_F_BLK_SIZE) */ + __u32 blk_size; } __attribute__((packed)); /* These two define direction. */ -- cgit v1.2.3 From dd7c7bc46211785a1aa7d70feb15830f62682b3c Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 25 Jul 2008 12:06:07 -0500 Subject: virtio: Formally reserve bits 28-31 to be 'transport' features. We assign feature bits as required, but it makes sense to reserve some for the particular transport, rather than the particular device. Signed-off-by: Rusty Russell --- include/linux/virtio_config.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 7eb4b34d13bb..5a30cfb7934b 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -18,6 +18,12 @@ /* We've given up on this device. */ #define VIRTIO_CONFIG_S_FAILED 0x80 +/* Some virtio feature bits (currently bits 28 through 31) are reserved for the + * transport being used (eg. virtio_ring), the rest are per-device feature + * bits. */ +#define VIRTIO_TRANSPORT_F_START 28 +#define VIRTIO_TRANSPORT_F_END 32 + /* Do we get callbacks when the ring is completely used, even if we've * suppressed them? */ #define VIRTIO_F_NOTIFY_ON_EMPTY 24 -- cgit v1.2.3 From c624896e488ba2bff5ae497782cfb265c8b00646 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 25 Jul 2008 12:06:07 -0500 Subject: virtio: Rename set_features to finalize_features Rather than explicitly handing the features to the lower-level, we just hand the virtio_device and have it set the features. This make it clear that it has the chance to manipulate the features of the device at this point (and that all feature negotiation is already done). Signed-off-by: Rusty Russell --- include/linux/virtio_config.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 5a30cfb7934b..bf8ec283b232 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -61,9 +61,10 @@ * @get_features: get the array of feature bits for this device. * vdev: the virtio_device * Returns the first 32 feature bits (all we currently need). - * @set_features: confirm what device features we'll be using. + * @finalize_features: confirm what device features we'll be using. * vdev: the virtio_device - * feature: the first 32 feature bits + * This gives the final feature bits for the device: it can change + * the dev->feature bits if it wants. */ struct virtio_config_ops { @@ -79,7 +80,7 @@ struct virtio_config_ops void (*callback)(struct virtqueue *)); void (*del_vq)(struct virtqueue *vq); u32 (*get_features)(struct virtio_device *vdev); - void (*set_features)(struct virtio_device *vdev, u32 features); + void (*finalize_features)(struct virtio_device *vdev); }; /* If driver didn't advertise the feature, it will never appear. */ -- cgit v1.2.3 From e34f87256794b87e7f4a8f1812538be7b7b5214c Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 25 Jul 2008 12:06:13 -0500 Subject: virtio: Add transport feature handling stub for virtio_ring. To prepare for virtio_ring transport feature bits, hook in a call in all the users to manipulate them. This currently just clears all the bits, since it doesn't understand any features. Signed-off-by: Rusty Russell --- include/linux/virtio_ring.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index abe481ed990e..c4a598fb3826 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -120,6 +120,8 @@ struct virtqueue *vring_new_virtqueue(unsigned int num, void (*notify)(struct virtqueue *vq), void (*callback)(struct virtqueue *vq)); void vring_del_virtqueue(struct virtqueue *vq); +/* Filter out transport-specific feature bits. */ +void vring_transport_features(struct virtio_device *vdev); irqreturn_t vring_interrupt(int irq, void *_vq); #endif /* __KERNEL__ */ -- cgit v1.2.3 From ed9559d38a87a44e3bda87d73a50aab92471d7dc Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 25 Jul 2008 12:11:09 +1000 Subject: Label kthread_create() with printf attribute tag. Obvious misc patch been in my queue (& linux-next) for over a cycle. Signed-off-by: Rusty Russell Signed-off-by: Linus Torvalds --- include/linux/kthread.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 00dd957e245b..aabc8a13ba71 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -6,7 +6,8 @@ struct task_struct *kthread_create(int (*threadfn)(void *data), void *data, - const char namefmt[], ...); + const char namefmt[], ...) + __attribute__((format(printf, 3, 4))); /** * kthread_run - create and wake a thread. -- cgit v1.2.3 From 483fad1c3fa1060d7e6710e84a065ad514571739 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Tue, 22 Jul 2008 04:48:46 +1000 Subject: ELF loader support for auxvec base platform string Some IBM POWER-based platforms have the ability to run in a mode which mostly appears to the OS as a different processor from the actual hardware. For example, a Power6 system may appear to be a Power5+, which makes the AT_PLATFORM value "power5+". This means that programs are restricted to the ISA supported by Power5+; Power6-specific instructions are treated as illegal. However, some applications (virtual machines, optimized libraries) can benefit from knowledge of the underlying CPU model. A new aux vector entry, AT_BASE_PLATFORM, will denote the actual hardware. For example, on a Power6 system in Power5+ compatibility mode, AT_PLATFORM will be "power5+" and AT_BASE_PLATFORM will be "power6". The idea is that AT_PLATFORM indicates the instruction set supported, while AT_BASE_PLATFORM indicates the underlying microarchitecture. If the architecture has defined ELF_BASE_PLATFORM, copy that value to the user stack in the same manner as ELF_PLATFORM. Signed-off-by: Nathan Lynch Acked-by: Andrew Morton Signed-off-by: Benjamin Herrenschmidt --- include/linux/auxvec.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/auxvec.h b/include/linux/auxvec.h index 0da17d14fd13..d7afa9dd6635 100644 --- a/include/linux/auxvec.h +++ b/include/linux/auxvec.h @@ -26,9 +26,13 @@ #define AT_SECURE 23 /* secure mode boolean */ +#define AT_BASE_PLATFORM 24 /* string identifying real platform, may + * differ from AT_PLATFORM. */ + #define AT_EXECFN 31 /* filename of program */ + #ifdef __KERNEL__ -#define AT_VECTOR_SIZE_BASE 17 /* NEW_AUX_ENT entries in auxiliary table */ +#define AT_VECTOR_SIZE_BASE 18 /* NEW_AUX_ENT entries in auxiliary table */ /* number of "#define AT_.*" above, minus {AT_NULL, AT_IGNORE, AT_NOTELF} */ #endif -- cgit v1.2.3 From 3d6f4a20cc287a8980c6186624834cf10a70752b Mon Sep 17 00:00:00 2001 From: David Miller Date: Thu, 24 Jul 2008 23:38:31 -0700 Subject: endian: Always evaluate arguments. Changeset 7fa897b91a3ea0f16c2873b869d7a0eef05acff4 ("ide: trivial sparse annotations") created an IDE bootup regression on big-endian systems. In drivers/ide/ide-iops.c, function ide_fixstring() we now have the loop: for (p = end ; p != s;) be16_to_cpus((u16 *)(p -= 2)); which will never terminate on big-endian because in such a configuration be16_to_cpus() evaluates to "do { } while (0)" Therefore, always evaluate the arguments to nop endian transformation operations. Signed-off-by: David S. Miller Signed-off-by: Linus Torvalds --- include/linux/byteorder/big_endian.h | 12 ++++++------ include/linux/byteorder/little_endian.h | 12 ++++++------ 2 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/byteorder/big_endian.h b/include/linux/byteorder/big_endian.h index 961ed4b48d8e..44f95b92393b 100644 --- a/include/linux/byteorder/big_endian.h +++ b/include/linux/byteorder/big_endian.h @@ -94,12 +94,12 @@ static inline __u16 __be16_to_cpup(const __be16 *p) #define __le32_to_cpus(x) __swab32s((x)) #define __cpu_to_le16s(x) __swab16s((x)) #define __le16_to_cpus(x) __swab16s((x)) -#define __cpu_to_be64s(x) do {} while (0) -#define __be64_to_cpus(x) do {} while (0) -#define __cpu_to_be32s(x) do {} while (0) -#define __be32_to_cpus(x) do {} while (0) -#define __cpu_to_be16s(x) do {} while (0) -#define __be16_to_cpus(x) do {} while (0) +#define __cpu_to_be64s(x) do { (void)(x); } while (0) +#define __be64_to_cpus(x) do { (void)(x); } while (0) +#define __cpu_to_be32s(x) do { (void)(x); } while (0) +#define __be32_to_cpus(x) do { (void)(x); } while (0) +#define __cpu_to_be16s(x) do { (void)(x); } while (0) +#define __be16_to_cpus(x) do { (void)(x); } while (0) #ifdef __KERNEL__ #include diff --git a/include/linux/byteorder/little_endian.h b/include/linux/byteorder/little_endian.h index 05dc7c35b3b2..4cc170a31762 100644 --- a/include/linux/byteorder/little_endian.h +++ b/include/linux/byteorder/little_endian.h @@ -88,12 +88,12 @@ static inline __u16 __be16_to_cpup(const __be16 *p) { return __swab16p((__u16 *)p); } -#define __cpu_to_le64s(x) do {} while (0) -#define __le64_to_cpus(x) do {} while (0) -#define __cpu_to_le32s(x) do {} while (0) -#define __le32_to_cpus(x) do {} while (0) -#define __cpu_to_le16s(x) do {} while (0) -#define __le16_to_cpus(x) do {} while (0) +#define __cpu_to_le64s(x) do { (void)(x); } while (0) +#define __le64_to_cpus(x) do { (void)(x); } while (0) +#define __cpu_to_le32s(x) do { (void)(x); } while (0) +#define __le32_to_cpus(x) do { (void)(x); } while (0) +#define __cpu_to_le16s(x) do { (void)(x); } while (0) +#define __le16_to_cpus(x) do { (void)(x); } while (0) #define __cpu_to_be64s(x) __swab64s((x)) #define __be64_to_cpus(x) __swab64s((x)) #define __cpu_to_be32s(x) __swab32s((x)) -- cgit v1.2.3 From e0deaff470900a4c3222ca7139f6c9639e26a2f5 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 25 Jul 2008 01:45:24 -0700 Subject: split the typecheck macros out of include/linux/kernel.h Needed to fix up a recursive include snafu in locking-add-typecheck-on-irqsave-and-friends-for-correct-flags.patch Cc: Steven Rostedt Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 21 +-------------------- include/linux/typecheck.h | 24 ++++++++++++++++++++++++ 2 files changed, 25 insertions(+), 20 deletions(-) create mode 100644 include/linux/typecheck.h (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index f9cd7a513f9c..5c4b1251e110 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -441,26 +442,6 @@ static inline char *pack_hex_byte(char *buf, u8 byte) const typeof( ((type *)0)->member ) *__mptr = (ptr); \ (type *)( (char *)__mptr - offsetof(type,member) );}) -/* - * Check at compile time that something is of a particular type. - * Always evaluates to 1 so you may use it easily in comparisons. - */ -#define typecheck(type,x) \ -({ type __dummy; \ - typeof(x) __dummy2; \ - (void)(&__dummy == &__dummy2); \ - 1; \ -}) - -/* - * Check at compile time that 'function' is a certain type, or is a pointer - * to that type (needs to use typedef for the function type.) - */ -#define typecheck_fn(type,function) \ -({ typeof(type) __tmp = function; \ - (void)__tmp; \ -}) - struct sysinfo; extern int do_sysinfo(struct sysinfo *info); diff --git a/include/linux/typecheck.h b/include/linux/typecheck.h new file mode 100644 index 000000000000..eb5b74a575be --- /dev/null +++ b/include/linux/typecheck.h @@ -0,0 +1,24 @@ +#ifndef TYPECHECK_H_INCLUDED +#define TYPECHECK_H_INCLUDED + +/* + * Check at compile time that something is of a particular type. + * Always evaluates to 1 so you may use it easily in comparisons. + */ +#define typecheck(type,x) \ +({ type __dummy; \ + typeof(x) __dummy2; \ + (void)(&__dummy == &__dummy2); \ + 1; \ +}) + +/* + * Check at compile time that 'function' is a certain type, or is a pointer + * to that type (needs to use typedef for the function type.) + */ +#define typecheck_fn(type,function) \ +({ typeof(type) __tmp = function; \ + (void)__tmp; \ +}) + +#endif /* TYPECHECK_H_INCLUDED */ -- cgit v1.2.3 From 3f307891ce0e7b0438c432af1aacd656a092ff45 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 25 Jul 2008 01:45:25 -0700 Subject: locking: add typecheck on irqsave and friends for correct flags There haave been several areas in the kernel where an int has been used for flags in local_irq_save() and friends instead of a long. This can cause some hard to debug problems on some architectures. This patch adds a typecheck inside the irqsave and restore functions to flag these cases. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: build fix] Signed-off-by: Steven Rostedt Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/irqflags.h | 54 ++++++++++++++++++++++++++---------- include/linux/spinlock.h | 72 +++++++++++++++++++++++++++++++++++++----------- 2 files changed, 95 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 2b1c2e58566e..74bde13224c9 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -11,6 +11,8 @@ #ifndef _LINUX_TRACE_IRQFLAGS_H #define _LINUX_TRACE_IRQFLAGS_H +#include + #ifdef CONFIG_TRACE_IRQFLAGS extern void trace_softirqs_on(unsigned long ip); extern void trace_softirqs_off(unsigned long ip); @@ -58,18 +60,24 @@ do { trace_hardirqs_on(); raw_local_irq_enable(); } while (0) #define local_irq_disable() \ do { raw_local_irq_disable(); trace_hardirqs_off(); } while (0) -#define local_irq_save(flags) \ - do { raw_local_irq_save(flags); trace_hardirqs_off(); } while (0) +#define local_irq_save(flags) \ + do { \ + typecheck(unsigned long, flags); \ + raw_local_irq_save(flags); \ + trace_hardirqs_off(); \ + } while (0) -#define local_irq_restore(flags) \ - do { \ - if (raw_irqs_disabled_flags(flags)) { \ - raw_local_irq_restore(flags); \ - trace_hardirqs_off(); \ - } else { \ - trace_hardirqs_on(); \ - raw_local_irq_restore(flags); \ - } \ + +#define local_irq_restore(flags) \ + do { \ + typecheck(unsigned long, flags); \ + if (raw_irqs_disabled_flags(flags)) { \ + raw_local_irq_restore(flags); \ + trace_hardirqs_off(); \ + } else { \ + trace_hardirqs_on(); \ + raw_local_irq_restore(flags); \ + } \ } while (0) #else /* !CONFIG_TRACE_IRQFLAGS_SUPPORT */ /* @@ -78,8 +86,16 @@ */ # define raw_local_irq_disable() local_irq_disable() # define raw_local_irq_enable() local_irq_enable() -# define raw_local_irq_save(flags) local_irq_save(flags) -# define raw_local_irq_restore(flags) local_irq_restore(flags) +# define raw_local_irq_save(flags) \ + do { \ + typecheck(unsigned long, flags); \ + local_irq_save(flags); \ + } while (0) +# define raw_local_irq_restore(flags) \ + do { \ + typecheck(unsigned long, flags); \ + local_irq_restore(flags); \ + } while (0) #endif /* CONFIG_TRACE_IRQFLAGS_SUPPORT */ #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT @@ -89,7 +105,11 @@ raw_safe_halt(); \ } while (0) -#define local_save_flags(flags) raw_local_save_flags(flags) +#define local_save_flags(flags) \ + do { \ + typecheck(unsigned long, flags); \ + raw_local_save_flags(flags); \ + } while (0) #define irqs_disabled() \ ({ \ @@ -99,7 +119,11 @@ raw_irqs_disabled_flags(_flags); \ }) -#define irqs_disabled_flags(flags) raw_irqs_disabled_flags(flags) +#define irqs_disabled_flags(flags) \ +({ \ + typecheck(unsigned long, flags); \ + raw_irqs_disabled_flags(flags); \ +}) #endif /* CONFIG_X86 */ #endif diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index d311a090fae7..61e5610ad165 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -46,6 +46,7 @@ * linux/spinlock.h: builds the final spin_*() APIs. */ +#include #include #include #include @@ -191,23 +192,53 @@ do { \ #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) -#define spin_lock_irqsave(lock, flags) flags = _spin_lock_irqsave(lock) -#define read_lock_irqsave(lock, flags) flags = _read_lock_irqsave(lock) -#define write_lock_irqsave(lock, flags) flags = _write_lock_irqsave(lock) +#define spin_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + flags = _spin_lock_irqsave(lock); \ + } while (0) +#define read_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + flags = _read_lock_irqsave(lock); \ + } while (0) +#define write_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + flags = _write_lock_irqsave(lock); \ + } while (0) #ifdef CONFIG_DEBUG_LOCK_ALLOC -#define spin_lock_irqsave_nested(lock, flags, subclass) \ - flags = _spin_lock_irqsave_nested(lock, subclass) +#define spin_lock_irqsave_nested(lock, flags, subclass) \ + do { \ + typecheck(unsigned long, flags); \ + flags = _spin_lock_irqsave_nested(lock, subclass); \ + } while (0) #else -#define spin_lock_irqsave_nested(lock, flags, subclass) \ - flags = _spin_lock_irqsave(lock) +#define spin_lock_irqsave_nested(lock, flags, subclass) \ + do { \ + typecheck(unsigned long, flags); \ + flags = _spin_lock_irqsave(lock); \ + } while (0) #endif #else -#define spin_lock_irqsave(lock, flags) _spin_lock_irqsave(lock, flags) -#define read_lock_irqsave(lock, flags) _read_lock_irqsave(lock, flags) -#define write_lock_irqsave(lock, flags) _write_lock_irqsave(lock, flags) +#define spin_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + _spin_lock_irqsave(lock, flags); \ + } while (0) +#define read_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + _read_lock_irqsave(lock, flags); \ + } while (0) +#define write_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + _write_lock_irqsave(lock, flags); \ + } while (0) #define spin_lock_irqsave_nested(lock, flags, subclass) \ spin_lock_irqsave(lock, flags) @@ -260,16 +291,25 @@ do { \ } while (0) #endif -#define spin_unlock_irqrestore(lock, flags) \ - _spin_unlock_irqrestore(lock, flags) +#define spin_unlock_irqrestore(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + _spin_unlock_irqrestore(lock, flags); \ + } while (0) #define spin_unlock_bh(lock) _spin_unlock_bh(lock) -#define read_unlock_irqrestore(lock, flags) \ - _read_unlock_irqrestore(lock, flags) +#define read_unlock_irqrestore(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + _read_unlock_irqrestore(lock, flags); \ + } while (0) #define read_unlock_bh(lock) _read_unlock_bh(lock) -#define write_unlock_irqrestore(lock, flags) \ - _write_unlock_irqrestore(lock, flags) +#define write_unlock_irqrestore(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + _write_unlock_irqrestore(lock, flags); \ + } while (0) #define write_unlock_bh(lock) _write_unlock_bh(lock) #define spin_trylock_bh(lock) __cond_lock(lock, _spin_trylock_bh(lock)) -- cgit v1.2.3 From 8b5ac31e27135a6f2c210c40d03bf8f1b3a86b77 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Fri, 25 Jul 2008 01:45:26 -0700 Subject: include: use get/put_unaligned_* helpers Signed-off-by: Harvey Harrison Cc: "John W. Linville" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 4 ++-- include/linux/smb_fs.h | 19 +++++++------------ 2 files changed, 9 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 4aacaeecb56f..e9963af16cda 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -526,8 +526,8 @@ struct item_head { ** p is the array of __u32, i is the index into the array, v is the value ** to store there. */ -#define get_block_num(p, i) le32_to_cpu(get_unaligned((p) + (i))) -#define put_block_num(p, i, v) put_unaligned(cpu_to_le32(v), (p) + (i)) +#define get_block_num(p, i) get_unaligned_le32((p) + (i)) +#define put_block_num(p, i, v) put_unaligned_le32((v), (p) + (i)) // // in old version uniqueness field shows key type diff --git a/include/linux/smb_fs.h b/include/linux/smb_fs.h index 2c5cd55f44ff..923cd8a247b1 100644 --- a/include/linux/smb_fs.h +++ b/include/linux/smb_fs.h @@ -43,18 +43,13 @@ static inline struct smb_inode_info *SMB_I(struct inode *inode) } /* macro names are short for word, double-word, long value (?) */ -#define WVAL(buf,pos) \ - (le16_to_cpu(get_unaligned((__le16 *)((u8 *)(buf) + (pos))))) -#define DVAL(buf,pos) \ - (le32_to_cpu(get_unaligned((__le32 *)((u8 *)(buf) + (pos))))) -#define LVAL(buf,pos) \ - (le64_to_cpu(get_unaligned((__le64 *)((u8 *)(buf) + (pos))))) -#define WSET(buf,pos,val) \ - put_unaligned(cpu_to_le16((u16)(val)), (__le16 *)((u8 *)(buf) + (pos))) -#define DSET(buf,pos,val) \ - put_unaligned(cpu_to_le32((u32)(val)), (__le32 *)((u8 *)(buf) + (pos))) -#define LSET(buf,pos,val) \ - put_unaligned(cpu_to_le64((u64)(val)), (__le64 *)((u8 *)(buf) + (pos))) +#define WVAL(buf, pos) (get_unaligned_le16((u8 *)(buf) + (pos))) +#define DVAL(buf, pos) (get_unaligned_le32((u8 *)(buf) + (pos))) +#define LVAL(buf, pos) (get_unaligned_le64((u8 *)(buf) + (pos))) + +#define WSET(buf, pos, val) put_unaligned_le16((val), (u8 *)(buf) + (pos)) +#define DSET(buf, pos, val) put_unaligned_le32((val), (u8 *)(buf) + (pos)) +#define LSET(buf, pos, val) put_unaligned_le64((val), (u8 *)(buf) + (pos)) /* where to find the base of the SMB packet proper */ #define smb_base(buf) ((u8 *)(((u8 *)(buf))+4)) -- cgit v1.2.3 From b39c08cb692cb8898c30e0d8187c7cbe27cc905c Mon Sep 17 00:00:00 2001 From: "Robert P. J. Day" Date: Fri, 25 Jul 2008 01:45:29 -0700 Subject: Remove apparently unused fd1772.h header file. This header file has been unused for quite some time, and the corresponding source files appear to have been removed back in commit 99eb8a550dbccc0e1f6c7e866fe421810e0585f6 ("Remove the arm26 port") Signed-off-by: Robert P. J. Day Cc: Adrian Bunk Cc: Ian Molton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fd1772.h | 80 -------------------------------------------------- 1 file changed, 80 deletions(-) delete mode 100644 include/linux/fd1772.h (limited to 'include/linux') diff --git a/include/linux/fd1772.h b/include/linux/fd1772.h deleted file mode 100644 index 871d6e4c677e..000000000000 --- a/include/linux/fd1772.h +++ /dev/null @@ -1,80 +0,0 @@ -#ifndef _LINUX_FD1772REG_H -#define _LINUX_FD1772REG_H - -/* -** WD1772 stuff - originally from the M68K Linux - * Modified for Archimedes by Dave Gilbert (gilbertd@cs.man.ac.uk) - */ - -/* register codes */ - -#define FDC1772SELREG_STP (0x80) /* command/status register */ -#define FDC1772SELREG_TRA (0x82) /* track register */ -#define FDC1772SELREG_SEC (0x84) /* sector register */ -#define FDC1772SELREG_DTA (0x86) /* data register */ - -/* register names for FDC1772_READ/WRITE macros */ - -#define FDC1772REG_CMD 0 -#define FDC1772REG_STATUS 0 -#define FDC1772REG_TRACK 2 -#define FDC1772REG_SECTOR 4 -#define FDC1772REG_DATA 6 - -/* command opcodes */ - -#define FDC1772CMD_RESTORE (0x00) /* - */ -#define FDC1772CMD_SEEK (0x10) /* | */ -#define FDC1772CMD_STEP (0x20) /* | TYP 1 Commands */ -#define FDC1772CMD_STIN (0x40) /* | */ -#define FDC1772CMD_STOT (0x60) /* - */ -#define FDC1772CMD_RDSEC (0x80) /* - TYP 2 Commands */ -#define FDC1772CMD_WRSEC (0xa0) /* - " */ -#define FDC1772CMD_RDADR (0xc0) /* - */ -#define FDC1772CMD_RDTRA (0xe0) /* | TYP 3 Commands */ -#define FDC1772CMD_WRTRA (0xf0) /* - */ -#define FDC1772CMD_FORCI (0xd0) /* - TYP 4 Command */ - -/* command modifier bits */ - -#define FDC1772CMDADD_SR6 (0x00) /* step rate settings */ -#define FDC1772CMDADD_SR12 (0x01) -#define FDC1772CMDADD_SR2 (0x02) -#define FDC1772CMDADD_SR3 (0x03) -#define FDC1772CMDADD_V (0x04) /* verify */ -#define FDC1772CMDADD_H (0x08) /* wait for spin-up */ -#define FDC1772CMDADD_U (0x10) /* update track register */ -#define FDC1772CMDADD_M (0x10) /* multiple sector access */ -#define FDC1772CMDADD_E (0x04) /* head settling flag */ -#define FDC1772CMDADD_P (0x02) /* precompensation */ -#define FDC1772CMDADD_A0 (0x01) /* DAM flag */ - -/* status register bits */ - -#define FDC1772STAT_MOTORON (0x80) /* motor on */ -#define FDC1772STAT_WPROT (0x40) /* write protected (FDC1772CMD_WR*) */ -#define FDC1772STAT_SPINUP (0x20) /* motor speed stable (Type I) */ -#define FDC1772STAT_DELDAM (0x20) /* sector has deleted DAM (Type II+III) */ -#define FDC1772STAT_RECNF (0x10) /* record not found */ -#define FDC1772STAT_CRC (0x08) /* CRC error */ -#define FDC1772STAT_TR00 (0x04) /* Track 00 flag (Type I) */ -#define FDC1772STAT_LOST (0x04) /* Lost Data (Type II+III) */ -#define FDC1772STAT_IDX (0x02) /* Index status (Type I) */ -#define FDC1772STAT_DRQ (0x02) /* DRQ status (Type II+III) */ -#define FDC1772STAT_BUSY (0x01) /* FDC1772 is busy */ - - -/* PSG Port A Bit Nr 0 .. Side Sel .. 0 -> Side 1 1 -> Side 2 */ -#define DSKSIDE (0x01) - -#define DSKDRVNONE (0x06) -#define DSKDRV0 (0x02) -#define DSKDRV1 (0x04) - -/* step rates */ -#define FDC1772STEP_6 0x00 -#define FDC1772STEP_12 0x01 -#define FDC1772STEP_2 0x02 -#define FDC1772STEP_3 0x03 - -#endif -- cgit v1.2.3 From e0ce0da9fefcc723dc006c35a7f91a32750abd40 Mon Sep 17 00:00:00 2001 From: "Robert P. J. Day" Date: Fri, 25 Jul 2008 01:45:32 -0700 Subject: lists: remove a redundant conditional definition of list_add() Remove the conditional surrounding the definition of list_add() from list.h since, if you define CONFIG_DEBUG_LIST, the definition you will subsequently pick up from lib/list_debug.c will be absolutely identical, at which point you can remove that redundant definition from list_debug.c as well. Signed-off-by: Robert P. J. Day Cc: Dave Jones Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 139ec41d9c2e..453916bc0412 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -61,14 +61,10 @@ extern void __list_add(struct list_head *new, * Insert a new entry after the specified head. * This is good for implementing stacks. */ -#ifndef CONFIG_DEBUG_LIST static inline void list_add(struct list_head *new, struct list_head *head) { __list_add(new, head, head->next); } -#else -extern void list_add(struct list_head *new, struct list_head *head); -#endif /** -- cgit v1.2.3 From b03f6489f9f27dc519a4c60ebf39cc7b8a58eae7 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 01:45:35 -0700 Subject: build kernel/profile.o only when requested Build kernel/profile.o only if CONFIG_PROFILING is enabled. This makes CONFIG_PROFILING=n kernels smaller. As a bonus, some profile_tick() calls and one branch from schedule() are now eliminated with CONFIG_PROFILING=n (but I doubt these are measurable effects). This patch changes the effects of CONFIG_PROFILING=n, but I don't think having more than two choices would be the better choice. This patch also adds the name of the first parameter to the prototypes of profile_{hits,tick}() since I anyway had to add them for the dummy functions. Signed-off-by: Adrian Bunk Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/profile.h | 56 ++++++++++++++++++++++++++++++++++--------------- 1 file changed, 39 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/profile.h b/include/linux/profile.h index 05c1cc736937..4081fa31081f 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -8,8 +8,6 @@ #include -extern int prof_on __read_mostly; - #define CPU_PROFILING 1 #define SCHED_PROFILING 2 #define SLEEP_PROFILING 3 @@ -19,14 +17,29 @@ struct proc_dir_entry; struct pt_regs; struct notifier_block; +#if defined(CONFIG_PROFILING) && defined(CONFIG_PROC_FS) +void create_prof_cpu_mask(struct proc_dir_entry *); +#else +#define create_prof_cpu_mask(x) do { (void)(x); } while (0) +#endif + +enum profile_type { + PROFILE_TASK_EXIT, + PROFILE_MUNMAP +}; + +#ifdef CONFIG_PROFILING + +extern int prof_on __read_mostly; + /* init basic kernel profiler */ void __init profile_init(void); -void profile_tick(int); +void profile_tick(int type); /* * Add multiple profiler hits to a given address: */ -void profile_hits(int, void *ip, unsigned int nr_hits); +void profile_hits(int type, void *ip, unsigned int nr_hits); /* * Single profiler hit: @@ -40,19 +53,6 @@ static inline void profile_hit(int type, void *ip) profile_hits(type, ip, 1); } -#ifdef CONFIG_PROC_FS -void create_prof_cpu_mask(struct proc_dir_entry *); -#else -#define create_prof_cpu_mask(x) do { (void)(x); } while (0) -#endif - -enum profile_type { - PROFILE_TASK_EXIT, - PROFILE_MUNMAP -}; - -#ifdef CONFIG_PROFILING - struct task_struct; struct mm_struct; @@ -80,6 +80,28 @@ struct pt_regs; #else +#define prof_on 0 + +static inline void profile_init(void) +{ + return; +} + +static inline void profile_tick(int type) +{ + return; +} + +static inline void profile_hits(int type, void *ip, unsigned int nr_hits) +{ + return; +} + +static inline void profile_hit(int type, void *ip) +{ + return; +} + static inline int task_handoff_register(struct notifier_block * n) { return -ENOSYS; -- cgit v1.2.3 From cebbd3fb803603b12408458ba17c29ce1e15a5f2 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 25 Jul 2008 01:45:35 -0700 Subject: build-kernel-profileo-only-when-requested-cleanups Cc: Adrian Bunk Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/profile.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/profile.h b/include/linux/profile.h index 4081fa31081f..7e7087239af5 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -18,9 +18,11 @@ struct pt_regs; struct notifier_block; #if defined(CONFIG_PROFILING) && defined(CONFIG_PROC_FS) -void create_prof_cpu_mask(struct proc_dir_entry *); +void create_prof_cpu_mask(struct proc_dir_entry *de); #else -#define create_prof_cpu_mask(x) do { (void)(x); } while (0) +static inline void create_prof_cpu_mask(struct proc_dir_entry *de) +{ +} #endif enum profile_type { -- cgit v1.2.3 From ac331d158e198d2a91a5b0a3ec4ca9991fdb57af Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Fri, 25 Jul 2008 01:45:38 -0700 Subject: call_usermodehelper(): increase reliability Presently call_usermodehelper_setup() uses GFP_ATOMIC. but it can return NULL _very_ easily. GFP_ATOMIC is needed only when we can't sleep. and, GFP_KERNEL is robust and better. thus, I add gfp_mask argument to call_usermodehelper_setup(). So, its callers pass the gfp_t as below: call_usermodehelper() and call_usermodehelper_keys(): depend on 'wait' argument. call_usermodehelper_pipe(): always GFP_KERNEL because always run under process context. orderly_poweroff(): pass to GFP_ATOMIC because may run under interrupt context. Signed-off-by: KOSAKI Motohiro Cc: "Paul Menage" Reviewed-by: Li Zefan Acked-by: Jeremy Fitzhardinge Cc: Rusty Russell Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kmod.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 0509c4ce4857..a1a91577813c 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -19,6 +19,7 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ +#include #include #include #include @@ -41,8 +42,8 @@ struct file; struct subprocess_info; /* Allocate a subprocess_info structure */ -struct subprocess_info *call_usermodehelper_setup(char *path, - char **argv, char **envp); +struct subprocess_info *call_usermodehelper_setup(char *path, char **argv, + char **envp, gfp_t gfp_mask); /* Set various pieces of state into the subprocess_info structure */ void call_usermodehelper_setkeys(struct subprocess_info *info, @@ -69,8 +70,9 @@ static inline int call_usermodehelper(char *path, char **argv, char **envp, enum umh_wait wait) { struct subprocess_info *info; + gfp_t gfp_mask = (wait == UMH_NO_WAIT) ? GFP_ATOMIC : GFP_KERNEL; - info = call_usermodehelper_setup(path, argv, envp); + info = call_usermodehelper_setup(path, argv, envp, gfp_mask); if (info == NULL) return -ENOMEM; return call_usermodehelper_exec(info, wait); @@ -81,8 +83,9 @@ call_usermodehelper_keys(char *path, char **argv, char **envp, struct key *session_keyring, enum umh_wait wait) { struct subprocess_info *info; + gfp_t gfp_mask = (wait == UMH_NO_WAIT) ? GFP_ATOMIC : GFP_KERNEL; - info = call_usermodehelper_setup(path, argv, envp); + info = call_usermodehelper_setup(path, argv, envp, gfp_mask); if (info == NULL) return -ENOMEM; -- cgit v1.2.3 From 4500d067eeb3d00679335d9cf5c6536e79cd3ef4 Mon Sep 17 00:00:00 2001 From: "Robert P. J. Day" Date: Fri, 25 Jul 2008 01:45:49 -0700 Subject: init.h: remove obsolete content Remove apparently obsolete content from init.h referring to gcc 2.9x and to "no_module_init". Signed-off-by: Robert P. J. Day Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index 21d658cdfa27..42ae95411a93 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -275,13 +275,7 @@ void __init parse_early_param(void); #define security_initcall(fn) module_init(fn) -/* These macros create a dummy inline: gcc 2.9x does not count alias - as usage, hence the `unused function' warning when __init functions - are declared static. We use the dummy __*_module_inline functions - both to kill the warning and check the type of the init/cleanup - function. */ - -/* Each module must use one module_init(), or one no_module_init */ +/* Each module must use one module_init(). */ #define module_init(initfn) \ static inline initcall_t __inittest(void) \ { return initfn; } \ -- cgit v1.2.3 From b6c63937001889af6fe431aaba97e59d04e028e7 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Fri, 25 Jul 2008 01:45:52 -0700 Subject: Rename WARN() to WARNING() to clear the namespace We want to use WARN() as a variant of WARN_ON(), however a few drivers are using WARN() internally. This patch renames these to WARNING() to avoid the namespace clash. A few cases were defining but not using the thing, for those cases I just deleted the definition. Signed-off-by: Arjan van de Ven Acked-by: Greg KH Cc: Karsten Keil Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/usb/composite.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 747c3a49cdc9..c932390c6da0 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -330,7 +330,7 @@ extern int usb_string_id(struct usb_composite_dev *c); dev_vdbg(&(d)->gadget->dev , fmt , ## args) #define ERROR(d, fmt, args...) \ dev_err(&(d)->gadget->dev , fmt , ## args) -#define WARN(d, fmt, args...) \ +#define WARNING(d, fmt, args...) \ dev_warn(&(d)->gadget->dev , fmt , ## args) #define INFO(d, fmt, args...) \ dev_info(&(d)->gadget->dev , fmt , ## args) -- cgit v1.2.3 From 2711b793eb62a5873a0ba583a69252040aef176e Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Fri, 25 Jul 2008 01:45:56 -0700 Subject: kallsyms: unify 32- and 64-bit code Use the %p format string which already accounts for the padding you need with a pointer type on a particular architecture. Also replace the macro with a static inline function to match the rest of the file. Cc: Heiko Carstens Cc: Arjan van de Ven Signed-off-by: Vegard Nossum Cc: Sam Ravnborg Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kallsyms.h | 19 ++++++------------- 1 file changed, 6 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 00c1801099fa..57aefa160a92 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -6,6 +6,7 @@ #define _LINUX_KALLSYMS_H #include +#include #include #define KSYM_NAME_LEN 128 @@ -105,18 +106,10 @@ static inline void print_fn_descriptor_symbol(const char *fmt, void *addr) print_symbol(fmt, (unsigned long)addr); } -#ifndef CONFIG_64BIT -#define print_ip_sym(ip) \ -do { \ - printk("[<%08lx>]", ip); \ - print_symbol(" %s\n", ip); \ -} while(0) -#else -#define print_ip_sym(ip) \ -do { \ - printk("[<%016lx>]", ip); \ - print_symbol(" %s\n", ip); \ -} while(0) -#endif +static inline void print_ip_sym(unsigned long ip) +{ + printk("[<%p>]", (void *) ip); + print_symbol(" %s\n", ip); +} #endif /*_LINUX_KALLSYMS_H*/ -- cgit v1.2.3 From 717115e1a5856b57af0f71e1df7149108294fc10 Mon Sep 17 00:00:00 2001 From: Dave Young Date: Fri, 25 Jul 2008 01:45:58 -0700 Subject: printk ratelimiting rewrite All ratelimit user use same jiffies and burst params, so some messages (callbacks) will be lost. For example: a call printk_ratelimit(5 * HZ, 1) b call printk_ratelimit(5 * HZ, 1) before the 5*HZ timeout of a, then b will will be supressed. - rewrite __ratelimit, and use a ratelimit_state as parameter. Thanks for hints from andrew. - Add WARN_ON_RATELIMIT, update rcupreempt.h - remove __printk_ratelimit - use __ratelimit in net_ratelimit Signed-off-by: Dave Young Cc: "David S. Miller" Cc: "Paul E. McKenney" Cc: Dave Young Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 8 ++------ include/linux/net.h | 3 +-- include/linux/ratelimit.h | 27 +++++++++++++++++++++++++++ include/linux/rcupreempt.h | 9 +++++++-- 4 files changed, 37 insertions(+), 10 deletions(-) create mode 100644 include/linux/ratelimit.h (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 5c4b1251e110..fdbbf72ca2eb 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -189,11 +190,8 @@ asmlinkage int vprintk(const char *fmt, va_list args) asmlinkage int printk(const char * fmt, ...) __attribute__ ((format (printf, 1, 2))) __cold; -extern int printk_ratelimit_jiffies; -extern int printk_ratelimit_burst; +extern struct ratelimit_state printk_ratelimit_state; extern int printk_ratelimit(void); -extern int __ratelimit(int ratelimit_jiffies, int ratelimit_burst); -extern int __printk_ratelimit(int ratelimit_jiffies, int ratelimit_burst); extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec); #else @@ -204,8 +202,6 @@ static inline int printk(const char *s, ...) __attribute__ ((format (printf, 1, 2))); static inline int __cold printk(const char *s, ...) { return 0; } static inline int printk_ratelimit(void) { return 0; } -static inline int __printk_ratelimit(int ratelimit_jiffies, \ - int ratelimit_burst) { return 0; } static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, \ unsigned int interval_msec) \ { return false; } diff --git a/include/linux/net.h b/include/linux/net.h index 2f999fbb188d..4a9a30f2d68f 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -351,8 +351,7 @@ static const struct proto_ops name##_ops = { \ #ifdef CONFIG_SYSCTL #include -extern int net_msg_cost; -extern int net_msg_burst; +extern struct ratelimit_state net_ratelimit_state; #endif #endif /* __KERNEL__ */ diff --git a/include/linux/ratelimit.h b/include/linux/ratelimit.h new file mode 100644 index 000000000000..18a5b9ba9d40 --- /dev/null +++ b/include/linux/ratelimit.h @@ -0,0 +1,27 @@ +#ifndef _LINUX_RATELIMIT_H +#define _LINUX_RATELIMIT_H +#include + +#define DEFAULT_RATELIMIT_INTERVAL (5 * HZ) +#define DEFAULT_RATELIMIT_BURST 10 + +struct ratelimit_state { + int interval; + int burst; + int printed; + int missed; + unsigned long begin; +}; + +#define DEFINE_RATELIMIT_STATE(name, interval, burst) \ + struct ratelimit_state name = {interval, burst,} + +extern int __ratelimit(struct ratelimit_state *rs); + +static inline int ratelimit(void) +{ + static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + return __ratelimit(&rs); +} +#endif diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h index f04b64eca636..0967f03b0705 100644 --- a/include/linux/rcupreempt.h +++ b/include/linux/rcupreempt.h @@ -115,16 +115,21 @@ DECLARE_PER_CPU(struct rcu_dyntick_sched, rcu_dyntick_sched); static inline void rcu_enter_nohz(void) { + static DEFINE_RATELIMIT_STATE(rs, 10 * HZ, 1); + smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */ __get_cpu_var(rcu_dyntick_sched).dynticks++; - WARN_ON(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1); + WARN_ON_RATELIMIT(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1, &rs); } static inline void rcu_exit_nohz(void) { + static DEFINE_RATELIMIT_STATE(rs, 10 * HZ, 1); + smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */ __get_cpu_var(rcu_dyntick_sched).dynticks++; - WARN_ON(!(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1)); + WARN_ON_RATELIMIT(!(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1), + &rs); } #else /* CONFIG_NO_HZ */ -- cgit v1.2.3 From 472dba7d117844c746be97db6be26c2810d79b62 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Fri, 25 Jul 2008 01:45:58 -0700 Subject: sm501: add power control callback Add callback to get or set the power control if the device has the sleep connected to some form of GPIO. Signed-off-by: Ben Dooks Cc: Arnaud Patard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sm501.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sm501.h b/include/linux/sm501.h index b530fa6a1d34..145405bf9efa 100644 --- a/include/linux/sm501.h +++ b/include/linux/sm501.h @@ -157,6 +157,8 @@ struct sm501_init_gpio { struct sm501_reg_init gpio_ddr_high; }; +#define SM501_FLAG_SUSPEND_OFF (1<<4) + /* sm501_platdata * * This is passed with the platform device to allow the board @@ -170,6 +172,11 @@ struct sm501_platdata { struct sm501_init_gpio *init_gpiop; struct sm501_platdata_fb *fb; + int flags; + + int (*get_power)(struct device *dev); + int (*set_power)(struct device *dev, unsigned int on); + struct sm501_platdata_gpio_i2c *gpio_i2c; unsigned int gpio_i2c_nr; }; -- cgit v1.2.3 From f61be273d3699d174bc1438e6804f9f9e52bb932 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Fri, 25 Jul 2008 01:45:59 -0700 Subject: sm501: add gpiolib support Add support for exporting the GPIOs on the SM501 via gpiolib. Signed-off-by: Ben Dooks Cc: Arnaud Patard Cc: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sm501.h | 20 ++------------------ 1 file changed, 2 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sm501.h b/include/linux/sm501.h index 145405bf9efa..6ea39007c8a3 100644 --- a/include/linux/sm501.h +++ b/include/linux/sm501.h @@ -46,24 +46,6 @@ extern unsigned long sm501_modify_reg(struct device *dev, unsigned long set, unsigned long clear); -/* sm501_gpio_set - * - * set the state of the given GPIO line -*/ - -extern void sm501_gpio_set(struct device *dev, - unsigned long gpio, - unsigned int to, - unsigned int dir); - -/* sm501_gpio_get - * - * get the state of the given GPIO line -*/ - -extern unsigned long sm501_gpio_get(struct device *dev, - unsigned long gpio); - /* Platform data definitions */ @@ -131,6 +113,7 @@ struct sm501_reg_init { #define SM501_USE_FBACCEL (1<<6) #define SM501_USE_AC97 (1<<7) #define SM501_USE_I2S (1<<8) +#define SM501_USE_GPIO (1<<9) #define SM501_USE_ALL (0xffffffff) @@ -173,6 +156,7 @@ struct sm501_platdata { struct sm501_platdata_fb *fb; int flags; + unsigned gpio_base; int (*get_power)(struct device *dev); int (*set_power)(struct device *dev, unsigned int on); -- cgit v1.2.3 From 60e540d617b40eb3d37f1dd99c97af588ff9b70b Mon Sep 17 00:00:00 2001 From: Arnaud Patard Date: Fri, 25 Jul 2008 01:46:00 -0700 Subject: sm501: gpio dynamic registration for PCI devices The SM501 PCI card requires a dyanmic gpio allocation as the number of cards is not known at compile time. Fixup the platform data and registration to deal with this. Acked-by: Ben Dooks Signed-off-by: Arnaud Patard Cc: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sm501.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sm501.h b/include/linux/sm501.h index 6ea39007c8a3..a8d02f36ad32 100644 --- a/include/linux/sm501.h +++ b/include/linux/sm501.h @@ -156,7 +156,7 @@ struct sm501_platdata { struct sm501_platdata_fb *fb; int flags; - unsigned gpio_base; + int gpio_base; int (*get_power)(struct device *dev); int (*set_power)(struct device *dev, unsigned int on); -- cgit v1.2.3 From 42cd2366fb9b58cdfc1855be32b31a78e40b2079 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Fri, 25 Jul 2008 01:46:01 -0700 Subject: sm501: gpio I2C support Add support for adding the GPIO based I2C resources. Signed-off-by: Ben Dooks Cc: Arnaud Patard Cc: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sm501.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sm501.h b/include/linux/sm501.h index a8d02f36ad32..214f93209b8c 100644 --- a/include/linux/sm501.h +++ b/include/linux/sm501.h @@ -86,11 +86,19 @@ struct sm501_platdata_fb { struct sm501_platdata_fbsub *fb_pnl; }; -/* gpio i2c */ +/* gpio i2c + * + * Note, we have to pass in the bus number, as the number used will be + * passed to the i2c-gpio driver's platform_device.id, subsequently used + * to register the i2c bus. +*/ struct sm501_platdata_gpio_i2c { + unsigned int bus_num; unsigned int pin_sda; unsigned int pin_scl; + int udelay; + int timeout; }; /* sm501_initdata -- cgit v1.2.3 From ef53d9c5e4da147ecaa43c44c5e5945eb83970a2 Mon Sep 17 00:00:00 2001 From: Srinivasa D S Date: Fri, 25 Jul 2008 01:46:04 -0700 Subject: kprobes: improve kretprobe scalability with hashed locking Currently list of kretprobe instances are stored in kretprobe object (as used_instances,free_instances) and in kretprobe hash table. We have one global kretprobe lock to serialise the access to these lists. This causes only one kretprobe handler to execute at a time. Hence affects system performance, particularly on SMP systems and when return probe is set on lot of functions (like on all systemcalls). Solution proposed here gives fine-grain locks that performs better on SMP system compared to present kretprobe implementation. Solution: 1) Instead of having one global lock to protect kretprobe instances present in kretprobe object and kretprobe hash table. We will have two locks, one lock for protecting kretprobe hash table and another lock for kretporbe object. 2) We hold lock present in kretprobe object while we modify kretprobe instance in kretprobe object and we hold per-hash-list lock while modifying kretprobe instances present in that hash list. To prevent deadlock, we never grab a per-hash-list lock while holding a kretprobe lock. 3) We can remove used_instances from struct kretprobe, as we can track used instances of kretprobe instances using kretprobe hash table. Time duration for kernel compilation ("make -j 8") on a 8-way ppc64 system with return probes set on all systemcalls looks like this. cacheline non-cacheline Un-patched kernel aligned patch aligned patch =============================================================================== real 9m46.784s 9m54.412s 10m2.450s user 40m5.715s 40m7.142s 40m4.273s sys 2m57.754s 2m58.583s 3m17.430s =========================================================== Time duration for kernel compilation ("make -j 8) on the same system, when kernel is not probed. ========================= real 9m26.389s user 40m8.775s sys 2m7.283s ========================= Signed-off-by: Srinivasa DS Signed-off-by: Jim Keniston Acked-by: Ananth N Mavinakayanahalli Cc: Anil S Keshavamurthy Cc: David S. Miller Cc: Masami Hiramatsu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kprobes.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 04a3556bdea6..0be7795655fa 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -157,11 +157,10 @@ struct kretprobe { int nmissed; size_t data_size; struct hlist_head free_instances; - struct hlist_head used_instances; + spinlock_t lock; }; struct kretprobe_instance { - struct hlist_node uflist; /* either on free list or used list */ struct hlist_node hlist; struct kretprobe *rp; kprobe_opcode_t *ret_addr; @@ -201,7 +200,6 @@ static inline int init_test_probes(void) } #endif /* CONFIG_KPROBES_SANITY_TEST */ -extern spinlock_t kretprobe_lock; extern struct mutex kprobe_mutex; extern int arch_prepare_kprobe(struct kprobe *p); extern void arch_arm_kprobe(struct kprobe *p); @@ -214,6 +212,9 @@ extern void kprobes_inc_nmissed_count(struct kprobe *p); /* Get the kprobe at this addr (if any) - called with preemption disabled */ struct kprobe *get_kprobe(void *addr); +void kretprobe_hash_lock(struct task_struct *tsk, + struct hlist_head **head, unsigned long *flags); +void kretprobe_hash_unlock(struct task_struct *tsk, unsigned long *flags); struct hlist_head * kretprobe_inst_table_head(struct task_struct *tsk); /* kprobe_running() will just return the current_kprobe on this CPU */ -- cgit v1.2.3 From d8f388d8dc8d4f36539dd37c1fff62cc404ea0fc Mon Sep 17 00:00:00 2001 From: David Brownell Date: Fri, 25 Jul 2008 01:46:07 -0700 Subject: gpio: sysfs interface This adds a simple sysfs interface for GPIOs. /sys/class/gpio /export ... asks the kernel to export a GPIO to userspace /unexport ... to return a GPIO to the kernel /gpioN ... for each exported GPIO #N /value ... always readable, writes fail for input GPIOs /direction ... r/w as: in, out (default low); write high, low /gpiochipN ... for each gpiochip; #N is its first GPIO /base ... (r/o) same as N /label ... (r/o) descriptive, not necessarily unique /ngpio ... (r/o) number of GPIOs; numbered N .. N+(ngpio - 1) GPIOs claimed by kernel code may be exported by its owner using a new gpio_export() call, which should be most useful for driver debugging. Such exports may optionally be done without a "direction" attribute. Userspace may ask to take over a GPIO by writing to a sysfs control file, helping to cope with incomplete board support or other "one-off" requirements that don't merit full kernel support: echo 23 > /sys/class/gpio/export ... will gpio_request(23, "sysfs") and gpio_export(23); use /sys/class/gpio/gpio-23/direction to (re)configure it, when that GPIO can be used as both input and output. echo 23 > /sys/class/gpio/unexport ... will gpio_free(23), when it was exported as above The extra D-space footprint is a few hundred bytes, except for the sysfs resources associated with each exported GPIO. The additional I-space footprint is about two thirds of the current size of gpiolib (!). Since no /dev node creation is involved, no "udev" support is needed. Related changes: * This adds a device pointer to "struct gpio_chip". When GPIO providers initialize that, sysfs gpio class devices become children of that device instead of being "virtual" devices. * The (few) gpio_chip providers which have such a device node have been updated. * Some gpio_chip drivers also needed to update their module "owner" field ... for which missing kerneldoc was added. * Some gpio_chips don't support input GPIOs. Those GPIOs are now flagged appropriately when the chip is registered. Based on previous patches, and discussion both on and off LKML. A Documentation/ABI/testing/sysfs-gpio update is ready to submit once this merges to mainline. [akpm@linux-foundation.org: a few maintenance build fixes] Signed-off-by: David Brownell Cc: Guennadi Liakhovetski Cc: Greg KH Cc: Kay Sievers Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gpio.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 98be6c5762b9..730a20b83576 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -79,6 +79,19 @@ static inline void gpio_set_value_cansleep(unsigned gpio, int value) WARN_ON(1); } +static inline int gpio_export(unsigned gpio, bool direction_may_change) +{ + /* GPIO can never have been requested or set as {in,out}put */ + WARN_ON(1); + return -EINVAL; +} + +static inline void gpio_unexport(unsigned gpio) +{ + /* GPIO can never have been exported */ + WARN_ON(1); +} + static inline int gpio_to_irq(unsigned gpio) { /* GPIO can never have been requested or set as input */ -- cgit v1.2.3 From 8f1cc3b10e6ee0c5c7c8ed27f8771c4f252b4862 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Fri, 25 Jul 2008 01:46:09 -0700 Subject: gpio: mcp23s08 handles multiple chips per chipselect Teach the mcp23s08 driver about a curious feature of these chips: up to four of them can share the same chipselect, with the SPI signals wired in parallel, by matching two bits in the first protocol byte against two address lines on the chip. This is handled by three software changes: * Platform data now holds an array of per-chip structs, not just one chip's address and pullup configuration. * Probe() and remove() now use another level of structure, wrapping an instance of the original structure for each mcp23s08 chip sharing that chipselect. * The HAEN bit is set, so that the hardware address bits can no longer be ignored (boot firmware may not have enabled them). The "one struct per chip" preserves the guts of the current code, but platform_data will need minor changes. OLD: /* incorrect "slave" ID may not have mattered */ .slave = 3, .pullups = BIT(3) | BIT(1) | BIT(0), NEW: /* slave address _must_ match chip's wiring */ .chip[3] = { .is_present = true, .pullups = BIT(3) | BIT(1) | BIT(0), }, There's no change in how things _behave_ for spi_device nodes with a single mcp23s08 chip. New multi-chip configurations assign GPIOs in sequence, without holes. The spi_device just resembles a bigger controller, but internally it has multiple gpio_chip instances. Signed-off-by: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/spi/mcp23s08.h | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/mcp23s08.h b/include/linux/spi/mcp23s08.h index 835ddf47d45c..22ef107d7704 100644 --- a/include/linux/spi/mcp23s08.h +++ b/include/linux/spi/mcp23s08.h @@ -1,18 +1,25 @@ -/* FIXME driver should be able to handle all four slaves that - * can be hooked up to each chipselect, as well as IRQs... - */ +/* FIXME driver should be able to handle IRQs... */ + +struct mcp23s08_chip_info { + bool is_present; /* true iff populated */ + u8 pullups; /* BIT(x) means enable pullup x */ +}; struct mcp23s08_platform_data { - /* four slaves can share one SPI chipselect */ - u8 slave; + /* Four slaves (numbered 0..3) can share one SPI chipselect, and + * will provide 8..32 GPIOs using 1..4 gpio_chip instances. + */ + struct mcp23s08_chip_info chip[4]; - /* number assigned to the first GPIO */ + /* "base" is the number of the first GPIO. Dynamic assignment is + * not currently supported, and even if there are gaps in chip + * addressing the GPIO numbers are sequential .. so for example + * if only slaves 0 and 3 are present, their GPIOs range from + * base to base+15. + */ unsigned base; - /* pins with pullups */ - u8 pullups; - void *context; /* param to setup/teardown */ int (*setup)(struct spi_device *spi, -- cgit v1.2.3 From bbcd6d543de335bf81e96477f46a60a8bf51039c Mon Sep 17 00:00:00 2001 From: Eric Miao Date: Fri, 25 Jul 2008 01:46:14 -0700 Subject: gpio: max732x driver This adds a driver supporting a family of I2C port expanders from Maxim, which includes the MAX7319 and MAX7320-7327 chips. [dbrownell@users.sourceforge.net: minor fixes] Signed-off-by: Jack Ren Signed-off-by: Eric Miao Acked-by: Jean Delvare Signed-off-by: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/i2c/max732x.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 include/linux/i2c/max732x.h (limited to 'include/linux') diff --git a/include/linux/i2c/max732x.h b/include/linux/i2c/max732x.h new file mode 100644 index 000000000000..e10336631c62 --- /dev/null +++ b/include/linux/i2c/max732x.h @@ -0,0 +1,19 @@ +#ifndef __LINUX_I2C_MAX732X_H +#define __LINUX_I2C_MAX732X_H + +/* platform data for the MAX732x 8/16-bit I/O expander driver */ + +struct max732x_platform_data { + /* number of the first GPIO */ + unsigned gpio_base; + + void *context; /* param to setup/teardown */ + + int (*setup)(struct i2c_client *client, + unsigned gpio, unsigned ngpio, + void *context); + int (*teardown)(struct i2c_client *client, + unsigned gpio, unsigned ngpio, + void *context); +}; +#endif /* __LINUX_I2C_MAX732X_H */ -- cgit v1.2.3 From 50c33a84db4aa5082e3af8d873b22344ae2ebea8 Mon Sep 17 00:00:00 2001 From: Samuel Thibault Date: Fri, 25 Jul 2008 01:46:16 -0700 Subject: ext2: fix typo in Hurd part of include/linux/ext2_fs.h Fix typo in Hurd part of include/linux/ext2_fs.h The ';' here is redundant or can even pose problem. This is actually not used by the Linux kernel, but it is exposed in GNU/Hurd. Signed-off-by: Samuel Thibault Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext2_fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext2_fs.h b/include/linux/ext2_fs.h index 84cec2aa9f1e..2efe7b863cff 100644 --- a/include/linux/ext2_fs.h +++ b/include/linux/ext2_fs.h @@ -284,8 +284,8 @@ struct ext2_inode { #ifdef __hurd__ #define i_translator osd1.hurd1.h_i_translator -#define i_frag osd2.hurd2.h_i_frag; -#define i_fsize osd2.hurd2.h_i_fsize; +#define i_frag osd2.hurd2.h_i_frag +#define i_fsize osd2.hurd2.h_i_fsize #define i_uid_high osd2.hurd2.h_i_uid_high #define i_gid_high osd2.hurd2.h_i_gid_high #define i_author osd2.hurd2.h_i_author -- cgit v1.2.3 From ae76dd9a6b5bbe5315fb7028e03f68f75b8538f3 Mon Sep 17 00:00:00 2001 From: Duane Griffin Date: Fri, 25 Jul 2008 01:46:23 -0700 Subject: ext3: handle corrupted orphan list at mount If the orphan node list includes valid, untruncatable nodes with nlink > 0 the ext3_orphan_cleanup loop which attempts to delete them will not do so, causing it to loop forever. Fix by checking for such nodes in the ext3_orphan_get function. This patch fixes the second case (image hdb.20000009.softlockup.gz) reported in http://bugzilla.kernel.org/show_bug.cgi?id=10882. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: printk warning fix] Signed-off-by: Duane Griffin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext3_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index 36c540396377..80171ee89a22 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -832,6 +832,7 @@ extern void ext3_discard_reservation (struct inode *); extern void ext3_dirty_inode(struct inode *); extern int ext3_change_inode_journal_flag(struct inode *, int); extern int ext3_get_inode_loc(struct inode *, struct ext3_iloc *); +extern int ext3_can_truncate(struct inode *inode); extern void ext3_truncate (struct inode *); extern void ext3_set_inode_flags(struct inode *); extern void ext3_get_inode_flags(struct ext3_inode_info *); -- cgit v1.2.3 From de0ca06a99c33df8333955642843331ab6b6e7ff Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 01:46:34 -0700 Subject: coda: remove CODA_FS_OLD_API While fixing CONFIG_ leakages to the userspace kernel headers I ran into CODA_FS_OLD_API. After five years, are there still people using the old API left? Especially considering that you have to choose at compile time which API to support in the kernel (and distributions tend to offer the new API for some time). Jan: "The old API can definitely go. Around the time the new interface went in there were some non-Coda userspace file system implementations that took a while longer to convert to the new API, but by now they all switched to the new interface or in some cases to a FUSE-based solution." Signed-off-by: Adrian Bunk Acked-by: Jan Harkes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/coda.h | 43 ------------------------------------------- 1 file changed, 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coda.h b/include/linux/coda.h index b5cf0780c51a..96c87693800b 100644 --- a/include/linux/coda.h +++ b/include/linux/coda.h @@ -199,28 +199,6 @@ typedef u_int32_t vuid_t; typedef u_int32_t vgid_t; #endif /*_VUID_T_ */ -#ifdef CONFIG_CODA_FS_OLD_API -struct CodaFid { - u_int32_t opaque[3]; -}; - -static __inline__ ino_t coda_f2i(struct CodaFid *fid) -{ - if ( ! fid ) - return 0; - if (fid->opaque[1] == 0xfffffffe || fid->opaque[1] == 0xffffffff) - return ((fid->opaque[0] << 20) | (fid->opaque[2] & 0xfffff)); - else - return (fid->opaque[2] + (fid->opaque[1]<<10) + (fid->opaque[0]<<20)); -} - -struct coda_cred { - vuid_t cr_uid, cr_euid, cr_suid, cr_fsuid; /* Real, efftve, set, fs uid*/ - vgid_t cr_groupid, cr_egid, cr_sgid, cr_fsgid; /* same for groups */ -}; - -#else /* not defined(CONFIG_CODA_FS_OLD_API) */ - struct CodaFid { u_int32_t opaque[4]; }; @@ -228,8 +206,6 @@ struct CodaFid { #define coda_f2i(fid)\ (fid ? (fid->opaque[3] ^ (fid->opaque[2]<<10) ^ (fid->opaque[1]<<20) ^ fid->opaque[0]) : 0) -#endif - #ifndef _VENUS_VATTR_T_ #define _VENUS_VATTR_T_ /* @@ -313,15 +289,7 @@ struct coda_statfs { #define CIOC_KERNEL_VERSION _IOWR('c', 10, size_t) -#if 0 -#define CODA_KERNEL_VERSION 0 /* don't care about kernel version number */ -#define CODA_KERNEL_VERSION 1 /* The old venus 4.6 compatible interface */ -#endif -#ifdef CONFIG_CODA_FS_OLD_API -#define CODA_KERNEL_VERSION 2 /* venus_lookup got an extra parameter */ -#else #define CODA_KERNEL_VERSION 3 /* 128-bit file identifiers */ -#endif /* * Venus <-> Coda RPC arguments @@ -329,16 +297,9 @@ struct coda_statfs { struct coda_in_hdr { u_int32_t opcode; u_int32_t unique; /* Keep multiple outstanding msgs distinct */ -#ifdef CONFIG_CODA_FS_OLD_API - u_int16_t pid; /* Common to all */ - u_int16_t pgid; /* Common to all */ - u_int16_t sid; /* Common to all */ - struct coda_cred cred; /* Common to all */ -#else pid_t pid; pid_t pgid; vuid_t uid; -#endif }; /* Really important that opcode and unique are 1st two fields! */ @@ -613,11 +574,7 @@ struct coda_vget_out { /* CODA_PURGEUSER is a venus->kernel call */ struct coda_purgeuser_out { struct coda_out_hdr oh; -#ifdef CONFIG_CODA_FS_OLD_API - struct coda_cred cred; -#else vuid_t uid; -#endif }; /* coda_zapfile: */ -- cgit v1.2.3 From f68215c4640a38d66429014e524a627bf572d26a Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Fri, 25 Jul 2008 01:46:38 -0700 Subject: reiserfs: convert j_lock to mutex j_lock is a semaphore but uses it as if it were a mutex. This patch converts it to a mutex. Signed-off-by: Jeff Mahoney Cc: Matthew Wilcox Cc: Chris Mason Cc: Edward Shishkin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs_sb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h index 336ee43ed7d8..49b639b88bac 100644 --- a/include/linux/reiserfs_fs_sb.h +++ b/include/linux/reiserfs_fs_sb.h @@ -193,7 +193,7 @@ struct reiserfs_journal { struct buffer_head *j_header_bh; time_t j_trans_start_time; /* time this transaction started */ - struct semaphore j_lock; + struct mutex j_mutex; struct semaphore j_flush_sem; wait_queue_head_t j_join_wait; /* wait for current transaction to finish before starting new one */ atomic_t j_jlock; /* lock for j_join_wait */ -- cgit v1.2.3 From afe70259076fff0446001eaa1a287f615241a357 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Fri, 25 Jul 2008 01:46:39 -0700 Subject: reiserfs: convert j_flush_sem to mutex j_flush_sem is a semaphore but uses it as if it were a mutex. This patch converts it to a mutex. [akpm@linux-foundation.org: fix mutex_trylock retval treatment] Signed-off-by: Jeff Mahoney Cc: Matthew Wilcox Cc: Chris Mason Cc: Edward Shishkin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs_sb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h index 49b639b88bac..c0751724ee64 100644 --- a/include/linux/reiserfs_fs_sb.h +++ b/include/linux/reiserfs_fs_sb.h @@ -194,7 +194,7 @@ struct reiserfs_journal { time_t j_trans_start_time; /* time this transaction started */ struct mutex j_mutex; - struct semaphore j_flush_sem; + struct mutex j_flush_mutex; wait_queue_head_t j_join_wait; /* wait for current transaction to finish before starting new one */ atomic_t j_jlock; /* lock for j_join_wait */ int j_list_bitmap_index; /* number of next list bitmap to use */ -- cgit v1.2.3 From 90415deac75a761a25239af6f56381546f8d2201 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Fri, 25 Jul 2008 01:46:40 -0700 Subject: reiserfs: convert j_commit_lock to mutex j_commit_lock is a semaphore but uses it as if it were a mutex. This patch converts it to a mutex. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Jeff Mahoney Cc: Matthew Wilcox Cc: Chris Mason Cc: Edward Shishkin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs_sb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h index c0751724ee64..315517e8bfa1 100644 --- a/include/linux/reiserfs_fs_sb.h +++ b/include/linux/reiserfs_fs_sb.h @@ -152,7 +152,7 @@ struct reiserfs_journal_list { atomic_t j_nonzerolen; atomic_t j_commit_left; atomic_t j_older_commits_done; /* all commits older than this on disk */ - struct semaphore j_commit_lock; + struct mutex j_commit_mutex; unsigned long j_trans_id; time_t j_timestamp; struct reiserfs_list_bitmap *j_list_bitmap; -- cgit v1.2.3 From 4596c8aaf96e8634ca755c9f34b91420a39bebd4 Mon Sep 17 00:00:00 2001 From: OGAWA Hirofumi Date: Fri, 25 Jul 2008 01:46:42 -0700 Subject: fat: fix VFAT_IOCTL_READDIR_xxx and cleanup for userland "struct dirent" is a kernel type here, but is a **different type** in userspace! This means both the structure and the IOCTL number is wrong! So, this adds new "struct __fat_dirent" to generate correct IOCTL number. And kernel stuff moves to under __KERNEL__. Signed-off-by: OGAWA Hirofumi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/msdos_fs.h | 47 +++++++++++++++++++++++++++-------------------- 1 file changed, 27 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msdos_fs.h b/include/linux/msdos_fs.h index 81cd36b735b0..5161394c7894 100644 --- a/include/linux/msdos_fs.h +++ b/include/linux/msdos_fs.h @@ -2,11 +2,11 @@ #define _LINUX_MSDOS_FS_H #include +#include /* * The MS-DOS filesystem constants/structures */ -#include #define SECTOR_SIZE 512 /* sector size (bytes) */ #define SECTOR_BITS 9 /* log2(SECTOR_SIZE) */ @@ -89,24 +89,22 @@ #define IS_FSINFO(x) (le32_to_cpu((x)->signature1) == FAT_FSINFO_SIG1 \ && le32_to_cpu((x)->signature2) == FAT_FSINFO_SIG2) +struct __fat_dirent { + long d_ino; + __kernel_off_t d_off; + unsigned short d_reclen; + char d_name[256]; /* We must not include limits.h! */ +}; + /* * ioctl commands */ -#define VFAT_IOCTL_READDIR_BOTH _IOR('r', 1, struct dirent [2]) -#define VFAT_IOCTL_READDIR_SHORT _IOR('r', 2, struct dirent [2]) +#define VFAT_IOCTL_READDIR_BOTH _IOR('r', 1, struct __fat_dirent[2]) +#define VFAT_IOCTL_READDIR_SHORT _IOR('r', 2, struct __fat_dirent[2]) /* has used 0x72 ('r') in collision, so skip a few */ #define FAT_IOCTL_GET_ATTRIBUTES _IOR('r', 0x10, __u32) #define FAT_IOCTL_SET_ATTRIBUTES _IOW('r', 0x11, __u32) -/* - * vfat shortname flags - */ -#define VFAT_SFN_DISPLAY_LOWER 0x0001 /* convert to lowercase for display */ -#define VFAT_SFN_DISPLAY_WIN95 0x0002 /* emulate win95 rule for display */ -#define VFAT_SFN_DISPLAY_WINNT 0x0004 /* emulate winnt rule for display */ -#define VFAT_SFN_CREATE_WIN95 0x0100 /* emulate win95 rule for create */ -#define VFAT_SFN_CREATE_WINNT 0x0200 /* emulate winnt rule for create */ - struct fat_boot_sector { __u8 ignored[3]; /* Boot strap short or near jump */ __u8 system_id[8]; /* Name - can be used to special case @@ -168,14 +166,6 @@ struct msdos_dir_slot { __u8 name11_12[4]; /* last 2 characters in name */ }; -struct fat_slot_info { - loff_t i_pos; /* on-disk position of directory entry */ - loff_t slot_off; /* offset for slot or de start */ - int nr_slots; /* number of slots + 1(de) in filename */ - struct msdos_dir_entry *de; - struct buffer_head *bh; -}; - #ifdef __KERNEL__ #include @@ -184,6 +174,15 @@ struct fat_slot_info { #include #include +/* + * vfat shortname flags + */ +#define VFAT_SFN_DISPLAY_LOWER 0x0001 /* convert to lowercase for display */ +#define VFAT_SFN_DISPLAY_WIN95 0x0002 /* emulate win95 rule for display */ +#define VFAT_SFN_DISPLAY_WINNT 0x0004 /* emulate winnt rule for display */ +#define VFAT_SFN_CREATE_WIN95 0x0100 /* emulate win95 rule for create */ +#define VFAT_SFN_CREATE_WINNT 0x0200 /* emulate winnt rule for create */ + struct fat_mount_options { uid_t fs_uid; gid_t fs_gid; @@ -267,6 +266,14 @@ struct msdos_inode_info { struct inode vfs_inode; }; +struct fat_slot_info { + loff_t i_pos; /* on-disk position of directory entry */ + loff_t slot_off; /* offset for slot or de start */ + int nr_slots; /* number of slots + 1(de) in filename */ + struct msdos_dir_entry *de; + struct buffer_head *bh; +}; + static inline struct msdos_sb_info *MSDOS_SB(struct super_block *sb) { return sb->s_fs_info; -- cgit v1.2.3 From 7557bc66be629d19a402e752673708bfbb8b5e86 Mon Sep 17 00:00:00 2001 From: Rene Scharfe Date: Fri, 25 Jul 2008 01:46:45 -0700 Subject: msdos fs: remove unsettable atari option It has been impossible to set the option 'atari' of the MSDOS filesystem for several years. Since nobody seems to have missed it, let's remove its remains. Signed-off-by: Rene Scharfe Acked-by: OGAWA Hirofumi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/msdos_fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/msdos_fs.h b/include/linux/msdos_fs.h index 5161394c7894..3346c9c8f17a 100644 --- a/include/linux/msdos_fs.h +++ b/include/linux/msdos_fs.h @@ -201,7 +201,6 @@ struct fat_mount_options { utf8:1, /* Use of UTF-8 character set (Default) */ unicode_xlate:1, /* create escape sequences for unhandled Unicode */ numtail:1, /* Does first alias have a numeric '~1' type tail? */ - atari:1, /* Use Atari GEMDOS variation of MS-DOS fs */ flush:1, /* write things quickly */ nocase:1, /* Does this need case conversion? 0=need case conversion*/ usefree:1; /* Use free_clusters for FAT32 */ -- cgit v1.2.3 From cf6ae8b50e0ee3f764392dadd1970e3f03c40773 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 01:46:46 -0700 Subject: remove the in-kernel struct dirent{,64} The kernel struct dirent{,64} were different from the ones in userspace. Even worse, we exported the kernel ones to userspace. But after the fat usages are fixed we can remove the conflicting kernel versions. Reviewed-by: H. Peter Anvin Signed-off-by: Adrian Bunk Cc: OGAWA Hirofumi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/Kbuild | 1 - include/linux/dirent.h | 20 -------------------- 2 files changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 71d70d1fbce2..a18008ce7aba 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -189,7 +189,6 @@ unifdef-y += connector.h unifdef-y += cuda.h unifdef-y += cyclades.h unifdef-y += dccp.h -unifdef-y += dirent.h unifdef-y += dlm.h unifdef-y += dlm_plock.h unifdef-y += edd.h diff --git a/include/linux/dirent.h b/include/linux/dirent.h index 5d6023b87800..f072fb8d10a3 100644 --- a/include/linux/dirent.h +++ b/include/linux/dirent.h @@ -1,23 +1,6 @@ #ifndef _LINUX_DIRENT_H #define _LINUX_DIRENT_H -struct dirent { - long d_ino; - __kernel_off_t d_off; - unsigned short d_reclen; - char d_name[256]; /* We must not include limits.h! */ -}; - -struct dirent64 { - __u64 d_ino; - __s64 d_off; - unsigned short d_reclen; - unsigned char d_type; - char d_name[256]; -}; - -#ifdef __KERNEL__ - struct linux_dirent64 { u64 d_ino; s64 d_off; @@ -26,7 +9,4 @@ struct linux_dirent64 { char d_name[0]; }; -#endif /* __KERNEL__ */ - - #endif -- cgit v1.2.3 From e8938a62a85d1f487e02c3b01955b47c9598f6d2 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 01:46:46 -0700 Subject: remove unused #include 's Remove some unused #include 's. Signed-off-by: Adrian Bunk Cc: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/nfsd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index a2861d95ecc3..108f47e5fd95 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -12,7 +12,6 @@ #include #include -#include #include #include #include -- cgit v1.2.3 From b271e067c896ad4082b15e96077675d08db40625 Mon Sep 17 00:00:00 2001 From: Joe Peterson Date: Fri, 25 Jul 2008 01:46:47 -0700 Subject: fatfs: add UTC timestamp option Provide a new mount option ("tz=UTC") for DOS (vfat/msdos) filesystems, allowing timestamps to be in coordinated universal time (UTC) rather than local time in applications where doing this is advantageous. In particular, portable devices that use fat/vfat (such as digital cameras) can benefit from using UTC in their internal clocks, thus avoiding daylight saving time errors and general time ambiguity issues. The user of the device does not have to worry about changing the time when moving from place or when daylight saving changes. The new mount option, when set, disables the counter-adjustment that Linux currently makes to FAT timestamp info in anticipation of the normal userspace time zone correction. When used in this new mode, all daylight saving time and time zone handling is done in userspace as is normal for many other filesystems (like ext3). The default mode, which remains unchanged, is still appropriate when mounting volumes written in Windows (because of its use of local time). I originally based this patch on one submitted last year by Paul Collins, but I updated it to work with current source and changed variable/option naming. Ogawa Hirofumi (who maintains these filesystems) and I discussed this patch at length on lkml, and he suggested using the option name in the attached version of the patch. Barry Bouwsma pointed out a good addition to the patch as well. Signed-off-by: Joe Peterson Signed-off-by: Paul Collins Acked-by: OGAWA Hirofumi Cc: Barry Bouwsma Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/msdos_fs.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msdos_fs.h b/include/linux/msdos_fs.h index 3346c9c8f17a..ba63858056c7 100644 --- a/include/linux/msdos_fs.h +++ b/include/linux/msdos_fs.h @@ -203,7 +203,8 @@ struct fat_mount_options { numtail:1, /* Does first alias have a numeric '~1' type tail? */ flush:1, /* write things quickly */ nocase:1, /* Does this need case conversion? 0=need case conversion*/ - usefree:1; /* Use free_clusters for FAT32 */ + usefree:1, /* Use free_clusters for FAT32 */ + tz_utc:1; /* Filesystem timestamps are in UTC */ }; #define FAT_HASH_BITS 8 @@ -434,8 +435,9 @@ extern int fat_flush_inodes(struct super_block *sb, struct inode *i1, extern void fat_fs_panic(struct super_block *s, const char *fmt, ...); extern void fat_clusters_flush(struct super_block *sb); extern int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster); -extern int date_dos2unix(unsigned short time, unsigned short date); -extern void fat_date_unix2dos(int unix_date, __le16 *time, __le16 *date); +extern int date_dos2unix(unsigned short time, unsigned short date, int tz_utc); +extern void fat_date_unix2dos(int unix_date, __le16 *time, __le16 *date, + int tz_utc); extern int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs); int fat_cache_init(void); -- cgit v1.2.3 From b85f4b87a511bea86dac68c4f0fabaee2cac6c4c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 25 Jul 2008 01:46:50 -0700 Subject: quota: rename quota functions from upper case, make bigger ones non-inline Cleanup quotaops.h: Rename functions from uppercase to lowercase (and define backward compatibility macros), move larger functions to dquot.c and make them non-inline. Signed-off-by: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/quotaops.h | 226 ++++++++++++++++++++++------------------------- 1 file changed, 107 insertions(+), 119 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index f86702053853..0c8f9fe462af 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -19,34 +19,38 @@ /* * declaration of quota_function calls in kernel. */ -extern void sync_dquots(struct super_block *sb, int type); - -extern int dquot_initialize(struct inode *inode, int type); -extern int dquot_drop(struct inode *inode); - -extern int dquot_alloc_space(struct inode *inode, qsize_t number, int prealloc); -extern int dquot_alloc_inode(const struct inode *inode, unsigned long number); - -extern int dquot_free_space(struct inode *inode, qsize_t number); -extern int dquot_free_inode(const struct inode *inode, unsigned long number); - -extern int dquot_transfer(struct inode *inode, struct iattr *iattr); -extern int dquot_commit(struct dquot *dquot); -extern int dquot_acquire(struct dquot *dquot); -extern int dquot_release(struct dquot *dquot); -extern int dquot_commit_info(struct super_block *sb, int type); -extern int dquot_mark_dquot_dirty(struct dquot *dquot); - -extern int vfs_quota_on(struct super_block *sb, int type, int format_id, - char *path, int remount); -extern int vfs_quota_on_mount(struct super_block *sb, char *qf_name, - int format_id, int type); -extern int vfs_quota_off(struct super_block *sb, int type, int remount); -extern int vfs_quota_sync(struct super_block *sb, int type); -extern int vfs_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); -extern int vfs_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); -extern int vfs_get_dqblk(struct super_block *sb, int type, qid_t id, struct if_dqblk *di); -extern int vfs_set_dqblk(struct super_block *sb, int type, qid_t id, struct if_dqblk *di); +void sync_dquots(struct super_block *sb, int type); + +int dquot_initialize(struct inode *inode, int type); +int dquot_drop(struct inode *inode); + +int dquot_alloc_space(struct inode *inode, qsize_t number, int prealloc); +int dquot_alloc_inode(const struct inode *inode, unsigned long number); + +int dquot_free_space(struct inode *inode, qsize_t number); +int dquot_free_inode(const struct inode *inode, unsigned long number); + +int dquot_transfer(struct inode *inode, struct iattr *iattr); +int dquot_commit(struct dquot *dquot); +int dquot_acquire(struct dquot *dquot); +int dquot_release(struct dquot *dquot); +int dquot_commit_info(struct super_block *sb, int type); +int dquot_mark_dquot_dirty(struct dquot *dquot); + +int vfs_quota_on(struct super_block *sb, int type, int format_id, + char *path, int remount); +int vfs_quota_on_mount(struct super_block *sb, char *qf_name, + int format_id, int type); +int vfs_quota_off(struct super_block *sb, int type, int remount); +int vfs_quota_sync(struct super_block *sb, int type); +int vfs_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); +int vfs_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); +int vfs_get_dqblk(struct super_block *sb, int type, qid_t id, struct if_dqblk *di); +int vfs_set_dqblk(struct super_block *sb, int type, qid_t id, struct if_dqblk *di); + +void vfs_dq_drop(struct inode *inode); +int vfs_dq_transfer(struct inode *inode, struct iattr *iattr); +int vfs_dq_quota_on_remount(struct super_block *sb); /* * Operations supported for diskquotas. @@ -59,38 +63,16 @@ extern struct quotactl_ops vfs_quotactl_ops; /* It is better to call this function outside of any transaction as it might * need a lot of space in journal for dquot structure allocation. */ -static inline void DQUOT_INIT(struct inode *inode) +static inline void vfs_dq_init(struct inode *inode) { BUG_ON(!inode->i_sb); if (sb_any_quota_enabled(inode->i_sb) && !IS_NOQUOTA(inode)) inode->i_sb->dq_op->initialize(inode, -1); } -/* The same as with DQUOT_INIT */ -static inline void DQUOT_DROP(struct inode *inode) -{ - /* Here we can get arbitrary inode from clear_inode() so we have - * to be careful. OTOH we don't need locking as quota operations - * are allowed to change only at mount time */ - if (!IS_NOQUOTA(inode) && inode->i_sb && inode->i_sb->dq_op - && inode->i_sb->dq_op->drop) { - int cnt; - /* Test before calling to rule out calls from proc and such - * where we are not allowed to block. Note that this is - * actually reliable test even without the lock - the caller - * must assure that nobody can come after the DQUOT_DROP and - * add quota pointers back anyway */ - for (cnt = 0; cnt < MAXQUOTAS; cnt++) - if (inode->i_dquot[cnt] != NODQUOT) - break; - if (cnt < MAXQUOTAS) - inode->i_sb->dq_op->drop(inode); - } -} - /* The following allocation/freeing/transfer functions *must* be called inside * a transaction (deadlocks possible otherwise) */ -static inline int DQUOT_PREALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t nr) +static inline int vfs_dq_prealloc_space_nodirty(struct inode *inode, qsize_t nr) { if (sb_any_quota_enabled(inode->i_sb)) { /* Used space is updated in alloc_space() */ @@ -102,15 +84,15 @@ static inline int DQUOT_PREALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t nr) return 0; } -static inline int DQUOT_PREALLOC_SPACE(struct inode *inode, qsize_t nr) +static inline int vfs_dq_prealloc_space(struct inode *inode, qsize_t nr) { int ret; - if (!(ret = DQUOT_PREALLOC_SPACE_NODIRTY(inode, nr))) + if (!(ret = vfs_dq_prealloc_space_nodirty(inode, nr))) mark_inode_dirty(inode); return ret; } -static inline int DQUOT_ALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t nr) +static inline int vfs_dq_alloc_space_nodirty(struct inode *inode, qsize_t nr) { if (sb_any_quota_enabled(inode->i_sb)) { /* Used space is updated in alloc_space() */ @@ -122,25 +104,25 @@ static inline int DQUOT_ALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t nr) return 0; } -static inline int DQUOT_ALLOC_SPACE(struct inode *inode, qsize_t nr) +static inline int vfs_dq_alloc_space(struct inode *inode, qsize_t nr) { int ret; - if (!(ret = DQUOT_ALLOC_SPACE_NODIRTY(inode, nr))) + if (!(ret = vfs_dq_alloc_space_nodirty(inode, nr))) mark_inode_dirty(inode); return ret; } -static inline int DQUOT_ALLOC_INODE(struct inode *inode) +static inline int vfs_dq_alloc_inode(struct inode *inode) { if (sb_any_quota_enabled(inode->i_sb)) { - DQUOT_INIT(inode); + vfs_dq_init(inode); if (inode->i_sb->dq_op->alloc_inode(inode, 1) == NO_QUOTA) return 1; } return 0; } -static inline void DQUOT_FREE_SPACE_NODIRTY(struct inode *inode, qsize_t nr) +static inline void vfs_dq_free_space_nodirty(struct inode *inode, qsize_t nr) { if (sb_any_quota_enabled(inode->i_sb)) inode->i_sb->dq_op->free_space(inode, nr); @@ -148,35 +130,25 @@ static inline void DQUOT_FREE_SPACE_NODIRTY(struct inode *inode, qsize_t nr) inode_sub_bytes(inode, nr); } -static inline void DQUOT_FREE_SPACE(struct inode *inode, qsize_t nr) +static inline void vfs_dq_free_space(struct inode *inode, qsize_t nr) { - DQUOT_FREE_SPACE_NODIRTY(inode, nr); + vfs_dq_free_space_nodirty(inode, nr); mark_inode_dirty(inode); } -static inline void DQUOT_FREE_INODE(struct inode *inode) +static inline void vfs_dq_free_inode(struct inode *inode) { if (sb_any_quota_enabled(inode->i_sb)) inode->i_sb->dq_op->free_inode(inode, 1); } -static inline int DQUOT_TRANSFER(struct inode *inode, struct iattr *iattr) -{ - if (sb_any_quota_enabled(inode->i_sb) && !IS_NOQUOTA(inode)) { - DQUOT_INIT(inode); - if (inode->i_sb->dq_op->transfer(inode, iattr) == NO_QUOTA) - return 1; - } - return 0; -} - /* The following two functions cannot be called inside a transaction */ -static inline void DQUOT_SYNC(struct super_block *sb) +static inline void vfs_dq_sync(struct super_block *sb) { sync_dquots(sb, -1); } -static inline int DQUOT_OFF(struct super_block *sb, int remount) +static inline int vfs_dq_off(struct super_block *sb, int remount) { int ret = -ENOSYS; @@ -185,21 +157,6 @@ static inline int DQUOT_OFF(struct super_block *sb, int remount) return ret; } -static inline int DQUOT_ON_REMOUNT(struct super_block *sb) -{ - int cnt; - int ret = 0, err; - - if (!sb->s_qcop || !sb->s_qcop->quota_on) - return -ENOSYS; - for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - err = sb->s_qcop->quota_on(sb, cnt, 0, NULL, 1); - if (err < 0 && !ret) - ret = err; - } - return ret; -} - #else /* @@ -208,113 +165,144 @@ static inline int DQUOT_ON_REMOUNT(struct super_block *sb) #define sb_dquot_ops (NULL) #define sb_quotactl_ops (NULL) -static inline void DQUOT_INIT(struct inode *inode) +static inline void vfs_dq_init(struct inode *inode) { } -static inline void DQUOT_DROP(struct inode *inode) +static inline void vfs_dq_drop(struct inode *inode) { } -static inline int DQUOT_ALLOC_INODE(struct inode *inode) +static inline int vfs_dq_alloc_inode(struct inode *inode) { return 0; } -static inline void DQUOT_FREE_INODE(struct inode *inode) +static inline void vfs_dq_free_inode(struct inode *inode) { } -static inline void DQUOT_SYNC(struct super_block *sb) +static inline void vfs_dq_sync(struct super_block *sb) { } -static inline int DQUOT_OFF(struct super_block *sb, int remount) +static inline int vfs_dq_off(struct super_block *sb, int remount) { return 0; } -static inline int DQUOT_ON_REMOUNT(struct super_block *sb) +static inline int vfs_dq_quota_on_remount(struct super_block *sb) { return 0; } -static inline int DQUOT_TRANSFER(struct inode *inode, struct iattr *iattr) +static inline int vfs_dq_transfer(struct inode *inode, struct iattr *iattr) { return 0; } -static inline int DQUOT_PREALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t nr) +static inline int vfs_dq_prealloc_space_nodirty(struct inode *inode, qsize_t nr) { inode_add_bytes(inode, nr); return 0; } -static inline int DQUOT_PREALLOC_SPACE(struct inode *inode, qsize_t nr) +static inline int vfs_dq_prealloc_space(struct inode *inode, qsize_t nr) { - DQUOT_PREALLOC_SPACE_NODIRTY(inode, nr); + vfs_dq_prealloc_space_nodirty(inode, nr); mark_inode_dirty(inode); return 0; } -static inline int DQUOT_ALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t nr) +static inline int vfs_dq_alloc_space_nodirty(struct inode *inode, qsize_t nr) { inode_add_bytes(inode, nr); return 0; } -static inline int DQUOT_ALLOC_SPACE(struct inode *inode, qsize_t nr) +static inline int vfs_dq_alloc_space(struct inode *inode, qsize_t nr) { - DQUOT_ALLOC_SPACE_NODIRTY(inode, nr); + vfs_dq_alloc_space_nodirty(inode, nr); mark_inode_dirty(inode); return 0; } -static inline void DQUOT_FREE_SPACE_NODIRTY(struct inode *inode, qsize_t nr) +static inline void vfs_dq_free_space_nodirty(struct inode *inode, qsize_t nr) { inode_sub_bytes(inode, nr); } -static inline void DQUOT_FREE_SPACE(struct inode *inode, qsize_t nr) +static inline void vfs_dq_free_space(struct inode *inode, qsize_t nr) { - DQUOT_FREE_SPACE_NODIRTY(inode, nr); + vfs_dq_free_space_nodirty(inode, nr); mark_inode_dirty(inode); } #endif /* CONFIG_QUOTA */ -static inline int DQUOT_PREALLOC_BLOCK_NODIRTY(struct inode *inode, qsize_t nr) +static inline int vfs_dq_prealloc_block_nodirty(struct inode *inode, qsize_t nr) { - return DQUOT_PREALLOC_SPACE_NODIRTY(inode, + return vfs_dq_prealloc_space_nodirty(inode, nr << inode->i_sb->s_blocksize_bits); } -static inline int DQUOT_PREALLOC_BLOCK(struct inode *inode, qsize_t nr) +static inline int vfs_dq_prealloc_block(struct inode *inode, qsize_t nr) { - return DQUOT_PREALLOC_SPACE(inode, + return vfs_dq_prealloc_space(inode, nr << inode->i_sb->s_blocksize_bits); } -static inline int DQUOT_ALLOC_BLOCK_NODIRTY(struct inode *inode, qsize_t nr) +static inline int vfs_dq_alloc_block_nodirty(struct inode *inode, qsize_t nr) { - return DQUOT_ALLOC_SPACE_NODIRTY(inode, + return vfs_dq_alloc_space_nodirty(inode, nr << inode->i_sb->s_blocksize_bits); } -static inline int DQUOT_ALLOC_BLOCK(struct inode *inode, qsize_t nr) +static inline int vfs_dq_alloc_block(struct inode *inode, qsize_t nr) { - return DQUOT_ALLOC_SPACE(inode, + return vfs_dq_alloc_space(inode, nr << inode->i_sb->s_blocksize_bits); } -static inline void DQUOT_FREE_BLOCK_NODIRTY(struct inode *inode, qsize_t nr) +static inline void vfs_dq_free_block_nodirty(struct inode *inode, qsize_t nr) { - DQUOT_FREE_SPACE_NODIRTY(inode, nr << inode->i_sb->s_blocksize_bits); + vfs_dq_free_space_nodirty(inode, nr << inode->i_sb->s_blocksize_bits); } -static inline void DQUOT_FREE_BLOCK(struct inode *inode, qsize_t nr) +static inline void vfs_dq_free_block(struct inode *inode, qsize_t nr) { - DQUOT_FREE_SPACE(inode, nr << inode->i_sb->s_blocksize_bits); + vfs_dq_free_space(inode, nr << inode->i_sb->s_blocksize_bits); } +/* + * Define uppercase equivalents for compatibility with old function names + * Can go away when we think all users have been converted (15/04/2008) + */ +#define DQUOT_INIT(inode) vfs_dq_init(inode) +#define DQUOT_DROP(inode) vfs_dq_drop(inode) +#define DQUOT_PREALLOC_SPACE_NODIRTY(inode, nr) \ + vfs_dq_prealloc_space_nodirty(inode, nr) +#define DQUOT_PREALLOC_SPACE(inode, nr) vfs_dq_prealloc_space(inode, nr) +#define DQUOT_ALLOC_SPACE_NODIRTY(inode, nr) \ + vfs_dq_alloc_space_nodirty(inode, nr) +#define DQUOT_ALLOC_SPACE(inode, nr) vfs_dq_alloc_space(inode, nr) +#define DQUOT_PREALLOC_BLOCK_NODIRTY(inode, nr) \ + vfs_dq_prealloc_block_nodirty(inode, nr) +#define DQUOT_PREALLOC_BLOCK(inode, nr) vfs_dq_prealloc_block(inode, nr) +#define DQUOT_ALLOC_BLOCK_NODIRTY(inode, nr) \ + vfs_dq_alloc_block_nodirty(inode, nr) +#define DQUOT_ALLOC_BLOCK(inode, nr) vfs_dq_alloc_block(inode, nr) +#define DQUOT_ALLOC_INODE(inode) vfs_dq_alloc_inode(inode) +#define DQUOT_FREE_SPACE_NODIRTY(inode, nr) \ + vfs_dq_free_space_nodirty(inode, nr) +#define DQUOT_FREE_SPACE(inode, nr) vfs_dq_free_space(inode, nr) +#define DQUOT_FREE_BLOCK_NODIRTY(inode, nr) \ + vfs_dq_free_block_nodirty(inode, nr) +#define DQUOT_FREE_BLOCK(inode, nr) vfs_dq_free_block(inode, nr) +#define DQUOT_FREE_INODE(inode) vfs_dq_free_inode(inode) +#define DQUOT_TRANSFER(inode, iattr) vfs_dq_transfer(inode, iattr) +#define DQUOT_SYNC(sb) vfs_dq_sync(sb) +#define DQUOT_OFF(sb, remount) vfs_dq_off(sb, remount) +#define DQUOT_ON_REMOUNT(sb) vfs_dq_quota_on_remount(sb) + #endif /* _LINUX_QUOTAOPS_ */ -- cgit v1.2.3 From 02a55ca87185e114e5d298a8d00608501dbabf67 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 25 Jul 2008 01:46:50 -0700 Subject: quota: cleanup loop in sync_dquots() Make loop in sync_dquots() checking whether there's something to write more readable, remove useless variable and macro info_any_dirty() which is used only in this place. Signed-off-by: Jan Kara Cc: "Vegard Nossum" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/quota.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index dcddfb200947..6f1d97ddf828 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -224,8 +224,6 @@ struct super_block; extern void mark_info_dirty(struct super_block *sb, int type); #define info_dirty(info) test_bit(DQF_INFO_DIRTY_B, &(info)->dqi_flags) -#define info_any_dquot_dirty(info) (!list_empty(&(info)->dqi_dirty_list)) -#define info_any_dirty(info) (info_dirty(info) || info_any_dquot_dirty(info)) #define sb_dqopt(sb) (&(sb)->s_dquot) #define sb_dqinfo(sb, type) (sb_dqopt(sb)->info+(type)) -- cgit v1.2.3 From 74abb9890dafb12a50dc140de215ed477beb1b88 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 25 Jul 2008 01:46:51 -0700 Subject: quota: move function-macros from quota.h to quotaops.h Move declarations of some macros, which should be in fact functions to quotaops.h. This way they can be later converted to inline functions because we can now use declarations from quota.h. Also add necessary includes of quotaops.h to a few files. [akpm@linux-foundation.org: fix JFS build] [akpm@linux-foundation.org: fix UFS build] [vegard.nossum@gmail.com: fix QUOTA=n build] Signed-off-by: Jan Kara Cc: Vegard Nossum Cc: Arjen Pool Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/quota.h | 22 +++------------------- include/linux/quotaops.h | 26 ++++++++++++++++++++++++++ 2 files changed, 29 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index 6f1d97ddf828..f9983ea0ff88 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -41,9 +41,6 @@ #define __DQUOT_VERSION__ "dquot_6.5.1" #define __DQUOT_NUM_VERSION__ 6*10000+5*100+1 -typedef __kernel_uid32_t qid_t; /* Type in which we store ids in memory */ -typedef __u64 qsize_t; /* Type in which we store sizes */ - /* Size of blocks in which are counted size limits */ #define QUOTABLOCK_BITS 10 #define QUOTABLOCK_SIZE (1 << QUOTABLOCK_BITS) @@ -172,6 +169,9 @@ enum { #include +typedef __kernel_uid32_t qid_t; /* Type in which we store ids in memory */ +typedef __u64 qsize_t; /* Type in which we store sizes */ + extern spinlock_t dq_data_lock; /* Maximal numbers of writes for quota operation (insert/delete/update) @@ -225,9 +225,6 @@ struct super_block; extern void mark_info_dirty(struct super_block *sb, int type); #define info_dirty(info) test_bit(DQF_INFO_DIRTY_B, &(info)->dqi_flags) -#define sb_dqopt(sb) (&(sb)->s_dquot) -#define sb_dqinfo(sb, type) (sb_dqopt(sb)->info+(type)) - struct dqstats { int lookups; int drops; @@ -335,19 +332,6 @@ struct quota_info { struct quota_format_ops *ops[MAXQUOTAS]; /* Operations for each type */ }; -#define sb_has_quota_enabled(sb, type) ((type)==USRQUOTA ? \ - (sb_dqopt(sb)->flags & DQUOT_USR_ENABLED) : (sb_dqopt(sb)->flags & DQUOT_GRP_ENABLED)) - -#define sb_any_quota_enabled(sb) (sb_has_quota_enabled(sb, USRQUOTA) | \ - sb_has_quota_enabled(sb, GRPQUOTA)) - -#define sb_has_quota_suspended(sb, type) \ - ((type) == USRQUOTA ? (sb_dqopt(sb)->flags & DQUOT_USR_SUSPENDED) : \ - (sb_dqopt(sb)->flags & DQUOT_GRP_SUSPENDED)) - -#define sb_any_quota_suspended(sb) (sb_has_quota_suspended(sb, USRQUOTA) | \ - sb_has_quota_suspended(sb, GRPQUOTA)) - int register_quota_format(struct quota_format_type *fmt); void unregister_quota_format(struct quota_format_type *fmt); diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 0c8f9fe462af..38218c1334b1 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -14,6 +14,8 @@ #include +#define sb_dqopt(sb) (&(sb)->s_dquot) + #if defined(CONFIG_QUOTA) /* @@ -52,6 +54,25 @@ void vfs_dq_drop(struct inode *inode); int vfs_dq_transfer(struct inode *inode, struct iattr *iattr); int vfs_dq_quota_on_remount(struct super_block *sb); +#define sb_dqinfo(sb, type) (sb_dqopt(sb)->info+(type)) + +/* + * Functions for checking status of quota + */ + +#define sb_has_quota_enabled(sb, type) ((type)==USRQUOTA ? \ + (sb_dqopt(sb)->flags & DQUOT_USR_ENABLED) : (sb_dqopt(sb)->flags & DQUOT_GRP_ENABLED)) + +#define sb_any_quota_enabled(sb) (sb_has_quota_enabled(sb, USRQUOTA) | \ + sb_has_quota_enabled(sb, GRPQUOTA)) + +#define sb_has_quota_suspended(sb, type) \ + ((type) == USRQUOTA ? (sb_dqopt(sb)->flags & DQUOT_USR_SUSPENDED) : \ + (sb_dqopt(sb)->flags & DQUOT_GRP_SUSPENDED)) + +#define sb_any_quota_suspended(sb) (sb_has_quota_suspended(sb, USRQUOTA) | \ + sb_has_quota_suspended(sb, GRPQUOTA)) + /* * Operations supported for diskquotas. */ @@ -159,6 +180,11 @@ static inline int vfs_dq_off(struct super_block *sb, int remount) #else +#define sb_has_quota_enabled(sb, type) 0 +#define sb_any_quota_enabled(sb) 0 +#define sb_has_quota_suspended(sb, type) 0 +#define sb_any_quota_suspended(sb) 0 + /* * NO-OP when quota not configured. */ -- cgit v1.2.3 From 03b063436ca1076301de58d9d628f610ab5404ad Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 25 Jul 2008 01:46:52 -0700 Subject: quota: convert macros to inline functions Signed-off-by: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/quota.h | 5 +++- include/linux/quotaops.h | 65 ++++++++++++++++++++++++++++++++++++------------ 2 files changed, 53 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index f9983ea0ff88..4e004fef8134 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -223,7 +223,10 @@ struct super_block; #define DQF_INFO_DIRTY (1 << DQF_INFO_DIRTY_B) /* Is info dirty? */ extern void mark_info_dirty(struct super_block *sb, int type); -#define info_dirty(info) test_bit(DQF_INFO_DIRTY_B, &(info)->dqi_flags) +static inline int info_dirty(struct mem_dqinfo *info) +{ + return test_bit(DQF_INFO_DIRTY_B, &info->dqi_flags); +} struct dqstats { int lookups; diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 38218c1334b1..742187f7a05c 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -11,10 +11,12 @@ #define _LINUX_QUOTAOPS_ #include - #include -#define sb_dqopt(sb) (&(sb)->s_dquot) +static inline struct quota_info *sb_dqopt(struct super_block *sb) +{ + return &sb->s_dquot; +} #if defined(CONFIG_QUOTA) @@ -54,24 +56,40 @@ void vfs_dq_drop(struct inode *inode); int vfs_dq_transfer(struct inode *inode, struct iattr *iattr); int vfs_dq_quota_on_remount(struct super_block *sb); -#define sb_dqinfo(sb, type) (sb_dqopt(sb)->info+(type)) +static inline struct mem_dqinfo *sb_dqinfo(struct super_block *sb, int type) +{ + return sb_dqopt(sb)->info + type; +} /* * Functions for checking status of quota */ -#define sb_has_quota_enabled(sb, type) ((type)==USRQUOTA ? \ - (sb_dqopt(sb)->flags & DQUOT_USR_ENABLED) : (sb_dqopt(sb)->flags & DQUOT_GRP_ENABLED)) +static inline int sb_has_quota_enabled(struct super_block *sb, int type) +{ + if (type == USRQUOTA) + return sb_dqopt(sb)->flags & DQUOT_USR_ENABLED; + return sb_dqopt(sb)->flags & DQUOT_GRP_ENABLED; +} -#define sb_any_quota_enabled(sb) (sb_has_quota_enabled(sb, USRQUOTA) | \ - sb_has_quota_enabled(sb, GRPQUOTA)) +static inline int sb_any_quota_enabled(struct super_block *sb) +{ + return sb_has_quota_enabled(sb, USRQUOTA) || + sb_has_quota_enabled(sb, GRPQUOTA); +} -#define sb_has_quota_suspended(sb, type) \ - ((type) == USRQUOTA ? (sb_dqopt(sb)->flags & DQUOT_USR_SUSPENDED) : \ - (sb_dqopt(sb)->flags & DQUOT_GRP_SUSPENDED)) +static inline int sb_has_quota_suspended(struct super_block *sb, int type) +{ + if (type == USRQUOTA) + return sb_dqopt(sb)->flags & DQUOT_USR_SUSPENDED; + return sb_dqopt(sb)->flags & DQUOT_GRP_SUSPENDED; +} -#define sb_any_quota_suspended(sb) (sb_has_quota_suspended(sb, USRQUOTA) | \ - sb_has_quota_suspended(sb, GRPQUOTA)) +static inline int sb_any_quota_suspended(struct super_block *sb) +{ + return sb_has_quota_suspended(sb, USRQUOTA) || + sb_has_quota_suspended(sb, GRPQUOTA); +} /* * Operations supported for diskquotas. @@ -180,10 +198,25 @@ static inline int vfs_dq_off(struct super_block *sb, int remount) #else -#define sb_has_quota_enabled(sb, type) 0 -#define sb_any_quota_enabled(sb) 0 -#define sb_has_quota_suspended(sb, type) 0 -#define sb_any_quota_suspended(sb) 0 +static inline int sb_has_quota_enabled(struct super_block *sb, int type) +{ + return 0; +} + +static inline int sb_any_quota_enabled(struct super_block *sb) +{ + return 0; +} + +static inline int sb_has_quota_suspended(struct super_block *sb, int type) +{ + return 0; +} + +static inline int sb_any_quota_suspended(struct super_block *sb) +{ + return 0; +} /* * NO-OP when quota not configured. -- cgit v1.2.3 From 657d3bfa98e542271b449f8cd84c7501ae2b2255 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 25 Jul 2008 01:46:52 -0700 Subject: quota: implement sending information via netlink about user below quota Sometimes it may be useful for userspace to know (e.g. for some hosting guys) that some user stopped exceeding his hardlimit or softlimit in quotas. Implement sending of such events to userspace via quota netlink protocol so that they don't have to poll for such events. Based on idea and initial implementation by Vladislav Bogdanov. Cc: Vladislav Bogdanov Signed-off-by: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/quota.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index 4e004fef8134..376a05048bc5 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -135,6 +135,10 @@ struct if_dqinfo { #define QUOTA_NL_BHARDWARN 4 /* Block hardlimit reached */ #define QUOTA_NL_BSOFTLONGWARN 5 /* Block grace time expired */ #define QUOTA_NL_BSOFTWARN 6 /* Block softlimit reached */ +#define QUOTA_NL_IHARDBELOW 7 /* Usage got below inode hardlimit */ +#define QUOTA_NL_ISOFTBELOW 8 /* Usage got below inode softlimit */ +#define QUOTA_NL_BHARDBELOW 9 /* Usage got below block hardlimit */ +#define QUOTA_NL_BSOFTBELOW 10 /* Usage got below block softlimit */ enum { QUOTA_NL_C_UNSPEC, -- cgit v1.2.3 From f2992db2a4f7ae10f61d5bc68c7c1528cec639e2 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Fri, 25 Jul 2008 01:46:55 -0700 Subject: Mark res_counter_charge(_locked) with __must_check Ignoring their return values may result in counter underflow in the future - when the value charged will be uncharged (or in "leaks" - when the value is not uncharged). This also prevents from using charging routines to decrement the counter value (i.e. uncharge it) ;) (Current code works OK with res_counter, however :) ) Signed-off-by: Pavel Emelyanov Cc: Balbir Singh Cc: Paul Menage Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/res_counter.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index 6d9e1fca098c..125660e7793f 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -95,8 +95,10 @@ void res_counter_init(struct res_counter *counter); * counter->limit _locked call expects the counter->lock to be taken */ -int res_counter_charge_locked(struct res_counter *counter, unsigned long val); -int res_counter_charge(struct res_counter *counter, unsigned long val); +int __must_check res_counter_charge_locked(struct res_counter *counter, + unsigned long val); +int __must_check res_counter_charge(struct res_counter *counter, + unsigned long val); /* * uncharge - tell that some portion of the resource is released -- cgit v1.2.3 From ce16b49d37e748574f7fabc2726268d542d0aa1a Mon Sep 17 00:00:00 2001 From: Paul Menage Date: Fri, 25 Jul 2008 01:46:57 -0700 Subject: cgroup files: clean up whitespace in struct cftype This patch removes some extraneous spaces from method declarations in struct cftype, to fit in with conventional kernel style. Signed-off-by: Paul Menage Cc: Paul Jackson Cc: Pavel Emelyanov Cc: Balbir Singh Cc: Serge Hallyn Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index e155aa78d859..88a734edccbc 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -205,48 +205,48 @@ struct cftype { * subsystem, followed by a period */ char name[MAX_CFTYPE_NAME]; int private; - int (*open) (struct inode *inode, struct file *file); - ssize_t (*read) (struct cgroup *cgrp, struct cftype *cft, - struct file *file, - char __user *buf, size_t nbytes, loff_t *ppos); + int (*open)(struct inode *inode, struct file *file); + ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft, + struct file *file, + char __user *buf, size_t nbytes, loff_t *ppos); /* * read_u64() is a shortcut for the common case of returning a * single integer. Use it in place of read() */ - u64 (*read_u64) (struct cgroup *cgrp, struct cftype *cft); + u64 (*read_u64)(struct cgroup *cgrp, struct cftype *cft); /* * read_s64() is a signed version of read_u64() */ - s64 (*read_s64) (struct cgroup *cgrp, struct cftype *cft); + s64 (*read_s64)(struct cgroup *cgrp, struct cftype *cft); /* * read_map() is used for defining a map of key/value * pairs. It should call cb->fill(cb, key, value) for each * entry. The key/value pairs (and their ordering) should not * change between reboots. */ - int (*read_map) (struct cgroup *cont, struct cftype *cft, - struct cgroup_map_cb *cb); + int (*read_map)(struct cgroup *cont, struct cftype *cft, + struct cgroup_map_cb *cb); /* * read_seq_string() is used for outputting a simple sequence * using seqfile. */ - int (*read_seq_string) (struct cgroup *cont, struct cftype *cft, - struct seq_file *m); + int (*read_seq_string)(struct cgroup *cont, struct cftype *cft, + struct seq_file *m); - ssize_t (*write) (struct cgroup *cgrp, struct cftype *cft, - struct file *file, - const char __user *buf, size_t nbytes, loff_t *ppos); + ssize_t (*write)(struct cgroup *cgrp, struct cftype *cft, + struct file *file, + const char __user *buf, size_t nbytes, loff_t *ppos); /* * write_u64() is a shortcut for the common case of accepting * a single integer (as parsed by simple_strtoull) from * userspace. Use in place of write(); return 0 or error. */ - int (*write_u64) (struct cgroup *cgrp, struct cftype *cft, u64 val); + int (*write_u64)(struct cgroup *cgrp, struct cftype *cft, u64 val); /* * write_s64() is a signed version of write_u64() */ - int (*write_s64) (struct cgroup *cgrp, struct cftype *cft, s64 val); + int (*write_s64)(struct cgroup *cgrp, struct cftype *cft, s64 val); /* * trigger() callback can be used to get some kick from the @@ -256,7 +256,7 @@ struct cftype { */ int (*trigger)(struct cgroup *cgrp, unsigned int event); - int (*release) (struct inode *inode, struct file *file); + int (*release)(struct inode *inode, struct file *file); }; struct cgroup_scanner { -- cgit v1.2.3 From db3b14978abc02041046ed8353f0899cb58ffffc Mon Sep 17 00:00:00 2001 From: Paul Menage Date: Fri, 25 Jul 2008 01:46:58 -0700 Subject: cgroup files: add write_string cgroup control file method This patch adds a write_string() method for cgroups control files. The semantics are that a buffer is copied from userspace to kernelspace and the handler function invoked on that buffer. The buffer is guaranteed to be nul-terminated, and no longer than max_write_len (defaulting to 64 bytes if unspecified). Later patches will convert existing raw file write handlers in control group subsystems to use this method. Signed-off-by: Paul Menage Cc: Paul Jackson Cc: Pavel Emelyanov Acked-by: Balbir Singh Acked-by: Serge Hallyn Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 88a734edccbc..f5379455bb59 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -205,6 +205,13 @@ struct cftype { * subsystem, followed by a period */ char name[MAX_CFTYPE_NAME]; int private; + + /* + * If non-zero, defines the maximum length of string that can + * be passed to write_string; defaults to 64 + */ + size_t max_write_len; + int (*open)(struct inode *inode, struct file *file); ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft, struct file *file, @@ -248,6 +255,13 @@ struct cftype { */ int (*write_s64)(struct cgroup *cgrp, struct cftype *cft, s64 val); + /* + * write_string() is passed a nul-terminated kernelspace + * buffer of maximum length determined by max_write_len. + * Returns 0 or -ve error code. + */ + int (*write_string)(struct cgroup *cgrp, struct cftype *cft, + const char *buffer); /* * trigger() callback can be used to get some kick from the * userspace, when the actual string written is not important -- cgit v1.2.3 From e788e066c651b1bbf4a927dc95395c1aa13be436 Mon Sep 17 00:00:00 2001 From: Paul Menage Date: Fri, 25 Jul 2008 01:46:59 -0700 Subject: cgroup files: move the release_agent file to use typed handlers Adds cgroup_release_agent_write() and cgroup_release_agent_show() methods to handle writing/reading the path to a cgroup hierarchy's release agent. As a result, cgroup_common_file_read() is now unnecessary. As part of the change, a previously-tolerated race in cgroup_release_agent() is avoided by copying the current release_agent_path prior to calling call_usermode_helper(). Signed-off-by: Paul Menage Cc: Paul Jackson Cc: Pavel Emelyanov Cc: Balbir Singh Acked-by: Serge Hallyn Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index f5379455bb59..e78377a91a74 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -295,6 +295,8 @@ int cgroup_add_files(struct cgroup *cgrp, int cgroup_is_removed(const struct cgroup *cgrp); +int cgroup_lock_live_group(struct cgroup *cgrp); + int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen); int cgroup_task_count(const struct cgroup *cgrp); -- cgit v1.2.3 From 84eea842886ac35020be6043e04748ed22014359 Mon Sep 17 00:00:00 2001 From: Paul Menage Date: Fri, 25 Jul 2008 01:47:00 -0700 Subject: cgroups: misc cleanups to write_string patchset This patch contains cleanups suggested by reviewers for the recent write_string() patchset: - pair cgroup_lock_live_group() with cgroup_unlock() in cgroup.c for clarity, rather than directly unlocking cgroup_mutex. - make the return type of cgroup_lock_live_group() a bool - use a #define'd constant for the local buffer size in read/write functions Signed-off-by: Paul Menage Cc: Paul Jackson Cc: Pavel Emelyanov Cc: Balbir Singh Acked-by: Serge Hallyn Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index e78377a91a74..cc59d3a21d87 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -21,11 +21,13 @@ struct cgroupfs_root; struct cgroup_subsys; struct inode; +struct cgroup; extern int cgroup_init_early(void); extern int cgroup_init(void); extern void cgroup_init_smp(void); extern void cgroup_lock(void); +extern bool cgroup_lock_live_group(struct cgroup *cgrp); extern void cgroup_unlock(void); extern void cgroup_fork(struct task_struct *p); extern void cgroup_fork_callbacks(struct task_struct *p); @@ -295,8 +297,6 @@ int cgroup_add_files(struct cgroup *cgrp, int cgroup_is_removed(const struct cgroup *cgrp); -int cgroup_lock_live_group(struct cgroup *cgrp); - int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen); int cgroup_task_count(const struct cgroup *cgrp); -- cgit v1.2.3 From 856c13aa1ff6136c1968414fdea5938ea9d5ebf2 Mon Sep 17 00:00:00 2001 From: Paul Menage Date: Fri, 25 Jul 2008 01:47:04 -0700 Subject: cgroup files: convert res_counter_write() to be a cgroups write_string() handler Currently res_counter_write() is a raw file handler even though it's ultimately taking a number, since in some cases it wants to pre-process the string when converting it to a number. This patch converts res_counter_write() from a raw file handler to a write_string() handler; this allows some of the boilerplate copying/locking/checking to be removed, and simplies the cleanup path, since these functions are now performed by the cgroups framework. [lizf@cn.fujitsu.com: build fix] Signed-off-by: Paul Menage Cc: Paul Jackson Cc: Pavel Emelyanov Cc: Balbir Singh Cc: Serge Hallyn Cc: KAMEZAWA Hiroyuki Signed-off-by: Li Zefan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/res_counter.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index 125660e7793f..290205dfe094 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -63,9 +63,14 @@ u64 res_counter_read_u64(struct res_counter *counter, int member); ssize_t res_counter_read(struct res_counter *counter, int member, const char __user *buf, size_t nbytes, loff_t *pos, int (*read_strategy)(unsigned long long val, char *s)); -ssize_t res_counter_write(struct res_counter *counter, int member, - const char __user *buf, size_t nbytes, loff_t *pos, - int (*write_strategy)(char *buf, unsigned long long *val)); + +typedef int (*write_strategy_fn)(const char *buf, unsigned long long *val); + +int res_counter_memparse_write_strategy(const char *buf, + unsigned long long *res); + +int res_counter_write(struct res_counter *counter, int member, + const char *buffer, write_strategy_fn write_strategy); /* * the field descriptors. one for each member of res_counter -- cgit v1.2.3 From e885dcde75685e09f23cffae1f6d5169c105b8a0 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Fri, 25 Jul 2008 01:47:06 -0700 Subject: cgroup_clone: use pid of newly created task for new cgroup cgroup_clone creates a new cgroup with the pid of the task. This works correctly for unshare, but for clone cgroup_clone is called from copy_namespaces inside copy_process, which happens before the new pid is created. As a result, the new cgroup was created with current's pid. This patch: 1. Moves the call inside copy_process to after the new pid is created 2. Passes the struct pid into ns_cgroup_clone (as it is not yet attached to the task) 3. Passes a name from ns_cgroup_clone() into cgroup_clone() so as to keep cgroup_clone() itself simpler 4. Uses pid_vnr() to get the process id value, so that the pid used to name the new cgroup is always the pid as it would be known to the task which did the cloning or unsharing. I think that is the most intuitive thing to do. This way, task t1 does clone(CLONE_NEWPID) to get t2, which does clone(CLONE_NEWPID) to get t3, then the cgroup for t3 will be named for the pid by which t2 knows t3. (Thanks to Dan Smith for finding the main bug) Changelog: June 11: Incorporate Paul Menage's feedback: don't pass NULL to ns_cgroup_clone from unshare, and reduce patch size by using 'nodename' in cgroup_clone. June 10: Original version [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Serge Hallyn Acked-by: Paul Menage Tested-by: Dan Smith Cc: Balbir Singh Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 3 ++- include/linux/nsproxy.h | 7 +++++-- 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index cc59d3a21d87..c98dd7cb7076 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -364,7 +364,8 @@ static inline struct cgroup* task_cgroup(struct task_struct *task, return task_subsys_state(task, subsys_id)->cgroup; } -int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *ss); +int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *ss, + char *nodename); /* A cgroup_iter should be treated as an opaque object */ struct cgroup_iter { diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 0e66b57631fc..c8a768e59640 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -82,9 +82,12 @@ static inline void get_nsproxy(struct nsproxy *ns) } #ifdef CONFIG_CGROUP_NS -int ns_cgroup_clone(struct task_struct *tsk); +int ns_cgroup_clone(struct task_struct *tsk, struct pid *pid); #else -static inline int ns_cgroup_clone(struct task_struct *tsk) { return 0; } +static inline int ns_cgroup_clone(struct task_struct *tsk, struct pid *pid) +{ + return 0; +} #endif #endif -- cgit v1.2.3 From e8589cc189f96b87348ae83ea4db38eaac624135 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Fri, 25 Jul 2008 01:47:10 -0700 Subject: memcg: better migration handling This patch changes page migration under memory controller to use a different algorithm. (thanks to Christoph for new idea.) Before: - page_cgroup is migrated from an old page to a new page. After: - a new page is accounted , no reuse of page_cgroup. Pros: - We can avoid compliated lock depndencies and races in migration. Cons: - new param to mem_cgroup_charge_common(). - mem_cgroup_getref() is added for handling ref_cnt ping-pong. This version simplifies complicated lock dependency in page migraiton under memory resource controller. new refcnt sequence is following. a mapped page: prepage_migration() ..... +1 to NEW page try_to_unmap() ..... all refs to OLD page is gone. move_pages() ..... +1 to NEW page if page cache. remap... ..... all refs from *map* is added to NEW one. end_migration() ..... -1 to New page. page's mapcount + (page_is_cache) refs are added to NEW one. Signed-off-by: KAMEZAWA Hiroyuki Cc: Balbir Singh Cc: Pavel Emelyanov Cc: Li Zefan Cc: YAMAMOTO Takashi Cc: Hugh Dickins Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e6608776bc96..84ead2aa6f18 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -50,9 +50,10 @@ extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); #define mm_match_cgroup(mm, cgroup) \ ((cgroup) == mem_cgroup_from_task((mm)->owner)) -extern int mem_cgroup_prepare_migration(struct page *page); +extern int +mem_cgroup_prepare_migration(struct page *page, struct page *newpage); extern void mem_cgroup_end_migration(struct page *page); -extern void mem_cgroup_page_migration(struct page *page, struct page *newpage); +extern int mem_cgroup_getref(struct page *page); /* * For memory reclaim. @@ -112,7 +113,8 @@ static inline int task_in_mem_cgroup(struct task_struct *task, return 1; } -static inline int mem_cgroup_prepare_migration(struct page *page) +static inline int +mem_cgroup_prepare_migration(struct page *page, struct page *newpage) { return 0; } @@ -121,8 +123,7 @@ static inline void mem_cgroup_end_migration(struct page *page) { } -static inline void -mem_cgroup_page_migration(struct page *page, struct page *newpage) +static inline void mem_cgroup_getref(struct page *page) { } -- cgit v1.2.3 From 69029cd550284e32de13d6dd2f77b723c8a0e444 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Fri, 25 Jul 2008 01:47:14 -0700 Subject: memcg: remove refcnt from page_cgroup memcg: performance improvements Patch Description 1/5 ... remove refcnt fron page_cgroup patch (shmem handling is fixed) 2/5 ... swapcache handling patch 3/5 ... add helper function for shmem's memory reclaim patch 4/5 ... optimize by likely/unlikely ppatch 5/5 ... remove redundunt check patch (shmem handling is fixed.) Unix bench result. == 2.6.26-rc2-mm1 + memory resource controller Execl Throughput 2915.4 lps (29.6 secs, 3 samples) C Compiler Throughput 1019.3 lpm (60.0 secs, 3 samples) Shell Scripts (1 concurrent) 5796.0 lpm (60.0 secs, 3 samples) Shell Scripts (8 concurrent) 1097.7 lpm (60.0 secs, 3 samples) Shell Scripts (16 concurrent) 565.3 lpm (60.0 secs, 3 samples) File Read 1024 bufsize 2000 maxblocks 1022128.0 KBps (30.0 secs, 3 samples) File Write 1024 bufsize 2000 maxblocks 544057.0 KBps (30.0 secs, 3 samples) File Copy 1024 bufsize 2000 maxblocks 346481.0 KBps (30.0 secs, 3 samples) File Read 256 bufsize 500 maxblocks 319325.0 KBps (30.0 secs, 3 samples) File Write 256 bufsize 500 maxblocks 148788.0 KBps (30.0 secs, 3 samples) File Copy 256 bufsize 500 maxblocks 99051.0 KBps (30.0 secs, 3 samples) File Read 4096 bufsize 8000 maxblocks 2058917.0 KBps (30.0 secs, 3 samples) File Write 4096 bufsize 8000 maxblocks 1606109.0 KBps (30.0 secs, 3 samples) File Copy 4096 bufsize 8000 maxblocks 854789.0 KBps (30.0 secs, 3 samples) Dc: sqrt(2) to 99 decimal places 126145.2 lpm (30.0 secs, 3 samples) INDEX VALUES TEST BASELINE RESULT INDEX Execl Throughput 43.0 2915.4 678.0 File Copy 1024 bufsize 2000 maxblocks 3960.0 346481.0 875.0 File Copy 256 bufsize 500 maxblocks 1655.0 99051.0 598.5 File Copy 4096 bufsize 8000 maxblocks 5800.0 854789.0 1473.8 Shell Scripts (8 concurrent) 6.0 1097.7 1829.5 ========= FINAL SCORE 991.3 == 2.6.26-rc2-mm1 + this set == Execl Throughput 3012.9 lps (29.9 secs, 3 samples) C Compiler Throughput 981.0 lpm (60.0 secs, 3 samples) Shell Scripts (1 concurrent) 5872.0 lpm (60.0 secs, 3 samples) Shell Scripts (8 concurrent) 1120.3 lpm (60.0 secs, 3 samples) Shell Scripts (16 concurrent) 578.0 lpm (60.0 secs, 3 samples) File Read 1024 bufsize 2000 maxblocks 1003993.0 KBps (30.0 secs, 3 samples) File Write 1024 bufsize 2000 maxblocks 550452.0 KBps (30.0 secs, 3 samples) File Copy 1024 bufsize 2000 maxblocks 347159.0 KBps (30.0 secs, 3 samples) File Read 256 bufsize 500 maxblocks 314644.0 KBps (30.0 secs, 3 samples) File Write 256 bufsize 500 maxblocks 151852.0 KBps (30.0 secs, 3 samples) File Copy 256 bufsize 500 maxblocks 101000.0 KBps (30.0 secs, 3 samples) File Read 4096 bufsize 8000 maxblocks 2033256.0 KBps (30.0 secs, 3 samples) File Write 4096 bufsize 8000 maxblocks 1611814.0 KBps (30.0 secs, 3 samples) File Copy 4096 bufsize 8000 maxblocks 847979.0 KBps (30.0 secs, 3 samples) Dc: sqrt(2) to 99 decimal places 128148.7 lpm (30.0 secs, 3 samples) INDEX VALUES TEST BASELINE RESULT INDEX Execl Throughput 43.0 3012.9 700.7 File Copy 1024 bufsize 2000 maxblocks 3960.0 347159.0 876.7 File Copy 256 bufsize 500 maxblocks 1655.0 101000.0 610.3 File Copy 4096 bufsize 8000 maxblocks 5800.0 847979.0 1462.0 Shell Scripts (8 concurrent) 6.0 1120.3 1867.2 ========= FINAL SCORE 1004.6 This patch: Remove refcnt from page_cgroup(). After this, * A page is charged only when !page_mapped() && no page_cgroup is assigned. * Anon page is newly mapped. * File page is added to mapping->tree. * A page is uncharged only when * Anon page is fully unmapped. * File page is removed from LRU. There is no change in behavior from user's view. This patch also removes unnecessary calls in rmap.c which was used only for refcnt mangement. [akpm@linux-foundation.org: fix warning] [hugh@veritas.com: fix shmem_unuse_inode charging] Signed-off-by: KAMEZAWA Hiroyuki Cc: Balbir Singh Cc: "Eric W. Biederman" Cc: Pavel Emelyanov Cc: Li Zefan Cc: Hugh Dickins Cc: YAMAMOTO Takashi Cc: Paul Menage Cc: David Rientjes Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 84ead2aa6f18..b4980b8f048e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -35,6 +35,7 @@ extern int mem_cgroup_charge(struct page *page, struct mm_struct *mm, extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); extern void mem_cgroup_uncharge_page(struct page *page); +extern void mem_cgroup_uncharge_cache_page(struct page *page); extern void mem_cgroup_move_lists(struct page *page, bool active); extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, struct list_head *dst, @@ -53,7 +54,6 @@ extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); extern int mem_cgroup_prepare_migration(struct page *page, struct page *newpage); extern void mem_cgroup_end_migration(struct page *page); -extern int mem_cgroup_getref(struct page *page); /* * For memory reclaim. @@ -98,6 +98,10 @@ static inline void mem_cgroup_uncharge_page(struct page *page) { } +static inline void mem_cgroup_uncharge_cache_page(struct page *page) +{ +} + static inline void mem_cgroup_move_lists(struct page *page, bool active) { } @@ -123,10 +127,6 @@ static inline void mem_cgroup_end_migration(struct page *page) { } -static inline void mem_cgroup_getref(struct page *page) -{ -} - static inline int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem) { return 0; -- cgit v1.2.3 From c9b0ed51483cc2fc42bb801b6675c4231b0e4634 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Fri, 25 Jul 2008 01:47:15 -0700 Subject: memcg: helper function for relcaim from shmem. A new call, mem_cgroup_shrink_usage() is added for shmem handling and relacing non-standard usage of mem_cgroup_charge/uncharge. Now, shmem calls mem_cgroup_charge() just for reclaim some pages from mem_cgroup. In general, shmem is used by some process group and not for global resource (like file caches). So, it's reasonable to reclaim pages from mem_cgroup where shmem is mainly used. [hugh@veritas.com: shmem_getpage release page sooner] [hugh@veritas.com: mem_cgroup_shrink_usage css_put] Signed-off-by: KAMEZAWA Hiroyuki Cc: Balbir Singh Cc: "Eric W. Biederman" Cc: Pavel Emelyanov Cc: Li Zefan Cc: YAMAMOTO Takashi Cc: Paul Menage Cc: David Rientjes Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b4980b8f048e..fdf3967e1397 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -37,6 +37,8 @@ extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, extern void mem_cgroup_uncharge_page(struct page *page); extern void mem_cgroup_uncharge_cache_page(struct page *page); extern void mem_cgroup_move_lists(struct page *page, bool active); +extern int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask); + extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, struct list_head *dst, unsigned long *scanned, int order, @@ -102,6 +104,11 @@ static inline void mem_cgroup_uncharge_cache_page(struct page *page) { } +static inline int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask) +{ + return 0; +} + static inline void mem_cgroup_move_lists(struct page *page, bool active) { } -- cgit v1.2.3 From 12b9804419cfb1c1bdac413f6c373af3b88d154b Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Fri, 25 Jul 2008 01:47:19 -0700 Subject: res_counter: limit change support ebusy Add an interface to set limit. This is necessary to memory resource controller because it shrinks usage at set limit. Other controllers may not need this interface to shrink usage because shrinking is not necessary or impossible. Acked-by: Balbir Singh Acked-by: Pavel Emelyanov Signed-off-by: KAMEZAWA Hiroyuki Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/res_counter.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index 290205dfe094..fdeadd9740dc 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -158,4 +158,20 @@ static inline void res_counter_reset_failcnt(struct res_counter *cnt) cnt->failcnt = 0; spin_unlock_irqrestore(&cnt->lock, flags); } + +static inline int res_counter_set_limit(struct res_counter *cnt, + unsigned long long limit) +{ + unsigned long flags; + int ret = -EBUSY; + + spin_lock_irqsave(&cnt->lock, flags); + if (cnt->usage < limit) { + cnt->limit = limit; + ret = 0; + } + spin_unlock_irqrestore(&cnt->lock, flags); + return ret; +} + #endif -- cgit v1.2.3 From 364d3c13c17f45da6d638011078d4c4d3070d719 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 25 Jul 2008 01:47:36 -0700 Subject: ptrace: give more respect to SIGKILL ptrace_stop() has some complicated checks to prevent the scheduling in the TASK_TRACED state with the pending SIGKILL, but these checks are racy, and they depend on arch_ptrace_stop_needed(). This patch assumes that the traced task should die asap if it was killed by SIGKILL, in that case schedule()->signal_pending_state() has no reason to ignore the TASK_WAKEKILL part of TASK_TRACED, and we can kill this nasty special case. Note: do_exit()->ptrace_notify() is special, the killed task can already dequeue SIGKILL at this point. Another indication that fatal_signal_pending() is not exactly right. Signed-off-by: Oleg Nesterov Cc: Ingo Molnar Cc: Matthew Wilcox Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6aca4a16e377..79e749dbf81e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2054,9 +2054,6 @@ static inline int signal_pending_state(long state, struct task_struct *p) if (!signal_pending(p)) return 0; - if (state & (__TASK_STOPPED | __TASK_TRACED)) - return 0; - return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); } -- cgit v1.2.3 From 7b34e4283c685f5cc6ba6d30e939906eee0d4bcf Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 25 Jul 2008 01:47:37 -0700 Subject: introduce PF_KTHREAD flag Introduce the new PF_KTHREAD flag to mark the kernel threads. It is set by INIT_TASK() and copied to the forked childs (we could set it in kthreadd() along with PF_NOFREEZE instead). daemonize() was changed as well. In that case testing of PF_KTHREAD is racy, but daemonize() is hopeless anyway. This flag is cleared in do_execve(), before search_binary_handler(). Probably not the best place, we can do this in exec_mmap() or in start_thread(), or clear it along with PF_FORKNOEXEC. But I think this doesn't matter in practice, and if do_execve() fails kthread should die soon. Signed-off-by: Oleg Nesterov Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 2 +- include/linux/sched.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 93c45acf249a..021d8e720c79 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -122,7 +122,7 @@ extern struct group_info init_groups; .state = 0, \ .stack = &init_thread_info, \ .usage = ATOMIC_INIT(2), \ - .flags = 0, \ + .flags = PF_KTHREAD, \ .lock_depth = -1, \ .prio = MAX_PRIO-20, \ .static_prio = MAX_PRIO-20, \ diff --git a/include/linux/sched.h b/include/linux/sched.h index 79e749dbf81e..eec64a4adb9d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1483,6 +1483,7 @@ static inline void put_task_struct(struct task_struct *t) #define PF_EXITING 0x00000004 /* getting shut down */ #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ +#define PF_KTHREAD 0x00000020 /* I am a kernel thread */ #define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */ #define PF_SUPERPRIV 0x00000100 /* used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* dumped core */ -- cgit v1.2.3 From 246bb0b1deb29726990620d8b5e55ca29f331362 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 25 Jul 2008 01:47:38 -0700 Subject: kill PF_BORROWED_MM in favour of PF_KTHREAD Kill PF_BORROWED_MM. Change use_mm/unuse_mm to not play with ->flags, and do s/PF_BORROWED_MM/PF_KTHREAD/ for a couple of other users. No functional changes yet. But this allows us to do further fixes/cleanups. oom_kill/ptrace/etc often check "p->mm != NULL" to filter out the kthreads, this is wrong because of use_mm(). The problem with PF_BORROWED_MM is that we need task_lock() to avoid races. With this patch we can check PF_KTHREAD directly, or use a simple lockless helper: /* The result must not be dereferenced !!! */ struct mm_struct *__get_task_mm(struct task_struct *tsk) { if (tsk->flags & PF_KTHREAD) return NULL; return tsk->mm; } Note also ecard_task(). It runs with ->mm != NULL, but it's the kernel thread without PF_BORROWED_MM. Signed-off-by: Oleg Nesterov Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index eec64a4adb9d..0560999eb1db 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1483,7 +1483,6 @@ static inline void put_task_struct(struct task_struct *t) #define PF_EXITING 0x00000004 /* getting shut down */ #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ -#define PF_KTHREAD 0x00000020 /* I am a kernel thread */ #define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */ #define PF_SUPERPRIV 0x00000100 /* used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* dumped core */ @@ -1497,7 +1496,7 @@ static inline void put_task_struct(struct task_struct *t) #define PF_KSWAPD 0x00040000 /* I am kswapd */ #define PF_SWAPOFF 0x00080000 /* I am in swapoff */ #define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */ -#define PF_BORROWED_MM 0x00200000 /* I am a kthread doing use_mm */ +#define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ #define PF_SPREAD_PAGE 0x01000000 /* Spread page cache over cpuset */ -- cgit v1.2.3 From 32ecb1f26dd50eeaac4e3f4dea4541c97848e459 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 25 Jul 2008 01:47:41 -0700 Subject: coredump: turn mm->core_startup_done into the pointer to struct core_state mm->core_startup_done points to "struct completion startup_done" allocated on the coredump_wait()'s stack. Introduce the new structure, core_state, which holds this "struct completion". This way we can add more info visible to the threads participating in coredump without enlarging mm_struct. No changes in affected .o files. Signed-off-by: Oleg Nesterov Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 02a27ae78539..97819efd2333 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -159,6 +159,10 @@ struct vm_area_struct { #endif }; +struct core_state { + struct completion startup; +}; + struct mm_struct { struct vm_area_struct * mmap; /* list of VMAs */ struct rb_root mm_rb; @@ -220,7 +224,8 @@ struct mm_struct { unsigned long flags; /* Must use atomic bitops to access the bits */ /* coredumping support */ - struct completion *core_startup_done, core_done; + struct core_state *core_state; + struct completion core_done; /* aio bits */ rwlock_t ioctx_list_lock; /* aio lock */ -- cgit v1.2.3 From 999d9fc1670bc082928b93b11d1f2e0e417d973c Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 25 Jul 2008 01:47:41 -0700 Subject: coredump: move mm->core_waiters into struct core_state Move mm->core_waiters into "struct core_state" allocated on stack. This shrinks mm_struct a little bit and allows further changes. This patch mostly does s/core_waiters/core_state. The only essential change is that coredump_wait() must clear mm->core_state before return. The coredump_wait()'s path is uglified and .text grows by 30 bytes, this is fixed by the next patch. Signed-off-by: Oleg Nesterov Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 97819efd2333..c0b1747b61a5 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -160,6 +160,7 @@ struct vm_area_struct { }; struct core_state { + int nr_threads; struct completion startup; }; @@ -179,7 +180,6 @@ struct mm_struct { atomic_t mm_users; /* How many users with user space? */ atomic_t mm_count; /* How many references to "struct mm_struct" (users count as 1) */ int map_count; /* number of VMAs */ - int core_waiters; struct rw_semaphore mmap_sem; spinlock_t page_table_lock; /* Protects page tables and some counters */ -- cgit v1.2.3 From c5f1cc8c1828486a61ab3e575da6e2c62b34d399 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 25 Jul 2008 01:47:42 -0700 Subject: coredump: turn core_state->nr_threads into atomic_t Turn core_state->nr_threads into atomic_t and kill now unneeded down_write(&mm->mmap_sem) in exit_mm(). Signed-off-by: Oleg Nesterov Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c0b1747b61a5..ae99a28ba6ae 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -160,7 +160,7 @@ struct vm_area_struct { }; struct core_state { - int nr_threads; + atomic_t nr_threads; struct completion startup; }; -- cgit v1.2.3 From b564daf806d492dd4f7afe9b6c83b8d35d137669 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 25 Jul 2008 01:47:44 -0700 Subject: coredump: construct the list of coredumping threads at startup time binfmt->core_dump() has to iterate over the all threads in system in order to find the coredumping threads and construct the list using the GFP_ATOMIC allocations. With this patch each thread allocates the list node on exit_mm()'s stack and adds itself to the list. This allows us to do further changes: - simplify ->core_dump() - change exit_mm() to clear ->mm first, then wait for ->core_done. this makes the coredumping process visible to oom_kill - kill mm->core_done Signed-off-by: Oleg Nesterov Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index ae99a28ba6ae..4d0d0abc79fe 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -159,8 +159,14 @@ struct vm_area_struct { #endif }; +struct core_thread { + struct task_struct *task; + struct core_thread *next; +}; + struct core_state { atomic_t nr_threads; + struct core_thread dumper; struct completion startup; }; -- cgit v1.2.3 From a94e2d408eaedbd85aae259621d46fafc10479a2 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 25 Jul 2008 01:47:46 -0700 Subject: coredump: kill mm->core_done Now that we have core_state->dumper list we can use it to wake up the sub-threads waiting for the coredump completion. This uglifies the code and .text grows by 47 bytes, but otoh mm_struct lessens by sizeof(struct completion). Also, with this change we can decouple exit_mm() from the coredumping code. Signed-off-by: Oleg Nesterov Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 4d0d0abc79fe..746f975b58ef 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -229,9 +229,7 @@ struct mm_struct { unsigned long flags; /* Must use atomic bitops to access the bits */ - /* coredumping support */ - struct core_state *core_state; - struct completion core_done; + struct core_state *core_state; /* coredumping support */ /* aio bits */ rwlock_t ioctx_list_lock; /* aio lock */ -- cgit v1.2.3 From db700897224b5ebdf852f2d38920ce428940d059 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 25 Jul 2008 01:47:49 -0700 Subject: workqueues: implement flush_work() Most of users of flush_workqueue() can be changed to use cancel_work_sync(), but sometimes we really need to wait for the completion and cancelling is not an option. schedule_on_each_cpu() is good example. Add the new helper, flush_work(work), which waits for the completion of the specific work_struct. More precisely, it "flushes" the result of of the last queue_work() which is visible to the caller. For example, this code queue_work(wq, work); /* WINDOW */ queue_work(wq, work); flush_work(work); doesn't necessary work "as expected". What can happen in the WINDOW above is - wq starts the execution of work->func() - the caller migrates to another CPU now, after the 2nd queue_work() this work is active on the previous CPU, and at the same time it is queued on another. In this case flush_work(work) may return before the first work->func() completes. It is trivial to add another helper int flush_work_sync(struct work_struct *work) { return flush_work(work) || wait_on_work(work); } which works "more correctly", but it has to iterate over all CPUs and thus it much slower than flush_work(). Signed-off-by: Oleg Nesterov Acked-by: Max Krasnyansky Acked-by: Jarek Poplawski Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/workqueue.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 14d47120682b..5c158c477ac7 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -201,6 +201,8 @@ extern int keventd_up(void); extern void init_workqueues(void); int execute_in_process_context(work_func_t fn, struct execute_work *); +extern int flush_work(struct work_struct *work); + extern int cancel_work_sync(struct work_struct *work); /* -- cgit v1.2.3 From 3da1c84c00c7e5fa8348336bd8c342f9128b0f14 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 25 Jul 2008 01:47:50 -0700 Subject: workqueues: make get_online_cpus() useable for work->func() workqueue_cpu_callback(CPU_DEAD) flushes cwq->thread under cpu_maps_update_begin(). This means that the multithreaded workqueues can't use get_online_cpus() due to the possible deadlock, very bad and very old problem. Introduce the new state, CPU_POST_DEAD, which is called after cpu_hotplug_done() but before cpu_maps_update_done(). Change workqueue_cpu_callback() to use CPU_POST_DEAD instead of CPU_DEAD. This means that create/destroy functions can't rely on get_online_cpus() any longer and should take cpu_add_remove_lock instead. [akpm@linux-foundation.org: fix CONFIG_SMP=n] Signed-off-by: Oleg Nesterov Acked-by: Gautham R Shenoy Cc: Heiko Carstens Cc: Max Krasnyansky Cc: Paul Jackson Cc: Paul Menage Cc: Peter Zijlstra Cc: Vegard Nossum Cc: Martin Schwidefsky Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpu.h | 15 +++++++++++---- include/linux/notifier.h | 2 ++ 2 files changed, 13 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 7464ba3b4333..d7faf8808497 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -69,10 +69,11 @@ static inline void unregister_cpu_notifier(struct notifier_block *nb) #endif int cpu_up(unsigned int cpu); - extern void cpu_hotplug_init(void); +extern void cpu_maps_update_begin(void); +extern void cpu_maps_update_done(void); -#else +#else /* CONFIG_SMP */ static inline int register_cpu_notifier(struct notifier_block *nb) { @@ -87,10 +88,16 @@ static inline void cpu_hotplug_init(void) { } +static inline void cpu_maps_update_begin(void) +{ +} + +static inline void cpu_maps_update_done(void) +{ +} + #endif /* CONFIG_SMP */ extern struct sysdev_class cpu_sysdev_class; -extern void cpu_maps_update_begin(void); -extern void cpu_maps_update_done(void); #ifdef CONFIG_HOTPLUG_CPU /* Stop CPUs going up and down. */ diff --git a/include/linux/notifier.h b/include/linux/notifier.h index bd3d72ddf333..da2698b0fdd1 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -214,6 +214,8 @@ static inline int notifier_to_errno(int ret) #define CPU_DEAD 0x0007 /* CPU (unsigned)v dead */ #define CPU_DYING 0x0008 /* CPU (unsigned)v not running any task, * not handling interrupts, soon dead */ +#define CPU_POST_DEAD 0x0009 /* CPU (unsigned)v dead, cpu_hotplug + * lock is dropped */ /* Used for CPU hotplug events occuring while tasks are frozen due to a suspend * operation in progress -- cgit v1.2.3 From 95b68dec0d52c7b8fea3698b3938cf3ab936436b Mon Sep 17 00:00:00 2001 From: Chandru Date: Fri, 25 Jul 2008 01:47:55 -0700 Subject: calgary iommu: use the first kernels TCE tables in kdump kdump kernel fails to boot with calgary iommu and aacraid driver on a x366 box. The ongoing dma's of aacraid from the first kernel continue to exist until the driver is loaded in the kdump kernel. Calgary is initialized prior to aacraid and creation of new tce tables causes wrong dma's to occur. Here we try to get the tce tables of the first kernel in kdump kernel and use them. While in the kdump kernel we do not allocate new tce tables but instead read the base address register contents of calgary iommu and use the tables that the registers point to. With these changes the kdump kernel and hence aacraid now boots normally. Signed-off-by: Chandru Siddalingappa Acked-by: Muli Ben-Yehuda Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/crash_dump.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 22c7ac5cd80c..6cd39a927e1f 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -22,5 +22,13 @@ extern struct proc_dir_entry *proc_vmcore; #define vmcore_elf_check_arch(x) (elf_check_arch(x) || vmcore_elf_check_arch_cross(x)) +static inline int is_kdump_kernel(void) +{ + return (elfcorehdr_addr != ELFCORE_ADDR_MAX) ? 1 : 0; +} +#else /* !CONFIG_CRASH_DUMP */ +static inline int is_kdump_kernel(void) { return 0; } #endif /* CONFIG_CRASH_DUMP */ + +extern unsigned long saved_max_pfn; #endif /* LINUX_CRASHDUMP_H */ -- cgit v1.2.3 From 2027d1abc25ff770cc3bc936abd33570ce85d85a Mon Sep 17 00:00:00 2001 From: Nadia Derbey Date: Fri, 25 Jul 2008 01:47:57 -0700 Subject: idr: change the idr structure After scalability problems have been detected when using the sysV ipcs, I have proposed to use an RCU based implementation of the IDR api instead (see threads http://lkml.org/lkml/2008/4/11/212 and http://lkml.org/lkml/2008/4/29/295). This resulted in many people asking to convert the idr API and make it rcu safe (because most of the code was duplicated and thus unmaintanable and unreviewable). So here is a first attempt. The important change wrt to the idr API itself is during idr removes: idr layers are freed after a grace period, instead of being moved to the free list. The important change wrt to ipcs, is that idr_find() can now be called locklessly inside a rcu read critical section. Here are the results I've got for the pmsg test sent by Manfred: 2.6.25-rc3-mm1 2.6.25-rc3-mm1+ 2.6.25-mm1 Patched 2.6.25-mm1 1 1168441 1064021 876000 947488 2 1094264 921059 1549592 1730685 3 2082520 1738165 1694370 2324880 4 2079929 1695521 404553 2400408 5 2898758 406566 391283 3246580 6 2921417 261275 263249 3752148 7 3308761 126056 191742 4243142 8 3329456 100129 141722 4275780 1st column: stock 2.6.25-rc3-mm1 2nd column: 2.6.25-rc3-mm1 + ipc patches (store ipcs into idrs) 3nd column: stock 2.6.25-mm1 4th column: 2.6.25-mm1 + this pacth series. This patch: Add an rcu_head to the idr_layer structure in order to free it after a grace period. Signed-off-by: Nadia Derbey Reviewed-by: "Paul E. McKenney" Cc: Manfred Spraul Cc: Jim Houston Cc: Pierre Peiffer Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 9a2d762124de..1af61d23be36 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -15,6 +15,7 @@ #include #include #include +#include #if BITS_PER_LONG == 32 # define IDR_BITS 5 @@ -51,6 +52,7 @@ struct idr_layer { unsigned long bitmap; /* A zero bit means "space here" */ struct idr_layer *ary[1< Date: Fri, 25 Jul 2008 01:47:59 -0700 Subject: idr: error checking factorization Do some code factorization in the return code analysis. Signed-off-by: Nadia Derbey Cc: "Paul E. McKenney" Cc: Manfred Spraul Cc: Jim Houston Cc: Pierre Peiffer Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 1af61d23be36..762c3f2c631d 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -73,6 +73,12 @@ struct idr { } #define DEFINE_IDR(name) struct idr name = IDR_INIT(name) +/* Actions to be taken after a call to _idr_sub_alloc */ +#define IDR_NEED_TO_GROW -2 +#define IDR_NOMORE_SPACE -3 + +#define _idr_rc_to_errno(rc) ((rc) == -1 ? -EAGAIN : -ENOSPC) + /* * This is what we export. */ -- cgit v1.2.3 From f9c46d6ea5ce138a886c3a0f10a46130afab75f5 Mon Sep 17 00:00:00 2001 From: Nadia Derbey Date: Fri, 25 Jul 2008 01:48:01 -0700 Subject: idr: make idr_find rcu-safe Make idr_find rcu-safe: it can now be called inside an rcu_read critical section. Signed-off-by: Nadia Derbey Reviewed-by: "Paul E. McKenney" Cc: Manfred Spraul Cc: Jim Houston Cc: Pierre Peiffer Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 762c3f2c631d..fa035f96f2a3 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -79,6 +79,22 @@ struct idr { #define _idr_rc_to_errno(rc) ((rc) == -1 ? -EAGAIN : -ENOSPC) +/** + * idr synchronization (stolen from radix-tree.h) + * + * idr_find() is able to be called locklessly, using RCU. The caller must + * ensure calls to this function are made within rcu_read_lock() regions. + * Other readers (lock-free or otherwise) and modifications may be running + * concurrently. + * + * It is still required that the caller manage the synchronization and + * lifetimes of the items. So if RCU lock-free lookups are used, typically + * this would mean that the items have their own locks, or are amenable to + * lock-free access; and that the items are freed by RCU (or only freed after + * having been deleted from the idr tree *and* a synchronize_rcu() grace + * period). + */ + /* * This is what we export. */ -- cgit v1.2.3 From 4daa28f6d8f5cda8ea0f55048e3c8811c384cbdd Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Fri, 25 Jul 2008 01:48:04 -0700 Subject: ipc/sem.c: convert undo structures to struct list_head The undo structures contain two linked lists, the attached patch replaces them with generic struct list_head lists. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Manfred Spraul Cc: Nadia Derbey Cc: Pierre Peiffer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sem.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sem.h b/include/linux/sem.h index c8eaad9e4b72..6a1af1b49a13 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -95,7 +95,7 @@ struct sem_array { struct sem *sem_base; /* ptr to first semaphore in array */ struct sem_queue *sem_pending; /* pending operations to be processed */ struct sem_queue **sem_pending_last; /* last pending operation */ - struct sem_undo *undo; /* undo requests on this array */ + struct list_head list_id; /* undo requests on this array */ unsigned long sem_nsems; /* no. of semaphores in array */ }; @@ -118,8 +118,8 @@ struct sem_queue { * when the process exits. */ struct sem_undo { - struct sem_undo * proc_next; /* next entry on this process */ - struct sem_undo * id_next; /* next entry on this semaphore set */ + struct list_head list_proc; /* per-process list: all undos from one process */ + struct list_head list_id; /* per semaphore array list: all undos for one array */ int semid; /* semaphore set identifier */ short * semadj; /* array of adjustments, one per semaphore */ }; @@ -128,9 +128,9 @@ struct sem_undo { * that may be shared among all a CLONE_SYSVSEM task group. */ struct sem_undo_list { - atomic_t refcnt; - spinlock_t lock; - struct sem_undo *proc_list; + atomic_t refcnt; + spinlock_t lock; + struct list_head list_proc; }; struct sysv_sem { -- cgit v1.2.3 From 2c0c29d414087f3b021059673c20a7088f5f1fff Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Fri, 25 Jul 2008 01:48:05 -0700 Subject: ipc/sem.c: remove unused entries from struct sem_queue sem_queue.sma and sem_queue.id were never used, the attached patch removes them. Signed-off-by: Manfred Spraul Reviewed-by: Nadia Derbey Cc: Pierre Peiffer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sem.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sem.h b/include/linux/sem.h index 6a1af1b49a13..87756ef1198e 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -107,8 +107,6 @@ struct sem_queue { struct sem_undo * undo; /* undo structure */ int pid; /* process id of requesting process */ int status; /* completion status of operation */ - struct sem_array * sma; /* semaphore array for operations */ - int id; /* internal sem id */ struct sembuf * sops; /* array of pending operations */ int nsops; /* number of operations */ int alter; /* does the operation alter the array? */ -- cgit v1.2.3 From a1193f8ec091cd8fd309cc2982abe4499f6f2b4d Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Fri, 25 Jul 2008 01:48:06 -0700 Subject: ipc/sem.c: convert sem_array.sem_pending to struct list_head sem_array.sem_pending is a double linked list, the attached patch converts it to struct list_head. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Manfred Spraul Reviewed-by: Nadia Derbey Cc: Pierre Peiffer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sem.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sem.h b/include/linux/sem.h index 87756ef1198e..d42599395d79 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -93,21 +93,19 @@ struct sem_array { time_t sem_otime; /* last semop time */ time_t sem_ctime; /* last change time */ struct sem *sem_base; /* ptr to first semaphore in array */ - struct sem_queue *sem_pending; /* pending operations to be processed */ - struct sem_queue **sem_pending_last; /* last pending operation */ + struct list_head sem_pending; /* pending operations to be processed */ struct list_head list_id; /* undo requests on this array */ unsigned long sem_nsems; /* no. of semaphores in array */ }; /* One queue for each sleeping process in the system. */ struct sem_queue { - struct sem_queue * next; /* next entry in the queue */ - struct sem_queue ** prev; /* previous entry in the queue, *(q->prev) == q */ - struct task_struct* sleeper; /* this process */ - struct sem_undo * undo; /* undo structure */ + struct list_head list; /* queue of pending operations */ + struct task_struct *sleeper; /* this process */ + struct sem_undo *undo; /* undo structure */ int pid; /* process id of requesting process */ int status; /* completion status of operation */ - struct sembuf * sops; /* array of pending operations */ + struct sembuf *sops; /* array of pending operations */ int nsops; /* number of operations */ int alter; /* does the operation alter the array? */ }; -- cgit v1.2.3 From 380af1b33b3ff92df5cda96329b58f5d1b6b5a53 Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Fri, 25 Jul 2008 01:48:06 -0700 Subject: ipc/sem.c: rewrite undo list locking The attached patch: - reverses the locking order of ulp->lock and sem_lock: Previously, it was first ulp->lock, then inside sem_lock. Now it's the other way around. - converts the undo structure to rcu. Benefits: - With the old locking order, IPC_RMID could not kfree the undo structures. The stale entries remained in the linked lists and were released later. - The patch fixes a a race in semtimedop(): if both IPC_RMID and a semget() that recreates exactly the same id happen between find_alloc_undo() and sem_lock, then semtimedop() would access already kfree'd memory. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Manfred Spraul Reviewed-by: Nadia Derbey Cc: Pierre Peiffer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sem.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sem.h b/include/linux/sem.h index d42599395d79..1b191c176bcd 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -78,6 +78,7 @@ struct seminfo { #ifdef __KERNEL__ #include +#include struct task_struct; @@ -114,7 +115,10 @@ struct sem_queue { * when the process exits. */ struct sem_undo { - struct list_head list_proc; /* per-process list: all undos from one process */ + struct list_head list_proc; /* per-process list: all undos from one process. */ + /* rcu protected */ + struct rcu_head rcu; /* rcu struct for sem_undo() */ + struct sem_undo_list *ulp; /* sem_undo_list for the process */ struct list_head list_id; /* per semaphore array list: all undos for one array */ int semid; /* semaphore set identifier */ short * semadj; /* array of adjustments, one per semaphore */ -- cgit v1.2.3 From 9eefe520c814f6f62c5d36a2ddcd3fb99dfdb30e Mon Sep 17 00:00:00 2001 From: Nadia Derbey Date: Fri, 25 Jul 2008 01:48:08 -0700 Subject: ipc: do not use a negative value to re-enable msgmni automatic recomputing This patch proposes an alternative to the "magical positive-versus-negative number trick" Andrew complained about last week in http://lkml.org/lkml/2008/6/24/418. This had been introduced with the patches that scale msgmni to the amount of lowmem. With these patches, msgmni has a registered notification routine that recomputes msgmni value upon memory add/remove or ipc namespace creation/ removal. When msgmni is changed from user space (i.e. value written to the proc file), that notification routine is unregistered, and the way to make it registered back is to write a negative value into the proc file. This is the "magical positive-versus-negative number trick". To fix this, a new proc file is introduced: /proc/sys/kernel/auto_msgmni. This file acts as ON/OFF for msgmni automatic recomputing. With this patch, the process is the following: 1) kernel boots in "automatic recomputing mode" /proc/sys/kernel/msgmni contains the value that has been computed (depends on lowmem) /proc/sys/kernel/automatic_msgmni contains "1" 2) echo > /proc/sys/kernel/msgmni . sets msg_ctlmni to . de-activates automatic recomputing (i.e. if, say, some memory is added msgmni won't be recomputed anymore) . /proc/sys/kernel/automatic_msgmni now contains "0" 3) echo "0" > /proc/sys/kernel/automatic_msgmni . de-activates msgmni automatic recomputing this has the same effect as 2) except that msg_ctlmni's value stays blocked at its current value) 3) echo "1" > /proc/sys/kernel/automatic_msgmni . recomputes msgmni's value based on the current available memory size and number of ipc namespaces . re-activates automatic recomputing for msgmni. Signed-off-by: Nadia Derbey Cc: Solofo Ramangalahy Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index ea6c18a8b0d4..ea330f9e7100 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -36,6 +36,7 @@ struct ipc_namespace { int msg_ctlmni; atomic_t msg_bytes; atomic_t msg_hdrs; + int auto_msgmni; size_t shm_ctlmax; size_t shm_ctlall; @@ -53,7 +54,7 @@ extern atomic_t nr_ipc_ns; extern int register_ipcns_notifier(struct ipc_namespace *); extern int cond_register_ipcns_notifier(struct ipc_namespace *); -extern int unregister_ipcns_notifier(struct ipc_namespace *); +extern void unregister_ipcns_notifier(struct ipc_namespace *); extern int ipcns_notify(unsigned long); #else /* CONFIG_SYSVIPC */ -- cgit v1.2.3 From d805dda412346225a50af2d399d958a4bc676c38 Mon Sep 17 00:00:00 2001 From: Abdel Benamrouche Date: Fri, 25 Jul 2008 01:48:25 -0700 Subject: fs/partition/check.c: fix return value warning fs/partitions/check.c:381: warning: ignoring return value of ___device_add___, declared with attribute warn_unused_result [akpm@linux-foundation.org: multiple-return-statements-per-function are evil] Signed-off-by: Abdel Benamrouche Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/genhd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index e8787417f65a..118216f1bd3c 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -541,7 +541,7 @@ extern dev_t blk_lookup_devt(const char *name, int part); extern char *disk_name (struct gendisk *hd, int part, char *buf); extern int rescan_partitions(struct gendisk *disk, struct block_device *bdev); -extern void add_partition(struct gendisk *, int, sector_t, sector_t, int); +extern int __must_check add_partition(struct gendisk *, int, sector_t, sector_t, int); extern void delete_partition(struct gendisk *, int); extern void printk_all_partitions(void); -- cgit v1.2.3 From 6e644c3126149b65460610fe5a00d8a162092abe Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 01:48:28 -0700 Subject: move proc_kmsg_operations to fs/proc/internal.h This patch moves the extern of struct proc_kmsg_operations to fs/proc/internal.h and adds an #include "internal.h" to fs/proc/kmsg.c so that the latter sees the former. Signed-off-by: Adrian Bunk Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/proc_fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 15a9eaf4a802..cdabc2fc02f7 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -138,7 +138,6 @@ extern int proc_readdir(struct file *, void *, filldir_t); extern struct dentry *proc_lookup(struct inode *, struct dentry *, struct nameidata *); extern const struct file_operations proc_kcore_operations; -extern const struct file_operations proc_kmsg_operations; extern const struct file_operations ppc_htab_operations; extern int pid_ns_prepare_proc(struct pid_namespace *ns); -- cgit v1.2.3 From 881adb85358309ea9c6f707394002719982ec607 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 25 Jul 2008 01:48:29 -0700 Subject: proc: always do ->release Current two-stage scheme of removing PDE emphasizes one bug in proc: open rmmod remove_proc_entry close ->release won't be called because ->proc_fops were cleared. In simple cases it's small memory leak. For every ->open, ->release has to be done. List of openers is introduced which is traversed at remove_proc_entry() if neeeded. Discussions with Al long ago (sigh). Signed-off-by: Alexey Dobriyan Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/proc_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index cdabc2fc02f7..f560d1705afe 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -79,6 +79,7 @@ struct proc_dir_entry { int pde_users; /* number of callers into module in progress */ spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */ struct completion *pde_unload_completion; + struct list_head pde_openers; /* who did ->open, but not ->release */ }; struct kcore_list { -- cgit v1.2.3 From 3ae4eed34be0177a8e003411a84e4ee212adbced Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 01:48:34 -0700 Subject: proper pid{hash,map}_init() prototypes This patch adds proper prototypes for pid{hash,map}_init() in include/linux/pid_namespace.h Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pid_namespace.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index caff5283d15c..1a49ab5ec7b9 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -85,4 +85,7 @@ static inline struct task_struct *task_child_reaper(struct task_struct *tsk) return tsk->nsproxy->pid_ns->child_reaper; } +void pidhash_init(void); +void pidmap_init(void); + #endif /* _LINUX_PID_NS_H */ -- cgit v1.2.3 From 33166b1ffca5e1945246bcaa77d72a22b0d3e531 Mon Sep 17 00:00:00 2001 From: Richard Kennedy Date: Fri, 25 Jul 2008 01:48:35 -0700 Subject: shrink struct pid by removing padding on 64 bit builds When struct pid is built on a 64 bit platform gcc has to insert padding to maintain the correct alignment, by simply reordering its members the memory usage shrinks from 88 bytes to 80. I've successfully run with this patch on my desktop AMD64 machine. There are no significant kernel size changes to a default config.X86_64 on the latest git v2.6.26-rc1 text data bss dec hex filename 5404828 976760 734280 7115868 6c945c vmlinux 5404811 976760 734280 7115851 6c944b vmlinux.pid-patch Acked-by: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pid.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index c21c7e8124a7..6f084b9e2c40 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -57,10 +57,10 @@ struct upid { struct pid { atomic_t count; + unsigned int level; /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; struct rcu_head rcu; - unsigned int level; struct upid numbers[1]; }; -- cgit v1.2.3 From 19b0cfcca41dd772065671ad0584e1cea0f3fd13 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Fri, 25 Jul 2008 01:48:35 -0700 Subject: pidns: remove now unused kill_proc function This function operated on a pid_t to kill a task, which is no longer valid in a containerized system. It has finally lost all its users and we can safely remove it from the tree. Signed-off-by: Pavel Emelyanov Cc: Oleg Nesterov Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 0560999eb1db..134cb5cb506c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1800,7 +1800,6 @@ extern void force_sig(int, struct task_struct *); extern void force_sig_specific(int, struct task_struct *); extern int send_sig(int, struct task_struct *, int); extern void zap_other_threads(struct task_struct *p); -extern int kill_proc(pid_t, int, int); extern struct sigqueue *sigqueue_alloc(void); extern void sigqueue_free(struct sigqueue *); extern int send_sigqueue(struct sigqueue *, struct task_struct *, int group); -- cgit v1.2.3 From e49859e71e0318b564de1546bdc30fab738f9deb Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Fri, 25 Jul 2008 01:48:36 -0700 Subject: pidns: remove now unused find_pid function. This one had the only users so far - the kill_proc, which is removed, so drop this (invalid in namespaced world) call too. And of course - erase all references on it from comments. Signed-off-by: Pavel Emelyanov Cc: Oleg Nesterov Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pid.h | 4 +--- include/linux/sched.h | 2 +- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index 6f084b9e2c40..ff1b2a5814d4 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -48,7 +48,7 @@ enum pid_type */ struct upid { - /* Try to keep pid_chain in the same cacheline as nr for find_pid */ + /* Try to keep pid_chain in the same cacheline as nr for find_vpid */ int nr; struct pid_namespace *ns; struct hlist_node pid_chain; @@ -105,14 +105,12 @@ extern struct pid_namespace init_pid_ns; * or rcu_read_lock() held. * * find_pid_ns() finds the pid in the namespace specified - * find_pid() find the pid by its global id, i.e. in the init namespace * find_vpid() finr the pid by its virtual id, i.e. in the current namespace * * see also find_task_by_pid() set in include/linux/sched.h */ extern struct pid *find_pid_ns(int nr, struct pid_namespace *ns); extern struct pid *find_vpid(int nr); -extern struct pid *find_pid(int nr); /* * Lookup a PID in the hash table, and return with it's count elevated. diff --git a/include/linux/sched.h b/include/linux/sched.h index 134cb5cb506c..182da1550fad 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1718,7 +1718,7 @@ extern struct pid_namespace init_pid_ns; * find_task_by_pid(): * finds a task by its global pid * - * see also find_pid() etc in include/linux/pid.h + * see also find_vpid() etc in include/linux/pid.h */ extern struct task_struct *find_task_by_pid_type_ns(int type, int pid, -- cgit v1.2.3 From dbda0de52618d13d1b927c7ba7bb839cfddc4e8c Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Fri, 25 Jul 2008 01:48:37 -0700 Subject: pidns: remove find_task_by_pid, unused for a long time It seems to me that it was a mistake marking this function as deprecated and scheduling it for removal, rather than resolutely removing it after the last caller's death. Anyway - better late, then never. Signed-off-by: Pavel Emelyanov Cc: Oleg Nesterov Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pid.h | 2 +- include/linux/sched.h | 6 ------ 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index ff1b2a5814d4..22921ac4cfd9 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -107,7 +107,7 @@ extern struct pid_namespace init_pid_ns; * find_pid_ns() finds the pid in the namespace specified * find_vpid() finr the pid by its virtual id, i.e. in the current namespace * - * see also find_task_by_pid() set in include/linux/sched.h + * see also find_task_by_vpid() set in include/linux/sched.h */ extern struct pid *find_pid_ns(int nr, struct pid_namespace *ns); extern struct pid *find_vpid(int nr); diff --git a/include/linux/sched.h b/include/linux/sched.h index 182da1550fad..354ef478a80d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1715,8 +1715,6 @@ extern struct pid_namespace init_pid_ns; * finds a task by its pid in the specified namespace * find_task_by_vpid(): * finds a task by its virtual pid - * find_task_by_pid(): - * finds a task by its global pid * * see also find_vpid() etc in include/linux/pid.h */ @@ -1724,10 +1722,6 @@ extern struct pid_namespace init_pid_ns; extern struct task_struct *find_task_by_pid_type_ns(int type, int pid, struct pid_namespace *ns); -static inline struct task_struct *__deprecated find_task_by_pid(pid_t nr) -{ - return find_task_by_pid_type_ns(PIDTYPE_PID, nr, &init_pid_ns); -} extern struct task_struct *find_task_by_vpid(pid_t nr); extern struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns); -- cgit v1.2.3 From 49b5cf34727a6c1be1568ab28e89a2d9a6bf51e0 Mon Sep 17 00:00:00 2001 From: Jonathan Lim Date: Fri, 25 Jul 2008 01:48:40 -0700 Subject: accounting: account for user time when updating memory integrals Adapt acct_update_integrals() to include user time when calculating the time difference. The units of acct_rss_mem1 and acct_vm_mem1 are also changed from pages-jiffies to pages-usecs to avoid calling jiffies_to_usecs() in xacct_add_tsk() which might overflow. Signed-off-by: Jonathan Lim Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 354ef478a80d..af780f299c7c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1257,7 +1257,7 @@ struct task_struct { #if defined(CONFIG_TASK_XACCT) u64 acct_rss_mem1; /* accumulated rss usage */ u64 acct_vm_mem1; /* accumulated virtual memory usage */ - cputime_t acct_stimexpd;/* stime since last update */ + cputime_t acct_timexpd; /* stime + utime since last update */ #endif #ifdef CONFIG_CPUSETS nodemask_t mems_allowed; -- cgit v1.2.3 From 20fad13ac66ac001c19220d3d08b4de5b6cca6e1 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Fri, 25 Jul 2008 01:48:43 -0700 Subject: pidns: add the struct bsd_acct_struct pointer on pid_namespace struct All the bsdacct-related info will be stored in the area, pointer by this one. It will be NULL automatically for all new namespaces. Signed-off-by: Pavel Emelyanov Cc: Balbir Singh Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pid_namespace.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 1a49ab5ec7b9..1af82c4e17d4 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -14,6 +14,8 @@ struct pidmap { #define PIDMAP_ENTRIES ((PID_MAX_LIMIT + 8*PAGE_SIZE - 1)/PAGE_SIZE/8) +struct bsd_acct_struct; + struct pid_namespace { struct kref kref; struct pidmap pidmap[PIDMAP_ENTRIES]; @@ -25,6 +27,9 @@ struct pid_namespace { #ifdef CONFIG_PROC_FS struct vfsmount *proc_mnt; #endif +#ifdef CONFIG_BSD_PROCESS_ACCT + struct bsd_acct_struct *bacct; +#endif }; extern struct pid_namespace init_pid_ns; -- cgit v1.2.3 From 0b6b030fc30d169bb406b34b4fc60d99dde4a9c6 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Fri, 25 Jul 2008 01:48:47 -0700 Subject: bsdacct: switch from global bsd_acct_struct instance to per-pidns one Allocate the structure on the first call to sys_acct(). After this each namespace, that ordered the accounting, will live with this structure till its own death. Two notes - routines, that close the accounting on fs umount time use the init_pid_ns's acct by now; - accounting routine accounts to dying task's namespace (also by now). Signed-off-by: Pavel Emelyanov Cc: Balbir Singh Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/acct.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acct.h b/include/linux/acct.h index e8cae54e8d88..882dc7248766 100644 --- a/include/linux/acct.h +++ b/include/linux/acct.h @@ -120,17 +120,20 @@ struct acct_v3 struct vfsmount; struct super_block; struct pacct_struct; +struct pid_namespace; extern void acct_auto_close_mnt(struct vfsmount *m); extern void acct_auto_close(struct super_block *sb); extern void acct_init_pacct(struct pacct_struct *pacct); extern void acct_collect(long exitcode, int group_dead); extern void acct_process(void); +extern void acct_exit_ns(struct pid_namespace *); #else #define acct_auto_close_mnt(x) do { } while (0) #define acct_auto_close(x) do { } while (0) #define acct_init_pacct(x) do { } while (0) #define acct_collect(x,y) do { } while (0) #define acct_process() do { } while (0) +#define acct_exit_ns(ns) do { } while (0) #endif /* -- cgit v1.2.3 From 297c5d92634c809cef23d73e7b2556f2528ff7e2 Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Fri, 25 Jul 2008 01:48:49 -0700 Subject: task IO accounting: provide distinct tgid/tid I/O statistics Report per-thread I/O statistics in /proc/pid/task/tid/io and aggregate parent I/O statistics in /proc/pid/io. This approach follows the same model used to account per-process and per-thread CPU times. As a practial application, this allows for example to quickly find the top I/O consumer when a process spawns many child threads that perform the actual I/O work, because the aggregated I/O statistics can always be found in /proc/pid/io. [ Oleg Nesterov points out that we should check that the task is still alive before we iterate over the threads, but also says that we can do that fixup on top of this later. - Linus ] Acked-by: Balbir Singh Signed-off-by: Andrea Righi Cc: Matt Heaton Cc: Shailabh Nagar Acked-by-with-comments: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index af780f299c7c..d22ffe06d0eb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -506,6 +506,10 @@ struct signal_struct { unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; +#ifdef CONFIG_TASK_XACCT + u64 rchar, wchar, syscr, syscw; +#endif + struct task_io_accounting ioac; /* * Cumulative ns of scheduled CPU time for dead threads in the -- cgit v1.2.3 From 873b47717732c2f33a4b14de02571a4295a02f0c Mon Sep 17 00:00:00 2001 From: Keika Kobayashi Date: Fri, 25 Jul 2008 01:48:52 -0700 Subject: per-task-delay-accounting: add memory reclaim delay Sometimes, application responses become bad under heavy memory load. Applications take a bit time to reclaim memory. The statistics, how long memory reclaim takes, will be useful to measure memory usage. This patch adds accounting memory reclaim to per-task-delay-accounting for accounting the time of do_try_to_free_pages(). - When System is under low memory load, memory reclaim may not occur. $ free total used free shared buffers cached Mem: 8197800 1577300 6620500 0 4808 1516724 -/+ buffers/cache: 55768 8142032 Swap: 16386292 0 16386292 $ vmstat 1 procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu---- r b swpd free buff cache si so bi bo in cs us sy id wa 0 0 0 5069748 10612 3014060 0 0 0 0 3 26 0 0 100 0 0 0 0 5069748 10612 3014060 0 0 0 0 4 22 0 0 100 0 0 0 0 5069748 10612 3014060 0 0 0 0 3 18 0 0 100 0 Measure the time of tar command. $ ls -s test.dat 1501472 test.dat $ time tar cvf test.tar test.dat real 0m13.388s user 0m0.116s sys 0m5.304s $ ./delayget -d -p CPU count real total virtual total delay total 428 5528345500 5477116080 62749891 IO count delay total 338 8078977189 SWAP count delay total 0 0 RECLAIM count delay total 0 0 - When system is under heavy memory load memory reclaim may occur. $ vmstat 1 procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu---- r b swpd free buff cache si so bi bo in cs us sy id wa 0 0 7159032 49724 1812 3012 0 0 0 0 3 24 0 0 100 0 0 0 7159032 49724 1812 3012 0 0 0 0 4 24 0 0 100 0 0 0 7159032 49848 1812 3012 0 0 0 0 3 22 0 0 100 0 In this case, one process uses more 8G memory by execution of malloc() and memset(). $ time tar cvf test.tar test.dat real 1m38.563s <- increased by 85 sec user 0m0.140s sys 0m7.060s $ ./delayget -d -p CPU count real total virtual total delay total 9021 7140446250 7315277975 923201824 IO count delay total 8965 90466349669 SWAP count delay total 3 21036367 RECLAIM count delay total 740 61011951153 In the later case, the value of RECLAIM is increasing. So, taskstats can show how much memory reclaim influences TAT. Signed-off-by: Keika Kobayashi Acked-by: Balbir Singh Acked-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/delayacct.h | 19 +++++++++++++++++++ include/linux/sched.h | 4 ++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index ab94bc083558..f352f06fa063 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -39,6 +39,8 @@ extern void __delayacct_blkio_start(void); extern void __delayacct_blkio_end(void); extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *); extern __u64 __delayacct_blkio_ticks(struct task_struct *); +extern void __delayacct_freepages_start(void); +extern void __delayacct_freepages_end(void); static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) { @@ -107,6 +109,18 @@ static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk) return 0; } +static inline void delayacct_freepages_start(void) +{ + if (current->delays) + __delayacct_freepages_start(); +} + +static inline void delayacct_freepages_end(void) +{ + if (current->delays) + __delayacct_freepages_end(); +} + #else static inline void delayacct_set_flag(int flag) {} @@ -129,6 +143,11 @@ static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk) { return 0; } static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) { return 0; } +static inline void delayacct_freepages_start(void) +{} +static inline void delayacct_freepages_end(void) +{} + #endif /* CONFIG_TASK_DELAY_ACCT */ #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index d22ffe06d0eb..42036ffe6b00 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -672,6 +672,10 @@ struct task_delay_info { /* io operations performed */ u32 swapin_count; /* total count of the number of swapin block */ /* io operations performed */ + + struct timespec freepages_start, freepages_end; + u64 freepages_delay; /* wait for memory reclaim */ + u32 freepages_count; /* total count of memory reclaim */ }; #endif /* CONFIG_TASK_DELAY_ACCT */ -- cgit v1.2.3 From 016ae219b920c4e606088761d3d6070cdf8ba706 Mon Sep 17 00:00:00 2001 From: Keika Kobayashi Date: Fri, 25 Jul 2008 01:48:53 -0700 Subject: per-task-delay-accounting: update taskstats for memory reclaim delay Add members for memory reclaim delay to taskstats, and accumulate them in __delayacct_add_tsk() . Signed-off-by: Keika Kobayashi Cc: Hiroshi Shimamoto Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/taskstats.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/taskstats.h b/include/linux/taskstats.h index 5d69c0744fff..18269e956a71 100644 --- a/include/linux/taskstats.h +++ b/include/linux/taskstats.h @@ -31,7 +31,7 @@ */ -#define TASKSTATS_VERSION 6 +#define TASKSTATS_VERSION 7 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -157,6 +157,10 @@ struct taskstats { __u64 ac_utimescaled; /* utime scaled on frequency etc */ __u64 ac_stimescaled; /* stime scaled on frequency etc */ __u64 cpu_scaled_run_real_total; /* scaled cpu_run_real_total */ + + /* Delay waiting for memory reclaim */ + __u64 freepages_count; + __u64 freepages_delay_total; }; -- cgit v1.2.3 From bde74e4bc64415b142e556a34d295a52a1b7da9d Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 25 Jul 2008 01:48:57 -0700 Subject: locks: add special return value for asynchronous locks Use a special error value FILE_LOCK_DEFERRED to mean that a locking operation returned asynchronously. This is returned by posix_lock_file() for sleeping locks to mean that the lock has been queued on the block list, and will be woken up when it might become available and needs to be retried (either fl_lmops->fl_notify() is called or fl_wait is woken up). f_op->lock() to mean either the above, or that the filesystem will call back with fl_lmops->fl_grant() when the result of the locking operation is known. The filesystem can do this for sleeping as well as non-sleeping locks. This is to make sure, that return values of -EAGAIN and -EINPROGRESS by filesystems are not mistaken to mean an asynchronous locking. This also makes error handling in fs/locks.c and lockd/svclock.c slightly cleaner. Signed-off-by: Miklos Szeredi Cc: Trond Myklebust Cc: "J. Bruce Fields" Cc: Matthew Wilcox Cc: David Teigland Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4b86f806014c..49d8eb7a71be 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -885,6 +885,12 @@ static inline int file_check_writeable(struct file *filp) #define FL_CLOSE 64 /* unlock on close */ #define FL_SLEEP 128 /* A blocking lock */ +/* + * Special return value from posix_lock_file() and vfs_lock_file() for + * asynchronous locking. + */ +#define FILE_LOCK_DEFERRED 1 + /* * The POSIX file lock owner is determined by * the "struct files_struct" in the thread group -- cgit v1.2.3 From 33670fa296860283f04a7975b8c790f101e43a6e Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 25 Jul 2008 01:49:02 -0700 Subject: fuse: nfs export special lookups Implement the get_parent export operation by sending a LOOKUP request with ".." as the name. Implement looking up an inode by node ID after it has been evicted from the cache. This is done by seding a LOOKUP request with "." as the name (for all file types, not just directories). The filesystem can set the FUSE_EXPORT_SUPPORT flag in the INIT reply, to indicate that it supports these special lookups. Thanks to John Muir for the original implementation of this feature. Signed-off-by: Miklos Szeredi Cc: "J. Bruce Fields" Cc: Trond Myklebust Cc: Matthew Wilcox Cc: David Teigland Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fuse.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index d48282197696..265635dc9908 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -104,11 +104,14 @@ struct fuse_file_lock { /** * INIT request/reply flags + * + * FUSE_EXPORT_SUPPORT: filesystem handles lookups of "." and ".." */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) #define FUSE_FILE_OPS (1 << 2) #define FUSE_ATOMIC_O_TRUNC (1 << 3) +#define FUSE_EXPORT_SUPPORT (1 << 4) #define FUSE_BIG_WRITES (1 << 5) /** -- cgit v1.2.3 From 8f421c595a9145959d8aab09172743132abdffdb Mon Sep 17 00:00:00 2001 From: Arthur Jones Date: Fri, 25 Jul 2008 01:49:04 -0700 Subject: edac: i5100 new intel chipset driver Preliminary support for the Intel 5100 MCH. CE and UE errors are reported along with the current DIMM label information and other memory parameters. Reasons why this is preliminary: 1) This chip has 2 independent memory controllers which, for best perforance, use interleaved accesses to the DDR2 memory. This architecture does not map very well to the current edac data structures which depend on symmetric channel access to the interleaved data. Without core changes, the best I could do for now is to map both memory controllers to different csrows (first all ranks of controller 0, then all ranks of controller 1). Someone much more familiar with the edac core than I will probably need to come up with a more general data structure to handle the interleaving and de-interleaving of the two memory controllers. 2) I have not yet tackled the de-interleaving of the rank/controller address space into the physical address space of the CPU. There is nothing fundamentally missing, it is just ending up to be a lot of code, and I'd rather keep it separate for now, esp since it doesn't work yet... 3) The code depends on a particular i5100 chip select to DIMM mainboard chip select mapping. This mapping seems obvious to me in order to support dual and single ranked memory, but it is not unique and DIMM labels could be wrong on other mainboards. There is no way to query this mapping that I know of. 4) The code requires that the i5100 is in 32GB mode. Only 4 ranks per controller, 2 ranks per DIMM are supported. I do not have hardware (nor do I expect to have hardware anytime soon) for the 48GB (6 ranks per controller) mode. 5) The serial presence detect code should be broken out into a "real" i2c driver so that decode-dimms.pl can work. Signed-off-by: Arthur Jones Signed-off-by: Doug Thompson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci_ids.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 119ae7b8f028..c3b1761aba26 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2400,6 +2400,9 @@ #define PCI_DEVICE_ID_INTEL_ICH10_4 0x3a30 #define PCI_DEVICE_ID_INTEL_ICH10_5 0x3a60 #define PCI_DEVICE_ID_INTEL_IOAT_SNB 0x402f +#define PCI_DEVICE_ID_INTEL_5100_16 0x65f0 +#define PCI_DEVICE_ID_INTEL_5100_21 0x65f5 +#define PCI_DEVICE_ID_INTEL_5100_22 0x65f6 #define PCI_DEVICE_ID_INTEL_5400_ERR 0x4030 #define PCI_DEVICE_ID_INTEL_5400_FBD0 0x4035 #define PCI_DEVICE_ID_INTEL_5400_FBD1 0x4036 -- cgit v1.2.3 From 7dcf2a9fced59e58e4694cdcf15850c01fdba89b Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Tue, 1 Jul 2008 19:27:16 +0300 Subject: remove dummy asm/kvm.h files This patch removes the dummy asm/kvm.h files on architectures not (yet) supporting KVM and uses the same conditional headers installation as already used for a.out.h . Also removed are superfluous install rules in the s390 and x86 Kbuild files (they are already in Kbuild.asm). Signed-off-by: Adrian Bunk Acked-by: Sam Ravnborg Signed-off-by: David Woodhouse --- include/linux/Kbuild | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 71d70d1fbce2..402c8f55d713 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -256,7 +256,9 @@ unifdef-y += kd.h unifdef-y += kernelcapi.h unifdef-y += kernel.h unifdef-y += keyboard.h +ifneq ($(wildcard $(srctree)/include/asm-$(SRCARCH)/kvm.h),) unifdef-y += kvm.h +endif unifdef-y += llc.h unifdef-y += loop.h unifdef-y += lp.h -- cgit v1.2.3 From c6af5e9f8a57467df2e55e428316a43480174521 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 25 Jul 2008 15:48:04 +0200 Subject: bootmem: Move node allocation macros back to !HAVE_ARCH_BOOTMEM_NODE These got unintentionally moved, put them back as x86 provides its own versions. Signed-off-by: Johannes Weiner Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 4ddf2922fc8d..652470b687c9 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -103,17 +103,16 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, __alloc_bootmem(x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_low_pages(x) \ __alloc_bootmem_low(x, PAGE_SIZE, 0) -#endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */ - -extern int reserve_bootmem_generic(unsigned long addr, unsigned long size, - int flags); - #define alloc_bootmem_node(pgdat, x) \ __alloc_bootmem_node(pgdat, x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_pages_node(pgdat, x) \ __alloc_bootmem_node(pgdat, x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_low_pages_node(pgdat, x) \ __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0) +#endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */ + +extern int reserve_bootmem_generic(unsigned long addr, unsigned long size, + int flags); extern void *alloc_bootmem_section(unsigned long size, unsigned long section_nr); -- cgit v1.2.3 From b4615e69b6c6353878b734a8202b65efbc554df4 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Fri, 25 Jul 2008 13:19:22 -0700 Subject: sys_paccept definition missing __user annotation Introduced by commit aaca0bdca573f3f51ea03139f9c7289541e7bca3 ("flag parameters: paccept"): net/socket.c:1515:17: error: symbol 'sys_paccept' redeclared with different type (originally declared at include/linux/syscalls.h:413) - incompatible argument 4 (different address spaces) Signed-off-by: Harvey Harrison Signed-off-by: Linus Torvalds --- include/linux/syscalls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 06f2bf76c030..d6ff145919ca 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -411,7 +411,7 @@ asmlinkage long sys_bind(int, struct sockaddr __user *, int); asmlinkage long sys_connect(int, struct sockaddr __user *, int); asmlinkage long sys_accept(int, struct sockaddr __user *, int __user *); asmlinkage long sys_paccept(int, struct sockaddr __user *, int __user *, - const sigset_t *, size_t, int); + const __user sigset_t *, size_t, int); asmlinkage long sys_getsockname(int, struct sockaddr __user *, int __user *); asmlinkage long sys_getpeername(int, struct sockaddr __user *, int __user *); asmlinkage long sys_send(int, void __user *, size_t, unsigned); -- cgit v1.2.3