From 1d93e52eb48df986a3c4d5ad8a520bf1f6837367 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 11 Feb 2009 08:47:19 -0700 Subject: dmaengine: update kerneldoc Some of the kerneldoc comments in the dmaengine header describe already removed structure members. Remove them. Also add a short description for dma_device->device_is_tx_complete. Signed-off-by: Johannes Weiner Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 3e68469c1885..087e79acf8c7 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -97,7 +97,6 @@ typedef struct { DECLARE_BITMAP(bits, DMA_TX_TYPE_END); } dma_cap_mask_t; /** * struct dma_chan_percpu - the per-CPU part of struct dma_chan - * @refcount: local_t used for open-coded "bigref" counting * @memcpy_count: transaction counter * @bytes_transferred: byte counter */ @@ -114,9 +113,6 @@ struct dma_chan_percpu { * @cookie: last cookie value returned to client * @chan_id: channel ID for sysfs * @dev: class device for sysfs - * @refcount: kref, used in "bigref" slow-mode - * @slow_ref: indicates that the DMA channel is free - * @rcu: the DMA channel's RCU head * @device_node: used to add this to the device chan list * @local: per-cpu pointer to a struct dma_chan_percpu * @client-count: how many clients are using this channel @@ -211,8 +207,6 @@ struct dma_async_tx_descriptor { * @global_node: list_head for global dma_device_list * @cap_mask: one or more dma_capability flags * @max_xor: maximum number of xor sources, 0 if no capability - * @refcount: reference count - * @done: IO completion struct * @dev_id: unique device ID * @dev: struct device reference for dma mapping api * @device_alloc_chan_resources: allocate resources and return the @@ -225,6 +219,7 @@ struct dma_async_tx_descriptor { * @device_prep_dma_interrupt: prepares an end of chain interrupt operation * @device_prep_slave_sg: prepares a slave dma operation * @device_terminate_all: terminate all pending operations + * @device_is_tx_complete: poll for transaction completion * @device_issue_pending: push pending transactions to hardware */ struct dma_device { -- cgit v1.2.3 From a682604838763981613e42015cd0e39f2989d6bb Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 25 Feb 2009 18:03:42 -0800 Subject: rcu: Teach RCU that idle task is not quiscent state at boot This patch fixes a bug located by Vegard Nossum with the aid of kmemcheck, updated based on review comments from Nick Piggin, Ingo Molnar, and Andrew Morton. And cleans up the variable-name and function-name language. ;-) The boot CPU runs in the context of its idle thread during boot-up. During this time, idle_cpu(0) will always return nonzero, which will fool Classic and Hierarchical RCU into deciding that a large chunk of the boot-up sequence is a big long quiescent state. This in turn causes RCU to prematurely end grace periods during this time. This patch changes the rcutree.c and rcuclassic.c rcu_check_callbacks() function to ignore the idle task as a quiescent state until the system has started up the scheduler in rest_init(), introducing a new non-API function rcu_idle_now_means_idle() to inform RCU of this transition. RCU maintains an internal rcu_idle_cpu_truthful variable to track this state, which is then used by rcu_check_callback() to determine if it should believe idle_cpu(). Because this patch has the effect of disallowing RCU grace periods during long stretches of the boot-up sequence, this patch also introduces Josh Triplett's UP-only optimization that makes synchronize_rcu() be a no-op if num_online_cpus() returns 1. This allows boot-time code that calls synchronize_rcu() to proceed normally. Note, however, that RCU callbacks registered by call_rcu() will likely queue up until later in the boot sequence. Although rcuclassic and rcutree can also use this same optimization after boot completes, rcupreempt must restrict its use of this optimization to the portion of the boot sequence before the scheduler starts up, given that an rcupreempt RCU read-side critical section may be preeempted. In addition, this patch takes Nick Piggin's suggestion to make the system_state global variable be __read_mostly. Changes since v4: o Changes the name of the introduced function and variable to be less emotional. ;-) Changes since v3: o WARN_ON(nr_context_switches() > 0) to verify that RCU switches out of boot-time mode before the first context switch, as suggested by Nick Piggin. Changes since v2: o Created rcu_blocking_is_gp() internal-to-RCU API that determines whether a call to synchronize_rcu() is itself a grace period. o The definition of rcu_blocking_is_gp() for rcuclassic and rcutree checks to see if but a single CPU is online. o The definition of rcu_blocking_is_gp() for rcupreempt checks to see both if but a single CPU is online and if the system is still in early boot. This allows rcupreempt to again work correctly if running on a single CPU after booting is complete. o Added check to rcupreempt's synchronize_sched() for there being but one online CPU. Tested all three variants both SMP and !SMP, booted fine, passed a short rcutorture test on both x86 and Power. Located-by: Vegard Nossum Tested-by: Vegard Nossum Tested-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Signed-off-by: Ingo Molnar --- include/linux/rcuclassic.h | 6 ++++++ include/linux/rcupdate.h | 4 ++++ include/linux/rcupreempt.h | 15 +++++++++++++++ include/linux/rcutree.h | 6 ++++++ 4 files changed, 31 insertions(+) (limited to 'include') diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h index f3f697df1d71..80044a4f3ab9 100644 --- a/include/linux/rcuclassic.h +++ b/include/linux/rcuclassic.h @@ -181,4 +181,10 @@ extern long rcu_batches_completed_bh(void); #define rcu_enter_nohz() do { } while (0) #define rcu_exit_nohz() do { } while (0) +/* A context switch is a grace period for rcuclassic. */ +static inline int rcu_blocking_is_gp(void) +{ + return num_online_cpus() == 1; +} + #endif /* __LINUX_RCUCLASSIC_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 921340a7b71c..528343e6da51 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -52,6 +52,9 @@ struct rcu_head { void (*func)(struct rcu_head *head); }; +/* Internal to kernel, but needed by rcupreempt.h. */ +extern int rcu_scheduler_active; + #if defined(CONFIG_CLASSIC_RCU) #include #elif defined(CONFIG_TREE_RCU) @@ -265,6 +268,7 @@ extern void rcu_barrier_sched(void); /* Internal to kernel */ extern void rcu_init(void); +extern void rcu_scheduler_starting(void); extern int rcu_needs_cpu(int cpu); #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h index 3e05c09b54a2..74304b4538d8 100644 --- a/include/linux/rcupreempt.h +++ b/include/linux/rcupreempt.h @@ -142,4 +142,19 @@ static inline void rcu_exit_nohz(void) #define rcu_exit_nohz() do { } while (0) #endif /* CONFIG_NO_HZ */ +/* + * A context switch is a grace period for rcupreempt synchronize_rcu() + * only during early boot, before the scheduler has been initialized. + * So, how the heck do we get a context switch? Well, if the caller + * invokes synchronize_rcu(), they are willing to accept a context + * switch, so we simply pretend that one happened. + * + * After boot, there might be a blocked or preempted task in an RCU + * read-side critical section, so we cannot then take the fastpath. + */ +static inline int rcu_blocking_is_gp(void) +{ + return num_online_cpus() == 1 && !rcu_scheduler_active; +} + #endif /* __LINUX_RCUPREEMPT_H */ diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index d4368b7975c3..a722fb67bb2d 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -326,4 +326,10 @@ static inline void rcu_exit_nohz(void) } #endif /* CONFIG_NO_HZ */ +/* A context switch is a grace period for rcutree. */ +static inline int rcu_blocking_is_gp(void) +{ + return num_online_cpus() == 1; +} + #endif /* __LINUX_RCUTREE_H */ -- cgit v1.2.3 From 54e991242850edc8c53f71fa5aa3ba7a93ce38f5 Mon Sep 17 00:00:00 2001 From: Dhaval Giani Date: Fri, 27 Feb 2009 15:13:54 +0530 Subject: sched: don't allow setuid to succeed if the user does not have rt bandwidth Impact: fix hung task with certain (non-default) rt-limit settings Corey Hickey reported that on using setuid to change the uid of a rt process, the process would be unkillable and not be running. This is because there was no rt runtime for that user group. Add in a check to see if a user can attach an rt task to its task group. On failure, return EINVAL, which is also returned in CONFIG_CGROUP_SCHED. Reported-by: Corey Hickey Signed-off-by: Dhaval Giani Acked-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8981e52c714f..8c216e057c94 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2291,9 +2291,13 @@ extern long sched_group_rt_runtime(struct task_group *tg); extern int sched_group_set_rt_period(struct task_group *tg, long rt_period_us); extern long sched_group_rt_period(struct task_group *tg); +extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk); #endif #endif +extern int task_can_switch_user(struct user_struct *up, + struct task_struct *tsk); + #ifdef CONFIG_TASK_XACCT static inline void add_rchar(struct task_struct *tsk, ssize_t amt) { -- cgit v1.2.3 From 17edde520927070a6bf14a6a75027c0b843443e5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 22 Feb 2009 00:11:09 -0800 Subject: netns: Remove net_alive It turns out that net_alive is unnecessary, and the original problem that led to it being added was simply that the icmp code thought it was a network device and wound up being unable to handle packets while there were still packets in the network namespace. Now that icmp and tcp have been fixed to properly register themselves this problem is no longer present and we have a stronger guarantee that packets will not arrive in a network namespace then that provided by net_alive in netif_receive_skb. So remove net_alive allowing packet reception run a little faster. Additionally document the strong reason why network namespace cleanup is safe so that if something happens again someone else will have a chance of figuring it out. Signed-off-by: Eric W. Biederman Signed-off-by: David S. Miller --- include/net/net_namespace.h | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 6fc13d905c5f..ded434b032a4 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -109,11 +109,6 @@ extern struct list_head net_namespace_list; #ifdef CONFIG_NET_NS extern void __put_net(struct net *net); -static inline int net_alive(struct net *net) -{ - return net && atomic_read(&net->count); -} - static inline struct net *get_net(struct net *net) { atomic_inc(&net->count); @@ -145,11 +140,6 @@ int net_eq(const struct net *net1, const struct net *net2) } #else -static inline int net_alive(struct net *net) -{ - return 1; -} - static inline struct net *get_net(struct net *net) { return net; @@ -234,6 +224,23 @@ struct pernet_operations { void (*exit)(struct net *net); }; +/* + * Use these carefully. If you implement a network device and it + * needs per network namespace operations use device pernet operations, + * otherwise use pernet subsys operations. + * + * This is critically important. Most of the network code cleanup + * runs with the assumption that dev_remove_pack has been called so no + * new packets will arrive during and after the cleanup functions have + * been called. dev_remove_pack is not per namespace so instead the + * guarantee of no more packets arriving in a network namespace is + * provided by ensuring that all network devices and all sockets have + * left the network namespace before the cleanup methods are called. + * + * For the longest time the ipv4 icmp code was registered as a pernet + * device which caused kernel oops, and panics during network + * namespace cleanup. So please don't get this wrong. + */ extern int register_pernet_subsys(struct pernet_operations *); extern void unregister_pernet_subsys(struct pernet_operations *); extern int register_pernet_gen_subsys(int *id, struct pernet_operations *); -- cgit v1.2.3 From 9d40bbda599def1e1d155d7f7dca14fe8744bd2b Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 4 Mar 2009 23:46:25 -0800 Subject: vlan: Fix vlan-in-vlan crashes. As analyzed by Patrick McHardy, vlan needs to reset it's netdev_ops pointer in it's ->init() function but this leaves the compat method pointers stale. Add a netdev_resync_ops() and call it from the vlan code. Any other driver which changes ->netdev_ops after register_netdevice() will need to call this new function after doing so too. With help from Patrick McHardy. Tested-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ec54785d34f9..659366734f3f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1079,6 +1079,7 @@ extern void synchronize_net(void); extern int register_netdevice_notifier(struct notifier_block *nb); extern int unregister_netdevice_notifier(struct notifier_block *nb); extern int init_dummy_netdev(struct net_device *dev); +extern void netdev_resync_ops(struct net_device *dev); extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev); extern struct net_device *dev_get_by_index(struct net *net, int ifindex); -- cgit v1.2.3 From e7d3ef13d52a126438f687a1a32da65ff926ed57 Mon Sep 17 00:00:00 2001 From: Stuart Hayes Date: Wed, 4 Mar 2009 11:59:46 -0800 Subject: libata: change drive ready wait after hard reset to 5s This fixes problems during resume with drives that take longer than 1s to be ready. The ATA-6 spec appears to allow 5 seconds for a drive to be ready. On one affected system, this patch changes "PM: resume devices took..." message from 17 seconds to 4 seconds, and gets rid of a lot of ugly timeout/error messages. Without this patch, the libata code moves on after 1s, tries to send a soft reset (which the drive doesn't see because it isn't ready) which also times out, then an IDENTIFY command is sent to the drive which times out, and finally the error handler will try to send another hard reset which will finally get things working. Signed-off-by: Stuart Hayes Signed-off-by: Andrew Morton Signed-off-by: Jeff Garzik --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index 5d87bc09a1f5..dd818c7decd7 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -275,7 +275,7 @@ enum { * advised to wait only for the following duration before * doing SRST. */ - ATA_TMOUT_PMP_SRST_WAIT = 1000, + ATA_TMOUT_PMP_SRST_WAIT = 5000, /* ATA bus states */ BUS_UNKNOWN = 0, -- cgit v1.2.3 From 5825627c9463581fd9e70f8285685889ae5bb9bb Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Fri, 27 Feb 2009 17:35:43 +0900 Subject: libata: fix dma_unmap_sg misuse libata passes the returned value of dma_map_sg() to dma_unmap_sg(),which is the misuse of dma_unmap_sg(). DMA-mapping.txt says: To unmap a scatterlist, just call: pci_unmap_sg(pdev, sglist, nents, direction); Again, make sure DMA activity has already finished. PLEASE NOTE: The 'nents' argument to the pci_unmap_sg call must be the _same_ one you passed into the pci_map_sg call, it should _NOT_ be the 'count' value _returned_ from the pci_map_sg call. Signed-off-by: FUJITA Tomonori Acked-by: Bartlomiej Zolnierkiewicz Acked-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index dd818c7decd7..fbf064e13ad5 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -530,6 +530,7 @@ struct ata_queued_cmd { unsigned long flags; /* ATA_QCFLAG_xxx */ unsigned int tag; unsigned int n_elem; + unsigned int orig_n_elem; int dma_dir; -- cgit v1.2.3 From 84bda12af31f930e4200c5244aa111de2485d7b0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 2 Mar 2009 18:53:26 +0900 Subject: libata: align ap->sector_buf ap->sector_buf is used as DMA target and should at least be aligned on cacheline. This caused problems on some embedded machines. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index fbf064e13ad5..dc18b87ed722 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -751,7 +751,8 @@ struct ata_port { acpi_handle acpi_handle; struct ata_acpi_gtm __acpi_init_gtm; /* use ata_acpi_init_gtm() */ #endif - u8 sector_buf[ATA_SECT_SIZE]; /* owned by EH */ + /* owned by EH */ + u8 sector_buf[ATA_SECT_SIZE] ____cacheline_aligned; }; /* The following initializer overrides a method to NULL whether one of -- cgit v1.2.3 From 849d7130001ab740a5a4778a561049841fdd77c9 Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Thu, 5 Mar 2009 16:10:57 +0100 Subject: ide: allow to wrap interrupt handler Signed-off-by: Stanislaw Gruszka Cc: Andrew Victor [bart: minor checkpatch.pl / CodingStyle fixups] Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ide.h b/include/linux/ide.h index fe235b65207e..e0cedfe9fad4 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -866,6 +866,7 @@ struct ide_host { unsigned int n_ports; struct device *dev[2]; unsigned int (*init_chipset)(struct pci_dev *); + irq_handler_t irq_handler; unsigned long host_flags; void *host_priv; ide_hwif_t *cur_port; /* for hosts requiring serialization */ -- cgit v1.2.3 From ebcad5aaea26da3cb2ca90b7f31a67a027eb60db Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Thu, 5 Mar 2009 16:10:59 +0100 Subject: remove stale comment from HDIO_GET_IDENTITY returns 256 words currently. Noticed by Norman Diamond. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/hdreg.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/hdreg.h b/include/linux/hdreg.h index c37e9241fae7..ed21bd3dbd25 100644 --- a/include/linux/hdreg.h +++ b/include/linux/hdreg.h @@ -511,7 +511,6 @@ struct hd_driveid { unsigned short words69_70[2]; /* reserved words 69-70 * future command overlap and queuing */ - /* HDIO_GET_IDENTITY currently returns only words 0 through 70 */ unsigned short words71_74[4]; /* reserved words 71-74 * for IDENTIFY PACKET DEVICE command */ -- cgit v1.2.3 From d42ad15b759d05a87f22b484af63987eff38ea88 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Thu, 5 Mar 2009 17:20:55 +0100 Subject: ata: add CFA specific identify data words Declare CFA specific identify data words 162 and 163 for future use. Signed-off-by: Sergei Shtylyov Signed-off-by: Jeff Garzik [bart: update patch summary/description] Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ata.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ata.h b/include/linux/ata.h index 08a86d5cdf1b..9a061accd8b8 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -89,6 +89,8 @@ enum { ATA_ID_DLF = 128, ATA_ID_CSFO = 129, ATA_ID_CFA_POWER = 160, + ATA_ID_CFA_KEY_MGMT = 162, + ATA_ID_CFA_MODES = 163, ATA_ID_ROT_SPEED = 217, ATA_ID_PIO4 = (1 << 1), -- cgit v1.2.3 From ab96ddec7213004b632d24dc2cdcd2df5f16f50b Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sat, 7 Mar 2009 13:39:22 -0800 Subject: Input: serio - fix protocol number for TouchIT213 Protocol 0x37 has been reserved for iNexio devices and Sahara was supposed to get 0x38. Reported-by: Claudio Nieder Signed-off-by: Dmitry Torokhov --- include/linux/serio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/serio.h b/include/linux/serio.h index 1bcb357a01a1..e0417e4d3f15 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -212,7 +212,7 @@ static inline void serio_unpin_driver(struct serio *serio) #define SERIO_FUJITSU 0x35 #define SERIO_ZHENHUA 0x36 #define SERIO_INEXIO 0x37 -#define SERIO_TOUCHIT213 0x37 +#define SERIO_TOUCHIT213 0x38 #define SERIO_W8001 0x39 #endif -- cgit v1.2.3 From 129f8ae9b1b5be94517da76009ea956e89104ce8 Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Mon, 9 Mar 2009 15:07:33 -0400 Subject: Revert "[CPUFREQ] Disable sysfs ui for p4-clockmod." This reverts commit e088e4c9cdb618675874becb91b2fd581ee707e6. Removing the sysfs interface for p4-clockmod was flagged as a regression in bug 12826. Course of action: - Find out the remaining causes of overheating, and fix them if possible. ACPI should be doing the right thing automatically. If it isn't, we need to fix that. - mark p4-clockmod ui as deprecated - try again with the removal in six months. It's not really feasible to printk about the deprecation, because it needs to happen at all the sysfs entry points, which means adding a lot of strcmp("p4-clockmod".. calls to the core, which.. bleuch. Signed-off-by: Dave Jones --- include/linux/cpufreq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 384b38d3e8e2..161042746afc 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -234,7 +234,6 @@ struct cpufreq_driver { int (*suspend) (struct cpufreq_policy *policy, pm_message_t pmsg); int (*resume) (struct cpufreq_policy *policy); struct freq_attr **attr; - bool hide_interface; }; /* flags */ -- cgit v1.2.3