From e92251762d02a46177d4105d1744041e3f8bc465 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 2 Feb 2006 12:23:12 +0000 Subject: [MMC] Add MMC command type flags Some hosts need to know the command type, so pass it via a set of flags in cmd->flags. Signed-off-by: Russell King --- include/linux/mmc/mmc.h | 35 +++++++++++++++++++++++------------ include/linux/mmc/protocol.h | 2 +- 2 files changed, 24 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index ccd3e13de1e8..f38872abc126 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -21,24 +21,35 @@ struct mmc_command { u32 arg; u32 resp[4]; unsigned int flags; /* expected response type */ -#define MMC_RSP_NONE (0 << 0) -#define MMC_RSP_SHORT (1 << 0) -#define MMC_RSP_LONG (2 << 0) -#define MMC_RSP_MASK (3 << 0) -#define MMC_RSP_CRC (1 << 3) /* expect valid crc */ -#define MMC_RSP_BUSY (1 << 4) /* card may send busy */ -#define MMC_RSP_OPCODE (1 << 5) /* response contains opcode */ +#define MMC_RSP_PRESENT (1 << 0) +#define MMC_RSP_136 (1 << 1) /* 136 bit response */ +#define MMC_RSP_CRC (1 << 2) /* expect valid crc */ +#define MMC_RSP_BUSY (1 << 3) /* card may send busy */ +#define MMC_RSP_OPCODE (1 << 4) /* response contains opcode */ +#define MMC_CMD_MASK (3 << 5) /* command type */ +#define MMC_CMD_AC (0 << 5) +#define MMC_CMD_ADTC (1 << 5) +#define MMC_CMD_BC (2 << 5) +#define MMC_CMD_BCR (3 << 5) /* * These are the response types, and correspond to valid bit * patterns of the above flags. One additional valid pattern * is all zeros, which means we don't expect a response. */ -#define MMC_RSP_R1 (MMC_RSP_SHORT|MMC_RSP_CRC|MMC_RSP_OPCODE) -#define MMC_RSP_R1B (MMC_RSP_SHORT|MMC_RSP_CRC|MMC_RSP_OPCODE|MMC_RSP_BUSY) -#define MMC_RSP_R2 (MMC_RSP_LONG|MMC_RSP_CRC) -#define MMC_RSP_R3 (MMC_RSP_SHORT) -#define MMC_RSP_R6 (MMC_RSP_SHORT|MMC_RSP_CRC) +#define MMC_RSP_NONE (0) +#define MMC_RSP_R1 (MMC_RSP_PRESENT|MMC_RSP_CRC|MMC_RSP_OPCODE) +#define MMC_RSP_R1B (MMC_RSP_PRESENT|MMC_RSP_CRC|MMC_RSP_OPCODE|MMC_RSP_BUSY) +#define MMC_RSP_R2 (MMC_RSP_PRESENT|MMC_RSP_136|MMC_RSP_CRC) +#define MMC_RSP_R3 (MMC_RSP_PRESENT) +#define MMC_RSP_R6 (MMC_RSP_PRESENT|MMC_RSP_CRC) + +#define mmc_resp_type(cmd) ((cmd)->flags & (MMC_RSP_PRESENT|MMC_RSP_136|MMC_RSP_CRC|MMC_RSP_BUSY|MMC_RSP_OPCODE)) + +/* + * These are the command types. + */ +#define mmc_cmd_type(cmd) ((cmd)->flags & MMC_CMD_TYPE) unsigned int retries; /* max number of retries */ unsigned int error; /* command error */ diff --git a/include/linux/mmc/protocol.h b/include/linux/mmc/protocol.h index a14dc306545b..81c3f77f652c 100644 --- a/include/linux/mmc/protocol.h +++ b/include/linux/mmc/protocol.h @@ -79,7 +79,7 @@ /* SD commands type argument response */ /* class 8 */ /* This is basically the same command as for MMC with some quirks. */ -#define SD_SEND_RELATIVE_ADDR 3 /* ac R6 */ +#define SD_SEND_RELATIVE_ADDR 3 /* bcr R6 */ /* Application commands */ #define SD_APP_SET_BUS_WIDTH 6 /* ac [1:0] bus width R1 */ -- cgit v1.2.3 From 3ec9c59449744dcc390d593a017d30671546fd9e Mon Sep 17 00:00:00 2001 From: Andrey Panin Date: Thu, 2 Feb 2006 20:15:09 +0000 Subject: [SERIAL] SIIG 8-port serial boards support This patch adds support for SIIG 8-port boards. These boards have 4 ports in separate bars and another 4 ports in the single bar. Because of this strange port arrangement these cards need special setup function. Fortunately no other SIIG cards have more than 4 port, so this setup function could be used for them too. Signed-off-by: Andrey Panin Signed-off-by: Russell King --- include/linux/pci_ids.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index b0b908f583c5..92a619ba163f 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1670,6 +1670,9 @@ #define PCI_DEVICE_ID_SIIG_2S1P_20x_550 0x2060 #define PCI_DEVICE_ID_SIIG_2S1P_20x_650 0x2061 #define PCI_DEVICE_ID_SIIG_2S1P_20x_850 0x2062 +#define PCI_DEVICE_ID_SIIG_8S_20x_550 0x2080 +#define PCI_DEVICE_ID_SIIG_8S_20x_650 0x2081 +#define PCI_DEVICE_ID_SIIG_8S_20x_850 0x2082 #define PCI_SUBDEVICE_ID_SIIG_QUARTET_SERIAL 0x2050 #define PCI_VENDOR_ID_RADISYS 0x1331 -- cgit v1.2.3 From 3d0f89bb169482d26d5aa4e82e763077e7e9bc4d Mon Sep 17 00:00:00 2001 From: Joel Becker Date: Wed, 25 Jan 2006 13:31:07 -0800 Subject: configfs: Add permission and ownership to configfs objects. configfs always made item and attribute ownership root.root and permissions based on a umask of 022. Add ->setattr() to allow chown(2)/chmod(2), and persist the changes for the lifetime of the items and attributes. Signed-off-by: Joel Becker Signed-off-by: Mark Fasheh --- include/linux/configfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/configfs.h b/include/linux/configfs.h index acffb8c9073a..a7f015027535 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -126,7 +126,7 @@ extern struct config_item *config_group_find_obj(struct config_group *, const ch struct configfs_attribute { - char *ca_name; + const char *ca_name; struct module *ca_owner; mode_t ca_mode; }; -- cgit v1.2.3 From 53ea68ecea11bcbb3451c2758ce181bd97b569a9 Mon Sep 17 00:00:00 2001 From: Stephen Smalley Date: Fri, 3 Feb 2006 08:21:12 -0500 Subject: [PATCH] SELinux: fix size-128 slab leak Remove private inode tests from security_inode_alloc and security_inode_free, as we otherwise end up leaking inode security structures for private inodes. Signed-off-by: Stephen Smalley Acked-by: James Morris Signed-off-by: Linus Torvalds --- include/linux/security.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index bb1da86747c7..7cbef482e13a 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1499,15 +1499,11 @@ static inline void security_sb_post_pivotroot (struct nameidata *old_nd, static inline int security_inode_alloc (struct inode *inode) { - if (unlikely (IS_PRIVATE (inode))) - return 0; return security_ops->inode_alloc_security (inode); } static inline void security_inode_free (struct inode *inode) { - if (unlikely (IS_PRIVATE (inode))) - return; security_ops->inode_free_security (inode); } -- cgit v1.2.3 From 19ea7302df2eb4f2ad7f29af814d8cf55fc8b9c9 Mon Sep 17 00:00:00 2001 From: Yasuyuki Kozakai Date: Sat, 4 Feb 2006 02:15:36 -0800 Subject: [NETFILTER]: iptables: fix typos in ipt_connbytes.h Fix some typos that make iptables userspace compilation fail. Signed-off-by: Yasuyuki Kozakai Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ipt_connbytes.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ipt_connbytes.h b/include/linux/netfilter_ipv4/ipt_connbytes.h index b04dfa3083c9..f63e6ee91113 100644 --- a/include/linux/netfilter_ipv4/ipt_connbytes.h +++ b/include/linux/netfilter_ipv4/ipt_connbytes.h @@ -1,10 +1,10 @@ #ifndef _IPT_CONNBYTES_H #define _IPT_CONNBYTES_H -#include +#include #define ipt_connbytes_what xt_connbytes_what -#define IPT_CONNBYTES_PKTS XT_CONNBYTES_PACKETS +#define IPT_CONNBYTES_PKTS XT_CONNBYTES_PKTS #define IPT_CONNBYTES_BYTES XT_CONNBYTES_BYTES #define IPT_CONNBYTES_AVGPKT XT_CONNBYTES_AVGPKT -- cgit v1.2.3 From 0047c65a60fa3b6607b55e058ea6a89f39cb3f28 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sat, 4 Feb 2006 02:19:09 -0800 Subject: [NETFILTER]: Prepare {ipt,ip6t}_policy match for x_tables unification The IPv4 and IPv6 version of the policy match are identical besides address comparison and the data structure used for userspace communication. Unify the data structures to break compatiblity now (before it is released), so we can port it to x_tables in 2.6.17. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ipt_policy.h | 22 ++++++++++++++-------- include/linux/netfilter_ipv6/ip6t_policy.h | 22 ++++++++++++++-------- 2 files changed, 28 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ipt_policy.h b/include/linux/netfilter_ipv4/ipt_policy.h index 7fd1bec453f1..a3f6eff39d33 100644 --- a/include/linux/netfilter_ipv4/ipt_policy.h +++ b/include/linux/netfilter_ipv4/ipt_policy.h @@ -27,16 +27,22 @@ struct ipt_policy_spec reqid:1; }; +union ipt_policy_addr +{ + struct in_addr a4; + struct in6_addr a6; +}; + struct ipt_policy_elem { - u_int32_t saddr; - u_int32_t smask; - u_int32_t daddr; - u_int32_t dmask; - u_int32_t spi; - u_int32_t reqid; - u_int8_t proto; - u_int8_t mode; + union ipt_policy_addr saddr; + union ipt_policy_addr smask; + union ipt_policy_addr daddr; + union ipt_policy_addr dmask; + u_int32_t spi; + u_int32_t reqid; + u_int8_t proto; + u_int8_t mode; struct ipt_policy_spec match; struct ipt_policy_spec invert; diff --git a/include/linux/netfilter_ipv6/ip6t_policy.h b/include/linux/netfilter_ipv6/ip6t_policy.h index 5a93afcd2ff1..671bd818300f 100644 --- a/include/linux/netfilter_ipv6/ip6t_policy.h +++ b/include/linux/netfilter_ipv6/ip6t_policy.h @@ -27,16 +27,22 @@ struct ip6t_policy_spec reqid:1; }; +union ip6t_policy_addr +{ + struct in_addr a4; + struct in6_addr a6; +}; + struct ip6t_policy_elem { - struct in6_addr saddr; - struct in6_addr smask; - struct in6_addr daddr; - struct in6_addr dmask; - u_int32_t spi; - u_int32_t reqid; - u_int8_t proto; - u_int8_t mode; + union ip6t_policy_addr saddr; + union ip6t_policy_addr smask; + union ip6t_policy_addr daddr; + union ip6t_policy_addr dmask; + u_int32_t spi; + u_int32_t reqid; + u_int8_t proto; + u_int8_t mode; struct ip6t_policy_spec match; struct ip6t_policy_spec invert; -- cgit v1.2.3 From a460ad62260def15c42130de253d6cfc32528a2f Mon Sep 17 00:00:00 2001 From: Phillip Susi Date: Sat, 4 Feb 2006 23:27:44 -0800 Subject: [PATCH] pktcdvd: Fix overflow for discs with large packets The pktcdvd driver was using an 8 bit field to store the packet length obtained from the disc track info. This causes it to overflow packet length values of 128KB or more. I changed the field to 32 bits to fix this. The pktcdvd driver defaulted to its maximum allowed packet length when it detected a 0 in the track info field. I changed this to fail the operation and refuse to access the media. This seems more sane than attempting to access it with a value that almost certainly will not work. Signed-off-by: Peter Osterlund Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pktcdvd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h index 2c177e4c8f22..d1c9c4a86e52 100644 --- a/include/linux/pktcdvd.h +++ b/include/linux/pktcdvd.h @@ -114,7 +114,7 @@ struct pkt_ctrl_command { struct packet_settings { - __u8 size; /* packet size in (512 byte) sectors */ + __u32 size; /* packet size in (512 byte) sectors */ __u8 fp; /* fixed packets */ __u8 link_loss; /* the rest is specified * as per Mt Fuji */ -- cgit v1.2.3 From e1bc89bc9991e994f2b3c60d9ad2fdb5ad9b10fc Mon Sep 17 00:00:00 2001 From: Peter Osterlund Date: Sat, 4 Feb 2006 23:27:47 -0800 Subject: [PATCH] pktcdvd: Don't waste kernel memory Allocate memory for read-gathering at open time, when it is known just how much memory is needed. This avoids wasting kernel memory when the real packet size is smaller than the maximum packet size supported by the driver. This is always the case when using DVD discs. Signed-off-by: Peter Osterlund Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pktcdvd.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h index d1c9c4a86e52..1623da88d6fe 100644 --- a/include/linux/pktcdvd.h +++ b/include/linux/pktcdvd.h @@ -170,7 +170,7 @@ struct packet_iosched #error "PAGE_SIZE must be a multiple of CD_FRAMESIZE" #endif #define PACKET_MAX_SIZE 32 -#define PAGES_PER_PACKET (PACKET_MAX_SIZE * CD_FRAMESIZE / PAGE_SIZE) +#define FRAMES_PER_PAGE (PAGE_SIZE / CD_FRAMESIZE) #define PACKET_MAX_SECTORS (PACKET_MAX_SIZE * CD_FRAMESIZE >> 9) enum packet_data_state { @@ -219,7 +219,7 @@ struct packet_data atomic_t io_errors; /* Number of read/write errors during IO */ struct bio *r_bios[PACKET_MAX_SIZE]; /* bios to use during data gathering */ - struct page *pages[PAGES_PER_PACKET]; + struct page *pages[PACKET_MAX_SIZE / FRAMES_PER_PAGE]; int cache_valid; /* If non-zero, the data for the zone defined */ /* by the sector variable is completely cached */ -- cgit v1.2.3 From 5c55ac9bbca22ee134408f83de5f2bda3b1b2a53 Mon Sep 17 00:00:00 2001 From: Phillip Susi Date: Sat, 4 Feb 2006 23:27:48 -0800 Subject: [PATCH] pktcdvd: Allow larger packets The pktcdvd driver uses a compile time macro constant to define the maximum supported packet length. I changed this from 32 sectors to 128 sectors because that allows over 100 MB of additional usable space on a 700 MB cdrw, and increases throughput. Note that you need a modified cdrwtool program that can format a CDRW disc with larger packets to benefit from this change. Signed-off-by: Peter Osterlund Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pktcdvd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h index 1623da88d6fe..8a94c717c266 100644 --- a/include/linux/pktcdvd.h +++ b/include/linux/pktcdvd.h @@ -169,7 +169,7 @@ struct packet_iosched #if (PAGE_SIZE % CD_FRAMESIZE) != 0 #error "PAGE_SIZE must be a multiple of CD_FRAMESIZE" #endif -#define PACKET_MAX_SIZE 32 +#define PACKET_MAX_SIZE 128 #define FRAMES_PER_PAGE (PAGE_SIZE / CD_FRAMESIZE) #define PACKET_MAX_SECTORS (PACKET_MAX_SIZE * CD_FRAMESIZE >> 9) -- cgit v1.2.3 From bc5e483da61eb5ab8d24b4a919fb512e5886d02c Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Sat, 4 Feb 2006 23:27:51 -0800 Subject: [PATCH] reiserfs_get_acl() build fix With CONFIG_REISERFS_FS_XATTR=y, CONFIG_REISERFS_FS_POSIX_ACL=n: fs/reiserfs/xattr.c: In function `reiserfs_check_acl': fs/reiserfs/xattr.c:1330: called object is not a function Cc: Chris Mason Cc: Jeff Mahoney Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reiserfs_acl.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_acl.h b/include/linux/reiserfs_acl.h index 0a3605099c44..806ec5b06707 100644 --- a/include/linux/reiserfs_acl.h +++ b/include/linux/reiserfs_acl.h @@ -58,9 +58,13 @@ extern struct reiserfs_xattr_handler posix_acl_default_handler; extern struct reiserfs_xattr_handler posix_acl_access_handler; #else -#define reiserfs_get_acl NULL #define reiserfs_cache_default_acl(inode) 0 +static inline struct posix_acl *reiserfs_get_acl(struct inode *inode, int type) +{ + return NULL; +} + static inline int reiserfs_xattr_posix_acl_init(void) { return 0; -- cgit v1.2.3 From fe1dcbc4f311c2e6c23b33c0fa8572461618ab3e Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Sat, 4 Feb 2006 23:27:54 -0800 Subject: [PATCH] jbd: fix transaction batching Ben points out that: When writing files out using O_SYNC, jbd's 1 jiffy delay results in a significant drop in throughput as the disk sits idle. The patch below results in a 4-5x performance improvement (from 6.5MB/s to ~24-30MB/s on my IDE test box) when writing out files using O_SYNC. So optimise the batching code by omitting it entirely if the process which is doing a sync write is the same as the one which did the most recent sync write. If that's true, we're unlikely to get any other processes joining the transaction. (Has been in -mm for ages - it took me a long time to get on to performance testing it) Numbers, on write-cache-disabled IDE: /usr/bin/time -p synctest -n 10 -uf -t 1 -p 1 dir-name Unpatched: 40 seconds Patched: 35 seconds Batching disabled: 35 seconds This is the problematic single-process-doing-fsync case. With multiple fsyncing processes the numbers are AFACIT unaltered by the patch. Aside: performance testing and instrumentation shows that the transaction batching almost doesn't help (testing with synctest -n 1 -uf -t 100 -p 10 dir-name on non-writeback-caching IDE). This is because by the time one process is running a synchronous commit, a bunch of other processes already have a transaction handle open, so they're all going to batch into the same transaction anyway. The batching seems to offer maybe 5-10% speedup with this workload, but I'm pretty sure it was more important than that when it was first developed 4-odd years ago... Cc: "Stephen C. Tweedie" Cc: Benjamin LaHaise Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/jbd.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 558cb4c26ec9..751bb3849467 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -23,6 +23,7 @@ #define jfs_debug jbd_debug #else +#include #include #include #include @@ -618,6 +619,7 @@ struct transaction_s * @j_wbuf: array of buffer_heads for journal_commit_transaction * @j_wbufsize: maximum number of buffer_heads allowed in j_wbuf, the * number that will fit in j_blocksize + * @j_last_sync_writer: most recent pid which did a synchronous write * @j_private: An opaque pointer to fs-private information. */ @@ -807,6 +809,8 @@ struct journal_s struct buffer_head **j_wbuf; int j_wbufsize; + pid_t j_last_sync_writer; + /* * An opaque pointer to fs-private information. ext3 puts its * superblock pointer here -- cgit v1.2.3 From 21bbd691827e3610ef975a88863859381ac8d8e0 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 9 Jan 2006 15:19:18 +1100 Subject: [PATCH] I2C: Resurrect i2c_smbus_write_i2c_block_data. Signed-off-by: Jean Delvare --- include/linux/i2c.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 7863a59bd598..63f1d63cc1d8 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -100,6 +100,9 @@ extern s32 i2c_smbus_write_block_data(struct i2c_client * client, /* Returns the number of read bytes */ extern s32 i2c_smbus_read_i2c_block_data(struct i2c_client * client, u8 command, u8 *values); +extern s32 i2c_smbus_write_i2c_block_data(struct i2c_client * client, + u8 command, u8 length, + u8 *values); /* * A driver is capable of handling one or more physical devices present on -- cgit v1.2.3 From 0dfd812d4b2afc797310943b451608d347854e76 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 7 Feb 2006 06:45:34 -0200 Subject: V4L/DVB (3300): Add standard for South Korean NTSC-M using A2 audio. South Korea uses NTSC-M but with A2 audio instead of BTSC. Several audio chips need this information in order to set the correct audio processing registers. Acked-by: Mauro Carvalho Chehab Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index ce40675324bd..839ccc70698e 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -628,6 +628,7 @@ typedef __u64 v4l2_std_id; #define V4L2_STD_NTSC_M ((v4l2_std_id)0x00001000) #define V4L2_STD_NTSC_M_JP ((v4l2_std_id)0x00002000) #define V4L2_STD_NTSC_443 ((v4l2_std_id)0x00004000) +#define V4L2_STD_NTSC_M_KR ((v4l2_std_id)0x00008000) #define V4L2_STD_SECAM_B ((v4l2_std_id)0x00010000) #define V4L2_STD_SECAM_D ((v4l2_std_id)0x00020000) @@ -660,7 +661,8 @@ typedef __u64 v4l2_std_id; V4L2_STD_PAL_H |\ V4L2_STD_PAL_I) #define V4L2_STD_NTSC (V4L2_STD_NTSC_M |\ - V4L2_STD_NTSC_M_JP) + V4L2_STD_NTSC_M_JP |\ + V4L2_STD_NTSC_M_KR) #define V4L2_STD_SECAM_DK (V4L2_STD_SECAM_D |\ V4L2_STD_SECAM_K |\ V4L2_STD_SECAM_K1) -- cgit v1.2.3 From 46cd2f32baf181b74b16cceb123bab6fe1f61f85 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 7 Feb 2006 12:58:50 -0800 Subject: [PATCH] Fix build failure in recent pm_prepare_* changes. Fix compilation problem in PM headers. Signed-off-by: Rafael J. Wysocki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/suspend.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 43bcd13eb1ec..37c1c76fd547 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -42,13 +42,21 @@ extern void mark_free_pages(struct zone *zone); #ifdef CONFIG_PM /* kernel/power/swsusp.c */ extern int software_suspend(void); + +#if defined(CONFIG_VT) && defined(CONFIG_VT_CONSOLE) +extern int pm_prepare_console(void); +extern void pm_restore_console(void); +#else +static inline int pm_prepare_console(void) { return 0; } +static inline void pm_restore_console(void) {} +#endif /* defined(CONFIG_VT) && defined(CONFIG_VT_CONSOLE) */ #else static inline int software_suspend(void) { printk("Warning: fake suspend called\n"); return -EPERM; } -#endif +#endif /* CONFIG_PM */ #ifdef CONFIG_SUSPEND_SMP extern void disable_nonboot_cpus(void); -- cgit v1.2.3 From 8519fb30e438f8088b71a94a7d5a660a814d3872 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Tue, 7 Feb 2006 12:58:52 -0800 Subject: [PATCH] mm: compound release fix Compound pages on SMP systems can now often be freed from pagetables via the release_pages path. This uses put_page_testzero which does not handle compound pages at all. Releasing constituent pages from process mappings decrements their count to a large negative number and leaks the reference at the head page - net result is a memory leak. The problem was hidden because the debug check in put_page_testzero itself actually did take compound pages into consideration. Fix the bug and the debug check. Signed-off-by: Nick Piggin Acked-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 85854b867463..75e9f0724997 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -303,7 +303,7 @@ struct page { */ #define put_page_testzero(p) \ ({ \ - BUG_ON(page_count(p) == 0); \ + BUG_ON(atomic_read(&(p)->_count) == -1);\ atomic_add_negative(-1, &(p)->_count); \ }) -- cgit v1.2.3 From 741a295130606143edbf9fc740f633dbc1e6225f Mon Sep 17 00:00:00 2001 From: JANAK DESAI Date: Tue, 7 Feb 2006 12:59:00 -0800 Subject: [PATCH] unshare system call -v5: unshare namespace If the namespace structure is being shared, allocate a new one and copy information from the current, shared, structure. Signed-off-by: Janak Desai Cc: Al Viro Cc: Christoph Hellwig Cc: Michael Kerrisk Cc: Andi Kleen Cc: Paul Mackerras Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/namespace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/namespace.h b/include/linux/namespace.h index 6731977c4c13..3abc8e3b4879 100644 --- a/include/linux/namespace.h +++ b/include/linux/namespace.h @@ -15,6 +15,7 @@ struct namespace { extern int copy_namespace(int, struct task_struct *); extern void __put_namespace(struct namespace *namespace); +extern struct namespace *dup_namespace(struct task_struct *, struct fs_struct *); static inline void put_namespace(struct namespace *namespace) { -- cgit v1.2.3 From 1b8623545b42c03eb92e51b28c84acf4b8ba00a3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 15 Dec 2005 01:07:03 -0500 Subject: [PATCH] remove bogus asm/bug.h includes. A bunch of asm/bug.h includes are both not needed (since it will get pulled anyway) and bogus (since they are done too early). Removed. Signed-off-by: Al Viro --- include/linux/cpumask.h | 1 - include/linux/dcache.h | 1 - include/linux/jbd.h | 1 - include/linux/mtd/map.h | 1 - include/linux/nodemask.h | 1 - include/linux/smp.h | 1 - 6 files changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 13e9f4a3ab26..20b446f26ecd 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -84,7 +84,6 @@ #include #include #include -#include typedef struct { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; extern cpumask_t _unused_cpumask_arg_; diff --git a/include/linux/dcache.h b/include/linux/dcache.h index a3f09947940e..4361f3789975 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -8,7 +8,6 @@ #include #include #include -#include struct nameidata; struct vfsmount; diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 751bb3849467..0fe4aa891ddc 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -239,7 +239,6 @@ typedef struct journal_superblock_s #include #include -#include #define JBD_ASSERTIONS #ifdef JBD_ASSERTIONS diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index fedfbc8a287f..7dfd6e1fcde7 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -15,7 +15,6 @@ #include #include #include -#include #ifdef CONFIG_MTD_MAP_BANK_WIDTH_1 #define map_bankwidth(map) 1 diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 4726ef7ba8e8..b959a4525cbd 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -84,7 +84,6 @@ #include #include #include -#include typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t; extern nodemask_t _unused_nodemask_arg_; diff --git a/include/linux/smp.h b/include/linux/smp.h index 9dfa3ee769ae..44153fdf73fc 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -17,7 +17,6 @@ extern void cpu_idle(void); #include #include #include -#include /* * main cross-CPU interfaces, handles INIT, TLB flush, STOP, etc. -- cgit v1.2.3 From bee14e1f8ae2d5fd3f324e0c8562f791537160b2 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 1 Feb 2006 07:33:44 -0500 Subject: [PATCH] __user annotations of video_spu_palette Signed-off-by: Al Viro --- include/linux/dvb/video.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dvb/video.h b/include/linux/dvb/video.h index b1999bfeaa56..b81e58b2ebf8 100644 --- a/include/linux/dvb/video.h +++ b/include/linux/dvb/video.h @@ -135,7 +135,7 @@ typedef struct video_spu { typedef struct video_spu_palette { /* SPU Palette information */ int length; - uint8_t *palette; + uint8_t __user *palette; } video_spu_palette_t; -- cgit v1.2.3 From 5b1a43d7df65689b4c3b5a1c5c8158f1d4f74fbd Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 1 Feb 2006 05:24:20 -0500 Subject: [PATCH] drivers/media/video __user annotations and fixes * compat_alloc_user_space() returns __user pointer * copying between two userland areas is copy_in_user(), not copy_from_user() * dereferencing userland pointers is bad * so's get_user() from local variables ... plus usual __user annotations Signed-off-by: Al Viro --- include/linux/videodev2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index b23be44cbea8..5208b12d5550 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -549,7 +549,7 @@ struct v4l2_framebuffer struct v4l2_clip { struct v4l2_rect c; - struct v4l2_clip *next; + struct v4l2_clip __user *next; }; struct v4l2_window -- cgit v1.2.3 From d656101009d76000b8fc0998a33d592100334d52 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 1 Feb 2006 05:59:06 -0500 Subject: [PATCH] sn3 iomem annotations and fixes Signed-off-by: Al Viro --- include/linux/ioc3.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ioc3.h b/include/linux/ioc3.h index e7906a72a4f1..da7c09e4ede6 100644 --- a/include/linux/ioc3.h +++ b/include/linux/ioc3.h @@ -27,7 +27,7 @@ struct ioc3_driver_data { int id; /* IOC3 sequence number */ /* PCI mapping */ unsigned long pma; /* physical address */ - struct __iomem ioc3 *vma; /* pointer to registers */ + struct ioc3 __iomem *vma; /* pointer to registers */ struct pci_dev *pdev; /* PCI device */ /* IRQ stuff */ int dual_irq; /* set if separate IRQs are used */ -- cgit v1.2.3 From 30e9656cc340035e102fea46e1908689494b042d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 8 Feb 2006 01:01:31 -0800 Subject: [PATCH] block: implement elv_insert and use it (fix ordcolor flipping bug) q->ordcolor must only be flipped on initial queueing of a hardbarrier request. Constructing ordered sequence and requeueing used to pass through __elv_add_request() which flips q->ordcolor when it sees a barrier request. This patch separates out elv_insert() from __elv_add_request() and uses elv_insert() when constructing ordered sequence and requeueing. elv_insert() inserts the given request at the specified position and does nothing else. Signed-off-by: Tejun Heo Acked-by: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 23fe746a1d51..18cf1f3e1184 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -82,6 +82,7 @@ struct elevator_queue extern void elv_dispatch_sort(request_queue_t *, struct request *); extern void elv_add_request(request_queue_t *, struct request *, int, int); extern void __elv_add_request(request_queue_t *, struct request *, int, int); +extern void elv_insert(request_queue_t *, struct request *, int); extern int elv_merge(request_queue_t *, struct request **, struct bio *); extern void elv_merge_requests(request_queue_t *, struct request *, struct request *); -- cgit v1.2.3 From 85d1494e5ff8e20a52ce514584ffda4f0265025e Mon Sep 17 00:00:00 2001 From: Yoichi Yuasa Date: Wed, 8 Feb 2006 21:46:24 +0000 Subject: [SERIAL] 8250_pci: add new PCI serial card support This patch adds new PCI serial card support. Signed-off-by: Yoichi Yuasa Signed-off-by: Russell King --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 92a619ba163f..7a61ccdcbc4b 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1832,6 +1832,7 @@ #define PCI_VENDOR_ID_AFAVLAB 0x14db #define PCI_DEVICE_ID_AFAVLAB_P028 0x2180 #define PCI_DEVICE_ID_AFAVLAB_P030 0x2182 +#define PCI_SUBDEVICE_ID_AFAVLAB_P061 0x2150 #define PCI_VENDOR_ID_BROADCOM 0x14e4 #define PCI_DEVICE_ID_TIGON3_5752 0x1600 -- cgit v1.2.3 From 9ac95f2f90e022c16d293d7978faddf7e779a1a9 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 9 Feb 2006 22:41:50 +0300 Subject: [PATCH] do_sigaction: cleanup ->sa_mask manipulation Clear unblockable signals beforehand. Signed-off-by: Oleg Nesterov Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 0cfcd1c7865e..9c1da0269a18 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1098,7 +1098,7 @@ extern struct sigqueue *sigqueue_alloc(void); extern void sigqueue_free(struct sigqueue *); extern int send_sigqueue(int, struct sigqueue *, struct task_struct *); extern int send_group_sigqueue(int, struct sigqueue *, struct task_struct *); -extern int do_sigaction(int, const struct k_sigaction *, struct k_sigaction *); +extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long); /* These can be the second arg to send_sig_info/send_group_sig_info. */ -- cgit v1.2.3 From a70ea994a0d83fd0151a070be72b87d014ef0a7e Mon Sep 17 00:00:00 2001 From: Alexey Kuznetsov Date: Thu, 9 Feb 2006 16:40:11 -0800 Subject: [NETLINK]: Fix a severe bug netlink overrun was broken while improvement of netlink. Destination socket is used in the place where it was meant to be source socket, so that now overrun is never sent to user netlink sockets, when it should be, and it even can be set on kernel socket, which results in complete deadlock of rtnetlink. Suggested fix is to restore status quo passing source socket as additional argument to netlink_attachskb(). A little explanation: overrun is set on a socket, when it failed to receive some message and sender of this messages does not or even have no way to handle this error. This happens in two cases: 1. when kernel sends something. Kernel never retransmits and cannot wait for buffer space. 2. when user sends a broadcast and the message was not delivered to some recipients. Signed-off-by: Alexey Kuznetsov Signed-off-by: David S. Miller --- include/linux/netlink.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 6a2ccf78a356..c256ebe2a7b4 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -160,7 +160,8 @@ extern int netlink_unregister_notifier(struct notifier_block *nb); /* finegrained unicast helpers: */ struct sock *netlink_getsockbyfilp(struct file *filp); -int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock, long timeo); +int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock, + long timeo, struct sock *ssk); void netlink_detachskb(struct sock *sk, struct sk_buff *skb); int netlink_sendskb(struct sock *sk, struct sk_buff *skb, int protocol); -- cgit v1.2.3 From 9c15e852a524d55ab768cf48c97f5c684f876af2 Mon Sep 17 00:00:00 2001 From: Haren Myneni Date: Fri, 10 Feb 2006 01:51:05 -0800 Subject: [PATCH] kexec: fix in free initrd when overlapped with crashkernel region It is possible that the reserved crashkernel region can be overlapped with initrd since the bootloader sets the initrd location. When the initrd region is freed, the second kernel memory will not be contiguous. The Kexec_load can cause an oops since there is no contiguous memory to write the second kernel or this memory could be used in the first kernel itself and may not be part of the dump. For example, on powerpc, the initrd is located at 36MB and the crashkernel starts at 32MB. The kexec_load caused panic since writing into non-allocated memory (after 36MB). We could see the similar issue even on other archs. One possibility is to move the initrd outside of crashkernel region. But, the initrd region will be freed anyway before the system is up. This patch fixes this issue and frees only regions that are not part of crashkernel memory in case overlaps. Signed-off-by: Haren Myneni Acked-by: "Eric W. Biederman" Cc: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index a311f58c8a7c..cfb3410e32b1 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -6,6 +6,7 @@ #include #include #include +#include #include /* Verify architecture specific macros are defined */ -- cgit v1.2.3 From 7a8ef1cb774e5438d292365626f9b96616283706 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 10 Feb 2006 01:51:08 -0800 Subject: [PATCH] x86: don't initialise cpu_possible_map to all ones Initialising cpu_possible_map to all-ones with CONFIG_HOTPLUG_CPU means that a) All for_each_cpu() loops will iterate across all NR_CPUS CPUs, rather than over possible ones. That can be quite expensive. b) Soon we'll be allocating per-cpu areas only for possible CPUs. So with CPU_MASK_ALL, we'll be wasting memory. I also switched voyager over to not use CPU_MASK_ALL in the non-CPU-hotplug case. Should be OK.. I note that parisc is also using CPU_MASK_ALL. Suggest that it stop doing that. Cc: James Bottomley Cc: Kyle McMartin Cc: Paul Jackson Cc: Ashok Raj Cc: Zwane Mwaikambo Cc: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 20b446f26ecd..60e56c6e03dd 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -328,7 +328,7 @@ static inline void __cpus_remap(cpumask_t *dstp, const cpumask_t *srcp, * bitmap of size NR_CPUS. * * #ifdef CONFIG_HOTPLUG_CPU - * cpu_possible_map - all NR_CPUS bits set + * cpu_possible_map - has bit 'cpu' set iff cpu is populatable * cpu_present_map - has bit 'cpu' set iff cpu is populated * cpu_online_map - has bit 'cpu' set iff cpu available to scheduler * #else -- cgit v1.2.3 From 8977d929e49021d9a6e031310aab01fa72f849c2 Mon Sep 17 00:00:00 2001 From: Paul Fulghum Date: Fri, 10 Feb 2006 01:51:14 -0800 Subject: [PATCH] tty buffering stall fix Prevent stalled processing of received data when a driver allocates tty buffer space but does not immediately follow the allocation with more data and a call to schedule receive tty processing. (example: hvc_console) This bug was introduced by the first locking patch for the new tty buffering. Signed-off-by: Paul Fulghum Cc: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kbd_kern.h | 4 +++- include/linux/tty.h | 2 ++ include/linux/tty_flip.h | 4 +++- 3 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kbd_kern.h b/include/linux/kbd_kern.h index 3aed37314ab8..e87c32a5c86a 100644 --- a/include/linux/kbd_kern.h +++ b/include/linux/kbd_kern.h @@ -153,8 +153,10 @@ static inline void con_schedule_flip(struct tty_struct *t) { unsigned long flags; spin_lock_irqsave(&t->buf.lock, flags); - if (t->buf.tail != NULL) + if (t->buf.tail != NULL) { t->buf.tail->active = 0; + t->buf.tail->commit = t->buf.tail->used; + } spin_unlock_irqrestore(&t->buf.lock, flags); schedule_work(&t->buf.work); } diff --git a/include/linux/tty.h b/include/linux/tty.h index a7bd3b4558d2..f45cd74e6f24 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -58,6 +58,8 @@ struct tty_buffer { int used; int size; int active; + int commit; + int read; /* Data points here */ unsigned long data[0]; }; diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index 82961eb19888..222faf97d5f9 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -29,8 +29,10 @@ _INLINE_ void tty_schedule_flip(struct tty_struct *tty) { unsigned long flags; spin_lock_irqsave(&tty->buf.lock, flags); - if (tty->buf.tail != NULL) + if (tty->buf.tail != NULL) { tty->buf.tail->active = 0; + tty->buf.tail->commit = tty->buf.tail->used; + } spin_unlock_irqrestore(&tty->buf.lock, flags); schedule_delayed_work(&tty->buf.work, 1); } -- cgit v1.2.3 From cff2b760096d1e6feaa31948e7af4abbefe47822 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Sat, 11 Feb 2006 17:55:47 -0800 Subject: [PATCH] fstatat64 support The *at patches introduced fstatat and, due to inusfficient research, I used the newfstat functions generally as the guideline. The result is that on 32-bit platforms we don't have all the information needed to implement fstatat64. This patch modifies the code to pass up 64-bit information if __ARCH_WANT_STAT64 is defined. I renamed the syscall entry point to make this clear. Other archs will continue to use the existing code. On x86-64 the compat code is implemented using a new sys32_ function. this is what is done for the other stat syscalls as well. This patch might break some other archs (those which define __ARCH_WANT_STAT64 and which already wired up the syscall). Yet others might need changes to accomodate the compatibility mode. I really don't want to do that work because all this stat handling is a mess (more so in glibc, but the kernel is also affected). It should be done by the arch maintainers. I'll provide some stand-alone test shortly. Those who are eager could compile glibc and run 'make check' (no installation needed). The patch below has been tested on x86 and x86-64. Signed-off-by: Ulrich Drepper Cc: Christoph Hellwig Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/syscalls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 3877209d23c3..d73501ba7e44 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -557,6 +557,8 @@ asmlinkage long sys_openat(int dfd, const char __user *filename, int flags, int mode); asmlinkage long sys_newfstatat(int dfd, char __user *filename, struct stat __user *statbuf, int flag); +asmlinkage long sys_fstatat64(int dfd, char __user *filename, + struct stat64 __user *statbuf, int flag); asmlinkage long sys_readlinkat(int dfd, const char __user *path, char __user *buf, int bufsiz); asmlinkage long compat_sys_futimesat(unsigned int dfd, char __user *filename, -- cgit v1.2.3 From 643a654540579b0dcc7a206a4a7475276a41aff0 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Sat, 11 Feb 2006 17:55:52 -0800 Subject: [PATCH] select: fix returned timeval With David Woodhouse select() presently has a habit of increasing the value of the user's `timeout' argument on return. We were writing back a timeout larger than the original. We _deliberately_ round up, since we know we must wait at _least_ as long as the caller asks us to. The patch adds a couple of helper functions for magnitude comparison of timespecs and of timevals, and uses them to prevent the various poll and select functions from returning a timeout which is larger than the one which was passed in. The patch also fixes a bug in compat_sys_pselect7(): it was adding the new timeout value to the old one and was returning that. It should just return the new timeout value. (We have various handy timespec/timeval-to-from-nsec conversion functions in time.h. But this code open-codes it all). Cc: "David S. Miller" Cc: Andi Kleen Cc: Ulrich Drepper Cc: Thomas Gleixner Cc: george anzinger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 20 ++++++++++++++++++++ include/linux/time.h | 25 ++++++++++++++++++++++++- 2 files changed, 44 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index f9ca534787e2..c9ab2a26348c 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -161,5 +161,25 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *to, siginfo_t *from); int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event); +static inline int compat_timeval_compare(struct compat_timeval *lhs, + struct compat_timeval *rhs) +{ + if (lhs->tv_sec < rhs->tv_sec) + return -1; + if (lhs->tv_sec > rhs->tv_sec) + return 1; + return lhs->tv_usec - rhs->tv_usec; +} + +static inline int compat_timespec_compare(struct compat_timespec *lhs, + struct compat_timespec *rhs) +{ + if (lhs->tv_sec < rhs->tv_sec) + return -1; + if (lhs->tv_sec > rhs->tv_sec) + return 1; + return lhs->tv_nsec - rhs->tv_nsec; +} + #endif /* CONFIG_COMPAT */ #endif /* _LINUX_COMPAT_H */ diff --git a/include/linux/time.h b/include/linux/time.h index 7b4dc36532bb..d9cdba54b789 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -33,11 +33,34 @@ struct timezone { #define NSEC_PER_SEC 1000000000L #define NSEC_PER_USEC 1000L -static __inline__ int timespec_equal(struct timespec *a, struct timespec *b) +static inline int timespec_equal(struct timespec *a, struct timespec *b) { return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); } +/* + * lhs < rhs: return <0 + * lhs == rhs: return 0 + * lhs > rhs: return >0 + */ +static inline int timespec_compare(struct timespec *lhs, struct timespec *rhs) +{ + if (lhs->tv_sec < rhs->tv_sec) + return -1; + if (lhs->tv_sec > rhs->tv_sec) + return 1; + return lhs->tv_nsec - rhs->tv_nsec; +} + +static inline int timeval_compare(struct timeval *lhs, struct timeval *rhs) +{ + if (lhs->tv_sec < rhs->tv_sec) + return -1; + if (lhs->tv_sec > rhs->tv_sec) + return 1; + return lhs->tv_usec - rhs->tv_usec; +} + extern unsigned long mktime(const unsigned int year, const unsigned int mon, const unsigned int day, const unsigned int hour, const unsigned int min, const unsigned int sec); -- cgit v1.2.3 From bc7fc0601b3eb2254f080492f3fd69e319ed32d0 Mon Sep 17 00:00:00 2001 From: "Antonino A. Daplas" Date: Sat, 11 Feb 2006 17:56:07 -0800 Subject: [PATCH] nvidiafb: Add support for Geforce4 MX 4000 Add support for Geforce4 MX 4000 (0x185) Signed-off-by: Antonino Daplas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 7a61ccdcbc4b..82b83da25d77 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1087,6 +1087,7 @@ #define PCI_DEVICE_ID_NVIDIA_GEFORCE4_MX_440_8X 0x0181 #define PCI_DEVICE_ID_NVIDIA_GEFORCE4_MX_440SE_8X 0x0182 #define PCI_DEVICE_ID_NVIDIA_GEFORCE4_MX_420_8X 0x0183 +#define PCI_DEVICE_ID_NVIDIA_GEFORCE4_MX_4000 0x0185 #define PCI_DEVICE_ID_NVIDIA_GEFORCE4_448_GO 0x0186 #define PCI_DEVICE_ID_NVIDIA_GEFORCE4_488_GO 0x0187 #define PCI_DEVICE_ID_NVIDIA_QUADRO4_580_XGL 0x0188 -- cgit v1.2.3 From 7c8903f6373f9abecf060bad53ca36bc4ac037f2 Mon Sep 17 00:00:00 2001 From: Mark Fasheh Date: Tue, 14 Feb 2006 13:53:03 -0800 Subject: [PATCH] jbd: revert checkpoint list changes This patch reverts commit f93ea411b73594f7d144855fd34278bcf34a9afc: [PATCH] jbd: split checkpoint lists This broke journal_flush() for OCFS2, which is its method of being sure that metadata is sent to disk for another node. And two related commits 8d3c7fce2d20ecc3264c8d8c91ae3beacdeaed1b and 43c3e6f5abdf6acac9b90c86bf03f995bf7d3d92 with the subjects: [PATCH] jbd: log_do_checkpoint fix [PATCH] jbd: remove_transaction fix These seem to be incremental bugfixes on the original patch and as such are no longer needed. Signed-off-by: Mark Fasheh Cc: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/jbd.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 0fe4aa891ddc..41ee79962bb2 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -497,12 +497,6 @@ struct transaction_s */ struct journal_head *t_checkpoint_list; - /* - * Doubly-linked circular list of all buffers submitted for IO while - * checkpointing. [j_list_lock] - */ - struct journal_head *t_checkpoint_io_list; - /* * Doubly-linked circular list of temporary buffers currently undergoing * IO in the log [j_list_lock] @@ -852,7 +846,7 @@ extern void journal_commit_transaction(journal_t *); /* Checkpoint list management */ int __journal_clean_checkpoint_list(journal_t *journal); -int __journal_remove_checkpoint(struct journal_head *); +void __journal_remove_checkpoint(struct journal_head *); void __journal_insert_checkpoint(struct journal_head *, transaction_t *); /* Buffer IO */ -- cgit v1.2.3 From 5ac5f9d1ce8492163dbde5d357dc5d03becf7e36 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 14 Feb 2006 13:53:04 -0800 Subject: [PATCH] NLM: Fix the NLM_GRANTED callback checks If 2 threads attached to the same process are blocking on different locks on different files (maybe even on different servers) but have the same lock arguments (i.e. same offset+length - actually quite common, since most processes try to lock the entire file) then the first GRANTED call that wakes one up will also wake the other. Currently when the NLM_GRANTED callback comes in, lockd walks the list of blocked locks in search of a match to the lock that the NLM server has granted. Although it checks the lock pid, start and end, it fails to check the filehandle and the server address. By checking the filehandle and server IP address, we ensure that this only happens if the locks truly are referencing the same file. Signed-off-by: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/lockd.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 920766cea79c..ef21ed296039 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -149,7 +149,7 @@ struct nlm_rqst * nlmclnt_alloc_call(void); int nlmclnt_prepare_block(struct nlm_rqst *req, struct nlm_host *host, struct file_lock *fl); void nlmclnt_finish_block(struct nlm_rqst *req); long nlmclnt_block(struct nlm_rqst *req, long timeout); -u32 nlmclnt_grant(struct nlm_lock *); +u32 nlmclnt_grant(const struct sockaddr_in *addr, const struct nlm_lock *); void nlmclnt_recovery(struct nlm_host *, u32); int nlmclnt_reclaim(struct nlm_host *, struct file_lock *); int nlmclnt_setgrantargs(struct nlm_rqst *, struct nlm_lock *); @@ -204,7 +204,7 @@ nlmsvc_file_inode(struct nlm_file *file) * Compare two host addresses (needs modifying for ipv6) */ static __inline__ int -nlm_cmp_addr(struct sockaddr_in *sin1, struct sockaddr_in *sin2) +nlm_cmp_addr(const struct sockaddr_in *sin1, const struct sockaddr_in *sin2) { return sin1->sin_addr.s_addr == sin2->sin_addr.s_addr; } @@ -214,7 +214,7 @@ nlm_cmp_addr(struct sockaddr_in *sin1, struct sockaddr_in *sin2) * When the second lock is of type F_UNLCK, this acts like a wildcard. */ static __inline__ int -nlm_compare_locks(struct file_lock *fl1, struct file_lock *fl2) +nlm_compare_locks(const struct file_lock *fl1, const struct file_lock *fl2) { return fl1->fl_pid == fl2->fl_pid && fl1->fl_start == fl2->fl_start -- cgit v1.2.3 From d6077cb80cde4506720f9165eba99ee07438513f Mon Sep 17 00:00:00 2001 From: "Chen, Kenneth W" Date: Tue, 14 Feb 2006 13:53:10 -0800 Subject: [PATCH] sched: revert "filter affine wakeups" Revert commit d7102e95b7b9c00277562c29aad421d2d521c5f6: [PATCH] sched: filter affine wakeups Apparently caused more than 10% performance regression for aim7 benchmark. The setup in use is 16-cpu HP rx8620, 64Gb of memory and 12 MSA1000s with 144 disks. Each disk is 72Gb with a single ext3 filesystem (courtesy of HP, who supplied benchmark results). The problem is, for aim7, the wake-up pattern is random, but it still needs load balancing action in the wake-up path to achieve best performance. With the above commit, lack of load balancing hurts that workload. However, for workloads like database transaction processing, the requirement is exactly opposite. In the wake up path, best performance is achieved with absolutely zero load balancing. We simply wake up the process on the CPU that it was previously run. Worst performance is obtained when we do load balancing at wake up. There isn't an easy way to auto detect the workload characteristics. Ingo's earlier patch that detects idle CPU and decide whether to load balance or not doesn't perform with aim7 either since all CPUs are busy (it causes even bigger perf. regression). Revert commit d7102e95b7b9c00277562c29aad421d2d521c5f6, which causes more than 10% performance regression with aim7. Signed-off-by: Ken Chen Acked-by: Ingo Molnar Cc: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 9c1da0269a18..b6f51e3a38ec 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -697,11 +697,8 @@ struct task_struct { int lock_depth; /* BKL lock depth */ -#if defined(CONFIG_SMP) - int last_waker_cpu; /* CPU that last woke this task up */ -#if defined(__ARCH_WANT_UNLOCKED_CTXSW) +#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) int oncpu; -#endif #endif int prio, static_prio; struct list_head run_list; -- cgit v1.2.3 From ee68cea2c26b7a8222f9020f54d22c6067011e8b Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 15 Feb 2006 01:34:23 -0800 Subject: [NETFILTER]: Fix xfrm lookup after SNAT To find out if a packet needs to be handled by IPsec after SNAT, packets are currently rerouted in POST_ROUTING and a new xfrm lookup is done. This breaks SNAT of non-unicast packets to non-local addresses because the packet is routed as incoming packet and no neighbour entry is bound to the dst_entry. In general, it seems to be a bad idea to replace the dst_entry after the packet was already sent to the output routine because its state might not match what's expected. This patch changes the xfrm lookup in POST_ROUTING to re-use the original dst_entry without routing the packet again. This means no policy routing can be used for transport mode transforms (which keep the original route) when packets are SNATed to match the policy, but it looks like the best we can do for now. Signed-off-by: Patrick McHardy Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index fdc4a9527343..43c09d790b83 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -79,7 +79,7 @@ enum nf_ip_hook_priorities { #ifdef __KERNEL__ extern int ip_route_me_harder(struct sk_buff **pskb); - +extern int ip_xfrm_me_harder(struct sk_buff **pskb); #endif /*__KERNEL__*/ #endif /*__LINUX_IP_NETFILTER_H*/ -- cgit v1.2.3 From 5ecfbae093f0c37311e89b29bfc0c9d586eace87 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 15 Feb 2006 22:50:10 +0300 Subject: [PATCH] fix zap_thread's ptrace related problems 1. The tracee can go from ptrace_stop() to do_signal_stop() after __ptrace_unlink(p). 2. It is unsafe to __ptrace_unlink(p) while p->parent may wait for tasklist_lock in ptrace_detach(). Signed-off-by: Oleg Nesterov Cc: Roland McGrath Cc: Ingo Molnar Cc: Christoph Hellwig Cc: Eric W. Biederman Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 9d5cd106b344..0d36750fc0f1 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -84,6 +84,7 @@ extern int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __us extern int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len); extern int ptrace_attach(struct task_struct *tsk); extern int ptrace_detach(struct task_struct *, unsigned int); +extern void __ptrace_detach(struct task_struct *, unsigned int); extern void ptrace_disable(struct task_struct *); extern int ptrace_check_attach(struct task_struct *task, int kill); extern int ptrace_request(struct task_struct *child, long request, long addr, long data); -- cgit v1.2.3 From 48d5cad87c3a4998d0bda16ccfb5c60dfe4de5fb Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 15 Feb 2006 15:10:22 -0800 Subject: [XFRM]: Fix SNAT-related crash in xfrm4_output_finish When a packet matching an IPsec policy is SNATed so it doesn't match any policy anymore it looses its xfrm bundle, which makes xfrm4_output_finish crash because of a NULL pointer dereference. This patch directs these packets to the original output path instead. Since the packets have already passed the POST_ROUTING hook, but need to start at the beginning of the original output path which includes another POST_ROUTING invocation, a flag is added to the IPCB to indicate that the packet was rerouted and doesn't need to pass the POST_ROUTING hook again. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 4cf6088625c1..3ca3d9ee78a9 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -184,8 +184,11 @@ static inline int nf_hook_thresh(int pf, unsigned int hook, struct sk_buff **pskb, struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct sk_buff *), int thresh) + int (*okfn)(struct sk_buff *), int thresh, + int cond) { + if (!cond) + return 1; #ifndef CONFIG_NETFILTER_DEBUG if (list_empty(&nf_hooks[pf][hook])) return 1; @@ -197,7 +200,7 @@ static inline int nf_hook(int pf, unsigned int hook, struct sk_buff **pskb, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct sk_buff *)) { - return nf_hook_thresh(pf, hook, pskb, indev, outdev, okfn, INT_MIN); + return nf_hook_thresh(pf, hook, pskb, indev, outdev, okfn, INT_MIN, 1); } /* Activate hook; either okfn or kfree_skb called, unless a hook @@ -224,7 +227,13 @@ static inline int nf_hook(int pf, unsigned int hook, struct sk_buff **pskb, #define NF_HOOK_THRESH(pf, hook, skb, indev, outdev, okfn, thresh) \ ({int __ret; \ -if ((__ret=nf_hook_thresh(pf, hook, &(skb), indev, outdev, okfn, thresh)) == 1)\ +if ((__ret=nf_hook_thresh(pf, hook, &(skb), indev, outdev, okfn, thresh, 1)) == 1)\ + __ret = (okfn)(skb); \ +__ret;}) + +#define NF_HOOK_COND(pf, hook, skb, indev, outdev, okfn, cond) \ +({int __ret; \ +if ((__ret=nf_hook_thresh(pf, hook, &(skb), indev, outdev, okfn, INT_MIN, cond)) == 1)\ __ret = (okfn)(skb); \ __ret;}) @@ -295,11 +304,13 @@ extern struct proc_dir_entry *proc_net_netfilter; #else /* !CONFIG_NETFILTER */ #define NF_HOOK(pf, hook, skb, indev, outdev, okfn) (okfn)(skb) +#define NF_HOOK_COND(pf, hook, skb, indev, outdev, okfn, cond) (okfn)(skb) static inline int nf_hook_thresh(int pf, unsigned int hook, struct sk_buff **pskb, struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct sk_buff *), int thresh) + int (*okfn)(struct sk_buff *), int thresh, + int cond) { return okfn(*pskb); } -- cgit v1.2.3 From 9c92d3486434e7310cb288587953e2dae4a79701 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 15 Feb 2006 15:18:19 -0800 Subject: [NETFILTER]: Don't invoke okfn in CONFIG_NETFILTER=n variant of nf_hook() nf_hook() is supposed to call the netfilter hook and return control of the packet back to the caller in case it may pass, the okfn is only used for queueing. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 3ca3d9ee78a9..468896939843 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -318,7 +318,7 @@ static inline int nf_hook(int pf, unsigned int hook, struct sk_buff **pskb, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct sk_buff *)) { - return okfn(*pskb); + return 1; } static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} struct flowi; -- cgit v1.2.3 From b2ee9dbfad14ba8e34a589d552ddc67300a26bec Mon Sep 17 00:00:00 2001 From: Roman Zippel Date: Wed, 15 Feb 2006 15:17:40 -0800 Subject: [PATCH] hrtimer: fix multiple macro argument expansion For two macros the arguments were expanded twice, change them to inline functions to avoid it. Signed-off-by: Roman Zippel Acked-by: Ingo Molnar Acked-by: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ktime.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 6aca67a569a2..f3dec45ef874 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -96,10 +96,16 @@ static inline ktime_t ktime_set(const long secs, const unsigned long nsecs) ({ (ktime_t){ .tv64 = (kt).tv64 + (nsval) }; }) /* convert a timespec to ktime_t format: */ -#define timespec_to_ktime(ts) ktime_set((ts).tv_sec, (ts).tv_nsec) +static inline ktime_t timespec_to_ktime(struct timespec ts) +{ + return ktime_set(ts.tv_sec, ts.tv_nsec); +} /* convert a timeval to ktime_t format: */ -#define timeval_to_ktime(tv) ktime_set((tv).tv_sec, (tv).tv_usec * 1000) +static inline ktime_t timeval_to_ktime(struct timeval tv) +{ + return ktime_set(tv.tv_sec, tv.tv_usec * NSEC_PER_USEC); +} /* Map the ktime_t to timespec conversion to ns_to_timespec function */ #define ktime_to_timespec(kt) ns_to_timespec((kt).tv64) -- cgit v1.2.3 From a62eaf151d9cb478d127cfbc2e93c498869785b0 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 16 Feb 2006 23:41:58 +0100 Subject: [PATCH] x86_64: Add boot option to disable randomized mappings and cleanup AMD SimNow!'s JIT doesn't like them at all in the guest. For distribution installation it's easiest if it's a boot time option. Also I moved the variable to a more appropiate place and make it independent from sysctl And marked __read_mostly which it is. Signed-off-by: Andi Kleen Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 6 ------ include/linux/mm.h | 2 ++ 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index b49affa0ac5a..3b507bf05d09 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -326,12 +326,6 @@ struct sysinfo { /* Force a compilation error if condition is true */ #define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) -#ifdef CONFIG_SYSCTL -extern int randomize_va_space; -#else -#define randomize_va_space 1 -#endif - /* Trap pasters of __FUNCTION__ at compile-time */ #define __FUNCTION__ (__func__) diff --git a/include/linux/mm.h b/include/linux/mm.h index 75e9f0724997..26e1663a5cbe 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1051,5 +1051,7 @@ int shrink_slab(unsigned long scanned, gfp_t gfp_mask, void drop_pagecache(void); void drop_slab(void); +extern int randomize_va_space; + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ -- cgit v1.2.3 From 726c14bf499e91e7ede4f1728830aba05c675061 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Fri, 17 Feb 2006 10:30:23 +1100 Subject: [PATCH] Provide an interface for getting the current tick length This provides an interface for arch code to find out how many nanoseconds are going to be added on to xtime by the next call to do_timer. The value returned is a fixed-point number in 52.12 format in nanoseconds. The reason for this format is that it gives the full precision that the timekeeping code is using internally. The motivation for this is to fix a problem that has arisen on 32-bit powerpc in that the value returned by do_gettimeofday drifts apart from xtime if NTP is being used. PowerPC is now using a lockless do_gettimeofday based on reading the timebase register and performing some simple arithmetic. (This method of getting the time is also exported to userspace via the VDSO.) However, the factor and offset it uses were calculated based on the nominal tick length and weren't being adjusted when NTP varied the tick length. Note that 64-bit powerpc has had the lockless do_gettimeofday for a long time now. It also had an extremely hairy routine that got called from the 32-bit compat routine for adjtimex, which adjusted the factor and offset according to what it thought the timekeeping code was going to do. Not only was this only called if a 32-bit task did adjtimex (i.e. not if a 64-bit task did adjtimex), it was also duplicating computations from kernel/timer.c and it wasn't clear that it was (still) correct. The simple solution is to ask the timekeeping code how long the current jiffy will be on each timer interrupt, after calling do_timer. If this jiffy will be a different length from the last one, we then need to compute new values for the factor and offset used in the lockless do_gettimeofday. In this way we can keep xtime and do_gettimeofday in sync, even when NTP is varying the tick length. Note that when adjtimex varies the tick length, it almost always introduces the variation from the next tick on. The only case I could see where adjtimex would vary the length of the current tick is when an old-style adjtime adjustment is being cancelled. (It's not clear to me why the adjustment has to be cancelled immediately rather than from the next tick on.) Thus I don't see any real need for a hook in adjtimex; the rare case of an old-style adjustment being cancelled can be fixed up at the next tick. Signed-off-by: Paul Mackerras Acked-by: john stultz Signed-off-by: Linus Torvalds --- include/linux/timex.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index 04a4a8cb4ed3..b7ca1204e42a 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -345,6 +345,9 @@ time_interpolator_reset(void) #endif /* !CONFIG_TIME_INTERPOLATION */ +/* Returns how long ticks are at present, in ns / 2^(SHIFT_SCALE-10). */ +extern u64 current_tick_length(void); + #endif /* KERNEL */ #endif /* LINUX_TIMEX_H */ -- cgit v1.2.3 From cc1887f3d8ae8ea61efa1a75af8ec0467b9dd546 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 20 Feb 2006 23:48:38 +0900 Subject: [PATCH] libata: fix qc->n_elem == 0 case handling in ata_qc_next_sg This patch makes ata_for_each_sg() start with pad_sgent when qc->n_elem is zero. Previously, ata_for_each_sg() unconditionally started with qc->__sg, handling the first sg to fill_sg() routines even when the entry was invalid. And while at it, unwind ?: in ata_qc_next_sg() into if statement. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 9e5db2949c58..c91be5e64ede 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -556,6 +556,16 @@ ata_sg_is_last(struct scatterlist *sg, struct ata_queued_cmd *qc) return 0; } +static inline struct scatterlist * +ata_qc_first_sg(struct ata_queued_cmd *qc) +{ + if (qc->n_elem) + return qc->__sg; + if (qc->pad_len) + return &qc->pad_sgent; + return NULL; +} + static inline struct scatterlist * ata_qc_next_sg(struct scatterlist *sg, struct ata_queued_cmd *qc) { @@ -563,11 +573,13 @@ ata_qc_next_sg(struct scatterlist *sg, struct ata_queued_cmd *qc) return NULL; if (++sg - qc->__sg < qc->n_elem) return sg; - return qc->pad_len ? &qc->pad_sgent : NULL; + if (qc->pad_len) + return &qc->pad_sgent; + return NULL; } #define ata_for_each_sg(sg, qc) \ - for (sg = qc->__sg; sg; sg = ata_qc_next_sg(sg, qc)) + for (sg = ata_qc_first_sg(qc); sg; sg = ata_qc_next_sg(sg, qc)) static inline unsigned int ata_tag_valid(unsigned int tag) { -- cgit v1.2.3 From 9b0f8b040acd8dfd23860754c0d09ff4f44e2cbc Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 20 Feb 2006 18:27:52 -0800 Subject: [PATCH] Terminate process that fails on a constrained allocation Some allocations are restricted to a limited set of nodes (due to memory policies or cpuset constraints). If the page allocator is not able to find enough memory then that does not mean that overall system memory is low. In particular going postal and more or less randomly shooting at processes is not likely going to help the situation but may just lead to suicide (the whole system coming down). It is better to signal to the process that no memory exists given the constraints that the process (or the configuration of the process) has placed on the allocation behavior. The process may be killed but then the sysadmin or developer can investigate the situation. The solution is similar to what we do when running out of hugepages. This patch adds a check before we kill processes. At that point performance considerations do not matter much so we just scan the zonelist and reconstruct a list of nodes. If the list of nodes does not contain all online nodes then this is a constrained allocation and we should kill the current process. Signed-off-by: Christoph Lameter Cc: Nick Piggin Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index f3e17d5963c3..d572b19afb7d 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -147,7 +147,7 @@ struct swap_list_t { #define vm_swap_full() (nr_swap_pages*2 < total_swap_pages) /* linux/mm/oom_kill.c */ -extern void out_of_memory(gfp_t gfp_mask, int order); +extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order); /* linux/mm/memory.c */ extern void swapin_readahead(swp_entry_t, unsigned long, struct vm_area_struct *); -- cgit v1.2.3 From c255d844dd73616f23e4b4733edcc2e5fa4042b2 Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Mon, 20 Feb 2006 18:27:58 -0800 Subject: [PATCH] suspend-to-ram: allow video options to be set at runtime Currently, acpi video options can only be set on kernel command line. That's little inflexible; I'd like userland s2ram application that just works, and modifying kernel command line according to whitelist is not fun. It is better to just allow s2ram application to set video options just before suspend (according to the whitelist). This implements sysctl to allow setting suspend video options without reboot. (akpm: Documentation updates for this new sysctl are pending..) Signed-off-by: Pavel Machek Cc: "Brown, Len" Cc: "Antonino A. Daplas" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/acpi.h | 3 ++- include/linux/sysctl.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 84d3d9f034ce..d3bc25e6d27d 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -427,7 +427,8 @@ extern int acpi_mp_config; extern struct acpi_table_mcfg_config *pci_mmcfg_config; extern int pci_mmcfg_config_num; -extern int sbf_port ; +extern int sbf_port; +extern unsigned long acpi_video_flags; #else /* !CONFIG_ACPI */ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 32a4139c4ad8..0e92bf7ec28e 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -146,6 +146,7 @@ enum KERN_RANDOMIZE=68, /* int: randomize virtual address space */ KERN_SETUID_DUMPABLE=69, /* int: behaviour of dumps for setuid core */ KERN_SPIN_RETRY=70, /* int: number of spinlock retries */ + KERN_ACPI_VIDEO_FLAGS=71, /* int: flags for setting up video after ACPI sleep */ }; -- cgit v1.2.3 From 7a9166e3b037296366cea6f3c97f705d33e209e6 Mon Sep 17 00:00:00 2001 From: Luke Yang Date: Mon, 20 Feb 2006 18:28:07 -0800 Subject: [PATCH] Fix undefined symbols for nommu architecture Signed-off-by: Luke Yang Acked-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 26e1663a5cbe..498ff8778fb6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1051,7 +1051,11 @@ int shrink_slab(unsigned long scanned, gfp_t gfp_mask, void drop_pagecache(void); void drop_slab(void); +#ifndef CONFIG_MMU +#define randomize_va_space 0 +#else extern int randomize_va_space; +#endif #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ -- cgit v1.2.3 From 7fd105e758c8d746d57ab7e77f100e096bf153c8 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Mon, 20 Feb 2006 18:28:08 -0800 Subject: [PATCH] Fix compile for CONFIG_SYSVIPC=n or CONFIG_SYSCTL=n The compat syscalls are added to sys_ni.c since they are not defined if the above CONFIG options are off. Also, nfs would not build with CONFIG_SYSCTL off. Noticed by Arthur Othieno. Signed-off-by: Stephen Rothwell Cc: "David S. Miller" Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 547d649b274e..b4dc6e2e10c9 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -398,7 +398,7 @@ extern struct inode_operations nfs_symlink_inode_operations; extern int nfs_register_sysctl(void); extern void nfs_unregister_sysctl(void); #else -#define nfs_register_sysctl() do { } while(0) +#define nfs_register_sysctl() 0 #define nfs_unregister_sysctl() do { } while(0) #endif -- cgit v1.2.3 From 5bd546aa78b5d74f3162815e41940f862215d9e3 Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 17 Feb 2006 20:23:29 +0000 Subject: [MMC] Fix mmc_cmd_type() mask It's MMC_CMD_MASK not MMC_CMD_TYPE. Signed-off-by: Russell King --- include/linux/mmc/mmc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index f38872abc126..bdc556d88498 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -49,7 +49,7 @@ struct mmc_command { /* * These are the command types. */ -#define mmc_cmd_type(cmd) ((cmd)->flags & MMC_CMD_TYPE) +#define mmc_cmd_type(cmd) ((cmd)->flags & MMC_CMD_MASK) unsigned int retries; /* max number of retries */ unsigned int error; /* command error */ -- cgit v1.2.3 From fa675765afed59bb89adba3369094ebd428b930b Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 22 Feb 2006 09:39:02 -0800 Subject: Revert mount/umount uevent removal This change reverts the 033b96fd30db52a710d97b06f87d16fc59fee0f1 commit from Kay Sievers that removed the mount/umount uevents from the kernel. Some older versions of HAL still depend on these events to detect when a new device has been mounted. These events are not correctly emitted, and are broken by design, and so, should not be relied upon by any future program. Instead, the /proc/mounts file should be polled to properly detect this kind of event. A feature-removal-schedule.txt entry has been added, noting when this interface will be removed from the kernel. Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 2a8d8da70961..c374b5fa8d3b 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -41,8 +41,10 @@ enum kobject_action { KOBJ_ADD = (__force kobject_action_t) 0x01, /* exclusive to core */ KOBJ_REMOVE = (__force kobject_action_t) 0x02, /* exclusive to core */ KOBJ_CHANGE = (__force kobject_action_t) 0x03, /* device state change */ - KOBJ_OFFLINE = (__force kobject_action_t) 0x04, /* device offline */ - KOBJ_ONLINE = (__force kobject_action_t) 0x05, /* device online */ + KOBJ_MOUNT = (__force kobject_action_t) 0x04, /* mount event for block devices (broken) */ + KOBJ_UMOUNT = (__force kobject_action_t) 0x05, /* umount event for block devices (broken) */ + KOBJ_OFFLINE = (__force kobject_action_t) 0x06, /* device offline */ + KOBJ_ONLINE = (__force kobject_action_t) 0x07, /* device online */ }; struct kobject { -- cgit v1.2.3 From 85edae14e4ee5e68cf037e9e4bca7498ea16874d Mon Sep 17 00:00:00 2001 From: Michal Janusz Miroslaw Date: Thu, 23 Feb 2006 09:49:35 +0000 Subject: [SERIAL] Trivial comment fix: include/linux/serial_reg.h Trivial comment fix for include/linux/serial_reg.h Signed-off-by: Russell King --- include/linux/serial_reg.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_reg.h b/include/linux/serial_reg.h index 6a2bb955844b..3c8a6aa77415 100644 --- a/include/linux/serial_reg.h +++ b/include/linux/serial_reg.h @@ -247,10 +247,10 @@ #define UART_CTR 0xFF /* - * The 16C950 Additional Control Reigster + * The 16C950 Additional Control Register */ #define UART_ACR_RXDIS 0x01 /* Receiver disable */ -#define UART_ACR_TXDIS 0x02 /* Receiver disable */ +#define UART_ACR_TXDIS 0x02 /* Transmitter disable */ #define UART_ACR_DSRFC 0x04 /* DSR Flow Control */ #define UART_ACR_TLENB 0x20 /* 950 trigger levels enable */ #define UART_ACR_ICRRD 0x40 /* ICR Read enable */ -- cgit v1.2.3 From c04030e16dbea2f7581f82cc6688695927f6ac5b Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Fri, 24 Feb 2006 13:04:21 -0800 Subject: [PATCH] flags parameter for linkat I'm currently at the POSIX meeting and one thing covered was the incompatibility of Linux's link() with the POSIX definition. The name. Linux does not follow symlinks, POSIX requires it does. Even if somebody thinks this is a good default behavior we cannot change this because it would break the ABI. But the fact remains that some application might want this behavior. We have one chance to help implementing this without breaking the behavior. For this we could use the new linkat interface which would need a new flags parameter. If the new parameter is AT_SYMLINK_FOLLOW the new behavior could be invoked. I do not want to introduce such a patch now. But we could add the parameter now, just don't use it. The patch below would do this. Can we get this late patch applied before the release more or less fixes the syscall API? Signed-off-by: Ulrich Drepper Signed-off-by: Ralf Baechle Cc: Heiko Carstens Cc: Martin Schwidefsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/syscalls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index d73501ba7e44..b9ea44ac0ddb 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -543,7 +543,7 @@ asmlinkage long sys_unlinkat(int dfd, const char __user * pathname, int flag); asmlinkage long sys_symlinkat(const char __user * oldname, int newdfd, const char __user * newname); asmlinkage long sys_linkat(int olddfd, const char __user *oldname, - int newdfd, const char __user *newname); + int newdfd, const char __user *newname, int flags); asmlinkage long sys_renameat(int olddfd, const char __user * oldname, int newdfd, const char __user * newname); asmlinkage long sys_futimesat(int dfd, char __user *filename, -- cgit v1.2.3 From bafac2a512bf4fd2ce7520f3976ce8aab4435f74 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 27 Feb 2006 13:04:17 -0800 Subject: [NETFILTER]: Restore {ipt,ip6t,ebt}_LOG compatibility The nfnetlink_log infrastructure changes broke compatiblity of the LOG targets. They currently use whatever log backend was registered first, which means that if ipt_ULOG was loaded first, no messages will be printed to the ring buffer anymore. Restore compatiblity by using the old log functions by default and only use the nf_log backend if the user explicitly said so. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_bridge/ebt_log.h | 1 + include/linux/netfilter_ipv4/ipt_LOG.h | 3 ++- include/linux/netfilter_ipv6/ip6t_LOG.h | 3 ++- 3 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_bridge/ebt_log.h b/include/linux/netfilter_bridge/ebt_log.h index 358fbc84fb59..96e231ae7554 100644 --- a/include/linux/netfilter_bridge/ebt_log.h +++ b/include/linux/netfilter_bridge/ebt_log.h @@ -3,6 +3,7 @@ #define EBT_LOG_IP 0x01 /* if the frame is made by ip, log the ip information */ #define EBT_LOG_ARP 0x02 +#define EBT_LOG_NFLOG 0x04 #define EBT_LOG_MASK (EBT_LOG_IP | EBT_LOG_ARP) #define EBT_LOG_PREFIX_SIZE 30 #define EBT_LOG_WATCHER "log" diff --git a/include/linux/netfilter_ipv4/ipt_LOG.h b/include/linux/netfilter_ipv4/ipt_LOG.h index 22d16177319b..892f9a33fea8 100644 --- a/include/linux/netfilter_ipv4/ipt_LOG.h +++ b/include/linux/netfilter_ipv4/ipt_LOG.h @@ -6,7 +6,8 @@ #define IPT_LOG_TCPOPT 0x02 /* Log TCP options */ #define IPT_LOG_IPOPT 0x04 /* Log IP options */ #define IPT_LOG_UID 0x08 /* Log UID owning local socket */ -#define IPT_LOG_MASK 0x0f +#define IPT_LOG_NFLOG 0x10 /* Log using nf_log backend */ +#define IPT_LOG_MASK 0x1f struct ipt_log_info { unsigned char level; diff --git a/include/linux/netfilter_ipv6/ip6t_LOG.h b/include/linux/netfilter_ipv6/ip6t_LOG.h index 9008ff5c40ae..060c1a1c6c60 100644 --- a/include/linux/netfilter_ipv6/ip6t_LOG.h +++ b/include/linux/netfilter_ipv6/ip6t_LOG.h @@ -6,7 +6,8 @@ #define IP6T_LOG_TCPOPT 0x02 /* Log TCP options */ #define IP6T_LOG_IPOPT 0x04 /* Log IP options */ #define IP6T_LOG_UID 0x08 /* Log UID owning local socket */ -#define IP6T_LOG_MASK 0x0f +#define IP6T_LOG_NFLOG 0x10 /* Log using nf_log backend */ +#define IP6T_LOG_MASK 0x1f struct ip6t_log_info { unsigned char level; -- cgit v1.2.3 From d2b176ed878d4d5fcc0bd35656dfd373f3702af9 Mon Sep 17 00:00:00 2001 From: Jes Sorensen Date: Tue, 28 Feb 2006 09:42:23 -0800 Subject: [IA64] sysctl option to silence unaligned trap warnings Allow sysadmin to disable all warnings about userland apps making unaligned accesses by using: # echo 1 > /proc/sys/kernel/ignore-unaligned-usertrap Rather than having to use prctl on a process by process basis. Default behaivour leaves the warnings enabled. Signed-off-by: Jes Sorensen Signed-off-by: Tony Luck --- include/linux/sysctl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 0e92bf7ec28e..bac61db26456 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -147,6 +147,7 @@ enum KERN_SETUID_DUMPABLE=69, /* int: behaviour of dumps for setuid core */ KERN_SPIN_RETRY=70, /* int: number of spinlock retries */ KERN_ACPI_VIDEO_FLAGS=71, /* int: flags for setting up video after ACPI sleep */ + KERN_IA64_UNALIGNED=72, /* int: ia64 unaligned userland trap enable */ }; -- cgit v1.2.3 From 0551fbd29e16fccd46e41b7d01bf0f8f39b14212 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Tue, 28 Feb 2006 16:59:19 -0800 Subject: [PATCH] Add mm->task_size and fix powerpc vdso This patch adds mm->task_size to keep track of the task size of a given mm and uses that to fix the powerpc vdso so that it uses the mm task size to decide what pages to fault in instead of the current thread flags (which broke when ptracing). (akpm: I expect that mm_struct.task_size will become the way in which we finally sort out the confusion between 32-bit processes and 32-bit mm's. It may need tweaks, but at this stage this patch is powerpc-only.) Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b6f51e3a38ec..ff2e09c953b9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -298,8 +298,9 @@ struct mm_struct { unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); void (*unmap_area) (struct mm_struct *mm, unsigned long addr); - unsigned long mmap_base; /* base of mmap area */ - unsigned long cached_hole_size; /* if non-zero, the largest hole below free_area_cache */ + unsigned long mmap_base; /* base of mmap area */ + unsigned long task_size; /* size of task vm space */ + unsigned long cached_hole_size; /* if non-zero, the largest hole below free_area_cache */ unsigned long free_area_cache; /* first hole of size cached_hole_size or larger */ pgd_t * pgd; atomic_t mm_users; /* How many users with user space? */ -- cgit v1.2.3 From 3af1efe8a301f5b1c813f5f761cb1e10d6175605 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Thu, 2 Mar 2006 13:25:26 -0500 Subject: [PATCH] reiserfs: fix unaligned bitmap usage The bitmaps associated with generation numbers for directory entries are declared as an array of ints. On some platforms, this causes alignment exceptions. The following patch uses the standard bitmap declaration macros to declare the bitmaps, fixing the problem. Originally from Takashi Iwai. Signed-off-by: Takashi Iwai Acked-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 7d51149bd793..dad78cecfd20 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -1052,7 +1052,7 @@ struct reiserfs_dir_entry { int de_entrylen; int de_namelen; char *de_name; - char *de_gen_number_bit_string; + unsigned long *de_gen_number_bit_string; __u32 de_dir_id; __u32 de_objectid; -- cgit v1.2.3 From 1e4b27df55166ce3b276f55bab223fa4ae8c5525 Mon Sep 17 00:00:00 2001 From: Karsten Keil Date: Mon, 6 Mar 2006 15:42:37 -0800 Subject: [PATCH] i4l: add new PCI IDs for HFC-S PCI Add new PCI IDs for HFC-S PCI based ISDN TA 'Primux II S0' and 'Primux II S0' from Gerdes AG Signed-off-by: Martin Bachem Signed-off-by: Karsten Keil Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 82b83da25d77..1709b5009d2e 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1752,6 +1752,8 @@ #define PCI_DEVICE_ID_CCD_B00B 0xb00b #define PCI_DEVICE_ID_CCD_B00C 0xb00c #define PCI_DEVICE_ID_CCD_B100 0xb100 +#define PCI_DEVICE_ID_CCD_B700 0xb700 +#define PCI_DEVICE_ID_CCD_B701 0xb701 #define PCI_VENDOR_ID_EXAR 0x13a8 #define PCI_DEVICE_ID_EXAR_XR17C152 0x0152 -- cgit v1.2.3 From 69239749e1ac4f3496906aa4267cb9f61ce52c9c Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 6 Mar 2006 15:42:45 -0800 Subject: [PATCH] fix next_timer_interrupt() for hrtimer Also from Thomas Gleixner Function next_timer_interrupt() got broken with a recent patch 6ba1b91213e81aa92b5cf7539f7d2a94ff54947c as sys_nanosleep() was moved to hrtimer. This broke things as next_timer_interrupt() did not check hrtimer tree for next event. Function next_timer_interrupt() is needed with dyntick (CONFIG_NO_IDLE_HZ, VST) implementations, as the system can be in idle when next hrtimer event was supposed to happen. At least ARM and S390 currently use next_timer_interrupt(). Signed-off-by: Thomas Gleixner Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hrtimer.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 6361544bb6ae..6401c31d6add 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -116,6 +116,10 @@ extern int hrtimer_try_to_cancel(struct hrtimer *timer); extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer); extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp); +#ifdef CONFIG_NO_IDLE_HZ +extern ktime_t hrtimer_get_next_event(void); +#endif + static inline int hrtimer_active(const struct hrtimer *timer) { return timer->state == HRTIMER_PENDING; -- cgit v1.2.3 From 78679302fe428f4f3dc853a51ee24f306010d874 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Mon, 6 Mar 2006 15:42:49 -0800 Subject: [PATCH] memory-hotplug compile fix include/linux/memory_hotplug.h:53: warning: 'struct page' declared inside parameter list (akpm: I tossed in a couple more possibly-needed-sometime struct decls too) Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 01f03bc06eff..968b1aa3732c 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -6,6 +6,10 @@ #include #include +struct page; +struct zone; +struct pglist_data; + #ifdef CONFIG_MEMORY_HOTPLUG /* * pgdat resizing functions -- cgit v1.2.3 From a615fa83959896f8eac76c235953fb164cd1a9b9 Mon Sep 17 00:00:00 2001 From: Jack Steiner Date: Mon, 6 Mar 2006 15:42:50 -0800 Subject: [PATCH] Increase max kmalloc size for very large systems Systems with extemely large numbers of nodes or cpus need to kmalloc structures larger than is currently supported. This patch increases the maximum supported size for very large systems. This patch should have no effect on current systems. (akpm: why not just use alloc_pages() for sysfs_cpus?) Signed-off-by: Jack Steiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kmalloc_sizes.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kmalloc_sizes.h b/include/linux/kmalloc_sizes.h index d82d4c05c12d..bda23e00ed71 100644 --- a/include/linux/kmalloc_sizes.h +++ b/include/linux/kmalloc_sizes.h @@ -19,8 +19,10 @@ CACHE(32768) CACHE(65536) CACHE(131072) -#ifndef CONFIG_MMU +#if (NR_CPUS > 512) || (MAX_NUMNODES > 256) || !defined(CONFIG_MMU) CACHE(262144) +#endif +#ifndef CONFIG_MMU CACHE(524288) CACHE(1048576) #ifdef CONFIG_LARGE_ALLOCS -- cgit v1.2.3 From a19cbd4bf258840ade3b6ee9e9256006d0644e09 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 8 Mar 2006 14:03:09 -0800 Subject: Mark the pipe file operations static They aren't used (nor even really usable) outside of pipe.c anyway Signed-off-by: Linus Torvalds --- include/linux/fs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e059da947007..0cc34b1c42c9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1418,9 +1418,6 @@ extern int is_bad_inode(struct inode *); extern struct file_operations read_fifo_fops; extern struct file_operations write_fifo_fops; extern struct file_operations rdwr_fifo_fops; -extern struct file_operations read_pipe_fops; -extern struct file_operations write_pipe_fops; -extern struct file_operations rdwr_pipe_fops; extern int fs_may_remount_ro(struct super_block *); -- cgit v1.2.3 From e2bab3d92486fb781f4d06f56339264ed1492392 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 7 Mar 2006 21:55:31 -0800 Subject: [PATCH] percpu_counter_sum() Implement percpu_counter_sum(). This is a more accurate but slower version of percpu_counter_read_positive(). We need this for Alex's speedup-ext3_statfs patch and for the nr_file accounting fix. Otherwise these things would be too inaccurate on large CPU counts. Cc: Ravikiran G Thirumalai Cc: Alex Tomas Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/percpu_counter.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index bd6708e2c027..682525511c9e 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -39,6 +39,7 @@ static inline void percpu_counter_destroy(struct percpu_counter *fbc) } void percpu_counter_mod(struct percpu_counter *fbc, long amount); +long percpu_counter_sum(struct percpu_counter *fbc); static inline long percpu_counter_read(struct percpu_counter *fbc) { @@ -92,6 +93,11 @@ static inline long percpu_counter_read_positive(struct percpu_counter *fbc) return fbc->count; } +static inline long percpu_counter_sum(struct percpu_counter *fbc) +{ + return percpu_counter_read_positive(fbc); +} + #endif /* CONFIG_SMP */ static inline void percpu_counter_inc(struct percpu_counter *fbc) -- cgit v1.2.3 From 21a1ea9eb40411d4ee29448c53b9e4c0654d6ceb Mon Sep 17 00:00:00 2001 From: Dipankar Sarma Date: Tue, 7 Mar 2006 21:55:33 -0800 Subject: [PATCH] rcu batch tuning This patch adds new tunables for RCU queue and finished batches. There are two types of controls - number of completed RCU updates invoked in a batch (blimit) and monitoring for high rate of incoming RCUs on a cpu (qhimark, qlowmark). By default, the per-cpu batch limit is set to a small value. If the input RCU rate exceeds the high watermark, we do two things - force quiescent state on all cpus and set the batch limit of the CPU to INTMAX. Setting batch limit to INTMAX forces all finished RCUs to be processed in one shot. If we have more than INTMAX RCUs queued up, then we have bigger problems anyway. Once the incoming queued RCUs fall below the low watermark, the batch limit is set to the default. Signed-off-by: Dipankar Sarma Cc: "Paul E. McKenney" Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rcupdate.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index b87aefa082e2..c2ec6c77874e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -98,13 +98,17 @@ struct rcu_data { long batch; /* Batch # for current RCU batch */ struct rcu_head *nxtlist; struct rcu_head **nxttail; - long count; /* # of queued items */ + long qlen; /* # of queued callbacks */ struct rcu_head *curlist; struct rcu_head **curtail; struct rcu_head *donelist; struct rcu_head **donetail; + long blimit; /* Upper limit on a processed batch */ int cpu; struct rcu_head barrier; +#ifdef CONFIG_SMP + long last_rs_qlen; /* qlen during the last resched */ +#endif }; DECLARE_PER_CPU(struct rcu_data, rcu_data); -- cgit v1.2.3 From 529bf6be5c04f2e869d07bfdb122e9fd98ade714 Mon Sep 17 00:00:00 2001 From: Dipankar Sarma Date: Tue, 7 Mar 2006 21:55:35 -0800 Subject: [PATCH] fix file counting I have benchmarked this on an x86_64 NUMA system and see no significant performance difference on kernbench. Tested on both x86_64 and powerpc. The way we do file struct accounting is not very suitable for batched freeing. For scalability reasons, file accounting was constructor/destructor based. This meant that nr_files was decremented only when the object was removed from the slab cache. This is susceptible to slab fragmentation. With RCU based file structure, consequent batched freeing and a test program like Serge's, we just speed this up and end up with a very fragmented slab - llm22:~ # cat /proc/sys/fs/file-nr 587730 0 758844 At the same time, I see only a 2000+ objects in filp cache. The following patch I fixes this problem. This patch changes the file counting by removing the filp_count_lock. Instead we use a separate percpu counter, nr_files, for now and all accesses to it are through get_nr_files() api. In the sysctl handler for nr_files, we populate files_stat.nr_files before returning to user. Counting files as an when they are created and destroyed (as opposed to inside slab) allows us to correctly count open files with RCU. Signed-off-by: Dipankar Sarma Cc: "Paul E. McKenney" Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/file.h | 2 -- include/linux/fs.h | 1 + 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 418b6101b59a..9901b850f2e4 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -60,8 +60,6 @@ extern void put_filp(struct file *); extern int get_unused_fd(void); extern void FASTCALL(put_unused_fd(unsigned int fd)); struct kmem_cache; -extern void filp_ctor(void * objp, struct kmem_cache *cachep, unsigned long cflags); -extern void filp_dtor(void * objp, struct kmem_cache *cachep, unsigned long dflags); extern struct file ** alloc_fd_array(int); extern void free_fd_array(struct file **, int); diff --git a/include/linux/fs.h b/include/linux/fs.h index 0cc34b1c42c9..51c0c93bdf93 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -35,6 +35,7 @@ struct files_stat_struct { int max_files; /* tunable */ }; extern struct files_stat_struct files_stat; +extern int get_max_files(void); struct inodes_stat_t { int nr_inodes; -- cgit v1.2.3 From 0ef675d491bd65028fa838015ebc6ce8abefab6f Mon Sep 17 00:00:00 2001 From: Atsushi Nemoto Date: Thu, 9 Mar 2006 17:33:38 -0800 Subject: [PATCH] mtd: 64 bit fixes Fix some bugs in mtd/jffs2 on 64bit platform. The MEMGETBADBLOCK/MEMSETBADBLOCK ioctl are not listed in compat_ioctl.h. And some variables in jffs2 are declared as uint32_t but used to hold size_t values. Signed-off-by: Atsushi Nemoto Cc: Thomas Gleixner Acked-by: David Woodhouse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat_ioctl.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h index 8fad50f8e389..ae7dfb790df3 100644 --- a/include/linux/compat_ioctl.h +++ b/include/linux/compat_ioctl.h @@ -696,6 +696,8 @@ COMPATIBLE_IOCTL(MEMLOCK) COMPATIBLE_IOCTL(MEMUNLOCK) COMPATIBLE_IOCTL(MEMGETREGIONCOUNT) COMPATIBLE_IOCTL(MEMGETREGIONINFO) +COMPATIBLE_IOCTL(MEMGETBADBLOCK) +COMPATIBLE_IOCTL(MEMSETBADBLOCK) /* NBD */ ULONG_IOCTL(NBD_SET_SOCK) ULONG_IOCTL(NBD_SET_BLKSIZE) -- cgit v1.2.3 From 8fce4d8e3b9e3cf47cc8afeb6077e22ab795d989 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 9 Mar 2006 17:33:54 -0800 Subject: [PATCH] slab: Node rotor for freeing alien caches and remote per cpu pages. The cache reaper currently tries to free all alien caches and all remote per cpu pages in each pass of cache_reap. For a machines with large number of nodes (such as Altix) this may lead to sporadic delays of around ~10ms. Interrupts are disabled while reclaiming creating unacceptable delays. This patch changes that behavior by adding a per cpu reap_node variable. Instead of attempting to free all caches, we free only one alien cache and the per cpu pages from one remote node. That reduces the time spend in cache_reap. However, doing so will lengthen the time it takes to completely drain all remote per cpu pagesets and all alien caches. The time needed will grow with the number of nodes in the system. All caches are drained when they overflow their respective capacity. So the drawback here is only that a bit of memory may be wasted for awhile longer. Details: 1. Rename drain_remote_pages to drain_node_pages to allow the specification of the node to drain of pcp pages. 2. Add additional functions init_reap_node, next_reap_node for NUMA that manage a per cpu reap_node counter. 3. Add a reap_alien function that reaps only from the current reap_node. For us this seems to be a critical issue. Holdoffs of an average of ~7ms cause some HPC benchmarks to slow down significantly. F.e. NAS parallel slows down dramatically. NAS parallel has a 12-16 seconds runtime w/o rotor compared to 5.8 secs with the rotor patches. It gets down to 5.05 secs with the additional interrupt holdoff reductions. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 20f9148e38d9..7851e6b520cf 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -157,9 +157,9 @@ extern void FASTCALL(free_cold_page(struct page *page)); void page_alloc_init(void); #ifdef CONFIG_NUMA -void drain_remote_pages(void); +void drain_node_pages(int node); #else -static inline void drain_remote_pages(void) { }; +static inline void drain_node_pages(int node) { }; #endif #endif /* __LINUX_GFP_H */ -- cgit v1.2.3 From 0adb25d2e71ab047423d6fc63d5d184590d0a66f Mon Sep 17 00:00:00 2001 From: Kirill Korotaev Date: Sat, 11 Mar 2006 03:27:13 -0800 Subject: [PATCH] ext3: ext3_symlink should use GFP_NOFS allocations inside This patch fixes illegal __GFP_FS allocation inside ext3 transaction in ext3_symlink(). Such allocation may re-enter ext3 code from try_to_free_pages. But JBD/ext3 code keeps a pointer to current journal handle in task_struct and, hence, is not reentrable. This bug led to "Assertion failure in journal_dirty_metadata()" messages. http://bugzilla.openvz.org/show_bug.cgi?id=115 Signed-off-by: Andrey Savochkin Signed-off-by: Kirill Korotaev Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 51c0c93bdf93..128d0082522c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1664,6 +1664,8 @@ extern int vfs_follow_link(struct nameidata *, const char *); extern int page_readlink(struct dentry *, char __user *, int); extern void *page_follow_link_light(struct dentry *, struct nameidata *); extern void page_put_link(struct dentry *, struct nameidata *, void *); +extern int __page_symlink(struct inode *inode, const char *symname, int len, + gfp_t gfp_mask); extern int page_symlink(struct inode *inode, const char *symname, int len); extern struct inode_operations page_symlink_inode_operations; extern int generic_readlink(struct dentry *, char __user *, int); -- cgit v1.2.3 From 7cd9013be6c22f3ff6f777354f766c8c0b955e17 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 11 Mar 2006 03:27:18 -0800 Subject: [PATCH] remove __put_task_struct_cb export again The patch '[PATCH] RCU signal handling' [1] added an export for __put_task_struct_cb, a put_task_struct helper newly introduced in that patch. But the put_task_struct couldn't be used modular previously as __put_task_struct wasn't exported. There are not callers of it in modular code, and it shouldn't be exported because we don't want drivers to hold references to task_structs. This patch removes the export and folds __put_task_struct into __put_task_struct_cb as there's no other caller. [1] http://www2.kernel.org/git/gitweb.cgi?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=e56d090310d7625ecb43a1eeebd479f04affb48b Signed-off-by: Christoph Hellwig Acked-by: Paul E. McKenney Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ff2e09c953b9..62e6314382f0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -892,7 +892,6 @@ static inline int pid_alive(struct task_struct *p) } extern void free_task(struct task_struct *tsk); -extern void __put_task_struct(struct task_struct *tsk); #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0) extern void __put_task_struct_cb(struct rcu_head *rhp); -- cgit v1.2.3 From 4a29cc2e503b33a1e96db4c3f9a94165f153f259 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sun, 19 Mar 2006 13:21:12 -0800 Subject: [TG3]: 40-bit DMA workaround part 2 The 40-bit DMA workaround recently implemented for 5714, 5715, and 5780 needs to be expanded because there may be other tg3 devices behind the EPB Express to PCIX bridge in the 5780 class device. For example, some 4-port card or mother board designs have 5704 behind the 5714. All devices behind the EPB require the 40-bit DMA workaround. Thanks to Chris Elmquist again for reporting the problem and testing the patch. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 1709b5009d2e..751eea58bde8 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1365,6 +1365,7 @@ #define PCI_DEVICE_ID_SERVERWORKS_HE 0x0008 #define PCI_DEVICE_ID_SERVERWORKS_LE 0x0009 #define PCI_DEVICE_ID_SERVERWORKS_GCNB_LE 0x0017 +#define PCI_DEVICE_ID_SERVERWORKS_EPB 0x0103 #define PCI_DEVICE_ID_SERVERWORKS_OSB4 0x0200 #define PCI_DEVICE_ID_SERVERWORKS_CSB5 0x0201 #define PCI_DEVICE_ID_SERVERWORKS_CSB6 0x0203 -- cgit v1.2.3