From e162b39a368f0401e41b558f430c354d12a85b37 Mon Sep 17 00:00:00 2001 From: Mandeep Singh Baines Date: Thu, 15 Jan 2009 11:08:40 -0800 Subject: softlockup: decouple hung tasks check from softlockup detection Decoupling allows: * hung tasks check to happen at very low priority * hung tasks check and softlockup to be enabled/disabled independently at compile and/or run-time * individual panic settings to be enabled disabled independently at compile and/or run-time * softlockup threshold to be reduced without increasing hung tasks poll frequency (hung task check is expensive relative to softlock watchdog) * hung task check to be zero over-head when disabled at run-time Signed-off-by: Mandeep Singh Baines Signed-off-by: Ingo Molnar --- include/linux/sched.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 54cbabf3b87..f2f94d53230 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -297,9 +297,6 @@ extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos); extern unsigned int softlockup_panic; -extern unsigned long sysctl_hung_task_check_count; -extern unsigned long sysctl_hung_task_timeout_secs; -extern unsigned long sysctl_hung_task_warnings; extern int softlockup_thresh; #else static inline void softlockup_tick(void) @@ -316,6 +313,15 @@ static inline void touch_all_softlockup_watchdogs(void) } #endif +#ifdef CONFIG_DETECT_HUNG_TASK +extern unsigned int sysctl_hung_task_panic; +extern unsigned long sysctl_hung_task_check_count; +extern unsigned long sysctl_hung_task_timeout_secs; +extern unsigned long sysctl_hung_task_warnings; +extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, + size_t *lenp, loff_t *ppos); +#endif /* Attach to any functions which should be ignored in wchan output. */ #define __sched __attribute__((__section__(".sched.text"))) @@ -1236,7 +1242,7 @@ struct task_struct { /* ipc stuff */ struct sysv_sem sysvsem; #endif -#ifdef CONFIG_DETECT_SOFTLOCKUP +#ifdef CONFIG_DETECT_HUNG_TASK /* hung task detection */ unsigned long last_switch_timestamp; unsigned long last_switch_count; -- cgit v1.2.3 From 5e54f5986a579b8445aa1d5ad3435c2cf7568bed Mon Sep 17 00:00:00 2001 From: Mandeep Singh Baines Date: Fri, 30 Jan 2009 15:29:54 -0800 Subject: softlockup: remove unused definition for spawn_softlockup_task The definition of spawn_softlockup_task in sched.h became unnecessary once it was converted to the early_initcall() interface. Signed-off-by: Mandeep Singh Baines Signed-off-by: Ingo Molnar --- 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 f2f94d53230..2a2811c6239 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -302,9 +302,6 @@ extern int softlockup_thresh; static inline void softlockup_tick(void) { } -static inline void spawn_softlockup_task(void) -{ -} static inline void touch_softlockup_watchdog(void) { } -- cgit v1.2.3 From 9705ecc5c1f8f34f756164a711b4cc61110c0283 Mon Sep 17 00:00:00 2001 From: Balaji Rao Date: Tue, 27 Jan 2009 19:23:12 +0530 Subject: pcf50633_charger: Enable periodic charging restart The battery charger state machine switches into charging mode when the battery voltage falls below 96% of a battery float voltage. But the voltage drop in Li-ion batteries is marginal(1~2 %) till about 80% of its capacity - which means, after a BATFULL, charging won't be restarted until 80%. This work_struct function restarts charging at regular intervals to make sure the battery doesn't discharge too much. Signed-off-by: Balaji Rao Cc: Andy Green Signed-off-by: Anton Vorontsov --- include/linux/mfd/pcf50633/core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/pcf50633/core.h b/include/linux/mfd/pcf50633/core.h index 4455b212d75..c8f51c3c0a7 100644 --- a/include/linux/mfd/pcf50633/core.h +++ b/include/linux/mfd/pcf50633/core.h @@ -29,6 +29,8 @@ struct pcf50633_platform_data { char **batteries; int num_batteries; + int charging_restart_interval; + /* Callbacks */ void (*probe_done)(struct pcf50633 *); void (*mbc_event_callback)(struct pcf50633 *, int); -- cgit v1.2.3 From cc52a29e6245acd9032fcfa0ffcab4cc612de986 Mon Sep 17 00:00:00 2001 From: Balaji Rao Date: Tue, 27 Jan 2009 19:22:55 +0530 Subject: pcf50633_charger: Remove unused mbc_set_status function The 'pcf50633_mbc_set_status' function is unused, so remove it. Signed-off-by: Balaji Rao Cc: Andy Green Signed-off-by: Anton Vorontsov --- include/linux/mfd/pcf50633/mbc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/pcf50633/mbc.h b/include/linux/mfd/pcf50633/mbc.h index 6e17619b773..4119579acf2 100644 --- a/include/linux/mfd/pcf50633/mbc.h +++ b/include/linux/mfd/pcf50633/mbc.h @@ -128,7 +128,6 @@ enum pcf50633_reg_mbcs3 { int pcf50633_mbc_usb_curlim_set(struct pcf50633 *pcf, int ma); int pcf50633_mbc_get_status(struct pcf50633 *); -void pcf50633_mbc_set_status(struct pcf50633 *, int what, int status); #endif -- cgit v1.2.3 From 5bf2b994bfe11bfe86231050897b2d881ca544d9 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Sun, 18 Jan 2009 17:40:27 +0100 Subject: pda_power: Add optional OTG transceiver and voltage regulator support This patch allows machines to use an OTG transceiver driver instead of supplying a custom is_usb_online callback to check USB power. Also, in the case that the OTG transceiver handles charger control when connected to USB, a regulator named "ac_draw" can be supplied instead of the custom set_charge callback to control the charger when connected to AC. The check for (transceiver->state == OTG_STATE_B_PERIPHERAL) in otg_is_usb_online is probably too simple, I'm just using this with a peripheral only device and gpio_vbus + bq24022. I'm not sure which other OTG states can supply power. Signed-off-by: Philipp Zabel Signed-off-by: Anton Vorontsov --- include/linux/pda_power.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pda_power.h b/include/linux/pda_power.h index cb7d10f3076..d4cf7a2ceb3 100644 --- a/include/linux/pda_power.h +++ b/include/linux/pda_power.h @@ -31,6 +31,8 @@ struct pda_power_pdata { unsigned int wait_for_status; /* msecs, default is 500 */ unsigned int wait_for_charger; /* msecs, default is 500 */ unsigned int polling_interval; /* msecs, default is 2000 */ + + unsigned long ac_max_uA; /* current to draw when on AC */ }; #endif /* __PDA_POWER_H__ */ -- cgit v1.2.3 From 17406b82d621930cca8ccc1272cdac9a7dae8e40 Mon Sep 17 00:00:00 2001 From: Mandeep Singh Baines Date: Fri, 6 Feb 2009 15:37:47 -0800 Subject: softlockup: remove timestamp checking from hung_task Impact: saves sizeof(long) bytes per task_struct By guaranteeing that sysctl_hung_task_timeout_secs have elapsed between tasklist scans we can avoid using timestamps. Signed-off-by: Mandeep Singh Baines Signed-off-by: Ingo Molnar --- 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 2a2811c6239..e0d723fea9f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1241,7 +1241,6 @@ struct task_struct { #endif #ifdef CONFIG_DETECT_HUNG_TASK /* hung task detection */ - unsigned long last_switch_timestamp; unsigned long last_switch_count; #endif /* CPU-specific state of this task */ -- cgit v1.2.3 From 3aa551c9b4c40018f0e261a178e3d25478dc04a9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 23 Mar 2009 18:28:15 +0100 Subject: genirq: add threaded interrupt handler support Add support for threaded interrupt handlers: A device driver can request that its main interrupt handler runs in a thread. To achive this the device driver requests the interrupt with request_threaded_irq() and provides additionally to the handler a thread function. The handler function is called in hard interrupt context and needs to check whether the interrupt originated from the device. If the interrupt originated from the device then the handler can either return IRQ_HANDLED or IRQ_WAKE_THREAD. IRQ_HANDLED is returned when no further action is required. IRQ_WAKE_THREAD causes the genirq code to invoke the threaded (main) handler. When IRQ_WAKE_THREAD is returned handler must have disabled the interrupt on the device level. This is mandatory for shared interrupt handlers, but we need to do it as well for obscure x86 hardware where disabling an interrupt on the IO_APIC level redirects the interrupt to the legacy PIC interrupt lines. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar --- include/linux/hardirq.h | 2 +- include/linux/interrupt.h | 37 +++++++++++++++++++++++++++++++++++-- include/linux/irq.h | 5 +++++ include/linux/irqreturn.h | 2 ++ include/linux/sched.h | 5 +++++ 5 files changed, 48 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index f83288347dd..2dfaadbdb2a 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -105,7 +105,7 @@ # define IRQ_EXIT_OFFSET HARDIRQ_OFFSET #endif -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) || defined(CONFIG_GENERIC_HARDIRQS) extern void synchronize_irq(unsigned int irq); #else # define synchronize_irq(irq) barrier() diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 0c9cb63e689..6fc2b720c23 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -59,6 +59,16 @@ #define IRQF_NOBALANCING 0x00000800 #define IRQF_IRQPOLL 0x00001000 +/* + * Bits used by threaded handlers: + * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run + * IRQTF_DIED - handler thread died + */ +enum { + IRQTF_RUNTHREAD, + IRQTF_DIED, +}; + typedef irqreturn_t (*irq_handler_t)(int, void *); /** @@ -71,6 +81,9 @@ typedef irqreturn_t (*irq_handler_t)(int, void *); * @next: pointer to the next irqaction for shared interrupts * @irq: interrupt number * @dir: pointer to the proc/irq/NN/name entry + * @thread_fn: interupt handler function for threaded interrupts + * @thread: thread pointer for threaded interrupts + * @thread_flags: flags related to @thread */ struct irqaction { irq_handler_t handler; @@ -81,11 +94,31 @@ struct irqaction { struct irqaction *next; int irq; struct proc_dir_entry *dir; + irq_handler_t thread_fn; + struct task_struct *thread; + unsigned long thread_flags; }; extern irqreturn_t no_action(int cpl, void *dev_id); -extern int __must_check request_irq(unsigned int, irq_handler_t handler, - unsigned long, const char *, void *); + +extern int __must_check +request_threaded_irq(unsigned int irq, irq_handler_t handler, + irq_handler_t thread_fn, + unsigned long flags, const char *name, void *dev); + +static inline int __must_check +request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, + const char *name, void *dev) +{ + return request_threaded_irq(irq, handler, NULL, flags, name, dev); +} + +#ifdef CONFIG_GENERIC_HARDIRQS +extern void exit_irq_thread(void); +#else +static inline void exit_irq_thread(void) { } +#endif + extern void free_irq(unsigned int, void *); struct device; diff --git a/include/linux/irq.h b/include/linux/irq.h index 873e4ac11b8..8b1cf063021 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -155,6 +156,8 @@ struct irq_2_iommu; * @affinity: IRQ affinity on SMP * @cpu: cpu index useful for balancing * @pending_mask: pending rebalanced interrupts + * @threads_active: number of irqaction threads currently running + * @wait_for_threads: wait queue for sync_irq to wait for threaded handlers * @dir: /proc/irq/ procfs entry * @name: flow handler name for /proc/interrupts output */ @@ -186,6 +189,8 @@ struct irq_desc { cpumask_var_t pending_mask; #endif #endif + atomic_t threads_active; + wait_queue_head_t wait_for_threads; #ifdef CONFIG_PROC_FS struct proc_dir_entry *dir; #endif diff --git a/include/linux/irqreturn.h b/include/linux/irqreturn.h index c5584ca5b8c..819acaaac3f 100644 --- a/include/linux/irqreturn.h +++ b/include/linux/irqreturn.h @@ -5,10 +5,12 @@ * enum irqreturn * @IRQ_NONE interrupt was not from this device * @IRQ_HANDLED interrupt was handled by this device + * @IRQ_WAKE_THREAD handler requests to wake the handler thread */ enum irqreturn { IRQ_NONE, IRQ_HANDLED, + IRQ_WAKE_THREAD, }; typedef enum irqreturn irqreturn_t; diff --git a/include/linux/sched.h b/include/linux/sched.h index 46d680643f8..38b77b0f56e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1292,6 +1292,11 @@ struct task_struct { /* Protection of (de-)allocation: mm, files, fs, tty, keyrings */ spinlock_t alloc_lock; +#ifdef CONFIG_GENERIC_HARDIRQS + /* IRQ handler threads */ + struct irqaction *irqaction; +#endif + /* Protection of the PI data structures: */ spinlock_t pi_lock; -- cgit v1.2.3 From 935bd5b971f0df7c06d214d022cf8392e2f37952 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Mon, 23 Mar 2009 18:28:16 +0100 Subject: genirq: add support for threaded interrupts to devres Some devices use devres_request_irq() for to install their interrupt handler. Add support for threaded interrupts to devres as well. [tglx - simplified and adapted to latest threadirq version] Signed-off-by: Arjan van de Ven Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 6fc2b720c23..dbf6a6fd116 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -123,9 +123,20 @@ extern void free_irq(unsigned int, void *); struct device; -extern int __must_check devm_request_irq(struct device *dev, unsigned int irq, - irq_handler_t handler, unsigned long irqflags, - const char *devname, void *dev_id); +extern int __must_check +devm_request_threaded_irq(struct device *dev, unsigned int irq, + irq_handler_t handler, irq_handler_t thread_fn, + unsigned long irqflags, const char *devname, + void *dev_id); + +static inline int __must_check +devm_request_irq(struct device *dev, unsigned int irq, irq_handler_t handler, + unsigned long irqflags, const char *devname, void *dev_id) +{ + return devm_request_threaded_irq(dev, irq, handler, NULL, irqflags, + devname, dev_id); +} + extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id); /* -- cgit v1.2.3 From f48fe81e5b032914183e9a17052313720c2cac56 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 24 Mar 2009 11:46:22 +0100 Subject: genirq: threaded irq handlers review fixups Delta patch to address the review comments. - Implement warning when IRQ_WAKE_THREAD is requested and no thread handler installed - coding style fixes Pointed-out-by: Christoph Hellwig Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index dbf6a6fd116..266a5f5f57c 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -63,10 +63,12 @@ * Bits used by threaded handlers: * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run * IRQTF_DIED - handler thread died + * IRQTF_WARNED - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed */ enum { IRQTF_RUNTHREAD, IRQTF_DIED, + IRQTF_WARNED, }; typedef irqreturn_t (*irq_handler_t)(int, void *); -- cgit v1.2.3 From 3a38148f0488069cadb75c4a6909954072d648bf Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 24 Mar 2009 20:27:39 +0100 Subject: genirq: provide old request_irq() for CONFIG_GENERIC_HARDIRQ=n Impact: Undo compile breakage for archs with CONFIG_GENERIC_HARDIRQ=n The threaded interrupt handler patches changed request_irq from extern to inline. Architectures which do not use the generic irq code still have request_irq() as a global function and therefor fail to compile. Keep the extern declaration for CONFIG_GENERIC_HARDIRQ=n Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 266a5f5f57c..7e63b824833 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -103,6 +103,7 @@ struct irqaction { extern irqreturn_t no_action(int cpl, void *dev_id); +#ifdef CONFIG_GENERIC_HARDIRQS extern int __must_check request_threaded_irq(unsigned int irq, irq_handler_t handler, irq_handler_t thread_fn, @@ -115,9 +116,13 @@ request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, return request_threaded_irq(irq, handler, NULL, flags, name, dev); } -#ifdef CONFIG_GENERIC_HARDIRQS extern void exit_irq_thread(void); #else + +extern int __must_check +request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, + const char *name, void *dev); + static inline void exit_irq_thread(void) { } #endif -- cgit v1.2.3 From de18836e447c2dc30120c0919b8db8ddc0401cc4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 25 Mar 2009 17:33:38 +0100 Subject: genirq: fix devres.o build for GENERIC_HARDIRQS=n kernel/irq/devres.c is built by sparc (32bit) and m68k via the obscure ../../../kernel/irq/devres.o reference in arch/[sparc/m68k]/kernel/Makefile To avoid ifdeffery in devres.c provide request_threaded_irq as an inline for these users. Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 7e63b824833..143192f48bf 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -123,6 +123,20 @@ extern int __must_check request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev); +/* + * Special function to avoid ifdeffery in kernel/irq/devres.c which + * gets magically built by GENERIC_HARDIRQS=n architectures (sparc, + * m68k). I really love these $@%#!* obvious Makefile references: + * ../../../kernel/irq/devres.o + */ +static inline int __must_check +request_threaded_irq(unsigned int irq, irq_handler_t handler, + irq_handler_t thread_fn, + unsigned long flags, const char *name, void *dev) +{ + return request_irq(irq, handler, flags, name, dev); +} + static inline void exit_irq_thread(void) { } #endif -- cgit v1.2.3 From 9310933c832719b095f82dab30c6bf4e75e937ee Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Sat, 28 Mar 2009 15:07:16 -0600 Subject: powerpc: Remove unused symbols from fsl_devices.h Remove old artifacts leftover from the platform driver gianfar and fsl_i2c drivers. These symbols became unused when the drivers were migrated over to use the of_platform bus. Signed-off-by: Grant Likely Signed-off-by: Kumar Gala --- include/linux/fsl_devices.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h index d9051d717d2..4953709f687 100644 --- a/include/linux/fsl_devices.h +++ b/include/linux/fsl_devices.h @@ -18,7 +18,6 @@ #define _FSL_DEVICE_H_ #include -#include /* * Some conventions on how we handle peripherals on Freescale chips @@ -44,27 +43,6 @@ * */ -struct gianfar_platform_data { - /* device specific information */ - u32 device_flags; - char bus_id[BUS_ID_SIZE]; - phy_interface_t interface; -}; - -struct gianfar_mdio_data { - /* board specific information */ - int irq[32]; -}; - -/* Flags in gianfar_platform_data */ -#define FSL_GIANFAR_BRD_HAS_PHY_INTR 0x00000001 /* set or use a timer */ -#define FSL_GIANFAR_BRD_IS_REDUCED 0x00000002 /* Set if RGMII, RMII */ - -struct fsl_i2c_platform_data { - /* device specific information */ - u32 device_flags; -}; - /* Flags related to I2C device features */ #define FSL_I2C_DEV_SEPARATE_DFSRR 0x00000001 #define FSL_I2C_DEV_CLOCK_5200 0x00000002 -- cgit v1.2.3 From 9756b15e1b58453a6fd54b85c1ad8515209e10bb Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 30 Mar 2009 20:37:20 -0700 Subject: irq: fix cpumask memory leak on offstack cpumask kernels Need to free the old cpumask for affinity and pending_mask. Signed-off-by: Yinghai Lu Acked-by: Rusty Russell LKML-Reference: <49D18FF0.50707@kernel.org> Signed-off-by: Ingo Molnar --- include/linux/irq.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 974890b3c52..99d147efe39 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -482,6 +482,16 @@ static inline void init_copy_desc_masks(struct irq_desc *old_desc, #endif } +static inline void free_desc_masks(struct irq_desc *old_desc, + struct irq_desc *new_desc) +{ + free_cpumask_var(old_desc->affinity); + +#ifdef CONFIG_GENERIC_PENDING_IRQ + free_cpumask_var(old_desc->pending_mask); +#endif +} + #else /* !CONFIG_SMP */ static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu, @@ -495,6 +505,10 @@ static inline void init_copy_desc_masks(struct irq_desc *old_desc, { } +static inline void free_desc_masks(struct irq_desc *old_desc, + struct irq_desc *new_desc) +{ +} #endif /* CONFIG_SMP */ #endif /* _LINUX_IRQ_H */ -- cgit v1.2.3 From 296ccb086dfb89b5b8d73ef08c795ffdff12a597 Mon Sep 17 00:00:00 2001 From: Yuji Shimada Date: Fri, 3 Apr 2009 16:41:46 +0900 Subject: PCI: Setup disabled bridges even if buses are added This patch sets up disabled bridges even if buses have already been added. pci_assign_unassigned_resources is called after buses are added. pci_assign_unassigned_resources calls pci_bus_assign_resources. pci_bus_assign_resources calls pci_setup_bridge to configure BARs of bridges. Currently pci_setup_bridge returns immediately if the bus have already been added. So pci_assign_unassigned_resources can't configure BARs of bridges that were added in a disabled state; this patch fixes the issue. On logical hot-add, we need to prevent the kernel from re-initializing bridges that have already been initialized. To achieve this, pci_setup_bridge returns immediately if the bridge have already been enabled. We don't need to check whether the specified bus is a root bus or not. pci_setup_bridge is not called on a root bus, because a root bus does not have a bridge. The patch adds a new helper function, pci_is_enabled. I made the function name similar to pci_is_managed. The codes which use enable_cnt directly are changed to use pci_is_enabled. Acked-by: Alex Chiang Signed-off-by: Yuji Shimada Signed-off-by: Jesse Barnes --- include/linux/pci.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index a7fe4bbd7ff..72698d89e76 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -674,6 +674,11 @@ int __must_check pci_reenable_device(struct pci_dev *); int __must_check pcim_enable_device(struct pci_dev *pdev); void pcim_pin_device(struct pci_dev *pdev); +static inline int pci_is_enabled(struct pci_dev *pdev) +{ + return (atomic_read(&pdev->enable_cnt) > 0); +} + static inline int pci_is_managed(struct pci_dev *pdev) { return pdev->is_managed; -- cgit v1.2.3 From 0c659b82d11eaf5e1bee1f2bcb9994b9d09d175c Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 2 Apr 2009 10:37:25 -0400 Subject: ata: Add TRIM infrastructure This is common code shared between the IDE and libata implementations Signed-off-by: David Woodhouse Signed-off-by: Matthew Wilcox Signed-off-by: Jeff Garzik --- include/linux/ata.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index 6617c9f8f2c..cb79b7a208e 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -29,6 +29,8 @@ #ifndef __LINUX_ATA_H__ #define __LINUX_ATA_H__ +#include +#include #include #include @@ -91,6 +93,7 @@ enum { ATA_ID_CFA_POWER = 160, ATA_ID_CFA_KEY_MGMT = 162, ATA_ID_CFA_MODES = 163, + ATA_ID_DATA_SET_MGMT = 169, ATA_ID_ROT_SPEED = 217, ATA_ID_PIO4 = (1 << 1), @@ -248,6 +251,7 @@ enum { ATA_CMD_SMART = 0xB0, ATA_CMD_MEDIA_LOCK = 0xDE, ATA_CMD_MEDIA_UNLOCK = 0xDF, + ATA_CMD_DSM = 0x06, /* marked obsolete in the ATA/ATAPI-7 spec */ ATA_CMD_RESTORE = 0x10, @@ -321,6 +325,9 @@ enum { ATA_SMART_READ_VALUES = 0xD0, ATA_SMART_READ_THRESHOLDS = 0xD1, + /* feature values for Data Set Management */ + ATA_DSM_TRIM = 0x01, + /* password used in LBA Mid / LBA High for executing SMART commands */ ATA_SMART_LBAM_PASS = 0x4F, ATA_SMART_LBAH_PASS = 0xC2, @@ -723,6 +730,14 @@ static inline int ata_id_has_unload(const u16 *id) return 0; } +static inline int ata_id_has_trim(const u16 *id) +{ + if (ata_id_major_version(id) >= 7 && + (id[ATA_ID_DATA_SET_MGMT] & 1)) + return 1; + return 0; +} + static inline int ata_id_current_chs_valid(const u16 *id) { /* For ATA-1 devices, if the INITIALIZE DEVICE PARAMETERS command @@ -863,6 +878,32 @@ static inline void ata_id_to_hd_driveid(u16 *id) #endif } +/* + * Write up to 'max' LBA Range Entries to the buffer that will cover the + * extent from sector to sector + count. This is used for TRIM and for + * ADD LBA(S) TO NV CACHE PINNED SET. + */ +static inline unsigned ata_set_lba_range_entries(void *_buffer, unsigned max, + u64 sector, unsigned long count) +{ + __le64 *buffer = _buffer; + unsigned i = 0; + + while (i < max) { + u64 entry = sector | + ((u64)(count > 0xffff ? 0xffff : count) << 48); + buffer[i++] = __cpu_to_le64(entry); + if (count <= 0xffff) + break; + count -= 0xffff; + sector += 0xffff; + } + + max = ALIGN(i * 8, 512); + memset(buffer + i, 0, max - i * 8); + return max; +} + static inline int is_multi_taskfile(struct ata_taskfile *tf) { return (tf->command == ATA_CMD_READ_MULTI) || -- cgit v1.2.3 From e0d3bafd02586cfde286c320f56906fd9fa8d256 Mon Sep 17 00:00:00 2001 From: Sri Deevi Date: Tue, 3 Mar 2009 14:37:50 -0300 Subject: V4L/DVB (10954): Add cx231xx USB driver Signed-off-by: Srinivasa Deevi [mchehab@redhat.com: Remove the Kconfig changes, to avoid git breakages] Signed-off-by: Mauro Carvalho Chehab --- include/linux/i2c-id.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index f27604af837..f9d48c9ad5d 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -88,6 +88,7 @@ #define I2C_HW_B_CX2341X 0x010020 /* Conexant CX2341X MPEG encoder cards */ #define I2C_HW_B_CX23885 0x010022 /* conexant 23885 based tv cards (bus1) */ #define I2C_HW_B_AU0828 0x010023 /* auvitek au0828 usb bridge */ +#define I2C_HW_B_CX231XX 0x010024 /* Conexant CX231XX USB based cards */ #define I2C_HW_B_HDPVR 0x010025 /* Hauppauge HD PVR */ /* --- SGI adapters */ -- cgit v1.2.3 From dfa76fa2824967c0ec196fbcba36d3e74b66d3aa Mon Sep 17 00:00:00 2001 From: Adam Baker Date: Sun, 29 Mar 2009 19:17:10 -0300 Subject: V4L/DVB (11387): Sensor orientation reporting Add support to the SQ-905 driver to pass back to user space the sensor orientation information obtained from the camera during init. Modifies gspca and the videodev2.h header to create the necessary API. [mchehab@redhat.com: Changed "Output is" to "Frames are" at the comments, as suggested at LMML] Signed-off-by: Adam Baker Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 139d234923c..ebb2ea6b499 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -737,6 +737,11 @@ struct v4l2_input { #define V4L2_IN_ST_NO_SIGNAL 0x00000002 #define V4L2_IN_ST_NO_COLOR 0x00000004 +/* field 'status' - sensor orientation */ +/* If sensor is mounted upside down set both bits */ +#define V4L2_IN_ST_HFLIP 0x00000010 /* Frames are flipped horizontally */ +#define V4L2_IN_ST_VFLIP 0x00000020 /* Frames are flipped vertically */ + /* field 'status' - analog */ #define V4L2_IN_ST_NO_H_LOCK 0x00000100 /* No horizontal sync lock */ #define V4L2_IN_ST_COLOR_KILL 0x00000200 /* Color killer is active */ -- cgit v1.2.3 From 26308eab69aa193f7b3fb50764a64ae14544a39b Mon Sep 17 00:00:00 2001 From: Jerome Marchand Date: Fri, 27 Mar 2009 10:31:51 +0100 Subject: block: fix inconsistency in I/O stat accounting code This forces in_flight to be zero when turning off or on the I/O stat accounting and stops updating I/O stats in attempt_merge() when accounting is turned off. Signed-off-by: Jerome Marchand Signed-off-by: Jens Axboe --- include/linux/elevator.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 7a204256b15..c59b769f62b 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -116,6 +116,7 @@ extern void elv_abort_queue(struct request_queue *); extern void elv_completed_request(struct request_queue *, struct request *); extern int elv_set_request(struct request_queue *, struct request *, gfp_t); extern void elv_put_request(struct request_queue *, struct request *); +extern void elv_drain_elevator(struct request_queue *); /* * io scheduler registration -- cgit v1.2.3 From 3fbed4c61abd8458896e38633d10110cb5a589d4 Mon Sep 17 00:00:00 2001 From: unsik Kim Date: Thu, 2 Apr 2009 12:50:58 -0700 Subject: mflash: initial support This driver supports mflash IO mode for linux. Mflash is embedded flash drive and mainly targeted mobile and consumer electronic devices. Internally, mflash has nand flash and other hardware logics and supports 2 different operation (ATA, IO) modes. ATA mode doesn't need any new driver and currently works well under standard IDE subsystem. Actually it's one chip SSD. IO mode is ATA-like custom mode for the host that doesn't have IDE interface. Followings are brief descriptions about IO mode. A. IO mode based on ATA protocol and uses some custom command. (read confirm, write confirm) B. IO mode uses SRAM bus interface. C. IO mode supports 4kB boot area, so host can boot from mflash. This driver is quitely similar to a standard ATA driver, but because of following reasons it is currently seperated with ATA layer. 1. ATA layer deals standard ATA protocol. ATA layer have many low- level device specific interface, but data transfer keeps ATA rule. But, mflash IO mode doesn't. 2. Even though currently not used in mflash driver code, mflash has some custom command and modes. (nand fusing, firmware patch, etc) If this feature supported in linux kernel, ATA layer more altered. 3. Currently PATA platform device driver doesn't support interrupt. (I'm not sure) But, mflash uses interrupt (polling mode is just for debug). 4. mflash is somewhat under-develop product. Even though some company already using mflash their own product, I think more time is needed for standardization of custom command and mode. That time (maybe October) I will talk to with ATA people. If they accept integration, I will integrate. Signed-off-by: unsik Kim Cc: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Jens Axboe --- include/linux/mg_disk.h | 206 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 206 insertions(+) create mode 100644 include/linux/mg_disk.h (limited to 'include/linux') diff --git a/include/linux/mg_disk.h b/include/linux/mg_disk.h new file mode 100644 index 00000000000..1f76b1ebf62 --- /dev/null +++ b/include/linux/mg_disk.h @@ -0,0 +1,206 @@ +/* + * include/linux/mg_disk.c + * + * Support for the mGine m[g]flash IO mode. + * Based on legacy hd.c + * + * (c) 2008 mGine Co.,LTD + * (c) 2008 unsik Kim + * + * 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 __MG_DISK_H__ +#define __MG_DISK_H__ + +#include +#include + +/* name for block device */ +#define MG_DISK_NAME "mgd" +/* name for platform device */ +#define MG_DEV_NAME "mg_disk" + +#define MG_DISK_MAJ 0 +#define MG_DISK_MAX_PART 16 +#define MG_SECTOR_SIZE 512 +#define MG_MAX_SECTS 256 + +/* Register offsets */ +#define MG_BUFF_OFFSET 0x8000 +#define MG_STORAGE_BUFFER_SIZE 0x200 +#define MG_REG_OFFSET 0xC000 +#define MG_REG_FEATURE (MG_REG_OFFSET + 2) /* write case */ +#define MG_REG_ERROR (MG_REG_OFFSET + 2) /* read case */ +#define MG_REG_SECT_CNT (MG_REG_OFFSET + 4) +#define MG_REG_SECT_NUM (MG_REG_OFFSET + 6) +#define MG_REG_CYL_LOW (MG_REG_OFFSET + 8) +#define MG_REG_CYL_HIGH (MG_REG_OFFSET + 0xA) +#define MG_REG_DRV_HEAD (MG_REG_OFFSET + 0xC) +#define MG_REG_COMMAND (MG_REG_OFFSET + 0xE) /* write case */ +#define MG_REG_STATUS (MG_REG_OFFSET + 0xE) /* read case */ +#define MG_REG_DRV_CTRL (MG_REG_OFFSET + 0x10) +#define MG_REG_BURST_CTRL (MG_REG_OFFSET + 0x12) + +/* "Drive Select/Head Register" bit values */ +#define MG_REG_HEAD_MUST_BE_ON 0xA0 /* These 2 bits are always on */ +#define MG_REG_HEAD_DRIVE_MASTER (0x00 | MG_REG_HEAD_MUST_BE_ON) +#define MG_REG_HEAD_DRIVE_SLAVE (0x10 | MG_REG_HEAD_MUST_BE_ON) +#define MG_REG_HEAD_LBA_MODE (0x40 | MG_REG_HEAD_MUST_BE_ON) + + +/* "Device Control Register" bit values */ +#define MG_REG_CTRL_INTR_ENABLE 0x0 +#define MG_REG_CTRL_INTR_DISABLE (0x1<<1) +#define MG_REG_CTRL_RESET (0x1<<2) +#define MG_REG_CTRL_INTR_POLA_ACTIVE_HIGH 0x0 +#define MG_REG_CTRL_INTR_POLA_ACTIVE_LOW (0x1<<4) +#define MG_REG_CTRL_DPD_POLA_ACTIVE_LOW 0x0 +#define MG_REG_CTRL_DPD_POLA_ACTIVE_HIGH (0x1<<5) +#define MG_REG_CTRL_DPD_DISABLE 0x0 +#define MG_REG_CTRL_DPD_ENABLE (0x1<<6) + +/* Status register bit */ +/* error bit in status register */ +#define MG_REG_STATUS_BIT_ERROR 0x01 +/* corrected error in status register */ +#define MG_REG_STATUS_BIT_CORRECTED_ERROR 0x04 +/* data request bit in status register */ +#define MG_REG_STATUS_BIT_DATA_REQ 0x08 +/* DSC - Drive Seek Complete */ +#define MG_REG_STATUS_BIT_SEEK_DONE 0x10 +/* DWF - Drive Write Fault */ +#define MG_REG_STATUS_BIT_WRITE_FAULT 0x20 +#define MG_REG_STATUS_BIT_READY 0x40 +#define MG_REG_STATUS_BIT_BUSY 0x80 + +/* handy status */ +#define MG_STAT_READY (MG_REG_STATUS_BIT_READY | MG_REG_STATUS_BIT_SEEK_DONE) +#define MG_READY_OK(s) (((s) & (MG_STAT_READY | \ + (MG_REG_STATUS_BIT_BUSY | \ + MG_REG_STATUS_BIT_WRITE_FAULT | \ + MG_REG_STATUS_BIT_ERROR))) == MG_STAT_READY) + +/* Error register */ +#define MG_REG_ERR_AMNF 0x01 +#define MG_REG_ERR_ABRT 0x04 +#define MG_REG_ERR_IDNF 0x10 +#define MG_REG_ERR_UNC 0x40 +#define MG_REG_ERR_BBK 0x80 + +/* error code for others */ +#define MG_ERR_NONE 0 +#define MG_ERR_TIMEOUT 0x100 +#define MG_ERR_INIT_STAT 0x101 +#define MG_ERR_TRANSLATION 0x102 +#define MG_ERR_CTRL_RST 0x103 +#define MG_ERR_INV_STAT 0x104 +#define MG_ERR_RSTOUT 0x105 + +#define MG_MAX_ERRORS 6 /* Max read/write errors */ + +/* command */ +#define MG_CMD_RD 0x20 +#define MG_CMD_WR 0x30 +#define MG_CMD_SLEEP 0x99 +#define MG_CMD_WAKEUP 0xC3 +#define MG_CMD_ID 0xEC +#define MG_CMD_WR_CONF 0x3C +#define MG_CMD_RD_CONF 0x40 + +/* operation mode */ +#define MG_OP_CASCADE (1 << 0) +#define MG_OP_CASCADE_SYNC_RD (1 << 1) +#define MG_OP_CASCADE_SYNC_WR (1 << 2) +#define MG_OP_INTERLEAVE (1 << 3) + +/* synchronous */ +#define MG_BURST_LAT_4 (3 << 4) +#define MG_BURST_LAT_5 (4 << 4) +#define MG_BURST_LAT_6 (5 << 4) +#define MG_BURST_LAT_7 (6 << 4) +#define MG_BURST_LAT_8 (7 << 4) +#define MG_BURST_LEN_4 (1 << 1) +#define MG_BURST_LEN_8 (2 << 1) +#define MG_BURST_LEN_16 (3 << 1) +#define MG_BURST_LEN_32 (4 << 1) +#define MG_BURST_LEN_CONT (0 << 1) + +/* timeout value (unit: ms) */ +#define MG_TMAX_CONF_TO_CMD 1 +#define MG_TMAX_WAIT_RD_DRQ 10 +#define MG_TMAX_WAIT_WR_DRQ 500 +#define MG_TMAX_RST_TO_BUSY 10 +#define MG_TMAX_HDRST_TO_RDY 500 +#define MG_TMAX_SWRST_TO_RDY 500 +#define MG_TMAX_RSTOUT 3000 + +/* device attribution */ +/* use mflash as boot device */ +#define MG_BOOT_DEV (1 << 0) +/* use mflash as storage device */ +#define MG_STORAGE_DEV (1 << 1) +/* same as MG_STORAGE_DEV, but bootloader already done reset sequence */ +#define MG_STORAGE_DEV_SKIP_RST (1 << 2) + +#define MG_DEV_MASK (MG_BOOT_DEV | MG_STORAGE_DEV | MG_STORAGE_DEV_SKIP_RST) + +/* names of GPIO resource */ +#define MG_RST_PIN "mg_rst" +/* except MG_BOOT_DEV, reset-out pin should be assigned */ +#define MG_RSTOUT_PIN "mg_rstout" + +/* private driver data */ +struct mg_drv_data { + /* disk resource */ + u32 use_polling; + + /* device attribution */ + u32 dev_attr; + + /* internally used */ + struct mg_host *host; +}; + +/* main structure for mflash driver */ +struct mg_host { + struct device *dev; + + struct request_queue *breq; + spinlock_t lock; + struct gendisk *gd; + + struct timer_list timer; + void (*mg_do_intr) (struct mg_host *); + + u16 id[ATA_ID_WORDS]; + + u16 cyls; + u16 heads; + u16 sectors; + u32 n_sectors; + u32 nres_sectors; + + void __iomem *dev_base; + unsigned int irq; + unsigned int rst; + unsigned int rstout; + + u32 major; + u32 error; +}; + +/* + * Debugging macro and defines + */ +#undef DO_MG_DEBUG +#ifdef DO_MG_DEBUG +# define MG_DBG(fmt, args...) \ + printk(KERN_DEBUG "%s:%d "fmt, __func__, __LINE__, ##args) +#else /* CONFIG_MG_DEBUG */ +# define MG_DBG(fmt, args...) do { } while (0) +#endif /* CONFIG_MG_DEBUG */ + +#endif -- cgit v1.2.3 From 2385327725419a76cfbca7258abd95908b8ba9eb Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 7 Apr 2009 08:59:11 +0200 Subject: block: remove unused REQ_UNPLUG The request inherits the unplug flag from the bio, but it isn't actually used. The bio flag stops at __make_request(), which tells it to unplug after submission. Passing it on to the request doesn't make any sense. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e03660964e0..ba54c834a59 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -117,7 +117,6 @@ enum rq_flag_bits { __REQ_RW_META, /* metadata io request */ __REQ_COPY_USER, /* contains copies of user pages */ __REQ_INTEGRITY, /* integrity metadata has been remapped */ - __REQ_UNPLUG, /* unplug queue on submission */ __REQ_NOIDLE, /* Don't anticipate more IO after this one */ __REQ_NR_BITS, /* stops here */ }; @@ -145,7 +144,6 @@ enum rq_flag_bits { #define REQ_RW_META (1 << __REQ_RW_META) #define REQ_COPY_USER (1 << __REQ_COPY_USER) #define REQ_INTEGRITY (1 << __REQ_INTEGRITY) -#define REQ_UNPLUG (1 << __REQ_UNPLUG) #define REQ_NOIDLE (1 << __REQ_NOIDLE) #define BLK_MAX_CDB 16 -- cgit v1.2.3 From b486ddbc0fb8127ccf2c820cfbf0b98e6f8a4e97 Mon Sep 17 00:00:00 2001 From: Oskar Schirmer Date: Thu, 2 Apr 2009 13:19:07 +0200 Subject: i2c: xtensa s6000 i2c driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Support for the s6000 on-chip i2c controller. Signed-off-by: Oskar Schirmer Signed-off-by: Daniel Glöckner Signed-off-by: Ben Dooks --- include/linux/i2c/s6000.h | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 include/linux/i2c/s6000.h (limited to 'include/linux') diff --git a/include/linux/i2c/s6000.h b/include/linux/i2c/s6000.h new file mode 100644 index 00000000000..d9b34bfdae7 --- /dev/null +++ b/include/linux/i2c/s6000.h @@ -0,0 +1,10 @@ +#ifndef __LINUX_I2C_S6000_H +#define __LINUX_I2C_S6000_H + +struct s6_i2c_platform_data { + const char *clock; /* the clock to use */ + int bus_num; /* the bus number to register */ +}; + +#endif + -- cgit v1.2.3 From d9ad8bc0ca823705413f75b50c442a88cc518b35 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Sun, 5 Apr 2009 16:20:02 +0200 Subject: branch tracer: Fix for enabling branch profiling makes sparse unusable One of the changes between kernels 2.6.28 and 2.6.29 is that a branch profiler has been added for if() statements. Unfortunately this patch makes the sparse output unusable with CONFIG_TRACE_BRANCH_PROFILING=y: when branch profiling is enabled, sparse prints so much false positives that the real issues are no longer visible. This behavior can be reproduced as follows: * enable CONFIG_TRACE_BRANCH_PROFILING, e.g. by running make allyesconfig or make allmodconfig. * run make C=2 Result: a huge number of the following sparse warnings. ... include/linux/cpumask.h:547:2: warning: symbol '______r' shadows an earlier one include/linux/cpumask.h:547:2: originally declared here ... The patch below fixes this by disabling branch profiling while analyzing the kernel code with sparse. See also: * http://lkml.org/lkml/2008/11/21/18 * http://bugzilla.kernel.org/show_bug.cgi?id=12925 Signed-off-by: Bart Van Assche Cc: Andrew Morton Cc: Steven Rostedt LKML-Reference: <200904051620.02311.bart.vanassche@gmail.com> Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 6faa7e549de..8872ad6dd89 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -76,7 +76,8 @@ struct ftrace_branch_data { * Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code * to disable branch tracing on a per file basis. */ -#if defined(CONFIG_TRACE_BRANCH_PROFILING) && !defined(DISABLE_BRANCH_PROFILING) +#if defined(CONFIG_TRACE_BRANCH_PROFILING) \ + && !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__) void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); #define likely_notrace(x) __builtin_expect(!!(x), 1) -- cgit v1.2.3 From ab3c9c686e22ab264269337ce7b75d9760211198 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 7 Apr 2009 07:59:41 -0700 Subject: branch tracer, intel-iommu: fix build with CONFIG_BRANCH_TRACER=y Fix the branch tracer barfing on comma statements within if () statements. Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 8872ad6dd89..37bcb50a4d7 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -115,7 +115,9 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); * "Define 'is'", Bill Clinton * "Define 'if'", Steven Rostedt */ -#define if(cond) if (__builtin_constant_p((cond)) ? !!(cond) : \ +#define if(cond, ...) __trace_if( (cond , ## __VA_ARGS__) ) +#define __trace_if(cond) \ + if (__builtin_constant_p((cond)) ? !!(cond) : \ ({ \ int ______r; \ static struct ftrace_branch_data \ -- cgit v1.2.3 From fafd688e4c0c34da0f3de909881117d374e4c7af Mon Sep 17 00:00:00 2001 From: Peter W Morreale Date: Mon, 6 Apr 2009 19:00:29 -0700 Subject: mm: add /proc controls for pdflush threads Add /proc entries to give the admin the ability to control the minimum and maximum number of pdflush threads. This allows finer control of pdflush on both large and small machines. The rationale is simply one size does not fit all. Admins on large and/or small systems may want to tune the min/max pdflush thread count to best suit their needs. Right now the min/max is hardcoded to 2/8. While probably a fair estimate for smaller machines, large machines with large numbers of CPUs and large numbers of filesystems/block devices may benefit from larger numbers of threads working on different block devices. Even if the background flushing algorithm is radically changed, it is still likely that multiple threads will be involved and admins would still desire finer control on the min/max other than to have to recompile the kernel. The patch adds '/proc/sys/vm/nr_pdflush_threads_min' and '/proc/sys/vm/nr_pdflush_threads_max' with r/w permissions. The minimum value for nr_pdflush_threads_min is 1 and the maximum value is the current value of nr_pdflush_threads_max. This minimum is required since additional thread creation is performed in a pdflush thread itself. The minimum value for nr_pdflush_threads_max is the current value of nr_pdflush_threads_min and the maximum value can be 1000. Documentation/sysctl/vm.txt is also updated. [akpm@linux-foundation.org: fix comment, fix whitespace, use __read_mostly] Signed-off-by: Peter W Morreale Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/writeback.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 93445477f86..9c1ed1fb6dd 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -168,6 +168,8 @@ void writeback_set_ratelimit(void); /* pdflush.c */ extern int nr_pdflush_threads; /* Global so it can be exported to sysctl read-only. */ +extern int nr_pdflush_threads_max; /* Global so it can be exported to sysctl */ +extern int nr_pdflush_threads_min; /* Global so it can be exported to sysctl */ #endif /* WRITEBACK_H */ -- cgit v1.2.3 From fd5e191e7610eb7ecb5e35b2045ceb6554bea15a Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 6 Apr 2009 19:00:56 -0700 Subject: SPI: add dma_alignment field to spi_master Some SPI controllers have restrictions on DMAable buffers alignemt. Currently if the buffer supplied by protocol driver is not properly aligned, the controller silently performs transfer in PIO mode. Addition of dma_alignment field to spi_master allows protocol drivers to perform proper alignment. Signed-off-by: Mike Rapoport Cc: Bryan Wu Cc: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/spi/spi.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 68bb1c501d0..2cc43fa380c 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -204,6 +204,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * SPI slaves, and are numbered from zero to num_chipselects. * each slave has a chipselect signal, but it's common that not * every chipselect is connected to a slave. + * @dma_alignment: SPI controller constraint on DMA buffers alignment. * @setup: updates the device mode and clocking records used by a * device's SPI controller; protocol code may call this. This * must fail if an unrecognized or unsupported mode is requested. @@ -239,6 +240,11 @@ struct spi_master { */ u16 num_chipselect; + /* some SPI controllers pose alignment requirements on DMAable + * buffers; let protocol drivers know about these requirements. + */ + u16 dma_alignment; + /* setup mode and clock, etc (spi driver may call many times) */ int (*setup)(struct spi_device *spi); -- cgit v1.2.3 From cc00e9cfe0e5c4c31057c722e49fdf2c76dd5953 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Mon, 6 Apr 2009 19:01:00 -0700 Subject: kprobes: cleanup comment style in kprobes.h Fix comment style in kprobes.h. Signed-off-by: Masami Hiramatsu Acked-by: Ananth N Mavinakayanahalli Cc: Anil S Keshavamurthy Cc: David S. Miller Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kprobes.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 2ec6cc14a11..39826a67836 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -94,12 +94,16 @@ struct kprobe { /* Called after addr is executed, unless... */ kprobe_post_handler_t post_handler; - /* ... called if executing addr causes a fault (eg. page fault). - * Return 1 if it handled fault, otherwise kernel will see it. */ + /* + * ... called if executing addr causes a fault (eg. page fault). + * Return 1 if it handled fault, otherwise kernel will see it. + */ kprobe_fault_handler_t fault_handler; - /* ... called if breakpoint trap occurs in probe handler. - * Return 1 if it handled break, otherwise kernel will see it. */ + /* + * ... called if breakpoint trap occurs in probe handler. + * Return 1 if it handled break, otherwise kernel will see it. + */ kprobe_break_handler_t break_handler; /* Saved opcode (which has been replaced with breakpoint) */ -- cgit v1.2.3 From de5bd88d5a5cce3cacea904d3503e5ebdb3852a2 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Mon, 6 Apr 2009 19:01:02 -0700 Subject: kprobes: support per-kprobe disabling Add disable_kprobe() and enable_kprobe() to disable/enable kprobes temporarily. disable_kprobe() asynchronously disables probe handlers of specified kprobe. So, after calling it, some handlers can be called at a while. enable_kprobe() enables specified kprobe. aggr_pre_handler and aggr_post_handler check disabled probes. On the other hand aggr_break_handler and aggr_fault_handler don't check it because these handlers will be called while executing pre or post handlers and usually those help error handling. Signed-off-by: Masami Hiramatsu Acked-by: Ananth N Mavinakayanahalli Cc: Anil S Keshavamurthy Cc: David S. Miller Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kprobes.h | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 39826a67836..1071cfddddc 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -112,18 +112,28 @@ struct kprobe { /* copy of the original instruction */ struct arch_specific_insn ainsn; - /* Indicates various status flags. Protected by kprobe_mutex. */ + /* + * Indicates various status flags. + * Protected by kprobe_mutex after this kprobe is registered. + */ u32 flags; }; /* Kprobe status flags */ #define KPROBE_FLAG_GONE 1 /* breakpoint has already gone */ +#define KPROBE_FLAG_DISABLED 2 /* probe is temporarily disabled */ +/* Has this kprobe gone ? */ static inline int kprobe_gone(struct kprobe *p) { return p->flags & KPROBE_FLAG_GONE; } +/* Is this kprobe disabled ? */ +static inline int kprobe_disabled(struct kprobe *p) +{ + return p->flags & (KPROBE_FLAG_DISABLED | KPROBE_FLAG_GONE); +} /* * Special probe type that uses setjmp-longjmp type tricks to resume * execution at a specified entry with a matching prototype corresponding @@ -283,6 +293,9 @@ void unregister_kretprobes(struct kretprobe **rps, int num); void kprobe_flush_task(struct task_struct *tk); void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head); +int disable_kprobe(struct kprobe *kp); +int enable_kprobe(struct kprobe *kp); + #else /* !CONFIG_KPROBES: */ static inline int kprobes_built_in(void) @@ -349,5 +362,13 @@ static inline void unregister_kretprobes(struct kretprobe **rps, int num) static inline void kprobe_flush_task(struct task_struct *tk) { } +static inline int disable_kprobe(struct kprobe *kp) +{ + return -ENOSYS; +} +static inline int enable_kprobe(struct kprobe *kp) +{ + return -ENOSYS; +} #endif /* CONFIG_KPROBES */ #endif /* _LINUX_KPROBES_H */ -- cgit v1.2.3 From 8f9b15286a8ea49e997e845d02d357ed33ebd090 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Mon, 6 Apr 2009 19:01:02 -0700 Subject: kprobes: support kretprobe and jprobe per-probe disabling Add disable/enable_kretprobe() and disable/enable_jprobe(). Signed-off-by: Masami Hiramatsu Acked-by: Ananth N Mavinakayanahalli Cc: Anil S Keshavamurthy Cc: David S. Miller Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kprobes.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 1071cfddddc..bcd9c07848b 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -371,4 +371,21 @@ static inline int enable_kprobe(struct kprobe *kp) return -ENOSYS; } #endif /* CONFIG_KPROBES */ +static inline int disable_kretprobe(struct kretprobe *rp) +{ + return disable_kprobe(&rp->kp); +} +static inline int enable_kretprobe(struct kretprobe *rp) +{ + return enable_kprobe(&rp->kp); +} +static inline int disable_jprobe(struct jprobe *jp) +{ + return disable_kprobe(&jp->kp); +} +static inline int enable_jprobe(struct jprobe *jp) +{ + return enable_kprobe(&jp->kp); +} + #endif /* _LINUX_KPROBES_H */ -- cgit v1.2.3 From 909e6d94795654040ed416ac69858d5d2ce66dd3 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Mon, 6 Apr 2009 19:01:07 -0700 Subject: namespaces: move proc_net_get_sb to a generic fs/super.c helper The mqueuefs filesystem will use this helper as well. Proc's main get_sb could also be made to use it, but that will require a bit more rework. Signed-off-by: Serge E. Hallyn Cc: Cedric Le Goater Cc: Alexey Dobriyan Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index bce40a2207e..562d2855cf3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1699,6 +1699,9 @@ struct file_system_type { struct lock_class_key i_alloc_sem_key; }; +extern int get_sb_ns(struct file_system_type *fs_type, int flags, void *data, + int (*fill_super)(struct super_block *, void *, int), + struct vfsmount *mnt); extern int get_sb_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int), -- cgit v1.2.3 From 614b84cf4e4a920d2af32b8f147ea1e3b8c27ea6 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Mon, 6 Apr 2009 19:01:08 -0700 Subject: namespaces: mqueue ns: move mqueue_mnt into struct ipc_namespace Move mqueue vfsmount plus a few tunables into the ipc_namespace struct. The CONFIG_IPC_NS boolean and the ipc_namespace struct will serve both the posix message queue namespaces and the SYSV ipc namespaces. The sysctl code will be fixed separately in patch 3. After just this patch, making a change to posix mqueue tunables always changes the values in the initial ipc namespace. Signed-off-by: Cedric Le Goater Signed-off-by: Serge E. Hallyn Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 39 +++++++++++++++++++++++++++++++++++---- 1 file changed, 35 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index ea330f9e710..3e6fcacebe8 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -44,24 +44,55 @@ struct ipc_namespace { int shm_tot; struct notifier_block ipcns_nb; + + /* The kern_mount of the mqueuefs sb. We take a ref on it */ + struct vfsmount *mq_mnt; + + /* # queues in this ns, protected by mq_lock */ + unsigned int mq_queues_count; + + /* next fields are set through sysctl */ + unsigned int mq_queues_max; /* initialized to DFLT_QUEUESMAX */ + unsigned int mq_msg_max; /* initialized to DFLT_MSGMAX */ + unsigned int mq_msgsize_max; /* initialized to DFLT_MSGSIZEMAX */ + }; extern struct ipc_namespace init_ipc_ns; extern atomic_t nr_ipc_ns; -#ifdef CONFIG_SYSVIPC +#if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC) #define INIT_IPC_NS(ns) .ns = &init_ipc_ns, +#else +#define INIT_IPC_NS(ns) +#endif +#ifdef CONFIG_SYSVIPC extern int register_ipcns_notifier(struct ipc_namespace *); extern int cond_register_ipcns_notifier(struct ipc_namespace *); extern void unregister_ipcns_notifier(struct ipc_namespace *); extern int ipcns_notify(unsigned long); - #else /* CONFIG_SYSVIPC */ -#define INIT_IPC_NS(ns) +static inline int register_ipcns_notifier(struct ipc_namespace *ns) +{ return 0; } +static inline int cond_register_ipcns_notifier(struct ipc_namespace *ns) +{ return 0; } +static inline void unregister_ipcns_notifier(struct ipc_namespace *ns) { } +static inline int ipcns_notify(unsigned long l) { return 0; } #endif /* CONFIG_SYSVIPC */ -#if defined(CONFIG_SYSVIPC) && defined(CONFIG_IPC_NS) +#ifdef CONFIG_POSIX_MQUEUE +extern void mq_init_ns(struct ipc_namespace *ns); +/* default values */ +#define DFLT_QUEUESMAX 256 /* max number of message queues */ +#define DFLT_MSGMAX 10 /* max number of messages in each queue */ +#define HARD_MSGMAX (131072/sizeof(void *)) +#define DFLT_MSGSIZEMAX 8192 /* max message size */ +#else +#define mq_init_ns(ns) ((void) 0) +#endif + +#if defined(CONFIG_IPC_NS) extern void free_ipc_ns(struct kref *kref); extern struct ipc_namespace *copy_ipcs(unsigned long flags, struct ipc_namespace *ns); -- cgit v1.2.3 From 7eafd7c74c3f2e67c27621b987b28397110d643f Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Mon, 6 Apr 2009 19:01:10 -0700 Subject: namespaces: ipc namespaces: implement support for posix msqueues Implement multiple mounts of the mqueue file system, and link it to usage of CLONE_NEWIPC. Each ipc ns has a corresponding mqueuefs superblock. When a user does clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an internal mount of a new mqueuefs sb linked to the new ipc ns. When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the mqueuefs superblock. Posix message queues can be worked with both through the mq_* system calls (see mq_overview(7)), and through the VFS through the mqueue mount. Any usage of mq_open() and friends will work with the acting task's ipc namespace. Any actions through the VFS will work with the mqueuefs in which the file was created. So if a user doesn't remount mqueuefs after unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls /dev/mqueue". If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns, ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1) ipc_ns:1 will be freed, (2) it's superblock will live on until task b umounts the corresponding mqueuefs, and vfs actions will continue to succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to the deceased ipc_ns:1. To make this happen, we must protect the ipc reference count when a) a task exits and drops its ipcns->count, since it might be dropping it to 0 and freeing the ipcns b) a task accesses the ipcns through its mqueuefs interface, since it bumps the ipcns refcount and might race with the last task in the ipcns exiting. So the kref is changed to an atomic_t so we can use atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns through ns = mqueuefs_sb->s_fs_info is protected by the same lock. Signed-off-by: Cedric Le Goater Signed-off-by: Serge E. Hallyn Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 3e6fcacebe8..3392d50de35 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -25,7 +25,7 @@ struct ipc_ids { }; struct ipc_namespace { - struct kref kref; + atomic_t count; struct ipc_ids ids[3]; int sem_ctls[4]; @@ -61,6 +61,7 @@ struct ipc_namespace { extern struct ipc_namespace init_ipc_ns; extern atomic_t nr_ipc_ns; +extern spinlock_t mq_lock; #if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC) #define INIT_IPC_NS(ns) .ns = &init_ipc_ns, #else @@ -82,18 +83,18 @@ static inline int ipcns_notify(unsigned long l) { return 0; } #endif /* CONFIG_SYSVIPC */ #ifdef CONFIG_POSIX_MQUEUE -extern void mq_init_ns(struct ipc_namespace *ns); +extern int mq_init_ns(struct ipc_namespace *ns); /* default values */ #define DFLT_QUEUESMAX 256 /* max number of message queues */ #define DFLT_MSGMAX 10 /* max number of messages in each queue */ #define HARD_MSGMAX (131072/sizeof(void *)) #define DFLT_MSGSIZEMAX 8192 /* max message size */ #else -#define mq_init_ns(ns) ((void) 0) +static inline int mq_init_ns(struct ipc_namespace *ns) { return 0; } #endif #if defined(CONFIG_IPC_NS) -extern void free_ipc_ns(struct kref *kref); +extern void free_ipc_ns(struct ipc_namespace *ns); extern struct ipc_namespace *copy_ipcs(unsigned long flags, struct ipc_namespace *ns); extern void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids, @@ -103,14 +104,11 @@ extern void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids, static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) { if (ns) - kref_get(&ns->kref); + atomic_inc(&ns->count); return ns; } -static inline void put_ipc_ns(struct ipc_namespace *ns) -{ - kref_put(&ns->kref, free_ipc_ns); -} +extern void put_ipc_ns(struct ipc_namespace *ns); #else static inline struct ipc_namespace *copy_ipcs(unsigned long flags, struct ipc_namespace *ns) -- cgit v1.2.3 From bdc8e5f85f9abe2e7c78dcf39d81f9a97178788b Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Mon, 6 Apr 2009 19:01:11 -0700 Subject: namespaces: mqueue namespace: adapt sysctl Largely inspired from ipc/ipc_sysctl.c. This patch isolates the mqueue sysctl stuff in its own file. [akpm@linux-foundation.org: build fix] Signed-off-by: Cedric Le Goater Signed-off-by: Nadia Derbey Signed-off-by: Serge E. Hallyn Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 3392d50de35..3bf40e246a8 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -128,4 +128,18 @@ static inline void put_ipc_ns(struct ipc_namespace *ns) { } #endif + +#ifdef CONFIG_POSIX_MQUEUE_SYSCTL + +struct ctl_table_header; +extern struct ctl_table_header *mq_register_sysctl_table(void); + +#else /* CONFIG_POSIX_MQUEUE_SYSCTL */ + +static inline struct ctl_table_header *mq_register_sysctl_table(void) +{ + return NULL; +} + +#endif /* CONFIG_POSIX_MQUEUE_SYSCTL */ #endif -- cgit v1.2.3 From 284901a90a9e0b812ca3f5f852cbbfb60d10249d Mon Sep 17 00:00:00 2001 From: Yang Hongyang Date: Mon, 6 Apr 2009 19:01:15 -0700 Subject: dma-mapping: replace all DMA_32BIT_MASK macro with DMA_BIT_MASK(32) Replace all DMA_32BIT_MASK macro with DMA_BIT_MASK(32) Signed-off-by: Yang Hongyang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dma-mapping.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index d7d090d2103..8083b6a36a3 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -115,7 +115,7 @@ static inline u64 dma_get_mask(struct device *dev) { if (dev && dev->dma_mask && *dev->dma_mask) return *dev->dma_mask; - return DMA_32BIT_MASK; + return DMA_BIT_MASK(32); } extern u64 dma_get_required_mask(struct device *dev); -- cgit v1.2.3 From eed10e39b142eb4d284c8e4c751c0eaaa0bcd707 Mon Sep 17 00:00:00 2001 From: Koji Sato Date: Mon, 6 Apr 2009 19:01:21 -0700 Subject: nilfs2: disk format and userland interface This adds a header file which specifies the on-disk format and ioctl interface of the nilfs2 file system. Signed-off-by: Koji Sato Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nilfs2_fs.h | 854 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 854 insertions(+) create mode 100644 include/linux/nilfs2_fs.h (limited to 'include/linux') diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h new file mode 100644 index 00000000000..e38fad2f7c0 --- /dev/null +++ b/include/linux/nilfs2_fs.h @@ -0,0 +1,854 @@ +/* + * nilfs2_fs.h - NILFS2 on-disk structures and common declarations. + * + * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. + * + * 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; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + * + * Written by Koji Sato + * Ryusuke Konishi + */ +/* + * linux/include/linux/ext2_fs.h + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/include/linux/minix_fs.h + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +#ifndef _LINUX_NILFS_FS_H +#define _LINUX_NILFS_FS_H + +#include +#include + +/* + * Inode flags stored in nilfs_inode and on-memory nilfs inode + * + * We define these flags based on ext2-fs because of the + * compatibility reason; to avoid problems in chattr(1) + */ +#define NILFS_SECRM_FL 0x00000001 /* Secure deletion */ +#define NILFS_UNRM_FL 0x00000002 /* Undelete */ +#define NILFS_SYNC_FL 0x00000008 /* Synchronous updates */ +#define NILFS_IMMUTABLE_FL 0x00000010 /* Immutable file */ +#define NILFS_APPEND_FL 0x00000020 /* writes to file may only append */ +#define NILFS_NODUMP_FL 0x00000040 /* do not dump file */ +#define NILFS_NOATIME_FL 0x00000080 /* do not update atime */ +/* Reserved for compression usage... */ +#define NILFS_NOTAIL_FL 0x00008000 /* file tail should not be merged */ +#define NILFS_DIRSYNC_FL 0x00010000 /* dirsync behaviour */ + +#define NILFS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ +#define NILFS_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ + + +#define NILFS_INODE_BMAP_SIZE 7 +/** + * struct nilfs_inode - structure of an inode on disk + * @i_blocks: blocks count + * @i_size: size in bytes + * @i_ctime: creation time + * @i_mtime: modification time + * @i_dtime: deletion time + * @i_uid: user id + * @i_gid: group id + * @i_mode: file mode + * @i_links_count: links count + * @i_flags: file flags + * @i_bmap: block mapping + * @i_xattr: extended attributes + * @i_generation: file generation (for NFS) + * @i_pad: padding + */ +struct nilfs_inode { + __le64 i_blocks; + __le64 i_size; + __le64 i_ctime; + __le64 i_mtime; + __le64 i_dtime; + __le32 i_uid; + __le32 i_gid; + __le16 i_mode; + __le16 i_links_count; + __le32 i_flags; + __le64 i_bmap[NILFS_INODE_BMAP_SIZE]; +#define i_device_code i_bmap[0] + __le64 i_xattr; + __le32 i_generation; + __le32 i_pad; +}; + +/** + * struct nilfs_super_root - structure of super root + * @sr_sum: check sum + * @sr_bytes: byte count of the structure + * @sr_flags: flags (reserved) + * @sr_nongc_ctime: write time of the last segment not for cleaner operation + * @sr_dat: DAT file inode + * @sr_cpfile: checkpoint file inode + * @sr_sufile: segment usage file inode + */ +struct nilfs_super_root { + __le32 sr_sum; + __le16 sr_bytes; + __le16 sr_flags; + __le64 sr_nongc_ctime; + struct nilfs_inode sr_dat; + struct nilfs_inode sr_cpfile; + struct nilfs_inode sr_sufile; +}; + +#define NILFS_SR_MDT_OFFSET(inode_size, i) \ + ((unsigned long)&((struct nilfs_super_root *)0)->sr_dat + \ + (inode_size) * (i)) +#define NILFS_SR_DAT_OFFSET(inode_size) NILFS_SR_MDT_OFFSET(inode_size, 0) +#define NILFS_SR_CPFILE_OFFSET(inode_size) NILFS_SR_MDT_OFFSET(inode_size, 1) +#define NILFS_SR_SUFILE_OFFSET(inode_size) NILFS_SR_MDT_OFFSET(inode_size, 2) +#define NILFS_SR_BYTES (sizeof(struct nilfs_super_root)) + +/* + * Maximal mount counts + */ +#define NILFS_DFL_MAX_MNT_COUNT 50 /* 50 mounts */ + +/* + * File system states (sbp->s_state, nilfs->ns_mount_state) + */ +#define NILFS_VALID_FS 0x0001 /* Unmounted cleanly */ +#define NILFS_ERROR_FS 0x0002 /* Errors detected */ +#define NILFS_RESIZE_FS 0x0004 /* Resize required */ + +/* + * Mount flags (sbi->s_mount_opt) + */ +#define NILFS_MOUNT_ERROR_MODE 0x0070 /* Error mode mask */ +#define NILFS_MOUNT_ERRORS_CONT 0x0010 /* Continue on errors */ +#define NILFS_MOUNT_ERRORS_RO 0x0020 /* Remount fs ro on errors */ +#define NILFS_MOUNT_ERRORS_PANIC 0x0040 /* Panic on errors */ +#define NILFS_MOUNT_SNAPSHOT 0x0080 /* Snapshot flag */ +#define NILFS_MOUNT_BARRIER 0x1000 /* Use block barriers */ +#define NILFS_MOUNT_STRICT_ORDER 0x2000 /* Apply strict in-order + semantics also for data */ + + +/** + * struct nilfs_super_block - structure of super block on disk + */ +struct nilfs_super_block { + __le32 s_rev_level; /* Revision level */ + __le16 s_minor_rev_level; /* minor revision level */ + __le16 s_magic; /* Magic signature */ + + __le16 s_bytes; /* Bytes count of CRC calculation + for this structure. s_reserved + is excluded. */ + __le16 s_flags; /* flags */ + __le32 s_crc_seed; /* Seed value of CRC calculation */ + __le32 s_sum; /* Check sum of super block */ + + __le32 s_log_block_size; /* Block size represented as follows + blocksize = + 1 << (s_log_block_size + 10) */ + __le64 s_nsegments; /* Number of segments in filesystem */ + __le64 s_dev_size; /* block device size in bytes */ + __le64 s_first_data_block; /* 1st seg disk block number */ + __le32 s_blocks_per_segment; /* number of blocks per full segment */ + __le32 s_r_segments_percentage; /* Reserved segments percentage */ + + __le64 s_last_cno; /* Last checkpoint number */ + __le64 s_last_pseg; /* disk block addr pseg written last */ + __le64 s_last_seq; /* seq. number of seg written last */ + __le64 s_free_blocks_count; /* Free blocks count */ + + __le64 s_ctime; /* Creation time (execution time of + newfs) */ + __le64 s_mtime; /* Mount time */ + __le64 s_wtime; /* Write time */ + __le16 s_mnt_count; /* Mount count */ + __le16 s_max_mnt_count; /* Maximal mount count */ + __le16 s_state; /* File system state */ + __le16 s_errors; /* Behaviour when detecting errors */ + __le64 s_lastcheck; /* time of last check */ + + __le32 s_checkinterval; /* max. time between checks */ + __le32 s_creator_os; /* OS */ + __le16 s_def_resuid; /* Default uid for reserved blocks */ + __le16 s_def_resgid; /* Default gid for reserved blocks */ + __le32 s_first_ino; /* First non-reserved inode */ + + __le16 s_inode_size; /* Size of an inode */ + __le16 s_dat_entry_size; /* Size of a dat entry */ + __le16 s_checkpoint_size; /* Size of a checkpoint */ + __le16 s_segment_usage_size; /* Size of a segment usage */ + + __u8 s_uuid[16]; /* 128-bit uuid for volume */ + char s_volume_name[16]; /* volume name */ + char s_last_mounted[64]; /* directory where last mounted */ + + __le32 s_c_interval; /* Commit interval of segment */ + __le32 s_c_block_max; /* Threshold of data amount for + the segment construction */ + __u32 s_reserved[192]; /* padding to the end of the block */ +}; + +/* + * Codes for operating systems + */ +#define NILFS_OS_LINUX 0 +/* Codes from 1 to 4 are reserved to keep compatibility with ext2 creator-OS */ + +/* + * Revision levels + */ +#define NILFS_CURRENT_REV 2 /* current major revision */ +#define NILFS_MINOR_REV 0 /* minor revision */ + +/* + * Bytes count of super_block for CRC-calculation + */ +#define NILFS_SB_BYTES \ + ((long)&((struct nilfs_super_block *)0)->s_reserved) + +/* + * Special inode number + */ +#define NILFS_ROOT_INO 2 /* Root file inode */ +#define NILFS_DAT_INO 3 /* DAT file */ +#define NILFS_CPFILE_INO 4 /* checkpoint file */ +#define NILFS_SUFILE_INO 5 /* segment usage file */ +#define NILFS_IFILE_INO 6 /* ifile */ +#define NILFS_ATIME_INO 7 /* Atime file (reserved) */ +#define NILFS_XATTR_INO 8 /* Xattribute file (reserved) */ +#define NILFS_SKETCH_INO 10 /* Sketch file */ +#define NILFS_USER_INO 11 /* Fisrt user's file inode number */ + +#define NILFS_SB_OFFSET_BYTES 1024 /* byte offset of nilfs superblock */ +#define NILFS_SUPER_MAGIC 0x3434 /* NILFS filesystem magic number */ + +#define NILFS_SEG_MIN_BLOCKS 16 /* Minimum number of blocks in + a full segment */ +#define NILFS_PSEG_MIN_BLOCKS 2 /* Minimum number of blocks in + a partial segment */ +#define NILFS_MIN_NRSVSEGS 8 /* Minimum number of reserved + segments */ + + +/* + * Maximal count of links to a file + */ +#define NILFS_LINK_MAX 32000 + +/* + * Structure of a directory entry + * (Same as ext2) + */ + +#define NILFS_NAME_LEN 255 + +/* + * The new version of the directory entry. Since V0 structures are + * stored in intel byte order, and the name_len field could never be + * bigger than 255 chars, it's safe to reclaim the extra byte for the + * file_type field. + */ +struct nilfs_dir_entry { + __le64 inode; /* Inode number */ + __le16 rec_len; /* Directory entry length */ + __u8 name_len; /* Name length */ + __u8 file_type; + char name[NILFS_NAME_LEN]; /* File name */ + char pad; +}; + +/* + * NILFS directory file types. Only the low 3 bits are used. The + * other bits are reserved for now. + */ +enum { + NILFS_FT_UNKNOWN, + NILFS_FT_REG_FILE, + NILFS_FT_DIR, + NILFS_FT_CHRDEV, + NILFS_FT_BLKDEV, + NILFS_FT_FIFO, + NILFS_FT_SOCK, + NILFS_FT_SYMLINK, + NILFS_FT_MAX +}; + +/* + * NILFS_DIR_PAD defines the directory entries boundaries + * + * NOTE: It must be a multiple of 8 + */ +#define NILFS_DIR_PAD 8 +#define NILFS_DIR_ROUND (NILFS_DIR_PAD - 1) +#define NILFS_DIR_REC_LEN(name_len) (((name_len) + 12 + NILFS_DIR_ROUND) & \ + ~NILFS_DIR_ROUND) + + +/** + * struct nilfs_finfo - file information + * @fi_ino: inode number + * @fi_cno: checkpoint number + * @fi_nblocks: number of blocks (including intermediate blocks) + * @fi_ndatablk: number of file data blocks + */ +struct nilfs_finfo { + __le64 fi_ino; + __le64 fi_cno; + __le32 fi_nblocks; + __le32 fi_ndatablk; + /* array of virtual block numbers */ +}; + +/** + * struct nilfs_binfo_v - information for the block to which a virtual block number is assigned + * @bi_vblocknr: virtual block number + * @bi_blkoff: block offset + */ +struct nilfs_binfo_v { + __le64 bi_vblocknr; + __le64 bi_blkoff; +}; + +/** + * struct nilfs_binfo_dat - information for the block which belongs to the DAT file + * @bi_blkoff: block offset + * @bi_level: level + * @bi_pad: padding + */ +struct nilfs_binfo_dat { + __le64 bi_blkoff; + __u8 bi_level; + __u8 bi_pad[7]; +}; + +/** + * union nilfs_binfo: block information + * @bi_v: nilfs_binfo_v structure + * @bi_dat: nilfs_binfo_dat structure + */ +union nilfs_binfo { + struct nilfs_binfo_v bi_v; + struct nilfs_binfo_dat bi_dat; +}; + +/** + * struct nilfs_segment_summary - segment summary + * @ss_datasum: checksum of data + * @ss_sumsum: checksum of segment summary + * @ss_magic: magic number + * @ss_bytes: size of this structure in bytes + * @ss_flags: flags + * @ss_seq: sequence number + * @ss_create: creation timestamp + * @ss_next: next segment + * @ss_nblocks: number of blocks + * @ss_nfinfo: number of finfo structures + * @ss_sumbytes: total size of segment summary in bytes + * @ss_pad: padding + */ +struct nilfs_segment_summary { + __le32 ss_datasum; + __le32 ss_sumsum; + __le32 ss_magic; + __le16 ss_bytes; + __le16 ss_flags; + __le64 ss_seq; + __le64 ss_create; + __le64 ss_next; + __le32 ss_nblocks; + __le32 ss_nfinfo; + __le32 ss_sumbytes; + __le32 ss_pad; + /* array of finfo structures */ +}; + +#define NILFS_SEGSUM_MAGIC 0x1eaffa11 /* segment summary magic number */ + +/* + * Segment summary flags + */ +#define NILFS_SS_LOGBGN 0x0001 /* begins a logical segment */ +#define NILFS_SS_LOGEND 0x0002 /* ends a logical segment */ +#define NILFS_SS_SR 0x0004 /* has super root */ +#define NILFS_SS_SYNDT 0x0008 /* includes data only updates */ +#define NILFS_SS_GC 0x0010 /* segment written for cleaner operation */ + +/** + * struct nilfs_palloc_group_desc - block group descriptor + * @pg_nfrees: number of free entries in block group + */ +struct nilfs_palloc_group_desc { + __le32 pg_nfrees; +}; + +/** + * struct nilfs_dat_entry - disk address translation entry + * @dt_blocknr: block number + * @dt_start: start checkpoint number + * @dt_end: end checkpoint number + * @dt_rsv: reserved for future use + */ +struct nilfs_dat_entry { + __le64 de_blocknr; + __le64 de_start; + __le64 de_end; + __le64 de_rsv; +}; + +/** + * struct nilfs_dat_group_desc - block group descriptor + * @dg_nfrees: number of free virtual block numbers in block group + */ +struct nilfs_dat_group_desc { + __le32 dg_nfrees; +}; + + +/** + * struct nilfs_snapshot_list - snapshot list + * @ssl_next: next checkpoint number on snapshot list + * @ssl_prev: previous checkpoint number on snapshot list + */ +struct nilfs_snapshot_list { + __le64 ssl_next; + __le64 ssl_prev; +}; + +/** + * struct nilfs_checkpoint - checkpoint structure + * @cp_flags: flags + * @cp_checkpoints_count: checkpoints count in a block + * @cp_snapshot_list: snapshot list + * @cp_cno: checkpoint number + * @cp_create: creation timestamp + * @cp_nblk_inc: number of blocks incremented by this checkpoint + * @cp_inodes_count: inodes count + * @cp_blocks_count: blocks count + * @cp_ifile_inode: inode of ifile + */ +struct nilfs_checkpoint { + __le32 cp_flags; + __le32 cp_checkpoints_count; + struct nilfs_snapshot_list cp_snapshot_list; + __le64 cp_cno; + __le64 cp_create; + __le64 cp_nblk_inc; + __le64 cp_inodes_count; + __le64 cp_blocks_count; /* Reserved (might be deleted) */ + + /* Do not change the byte offset of ifile inode. + To keep the compatibility of the disk format, + additional fields should be added behind cp_ifile_inode. */ + struct nilfs_inode cp_ifile_inode; +}; + +/* checkpoint flags */ +enum { + NILFS_CHECKPOINT_SNAPSHOT, + NILFS_CHECKPOINT_INVALID, + NILFS_CHECKPOINT_SKETCH, +}; + +#define NILFS_CHECKPOINT_FNS(flag, name) \ +static inline void \ +nilfs_checkpoint_set_##name(struct nilfs_checkpoint *cp) \ +{ \ + cp->cp_flags = cpu_to_le32(le32_to_cpu(cp->cp_flags) | \ + (1UL << NILFS_CHECKPOINT_##flag)); \ +} \ +static inline void \ +nilfs_checkpoint_clear_##name(struct nilfs_checkpoint *cp) \ +{ \ + cp->cp_flags = cpu_to_le32(le32_to_cpu(cp->cp_flags) & \ + ~(1UL << NILFS_CHECKPOINT_##flag)); \ +} \ +static inline int \ +nilfs_checkpoint_##name(const struct nilfs_checkpoint *cp) \ +{ \ + return !!(le32_to_cpu(cp->cp_flags) & \ + (1UL << NILFS_CHECKPOINT_##flag)); \ +} + +NILFS_CHECKPOINT_FNS(SNAPSHOT, snapshot) +NILFS_CHECKPOINT_FNS(INVALID, invalid) +NILFS_CHECKPOINT_FNS(SKETCH, sketch) + +/** + * struct nilfs_cpinfo - checkpoint information + * @ci_flags: flags + * @ci_cno: checkpoint number + * @ci_create: creation timestamp + * @ci_nblk_inc: number of blocks incremented by this checkpoint + * @ci_inodes_count: inodes count + * @ci_blocks_count: blocks count + * @ci_next: next checkpoint number in snapshot list + */ +struct nilfs_cpinfo { + __u32 ci_flags; + __u64 ci_cno; + __u64 ci_create; + __u64 ci_nblk_inc; + __u64 ci_inodes_count; + __u64 ci_blocks_count; + __u64 ci_next; +}; + +#define NILFS_CPINFO_FNS(flag, name) \ +static inline int \ +nilfs_cpinfo_##name(const struct nilfs_cpinfo *cpinfo) \ +{ \ + return !!(cpinfo->ci_flags & (1UL << NILFS_CHECKPOINT_##flag)); \ +} + +NILFS_CPINFO_FNS(SNAPSHOT, snapshot) +NILFS_CPINFO_FNS(INVALID, invalid) +NILFS_CPINFO_FNS(SKETCH, sketch) + + +/** + * struct nilfs_cpfile_header - checkpoint file header + * @ch_ncheckpoints: number of checkpoints + * @ch_nsnapshots: number of snapshots + * @ch_snapshot_list: snapshot list + */ +struct nilfs_cpfile_header { + __le64 ch_ncheckpoints; + __le64 ch_nsnapshots; + struct nilfs_snapshot_list ch_snapshot_list; +}; + +#define NILFS_CPFILE_FIRST_CHECKPOINT_OFFSET \ + ((sizeof(struct nilfs_cpfile_header) + \ + sizeof(struct nilfs_checkpoint) - 1) / \ + sizeof(struct nilfs_checkpoint)) + +/** + * struct nilfs_segment_usage - segment usage + * @su_lastmod: last modified timestamp + * @su_nblocks: number of blocks in segment + * @su_flags: flags + */ +struct nilfs_segment_usage { + __le64 su_lastmod; + __le32 su_nblocks; + __le32 su_flags; +}; + +/* segment usage flag */ +enum { + NILFS_SEGMENT_USAGE_ACTIVE, + NILFS_SEGMENT_USAGE_DIRTY, + NILFS_SEGMENT_USAGE_ERROR, + + /* on-memory only */ + NILFS_SEGMENT_USAGE_VOLATILE_ACTIVE, + /* ... */ +}; + +#define NILFS_SEGMENT_USAGE_FNS(flag, name) \ +static inline void \ +nilfs_segment_usage_set_##name(struct nilfs_segment_usage *su) \ +{ \ + su->su_flags = cpu_to_le32(le32_to_cpu(su->su_flags) | \ + (1UL << NILFS_SEGMENT_USAGE_##flag));\ +} \ +static inline void \ +nilfs_segment_usage_clear_##name(struct nilfs_segment_usage *su) \ +{ \ + su->su_flags = \ + cpu_to_le32(le32_to_cpu(su->su_flags) & \ + ~(1UL << NILFS_SEGMENT_USAGE_##flag)); \ +} \ +static inline int \ +nilfs_segment_usage_##name(const struct nilfs_segment_usage *su) \ +{ \ + return !!(le32_to_cpu(su->su_flags) & \ + (1UL << NILFS_SEGMENT_USAGE_##flag)); \ +} + +NILFS_SEGMENT_USAGE_FNS(ACTIVE, active) +NILFS_SEGMENT_USAGE_FNS(DIRTY, dirty) +NILFS_SEGMENT_USAGE_FNS(ERROR, error) +NILFS_SEGMENT_USAGE_FNS(VOLATILE_ACTIVE, volatile_active) + +static inline void +nilfs_segment_usage_set_clean(struct nilfs_segment_usage *su) +{ + su->su_lastmod = cpu_to_le64(0); + su->su_nblocks = cpu_to_le32(0); + su->su_flags = cpu_to_le32(0); +} + +static inline int +nilfs_segment_usage_clean(const struct nilfs_segment_usage *su) +{ + return !le32_to_cpu(su->su_flags); +} + +/** + * struct nilfs_sufile_header - segment usage file header + * @sh_ncleansegs: number of clean segments + * @sh_ndirtysegs: number of dirty segments + * @sh_last_alloc: last allocated segment number + */ +struct nilfs_sufile_header { + __le64 sh_ncleansegs; + __le64 sh_ndirtysegs; + __le64 sh_last_alloc; + /* ... */ +}; + +#define NILFS_SUFILE_FIRST_SEGMENT_USAGE_OFFSET \ + ((sizeof(struct nilfs_sufile_header) + \ + sizeof(struct nilfs_segment_usage) - 1) / \ + sizeof(struct nilfs_segment_usage)) + +/** + * nilfs_suinfo - segment usage information + * @sui_lastmod: + * @sui_nblocks: + * @sui_flags: + */ +struct nilfs_suinfo { + __u64 sui_lastmod; + __u32 sui_nblocks; + __u32 sui_flags; +}; + +#define NILFS_SUINFO_FNS(flag, name) \ +static inline int \ +nilfs_suinfo_##name(const struct nilfs_suinfo *si) \ +{ \ + return si->sui_flags & (1UL << NILFS_SEGMENT_USAGE_##flag); \ +} + +NILFS_SUINFO_FNS(ACTIVE, active) +NILFS_SUINFO_FNS(DIRTY, dirty) +NILFS_SUINFO_FNS(ERROR, error) +NILFS_SUINFO_FNS(VOLATILE_ACTIVE, volatile_active) + +static inline int nilfs_suinfo_clean(const struct nilfs_suinfo *si) +{ + return !si->sui_flags; +} + +/* ioctl */ +enum { + NILFS_CHECKPOINT, + NILFS_SNAPSHOT, +}; + +/** + * struct nilfs_cpmode - + * @cc_cno: + * @cc_mode: + */ +struct nilfs_cpmode { + __u64 cm_cno; + int cm_mode; +}; + +/** + * struct nilfs_argv - argument vector + * @v_base: + * @v_nmembs: + * @v_size: + * @v_index: + * @v_flags: + */ +struct nilfs_argv { + void *v_base; + size_t v_nmembs; /* number of members */ + size_t v_size; /* size of members */ + int v_index; + int v_flags; +}; + +/** + * struct nilfs_period - + * @p_start: + * @p_end: + */ +struct nilfs_period { + __u64 p_start; + __u64 p_end; +}; + +/** + * struct nilfs_cpstat - + * @cs_cno: checkpoint number + * @cs_ncps: number of checkpoints + * @cs_nsss: number of snapshots + */ +struct nilfs_cpstat { + __u64 cs_cno; + __u64 cs_ncps; + __u64 cs_nsss; +}; + +/** + * struct nilfs_sustat - + * @ss_nsegs: number of segments + * @ss_ncleansegs: number of clean segments + * @ss_ndirtysegs: number of dirty segments + * @ss_ctime: + * @ss_nongc_ctime: + */ +struct nilfs_sustat { + __u64 ss_nsegs; + __u64 ss_ncleansegs; + __u64 ss_ndirtysegs; + time_t ss_ctime; + time_t ss_nongc_ctime; +}; + +/** + * struct nilfs_vinfo - virtual block number information + * @vi_vblocknr: + * @vi_start: + * @vi_end: + * @vi_blocknr: + */ +struct nilfs_vinfo { + __u64 vi_vblocknr; + __u64 vi_start; + __u64 vi_end; + __u64 vi_blocknr; +}; + +/** + * struct nilfs_vdesc - + */ +struct nilfs_vdesc { + __u64 vd_ino; + __u64 vd_cno; + __u64 vd_vblocknr; + struct nilfs_period vd_period; + __u64 vd_blocknr; + __u64 vd_offset; + __u32 vd_flags; +}; + +/** + * struct nilfs_bdesc - + */ +struct nilfs_bdesc { + __u64 bd_ino; + __u64 bd_oblocknr; + __u64 bd_blocknr; + __u64 bd_offset; + __u32 bd_level; +}; + +#define NILFS_TIMEDWAIT_WRITE_LOCKED 0x1 +#define NILFS_TIMEDWAIT_SEG_WRITE 0x2 + +/** + * struct nilfs_wait_cond - + */ +struct nilfs_wait_cond { + int wc_cond; + int wc_flags; + struct timespec wc_timeout; +}; + +#define NILFS_IOCTL_IDENT 'n' + +#define NILFS_IOCTL_CHANGE_CPMODE \ + _IOW(NILFS_IOCTL_IDENT, 0x80, struct nilfs_cpmode) +#define NILFS_IOCTL_DELETE_CHECKPOINT \ + _IOW(NILFS_IOCTL_IDENT, 0x81, __u64) +#define NILFS_IOCTL_GET_CPINFO \ + _IOR(NILFS_IOCTL_IDENT, 0x82, struct nilfs_argv) +#define NILFS_IOCTL_GET_CPSTAT \ + _IOR(NILFS_IOCTL_IDENT, 0x83, struct nilfs_cpstat) +#define NILFS_IOCTL_GET_SUINFO \ + _IOR(NILFS_IOCTL_IDENT, 0x84, struct nilfs_argv) +#define NILFS_IOCTL_GET_SUSTAT \ + _IOR(NILFS_IOCTL_IDENT, 0x85, struct nilfs_sustat) +#define NILFS_IOCTL_GET_VINFO \ + _IOWR(NILFS_IOCTL_IDENT, 0x86, struct nilfs_argv) +#define NILFS_IOCTL_GET_BDESCS \ + _IOWR(NILFS_IOCTL_IDENT, 0x87, struct nilfs_argv) +#define NILFS_IOCTL_CLEAN_SEGMENTS \ + _IOW(NILFS_IOCTL_IDENT, 0x88, struct nilfs_argv[5]) +#define NILFS_IOCTL_TIMEDWAIT \ + _IOWR(NILFS_IOCTL_IDENT, 0x89, struct nilfs_wait_cond) +#define NILFS_IOCTL_SYNC \ + _IOR(NILFS_IOCTL_IDENT, 0x8A, __u64) +#define NILFS_IOCTL_RESIZE \ + _IOW(NILFS_IOCTL_IDENT, 0x8B, __u64) + +/* compat_ioctl */ +#ifdef CONFIG_COMPAT +#include + +struct nilfs_cpmode32 { + __u64 cm_cno; + compat_int_t cm_mode; +}; + +struct nilfs_argv32 { + compat_caddr_t v_base; + compat_size_t v_nmembs; + compat_size_t v_size; + compat_int_t v_index; + compat_int_t v_flags; +}; + +struct nilfs_sustat32 { + __u64 ss_nsegs; + __u64 ss_ncleansegs; + __u64 ss_ndirtysegs; + compat_time_t ss_ctime; + compat_time_t ss_nongc_ctime; +}; + +struct nilfs_wait_cond32 { + compat_int_t wc_cond; + compat_int_t wc_flags; + struct compat_timespec wc_timeout; +}; + +#define NILFS_IOCTL32_CHANGE_CPMODE \ + _IOW(NILFS_IOCTL_IDENT, 0x80, struct nilfs_cpmode32) +#define NILFS_IOCTL32_GET_CPINFO \ + _IOR(NILFS_IOCTL_IDENT, 0x82, struct nilfs_argv32) +#define NILFS_IOCTL32_GET_SUINFO \ + _IOR(NILFS_IOCTL_IDENT, 0x84, struct nilfs_argv32) +#define NILFS_IOCTL32_GET_SUSTAT \ + _IOR(NILFS_IOCTL_IDENT, 0x85, struct nilfs_sustat32) +#define NILFS_IOCTL32_GET_VINFO \ + _IOWR(NILFS_IOCTL_IDENT, 0x86, struct nilfs_argv32) +#define NILFS_IOCTL32_GET_BDESCS \ + _IOWR(NILFS_IOCTL_IDENT, 0x87, struct nilfs_argv32) +#define NILFS_IOCTL32_CLEAN_SEGMENTS \ + _IOW(NILFS_IOCTL_IDENT, 0x88, struct nilfs_argv32[5]) +#define NILFS_IOCTL32_TIMEDWAIT \ + _IOWR(NILFS_IOCTL_IDENT, 0x89, struct nilfs_wait_cond32) +#endif /* CONFIG_COMPAT */ + +#endif /* _LINUX_NILFS_FS_H */ -- cgit v1.2.3 From 1088dcf4c3a0a27fdad5214781d5084b11405238 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Mon, 6 Apr 2009 19:01:51 -0700 Subject: nilfs2: remove timedwait ioctl command This removes NILFS_IOCTL_TIMEDWAIT command from ioctl interface along with the related flags and wait queue. The command is terrible because it just sleeps in the ioctl. I prefer to avoid this by devising means of event polling in userland program. By reconsidering the userland GC daemon, I found this is possible without changing behaviour of the daemon and sacrificing efficiency. Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nilfs2_fs.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index e38fad2f7c0..b0a6b39eedb 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -763,18 +763,6 @@ struct nilfs_bdesc { __u32 bd_level; }; -#define NILFS_TIMEDWAIT_WRITE_LOCKED 0x1 -#define NILFS_TIMEDWAIT_SEG_WRITE 0x2 - -/** - * struct nilfs_wait_cond - - */ -struct nilfs_wait_cond { - int wc_cond; - int wc_flags; - struct timespec wc_timeout; -}; - #define NILFS_IOCTL_IDENT 'n' #define NILFS_IOCTL_CHANGE_CPMODE \ @@ -795,8 +783,6 @@ struct nilfs_wait_cond { _IOWR(NILFS_IOCTL_IDENT, 0x87, struct nilfs_argv) #define NILFS_IOCTL_CLEAN_SEGMENTS \ _IOW(NILFS_IOCTL_IDENT, 0x88, struct nilfs_argv[5]) -#define NILFS_IOCTL_TIMEDWAIT \ - _IOWR(NILFS_IOCTL_IDENT, 0x89, struct nilfs_wait_cond) #define NILFS_IOCTL_SYNC \ _IOR(NILFS_IOCTL_IDENT, 0x8A, __u64) #define NILFS_IOCTL_RESIZE \ @@ -827,12 +813,6 @@ struct nilfs_sustat32 { compat_time_t ss_nongc_ctime; }; -struct nilfs_wait_cond32 { - compat_int_t wc_cond; - compat_int_t wc_flags; - struct compat_timespec wc_timeout; -}; - #define NILFS_IOCTL32_CHANGE_CPMODE \ _IOW(NILFS_IOCTL_IDENT, 0x80, struct nilfs_cpmode32) #define NILFS_IOCTL32_GET_CPINFO \ @@ -847,8 +827,6 @@ struct nilfs_wait_cond32 { _IOWR(NILFS_IOCTL_IDENT, 0x87, struct nilfs_argv32) #define NILFS_IOCTL32_CLEAN_SEGMENTS \ _IOW(NILFS_IOCTL_IDENT, 0x88, struct nilfs_argv32[5]) -#define NILFS_IOCTL32_TIMEDWAIT \ - _IOWR(NILFS_IOCTL_IDENT, 0x89, struct nilfs_wait_cond32) #endif /* CONFIG_COMPAT */ #endif /* _LINUX_NILFS_FS_H */ -- cgit v1.2.3 From dc498d09be28172846cacded35ca2378222a8c7b Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Mon, 6 Apr 2009 19:01:52 -0700 Subject: nilfs2: use fixed sized types for ioctl structures Nilfs ioctl had structures not having fixed sized types such as: struct nilfs_argv { void *v_base; size_t v_nmembs; size_t v_size; int v_index; int v_flags; }; Further, some of them are wrongly aligned: e.g. struct nilfs_cpmode { __u64 cm_cno; int cm_mode; }; The size of wrongly aligned structures varies depending on architectures, and it breaks the identity of ioctl commands, which leads to arch dependent errors. Previously, these are compensated by using compat_ioctl. This fixes these problems and allows removal of compat ioctl. Since this will change sizes of those structures, binary compatibility for the past utilities will once break; new utilities have to be used instead. However, it would be helpful to avoid platform dependent problems in the long term. Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nilfs2_fs.h | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index b0a6b39eedb..8fb64ce285f 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -499,6 +499,7 @@ NILFS_CHECKPOINT_FNS(SKETCH, sketch) /** * struct nilfs_cpinfo - checkpoint information * @ci_flags: flags + * @ci_pad: padding * @ci_cno: checkpoint number * @ci_create: creation timestamp * @ci_nblk_inc: number of blocks incremented by this checkpoint @@ -508,6 +509,7 @@ NILFS_CHECKPOINT_FNS(SKETCH, sketch) */ struct nilfs_cpinfo { __u32 ci_flags; + __u32 ci_pad; __u64 ci_cno; __u64 ci_create; __u64 ci_nblk_inc; @@ -668,7 +670,8 @@ enum { */ struct nilfs_cpmode { __u64 cm_cno; - int cm_mode; + __u32 cm_mode; + __u32 cm_pad; }; /** @@ -676,15 +679,15 @@ struct nilfs_cpmode { * @v_base: * @v_nmembs: * @v_size: - * @v_index: * @v_flags: + * @v_index: */ struct nilfs_argv { - void *v_base; - size_t v_nmembs; /* number of members */ - size_t v_size; /* size of members */ - int v_index; - int v_flags; + __u64 v_base; + __u32 v_nmembs; /* number of members */ + __u16 v_size; /* size of members */ + __u16 v_flags; + __u64 v_index; }; /** @@ -721,8 +724,8 @@ struct nilfs_sustat { __u64 ss_nsegs; __u64 ss_ncleansegs; __u64 ss_ndirtysegs; - time_t ss_ctime; - time_t ss_nongc_ctime; + __u64 ss_ctime; + __u64 ss_nongc_ctime; }; /** @@ -750,6 +753,7 @@ struct nilfs_vdesc { __u64 vd_blocknr; __u64 vd_offset; __u32 vd_flags; + __u32 vd_pad; }; /** @@ -761,6 +765,7 @@ struct nilfs_bdesc { __u64 bd_blocknr; __u64 bd_offset; __u32 bd_level; + __u32 bd_pad; }; #define NILFS_IOCTL_IDENT 'n' -- cgit v1.2.3 From 8082d36aed26c4fb6ed43e4008303682eabf839e Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Mon, 6 Apr 2009 19:01:53 -0700 Subject: nilfs2: remove compat ioctl code This removes compat code from the nilfs ioctls and applies the same function for both .ioctl and .compat_ioctl file operations. Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nilfs2_fs.h | 41 ----------------------------------------- 1 file changed, 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index 8fb64ce285f..306c446e694 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -793,45 +793,4 @@ struct nilfs_bdesc { #define NILFS_IOCTL_RESIZE \ _IOW(NILFS_IOCTL_IDENT, 0x8B, __u64) -/* compat_ioctl */ -#ifdef CONFIG_COMPAT -#include - -struct nilfs_cpmode32 { - __u64 cm_cno; - compat_int_t cm_mode; -}; - -struct nilfs_argv32 { - compat_caddr_t v_base; - compat_size_t v_nmembs; - compat_size_t v_size; - compat_int_t v_index; - compat_int_t v_flags; -}; - -struct nilfs_sustat32 { - __u64 ss_nsegs; - __u64 ss_ncleansegs; - __u64 ss_ndirtysegs; - compat_time_t ss_ctime; - compat_time_t ss_nongc_ctime; -}; - -#define NILFS_IOCTL32_CHANGE_CPMODE \ - _IOW(NILFS_IOCTL_IDENT, 0x80, struct nilfs_cpmode32) -#define NILFS_IOCTL32_GET_CPINFO \ - _IOR(NILFS_IOCTL_IDENT, 0x82, struct nilfs_argv32) -#define NILFS_IOCTL32_GET_SUINFO \ - _IOR(NILFS_IOCTL_IDENT, 0x84, struct nilfs_argv32) -#define NILFS_IOCTL32_GET_SUSTAT \ - _IOR(NILFS_IOCTL_IDENT, 0x85, struct nilfs_sustat32) -#define NILFS_IOCTL32_GET_VINFO \ - _IOWR(NILFS_IOCTL_IDENT, 0x86, struct nilfs_argv32) -#define NILFS_IOCTL32_GET_BDESCS \ - _IOWR(NILFS_IOCTL_IDENT, 0x87, struct nilfs_argv32) -#define NILFS_IOCTL32_CLEAN_SEGMENTS \ - _IOW(NILFS_IOCTL_IDENT, 0x88, struct nilfs_argv32[5]) -#endif /* CONFIG_COMPAT */ - #endif /* _LINUX_NILFS_FS_H */ -- cgit v1.2.3 From 2c2e52fc4fca251e68f90821c9ff5cb18be4df58 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Mon, 6 Apr 2009 19:01:54 -0700 Subject: nilfs2: extend nilfs_sustat ioctl struct This adds a new argument to the nilfs_sustat structure. The extended field allows to delete volatile active state of segments, which was needed to protect freshly-created segments from garbage collection but has confused code dealing with segments. This extension alleviates the mess and gives room for further simplifications. The volatile active flag is not persistent, so it's eliminable on this occasion without affecting compatibility other than the ioctl change. Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nilfs2_fs.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index 306c446e694..aa93f0ee29d 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -565,8 +565,6 @@ enum { NILFS_SEGMENT_USAGE_DIRTY, NILFS_SEGMENT_USAGE_ERROR, - /* on-memory only */ - NILFS_SEGMENT_USAGE_VOLATILE_ACTIVE, /* ... */ }; @@ -594,7 +592,6 @@ nilfs_segment_usage_##name(const struct nilfs_segment_usage *su) \ NILFS_SEGMENT_USAGE_FNS(ACTIVE, active) NILFS_SEGMENT_USAGE_FNS(DIRTY, dirty) NILFS_SEGMENT_USAGE_FNS(ERROR, error) -NILFS_SEGMENT_USAGE_FNS(VOLATILE_ACTIVE, volatile_active) static inline void nilfs_segment_usage_set_clean(struct nilfs_segment_usage *su) @@ -650,7 +647,6 @@ nilfs_suinfo_##name(const struct nilfs_suinfo *si) \ NILFS_SUINFO_FNS(ACTIVE, active) NILFS_SUINFO_FNS(DIRTY, dirty) NILFS_SUINFO_FNS(ERROR, error) -NILFS_SUINFO_FNS(VOLATILE_ACTIVE, volatile_active) static inline int nilfs_suinfo_clean(const struct nilfs_suinfo *si) { @@ -717,8 +713,9 @@ struct nilfs_cpstat { * @ss_nsegs: number of segments * @ss_ncleansegs: number of clean segments * @ss_ndirtysegs: number of dirty segments - * @ss_ctime: - * @ss_nongc_ctime: + * @ss_ctime: creation time of the last segment + * @ss_nongc_ctime: creation time of the last segment not for GC + * @ss_prot_seq: least sequence number of segments which must not be reclaimed */ struct nilfs_sustat { __u64 ss_nsegs; @@ -726,6 +723,7 @@ struct nilfs_sustat { __u64 ss_ndirtysegs; __u64 ss_ctime; __u64 ss_nongc_ctime; + __u64 ss_prot_seq; }; /** -- cgit v1.2.3 From 458c5b0822a669d170fdb7bb16c9145f652ebe06 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Mon, 6 Apr 2009 19:01:56 -0700 Subject: nilfs2: clean up sketch file The sketch file is a file to mark checkpoints with user data. It was experimentally introduced in the original implementation, and now obsolete. The file was handled differently with regular files; the file size got truncated when a checkpoint was created. This stops the special treatment and will treat it as a regular file. Most users are not affected because mkfs.nilfs2 no longer makes this file. Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nilfs2_fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index aa93f0ee29d..e9c84aa4a8e 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -494,7 +494,6 @@ nilfs_checkpoint_##name(const struct nilfs_checkpoint *cp) \ NILFS_CHECKPOINT_FNS(SNAPSHOT, snapshot) NILFS_CHECKPOINT_FNS(INVALID, invalid) -NILFS_CHECKPOINT_FNS(SKETCH, sketch) /** * struct nilfs_cpinfo - checkpoint information @@ -527,7 +526,6 @@ nilfs_cpinfo_##name(const struct nilfs_cpinfo *cpinfo) \ NILFS_CPINFO_FNS(SNAPSHOT, snapshot) NILFS_CPINFO_FNS(INVALID, invalid) -NILFS_CPINFO_FNS(SKETCH, sketch) /** -- cgit v1.2.3 From c96fa464a567a2a8796009af0e79bc68af73f485 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Mon, 6 Apr 2009 19:01:57 -0700 Subject: nilfs2: mark minor flag for checkpoint created by internal operation Nilfs creates checkpoints even for garbage collection or metadata updates such as checkpoint mode change. So, user often sees checkpoints created only by such internal operations. This is inconvenient in some situations. For example, application that monitors checkpoints and changes them to snapshots, will fall into an infinite loop because it cannot distinguish internally created checkpoints. This patch solves this sort of problem by adding a flag to checkpoint for identification. Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nilfs2_fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index e9c84aa4a8e..cbce6647f7f 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -470,6 +470,7 @@ enum { NILFS_CHECKPOINT_SNAPSHOT, NILFS_CHECKPOINT_INVALID, NILFS_CHECKPOINT_SKETCH, + NILFS_CHECKPOINT_MINOR, }; #define NILFS_CHECKPOINT_FNS(flag, name) \ @@ -494,6 +495,7 @@ nilfs_checkpoint_##name(const struct nilfs_checkpoint *cp) \ NILFS_CHECKPOINT_FNS(SNAPSHOT, snapshot) NILFS_CHECKPOINT_FNS(INVALID, invalid) +NILFS_CHECKPOINT_FNS(MINOR, minor) /** * struct nilfs_cpinfo - checkpoint information @@ -526,6 +528,7 @@ nilfs_cpinfo_##name(const struct nilfs_cpinfo *cpinfo) \ NILFS_CPINFO_FNS(SNAPSHOT, snapshot) NILFS_CPINFO_FNS(INVALID, invalid) +NILFS_CPINFO_FNS(MINOR, minor) /** -- cgit v1.2.3 From e339ad31f59925b48a92ee3947692fdf9758b8c7 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Mon, 6 Apr 2009 19:01:59 -0700 Subject: nilfs2: introduce secondary super block The former versions didn't have extra super blocks. This improves the weak point by introducing another super block at unused region in tail of the partition. This doesn't break disk format compatibility; older versions just ingore the secondary super block, and new versions just recover it if it doesn't exist. The partition created by an old mkfs may not have unused region, but in that case, the secondary super block will not be added. This doesn't make more redundant copies of the super block; it is a future work. Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nilfs2_fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index cbce6647f7f..1275b309953 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -252,6 +252,10 @@ struct nilfs_super_block { #define NILFS_MIN_NRSVSEGS 8 /* Minimum number of reserved segments */ +/* + * bytes offset of secondary super block + */ +#define NILFS_SB2_OFFSET_BYTES(devsize) ((((devsize) >> 12) - 1) << 12) /* * Maximal count of links to a file -- cgit v1.2.3 From 612392307cb09e49051225092cbbd7049bd8db93 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Mon, 6 Apr 2009 19:02:00 -0700 Subject: nilfs2: support nanosecond timestamp After a review of user's feedback for finding out other compatibility issues, I found nilfs improperly initializes timestamps in inode; CURRENT_TIME was used there instead of CURRENT_TIME_SEC even though nilfs didn't have nanosecond timestamps on disk. A few users gave us the report that the tar program sometimes failed to expand symbolic links on nilfs, and it turned out to be the cause. Instead of applying the above displacement, I've decided to support nanosecond timestamps on this occation. Fortunetaly, a needless 64-bit field was in the nilfs_inode struct, and I found it's available for this purpose without impact for the users. So, this will do the enhancement and resolve the tar problem. Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nilfs2_fs.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index 1275b309953..79fec6af3f9 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -67,9 +67,10 @@ * struct nilfs_inode - structure of an inode on disk * @i_blocks: blocks count * @i_size: size in bytes - * @i_ctime: creation time - * @i_mtime: modification time - * @i_dtime: deletion time + * @i_ctime: creation time (seconds) + * @i_mtime: modification time (seconds) + * @i_ctime_nsec: creation time (nano seconds) + * @i_mtime_nsec: modification time (nano seconds) * @i_uid: user id * @i_gid: group id * @i_mode: file mode @@ -85,7 +86,8 @@ struct nilfs_inode { __le64 i_size; __le64 i_ctime; __le64 i_mtime; - __le64 i_dtime; + __le32 i_ctime_nsec; + __le32 i_mtime_nsec; __le32 i_uid; __le32 i_gid; __le16 i_mode; -- cgit v1.2.3 From f786ddd285b4100909a013041d3eee1be9fac4db Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Tue, 7 Apr 2009 16:48:07 +0100 Subject: tty: Correct inline types for tty_driver_kref_get() tty_driver_kref_get() should be static inline and not extern inline (the latter even changed it's semantics in gcc >= 4.3). Signed-off-by: Adrian Bunk Signed-off-by: Alan Cox Signed-off-by: Linus Torvalds --- include/linux/tty_driver.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 8615d661ab6..bcba84ea2d8 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -309,7 +309,8 @@ extern void tty_set_operations(struct tty_driver *driver, extern struct tty_driver *tty_find_polling_driver(char *name, int *line); extern void tty_driver_kref_put(struct tty_driver *driver); -extern inline struct tty_driver *tty_driver_kref_get(struct tty_driver *d) + +static inline struct tty_driver *tty_driver_kref_get(struct tty_driver *d) { kref_get(&d->kref); return d; -- cgit v1.2.3 From 1dcb884ca8048efb4ce2999d367c26369ab2227c Mon Sep 17 00:00:00 2001 From: Christian Pellegrin Date: Tue, 7 Apr 2009 16:48:51 +0100 Subject: Add support for the MAX3100 SPI UART. (akpm: queued pending confirmation of the new major number) [randy.dunlap@oracle.com: select SERIAL_CORE] Signed-off-by: Christian Pellegrin Signed-off-by: Andrew Morton Signed-off-by: Alan Cox Signed-off-by: Linus Torvalds --- include/linux/serial_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 83e4b3ff9cd..57a97e52e58 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -164,6 +164,9 @@ /* NWPSERIAL */ #define PORT_NWPSERIAL 85 +/* MAX3100 */ +#define PORT_MAX3100 86 + #ifdef __KERNEL__ #include -- cgit v1.2.3 From 51dcdfec6a274afc1c6fce180d582add9ff512c0 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 7 Apr 2009 15:30:57 +0100 Subject: parport: Use the PCI IRQ if offered PCI parallel port devices can IRQ share so we should stop them hogging the line and making a mess on modern PC systems. We know the sharing side works as the PCMCIA driver has shared the parallel port IRQ for some time. Signed-off-by: Alan Cox Signed-off-by: Linus Torvalds --- include/linux/parport_pc.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/parport_pc.h b/include/linux/parport_pc.h index ea8c6d84996..cc1767f5cca 100644 --- a/include/linux/parport_pc.h +++ b/include/linux/parport_pc.h @@ -228,10 +228,11 @@ extern void parport_pc_release_resources(struct parport *p); extern int parport_pc_claim_resources(struct parport *p); /* PCMCIA code will want to get us to look at a port. Provide a mechanism. */ -extern struct parport *parport_pc_probe_port (unsigned long base, - unsigned long base_hi, - int irq, int dma, - struct device *dev); -extern void parport_pc_unregister_port (struct parport *p); +extern struct parport *parport_pc_probe_port(unsigned long base, + unsigned long base_hi, + int irq, int dma, + struct device *dev, + int irqflags); +extern void parport_pc_unregister_port(struct parport *p); #endif -- cgit v1.2.3 From aeeae86859f4319de0a4946b44771d9926eeed54 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 7 Apr 2009 07:59:41 -0700 Subject: Fix build errors due to CONFIG_BRANCH_TRACER=y The code that enables branch tracing for all (non-constant) branches plays games with the preprocessor and #define's the C 'if ()' construct to do tracing. That's all fine, but it fails for some unusual but valid C code that is sometimes used in macros, notably by the intel-iommu code: if (i=drhd->iommu, drhd->ignored) .. because now the preprocessor complains about multiple arguments to the 'if' macro. So make the macro expansion of this particularly horrid trick use varargs, and handle the case of comma-expressions in if-statements. Use another macro to do it cleanly in just one place. This replaces a patch by David (and acked by Steven) that did this all inside that one already-too-horrid macro. Tested-by: Ingo Molnar Cc: David Woodhouse Cc: Steven Rostedt Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 6faa7e549de..cebfdcd3dbd 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -114,7 +114,9 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); * "Define 'is'", Bill Clinton * "Define 'if'", Steven Rostedt */ -#define if(cond) if (__builtin_constant_p((cond)) ? !!(cond) : \ +#define if(cond, ...) __trace_if( (cond , ## __VA_ARGS__) ) +#define __trace_if(cond) \ + if (__builtin_constant_p((cond)) ? !!(cond) : \ ({ \ int ______r; \ static struct ftrace_branch_data \ -- cgit v1.2.3 From f876d346e3807647b1de411de6a86c44821896ca Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Wed, 8 Apr 2009 14:05:43 +0900 Subject: tracing: append a comma to INIT_FTRACE_GRAPH Impact: dont break future extensions of INIT_TASK While not a problem right now, due to lack of a comma, build fails if elements are appended to INIT_TASK() macro in development code: arch/x86/kernel/init_task.c:33: error: request for member `XXXXXXXXXX' in something not a structure or union arch/x86/kernel/init_task.c:33: error: initializer element is not constant arch/x86/kernel/init_task.c:33: error: (near initialization for `init_task.ret_stack') make[1]: *** [arch/x86/kernel/init_task.o] Error 1 make: *** [arch/x86/kernel] Error 2 Signed-off-by: Tetsuo Handa Cc: srostedt@redhat.com LKML-Reference: <200904080505.n3855hcn017109@www262.sakura.ne.jp> Signed-off-by: Ingo Molnar --- include/linux/ftrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index da5405dce34..ff112a872d7 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -357,7 +357,7 @@ struct ftrace_graph_ret { #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* for init task */ -#define INIT_FTRACE_GRAPH .ret_stack = NULL +#define INIT_FTRACE_GRAPH .ret_stack = NULL, /* * Stack of return addresses for functions -- cgit v1.2.3 From 7831d56b0a3544cbb6f82f76c34ca95e24d5b676 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Wed, 8 Apr 2009 20:13:16 +0100 Subject: tty: MAX3100 Thou shalt remember to use 'git add' or errors shall be visited on your downloads and there shall be wrath from on list and much gnashing of teeth. Thou shalt remember to use git status or there shall be catcalls and much embarrasment shall come to pass. Signed-off-by: Alan "I'm hiding" Cox Signed-off-by: Linus Torvalds --- include/linux/serial_max3100.h | 52 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) create mode 100644 include/linux/serial_max3100.h (limited to 'include/linux') diff --git a/include/linux/serial_max3100.h b/include/linux/serial_max3100.h new file mode 100644 index 00000000000..4976befb6ae --- /dev/null +++ b/include/linux/serial_max3100.h @@ -0,0 +1,52 @@ +/* + * + * Copyright (C) 2007 Christian Pellegrin + * + * 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; either version 2 of the License, or + * (at your option) any later version. + */ + + +#ifndef _LINUX_SERIAL_MAX3100_H +#define _LINUX_SERIAL_MAX3100_H 1 + + +/** + * struct plat_max3100 - MAX3100 SPI UART platform data + * @loopback: force MAX3100 in loopback + * @crystal: 1 for 3.6864 Mhz, 0 for 1.8432 + * @max3100_hw_suspend: MAX3100 has a shutdown pin. This is a hook + * called on suspend and resume to activate it. + * @poll_time: poll time for CTS signal in ms, 0 disables (so no hw + * flow ctrl is possible but you have less CPU usage) + * + * You should use this structure in your machine description to specify + * how the MAX3100 is connected. Example: + * + * static struct plat_max3100 max3100_plat_data = { + * .loopback = 0, + * .crystal = 0, + * .poll_time = 100, + * }; + * + * static struct spi_board_info spi_board_info[] = { + * { + * .modalias = "max3100", + * .platform_data = &max3100_plat_data, + * .irq = IRQ_EINT12, + * .max_speed_hz = 5*1000*1000, + * .chip_select = 0, + * }, + * }; + * + **/ +struct plat_max3100 { + int loopback; + int crystal; + void (*max3100_hw_suspend) (int suspend); + int poll_time; +}; + +#endif -- cgit v1.2.3 From 692d0eb9e02cf81fb387ff891f53840db2f3110a Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Thu, 9 Apr 2009 00:27:13 +0100 Subject: dm: remove limited barrier support Prepare for full barrier implementation: first remove the restricted support. Signed-off-by: Mikulas Patocka Signed-off-by: Alasdair G Kergon --- include/linux/device-mapper.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 66ec05a5795..ded2d7c4266 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -116,7 +116,6 @@ void dm_put_device(struct dm_target *ti, struct dm_dev *d); /* * Target features */ -#define DM_TARGET_SUPPORTS_BARRIERS 0x00000001 struct target_type { uint64_t features; -- cgit v1.2.3 From 47788c58e66c050982241d9a05eb690daceb05a9 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 8 Apr 2009 20:40:59 +0200 Subject: tracing/syscalls: use a dedicated file header Impact: fix build warnings and possibe compat misbehavior on IA64 Building a kernel on ia64 might trigger these ugly build warnings: CC arch/ia64/ia32/sys_ia32.o In file included from arch/ia64/ia32/sys_ia32.c:55: arch/ia64/ia32/ia32priv.h:290:1: warning: "elf_check_arch" redefined In file included from include/linux/elf.h:7, from include/linux/module.h:14, from include/linux/ftrace.h:8, from include/linux/syscalls.h:68, from arch/ia64/ia32/sys_ia32.c:18: arch/ia64/include/asm/elf.h:19:1: warning: this is the location of the previous definition [...] sys_ia32.c includes linux/syscalls.h which in turn includes linux/ftrace.h to import the syscalls tracing prototypes. But including ftrace.h can pull too much things for a low level file, especially on ia64 where the ia32 private headers conflict with higher level headers. Now we isolate the syscall tracing headers in their own lightweight file. Reported-by: Tony Luck Tested-by: Tony Luck Signed-off-by: Frederic Weisbecker Acked-by: Tony Luck Signed-off-by: Steven Rostedt Cc: Peter Zijlstra Cc: Jason Baron Cc: "Frank Ch. Eigler" Cc: Mathieu Desnoyers Cc: KOSAKI Motohiro Cc: Lai Jiangshan Cc: Jiaying Zhang Cc: Michael Rubin Cc: Martin Bligh Cc: Michael Davidson LKML-Reference: <20090408184058.GB6017@nowhere> Signed-off-by: Ingo Molnar --- include/linux/ftrace.h | 29 ----------------------------- include/linux/syscalls.h | 2 +- 2 files changed, 1 insertion(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ff112a872d7..8a0c2f221e6 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -511,33 +511,4 @@ static inline void trace_hw_branch_oops(void) {} #endif /* CONFIG_HW_BRANCH_TRACER */ -/* - * A syscall entry in the ftrace syscalls array. - * - * @name: name of the syscall - * @nb_args: number of parameters it takes - * @types: list of types as strings - * @args: list of args as strings (args[i] matches types[i]) - */ -struct syscall_metadata { - const char *name; - int nb_args; - const char **types; - const char **args; -}; - -#ifdef CONFIG_FTRACE_SYSCALLS -extern void arch_init_ftrace_syscalls(void); -extern struct syscall_metadata *syscall_nr_to_meta(int nr); -extern void start_ftrace_syscalls(void); -extern void stop_ftrace_syscalls(void); -extern void ftrace_syscall_enter(struct pt_regs *regs); -extern void ftrace_syscall_exit(struct pt_regs *regs); -#else -static inline void start_ftrace_syscalls(void) { } -static inline void stop_ftrace_syscalls(void) { } -static inline void ftrace_syscall_enter(struct pt_regs *regs) { } -static inline void ftrace_syscall_exit(struct pt_regs *regs) { } -#endif - #endif /* _LINUX_FTRACE_H */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 6470f74074a..dabe4ad8914 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -65,7 +65,7 @@ struct old_linux_dirent; #include #include #include -#include +#include #define __SC_DECL1(t1, a1) t1 a1 #define __SC_DECL2(t2, a2, ...) t2 a2, __SC_DECL1(__VA_ARGS__) -- cgit v1.2.3 From e3c8ca8336707062f3f7cb1cd7e6b3c753baccdd Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Wed, 8 Apr 2009 19:45:12 -0500 Subject: sched: do not count frozen tasks toward load Freezing tasks via the cgroup freezer causes the load average to climb because the freezer's current implementation puts frozen tasks in uninterruptible sleep (D state). Some applications which perform job-scheduling functions consult the load average when making decisions. If a cgroup is frozen, the load average does not provide a useful measure of the system's utilization to such applications. This is especially inconvenient if the job scheduler employs the cgroup freezer as a mechanism for preempting low priority jobs. Contrast this with using SIGSTOP for the same purpose: the stopped tasks do not count toward system load. Change task_contributes_to_load() to return false if the task is frozen. This results in /proc/loadavg behavior that better meets users' expectations. Signed-off-by: Nathan Lynch Acked-by: Andrew Morton Acked-by: Nigel Cunningham Tested-by: Nigel Cunningham Cc: Cc: containers@lists.linux-foundation.org Cc: linux-pm@lists.linux-foundation.org Cc: Matt Helsley LKML-Reference: <20090408194512.47a99b95@manatee.lan> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 98e1fe51601..b4c38bc8049 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -205,7 +205,8 @@ extern unsigned long long time_sync_thresh; #define task_is_stopped_or_traced(task) \ ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) #define task_contributes_to_load(task) \ - ((task->state & TASK_UNINTERRUPTIBLE) != 0) + ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \ + (task->flags & PF_FROZEN) == 0) #define __set_task_state(tsk, state_value) \ do { (tsk)->state = (state_value); } while (0) -- cgit v1.2.3 From 97c18e2c7a8e36d2d83d50ee070314aadac73a11 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 9 Apr 2009 10:35:47 +0800 Subject: module: try_then_request_module must wait Since the whole point of try_then_request_module is to retry the operation after a module has been loaded, we must wait for the module to fully load. Otherwise all sort of things start breaking, e.g., you won't be able to read your encrypted disks on the first attempt. Signed-off-by: Herbert Xu Tested-by: Maciej Rutecki Tested-by: Patrick McHardy Signed-off-by: Linus Torvalds --- include/linux/kmod.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kmod.h b/include/linux/kmod.h index d5fa565086d..384ca8bbf1a 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -34,7 +34,7 @@ extern int __request_module(bool wait, const char *name, ...) \ #define request_module(mod...) __request_module(true, mod) #define request_module_nowait(mod...) __request_module(false, mod) #define try_then_request_module(x, mod...) \ - ((x) ?: (__request_module(false, mod), (x))) + ((x) ?: (__request_module(true, mod), (x))) #else static inline int request_module(const char *name, ...) { return -ENOSYS; } static inline int request_module_nowait(const char *name, ...) { return -ENOSYS; } -- cgit v1.2.3