From e9720acd728a46cb40daa52c99a979f7c4ff195c Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Fri, 7 Mar 2008 11:08:40 -0800 Subject: [NET]: Make /proc/net a symlink on /proc/self/net (v3) Current /proc/net is done with so called "shadows", but current implementation is broken and has little chances to get fixed. The problem is that dentries subtree of /proc/net directory has fancy revalidation rules to make processes living in different net namespaces see different entries in /proc/net subtree, but currently, tasks see in the /proc/net subdir the contents of any other namespace, depending on who opened the file first. The proposed fix is to turn /proc/net into a symlink, which points to /proc/self/net, which in turn shows what previously was in /proc/net - the network-related info, from the net namespace the appropriate task lives in. # ls -l /proc/net lrwxrwxrwx 1 root root 8 Mar 5 15:17 /proc/net -> self/net In other words - this behaves like /proc/mounts, but unlike "mounts", "net" is not a file, but a directory. Changes from v2: * Fixed discrepancy of /proc/net nlink count and selinux labeling screwup pointed out by Stephen. To get the correct nlink count the ->getattr callback for /proc/net is overridden to read one from the net->proc_net entry. To make selinux still work the net->proc_net entry is initialized properly, i.e. with the "net" name and the proc_net parent. Selinux fixes are Acked-by: Stephen Smalley Changes from v1: * Fixed a task_struct leak in get_proc_task_net, pointed out by Paul. Signed-off-by: Pavel Emelyanov Acked-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/proc_fs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index d9a9e718ad19..9b6c935f69cf 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -50,8 +50,6 @@ typedef int (read_proc_t)(char *page, char **start, off_t off, typedef int (write_proc_t)(struct file *file, const char __user *buffer, unsigned long count, void *data); typedef int (get_info_t)(char *, char **, off_t, int); -typedef struct proc_dir_entry *(shadow_proc_t)(struct task_struct *task, - struct proc_dir_entry *pde); struct proc_dir_entry { unsigned int low_ino; @@ -82,7 +80,6 @@ struct proc_dir_entry { int pde_users; /* number of callers into module in progress */ spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */ struct completion *pde_unload_completion; - shadow_proc_t *shadow_proc; }; struct kcore_list { -- cgit v1.2.3 From e621e69137b24fdbbe7ad28214e8d81e614c25b7 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 7 Mar 2008 11:11:13 -0800 Subject: [NET]: include into linux/ethtool.h for __u* typedef Signed-off-by: Kirill A. Shutemov Signed-off-by: David S. Miller --- include/linux/ethtool.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index fcbe8b640ffb..c8d216357865 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -12,6 +12,7 @@ #ifndef _LINUX_ETHTOOL_H #define _LINUX_ETHTOOL_H +#include /* This should work for both 32 and 64 bit userland. */ struct ethtool_cmd { -- cgit v1.2.3 From b5e85dee2a5433246d5b7488918a1a0ad22c046a Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 10 Mar 2008 16:41:06 -0700 Subject: [NETFILTER]: nfnetlink: fix ifdef in nfnetlink_compat.h Use __KERNEL__ instead of __KERNEL to make sure the headers are not usable by the kernel. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink_compat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_compat.h b/include/linux/netfilter/nfnetlink_compat.h index 02a42d875cf7..e1451760c9cd 100644 --- a/include/linux/netfilter/nfnetlink_compat.h +++ b/include/linux/netfilter/nfnetlink_compat.h @@ -1,6 +1,6 @@ #ifndef _NFNETLINK_COMPAT_H #define _NFNETLINK_COMPAT_H -#ifndef __KERNEL +#ifndef __KERNEL__ /* Old nfnetlink macros for userspace */ /* nfnetlink groups: Up to 32 maximum */ -- cgit v1.2.3 From 0738c4bb8f2a8bf15178f852494643b0981f578b Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 12 Mar 2008 16:51:31 +0900 Subject: nommu: Provide is_vmalloc_addr() stub. Introduced in commit-id 9e2779fa281cfda13ac060753d674bbcaa23367e and ifdef'ed out for nommu in 8ca3ed87db062201e1fa15b64a9214e193fc3a8a, both approaches end up breaking the nommu build in different ways. An impressive feat for a 2-liner. Current is_vmalloc_addr() users fall in to two camps: - Determining whether to use vfree()/kfree() - Whether to do vmlist traversal (only /proc/kcore). Since we don't support /proc/kcore on nommu, that leaves the vfree()/kfree() determination use cases. nommu vfree() happens to be a wrapper to kfree() anyways, so is_vmalloc_addr() can always return 0 and end up with the right behaviour. Signed-off-by: Paul Mundt Signed-off-by: Linus Torvalds --- include/linux/mm.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3f3ccfe42de0..b695875d63e3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -235,15 +235,22 @@ static inline int get_page_unless_zero(struct page *page) struct page *vmalloc_to_page(const void *addr); unsigned long vmalloc_to_pfn(const void *addr); -#ifdef CONFIG_MMU -/* Determine if an address is within the vmalloc range */ +/* + * Determine if an address is within the vmalloc range + * + * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there + * is no special casing required. + */ static inline int is_vmalloc_addr(const void *x) { +#ifdef CONFIG_MMU unsigned long addr = (unsigned long)x; return addr >= VMALLOC_START && addr < VMALLOC_END; -} +#else + return 0; #endif +} static inline struct page *compound_head(struct page *page) { -- cgit v1.2.3 From a8ae50ba9336ff77d0df0943ac27b79ba0a5a521 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Wed, 12 Mar 2008 17:52:56 +0100 Subject: Remove from user-visible headers. It was all wrapped in '#ifdef CONFIG_BLOCK' anyway, so userspace was getting nothing useful out of it. And the special #ifndef __KERNEL__ version of 'struct partition' makes me inclined to promote an attitude of violence... Stick some comments on some of the #endifs too, while we're at it. Signed-off-by: David Woodhouse Signed-off-by: Linus Torvalds --- include/linux/Kbuild | 1 - include/linux/genhd.h | 30 +++--------------------------- 2 files changed, 3 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 994df3780007..0fac822c1157 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -205,7 +205,6 @@ unifdef-y += futex.h unifdef-y += fs.h unifdef-y += gameport.h unifdef-y += generic_serial.h -unifdef-y += genhd.h unifdef-y += gfs2_ondisk.h unifdef-y += hayesesp.h unifdef-y += hdlcdrv.h diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 32c2ac49a070..ecd2bf63fc84 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -55,24 +55,6 @@ enum { UNIXWARE_PARTITION = 0x63, /* Same as GNU_HURD and SCO Unix */ }; -#ifndef __KERNEL__ - -struct partition { - unsigned char boot_ind; /* 0x80 - active */ - unsigned char head; /* starting head */ - unsigned char sector; /* starting sector */ - unsigned char cyl; /* starting cylinder */ - unsigned char sys_ind; /* What partition type */ - unsigned char end_head; /* end head */ - unsigned char end_sector; /* end sector */ - unsigned char end_cyl; /* end cylinder */ - unsigned int start_sect; /* starting sector counting from 0 */ - unsigned int nr_sects; /* nr of sectors in partition */ -} __attribute__((packed)); - -#endif - -#ifdef __KERNEL__ #include #include #include @@ -228,7 +210,7 @@ static inline void part_stat_set_all(struct hd_struct *part, int value) { sizeof(struct disk_stats)); } -#else +#else /* !CONFIG_SMP */ #define __disk_stat_add(gendiskp, field, addnd) \ (gendiskp->dkstats.field += addnd) #define disk_stat_read(gendiskp, field) (gendiskp->dkstats.field) @@ -256,7 +238,7 @@ static inline void part_stat_set_all(struct hd_struct *part, int value) memset(&part->dkstats, value, sizeof(struct disk_stats)); } -#endif +#endif /* CONFIG_SMP */ #define disk_stat_add(gendiskp, field, addnd) \ do { \ @@ -395,8 +377,6 @@ static inline void set_capacity(struct gendisk *disk, sector_t size) disk->capacity = size; } -#endif /* __KERNEL__ */ - #ifdef CONFIG_SOLARIS_X86_PARTITION #define SOLARIS_X86_NUMSLICE 16 @@ -540,8 +520,6 @@ struct unixware_disklabel { # define MINIX_NR_SUBPARTITIONS 4 #endif /* CONFIG_MINIX_SUBPARTITION */ -#ifdef __KERNEL__ - #define ADDPART_FLAG_NONE 0 #define ADDPART_FLAG_RAID 1 #define ADDPART_FLAG_WHOLEDISK 2 @@ -570,8 +548,6 @@ static inline struct block_device *bdget_disk(struct gendisk *disk, int index) return bdget(MKDEV(disk->major, disk->first_minor) + index); } -#endif - #else /* CONFIG_BLOCK */ static inline void printk_all_partitions(void) { } @@ -584,4 +560,4 @@ static inline dev_t blk_lookup_devt(const char *name) #endif /* CONFIG_BLOCK */ -#endif +#endif /* _LINUX_GENHD_H */ -- cgit v1.2.3 From 07c941d00087581c9553661c2c4fb593da37f525 Mon Sep 17 00:00:00 2001 From: Tony Breeds Date: Wed, 12 Mar 2008 10:48:48 +1100 Subject: [POWERPC] Fix undefined pmu_sys_suspended compilation error pmu_sys_suspended is declared extern when: defined(CONFIG_PM_SLEEP) && defined(CONFIG_PPC32) but only defined when: defined(CONFIG_SUSPEND) && defined(CONFIG_PPC32) which is wrong. Let's fix that. Signed-off-by: Tony Breeds Signed-off-by: Paul Mackerras --- include/linux/pmu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pmu.h b/include/linux/pmu.h index 4c5f65392d36..b02b57c0fba0 100644 --- a/include/linux/pmu.h +++ b/include/linux/pmu.h @@ -192,7 +192,7 @@ extern unsigned int pmu_power_flags; extern void pmu_backlight_init(void); /* some code needs to know if the PMU was suspended for hibernation */ -#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_PPC32) +#if defined(CONFIG_SUSPEND) && defined(CONFIG_PPC32) extern int pmu_sys_suspended; #else /* if power management is not configured it can't be suspended */ -- cgit v1.2.3 From a99d9a6ebdf8328d5c61ca9f1038f4815e25720e Mon Sep 17 00:00:00 2001 From: Tony Breeds Date: Wed, 12 Mar 2008 10:48:48 +1100 Subject: [POWERPC] Fix drivers/macintosh/mediabay.c when !CONFIG_ADB_PMU When building drivers/macintosh/mediabay.c if CONFIG_ADB_PMU isn't defined we get: drivers/built-in.o: In function `media_bay_step': mediabay.c:(.text+0x92b84): undefined reference to `pmu_suspend' mediabay.c:(.text+0x92c08): undefined reference to `pmu_resume' Create empty place holders in that scenario. Signed-off-by: Tony Breeds Signed-off-by: Paul Mackerras --- include/linux/pmu.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pmu.h b/include/linux/pmu.h index b02b57c0fba0..cafe98d96948 100644 --- a/include/linux/pmu.h +++ b/include/linux/pmu.h @@ -147,8 +147,15 @@ extern void pmu_wait_complete(struct adb_request *req); /* For use before switching interrupts off for a long time; * warning: not stackable */ +#if defined(CONFIG_ADB_PMU) extern void pmu_suspend(void); extern void pmu_resume(void); +#else +static inline void pmu_suspend(void) +{} +static inline void pmu_resume(void) +{} +#endif extern void pmu_enable_irled(int on); -- cgit v1.2.3 From cc74d96f47b0d916840f92092595e3be9731e047 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 12 Mar 2008 21:48:03 -0700 Subject: PCI: fix issue with busses registering multiple times in sysfs PCI busses can be registered multiple times, so we need to detect if we have registered our bus structure in sysfs already. If so, don't do it again. Thanks to Guennadi Liakhovetski for reporting the problem, and to Linus for poking me to get me to believe that it was a real problem. Cc: Linus Torvalds Cc: Guennadi Liakhovetski Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 38eff1947750..9010f5458767 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -278,6 +278,7 @@ struct pci_bus { struct device dev; struct bin_attribute *legacy_io; /* legacy I/O for this bus */ struct bin_attribute *legacy_mem; /* legacy mem */ + unsigned int is_added:1; }; #define pci_bus_b(n) list_entry(n, struct pci_bus, node) -- cgit v1.2.3 From 9b89ca7a3847c0d5b1e86e83f4860a866f28a89b Mon Sep 17 00:00:00 2001 From: Marc Dionne Date: Fri, 14 Mar 2008 13:11:29 +0000 Subject: struct export_operations: adjust comments to match current members The comments in the definition of struct export_operations don't match the current members. Add a comment for the 2 new functions and remove 2 comments for unused ones. Signed-off-by: Marc Dionne Acked-by: David Howells Acked-by: Christoph Hellwig Signed-off-by: Linus Torvalds --- include/linux/exportfs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 51d214138814..adcbb05b120b 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -49,11 +49,11 @@ struct fid { /** * struct export_operations - for nfsd to communicate with file systems - * @decode_fh: decode a file handle fragment and return a &struct dentry * @encode_fh: encode a file handle fragment from a dentry + * @fh_to_dentry: find the implied object and get a dentry for it + * @fh_to_parent: find the implied object's parent and get a dentry for it * @get_name: find the name for a given inode in a given directory * @get_parent: find the parent of a given directory - * @get_dentry: find a dentry for the inode given a file handle sub-fragment * * See Documentation/filesystems/Exporting for details on how to use * this interface correctly. -- cgit v1.2.3 From 2af3e6017e53065ddf40bb19190a29199b7ffee3 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Thu, 6 Mar 2008 16:02:42 +0100 Subject: The ps2esdi driver was marked as BROKEN more than two years ago due to being no longer working for some time. A driver that had been marked as BROKEN for such a long time seems to be unlikely to be revived in the forseeable future. But if anyone wants to ever revive this driver, the code is still present in the older kernel releases. Signed-off-by: Adrian Bunk Acked-by: Alan Cox Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Jens Axboe --- include/linux/Kbuild | 1 - include/linux/ps2esdi.h | 98 ------------------------------------------------- 2 files changed, 99 deletions(-) delete mode 100644 include/linux/ps2esdi.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 0fac822c1157..4108b38ebb16 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -127,7 +127,6 @@ header-y += pkt_sched.h header-y += posix_types.h header-y += ppdev.h header-y += prctl.h -header-y += ps2esdi.h header-y += qnxtypes.h header-y += quotaio_v1.h header-y += quotaio_v2.h diff --git a/include/linux/ps2esdi.h b/include/linux/ps2esdi.h deleted file mode 100644 index c0e050b1dfe9..000000000000 --- a/include/linux/ps2esdi.h +++ /dev/null @@ -1,98 +0,0 @@ -#ifndef _PS2ESDI_H_ -#define _PS2ESDI_H_ - -#define NRML_ESDI_ID 0xddff -#define INTG_ESDI_ID 0xdf9f - -#define PRIMARY_IO_BASE 0x3510 -#define ALT_IO_BASE 0x3518 - -#define ESDI_CMD_INT (io_base+0) -#define ESDI_STT_INT (io_base+0) -#define ESDI_CONTROL (io_base+2) -#define ESDI_STATUS (io_base+2) -#define ESDI_ATTN (io_base+3) -#define ESDI_INTRPT (io_base+3) - -#define STATUS_ENABLED 0x01 -#define STATUS_ALTERNATE 0x02 -#define STATUS_BUSY 0x10 -#define STATUS_STAT_AVAIL 0x08 -#define STATUS_INTR 0x01 -#define STATUS_RESET_FAIL 0xea -#define STATUS_CMD_INF 0x04 - -#define CTRL_SOFT_RESET 0xe4 -#define CTRL_HARD_RESET 0x80 -#define CTRL_EOI 0xe2 -#define CTRL_ENABLE_DMA 0x02 -#define CTRL_ENABLE_INTR 0x01 -#define CTRL_DISABLE_INTR 0x00 - -#define ATT_EOI 0x02 - -/* bits of word 0 of configuration status block. more info see p.38 of tech ref */ -#define CONFIG_IS 0x10 /* Invalid Secondary */ -#define CONFIG_ZD 0x08 /* Zero Defect */ -#define CONFIG_SF 0x04 /* Skewed Format */ -#define CONFIG_FR 0x02 /* Removable */ -#define CONFIG_RT 0x01 /* Retries */ - -#define PORT_SYS_A 0x92 -#define PORT_DMA_FN 0x18 -#define PORT_DMA_EX 0x1a - -#define ON (unsigned char)0x40 -#define OFF (unsigned char)~ON -#define LITE_ON outb(inb(PORT_SYS_A) | ON,PORT_SYS_A) -#define LITE_OFF outb((inb(PORT_SYS_A) & OFF),PORT_SYS_A) - -#define FAIL 0 -#define SUCCES 1 - -#define INT_CMD_COMPLETE 0x01 -#define INT_CMD_ECC 0x03 -#define INT_CMD_RETRY 0x05 -#define INT_CMD_FORMAT 0x06 -#define INT_CMD_ECC_RETRY 0x07 -#define INT_CMD_WARNING 0x08 -#define INT_CMD_ABORT 0x09 -#define INT_RESET 0x0A -#define INT_TRANSFER_REQ 0x0B -#define INT_CMD_FAILED 0x0C -#define INT_DMA_ERR 0x0D -#define INT_CMD_BLK_ERR 0x0E -#define INT_ATTN_ERROR 0x0F - -#define DMA_MASK_CHAN 0x90 -#define DMA_UNMASK_CHAN 0xA0 -#define DMA_WRITE_ADDR 0x20 -#define DMA_WRITE_TC 0x40 -#define DMA_WRITE_MODE 0x70 - -#define CMD_GET_DEV_CONFIG 0x09 -#define CMD_READ 0x4601 -#define CMD_WRITE 0x4602 -#define DMA_READ_16 0x4C -#define DMA_WRITE_16 0x44 - - -#define MB 1024*1024 -#define SECT_SIZE 512 - -#define ERROR 1 -#define OK 0 - -#define HDIO_GETGEO 0x0301 - -#define FALSE 0 -#define TRUE !FALSE - -struct ps2esdi_geometry { - unsigned char heads; - unsigned char sectors; - unsigned short cylinders; - unsigned long start; -}; - -#endif /* _PS2ESDI_H_ */ -- cgit v1.2.3 From 4265f161b6bb7b31163671329b1142b9023bf4e3 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Fri, 14 Mar 2008 14:17:05 +0100 Subject: virtio: fix race in enable_cb There is a race in virtio_net, dealing with disabling/enabling the callback. I saw the following oops: kernel BUG at /space/kvm/drivers/virtio/virtio_ring.c:218! illegal operation: 0001 [#1] SMP Modules linked in: sunrpc dm_mod CPU: 2 Not tainted 2.6.25-rc1zlive-host-10623-gd358142-dirty #99 Process swapper (pid: 0, task: 000000000f85a610, ksp: 000000000f873c60) Krnl PSW : 0404300180000000 00000000002b81a6 (vring_disable_cb+0x16/0x20) R:0 T:1 IO:0 EX:0 Key:0 M:1 W:0 P:0 AS:0 CC:3 PM:0 EA:3 Krnl GPRS: 0000000000000001 0000000000000001 0000000010005800 0000000000000001 000000000f3a0900 000000000f85a610 0000000000000000 0000000000000000 0000000000000000 000000000f870000 0000000000000000 0000000000001237 000000000f3a0920 000000000010ff74 00000000002846f6 000000000fa0bcd8 Krnl Code: 00000000002b819a: a7110001 tmll %r1,1 00000000002b819e: a7840004 brc 8,2b81a6 00000000002b81a2: a7f40001 brc 15,2b81a4 >00000000002b81a6: a51b0001 oill %r1,1 00000000002b81aa: 40102000 sth %r1,0(%r2) 00000000002b81ae: 07fe bcr 15,%r14 00000000002b81b0: eb7ff0380024 stmg %r7,%r15,56(%r15) 00000000002b81b6: a7f13e00 tmll %r15,15872 Call Trace: ([<000000000fa0bcd0>] 0xfa0bcd0) [<00000000002b8350>] vring_interrupt+0x5c/0x6c [<000000000010ab08>] do_extint+0xb8/0xf0 [<0000000000110716>] ext_no_vtime+0x16/0x1a [<0000000000107e72>] cpu_idle+0x1c2/0x1e0 The problem can be triggered with a high amount of host->guest traffic. I think its the following race: poll says netif_rx_complete poll calls enable_cb enable_cb opens the interrupt mask a new packet comes, an interrupt is triggered----\ enable_cb sees that there is more work | enable_cb disables the interrupt | . V . interrupt is delivered . skb_recv_done does atomic napi test, ok some waiting disable_cb is called->check fails->bang! . poll would do napi check poll would do disable_cb The fix is to let enable_cb not disable the interrupt again, but expect the caller to do the cleanup if it returns false. In that case, the interrupt is only disabled, if the napi test_set_bit was successful. Signed-off-by: Christian Borntraeger Signed-off-by: Rusty Russell (cleaned up doco) --- include/linux/virtio.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 260d1fcf29a4..12c18ac1b973 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -43,8 +43,9 @@ struct virtqueue * vq: the struct virtqueue we're talking about. * @enable_cb: restart callbacks after disable_cb. * vq: the struct virtqueue we're talking about. - * This returns "false" (and doesn't re-enable) if there are pending - * buffers in the queue, to avoid a race. + * This re-enables callbacks; it returns "false" if there are pending + * buffers in the queue, to detect a possible race between the driver + * checking for more work, and enabling callbacks. * * Locking rules are straightforward: the driver is responsible for * locking. No two operations may be invoked simultaneously. -- cgit v1.2.3 From 916fbfb7ae5f8c8f86399794d89e6d273df8826b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 12 Mar 2008 15:26:34 +0900 Subject: devres: implement pcim_iomap_regions_request_all() Some drivers need to reserve all PCI BARs to prevent other drivers misusing unoccupied BARs. pcim_iomap_regions_request_all() requests all BARs and iomap specified BARs. Signed-off-by: Tejun Heo Cc: Greg Kroah-Hartman Cc: Alan Cox Cc: Jeff Garzik Signed-off-by: Jeff Garzik --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 9010f5458767..b7e4b633c69b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1045,6 +1045,8 @@ void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen); void pcim_iounmap(struct pci_dev *pdev, void __iomem *addr); void __iomem * const *pcim_iomap_table(struct pci_dev *pdev); int pcim_iomap_regions(struct pci_dev *pdev, u16 mask, const char *name); +int pcim_iomap_regions_request_all(struct pci_dev *pdev, u16 mask, + const char *name); void pcim_iounmap_regions(struct pci_dev *pdev, u16 mask); extern int pci_pci_problems; -- cgit v1.2.3 From 0382b9c35469be273ed10fa374496a924055a3c8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 17 Mar 2008 22:46:46 -0700 Subject: [PKT_SCHED]: annotate cls_u32 Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/pkt_cls.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pkt_cls.h b/include/linux/pkt_cls.h index 28dfc61cf79e..99efbed81fa2 100644 --- a/include/linux/pkt_cls.h +++ b/include/linux/pkt_cls.h @@ -201,8 +201,8 @@ enum struct tc_u32_key { - __u32 mask; - __u32 val; + __be32 mask; + __be32 val; int off; int offmask; }; @@ -213,12 +213,12 @@ struct tc_u32_sel unsigned char offshift; unsigned char nkeys; - __u16 offmask; + __be16 offmask; __u16 off; short offoff; short hoff; - __u32 hmask; + __be32 hmask; struct tc_u32_key keys[0]; }; -- cgit v1.2.3 From 0ff9663c88ac5efdb5c8ac21c0bd7f993a4e3849 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 17 Mar 2008 22:48:46 -0700 Subject: [IPV4]: ipv4_is_lbcast() misannotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/in.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/in.h b/include/linux/in.h index 70c6df882694..4065313cd7ee 100644 --- a/include/linux/in.h +++ b/include/linux/in.h @@ -265,7 +265,7 @@ static inline bool ipv4_is_local_multicast(__be32 addr) static inline bool ipv4_is_lbcast(__be32 addr) { /* limited broadcast */ - return addr == INADDR_BROADCAST; + return addr == htonl(INADDR_BROADCAST); } static inline bool ipv4_is_zeronet(__be32 addr) -- cgit v1.2.3 From 4ae7d5cefd4aa3560e359a3b0f03e12adc8b5c86 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 19 Mar 2008 01:42:00 +0100 Subject: sched: improve affine wakeups improve affine wakeups. Maintain the 'overlap' metric based on CFS's sum_exec_runtime - which means the amount of time a task executes after it wakes up some other task. Use the 'overlap' for the wakeup decisions: if the 'overlap' is short, it means there's strong workload coupling between this task and the woken up task. If the 'overlap' is large then the workload is decoupled and the scheduler will move them to separate CPUs more easily. ( Also slightly move the preempt_check within try_to_wake_up() - this has no effect on functionality but allows 'early wakeups' (for still-on-rq tasks) to be correctly accounted as well.) Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 11d8e9a74eff..3625fcaf5d0f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -929,6 +929,9 @@ struct sched_entity { u64 vruntime; u64 prev_sum_exec_runtime; + u64 last_wakeup; + u64 avg_overlap; + #ifdef CONFIG_SCHEDSTATS u64 wait_start; u64 wait_max; -- cgit v1.2.3 From 33b0c4217dcd67b788318c3192a2912b530e4eef Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 16 Mar 2008 11:14:30 +0100 Subject: sched: tune multi-core idle balancing WAKE_IDLE is too agressive on multi-core CPUs with the new wake-affine code, keep it on for SMT/HT balancing alone (where there's no cache affinity at all between logical CPUs). Signed-off-by: Ingo Molnar --- include/linux/topology.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index 2352f46160d3..2d8dac8799cf 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -138,7 +138,6 @@ | SD_BALANCE_FORK \ | SD_BALANCE_EXEC \ | SD_WAKE_AFFINE \ - | SD_WAKE_IDLE \ | SD_SHARE_PKG_RESOURCES\ | BALANCE_FOR_MC_POWER, \ .last_balance = jiffies, \ -- cgit v1.2.3 From ae66be9b71b12f16b84129860d06bbfe37fbec51 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 19 Mar 2008 17:00:57 -0700 Subject: rcu: fix misplaced mb() in rcu_enter/exit_nohz() In the process of writing up the mechanical proof of correctness for the dynticks/preemptable-RCU interface, I noticed misplaced memory barriers in rcu_enter_nohz() and rcu_exit_nohz(). This patch puts them in the right place and adds a comment. The key thing to keep in mind is that rcu_enter_nohz() is -exiting- the mode that can legally execute RCU read-side critical sections. The memory barrier must be between any potential RCU read-side critical sections and the increment of the per-CPU dynticks_progress_counter, and thus must come -before- this increment. And vice versa for rcu_exit_nohz(). The locking in the scheduler is probably saving us for the moment. Also, switch to smp_mb() - we don't need a barrier for uniprocessor kernels. Signed-off-by: Paul E. McKenney Acked-by: Steven Rostedt Cc: Nick Piggin Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rcupreempt.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h index 01152ed532c8..d038aa6e5ee1 100644 --- a/include/linux/rcupreempt.h +++ b/include/linux/rcupreempt.h @@ -87,15 +87,15 @@ DECLARE_PER_CPU(long, dynticks_progress_counter); static inline void rcu_enter_nohz(void) { + smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */ __get_cpu_var(dynticks_progress_counter)++; WARN_ON(__get_cpu_var(dynticks_progress_counter) & 0x1); - mb(); } static inline void rcu_exit_nohz(void) { - mb(); __get_cpu_var(dynticks_progress_counter)++; + smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */ WARN_ON(!(__get_cpu_var(dynticks_progress_counter) & 0x1)); } -- cgit v1.2.3 From a6b91919e0881a0d0a4ae5211d5c879a8c7ca92b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 19 Mar 2008 17:01:00 -0700 Subject: fs: fix kernel-doc notation warnings Fix kernel-doc notation warnings in fs/. Warning(mmotm-2008-0314-1449//fs/super.c:560): missing initial short description on line: * mark_files_ro Warning(mmotm-2008-0314-1449//fs/locks.c:1277): missing initial short description on line: * lease_get_mtime Warning(mmotm-2008-0314-1449//fs/locks.c:1277): missing initial short description on line: * lease_get_mtime Warning(mmotm-2008-0314-1449//fs/namei.c:1368): missing initial short description on line: * lookup_one_len: filesystem helper to lookup single pathname component Warning(mmotm-2008-0314-1449//fs/buffer.c:3221): missing initial short description on line: * bh_uptodate_or_lock: Test whether the buffer is uptodate Warning(mmotm-2008-0314-1449//fs/buffer.c:3240): missing initial short description on line: * bh_submit_read: Submit a locked buffer for reading Warning(mmotm-2008-0314-1449//fs/fs-writeback.c:30): missing initial short description on line: * writeback_acquire: attempt to get exclusive writeback access to a device Warning(mmotm-2008-0314-1449//fs/fs-writeback.c:47): missing initial short description on line: * writeback_in_progress: determine whether there is writeback in progress Warning(mmotm-2008-0314-1449//fs/fs-writeback.c:58): missing initial short description on line: * writeback_release: relinquish exclusive writeback access against a device. Warning(mmotm-2008-0314-1449//include/linux/jbd.h:351): contents before sections Warning(mmotm-2008-0314-1449//include/linux/jbd.h:561): contents before sections Warning(mmotm-2008-0314-1449//fs/jbd/transaction.c:1935): missing initial short description on line: * void journal_invalidatepage() Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/jbd.h | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd.h b/include/linux/jbd.h index b18fd3b9b835..423f58272188 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -348,8 +348,7 @@ static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) struct jbd_revoke_table_s; /** - * struct handle_s - The handle_s type is the concrete type associated with - * handle_t. + * struct handle_s - this is the concrete type associated with handle_t. * @h_transaction: Which compound transaction is this update a part of? * @h_buffer_credits: Number of remaining buffers we are allowed to dirty. * @h_ref: Reference count on this handle @@ -358,12 +357,7 @@ struct jbd_revoke_table_s; * @h_jdata: flag to force data journaling * @h_aborted: flag indicating fatal error on handle * @h_lockdep_map: lockdep info for debugging lock problems - **/ - -/* Docbook can't yet cope with the bit fields, but will leave the documentation - * in so it can be fixed later. */ - struct handle_s { /* Which compound transaction is this update a part of? */ @@ -558,8 +552,7 @@ struct transaction_s }; /** - * struct journal_s - The journal_s type is the concrete type associated with - * journal_t. + * struct journal_s - this is the concrete type associated with journal_t. * @j_flags: General journaling state flags * @j_errno: Is there an outstanding uncleared error on the journal (from a * prior abort)? -- cgit v1.2.3 From ead70773608a5d97f81cb492f117d20b5e9f323e Mon Sep 17 00:00:00 2001 From: Alex Dubov Date: Wed, 19 Mar 2008 17:01:06 -0700 Subject: memstick: automatically retrieve "INT" value from command response MemoryStick storage cards, when in parallel mode, send several meaningful bits of their "INT" register as part of command response. This data is stored by host and can be used to spare invocation of "GET_INT" TPC on each data page transferred between host and card. Signed-off-by: Alex Dubov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memstick.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memstick.h b/include/linux/memstick.h index b7ee25888836..3e686ec6a967 100644 --- a/include/linux/memstick.h +++ b/include/linux/memstick.h @@ -239,7 +239,6 @@ struct memstick_request { unsigned char tpc; unsigned char data_dir:1, need_card_int:1, - get_int_reg:1, long_data:1; unsigned char int_reg; int error; -- cgit v1.2.3 From aedb60a67c10a0861af179725d060765262ba0fb Mon Sep 17 00:00:00 2001 From: Serge Hallyn Date: Fri, 29 Feb 2008 15:14:57 +0000 Subject: file capabilities: remove cap_task_kill() The original justification for cap_task_kill() was as follows: check_kill_permission() does appropriate uid equivalence checks. However with file capabilities it becomes possible for an unprivileged user to execute a file with file capabilities resulting in a more privileged task with the same uid. However now that cap_task_kill() always returns 0 (permission granted) when p->uid==current->uid, the whole hook is worthless, and only likely to create more subtle problems in the corner cases where it might still be called but return -EPERM. Those cases are basically when uids are different but euid/suid is equivalent as per the check in check_kill_permission(). One example of a still-broken application is 'at' for non-root users. This patch removes cap_task_kill(). Signed-off-by: Serge Hallyn Acked-by: Andrew G. Morgan Earlier-version-tested-by: Luiz Fernando N. Capitulino Acked-by: Casey Schaufler Signed-off-by: Linus Torvalds --- include/linux/security.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index b07357ca2137..c673dfd4dffc 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -57,7 +57,6 @@ extern int cap_inode_need_killpriv(struct dentry *dentry); extern int cap_inode_killpriv(struct dentry *dentry); extern int cap_task_post_setuid (uid_t old_ruid, uid_t old_euid, uid_t old_suid, int flags); extern void cap_task_reparent_to_init (struct task_struct *p); -extern int cap_task_kill(struct task_struct *p, struct siginfo *info, int sig, u32 secid); extern int cap_task_setscheduler (struct task_struct *p, int policy, struct sched_param *lp); extern int cap_task_setioprio (struct task_struct *p, int ioprio); extern int cap_task_setnice (struct task_struct *p, int nice); @@ -2187,7 +2186,7 @@ static inline int security_task_kill (struct task_struct *p, struct siginfo *info, int sig, u32 secid) { - return cap_task_kill(p, info, sig, secid); + return 0; } static inline int security_task_wait (struct task_struct *p) -- cgit v1.2.3 From 9aefd0abd8610e8f3bb097debf3afb73f8b7b210 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 12 Mar 2008 18:31:58 +0100 Subject: sched: add exported arch_reinit_sched_domains() to header file. Needed so it can be called from outside of sched.c. Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 3625fcaf5d0f..fed07d03364e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -790,6 +790,7 @@ struct sched_domain { }; extern void partition_sched_domains(int ndoms_new, cpumask_t *doms_new); +extern int arch_reinit_sched_domains(void); #endif /* CONFIG_SMP */ -- cgit v1.2.3 From 22e52b072dd87faa9b2559fe89d4e8f2370f81ca Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 12 Mar 2008 18:31:59 +0100 Subject: sched: add arch_update_cpu_topology hook. Will be called each time the scheduling domains are rebuild. Needed for architectures that don't have a static cpu topology. Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky Signed-off-by: Ingo Molnar --- include/linux/topology.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index 2d8dac8799cf..bd14f8b30f09 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -50,6 +50,8 @@ for_each_online_node(node) \ if (nr_cpus_node(node)) +void arch_update_cpu_topology(void); + /* Conform to ACPI 2.0 SLIT distance definitions */ #define LOCAL_DISTANCE 10 #define REMOTE_DISTANCE 20 -- cgit v1.2.3 From 03c086a747d0b242878eb881971ec61c1555869d Mon Sep 17 00:00:00 2001 From: Darren Salt Date: Thu, 13 Mar 2008 15:35:49 +0000 Subject: PNP: increase the number of PnP memory resources from 12 to 24 Increase the number of PnP memory resources from 12 to 24. This removes an "exceeded the max num of mem resources" warning on boot. I also noticed the reservation of two more iomem ranges on the computer on which this was tested. Signed-off-by: Darren Salt Signed-off-by: Ingo Molnar Acked-by: Bjorn Helgaas Signed-off-by: Linus Torvalds --- include/linux/pnp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pnp.h b/include/linux/pnp.h index cd6332b88829..29dd55838e84 100644 --- a/include/linux/pnp.h +++ b/include/linux/pnp.h @@ -14,7 +14,7 @@ #include #define PNP_MAX_PORT 40 -#define PNP_MAX_MEM 12 +#define PNP_MAX_MEM 24 #define PNP_MAX_IRQ 2 #define PNP_MAX_DMA 2 #define PNP_NAME_LEN 50 -- cgit v1.2.3 From aacda37538e7f9cf2148eedf3766239829e51ba4 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Mar 2008 17:47:43 +0900 Subject: libata: implement ata_qc_raw_nbytes() Implement ata_qc_raw_nbytes() which determines the raw user-requested size of a PC command. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index a05f60013642..269cdba09578 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -463,6 +463,7 @@ struct ata_queued_cmd { unsigned int sect_size; unsigned int nbytes; + unsigned int extrabytes; unsigned int curbytes; struct scatterlist *cursg; @@ -1336,6 +1337,11 @@ static inline struct ata_queued_cmd *ata_qc_from_tag(struct ata_port *ap, return NULL; } +static inline unsigned int ata_qc_raw_nbytes(struct ata_queued_cmd *qc) +{ + return qc->nbytes - min(qc->extrabytes, qc->nbytes); +} + static inline void ata_tf_init(struct ata_device *dev, struct ata_taskfile *tf) { memset(tf, 0, sizeof(*tf)); @@ -1354,7 +1360,7 @@ static inline void ata_qc_reinit(struct ata_queued_cmd *qc) qc->flags = 0; qc->cursg = NULL; qc->cursg_ofs = 0; - qc->nbytes = qc->curbytes = 0; + qc->nbytes = qc->extrabytes = qc->curbytes = 0; qc->n_elem = 0; qc->err_mask = 0; qc->sect_size = ATA_SECT_SIZE; -- cgit v1.2.3 From 392e1d9817d0024c96aae237c3c4349e47c976fd Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 11 Mar 2008 10:20:12 -0400 Subject: USB: new quirk flag to avoid Set-Interface This patch (as1057) fixes a problem with the X-Rite/Gretag-Macbeth Eye-One Pro display colorimeter; the device crashes when it receives a Set-Interface request. A new quirk (USB_QUIRK_NO_SET_INTF) is introduced and a quirks entry is created for this device. Signed-off-by: Alan Stern Cc: stable Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/quirks.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 2692ec9389ca..1f999ec8d08c 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -9,3 +9,6 @@ /* device can't resume correctly so reset it instead */ #define USB_QUIRK_RESET_RESUME 0x00000002 + +/* device can't handle Set-Interface requests */ +#define USB_QUIRK_NO_SET_INTF 0x00000004 -- cgit v1.2.3 From cc36bdd47ae51b66780b317c1fa519221f894405 Mon Sep 17 00:00:00 2001 From: Constantin Baranov Date: Sun, 16 Mar 2008 20:04:23 +0000 Subject: USB: add support for Motorola ROKR Z6 cellphone in mass storage mode Motorola ROKR Z6 cellphone has bugs in its USB, so it is impossible to use it as mass storage. Patch describes new "unusual" USB device for it with FIX_INQUIRY and FIX_CAPACITY flags and new BULK_IGNORE_TAG flag. Last flag relaxes check for equality of bcs->Tag and us->tag in usb_stor_Bulk_transport routine. Signed-off-by: Constantin Baranov Signed-off-by: Matthew Dharm Signed-off-by: Daniel Drake Cc: stable Signed-off-by: Greg Kroah-Hartman --- include/linux/usb_usual.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h index cee0623b3c7b..0a40dfa44c9f 100644 --- a/include/linux/usb_usual.h +++ b/include/linux/usb_usual.h @@ -50,7 +50,9 @@ US_FLAG(CAPACITY_HEURISTICS, 0x00001000) \ /* sometimes sizes is too big */ \ US_FLAG(MAX_SECTORS_MIN,0x00002000) \ - /* Sets max_sectors to arch min */ + /* Sets max_sectors to arch min */ \ + US_FLAG(BULK_IGNORE_TAG,0x00004000) \ + /* Ignore tag mismatch in bulk operations */ #define US_FLAG(name, value) US_FL_##name = value , -- cgit v1.2.3 From 49741c4d01554c2630cea02cfdf236b17062a912 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Mon, 17 Mar 2008 14:21:18 -0700 Subject: PCI: revert "pcie: utilize pcie transaction pending bit" Revert as it is reported to cause problems for people. commit 4348a2dc49f9baecd34a9b0904245488c6189398 Author: Shaohua Li Date: Wed Oct 24 10:45:08 2007 +0800 pcie: utilize pcie transaction pending bit PCIE has a mechanism to wait for Non-Posted request to complete. I think pci_disable_device is a good place to do this. Signed-off-by: Shaohua Li Signed-off-by: Greg Kroah-Hartman Due to the regression reported at http://bugzilla.kernel.org/show_bug.cgi?id=10065 Cc: Shaohua Li Cc: Soeren Sonnenburg Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index b7e4b633c69b..ea760e519c46 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -513,7 +513,6 @@ int pci_find_next_capability(struct pci_dev *dev, u8 pos, int cap); int pci_find_ext_capability(struct pci_dev *dev, int cap); int pci_find_ht_capability(struct pci_dev *dev, int ht_cap); int pci_find_next_ht_capability(struct pci_dev *dev, int pos, int ht_cap); -void pcie_wait_pending_transaction(struct pci_dev *dev); struct pci_bus *pci_find_next_bus(const struct pci_bus *from); struct pci_dev *pci_get_device(unsigned int vendor, unsigned int device, @@ -884,9 +883,6 @@ static inline int pci_find_ext_capability(struct pci_dev *dev, int cap) return 0; } -static inline void pcie_wait_pending_transaction(struct pci_dev *dev) -{ } - /* Power management related routines */ static inline int pci_save_state(struct pci_dev *dev) { -- cgit v1.2.3 From 8b78cf602fd3bd97c0080edd22fe8fd5d0fa7832 Mon Sep 17 00:00:00 2001 From: Yi Yang Date: Mon, 25 Feb 2008 08:46:12 +0800 Subject: cpuidle: fix cpuidle time and usage overflow cpuidle C-state sysfs node time and usage are very easy to overflow because they are all of unsigned int type, time will overflow within about two hours, usage will take longer time to overflow, but they are increasing for ever. This patch will convert them to unsigned long long. Signed-off-by: Yi Yang Acked-by: Venkatesh Pallipadi Signed-off-by: Len Brown --- include/linux/cpuidle.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 6b72a4584086..51e6b1e520e6 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -38,8 +38,8 @@ struct cpuidle_state { unsigned int power_usage; /* in mW */ unsigned int target_residency; /* in US */ - unsigned int usage; - unsigned int time; /* in US */ + unsigned long long usage; + unsigned long long time; /* in US */ int (*enter) (struct cpuidle_device *dev, struct cpuidle_state *state); -- cgit v1.2.3 From 06d8308c61e54346585b2691c13ee3f90cb6fb2f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 22 Mar 2008 09:20:24 +0100 Subject: NOHZ: reevaluate idle sleep length after add_timer_on() add_timer_on() can add a timer on a CPU which is currently in a long idle sleep, but the timer wheel is not reevaluated by the nohz code on that CPU. So a timer can be delayed for quite a long time. This triggered a false positive in the clocksource watchdog code. To avoid this we need to wake up the idle CPU and enforce the reevaluation of the timer wheel for the next timer event. Add a function, which checks a given CPU for idle state, marks the idle task with NEED_RESCHED and sends a reschedule IPI to notify the other CPU of the change in the timer wheel. Call this function from add_timer_on(). Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra Acked-by: Ingo Molnar Cc: stable@kernel.org -- include/linux/sched.h | 6 ++++++ kernel/sched.c | 43 +++++++++++++++++++++++++++++++++++++++++++ kernel/timer.c | 10 +++++++++- 3 files changed, 58 insertions(+), 1 deletion(-) --- include/linux/sched.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index fed07d03364e..6a1e7afb099b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1541,6 +1541,12 @@ static inline void idle_task_exit(void) {} extern void sched_idle_next(void); +#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP) +extern void wake_up_idle_cpu(int cpu); +#else +static inline void wake_up_idle_cpu(int cpu) { } +#endif + #ifdef CONFIG_SCHED_DEBUG extern unsigned int sysctl_sched_latency; extern unsigned int sysctl_sched_min_granularity; -- cgit v1.2.3 From a6bd8e13034dd7d60b6f14217096efa192d0adc1 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 28 Mar 2008 11:05:53 -0500 Subject: lguest: comment documentation update. Took some cycles to re-read the Lguest Journey end-to-end, fix some rot and tighten some phrases. Only comments change. No new jokes, but a couple of recycled old jokes. Signed-off-by: Rusty Russell --- include/linux/lguest_launcher.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lguest_launcher.h b/include/linux/lguest_launcher.h index 589be3e1f3ac..e7217dc58f39 100644 --- a/include/linux/lguest_launcher.h +++ b/include/linux/lguest_launcher.h @@ -16,6 +16,10 @@ * a new device, we simply need to write a new virtio driver and create support * for it in the Launcher: this code won't need to change. * + * Virtio devices are also used by kvm, so we can simply reuse their optimized + * device drivers. And one day when everyone uses virtio, my plan will be + * complete. Bwahahahah! + * * Devices are described by a simplified ID, a status byte, and some "config" * bytes which describe this device's configuration. This is placed by the * Launcher just above the top of physical memory: @@ -26,7 +30,7 @@ struct lguest_device_desc { /* The number of virtqueues (first in config array) */ __u8 num_vq; /* The number of bytes of feature bits. Multiply by 2: one for host - * features and one for guest acknowledgements. */ + * features and one for Guest acknowledgements. */ __u8 feature_len; /* The number of bytes of the config array after virtqueues. */ __u8 config_len; -- cgit v1.2.3 From 7c4b93d8269b9d35971a8239426b1f6ddc3d5ef7 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 21 Mar 2008 23:59:49 -0400 Subject: [PATCH] count ghost references to vfsmounts make propagate_mount_busy() exclude references from the vfsmounts that had been isolated by umount_tree() and are just waiting for release_mounts() to dispose of their ->mnt_parent/->mnt_mountpoint. Signed-off-by: Al Viro --- include/linux/mount.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mount.h b/include/linux/mount.h index 6d3047d8c91c..dac5e67ff3ee 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -61,6 +61,7 @@ struct vfsmount { atomic_t mnt_count; int mnt_expiry_mark; /* true if marked for expiry */ int mnt_pinned; + int mnt_ghosts; }; static inline struct vfsmount *mntget(struct vfsmount *mnt) -- cgit v1.2.3 From c35038becad0adb0e25261fff66d85b1a6ddd0c2 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 22 Mar 2008 00:46:23 -0400 Subject: [PATCH] do shrink_submounts() for all fs types ... and take it out of ->umount_begin() instances. Call with all locks already taken (by do_umount()) and leave calling release_mounts() to caller (it will do release_mounts() anyway, so we can just put into the same list). Signed-off-by: Al Viro --- include/linux/mount.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mount.h b/include/linux/mount.h index dac5e67ff3ee..5ee2df217cdf 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -99,7 +99,6 @@ extern int do_add_mount(struct vfsmount *newmnt, struct nameidata *nd, int mnt_flags, struct list_head *fslist); extern void mark_mounts_for_expiry(struct list_head *mounts); -extern void shrink_submounts(struct vfsmount *mountpoint, struct list_head *mounts); extern spinlock_t vfsmount_lock; extern dev_t name_to_dev_t(char *name); -- cgit v1.2.3 From 8c703d35fa91911dd92a18c31a718853f483ad80 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Fri, 28 Mar 2008 14:15:49 -0700 Subject: in_atomic(): document why it is unsuitable for general use Discourage people from inappropriately using in_atomic() Signed-off-by: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hardirq.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 49829988bfa0..897f723bd222 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -72,6 +72,13 @@ #define in_softirq() (softirq_count()) #define in_interrupt() (irq_count()) +/* + * Are we running in atomic context? WARNING: this macro cannot + * always detect atomic context; in particular, it cannot know about + * held spinlocks in non-preemptible kernels. Thus it should not be + * used in the general case to determine whether sleeping is possible. + * Do not use in_atomic() in driver code. + */ #define in_atomic() ((preempt_count() & ~PREEMPT_ACTIVE) != 0) #ifdef CONFIG_PREEMPT -- cgit v1.2.3 From 3afe3925987adc3fc052abe404e44520c2072fc8 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Fri, 28 Mar 2008 14:16:01 -0700 Subject: kernel: add bit rotation helpers for 16 and 8 bit Will replace open-coded variants elsewhere. Done in the same style as the 32-bit versions. Signed-off-by: Harvey Harrison Acked-by: Randy Dunlap Cc: Johannes Berg Cc: John W. Linville Cc: Joe Perches Cc: Jiri Benc Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitops.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 69c1edb9fe54..40d54731de7e 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -65,6 +65,46 @@ static inline __u32 ror32(__u32 word, unsigned int shift) return (word >> shift) | (word << (32 - shift)); } +/** + * rol16 - rotate a 16-bit value left + * @word: value to rotate + * @shift: bits to roll + */ +static inline __u16 rol16(__u16 word, unsigned int shift) +{ + return (word << shift) | (word >> (16 - shift)); +} + +/** + * ror16 - rotate a 16-bit value right + * @word: value to rotate + * @shift: bits to roll + */ +static inline __u16 ror16(__u16 word, unsigned int shift) +{ + return (word >> shift) | (word << (16 - shift)); +} + +/** + * rol8 - rotate an 8-bit value left + * @word: value to rotate + * @shift: bits to roll + */ +static inline __u8 rol8(__u8 word, unsigned int shift) +{ + return (word << shift) | (word >> (8 - shift)); +} + +/** + * ror8 - rotate an 8-bit value right + * @word: value to rotate + * @shift: bits to roll + */ +static inline __u8 ror8(__u8 word, unsigned int shift) +{ + return (word >> shift) | (word << (8 - shift)); +} + static inline unsigned fls_long(unsigned long l) { if (sizeof(l) == 4) -- cgit v1.2.3 From 5ac7ec85bcc70ef605657fb2d1106d27ab3bd131 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 28 Mar 2008 14:16:03 -0700 Subject: ext3: don't export ext3_fs.h and jbd.h Neither of the headers actually compiles when included from userpsace nor should it be made available as userspace tools should be using the libraries or at least headers from e2fsprogs. Signed-off-by: Christoph Hellwig Acked-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/Kbuild | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 4108b38ebb16..4a446a19295e 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -195,7 +195,6 @@ unifdef-y += ethtool.h unifdef-y += eventpoll.h unifdef-y += signalfd.h unifdef-y += ext2_fs.h -unifdef-y += ext3_fs.h unifdef-y += fb.h unifdef-y += fcntl.h unifdef-y += filter.h @@ -248,7 +247,6 @@ unifdef-y += isdn.h unifdef-y += isdnif.h unifdef-y += isdn_divertif.h unifdef-y += isdn_ppp.h -unifdef-y += jbd.h unifdef-y += joystick.h unifdef-y += kdev_t.h unifdef-y += kd.h -- cgit v1.2.3 From 3ec25ebd69dc120d0590e64caaf1477aa88c8a93 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 27 Mar 2008 18:37:14 +0900 Subject: libata: ATA_EHI_LPM should be ATA_EH_LPM EH actions are ATA_EH_* not ATA_EHI_*. Rename ATA_EHI_LPM to ATA_EH_LPM. Signed-off-by: Tejun Heo Cc: Kristen Carlson Accardi Signed-off-by: Jeff Garzik --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 269cdba09578..b064bfeb69ee 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -295,6 +295,7 @@ enum { ATA_EH_SOFTRESET = (1 << 1), ATA_EH_HARDRESET = (1 << 2), ATA_EH_ENABLE_LINK = (1 << 3), + ATA_EH_LPM = (1 << 4), /* link power management action */ ATA_EH_RESET_MASK = ATA_EH_SOFTRESET | ATA_EH_HARDRESET, ATA_EH_PERDEV_MASK = ATA_EH_REVALIDATE, @@ -304,7 +305,6 @@ enum { ATA_EHI_RESUME_LINK = (1 << 1), /* resume link (reset modifier) */ ATA_EHI_NO_AUTOPSY = (1 << 2), /* no autopsy */ ATA_EHI_QUIET = (1 << 3), /* be quiet */ - ATA_EHI_LPM = (1 << 4), /* link power management action */ ATA_EHI_DID_SOFTRESET = (1 << 16), /* already soft-reset this port */ ATA_EHI_DID_HARDRESET = (1 << 17), /* already soft-reset this port */ -- cgit v1.2.3 From 729d4de96a5c090e40a918a41f63b7fb1b27c240 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Sat, 29 Mar 2008 19:55:17 +0100 Subject: ide: fix defining SUPPORT_VLB_SYNC We need to check for CONFIG_{CRIS,FRV} not {CRIS,FRV}. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index a3b69c10d667..bc26b2f27359 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -26,7 +26,7 @@ #include #include -#if defined(CRIS) || defined(FRV) +#if defined(CONFIG_CRIS) || defined(CONFIG_FRV) # define SUPPORT_VLB_SYNC 0 #else # define SUPPORT_VLB_SYNC 1 -- cgit v1.2.3 From 7d61c4596d11d624efb4bbcbad01f9cf2b321162 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 29 Mar 2008 03:09:28 +0000 Subject: compat_sys_wait4() prototype misannotation Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/compat.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index a671dbff7a1f..8fa7857e153b 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -192,8 +192,8 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, struct compat_timeval __user *tvp); asmlinkage long compat_sys_wait4(compat_pid_t pid, - compat_uint_t *stat_addr, int options, - struct compat_rusage *ru); + compat_uint_t __user *stat_addr, int options, + struct compat_rusage __user *ru); #define BITS_PER_COMPAT_LONG (8*sizeof(compat_long_t)) -- cgit v1.2.3 From b2ddb9019ea13fb7b62d8e45adcc468376af0de7 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 29 Mar 2008 03:09:38 +0000 Subject: dma_page_list ->base_address is a userland pointer Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/dmaengine.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 261e43a4c873..34d440698293 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -423,7 +423,7 @@ void dma_async_device_unregister(struct dma_device *device); /* --- Helper iov-locking functions --- */ struct dma_page_list { - char *base_address; + char __user *base_address; int nr_pages; struct page **pages; }; -- cgit v1.2.3