From 8e1a4857cd92e32e642b3e7184c7f6bf85c96e2e Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 6 Jan 2009 14:53:06 -0500 Subject: Update Documentation/filesystems/ext4.txt Fix paragraph with recommendations on how to tune ext4 for benchmarks. Signed-off-by: "Theodore Ts'o" --- Documentation/filesystems/ext4.txt | 42 +++++++++++++++++++++++++++++--------- 1 file changed, 32 insertions(+), 10 deletions(-) (limited to 'Documentation') diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index 174eaff7ded9..f75ab101c00a 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -58,13 +58,22 @@ Note: More extensive information for getting started with ext4 can be # mount -t ext4 /dev/hda1 /wherever - - When comparing performance with other filesystems, remember that - ext3/4 by default offers higher data integrity guarantees than most. - So when comparing with a metadata-only journalling filesystem, such - as ext3, use `mount -o data=writeback'. And you might as well use - `mount -o nobh' too along with it. Making the journal larger than - the mke2fs default often helps performance with metadata-intensive - workloads. + - When comparing performance with other filesystems, it's always + important to try multiple workloads; very often a subtle change in a + workload parameter can completely change the ranking of which + filesystems do well compared to others. When comparing versus ext3, + note that ext4 enables write barriers by default, while ext3 does + not enable write barriers by default. So it is useful to use + explicitly specify whether barriers are enabled or not when via the + '-o barriers=[0|1]' mount option for both ext3 and ext4 filesystems + for a fair comparison. When tuning ext3 for best benchmark numbers, + it is often worthwhile to try changing the data journaling mode; '-o + data=writeback,nobh' can be faster for some workloads. (Note + however that running mounted with data=writeback can potentially + leave stale data exposed in recently written files in case of an + unclean shutdown, which could be a security exposure in some + situations.) Configuring the filesystem with a large journal can + also be helpful for metadata-intensive workloads. 2. Features =========== @@ -74,7 +83,7 @@ Note: More extensive information for getting started with ext4 can be * ability to use filesystems > 16TB (e2fsprogs support not available yet) * extent format reduces metadata overhead (RAM, IO for access, transactions) * extent format more robust in face of on-disk corruption due to magics, -* internal redunancy in tree +* internal redundancy in tree * improved file allocation (multi-block alloc) * fix 32000 subdirectory limit * nsec timestamps for mtime, atime, ctime, create time @@ -116,6 +125,12 @@ grouping of bitmaps and inode tables. Some test results available here: When mounting an ext4 filesystem, the following option are accepted: (*) == default +ro Mount filesystem read only. Note that ext4 will + replay the journal (and thus write to the + partition) even when mounted "read only". The + mount options "ro,noload" can be used to prevent + writes to the filesystem. + extents (*) ext4 will use extents to address file data. The file system will no longer be mountable by ext3. @@ -144,7 +159,11 @@ journal_dev=devnum When the external journal device's major/minor numbers identified through its new major/minor numbers encoded in devnum. -noload Don't load the journal on mounting. +noload Don't load the journal on mounting. Note that + if the filesystem was not unmounted cleanly, + skipping the journal replay will lead to the + filesystem containing inconsistencies that can + lead to any number of problems. data=journal All data are committed into the journal prior to being written into the main file system. @@ -219,9 +238,12 @@ minixdf Make 'df' act like Minix. debug Extra debugging information is sent to syslog. -errors=remount-ro(*) Remount the filesystem read-only on an error. +errors=remount-ro Remount the filesystem read-only on an error. errors=continue Keep going on a filesystem error. errors=panic Panic and halt the machine if an error occurs. + (These mount options override the errors behavior + specified in the superblock, which can be configured + using tune2fs) data_err=ignore(*) Just print an error message if an error occurs in a file data buffer in ordered mode. -- cgit v1.2.3 From 30773840c19cea60dcef39545960d541b1ac1cf8 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 3 Jan 2009 20:27:38 -0500 Subject: ext4: add fsync batch tuning knobs Add new mount options, min_batch_time and max_batch_time, which controls how long the jbd2 layer should wait for additional filesystem operations to get batched with a synchronous write transaction. Signed-off-by: "Theodore Ts'o" --- Documentation/filesystems/ext4.txt | 29 +++++++++++++++++++++++ fs/ext4/ext4.h | 7 ++++++ fs/ext4/ext4_sb.h | 2 ++ fs/ext4/super.c | 47 ++++++++++++++++++++++++++++++++------ fs/jbd2/journal.c | 2 ++ fs/jbd2/transaction.c | 4 +++- include/linux/jbd2.h | 8 +++++++ 7 files changed, 91 insertions(+), 8 deletions(-) (limited to 'Documentation') diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index f75ab101c00a..e3fcbea3ec8c 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -283,6 +283,35 @@ delalloc (*) Deferring block allocation until write-out time. nodelalloc Disable delayed allocation. Blocks are allocation when data is copied from user to page cache. +max_batch_time=usec Maximum amount of time ext4 should wait for + additional filesystem operations to be batch + together with a synchronous write operation. + Since a synchronous write operation is going to + force a commit and then a wait for the I/O + complete, it doesn't cost much, and can be a + huge throughput win, we wait for a small amount + of time to see if any other transactions can + piggyback on the synchronous write. The + algorithm used is designed to automatically tune + for the speed of the disk, by measuring the + amount of time (on average) that it takes to + finish committing a transaction. Call this time + the "commit time". If the time that the + transactoin has been running is less than the + commit time, ext4 will try sleeping for the + commit time to see if other operations will join + the transaction. The commit time is capped by + the max_batch_time, which defaults to 15000us + (15ms). This optimization can be turned off + entirely by setting max_batch_time to 0. + +min_batch_time=usec This parameter sets the commit time (as + described above) to be at least min_batch_time. + It defaults to zero microseconds. Increasing + this parameter may improve the throughput of + multi-threaded, synchronous workloads on very + fast disks, at the cost of increasing latency. + Data Mode ========= There are 3 different data modes: diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index ac8551e0b70a..9ba9fd6d14da 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -328,6 +328,7 @@ struct ext4_mount_options { uid_t s_resuid; gid_t s_resgid; unsigned long s_commit_interval; + u32 s_min_batch_time, s_max_batch_time; #ifdef CONFIG_QUOTA int s_jquota_fmt; char *s_qf_names[MAXQUOTAS]; @@ -805,6 +806,12 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) #define EXT4_DEFM_JMODE_ORDERED 0x0040 #define EXT4_DEFM_JMODE_WBACK 0x0060 +/* + * Default journal batch times + */ +#define EXT4_DEF_MIN_BATCH_TIME 0 +#define EXT4_DEF_MAX_BATCH_TIME 15000 /* 15ms */ + /* * Structure of a directory entry */ diff --git a/fs/ext4/ext4_sb.h b/fs/ext4/ext4_sb.h index 3db800f399a6..039b6ea1a042 100644 --- a/fs/ext4/ext4_sb.h +++ b/fs/ext4/ext4_sb.h @@ -74,6 +74,8 @@ struct ext4_sb_info { struct journal_s *s_journal; struct list_head s_orphan; unsigned long s_commit_interval; + u32 s_max_batch_time; + u32 s_min_batch_time; struct block_device *journal_bdev; #ifdef CONFIG_JBD2_DEBUG struct timer_list turn_ro_timer; /* For turning read-only (crash simulation) */ diff --git a/fs/ext4/super.c b/fs/ext4/super.c index dc27d4c613c0..da377f9521bb 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -705,10 +705,19 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) #endif if (!test_opt(sb, RESERVATION)) seq_puts(seq, ",noreservation"); - if (sbi->s_commit_interval) { + if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) { seq_printf(seq, ",commit=%u", (unsigned) (sbi->s_commit_interval / HZ)); } + if (sbi->s_min_batch_time != EXT4_DEF_MIN_BATCH_TIME) { + seq_printf(seq, ",min_batch_time=%u", + (unsigned) sbi->s_min_batch_time); + } + if (sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) { + seq_printf(seq, ",max_batch_time=%u", + (unsigned) sbi->s_min_batch_time); + } + /* * We're changing the default of barrier mount option, so * let's always display its mount state so it's clear what its @@ -874,7 +883,8 @@ enum { Opt_nouid32, Opt_debug, Opt_oldalloc, Opt_orlov, Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl, Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh, - Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev, + Opt_commit, Opt_min_batch_time, Opt_max_batch_time, + Opt_journal_update, Opt_journal_inum, Opt_journal_dev, Opt_journal_checksum, Opt_journal_async_commit, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, Opt_data_err_abort, Opt_data_err_ignore, @@ -913,6 +923,8 @@ static const match_table_t tokens = { {Opt_nobh, "nobh"}, {Opt_bh, "bh"}, {Opt_commit, "commit=%u"}, + {Opt_min_batch_time, "min_batch_time=%u"}, + {Opt_max_batch_time, "max_batch_time=%u"}, {Opt_journal_update, "journal=update"}, {Opt_journal_inum, "journal=%u"}, {Opt_journal_dev, "journal_dev=%u"}, @@ -1131,6 +1143,22 @@ static int parse_options(char *options, struct super_block *sb, option = JBD2_DEFAULT_MAX_COMMIT_AGE; sbi->s_commit_interval = HZ * option; break; + case Opt_max_batch_time: + if (match_int(&args[0], &option)) + return 0; + if (option < 0) + return 0; + if (option == 0) + option = EXT4_DEF_MAX_BATCH_TIME; + sbi->s_max_batch_time = option; + break; + case Opt_min_batch_time: + if (match_int(&args[0], &option)) + return 0; + if (option < 0) + return 0; + sbi->s_min_batch_time = option; + break; case Opt_data_journal: data_opt = EXT4_MOUNT_JOURNAL_DATA; goto datacheck; @@ -1979,6 +2007,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_resuid = le16_to_cpu(es->s_def_resuid); sbi->s_resgid = le16_to_cpu(es->s_def_resgid); + sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ; + sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME; + sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME; set_opt(sbi->s_mount_opt, RESERVATION); set_opt(sbi->s_mount_opt, BARRIER); @@ -2524,11 +2555,9 @@ static void ext4_init_journal_params(struct super_block *sb, journal_t *journal) { struct ext4_sb_info *sbi = EXT4_SB(sb); - if (sbi->s_commit_interval) - journal->j_commit_interval = sbi->s_commit_interval; - /* We could also set up an ext4-specific default for the commit - * interval here, but for now we'll just fall back to the jbd - * default. */ + journal->j_commit_interval = sbi->s_commit_interval; + journal->j_min_batch_time = sbi->s_min_batch_time; + journal->j_max_batch_time = sbi->s_max_batch_time; spin_lock(&journal->j_state_lock); if (test_opt(sb, BARRIER)) @@ -3042,6 +3071,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) old_opts.s_resuid = sbi->s_resuid; old_opts.s_resgid = sbi->s_resgid; old_opts.s_commit_interval = sbi->s_commit_interval; + old_opts.s_min_batch_time = sbi->s_min_batch_time; + old_opts.s_max_batch_time = sbi->s_max_batch_time; #ifdef CONFIG_QUOTA old_opts.s_jquota_fmt = sbi->s_jquota_fmt; for (i = 0; i < MAXQUOTAS; i++) @@ -3178,6 +3209,8 @@ restore_opts: sbi->s_resuid = old_opts.s_resuid; sbi->s_resgid = old_opts.s_resgid; sbi->s_commit_interval = old_opts.s_commit_interval; + sbi->s_min_batch_time = old_opts.s_min_batch_time; + sbi->s_max_batch_time = old_opts.s_max_batch_time; #ifdef CONFIG_QUOTA sbi->s_jquota_fmt = old_opts.s_jquota_fmt; for (i = 0; i < MAXQUOTAS; i++) { diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 74d87290381c..fd1d7557a098 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -964,6 +964,8 @@ static journal_t * journal_init_common (void) spin_lock_init(&journal->j_state_lock); journal->j_commit_interval = (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE); + journal->j_min_batch_time = 0; + journal->j_max_batch_time = 15000; /* 15ms */ /* The journal is marked for error until we succeed with recovery! */ journal->j_flags = JBD2_ABORT; diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 13dcbc990f41..48c21bac5a56 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1255,8 +1255,10 @@ int jbd2_journal_stop(handle_t *handle) trans_time = ktime_to_ns(ktime_sub(ktime_get(), transaction->t_start_time)); + commit_time = max_t(u64, commit_time, + 1000*journal->j_min_batch_time); commit_time = min_t(u64, commit_time, - 1000*jiffies_to_usecs(1)); + 1000*journal->j_max_batch_time); if (trans_time < commit_time) { ktime_t expires = ktime_add_ns(ktime_get(), diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index ab8cef130c28..a3cd647ea1bc 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -956,6 +956,14 @@ struct journal_s */ u64 j_average_commit_time; + /* + * minimum and maximum times that we should wait for + * additional filesystem operations to get batched into a + * synchronous handle in microseconds + */ + u32 j_min_batch_time; + u32 j_max_batch_time; + /* This function is called when a transaction is closed */ void (*j_commit_callback)(journal_t *, transaction_t *); -- cgit v1.2.3 From cec87e38e92cdfe86678ca2a5c29c38d05127601 Mon Sep 17 00:00:00 2001 From: Peter Popovec Date: Tue, 11 Nov 2008 14:46:14 -0500 Subject: Input: add joystick driver for Walkera WK-0701 RC transmitter Signed-off-by: Peter Popovec Signed-off-by: Dmitry Torokhov --- Documentation/input/walkera0701.txt | 109 +++++++++++++ drivers/input/joystick/Kconfig | 12 ++ drivers/input/joystick/Makefile | 1 + drivers/input/joystick/walkera0701.c | 292 +++++++++++++++++++++++++++++++++++ 4 files changed, 414 insertions(+) create mode 100644 Documentation/input/walkera0701.txt create mode 100644 drivers/input/joystick/walkera0701.c (limited to 'Documentation') diff --git a/Documentation/input/walkera0701.txt b/Documentation/input/walkera0701.txt new file mode 100644 index 000000000000..8f4289efc5c4 --- /dev/null +++ b/Documentation/input/walkera0701.txt @@ -0,0 +1,109 @@ + +Walkera WK-0701 transmitter is supplied with a ready to fly Walkera +helicopters such as HM36, HM37, HM60. The walkera0701 module enables to use +this transmitter as joystick + +Devel homepage and download: +http://zub.fei.tuke.sk/walkera-wk0701/ + +or use cogito: +cg-clone http://zub.fei.tuke.sk/GIT/walkera0701-joystick + + +Connecting to PC: + +At back side of transmitter S-video connector can be found. Modulation +pulses from processor to HF part can be found at pin 2 of this connector, +pin 3 is GND. Between pin 3 and CPU 5k6 resistor can be found. To get +modulation pulses to PC, signal pulses must be amplified. + +Cable: (walkera TX to parport) + +Walkera WK-0701 TX S-VIDEO connector: + (back side of TX) + __ __ S-video: canon25 + / |_| \ pin 2 (signal) NPN parport + / O 4 3 O \ pin 3 (GND) LED ________________ 10 ACK + ( O 2 1 O ) | C + \ ___ / 2 ________________________|\|_____|/ + | [___] | |/| B |\ + ------- 3 __________________________________|________________ 25 GND + E + + +I use green LED and BC109 NPN transistor. + +Software: + +Build kernel with walkera0701 module. Module walkera0701 need exclusive +access to parport, modules like lp must be unloaded before loading +walkera0701 module, check dmesg for error messages. Connect TX to PC by +cable and run jstest /dev/input/js0 to see values from TX. If no value can +be changed by TX "joystick", check output from /proc/interrupts. Value for +(usually irq7) parport must increase if TX is on. + + + +Technical details: + +Driver use interrupt from parport ACK input bit to measure pulse length +using hrtimers. + +Frame format: +Based on walkera WK-0701 PCM Format description by Shaul Eizikovich. +(downloaded from http://www.smartpropoplus.com/Docs/Walkera_Wk-0701_PCM.pdf) + +Signal pulses: + (ANALOG) + SYNC BIN OCT + +---------+ +------+ + | | | | +--+ +------+ +--- + +Frame: + SYNC , BIN1, OCT1, BIN2, OCT2 ... BIN24, OCT24, BIN25, next frame SYNC .. + +pulse length: + Binary values: Analog octal values: + + 288 uS Binary 0 318 uS 000 + 438 uS Binary 1 398 uS 001 + 478 uS 010 + 558 uS 011 + 638 uS 100 + 1306 uS SYNC 718 uS 101 + 798 uS 110 + 878 uS 111 + +24 bin+oct values + 1 bin value = 24*4+1 bits = 97 bits + +(Warning, pulses on ACK ar inverted by transistor, irq is rised up on sync +to bin change or octal value to bin change). + +Binary data representations: + +One binary and octal value can be grouped to nibble. 24 nibbles + one binary +values can be sampled between sync pulses. + +Values for first four channels (analog joystick values) can be found in +first 10 nibbles. Analog value is represented by one sign bit and 9 bit +absolute binary value. (10 bits per channel). Next nibble is checksum for +first ten nibbles. + +Next nibbles 12 .. 21 represents four channels (not all channels can be +directly controlled from TX). Binary representations ar the same as in first +four channels. In nibbles 22 and 23 is a special magic number. Nibble 24 is +checksum for nibbles 12..23. + +After last octal value for nibble 24 and next sync pulse one additional +binary value can be sampled. This bit and magic number is not used in +software driver. Some details about this magic numbers can be found in +Walkera_Wk-0701_PCM.pdf. + +Checksum calculation: + +Summary of octal values in nibbles must be same as octal value in checksum +nibble (only first 3 bits are used). Binary value for checksum nibble is +calculated by sum of binary values in checked nibbles + sum of octal values +in checked nibbles divided by 8. Only bit 0 of this sum is used. + diff --git a/drivers/input/joystick/Kconfig b/drivers/input/joystick/Kconfig index be5c14a5a0a4..268dd3fef0ab 100644 --- a/drivers/input/joystick/Kconfig +++ b/drivers/input/joystick/Kconfig @@ -294,4 +294,16 @@ config JOYSTICK_XPAD_LEDS This option enables support for the LED which surrounds the Big X on XBox 360 controller. +config JOYSTICK_WALKERA0701 + tristate "Walkera WK-0701 RC transmitter" + depends on HIGH_RES_TIMERS && PARPORT + help + Say Y or M here if you have a Walkera WK-0701 transmitter which is + supplied with a ready to fly Walkera helicopters such as HM36, + HM37, HM60 and want to use it via parport as a joystick. More + information is available: + + To compile this driver as a module, choose M here: the + module will be called walkera0701. + endif diff --git a/drivers/input/joystick/Makefile b/drivers/input/joystick/Makefile index fdbf8c4c2876..723036295685 100644 --- a/drivers/input/joystick/Makefile +++ b/drivers/input/joystick/Makefile @@ -29,4 +29,5 @@ obj-$(CONFIG_JOYSTICK_TWIDJOY) += twidjoy.o obj-$(CONFIG_JOYSTICK_WARRIOR) += warrior.o obj-$(CONFIG_JOYSTICK_XPAD) += xpad.o obj-$(CONFIG_JOYSTICK_ZHENHUA) += zhenhua.o +obj-$(CONFIG_JOYSTICK_WALKERA0701) += walkera0701.o diff --git a/drivers/input/joystick/walkera0701.c b/drivers/input/joystick/walkera0701.c new file mode 100644 index 000000000000..4dfa1eed4b7c --- /dev/null +++ b/drivers/input/joystick/walkera0701.c @@ -0,0 +1,292 @@ +/* + * Parallel port to Walkera WK-0701 TX joystick + * + * Copyright (c) 2008 Peter Popovec + * + * More about driver: + */ + +/* + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. +*/ + +/* #define WK0701_DEBUG */ + +#define RESERVE 20000 +#define SYNC_PULSE 1306000 +#define BIN0_PULSE 288000 +#define BIN1_PULSE 438000 + +#define ANALOG_MIN_PULSE 318000 +#define ANALOG_MAX_PULSE 878000 +#define ANALOG_DELTA 80000 + +#define BIN_SAMPLE ((BIN0_PULSE + BIN1_PULSE) / 2) + +#define NO_SYNC 25 + +#include +#include +#include +#include +#include + +MODULE_AUTHOR("Peter Popovec "); +MODULE_DESCRIPTION("Walkera WK-0701 TX as joystick"); +MODULE_LICENSE("GPL"); + +static unsigned int walkera0701_pp_no; +module_param_named(port, walkera0701_pp_no, int, 0); +MODULE_PARM_DESC(port, + "Parallel port adapter for Walkera WK-0701 TX (default is 0)"); + +/* + * For now, only one device is supported, if somebody need more devices, code + * can be expanded, one struct walkera_dev per device must be allocated and + * set up by walkera0701_connect (release of device by walkera0701_disconnect) + */ + +struct walkera_dev { + unsigned char buf[25]; + u64 irq_time, irq_lasttime; + int counter; + int ack; + + struct input_dev *input_dev; + struct hrtimer timer; + + struct parport *parport; + struct pardevice *pardevice; +}; + +static struct walkera_dev w_dev; + +static inline void walkera0701_parse_frame(struct walkera_dev *w) +{ + int i; + int val1, val2, val3, val4, val5, val6, val7, val8; + int crc1, crc2; + + for (crc1 = crc2 = i = 0; i < 10; i++) { + crc1 += w->buf[i] & 7; + crc2 += (w->buf[i] & 8) >> 3; + } + if ((w->buf[10] & 7) != (crc1 & 7)) + return; + if (((w->buf[10] & 8) >> 3) != (((crc1 >> 3) + crc2) & 1)) + return; + for (crc1 = crc2 = 0, i = 11; i < 23; i++) { + crc1 += w->buf[i] & 7; + crc2 += (w->buf[i] & 8) >> 3; + } + if ((w->buf[23] & 7) != (crc1 & 7)) + return; + if (((w->buf[23] & 8) >> 3) != (((crc1 >> 3) + crc2) & 1)) + return; + val1 = ((w->buf[0] & 7) * 256 + w->buf[1] * 16 + w->buf[2]) >> 2; + val1 *= ((w->buf[0] >> 2) & 2) - 1; /* sign */ + val2 = (w->buf[2] & 1) << 8 | (w->buf[3] << 4) | w->buf[4]; + val2 *= (w->buf[2] & 2) - 1; /* sign */ + val3 = ((w->buf[5] & 7) * 256 + w->buf[6] * 16 + w->buf[7]) >> 2; + val3 *= ((w->buf[5] >> 2) & 2) - 1; /* sign */ + val4 = (w->buf[7] & 1) << 8 | (w->buf[8] << 4) | w->buf[9]; + val4 *= (w->buf[7] & 2) - 1; /* sign */ + val5 = ((w->buf[11] & 7) * 256 + w->buf[12] * 16 + w->buf[13]) >> 2; + val5 *= ((w->buf[11] >> 2) & 2) - 1; /* sign */ + val6 = (w->buf[13] & 1) << 8 | (w->buf[14] << 4) | w->buf[15]; + val6 *= (w->buf[13] & 2) - 1; /* sign */ + val7 = ((w->buf[16] & 7) * 256 + w->buf[17] * 16 + w->buf[18]) >> 2; + val7 *= ((w->buf[16] >> 2) & 2) - 1; /*sign */ + val8 = (w->buf[18] & 1) << 8 | (w->buf[19] << 4) | w->buf[20]; + val8 *= (w->buf[18] & 2) - 1; /*sign */ + +#ifdef WK0701_DEBUG + { + int magic, magic_bit; + magic = (w->buf[21] << 4) | w->buf[22]; + magic_bit = (w->buf[24] & 8) >> 3; + printk(KERN_DEBUG + "walkera0701: %4d %4d %4d %4d %4d %4d %4d %4d (magic %2x %d)\n", + val1, val2, val3, val4, val5, val6, val7, val8, magic, + magic_bit); + } +#endif + input_report_abs(w->input_dev, ABS_X, val2); + input_report_abs(w->input_dev, ABS_Y, val1); + input_report_abs(w->input_dev, ABS_Z, val6); + input_report_abs(w->input_dev, ABS_THROTTLE, val3); + input_report_abs(w->input_dev, ABS_RUDDER, val4); + input_report_abs(w->input_dev, ABS_MISC, val7); + input_report_key(w->input_dev, BTN_GEAR_DOWN, val5 > 0); +} + +static inline int read_ack(struct pardevice *p) +{ + return parport_read_status(p->port) & 0x40; +} + +/* falling edge, prepare to BIN value calculation */ +static void walkera0701_irq_handler(void *handler_data) +{ + u64 pulse_time; + struct walkera_dev *w = handler_data; + + w->irq_time = ktime_to_ns(ktime_get()); + pulse_time = w->irq_time - w->irq_lasttime; + w->irq_lasttime = w->irq_time; + + /* cancel timer, if in handler or active do resync */ + if (unlikely(0 != hrtimer_try_to_cancel(&w->timer))) { + w->counter = NO_SYNC; + return; + } + + if (w->counter < NO_SYNC) { + if (w->ack) { + pulse_time -= BIN1_PULSE; + w->buf[w->counter] = 8; + } else { + pulse_time -= BIN0_PULSE; + w->buf[w->counter] = 0; + } + if (w->counter == 24) { /* full frame */ + walkera0701_parse_frame(w); + w->counter = NO_SYNC; + if (abs(pulse_time - SYNC_PULSE) < RESERVE) /* new frame sync */ + w->counter = 0; + } else { + if ((pulse_time > (ANALOG_MIN_PULSE - RESERVE) + && (pulse_time < (ANALOG_MAX_PULSE + RESERVE)))) { + pulse_time -= (ANALOG_MIN_PULSE - RESERVE); + pulse_time = (u32) pulse_time / ANALOG_DELTA; /* overtiping is safe, pulsetime < s32.. */ + w->buf[w->counter++] |= (pulse_time & 7); + } else + w->counter = NO_SYNC; + } + } else if (abs(pulse_time - SYNC_PULSE - BIN0_PULSE) < + RESERVE + BIN1_PULSE - BIN0_PULSE) /* frame sync .. */ + w->counter = 0; + + hrtimer_start(&w->timer, ktime_set(0, BIN_SAMPLE), HRTIMER_MODE_REL); +} + +static enum hrtimer_restart timer_handler(struct hrtimer + *handle) +{ + struct walkera_dev *w; + + w = container_of(handle, struct walkera_dev, timer); + w->ack = read_ack(w->pardevice); + + return HRTIMER_NORESTART; +} + +static int walkera0701_open(struct input_dev *dev) +{ + struct walkera_dev *w = input_get_drvdata(dev); + + parport_enable_irq(w->parport); + return 0; +} + +static void walkera0701_close(struct input_dev *dev) +{ + struct walkera_dev *w = input_get_drvdata(dev); + + parport_disable_irq(w->parport); +} + +static int walkera0701_connect(struct walkera_dev *w, int parport) +{ + int err = -ENODEV; + + w->parport = parport_find_number(parport); + if (w->parport == NULL) + return -ENODEV; + + if (w->parport->irq == -1) { + printk(KERN_ERR "walkera0701: parport without interrupt\n"); + goto init_err; + } + + err = -EBUSY; + w->pardevice = parport_register_device(w->parport, "walkera0701", + NULL, NULL, walkera0701_irq_handler, + PARPORT_DEV_EXCL, w); + if (!w->pardevice) + goto init_err; + + if (parport_negotiate(w->pardevice->port, IEEE1284_MODE_COMPAT)) + goto init_err1; + + if (parport_claim(w->pardevice)) + goto init_err1; + + w->input_dev = input_allocate_device(); + if (!w->input_dev) + goto init_err2; + + input_set_drvdata(w->input_dev, w); + w->input_dev->name = "Walkera WK-0701 TX"; + w->input_dev->phys = w->parport->name; + w->input_dev->id.bustype = BUS_PARPORT; + + /* TODO what id vendor/product/version ? */ + w->input_dev->id.vendor = 0x0001; + w->input_dev->id.product = 0x0001; + w->input_dev->id.version = 0x0100; + w->input_dev->open = walkera0701_open; + w->input_dev->close = walkera0701_close; + + w->input_dev->evbit[0] = BIT(EV_ABS) | BIT_MASK(EV_KEY); + w->input_dev->keybit[BIT_WORD(BTN_GEAR_DOWN)] = BIT_MASK(BTN_GEAR_DOWN); + + input_set_abs_params(w->input_dev, ABS_X, -512, 512, 0, 0); + input_set_abs_params(w->input_dev, ABS_Y, -512, 512, 0, 0); + input_set_abs_params(w->input_dev, ABS_Z, -512, 512, 0, 0); + input_set_abs_params(w->input_dev, ABS_THROTTLE, -512, 512, 0, 0); + input_set_abs_params(w->input_dev, ABS_RUDDER, -512, 512, 0, 0); + input_set_abs_params(w->input_dev, ABS_MISC, -512, 512, 0, 0); + + err = input_register_device(w->input_dev); + if (err) + goto init_err3; + + hrtimer_init(&w->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + w->timer.function = timer_handler; + return 0; + + init_err3: + input_free_device(w->input_dev); + init_err2: + parport_release(w->pardevice); + init_err1: + parport_unregister_device(w->pardevice); + init_err: + parport_put_port(w->parport); + return err; +} + +static void walkera0701_disconnect(struct walkera_dev *w) +{ + hrtimer_cancel(&w->timer); + input_unregister_device(w->input_dev); + parport_release(w->pardevice); + parport_unregister_device(w->pardevice); + parport_put_port(w->parport); +} + +static int __init walkera0701_init(void) +{ + return walkera0701_connect(&w_dev, walkera0701_pp_no); +} + +static void __exit walkera0701_exit(void) +{ + walkera0701_disconnect(&w_dev); +} + +module_init(walkera0701_init); +module_exit(walkera0701_exit); -- cgit v1.2.3 From 1c12757c56b4c9ab5aab1f6c1248ae4ea8af3a01 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 13 Nov 2008 18:11:52 -0800 Subject: Document RCU and unloadable modules Signed-off-by: Paul E. McKenney Reviewed-by: Lai Jiangshan Signed-off-by: Jonathan Corbet --- Documentation/RCU/00-INDEX | 2 + Documentation/RCU/rcubarrier.txt | 304 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 306 insertions(+) create mode 100644 Documentation/RCU/rcubarrier.txt (limited to 'Documentation') diff --git a/Documentation/RCU/00-INDEX b/Documentation/RCU/00-INDEX index 461481dfb7c3..0f2a8d081681 100644 --- a/Documentation/RCU/00-INDEX +++ b/Documentation/RCU/00-INDEX @@ -12,6 +12,8 @@ rcuref.txt - Reference-count design for elements of lists/arrays protected by RCU rcu.txt - RCU Concepts +rcubarrier.txt + - Unloading modules that use RCU callbacks RTFP.txt - List of RCU papers (bibliography) going back to 1980. torture.txt diff --git a/Documentation/RCU/rcubarrier.txt b/Documentation/RCU/rcubarrier.txt new file mode 100644 index 000000000000..909602d409bb --- /dev/null +++ b/Documentation/RCU/rcubarrier.txt @@ -0,0 +1,304 @@ +RCU and Unloadable Modules + +[Originally published in LWN Jan. 14, 2007: http://lwn.net/Articles/217484/] + +RCU (read-copy update) is a synchronization mechanism that can be thought +of as a replacement for read-writer locking (among other things), but with +very low-overhead readers that are immune to deadlock, priority inversion, +and unbounded latency. RCU read-side critical sections are delimited +by rcu_read_lock() and rcu_read_unlock(), which, in non-CONFIG_PREEMPT +kernels, generate no code whatsoever. + +This means that RCU writers are unaware of the presence of concurrent +readers, so that RCU updates to shared data must be undertaken quite +carefully, leaving an old version of the data structure in place until all +pre-existing readers have finished. These old versions are needed because +such readers might hold a reference to them. RCU updates can therefore be +rather expensive, and RCU is thus best suited for read-mostly situations. + +How can an RCU writer possibly determine when all readers are finished, +given that readers might well leave absolutely no trace of their +presence? There is a synchronize_rcu() primitive that blocks until all +pre-existing readers have completed. An updater wishing to delete an +element p from a linked list might do the following, while holding an +appropriate lock, of course: + + list_del_rcu(p); + synchronize_rcu(); + kfree(p); + +But the above code cannot be used in IRQ context -- the call_rcu() +primitive must be used instead. This primitive takes a pointer to an +rcu_head struct placed within the RCU-protected data structure and +another pointer to a function that may be invoked later to free that +structure. Code to delete an element p from the linked list from IRQ +context might then be as follows: + + list_del_rcu(p); + call_rcu(&p->rcu, p_callback); + +Since call_rcu() never blocks, this code can safely be used from within +IRQ context. The function p_callback() might be defined as follows: + + static void p_callback(struct rcu_head *rp) + { + struct pstruct *p = container_of(rp, struct pstruct, rcu); + + kfree(p); + } + + +Unloading Modules That Use call_rcu() + +But what if p_callback is defined in an unloadable module? + +If we unload the module while some RCU callbacks are pending, +the CPUs executing these callbacks are going to be severely +disappointed when they are later invoked, as fancifully depicted at +http://lwn.net/images/ns/kernel/rcu-drop.jpg. + +We could try placing a synchronize_rcu() in the module-exit code path, +but this is not sufficient. Although synchronize_rcu() does wait for a +grace period to elapse, it does not wait for the callbacks to complete. + +One might be tempted to try several back-to-back synchronize_rcu() +calls, but this is still not guaranteed to work. If there is a very +heavy RCU-callback load, then some of the callbacks might be deferred +in order to allow other processing to proceed. Such deferral is required +in realtime kernels in order to avoid excessive scheduling latencies. + + +rcu_barrier() + +We instead need the rcu_barrier() primitive. This primitive is similar +to synchronize_rcu(), but instead of waiting solely for a grace +period to elapse, it also waits for all outstanding RCU callbacks to +complete. Pseudo-code using rcu_barrier() is as follows: + + 1. Prevent any new RCU callbacks from being posted. + 2. Execute rcu_barrier(). + 3. Allow the module to be unloaded. + +Quick Quiz #1: Why is there no srcu_barrier()? + +The rcutorture module makes use of rcu_barrier in its exit function +as follows: + + 1 static void + 2 rcu_torture_cleanup(void) + 3 { + 4 int i; + 5 + 6 fullstop = 1; + 7 if (shuffler_task != NULL) { + 8 VERBOSE_PRINTK_STRING("Stopping rcu_torture_shuffle task"); + 9 kthread_stop(shuffler_task); +10 } +11 shuffler_task = NULL; +12 +13 if (writer_task != NULL) { +14 VERBOSE_PRINTK_STRING("Stopping rcu_torture_writer task"); +15 kthread_stop(writer_task); +16 } +17 writer_task = NULL; +18 +19 if (reader_tasks != NULL) { +20 for (i = 0; i < nrealreaders; i++) { +21 if (reader_tasks[i] != NULL) { +22 VERBOSE_PRINTK_STRING( +23 "Stopping rcu_torture_reader task"); +24 kthread_stop(reader_tasks[i]); +25 } +26 reader_tasks[i] = NULL; +27 } +28 kfree(reader_tasks); +29 reader_tasks = NULL; +30 } +31 rcu_torture_current = NULL; +32 +33 if (fakewriter_tasks != NULL) { +34 for (i = 0; i < nfakewriters; i++) { +35 if (fakewriter_tasks[i] != NULL) { +36 VERBOSE_PRINTK_STRING( +37 "Stopping rcu_torture_fakewriter task"); +38 kthread_stop(fakewriter_tasks[i]); +39 } +40 fakewriter_tasks[i] = NULL; +41 } +42 kfree(fakewriter_tasks); +43 fakewriter_tasks = NULL; +44 } +45 +46 if (stats_task != NULL) { +47 VERBOSE_PRINTK_STRING("Stopping rcu_torture_stats task"); +48 kthread_stop(stats_task); +49 } +50 stats_task = NULL; +51 +52 /* Wait for all RCU callbacks to fire. */ +53 rcu_barrier(); +54 +55 rcu_torture_stats_print(); /* -After- the stats thread is stopped! */ +56 +57 if (cur_ops->cleanup != NULL) +58 cur_ops->cleanup(); +59 if (atomic_read(&n_rcu_torture_error)) +60 rcu_torture_print_module_parms("End of test: FAILURE"); +61 else +62 rcu_torture_print_module_parms("End of test: SUCCESS"); +63 } + +Line 6 sets a global variable that prevents any RCU callbacks from +re-posting themselves. This will not be necessary in most cases, since +RCU callbacks rarely include calls to call_rcu(). However, the rcutorture +module is an exception to this rule, and therefore needs to set this +global variable. + +Lines 7-50 stop all the kernel tasks associated with the rcutorture +module. Therefore, once execution reaches line 53, no more rcutorture +RCU callbacks will be posted. The rcu_barrier() call on line 53 waits +for any pre-existing callbacks to complete. + +Then lines 55-62 print status and do operation-specific cleanup, and +then return, permitting the module-unload operation to be completed. + +Quick Quiz #2: Is there any other situation where rcu_barrier() might + be required? + +Your module might have additional complications. For example, if your +module invokes call_rcu() from timers, you will need to first cancel all +the timers, and only then invoke rcu_barrier() to wait for any remaining +RCU callbacks to complete. + + +Implementing rcu_barrier() + +Dipankar Sarma's implementation of rcu_barrier() makes use of the fact +that RCU callbacks are never reordered once queued on one of the per-CPU +queues. His implementation queues an RCU callback on each of the per-CPU +callback queues, and then waits until they have all started executing, at +which point, all earlier RCU callbacks are guaranteed to have completed. + +The original code for rcu_barrier() was as follows: + + 1 void rcu_barrier(void) + 2 { + 3 BUG_ON(in_interrupt()); + 4 /* Take cpucontrol mutex to protect against CPU hotplug */ + 5 mutex_lock(&rcu_barrier_mutex); + 6 init_completion(&rcu_barrier_completion); + 7 atomic_set(&rcu_barrier_cpu_count, 0); + 8 on_each_cpu(rcu_barrier_func, NULL, 0, 1); + 9 wait_for_completion(&rcu_barrier_completion); +10 mutex_unlock(&rcu_barrier_mutex); +11 } + +Line 3 verifies that the caller is in process context, and lines 5 and 10 +use rcu_barrier_mutex to ensure that only one rcu_barrier() is using the +global completion and counters at a time, which are initialized on lines +6 and 7. Line 8 causes each CPU to invoke rcu_barrier_func(), which is +shown below. Note that the final "1" in on_each_cpu()'s argument list +ensures that all the calls to rcu_barrier_func() will have completed +before on_each_cpu() returns. Line 9 then waits for the completion. + +This code was rewritten in 2008 to support rcu_barrier_bh() and +rcu_barrier_sched() in addition to the original rcu_barrier(). + +The rcu_barrier_func() runs on each CPU, where it invokes call_rcu() +to post an RCU callback, as follows: + + 1 static void rcu_barrier_func(void *notused) + 2 { + 3 int cpu = smp_processor_id(); + 4 struct rcu_data *rdp = &per_cpu(rcu_data, cpu); + 5 struct rcu_head *head; + 6 + 7 head = &rdp->barrier; + 8 atomic_inc(&rcu_barrier_cpu_count); + 9 call_rcu(head, rcu_barrier_callback); +10 } + +Lines 3 and 4 locate RCU's internal per-CPU rcu_data structure, +which contains the struct rcu_head that needed for the later call to +call_rcu(). Line 7 picks up a pointer to this struct rcu_head, and line +8 increments a global counter. This counter will later be decremented +by the callback. Line 9 then registers the rcu_barrier_callback() on +the current CPU's queue. + +The rcu_barrier_callback() function simply atomically decrements the +rcu_barrier_cpu_count variable and finalizes the completion when it +reaches zero, as follows: + + 1 static void rcu_barrier_callback(struct rcu_head *notused) + 2 { + 3 if (atomic_dec_and_test(&rcu_barrier_cpu_count)) + 4 complete(&rcu_barrier_completion); + 5 } + +Quick Quiz #3: What happens if CPU 0's rcu_barrier_func() executes + immediately (thus incrementing rcu_barrier_cpu_count to the + value one), but the other CPU's rcu_barrier_func() invocations + are delayed for a full grace period? Couldn't this result in + rcu_barrier() returning prematurely? + + +rcu_barrier() Summary + +The rcu_barrier() primitive has seen relatively little use, since most +code using RCU is in the core kernel rather than in modules. However, if +you are using RCU from an unloadable module, you need to use rcu_barrier() +so that your module may be safely unloaded. + + +Answers to Quick Quizzes + +Quick Quiz #1: Why is there no srcu_barrier()? + +Answer: Since there is no call_srcu(), there can be no outstanding SRCU + callbacks. Therefore, there is no need to wait for them. + +Quick Quiz #2: Is there any other situation where rcu_barrier() might + be required? + +Answer: Interestingly enough, rcu_barrier() was not originally + implemented for module unloading. Nikita Danilov was using + RCU in a filesystem, which resulted in a similar situation at + filesystem-unmount time. Dipankar Sarma coded up rcu_barrier() + in response, so that Nikita could invoke it during the + filesystem-unmount process. + + Much later, yours truly hit the RCU module-unload problem when + implementing rcutorture, and found that rcu_barrier() solves + this problem as well. + +Quick Quiz #3: What happens if CPU 0's rcu_barrier_func() executes + immediately (thus incrementing rcu_barrier_cpu_count to the + value one), but the other CPU's rcu_barrier_func() invocations + are delayed for a full grace period? Couldn't this result in + rcu_barrier() returning prematurely? + +Answer: This cannot happen. The reason is that on_each_cpu() has its last + argument, the wait flag, set to "1". This flag is passed through + to smp_call_function() and further to smp_call_function_on_cpu(), + causing this latter to spin until the cross-CPU invocation of + rcu_barrier_func() has completed. This by itself would prevent + a grace period from completing on non-CONFIG_PREEMPT kernels, + since each CPU must undergo a context switch (or other quiescent + state) before the grace period can complete. However, this is + of no use in CONFIG_PREEMPT kernels. + + Therefore, on_each_cpu() disables preemption across its call + to smp_call_function() and also across the local call to + rcu_barrier_func(). This prevents the local CPU from context + switching, again preventing grace periods from completing. This + means that all CPUs have executed rcu_barrier_func() before + the first rcu_barrier_callback() can possibly execute, in turn + preventing rcu_barrier_cpu_count from prematurely reaching zero. + + Currently, -rt implementations of RCU keep but a single global + queue for RCU callbacks, and thus do not suffer from this + problem. However, when the -rt RCU eventually does have per-CPU + callback queues, things will have to change. One simple change + is to add an rcu_read_lock() before line 8 of rcu_barrier() + and an rcu_read_unlock() after line 8 of this same function. If + you can think of a better change, please let me know! -- cgit v1.2.3 From 2884f00b94be73a6a7875bada739bf9bb2f9a1b6 Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Wed, 26 Nov 2008 17:15:21 +0100 Subject: Document handling of bad memory MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Document how to deal with bad memory reported with memtest. Signed-off-by: Jan-Simon Möller Signed-off-by: Pavel Machek Signed-off-by: Jonathan Corbet --- Documentation/bad_memory.txt | 45 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) create mode 100644 Documentation/bad_memory.txt (limited to 'Documentation') diff --git a/Documentation/bad_memory.txt b/Documentation/bad_memory.txt new file mode 100644 index 000000000000..df8416213202 --- /dev/null +++ b/Documentation/bad_memory.txt @@ -0,0 +1,45 @@ +March 2008 +Jan-Simon Moeller, dl9pf@gmx.de + + +How to deal with bad memory e.g. reported by memtest86+ ? +######################################################### + +There are three possibilities I know of: + +1) Reinsert/swap the memory modules + +2) Buy new modules (best!) or try to exchange the memory + if you have spare-parts + +3) Use BadRAM or memmap + +This Howto is about number 3) . + + +BadRAM +###### +BadRAM is the actively developed and available as kernel-patch +here: http://rick.vanrein.org/linux/badram/ + +For more details see the BadRAM documentation. + +memmap +###### + +memmap is already in the kernel and usable as kernel-parameter at +boot-time. Its syntax is slightly strange and you may need to +calculate the values by yourself! + +Syntax to exclude a memory area (see kernel-parameters.txt for details): +memmap=$
+ +Example: memtest86+ reported here errors at address 0x18691458, 0x18698424 and + some others. All had 0x1869xxxx in common, so I chose a pattern of + 0x18690000,0xffff0000. + +With the numbers of the example above: +memmap=64K$0x18690000 + or +memmap=0x10000$0x18690000 + -- cgit v1.2.3 From ba84ed9546e91348fdf3ff2bff859b0ee53b407a Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 26 Oct 2008 20:56:30 +0100 Subject: ACPI hibernate: Introduce new kernel parameter acpi_sleep=s4_nonvs On some machines it may be necessary to disable the saving/restoring of the ACPI NVS memory region during hibernation/resume. For this purpose, introduce new ACPI kernel command line option acpi_sleep=s4_nonvs. Based on a patch by Zhang Rui. Signed-off-by: Rafael J. Wysocki Acked-by: Nigel Cunningham Acked-by: Pavel Machek Signed-off-by: Len Brown --- Documentation/kernel-parameters.txt | 5 ++++- arch/x86/kernel/acpi/sleep.c | 2 ++ drivers/acpi/sleep/main.c | 18 ++++++++++++++++-- include/linux/acpi.h | 1 + 4 files changed, 23 insertions(+), 3 deletions(-) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index e0f346d201ed..1d089eeff3cf 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -149,7 +149,8 @@ and is between 256 and 4096 characters. It is defined in the file default: 0 acpi_sleep= [HW,ACPI] Sleep options - Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig, old_ordering } + Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig, + old_ordering, s4_nonvs } See Documentation/power/video.txt for s3_bios and s3_mode. s3_beep is for debugging; it makes the PC's speaker beep as soon as the kernel's real-mode entry point is called. @@ -159,6 +160,8 @@ and is between 256 and 4096 characters. It is defined in the file control method, wrt putting devices into low power states, to be enforced (the ACPI 2.0 ordering of _PTS is used by default). + s4_nonvs prevents the kernel from saving/restoring the + ACPI NVS memory during hibernation. acpi_sci= [HW,ACPI] ACPI System Control Interrupt trigger mode Format: { level | edge | high | low } diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 806b4e9051b4..707c1f6f95fa 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -159,6 +159,8 @@ static int __init acpi_sleep_setup(char *str) #endif if (strncmp(str, "old_ordering", 12) == 0) acpi_old_suspend_ordering(); + if (strncmp(str, "s4_nonvs", 8) == 0) + acpi_s4_no_nvs(); str = strchr(str, ','); if (str != NULL) str += strspn(str, ", \t"); diff --git a/drivers/acpi/sleep/main.c b/drivers/acpi/sleep/main.c index 45a8015e4217..bef41fd4c877 100644 --- a/drivers/acpi/sleep/main.c +++ b/drivers/acpi/sleep/main.c @@ -101,6 +101,19 @@ void __init acpi_old_suspend_ordering(void) * cases. */ static bool set_sci_en_on_resume; +/* + * The ACPI specification wants us to save NVS memory regions during hibernation + * and to restore them during the subsequent resume. However, it is not certain + * if this mechanism is going to work on all machines, so we allow the user to + * disable this mechanism using the 'acpi_sleep=s4_nonvs' kernel command line + * option. + */ +static bool s4_no_nvs; + +void __init acpi_s4_no_nvs(void) +{ + s4_no_nvs = true; +} /** * acpi_pm_disable_gpes - Disable the GPEs. @@ -396,7 +409,7 @@ static int acpi_hibernation_begin(void) { int error; - error = hibernate_nvs_alloc(); + error = s4_no_nvs ? 0 : hibernate_nvs_alloc(); if (!error) { acpi_target_sleep_state = ACPI_STATE_S4; acpi_sleep_tts_switch(acpi_target_sleep_state); @@ -494,7 +507,8 @@ static int acpi_hibernation_begin_old(void) error = acpi_sleep_prepare(ACPI_STATE_S4); if (!error) { - error = hibernate_nvs_alloc(); + if (!s4_no_nvs) + error = hibernate_nvs_alloc(); if (!error) acpi_target_sleep_state = ACPI_STATE_S4; } diff --git a/include/linux/acpi.h b/include/linux/acpi.h index fba8051fb297..dfa0a5356c53 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -270,6 +270,7 @@ int acpi_check_mem_region(resource_size_t start, resource_size_t n, #ifdef CONFIG_PM_SLEEP void __init acpi_no_s4_hw_signature(void); void __init acpi_old_suspend_ordering(void); +void __init acpi_s4_no_nvs(void); #endif /* CONFIG_PM_SLEEP */ #else /* CONFIG_ACPI */ -- cgit v1.2.3 From ada9cfdd158abb8169873dc8e5ae39b1ec6ffa8c Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 19 Dec 2008 10:57:32 -0800 Subject: doc: fix kernel-parameters.txt formatting Spell out "wrt". I suspect plenty of people won't know what that means. Fix a '}' that should be a ']'. Reformat long lines into shorter lines. Signed-off-by: Randy Dunlap Signed-off-by: Len Brown --- Documentation/kernel-parameters.txt | 40 ++++++++++++++++++++----------------- 1 file changed, 22 insertions(+), 18 deletions(-) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 1d089eeff3cf..350e71960a96 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -151,15 +151,16 @@ and is between 256 and 4096 characters. It is defined in the file acpi_sleep= [HW,ACPI] Sleep options Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig, old_ordering, s4_nonvs } - See Documentation/power/video.txt for s3_bios and s3_mode. + See Documentation/power/video.txt for information on + s3_bios and s3_mode. s3_beep is for debugging; it makes the PC's speaker beep as soon as the kernel's real-mode entry point is called. s4_nohwsig prevents ACPI hardware signature from being used during resume from hibernation. old_ordering causes the ACPI 1.0 ordering of the _PTS - control method, wrt putting devices into low power - states, to be enforced (the ACPI 2.0 ordering of _PTS is - used by default). + control method, with respect to putting devices into + low power states, to be enforced (the ACPI 2.0 ordering + of _PTS is used by default). s4_nonvs prevents the kernel from saving/restoring the ACPI NVS memory during hibernation. @@ -196,7 +197,7 @@ and is between 256 and 4096 characters. It is defined in the file acpi_skip_timer_override [HW,ACPI] Recognize and ignore IRQ0/pin2 Interrupt Override. For broken nForce2 BIOS resulting in XT-PIC timer. - acpi_use_timer_override [HW,ACPI} + acpi_use_timer_override [HW,ACPI] Use timer override. For some broken Nvidia NF5 boards that require a timer override, but don't have HPET @@ -860,17 +861,19 @@ and is between 256 and 4096 characters. It is defined in the file See Documentation/ide/ide.txt. idle= [X86] - Format: idle=poll or idle=mwait, idle=halt, idle=nomwait - Poll forces a polling idle loop that can slightly improves the performance - of waking up a idle CPU, but will use a lot of power and make the system - run hot. Not recommended. - idle=mwait. On systems which support MONITOR/MWAIT but the kernel chose - to not use it because it doesn't save as much power as a normal idle - loop use the MONITOR/MWAIT idle loop anyways. Performance should be the same - as idle=poll. - idle=halt. Halt is forced to be used for CPU idle. + Format: idle=poll, idle=mwait, idle=halt, idle=nomwait + Poll forces a polling idle loop that can slightly + improve the performance of waking up a idle CPU, but + will use a lot of power and make the system run hot. + Not recommended. + idle=mwait: On systems which support MONITOR/MWAIT but + the kernel chose to not use it because it doesn't save + as much power as a normal idle loop, use the + MONITOR/MWAIT idle loop anyways. Performance should be + the same as idle=poll. + idle=halt: Halt is forced to be used for CPU idle. In such case C2/C3 won't be used again. - idle=nomwait. Disable mwait for CPU C-states + idle=nomwait: Disable mwait for CPU C-states ide-pci-generic.all-generic-ide [HW] (E)IDE subsystem Claim all unknown PCI IDE storage controllers. @@ -1052,8 +1055,8 @@ and is between 256 and 4096 characters. It is defined in the file lapic [X86-32,APIC] Enable the local APIC even if BIOS disabled it. - lapic_timer_c2_ok [X86-32,x86-64,APIC] trust the local apic timer in - C2 power state. + lapic_timer_c2_ok [X86-32,x86-64,APIC] trust the local apic timer + in C2 power state. libata.dma= [LIBATA] DMA control libata.dma=0 Disable all PATA and SATA DMA @@ -2241,7 +2244,8 @@ and is between 256 and 4096 characters. It is defined in the file thermal.psv= [HW,ACPI] -1: disable all passive trip points - : override all passive trip points to this value + : override all passive trip points to this + value thermal.tzp= [HW,ACPI] Specify global default ACPI thermal zone polling rate -- cgit v1.2.3 From 94409d6e1088517b6d6c8e669c604cc86d08ac1b Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Thu, 18 Dec 2008 19:37:23 +0300 Subject: powerpc: Add device tree bindings for BCSR GPIO banks The patch adds bindings for BCSR GPIO banks, the bindings are used to describe particular BCSR registers that act as simple GPIO controllers. These GPIO banks might control power switches, SPI chip-selects, LEDs, etc. While at it, also fix "length" spelling error in the PIXIS FPGA bindings. Signed-off-by: Anton Vorontsov Signed-off-by: Kumar Gala --- Documentation/powerpc/dts-bindings/fsl/board.txt | 32 +++++++++++++++++++++++- 1 file changed, 31 insertions(+), 1 deletion(-) (limited to 'Documentation') diff --git a/Documentation/powerpc/dts-bindings/fsl/board.txt b/Documentation/powerpc/dts-bindings/fsl/board.txt index 81a917ef96e9..6c974d28eeb4 100644 --- a/Documentation/powerpc/dts-bindings/fsl/board.txt +++ b/Documentation/powerpc/dts-bindings/fsl/board.txt @@ -18,7 +18,7 @@ This is the memory-mapped registers for on board FPGA. Required properities: - compatible : should be "fsl,fpga-pixis". -- reg : should contain the address and the lenght of the FPPGA register +- reg : should contain the address and the length of the FPPGA register set. Example (MPC8610HPCD): @@ -27,3 +27,33 @@ Example (MPC8610HPCD): compatible = "fsl,fpga-pixis"; reg = <0xe8000000 32>; }; + +* Freescale BCSR GPIO banks + +Some BCSR registers act as simple GPIO controllers, each such +register can be represented by the gpio-controller node. + +Required properities: +- compatible : Should be "fsl,-bcsr-gpio". +- reg : Should contain the address and the length of the GPIO bank + register. +- #gpio-cells : Should be two. The first cell is the pin number and the + second cell is used to specify optional paramters (currently unused). +- gpio-controller : Marks the port as GPIO controller. + +Example: + + bcsr@1,0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "fsl,mpc8360mds-bcsr"; + reg = <1 0 0x8000>; + ranges = <0 1 0 0x8000>; + + bcsr13: gpio-controller@d { + #gpio-cells = <2>; + compatible = "fsl,mpc8360mds-bcsr-gpio"; + reg = <0xd 1>; + gpio-controller; + }; + }; -- cgit v1.2.3 From 277d342fc423fca5e66e677fe629d1b2f8f1b9e2 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Wed, 31 Dec 2008 12:54:11 -0500 Subject: selinux: Deprecate and schedule the removal of the the compat_net functionality This patch is the first step towards removing the old "compat_net" code from the kernel. Secmark, the "compat_net" replacement was first introduced in 2.6.18 (September 2006) and the major Linux distributions with SELinux support have transitioned to Secmark so it is time to start deprecating the "compat_net" mechanism. Testing a patched version of 2.6.28-rc6 with the initial release of Fedora Core 5 did not show any problems when running in enforcing mode. This patch adds an entry to the feature-removal-schedule.txt file and removes the SECURITY_SELINUX_ENABLE_SECMARK_DEFAULT configuration option, forcing Secmark on by default although it can still be disabled at runtime. The patch also makes the Secmark permission checks "dynamic" in the sense that they are only executed when Secmark is configured; this should help prevent problems with older distributions that have not yet migrated to Secmark. Signed-off-by: Paul Moore Acked-by: James Morris --- Documentation/feature-removal-schedule.txt | 12 ++++++++++++ security/selinux/Kconfig | 27 --------------------------- security/selinux/hooks.c | 6 +++--- security/selinux/selinuxfs.c | 16 ++++++++-------- 4 files changed, 23 insertions(+), 38 deletions(-) (limited to 'Documentation') diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index dc7c681e532c..a0ed3964a219 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -324,3 +324,15 @@ When: 2.6.29 (ideally) or 2.6.30 (more likely) Why: Deprecated by the new (standard) device driver binding model. Use i2c_driver->probe() and ->remove() instead. Who: Jean Delvare + +--------------------------- + +What: SELinux "compat_net" functionality +When: 2.6.30 at the earliest +Why: In 2.6.18 the Secmark concept was introduced to replace the "compat_net" + network access control functionality of SELinux. Secmark offers both + better performance and greater flexibility than the "compat_net" + mechanism. Now that the major Linux distributions have moved to + Secmark, it is time to deprecate the older mechanism and start the + process of removing the old code. +Who: Paul Moore diff --git a/security/selinux/Kconfig b/security/selinux/Kconfig index 26301dd651d3..bca1b74a4a2f 100644 --- a/security/selinux/Kconfig +++ b/security/selinux/Kconfig @@ -94,33 +94,6 @@ config SECURITY_SELINUX_CHECKREQPROT_VALUE If you are unsure how to answer this question, answer 1. -config SECURITY_SELINUX_ENABLE_SECMARK_DEFAULT - bool "NSA SELinux enable new secmark network controls by default" - depends on SECURITY_SELINUX - default n - help - This option determines whether the new secmark-based network - controls will be enabled by default. If not, the old internal - per-packet controls will be enabled by default, preserving - old behavior. - - If you enable the new controls, you will need updated - SELinux userspace libraries, tools and policy. Typically, - your distribution will provide these and enable the new controls - in the kernel they also distribute. - - Note that this option can be overridden at boot with the - selinux_compat_net parameter, and after boot via - /selinux/compat_net. See Documentation/kernel-parameters.txt - for details on this parameter. - - If you enable the new network controls, you will likely - also require the SECMARK and CONNSECMARK targets, as - well as any conntrack helpers for protocols which you - wish to control. - - If you are unsure what to do here, select N. - config SECURITY_SELINUX_POLICYDB_VERSION_MAX bool "NSA SELinux maximum supported policy format version" depends on SECURITY_SELINUX diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index dbeaa783b2a9..df30a7555d8a 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -4185,7 +4185,7 @@ static int selinux_sock_rcv_skb_iptables_compat(struct sock *sk, static int selinux_sock_rcv_skb_compat(struct sock *sk, struct sk_buff *skb, u16 family) { - int err; + int err = 0; struct sk_security_struct *sksec = sk->sk_security; u32 peer_sid; u32 sk_sid = sksec->sid; @@ -4202,7 +4202,7 @@ static int selinux_sock_rcv_skb_compat(struct sock *sk, struct sk_buff *skb, if (selinux_compat_net) err = selinux_sock_rcv_skb_iptables_compat(sk, skb, &ad, family, addrp); - else + else if (selinux_secmark_enabled()) err = avc_has_perm(sk_sid, skb->secmark, SECCLASS_PACKET, PACKET__RECV, &ad); if (err) @@ -4705,7 +4705,7 @@ static unsigned int selinux_ip_postroute_compat(struct sk_buff *skb, if (selinux_ip_postroute_iptables_compat(skb->sk, ifindex, &ad, family, addrp)) return NF_DROP; - } else { + } else if (selinux_secmark_enabled()) { if (avc_has_perm(sksec->sid, skb->secmark, SECCLASS_PACKET, PACKET__SEND, &ad)) return NF_DROP; diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index c86303638235..77fb3c8d9267 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -47,13 +47,7 @@ static char *policycap_names[] = { unsigned int selinux_checkreqprot = CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE; -#ifdef CONFIG_SECURITY_SELINUX_ENABLE_SECMARK_DEFAULT -#define SELINUX_COMPAT_NET_VALUE 0 -#else -#define SELINUX_COMPAT_NET_VALUE 1 -#endif - -int selinux_compat_net = SELINUX_COMPAT_NET_VALUE; +int selinux_compat_net = 0; static int __init checkreqprot_setup(char *str) { @@ -494,7 +488,13 @@ static ssize_t sel_write_compat_net(struct file *file, const char __user *buf, if (sscanf(page, "%d", &new_value) != 1) goto out; - selinux_compat_net = new_value ? 1 : 0; + if (new_value) { + printk(KERN_NOTICE + "SELinux: compat_net is deprecated, please use secmark" + " instead\n"); + selinux_compat_net = 1; + } else + selinux_compat_net = 0; length = count; out: free_page((unsigned long) page); -- cgit v1.2.3 From c31910672376dfb8d020e32afa7249763bcd924a Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 6 Jan 2009 11:14:25 -0500 Subject: ext4: Remove code to create the journal inode This code has been obsolete in quite some time, since the supported method for adding a journal inode is to use tune2fs (or to creating new filesystem with a journal via mke2fs or mkfs.ext4). Signed-off-by: "Theodore Ts'o" --- Documentation/filesystems/ext4.txt | 4 --- fs/ext4/super.c | 68 +++-------------------------------- fs/jbd2/journal.c | 72 -------------------------------------- include/linux/jbd2.h | 1 - 4 files changed, 4 insertions(+), 141 deletions(-) (limited to 'Documentation') diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index e3fcbea3ec8c..9ec29d86ff8b 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -149,10 +149,6 @@ journal_async_commit Commit block can be written to disk without waiting journal=update Update the ext4 file system's journal to the current format. -journal=inum When a journal already exists, this option is ignored. - Otherwise, it specifies the number of the inode which - will represent the ext4 file system's journal file. - journal_dev=devnum When the external journal device's major/minor numbers have changed, this option allows the user to specify the new journal location. The journal device is diff --git a/fs/ext4/super.c b/fs/ext4/super.c index e5ab520724da..8036392b2121 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -51,8 +51,6 @@ struct proc_dir_entry *ext4_proc_root; static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); -static int ext4_create_journal(struct super_block *, struct ext4_super_block *, - unsigned int); static void ext4_commit_super(struct super_block *sb, struct ext4_super_block *es, int sync); static void ext4_mark_recovery_complete(struct super_block *sb, @@ -1006,7 +1004,7 @@ enum { Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl, Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh, Opt_commit, Opt_min_batch_time, Opt_max_batch_time, - Opt_journal_update, Opt_journal_inum, Opt_journal_dev, + Opt_journal_update, Opt_journal_dev, Opt_journal_checksum, Opt_journal_async_commit, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, Opt_data_err_abort, Opt_data_err_ignore, @@ -1048,7 +1046,6 @@ static const match_table_t tokens = { {Opt_min_batch_time, "min_batch_time=%u"}, {Opt_max_batch_time, "max_batch_time=%u"}, {Opt_journal_update, "journal=update"}, - {Opt_journal_inum, "journal=%u"}, {Opt_journal_dev, "journal_dev=%u"}, {Opt_journal_checksum, "journal_checksum"}, {Opt_journal_async_commit, "journal_async_commit"}, @@ -1102,7 +1099,7 @@ static ext4_fsblk_t get_sb_block(void **data) } static int parse_options(char *options, struct super_block *sb, - unsigned int *inum, unsigned long *journal_devnum, + unsigned long *journal_devnum, ext4_fsblk_t *n_blocks_count, int is_remount) { struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -1226,16 +1223,6 @@ static int parse_options(char *options, struct super_block *sb, } set_opt(sbi->s_mount_opt, UPDATE_JOURNAL); break; - case Opt_journal_inum: - if (is_remount) { - printk(KERN_ERR "EXT4-fs: cannot specify " - "journal on remount\n"); - return 0; - } - if (match_int(&args[0], &option)) - return 0; - *inum = option; - break; case Opt_journal_dev: if (is_remount) { printk(KERN_ERR "EXT4-fs: cannot specify " @@ -2035,7 +2022,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ext4_fsblk_t sb_block = get_sb_block(&data); ext4_fsblk_t logical_sb_block; unsigned long offset = 0; - unsigned int journal_inum = 0; unsigned long journal_devnum = 0; unsigned long def_mount_opts; struct inode *root; @@ -2155,8 +2141,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) set_opt(sbi->s_mount_opt, DELALLOC); - if (!parse_options((char *) data, sb, &journal_inum, &journal_devnum, - NULL, 0)) + if (!parse_options((char *) data, sb, &journal_devnum, NULL, 0)) goto failed_mount; sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | @@ -2460,9 +2445,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount4; } } - } else if (journal_inum) { - if (ext4_create_journal(sb, es, journal_inum)) - goto failed_mount3; } else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) && EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) { printk(KERN_ERR "EXT4-fs: required journal recovery " @@ -2926,48 +2908,6 @@ static int ext4_load_journal(struct super_block *sb, return 0; } -static int ext4_create_journal(struct super_block *sb, - struct ext4_super_block *es, - unsigned int journal_inum) -{ - journal_t *journal; - int err; - - if (sb->s_flags & MS_RDONLY) { - printk(KERN_ERR "EXT4-fs: readonly filesystem when trying to " - "create journal.\n"); - return -EROFS; - } - - journal = ext4_get_journal(sb, journal_inum); - if (!journal) - return -EINVAL; - - printk(KERN_INFO "EXT4-fs: creating new journal on inode %u\n", - journal_inum); - - err = jbd2_journal_create(journal); - if (err) { - printk(KERN_ERR "EXT4-fs: error creating journal.\n"); - jbd2_journal_destroy(journal); - return -EIO; - } - - EXT4_SB(sb)->s_journal = journal; - - ext4_update_dynamic_rev(sb); - EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); - EXT4_SET_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL); - - es->s_journal_inum = cpu_to_le32(journal_inum); - sb->s_dirt = 1; - - /* Make sure we flush the recovery flag to disk. */ - ext4_commit_super(sb, es, 1); - - return 0; -} - static void ext4_commit_super(struct super_block *sb, struct ext4_super_block *es, int sync) { @@ -3209,7 +3149,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) /* * Allow the "check" option to be passed as a remount option. */ - if (!parse_options(data, sb, NULL, NULL, &n_blocks_count, 1)) { + if (!parse_options(data, sb, NULL, &n_blocks_count, 1)) { err = -EINVAL; goto restore_opts; } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 34ef98057202..b10d7283ba5b 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -66,7 +66,6 @@ EXPORT_SYMBOL(jbd2_journal_update_format); EXPORT_SYMBOL(jbd2_journal_check_used_features); EXPORT_SYMBOL(jbd2_journal_check_available_features); EXPORT_SYMBOL(jbd2_journal_set_features); -EXPORT_SYMBOL(jbd2_journal_create); EXPORT_SYMBOL(jbd2_journal_load); EXPORT_SYMBOL(jbd2_journal_destroy); EXPORT_SYMBOL(jbd2_journal_abort); @@ -1162,77 +1161,6 @@ static int journal_reset(journal_t *journal) return jbd2_journal_start_thread(journal); } -/** - * int jbd2_journal_create() - Initialise the new journal file - * @journal: Journal to create. This structure must have been initialised - * - * Given a journal_t structure which tells us which disk blocks we can - * use, create a new journal superblock and initialise all of the - * journal fields from scratch. - **/ -int jbd2_journal_create(journal_t *journal) -{ - unsigned long long blocknr; - struct buffer_head *bh; - journal_superblock_t *sb; - int i, err; - - if (journal->j_maxlen < JBD2_MIN_JOURNAL_BLOCKS) { - printk (KERN_ERR "Journal length (%d blocks) too short.\n", - journal->j_maxlen); - journal_fail_superblock(journal); - return -EINVAL; - } - - if (journal->j_inode == NULL) { - /* - * We don't know what block to start at! - */ - printk(KERN_EMERG - "%s: creation of journal on external device!\n", - __func__); - BUG(); - } - - /* Zero out the entire journal on disk. We cannot afford to - have any blocks on disk beginning with JBD2_MAGIC_NUMBER. */ - jbd_debug(1, "JBD: Zeroing out journal blocks...\n"); - for (i = 0; i < journal->j_maxlen; i++) { - err = jbd2_journal_bmap(journal, i, &blocknr); - if (err) - return err; - bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); - lock_buffer(bh); - memset (bh->b_data, 0, journal->j_blocksize); - BUFFER_TRACE(bh, "marking dirty"); - mark_buffer_dirty(bh); - BUFFER_TRACE(bh, "marking uptodate"); - set_buffer_uptodate(bh); - unlock_buffer(bh); - __brelse(bh); - } - - sync_blockdev(journal->j_dev); - jbd_debug(1, "JBD: journal cleared.\n"); - - /* OK, fill in the initial static fields in the new superblock */ - sb = journal->j_superblock; - - sb->s_header.h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER); - sb->s_header.h_blocktype = cpu_to_be32(JBD2_SUPERBLOCK_V2); - - sb->s_blocksize = cpu_to_be32(journal->j_blocksize); - sb->s_maxlen = cpu_to_be32(journal->j_maxlen); - sb->s_first = cpu_to_be32(1); - - journal->j_transaction_sequence = 1; - - journal->j_flags &= ~JBD2_ABORT; - journal->j_format_version = 2; - - return journal_reset(journal); -} - /** * void jbd2_journal_update_superblock() - Update journal sb on disk. * @journal: The journal to update. diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 9d82084a1605..adef1c9940d3 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1104,7 +1104,6 @@ extern int jbd2_journal_set_features (journal_t *, unsigned long, unsigned long, unsigned long); extern void jbd2_journal_clear_features (journal_t *, unsigned long, unsigned long, unsigned long); -extern int jbd2_journal_create (journal_t *); extern int jbd2_journal_load (journal_t *journal); extern int jbd2_journal_destroy (journal_t *); extern int jbd2_journal_recover (journal_t *journal); -- cgit v1.2.3 From 2f6de3a199893ae3dd68e23bd79b55e1478c8268 Mon Sep 17 00:00:00 2001 From: Baodong Chen Date: Sat, 3 Jan 2009 12:37:06 +0800 Subject: Documentation/x86/boot.txt: payload length was changed to payload_length Signed-off-by: Baodong Chen <[email]chenbdchenbd@gmail.com[email]> Acked-by: Jiri Kosina Signed-off-by: Ingo Molnar --- Documentation/x86/boot.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'Documentation') diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt index fcdc62b3c3d8..7b4596ac4120 100644 --- a/Documentation/x86/boot.txt +++ b/Documentation/x86/boot.txt @@ -44,7 +44,7 @@ Protocol 2.07: (Kernel 2.6.24) Added paravirtualised boot protocol. and KEEP_SEGMENTS flag in load_flags. Protocol 2.08: (Kernel 2.6.26) Added crc32 checksum and ELF format - payload. Introduced payload_offset and payload length + payload. Introduced payload_offset and payload_length fields to aid in locating the payload. Protocol 2.09: (Kernel 2.6.26) Added a field of 64-bit physical -- cgit v1.2.3 From 9eb425c046f4129f1dafce7c04e949652e69fb01 Mon Sep 17 00:00:00 2001 From: Phillip Lougher Date: Mon, 5 Jan 2009 08:46:29 +0000 Subject: Squashfs: documentation Signed-off-by: Phillip Lougher --- Documentation/filesystems/squashfs.txt | 225 +++++++++++++++++++++++++++++++++ 1 file changed, 225 insertions(+) create mode 100644 Documentation/filesystems/squashfs.txt (limited to 'Documentation') diff --git a/Documentation/filesystems/squashfs.txt b/Documentation/filesystems/squashfs.txt new file mode 100644 index 000000000000..3e79e4a7a392 --- /dev/null +++ b/Documentation/filesystems/squashfs.txt @@ -0,0 +1,225 @@ +SQUASHFS 4.0 FILESYSTEM +======================= + +Squashfs is a compressed read-only filesystem for Linux. +It uses zlib compression to compress files, inodes and directories. +Inodes in the system are very small and all blocks are packed to minimise +data overhead. Block sizes greater than 4K are supported up to a maximum +of 1Mbytes (default block size 128K). + +Squashfs is intended for general read-only filesystem use, for archival +use (i.e. in cases where a .tar.gz file may be used), and in constrained +block device/memory systems (e.g. embedded systems) where low overhead is +needed. + +Mailing list: squashfs-devel@lists.sourceforge.net +Web site: www.squashfs.org + +1. FILESYSTEM FEATURES +---------------------- + +Squashfs filesystem features versus Cramfs: + + Squashfs Cramfs + +Max filesystem size: 2^64 16 MiB +Max file size: ~ 2 TiB 16 MiB +Max files: unlimited unlimited +Max directories: unlimited unlimited +Max entries per directory: unlimited unlimited +Max block size: 1 MiB 4 KiB +Metadata compression: yes no +Directory indexes: yes no +Sparse file support: yes no +Tail-end packing (fragments): yes no +Exportable (NFS etc.): yes no +Hard link support: yes no +"." and ".." in readdir: yes no +Real inode numbers: yes no +32-bit uids/gids: yes no +File creation time: yes no +Xattr and ACL support: no no + +Squashfs compresses data, inodes and directories. In addition, inode and +directory data are highly compacted, and packed on byte boundaries. Each +compressed inode is on average 8 bytes in length (the exact length varies on +file type, i.e. regular file, directory, symbolic link, and block/char device +inodes have different sizes). + +2. USING SQUASHFS +----------------- + +As squashfs is a read-only filesystem, the mksquashfs program must be used to +create populated squashfs filesystems. This and other squashfs utilities +can be obtained from http://www.squashfs.org. Usage instructions can be +obtained from this site also. + + +3. SQUASHFS FILESYSTEM DESIGN +----------------------------- + +A squashfs filesystem consists of seven parts, packed together on a byte +alignment: + + --------------- + | superblock | + |---------------| + | datablocks | + | & fragments | + |---------------| + | inode table | + |---------------| + | directory | + | table | + |---------------| + | fragment | + | table | + |---------------| + | export | + | table | + |---------------| + | uid/gid | + | lookup table | + --------------- + +Compressed data blocks are written to the filesystem as files are read from +the source directory, and checked for duplicates. Once all file data has been +written the completed inode, directory, fragment, export and uid/gid lookup +tables are written. + +3.1 Inodes +---------- + +Metadata (inodes and directories) are compressed in 8Kbyte blocks. Each +compressed block is prefixed by a two byte length, the top bit is set if the +block is uncompressed. A block will be uncompressed if the -noI option is set, +or if the compressed block was larger than the uncompressed block. + +Inodes are packed into the metadata blocks, and are not aligned to block +boundaries, therefore inodes overlap compressed blocks. Inodes are identified +by a 48-bit number which encodes the location of the compressed metadata block +containing the inode, and the byte offset into that block where the inode is +placed (). + +To maximise compression there are different inodes for each file type +(regular file, directory, device, etc.), the inode contents and length +varying with the type. + +To further maximise compression, two types of regular file inode and +directory inode are defined: inodes optimised for frequently occurring +regular files and directories, and extended types where extra +information has to be stored. + +3.2 Directories +--------------- + +Like inodes, directories are packed into compressed metadata blocks, stored +in a directory table. Directories are accessed using the start address of +the metablock containing the directory and the offset into the +decompressed block (). + +Directories are organised in a slightly complex way, and are not simply +a list of file names. The organisation takes advantage of the +fact that (in most cases) the inodes of the files will be in the same +compressed metadata block, and therefore, can share the start block. +Directories are therefore organised in a two level list, a directory +header containing the shared start block value, and a sequence of directory +entries, each of which share the shared start block. A new directory header +is written once/if the inode start block changes. The directory +header/directory entry list is repeated as many times as necessary. + +Directories are sorted, and can contain a directory index to speed up +file lookup. Directory indexes store one entry per metablock, each entry +storing the index/filename mapping to the first directory header +in each metadata block. Directories are sorted in alphabetical order, +and at lookup the index is scanned linearly looking for the first filename +alphabetically larger than the filename being looked up. At this point the +location of the metadata block the filename is in has been found. +The general idea of the index is ensure only one metadata block needs to be +decompressed to do a lookup irrespective of the length of the directory. +This scheme has the advantage that it doesn't require extra memory overhead +and doesn't require much extra storage on disk. + +3.3 File data +------------- + +Regular files consist of a sequence of contiguous compressed blocks, and/or a +compressed fragment block (tail-end packed block). The compressed size +of each datablock is stored in a block list contained within the +file inode. + +To speed up access to datablocks when reading 'large' files (256 Mbytes or +larger), the code implements an index cache that caches the mapping from +block index to datablock location on disk. + +The index cache allows Squashfs to handle large files (up to 1.75 TiB) while +retaining a simple and space-efficient block list on disk. The cache +is split into slots, caching up to eight 224 GiB files (128 KiB blocks). +Larger files use multiple slots, with 1.75 TiB files using all 8 slots. +The index cache is designed to be memory efficient, and by default uses +16 KiB. + +3.4 Fragment lookup table +------------------------- + +Regular files can contain a fragment index which is mapped to a fragment +location on disk and compressed size using a fragment lookup table. This +fragment lookup table is itself stored compressed into metadata blocks. +A second index table is used to locate these. This second index table for +speed of access (and because it is small) is read at mount time and cached +in memory. + +3.5 Uid/gid lookup table +------------------------ + +For space efficiency regular files store uid and gid indexes, which are +converted to 32-bit uids/gids using an id look up table. This table is +stored compressed into metadata blocks. A second index table is used to +locate these. This second index table for speed of access (and because it +is small) is read at mount time and cached in memory. + +3.6 Export table +---------------- + +To enable Squashfs filesystems to be exportable (via NFS etc.) filesystems +can optionally (disabled with the -no-exports Mksquashfs option) contain +an inode number to inode disk location lookup table. This is required to +enable Squashfs to map inode numbers passed in filehandles to the inode +location on disk, which is necessary when the export code reinstantiates +expired/flushed inodes. + +This table is stored compressed into metadata blocks. A second index table is +used to locate these. This second index table for speed of access (and because +it is small) is read at mount time and cached in memory. + + +4. TODOS AND OUTSTANDING ISSUES +------------------------------- + +4.1 Todo list +------------- + +Implement Xattr and ACL support. The Squashfs 4.0 filesystem layout has hooks +for these but the code has not been written. Once the code has been written +the existing layout should not require modification. + +4.2 Squashfs internal cache +--------------------------- + +Blocks in Squashfs are compressed. To avoid repeatedly decompressing +recently accessed data Squashfs uses two small metadata and fragment caches. + +The cache is not used for file datablocks, these are decompressed and cached in +the page-cache in the normal way. The cache is used to temporarily cache +fragment and metadata blocks which have been read as a result of a metadata +(i.e. inode or directory) or fragment access. Because metadata and fragments +are packed together into blocks (to gain greater compression) the read of a +particular piece of metadata or fragment will retrieve other metadata/fragments +which have been packed with it, these because of locality-of-reference may be +read in the near future. Temporarily caching them ensures they are available +for near future access without requiring an additional read and decompress. + +In the future this internal cache may be replaced with an implementation which +uses the kernel page cache. Because the page cache operates on page sized +units this may introduce additional complexity in terms of locking and +associated race conditions. -- cgit v1.2.3 From 2ec220e27f5040aec1e88901c1b6ea3d135787ad Mon Sep 17 00:00:00 2001 From: Ken Chen Date: Mon, 10 Nov 2008 11:26:08 +0300 Subject: proc: add /proc/*/stack /proc/*/stack adds the ability to query a task's stack trace. It is more useful than /proc/*/wchan as it provides full stack trace instead of single depth. Example output: $ cat /proc/self/stack [] save_stack_trace_tsk+0x17/0x35 [] proc_pid_stack+0x4a/0x76 [] proc_single_show+0x4a/0x5e [] seq_read+0xf3/0x29f [] vfs_read+0x6d/0x91 [] sys_read+0x3b/0x60 [] syscall_call+0x7/0xb [] 0xffffffff [add save_stack_trace_tsk() on mips, ACK Ralf --adobriyan] Signed-off-by: Ken Chen Signed-off-by: Ingo Molnar Signed-off-by: Alexey Dobriyan --- Documentation/filesystems/proc.txt | 1 + arch/mips/kernel/stacktrace.c | 24 ++++++++++++++++++------ fs/proc/base.c | 38 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 57 insertions(+), 6 deletions(-) (limited to 'Documentation') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 71df353e367c..334ef2f983fa 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -140,6 +140,7 @@ Table 1-1: Process specific entries in /proc statm Process memory status information status Process status in human readable form wchan If CONFIG_KALLSYMS is set, a pre-decoded wchan + stack Report full stack trace, enable via CONFIG_STACKTRACE smaps Extension based on maps, the rss size for each mapped file .............................................................................. diff --git a/arch/mips/kernel/stacktrace.c b/arch/mips/kernel/stacktrace.c index 0632e2a849c0..58f5cd76c8c3 100644 --- a/arch/mips/kernel/stacktrace.c +++ b/arch/mips/kernel/stacktrace.c @@ -32,7 +32,8 @@ static void save_raw_context_stack(struct stack_trace *trace, } } -static void save_context_stack(struct stack_trace *trace, struct pt_regs *regs) +static void save_context_stack(struct stack_trace *trace, + struct task_struct *tsk, struct pt_regs *regs) { unsigned long sp = regs->regs[29]; #ifdef CONFIG_KALLSYMS @@ -41,7 +42,7 @@ static void save_context_stack(struct stack_trace *trace, struct pt_regs *regs) if (raw_show_trace || !__kernel_text_address(pc)) { unsigned long stack_page = - (unsigned long)task_stack_page(current); + (unsigned long)task_stack_page(tsk); if (stack_page && sp >= stack_page && sp <= stack_page + THREAD_SIZE - 32) save_raw_context_stack(trace, sp); @@ -54,7 +55,7 @@ static void save_context_stack(struct stack_trace *trace, struct pt_regs *regs) trace->entries[trace->nr_entries++] = pc; if (trace->nr_entries >= trace->max_entries) break; - pc = unwind_stack(current, &sp, pc, &ra); + pc = unwind_stack(tsk, &sp, pc, &ra); } while (pc); #else save_raw_context_stack(trace, sp); @@ -65,13 +66,24 @@ static void save_context_stack(struct stack_trace *trace, struct pt_regs *regs) * Save stack-backtrace addresses into a stack_trace buffer. */ void save_stack_trace(struct stack_trace *trace) +{ + save_stack_trace_tsk(current, trace); +} +EXPORT_SYMBOL_GPL(save_stack_trace); + +void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { struct pt_regs dummyregs; struct pt_regs *regs = &dummyregs; WARN_ON(trace->nr_entries || !trace->max_entries); - prepare_frametrace(regs); - save_context_stack(trace, regs); + if (tsk != current) { + regs->regs[29] = tsk->thread.reg29; + regs->regs[31] = 0; + regs->cp0_epc = tsk->thread.reg31; + } else + prepare_frametrace(regs); + save_context_stack(trace, tsk, regs); } -EXPORT_SYMBOL_GPL(save_stack_trace); +EXPORT_SYMBOL_GPL(save_stack_trace_tsk); diff --git a/fs/proc/base.c b/fs/proc/base.c index ce7a6da1b6a0..eb7b4654d6aa 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -65,6 +65,7 @@ #include #include #include +#include #include #include #include @@ -337,6 +338,37 @@ static int proc_pid_wchan(struct task_struct *task, char *buffer) } #endif /* CONFIG_KALLSYMS */ +#ifdef CONFIG_STACKTRACE + +#define MAX_STACK_TRACE_DEPTH 64 + +static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) +{ + struct stack_trace trace; + unsigned long *entries; + int i; + + entries = kmalloc(MAX_STACK_TRACE_DEPTH * sizeof(*entries), GFP_KERNEL); + if (!entries) + return -ENOMEM; + + trace.nr_entries = 0; + trace.max_entries = MAX_STACK_TRACE_DEPTH; + trace.entries = entries; + trace.skip = 0; + save_stack_trace_tsk(task, &trace); + + for (i = 0; i < trace.nr_entries; i++) { + seq_printf(m, "[<%p>] %pS\n", + (void *)entries[i], (void *)entries[i]); + } + kfree(entries); + + return 0; +} +#endif + #ifdef CONFIG_SCHEDSTATS /* * Provides /proc/PID/schedstat @@ -2500,6 +2532,9 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_KALLSYMS INF("wchan", S_IRUGO, proc_pid_wchan), #endif +#ifdef CONFIG_STACKTRACE + ONE("stack", S_IRUSR, proc_pid_stack), +#endif #ifdef CONFIG_SCHEDSTATS INF("schedstat", S_IRUGO, proc_pid_schedstat), #endif @@ -2835,6 +2870,9 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_KALLSYMS INF("wchan", S_IRUGO, proc_pid_wchan), #endif +#ifdef CONFIG_STACKTRACE + ONE("stack", S_IRUSR, proc_pid_stack), +#endif #ifdef CONFIG_SCHEDSTATS INF("schedstat", S_IRUGO, proc_pid_schedstat), #endif -- cgit v1.2.3 From a808ad3b0d28411e2838117c5b2ae680ae42483c Mon Sep 17 00:00:00 2001 From: Sean MacLennan Date: Wed, 10 Dec 2008 13:16:34 +0000 Subject: [MTD] [NAND] ndfc driver The current ndfc driver only compiles under arch/ppc. This arch was removed from the kernel. I notice the event entry for the ndfc in Kconfig has been removed in 2.6.28. This patch converts the ndfc to a proper OF (OpenFirmware) driver. I can give a working example of the DTS if needed. The patch has been in production use on the PIKA Warp Appliance and is in use by others. The Warp basically boots from NAND, so the ndfc driver is very important to us. Signed-off-by: Sean MacLennan Acked-By: Josh Boyer Signed-off-by: David Woodhouse --- Documentation/powerpc/dts-bindings/4xx/ndfc.txt | 39 ++++ drivers/mtd/nand/Kconfig | 7 + drivers/mtd/nand/ndfc.c | 269 ++++++++++++------------ 3 files changed, 179 insertions(+), 136 deletions(-) create mode 100644 Documentation/powerpc/dts-bindings/4xx/ndfc.txt (limited to 'Documentation') diff --git a/Documentation/powerpc/dts-bindings/4xx/ndfc.txt b/Documentation/powerpc/dts-bindings/4xx/ndfc.txt new file mode 100644 index 000000000000..869f0b5f16e8 --- /dev/null +++ b/Documentation/powerpc/dts-bindings/4xx/ndfc.txt @@ -0,0 +1,39 @@ +AMCC NDFC (NanD Flash Controller) + +Required properties: +- compatible : "ibm,ndfc". +- reg : should specify chip select and size used for the chip (0x2000). + +Optional properties: +- ccr : NDFC config and control register value (default 0). +- bank-settings : NDFC bank configuration register value (default 0). + +Notes: +- partition(s) - follows the OF MTD standard for partitions + +Example: + +ndfc@1,0 { + compatible = "ibm,ndfc"; + reg = <0x00000001 0x00000000 0x00002000>; + ccr = <0x00001000>; + bank-settings = <0x80002222>; + #address-cells = <1>; + #size-cells = <1>; + + nand { + #address-cells = <1>; + #size-cells = <1>; + + partition@0 { + label = "kernel"; + reg = <0x00000000 0x00200000>; + }; + partition@200000 { + label = "root"; + reg = <0x00200000 0x03E00000>; + }; + }; +}; + + diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig index f8ae0400c49c..8b12e6e109d3 100644 --- a/drivers/mtd/nand/Kconfig +++ b/drivers/mtd/nand/Kconfig @@ -163,6 +163,13 @@ config MTD_NAND_S3C2410_HWECC incorrect ECC generation, and if using these, the default of software ECC is preferable. +config MTD_NAND_NDFC + tristate "NDFC NanD Flash Controller" + depends on 4xx + select MTD_NAND_ECC_SMC + help + NDFC Nand Flash Controllers are integrated in IBM/AMCC's 4xx SoCs + config MTD_NAND_S3C2410_CLKSTOP bool "S3C2410 NAND IDLE clock stop" depends on MTD_NAND_S3C2410 diff --git a/drivers/mtd/nand/ndfc.c b/drivers/mtd/nand/ndfc.c index 955959eb02d4..582cf80f555a 100644 --- a/drivers/mtd/nand/ndfc.c +++ b/drivers/mtd/nand/ndfc.c @@ -2,12 +2,20 @@ * drivers/mtd/ndfc.c * * Overview: - * Platform independend driver for NDFC (NanD Flash Controller) + * Platform independent driver for NDFC (NanD Flash Controller) * integrated into EP440 cores * + * Ported to an OF platform driver by Sean MacLennan + * + * The NDFC supports multiple chips, but this driver only supports a + * single chip since I do not have access to any boards with + * multiple chips. + * * Author: Thomas Gleixner * * Copyright 2006 IBM + * Copyright 2008 PIKA Technologies + * Sean MacLennan * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the @@ -21,27 +29,20 @@ #include #include #include -#include - +#include #include -#ifdef CONFIG_40x -#include -#else -#include -#endif - -struct ndfc_nand_mtd { - struct mtd_info mtd; - struct nand_chip chip; - struct platform_nand_chip *pl_chip; -}; -static struct ndfc_nand_mtd ndfc_mtd[NDFC_MAX_BANKS]; struct ndfc_controller { - void __iomem *ndfcbase; - struct nand_hw_control ndfc_control; - atomic_t childs_active; + struct of_device *ofdev; + void __iomem *ndfcbase; + struct mtd_info mtd; + struct nand_chip chip; + int chip_select; + struct nand_hw_control ndfc_control; +#ifdef CONFIG_MTD_PARTITIONS + struct mtd_partition *parts; +#endif }; static struct ndfc_controller ndfc_ctrl; @@ -50,17 +51,14 @@ static void ndfc_select_chip(struct mtd_info *mtd, int chip) { uint32_t ccr; struct ndfc_controller *ndfc = &ndfc_ctrl; - struct nand_chip *nandchip = mtd->priv; - struct ndfc_nand_mtd *nandmtd = nandchip->priv; - struct platform_nand_chip *pchip = nandmtd->pl_chip; - ccr = __raw_readl(ndfc->ndfcbase + NDFC_CCR); + ccr = in_be32(ndfc->ndfcbase + NDFC_CCR); if (chip >= 0) { ccr &= ~NDFC_CCR_BS_MASK; - ccr |= NDFC_CCR_BS(chip + pchip->chip_offset); + ccr |= NDFC_CCR_BS(chip + ndfc->chip_select); } else ccr |= NDFC_CCR_RESET_CE; - __raw_writel(ccr, ndfc->ndfcbase + NDFC_CCR); + out_be32(ndfc->ndfcbase + NDFC_CCR, ccr); } static void ndfc_hwcontrol(struct mtd_info *mtd, int cmd, unsigned int ctrl) @@ -80,7 +78,7 @@ static int ndfc_ready(struct mtd_info *mtd) { struct ndfc_controller *ndfc = &ndfc_ctrl; - return __raw_readl(ndfc->ndfcbase + NDFC_STAT) & NDFC_STAT_IS_READY; + return in_be32(ndfc->ndfcbase + NDFC_STAT) & NDFC_STAT_IS_READY; } static void ndfc_enable_hwecc(struct mtd_info *mtd, int mode) @@ -88,9 +86,9 @@ static void ndfc_enable_hwecc(struct mtd_info *mtd, int mode) uint32_t ccr; struct ndfc_controller *ndfc = &ndfc_ctrl; - ccr = __raw_readl(ndfc->ndfcbase + NDFC_CCR); + ccr = in_be32(ndfc->ndfcbase + NDFC_CCR); ccr |= NDFC_CCR_RESET_ECC; - __raw_writel(ccr, ndfc->ndfcbase + NDFC_CCR); + out_be32(ndfc->ndfcbase + NDFC_CCR, ccr); wmb(); } @@ -102,9 +100,10 @@ static int ndfc_calculate_ecc(struct mtd_info *mtd, uint8_t *p = (uint8_t *)&ecc; wmb(); - ecc = __raw_readl(ndfc->ndfcbase + NDFC_ECC); - ecc_code[0] = p[1]; - ecc_code[1] = p[2]; + ecc = in_be32(ndfc->ndfcbase + NDFC_ECC); + /* The NDFC uses Smart Media (SMC) bytes order */ + ecc_code[0] = p[2]; + ecc_code[1] = p[1]; ecc_code[2] = p[3]; return 0; @@ -123,7 +122,7 @@ static void ndfc_read_buf(struct mtd_info *mtd, uint8_t *buf, int len) uint32_t *p = (uint32_t *) buf; for(;len > 0; len -= 4) - *p++ = __raw_readl(ndfc->ndfcbase + NDFC_DATA); + *p++ = in_be32(ndfc->ndfcbase + NDFC_DATA); } static void ndfc_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len) @@ -132,7 +131,7 @@ static void ndfc_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len) uint32_t *p = (uint32_t *) buf; for(;len > 0; len -= 4) - __raw_writel(*p++, ndfc->ndfcbase + NDFC_DATA); + out_be32(ndfc->ndfcbase + NDFC_DATA, *p++); } static int ndfc_verify_buf(struct mtd_info *mtd, const uint8_t *buf, int len) @@ -141,7 +140,7 @@ static int ndfc_verify_buf(struct mtd_info *mtd, const uint8_t *buf, int len) uint32_t *p = (uint32_t *) buf; for(;len > 0; len -= 4) - if (*p++ != __raw_readl(ndfc->ndfcbase + NDFC_DATA)) + if (*p++ != in_be32(ndfc->ndfcbase + NDFC_DATA)) return -EFAULT; return 0; } @@ -149,10 +148,19 @@ static int ndfc_verify_buf(struct mtd_info *mtd, const uint8_t *buf, int len) /* * Initialize chip structure */ -static void ndfc_chip_init(struct ndfc_nand_mtd *mtd) +static int ndfc_chip_init(struct ndfc_controller *ndfc, + struct device_node *node) { - struct ndfc_controller *ndfc = &ndfc_ctrl; - struct nand_chip *chip = &mtd->chip; +#ifdef CONFIG_MTD_PARTITIONS +#ifdef CONFIG_MTD_CMDLINE_PARTS + static const char *part_types[] = { "cmdlinepart", NULL }; +#else + static const char *part_types[] = { NULL }; +#endif +#endif + struct device_node *flash_np; + struct nand_chip *chip = &ndfc->chip; + int ret; chip->IO_ADDR_R = ndfc->ndfcbase + NDFC_DATA; chip->IO_ADDR_W = ndfc->ndfcbase + NDFC_DATA; @@ -160,8 +168,6 @@ static void ndfc_chip_init(struct ndfc_nand_mtd *mtd) chip->dev_ready = ndfc_ready; chip->select_chip = ndfc_select_chip; chip->chip_delay = 50; - chip->priv = mtd; - chip->options = mtd->pl_chip->options; chip->controller = &ndfc->ndfc_control; chip->read_buf = ndfc_read_buf; chip->write_buf = ndfc_write_buf; @@ -172,143 +178,136 @@ static void ndfc_chip_init(struct ndfc_nand_mtd *mtd) chip->ecc.mode = NAND_ECC_HW; chip->ecc.size = 256; chip->ecc.bytes = 3; - chip->ecclayout = chip->ecc.layout = mtd->pl_chip->ecclayout; - mtd->mtd.priv = chip; - mtd->mtd.owner = THIS_MODULE; -} - -static int ndfc_chip_probe(struct platform_device *pdev) -{ - struct platform_nand_chip *nc = pdev->dev.platform_data; - struct ndfc_chip_settings *settings = nc->priv; - struct ndfc_controller *ndfc = &ndfc_ctrl; - struct ndfc_nand_mtd *nandmtd; - - if (nc->chip_offset >= NDFC_MAX_BANKS || nc->nr_chips > NDFC_MAX_BANKS) - return -EINVAL; - - /* Set the bank settings */ - __raw_writel(settings->bank_settings, - ndfc->ndfcbase + NDFC_BCFG0 + (nc->chip_offset << 2)); - nandmtd = &ndfc_mtd[pdev->id]; - if (nandmtd->pl_chip) - return -EBUSY; + ndfc->mtd.priv = chip; + ndfc->mtd.owner = THIS_MODULE; - nandmtd->pl_chip = nc; - ndfc_chip_init(nandmtd); - - /* Scan for chips */ - if (nand_scan(&nandmtd->mtd, nc->nr_chips)) { - nandmtd->pl_chip = NULL; + flash_np = of_get_next_child(node, NULL); + if (!flash_np) return -ENODEV; + + ndfc->mtd.name = kasprintf(GFP_KERNEL, "%s.%s", + ndfc->ofdev->dev.bus_id, flash_np->name); + if (!ndfc->mtd.name) { + ret = -ENOMEM; + goto err; } -#ifdef CONFIG_MTD_PARTITIONS - printk("Number of partitions %d\n", nc->nr_partitions); - if (nc->nr_partitions) { - /* Add the full device, so complete dumps can be made */ - add_mtd_device(&nandmtd->mtd); - add_mtd_partitions(&nandmtd->mtd, nc->partitions, - nc->nr_partitions); + ret = nand_scan(&ndfc->mtd, 1); + if (ret) + goto err; - } else -#else - add_mtd_device(&nandmtd->mtd); +#ifdef CONFIG_MTD_PARTITIONS + ret = parse_mtd_partitions(&ndfc->mtd, part_types, &ndfc->parts, 0); + if (ret < 0) + goto err; + +#ifdef CONFIG_MTD_OF_PARTS + if (ret == 0) { + ret = of_mtd_parse_partitions(&ndfc->ofdev->dev, flash_np, + &ndfc->parts); + if (ret < 0) + goto err; + } #endif - atomic_inc(&ndfc->childs_active); - return 0; -} + if (ret > 0) + ret = add_mtd_partitions(&ndfc->mtd, ndfc->parts, ret); + else +#endif + ret = add_mtd_device(&ndfc->mtd); -static int ndfc_chip_remove(struct platform_device *pdev) -{ - return 0; +err: + of_node_put(flash_np); + if (ret) + kfree(ndfc->mtd.name); + return ret; } -static int ndfc_nand_probe(struct platform_device *pdev) +static int __devinit ndfc_probe(struct of_device *ofdev, + const struct of_device_id *match) { - struct platform_nand_ctrl *nc = pdev->dev.platform_data; - struct ndfc_controller_settings *settings = nc->priv; - struct resource *res = pdev->resource; struct ndfc_controller *ndfc = &ndfc_ctrl; - unsigned long long phys = settings->ndfc_erpn | res->start; + const u32 *reg; + u32 ccr; + int err, len; -#ifndef CONFIG_PHYS_64BIT - ndfc->ndfcbase = ioremap((phys_addr_t)phys, res->end - res->start + 1); -#else - ndfc->ndfcbase = ioremap64(phys, res->end - res->start + 1); -#endif + spin_lock_init(&ndfc->ndfc_control.lock); + init_waitqueue_head(&ndfc->ndfc_control.wq); + ndfc->ofdev = ofdev; + dev_set_drvdata(&ofdev->dev, ndfc); + + /* Read the reg property to get the chip select */ + reg = of_get_property(ofdev->node, "reg", &len); + if (reg == NULL || len != 12) { + dev_err(&ofdev->dev, "unable read reg property (%d)\n", len); + return -ENOENT; + } + ndfc->chip_select = reg[0]; + + ndfc->ndfcbase = of_iomap(ofdev->node, 0); if (!ndfc->ndfcbase) { - printk(KERN_ERR "NDFC: ioremap failed\n"); + dev_err(&ofdev->dev, "failed to get memory\n"); return -EIO; } - __raw_writel(settings->ccr_settings, ndfc->ndfcbase + NDFC_CCR); + ccr = NDFC_CCR_BS(ndfc->chip_select); - spin_lock_init(&ndfc->ndfc_control.lock); - init_waitqueue_head(&ndfc->ndfc_control.wq); + /* It is ok if ccr does not exist - just default to 0 */ + reg = of_get_property(ofdev->node, "ccr", NULL); + if (reg) + ccr |= *reg; - platform_set_drvdata(pdev, ndfc); + out_be32(ndfc->ndfcbase + NDFC_CCR, ccr); - printk("NDFC NAND Driver initialized. Chip-Rev: 0x%08x\n", - __raw_readl(ndfc->ndfcbase + NDFC_REVID)); + /* Set the bank settings if given */ + reg = of_get_property(ofdev->node, "bank-settings", NULL); + if (reg) { + int offset = NDFC_BCFG0 + (ndfc->chip_select << 2); + out_be32(ndfc->ndfcbase + offset, *reg); + } + + err = ndfc_chip_init(ndfc, ofdev->node); + if (err) { + iounmap(ndfc->ndfcbase); + return err; + } return 0; } -static int ndfc_nand_remove(struct platform_device *pdev) +static int __devexit ndfc_remove(struct of_device *ofdev) { - struct ndfc_controller *ndfc = platform_get_drvdata(pdev); + struct ndfc_controller *ndfc = dev_get_drvdata(&ofdev->dev); - if (atomic_read(&ndfc->childs_active)) - return -EBUSY; + nand_release(&ndfc->mtd); - if (ndfc) { - platform_set_drvdata(pdev, NULL); - iounmap(ndfc_ctrl.ndfcbase); - ndfc_ctrl.ndfcbase = NULL; - } return 0; } -/* driver device registration */ - -static struct platform_driver ndfc_chip_driver = { - .probe = ndfc_chip_probe, - .remove = ndfc_chip_remove, - .driver = { - .name = "ndfc-chip", - .owner = THIS_MODULE, - }, +static const struct of_device_id ndfc_match[] = { + { .compatible = "ibm,ndfc", }, + {} }; +MODULE_DEVICE_TABLE(of, ndfc_match); -static struct platform_driver ndfc_nand_driver = { - .probe = ndfc_nand_probe, - .remove = ndfc_nand_remove, - .driver = { - .name = "ndfc-nand", - .owner = THIS_MODULE, +static struct of_platform_driver ndfc_driver = { + .driver = { + .name = "ndfc", }, + .match_table = ndfc_match, + .probe = ndfc_probe, + .remove = __devexit_p(ndfc_remove), }; static int __init ndfc_nand_init(void) { - int ret; - - spin_lock_init(&ndfc_ctrl.ndfc_control.lock); - init_waitqueue_head(&ndfc_ctrl.ndfc_control.wq); - - ret = platform_driver_register(&ndfc_nand_driver); - if (!ret) - ret = platform_driver_register(&ndfc_chip_driver); - return ret; + return of_register_platform_driver(&ndfc_driver); } static void __exit ndfc_nand_exit(void) { - platform_driver_unregister(&ndfc_chip_driver); - platform_driver_unregister(&ndfc_nand_driver); + of_unregister_platform_driver(&ndfc_driver); } module_init(ndfc_nand_init); @@ -316,6 +315,4 @@ module_exit(ndfc_nand_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Thomas Gleixner "); -MODULE_DESCRIPTION("Platform driver for NDFC"); -MODULE_ALIAS("platform:ndfc-chip"); -MODULE_ALIAS("platform:ndfc-nand"); +MODULE_DESCRIPTION("OF Platform driver for NDFC"); -- cgit v1.2.3 From 28405d8d9ce05f5bd869ef8b48da5086f9527d73 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 5 Jan 2009 17:14:31 -0700 Subject: async_tx, dmaengine: document channel allocation and api rework "Wouldn't it be better if the dmaengine layer made sure it didn't pass the same channel several times to a client? I mean, you seem concerned that the memcpy() API should be transparent and easy to use, but the whole registration interface is just ridiculously complicated..." - Haavard The dmaengine and async_tx registration/allocation interface is indeed needlessly complicated. This redesign has the following goals: 1/ Simplify reference counting: dma channels are not something one would expect to be hotplugged, it should be an exceptional event handled by drivers not something clients should be mandated to handle in a callback. The common case channel removal event is 'rmmod ', which for simplicity should be disallowed if the channel is in use. 2/ Add an interface for requesting exclusive access to a channel suitable to device-to-memory users. 3/ Convert all memory-to-memory users over to a common allocator, the goal here is to not have competing channel allocation schemes. The only competition should be between device-to-memory exclusive allocations and the memory-to-memory usage case where channels are shared between multiple "clients". Cc: Haavard Skinnemoen Cc: Neil Brown Cc: Jeff Garzik Reviewed-by: Andrew Morton Signed-off-by: Dan Williams --- Documentation/crypto/async-tx-api.txt | 96 ++++++++++++++++------------------- Documentation/dmaengine.txt | 1 + 2 files changed, 45 insertions(+), 52 deletions(-) create mode 100644 Documentation/dmaengine.txt (limited to 'Documentation') diff --git a/Documentation/crypto/async-tx-api.txt b/Documentation/crypto/async-tx-api.txt index c1e9545c59bd..9f59fcbf5d82 100644 --- a/Documentation/crypto/async-tx-api.txt +++ b/Documentation/crypto/async-tx-api.txt @@ -13,9 +13,9 @@ 3.6 Constraints 3.7 Example -4 DRIVER DEVELOPER NOTES +4 DMAENGINE DRIVER DEVELOPER NOTES 4.1 Conformance points -4.2 "My application needs finer control of hardware channels" +4.2 "My application needs exclusive control of hardware channels" 5 SOURCE @@ -150,6 +150,7 @@ ops_run_* and ops_complete_* routines in drivers/md/raid5.c for more implementation examples. 4 DRIVER DEVELOPMENT NOTES + 4.1 Conformance points: There are a few conformance points required in dmaengine drivers to accommodate assumptions made by applications using the async_tx API: @@ -158,58 +159,49 @@ accommodate assumptions made by applications using the async_tx API: 3/ Use async_tx_run_dependencies() in the descriptor clean up path to handle submission of dependent operations -4.2 "My application needs finer control of hardware channels" -This requirement seems to arise from cases where a DMA engine driver is -trying to support device-to-memory DMA. The dmaengine and async_tx -implementations were designed for offloading memory-to-memory -operations; however, there are some capabilities of the dmaengine layer -that can be used for platform-specific channel management. -Platform-specific constraints can be handled by registering the -application as a 'dma_client' and implementing a 'dma_event_callback' to -apply a filter to the available channels in the system. Before showing -how to implement a custom dma_event callback some background of -dmaengine's client support is required. - -The following routines in dmaengine support multiple clients requesting -use of a channel: -- dma_async_client_register(struct dma_client *client) -- dma_async_client_chan_request(struct dma_client *client) - -dma_async_client_register takes a pointer to an initialized dma_client -structure. It expects that the 'event_callback' and 'cap_mask' fields -are already initialized. - -dma_async_client_chan_request triggers dmaengine to notify the client of -all channels that satisfy the capability mask. It is up to the client's -event_callback routine to track how many channels the client needs and -how many it is currently using. The dma_event_callback routine returns a -dma_state_client code to let dmaengine know the status of the -allocation. - -Below is the example of how to extend this functionality for -platform-specific filtering of the available channels beyond the -standard capability mask: - -static enum dma_state_client -my_dma_client_callback(struct dma_client *client, - struct dma_chan *chan, enum dma_state state) -{ - struct dma_device *dma_dev; - struct my_platform_specific_dma *plat_dma_dev; - - dma_dev = chan->device; - plat_dma_dev = container_of(dma_dev, - struct my_platform_specific_dma, - dma_dev); - - if (!plat_dma_dev->platform_specific_capability) - return DMA_DUP; - - . . . -} +4.2 "My application needs exclusive control of hardware channels" +Primarily this requirement arises from cases where a DMA engine driver +is being used to support device-to-memory operations. A channel that is +performing these operations cannot, for many platform specific reasons, +be shared. For these cases the dma_request_channel() interface is +provided. + +The interface is: +struct dma_chan *dma_request_channel(dma_cap_mask_t mask, + dma_filter_fn filter_fn, + void *filter_param); + +Where dma_filter_fn is defined as: +typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param); + +When the optional 'filter_fn' parameter is set to NULL +dma_request_channel simply returns the first channel that satisfies the +capability mask. Otherwise, when the mask parameter is insufficient for +specifying the necessary channel, the filter_fn routine can be used to +disposition the available channels in the system. The filter_fn routine +is called once for each free channel in the system. Upon seeing a +suitable channel filter_fn returns DMA_ACK which flags that channel to +be the return value from dma_request_channel. A channel allocated via +this interface is exclusive to the caller, until dma_release_channel() +is called. + +The DMA_PRIVATE capability flag is used to tag dma devices that should +not be used by the general-purpose allocator. It can be set at +initialization time if it is known that a channel will always be +private. Alternatively, it is set when dma_request_channel() finds an +unused "public" channel. + +A couple caveats to note when implementing a driver and consumer: +1/ Once a channel has been privately allocated it will no longer be + considered by the general-purpose allocator even after a call to + dma_release_channel(). +2/ Since capabilities are specified at the device level a dma_device + with multiple channels will either have all channels public, or all + channels private. 5 SOURCE -include/linux/dmaengine.h: core header file for DMA drivers and clients + +include/linux/dmaengine.h: core header file for DMA drivers and api users drivers/dma/dmaengine.c: offload engine channel management routines drivers/dma/: location for offload engine drivers include/linux/async_tx.h: core header file for the async_tx api diff --git a/Documentation/dmaengine.txt b/Documentation/dmaengine.txt new file mode 100644 index 000000000000..0c1c2f63c0a9 --- /dev/null +++ b/Documentation/dmaengine.txt @@ -0,0 +1 @@ +See Documentation/crypto/async-tx-api.txt -- cgit v1.2.3 From b3881f74b31b7d47d0f1c4d89ac3e7f0b9c05e3e Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 5 Jan 2009 22:46:26 -0500 Subject: ext4: Add mount option to set kjournald's I/O priority Signed-off-by: "Theodore Ts'o" Cc: Jens Axboe --- Documentation/filesystems/ext4.txt | 7 +++++++ fs/ext4/super.c | 29 +++++++++++++++++++++++++---- fs/ioprio.c | 3 ++- include/linux/ioprio.h | 2 ++ 4 files changed, 36 insertions(+), 5 deletions(-) (limited to 'Documentation') diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index 9ec29d86ff8b..8938949b201e 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -308,6 +308,13 @@ min_batch_time=usec This parameter sets the commit time (as multi-threaded, synchronous workloads on very fast disks, at the cost of increasing latency. +journal_ioprio=prio The I/O priority (from 0 to 7, where 0 is the + highest priorty) which should be used for I/O + operations submitted by kjournald2 during a + commit operation. This defaults to 3, which is + a slightly higher priority than the default I/O + priority. + Data Mode ========= There are 3 different data modes: diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8036392b2121..8ff8709828fd 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1013,7 +1013,7 @@ enum { Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota, Opt_grpquota, Opt_extents, Opt_noextents, Opt_i_version, Opt_stripe, Opt_delalloc, Opt_nodelalloc, - Opt_inode_readahead_blks + Opt_inode_readahead_blks, Opt_journal_ioprio }; static const match_table_t tokens = { @@ -1074,6 +1074,7 @@ static const match_table_t tokens = { {Opt_delalloc, "delalloc"}, {Opt_nodelalloc, "nodelalloc"}, {Opt_inode_readahead_blks, "inode_readahead_blks=%u"}, + {Opt_journal_ioprio, "journal_ioprio=%u"}, {Opt_err, NULL}, }; @@ -1098,8 +1099,11 @@ static ext4_fsblk_t get_sb_block(void **data) return sb_block; } +#define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3)) + static int parse_options(char *options, struct super_block *sb, unsigned long *journal_devnum, + unsigned int *journal_ioprio, ext4_fsblk_t *n_blocks_count, int is_remount) { struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -1492,6 +1496,14 @@ set_qf_format: return 0; sbi->s_inode_readahead_blks = option; break; + case Opt_journal_ioprio: + if (match_int(&args[0], &option)) + return 0; + if (option < 0 || option > 7) + break; + *journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, + option); + break; default: printk(KERN_ERR "EXT4-fs: Unrecognized mount option \"%s\" " @@ -2035,6 +2047,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) int features; __u64 blocks_count; int err; + unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) @@ -2141,7 +2154,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) set_opt(sbi->s_mount_opt, DELALLOC); - if (!parse_options((char *) data, sb, &journal_devnum, NULL, 0)) + if (!parse_options((char *) data, sb, &journal_devnum, + &journal_ioprio, NULL, 0)) goto failed_mount; sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | @@ -2506,6 +2520,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) default: break; } + set_task_ioprio(sbi->s_journal->j_task, journal_ioprio); no_journal: @@ -3127,6 +3142,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) unsigned long old_sb_flags; struct ext4_mount_options old_opts; ext4_group_t g; + unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; int err; #ifdef CONFIG_QUOTA int i; @@ -3145,11 +3161,14 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) for (i = 0; i < MAXQUOTAS; i++) old_opts.s_qf_names[i] = sbi->s_qf_names[i]; #endif + if (sbi->s_journal && sbi->s_journal->j_task->io_context) + journal_ioprio = sbi->s_journal->j_task->io_context->ioprio; /* * Allow the "check" option to be passed as a remount option. */ - if (!parse_options(data, sb, NULL, &n_blocks_count, 1)) { + if (!parse_options(data, sb, NULL, &journal_ioprio, + &n_blocks_count, 1)) { err = -EINVAL; goto restore_opts; } @@ -3162,8 +3181,10 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) es = sbi->s_es; - if (sbi->s_journal) + if (sbi->s_journal) { ext4_init_journal_params(sb, sbi->s_journal); + set_task_ioprio(sbi->s_journal->j_task, journal_ioprio); + } if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY) || n_blocks_count > ext4_blocks_count(es)) { diff --git a/fs/ioprio.c b/fs/ioprio.c index 3569e0ad86a2..1a39ac370942 100644 --- a/fs/ioprio.c +++ b/fs/ioprio.c @@ -27,7 +27,7 @@ #include #include -static int set_task_ioprio(struct task_struct *task, int ioprio) +int set_task_ioprio(struct task_struct *task, int ioprio) { int err; struct io_context *ioc; @@ -70,6 +70,7 @@ static int set_task_ioprio(struct task_struct *task, int ioprio) task_unlock(task); return err; } +EXPORT_SYMBOL_GPL(set_task_ioprio); asmlinkage long sys_ioprio_set(int which, int who, int ioprio) { diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index f98a656b17e5..76dad4808847 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -86,4 +86,6 @@ static inline int task_nice_ioclass(struct task_struct *task) */ extern int ioprio_best(unsigned short aprio, unsigned short bprio); +extern int set_task_ioprio(struct task_struct *task, int ioprio); + #endif -- cgit v1.2.3 From 025dfdafe77f20b3890981a394774baab7b9c827 Mon Sep 17 00:00:00 2001 From: Frederik Schwarzer Date: Thu, 16 Oct 2008 19:02:37 +0200 Subject: trivial: fix then -> than typos in comments and documentation - (better, more, bigger ...) then -> (...) than Signed-off-by: Frederik Schwarzer Signed-off-by: Jiri Kosina --- Documentation/hwmon/abituguru-datasheet | 6 +++--- Documentation/networking/rxrpc.txt | 2 +- Documentation/scsi/ChangeLog.lpfc | 2 +- arch/blackfin/kernel/kgdb.c | 2 +- arch/ia64/kernel/kprobes.c | 2 +- arch/m68k/Kconfig | 2 +- arch/mips/pmc-sierra/yosemite/atmel_read_eeprom.c | 2 +- arch/powerpc/kernel/kprobes.c | 2 +- arch/powerpc/oprofile/cell/spu_profiler.c | 2 +- arch/s390/Kconfig | 2 +- arch/s390/kernel/kprobes.c | 2 +- arch/sparc/kernel/kprobes.c | 2 +- arch/x86/kernel/kprobes.c | 2 +- arch/x86/kernel/mfgpt_32.c | 2 +- drivers/hwmon/fschmd.c | 2 +- drivers/infiniband/hw/mlx4/cq.c | 2 +- drivers/message/i2o/i2o_scsi.c | 2 +- drivers/mtd/devices/pmc551.c | 2 +- drivers/mtd/ubi/eba.c | 2 +- drivers/mtd/ubi/io.c | 2 +- drivers/mtd/ubi/scan.c | 2 +- drivers/mtd/ubi/ubi-media.h | 4 ++-- drivers/mtd/ubi/vtbl.c | 2 +- drivers/mtd/ubi/wl.c | 4 ++-- drivers/net/bnx2x_link.c | 2 +- drivers/net/e1000/e1000_hw.c | 4 ++-- drivers/net/slip.h | 2 +- drivers/net/tehuti.c | 4 ++-- drivers/net/tokenring/smctr.c | 2 +- drivers/net/wireless/ipw2x00/ipw2100.c | 2 +- drivers/net/wireless/rt2x00/rt2x00crypto.c | 4 ++-- drivers/net/wireless/strip.c | 2 +- drivers/s390/block/dasd_eer.c | 4 ++-- drivers/s390/char/vmlogrdr.c | 4 ++-- drivers/scsi/lpfc/lpfc_hbadisc.c | 4 ++-- drivers/scsi/lpfc/lpfc_sli.c | 10 +++++----- drivers/serial/crisv10.c | 4 ++-- drivers/video/console/vgacon.c | 2 +- fs/ocfs2/cluster/heartbeat.c | 2 +- fs/proc/task_nommu.c | 2 +- fs/ubifs/Kconfig | 2 +- fs/ubifs/budget.c | 4 ++-- fs/ubifs/gc.c | 2 +- fs/ubifs/journal.c | 2 +- fs/ubifs/shrinker.c | 2 +- fs/xfs/linux-2.6/xfs_super.c | 2 +- include/linux/mtd/mtd.h | 2 +- include/linux/spi/spi.h | 4 ++-- include/mtd/ubi-user.h | 2 +- kernel/pid.c | 2 +- kernel/time/jiffies.c | 2 +- net/sctp/auth.c | 4 ++-- net/sctp/sm_statefuns.c | 6 +++--- net/sctp/socket.c | 2 +- net/sctp/tsnmap.c | 2 +- sound/usb/usx2y/usbusx2y.c | 2 +- 56 files changed, 76 insertions(+), 76 deletions(-) (limited to 'Documentation') diff --git a/Documentation/hwmon/abituguru-datasheet b/Documentation/hwmon/abituguru-datasheet index aef5a9b36846..4d184f2db0ea 100644 --- a/Documentation/hwmon/abituguru-datasheet +++ b/Documentation/hwmon/abituguru-datasheet @@ -74,7 +74,7 @@ a sensor. Notice that some banks have both a read and a write address this is how the uGuru determines if a read from or a write to the bank is taking place, thus when reading you should always use the read address and when writing the -write address. The write address is always one (1) more then the read address. +write address. The write address is always one (1) more than the read address. uGuru ready @@ -224,7 +224,7 @@ Bit 3: Beep if alarm (RW) Bit 4: 1 if alarm cause measured temp is over the warning threshold (R) Bit 5: 1 if alarm cause measured volt is over the max threshold (R) Bit 6: 1 if alarm cause measured volt is under the min threshold (R) -Bit 7: Volt sensor: Shutdown if alarm persist for more then 4 seconds (RW) +Bit 7: Volt sensor: Shutdown if alarm persist for more than 4 seconds (RW) Temp sensor: Shutdown if temp is over the shutdown threshold (RW) * This bit is only honored/used by the uGuru if a temp sensor is connected @@ -293,7 +293,7 @@ Byte 0: Alarm behaviour for the selected sensor. A 1 enables the described behaviour. Bit 0: Give an alarm if measured rpm is under the min threshold (RW) Bit 3: Beep if alarm (RW) -Bit 7: Shutdown if alarm persist for more then 4 seconds (RW) +Bit 7: Shutdown if alarm persist for more than 4 seconds (RW) Byte 1: min threshold (scale as bank 0x26) diff --git a/Documentation/networking/rxrpc.txt b/Documentation/networking/rxrpc.txt index c3669a3fb4af..60d05eb77c64 100644 --- a/Documentation/networking/rxrpc.txt +++ b/Documentation/networking/rxrpc.txt @@ -540,7 +540,7 @@ A client would issue an operation by: MSG_MORE should be set in msghdr::msg_flags on all but the last part of the request. Multiple requests may be made simultaneously. - If a call is intended to go to a destination other then the default + If a call is intended to go to a destination other than the default specified through connect(), then msghdr::msg_name should be set on the first request message of that call. diff --git a/Documentation/scsi/ChangeLog.lpfc b/Documentation/scsi/ChangeLog.lpfc index ae3f962a7cfc..ff19a52fe004 100644 --- a/Documentation/scsi/ChangeLog.lpfc +++ b/Documentation/scsi/ChangeLog.lpfc @@ -733,7 +733,7 @@ Changes from 20040920 to 20041018 I/O completion path a little more, especially taking care of fast-pathing the non-error case. Also removes tons of dead members and defines from lpfc_scsi.h - e.g. lpfc_target is down - to nothing more then the lpfc_nodelist pointer. + to nothing more than the lpfc_nodelist pointer. * Added binary sysfs file to issue mbox commands * Replaced #if __BIG_ENDIAN with #if __BIG_ENDIAN_BITFIELD for compatibility with the user space applications. diff --git a/arch/blackfin/kernel/kgdb.c b/arch/blackfin/kernel/kgdb.c index b795a207742c..1c5afaeb9504 100644 --- a/arch/blackfin/kernel/kgdb.c +++ b/arch/blackfin/kernel/kgdb.c @@ -105,7 +105,7 @@ void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) * Extracts ebp, esp and eip values understandable by gdb from the values * saved by switch_to. * thread.esp points to ebp. flags and ebp are pushed in switch_to hence esp - * prior to entering switch_to is 8 greater then the value that is saved. + * prior to entering switch_to is 8 greater than the value that is saved. * If switch_to changes, change following code appropriately. */ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p) diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index f07688da947c..0017b9de2ddf 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -434,7 +434,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) /* * It is possible to have multiple instances associated with a given * task either because an multiple functions in the call path - * have a return probe installed on them, and/or more then one return + * have a return probe installed on them, and/or more than one return * return probe was registered for a target function. * * We can handle this because: diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index c825bde17cb3..fb87c08c6b57 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -303,7 +303,7 @@ config M68KFPU_EMU_EXTRAPREC correct rounding, the emulator can (often) do the same but this extra calculation can cost quite some time, so you can disable it here. The emulator will then "only" calculate with a 64 bit - mantissa and round slightly incorrect, what is more then enough + mantissa and round slightly incorrect, what is more than enough for normal usage. config M68KFPU_EMU_ONLY diff --git a/arch/mips/pmc-sierra/yosemite/atmel_read_eeprom.c b/arch/mips/pmc-sierra/yosemite/atmel_read_eeprom.c index 97862f45496d..caf5e9a0acc7 100644 --- a/arch/mips/pmc-sierra/yosemite/atmel_read_eeprom.c +++ b/arch/mips/pmc-sierra/yosemite/atmel_read_eeprom.c @@ -148,7 +148,7 @@ int read_eeprom(char *buffer, int eeprom_size, int size) send_byte(W_HEADER); recv_ack(); - /* EEPROM with size of more then 2K need two byte addressing */ + /* EEPROM with size of more than 2K need two byte addressing */ if (eeprom_size > 2048) { send_byte(0x00); recv_ack(); diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index de79915452c8..b29005a5a8f5 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -316,7 +316,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, /* * It is possible to have multiple instances associated with a given * task either because an multiple functions in the call path - * have a return probe installed on them, and/or more then one return + * have a return probe installed on them, and/or more than one return * return probe was registered for a target function. * * We can handle this because: diff --git a/arch/powerpc/oprofile/cell/spu_profiler.c b/arch/powerpc/oprofile/cell/spu_profiler.c index dd499c3e9da7..83faa958b9d4 100644 --- a/arch/powerpc/oprofile/cell/spu_profiler.c +++ b/arch/powerpc/oprofile/cell/spu_profiler.c @@ -49,7 +49,7 @@ void set_spu_profiling_frequency(unsigned int freq_khz, unsigned int cycles_rese * of precision. This is close enough for the purpose at hand. * * The value of the timeout should be small enough that the hw - * trace buffer will not get more then about 1/3 full for the + * trace buffer will not get more than about 1/3 full for the * maximum user specified (the LFSR value) hw sampling frequency. * This is to ensure the trace buffer will never fill even if the * kernel thread scheduling varies under a heavy system load. diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 19577aeffd7b..a94a3c3ae932 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -299,7 +299,7 @@ config WARN_STACK This option enables the compiler options -mwarn-framesize and -mwarn-dynamicstack. If the compiler supports these options it will generate warnings for function which either use alloca or - create a stack frame bigger then CONFIG_WARN_STACK_SIZE. + create a stack frame bigger than CONFIG_WARN_STACK_SIZE. Say N if you are unsure. diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 569079ec4ff0..267f6698680a 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -381,7 +381,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, /* * It is possible to have multiple instances associated with a given * task either because an multiple functions in the call path - * have a return probe installed on them, and/or more then one return + * have a return probe installed on them, and/or more than one return * return probe was registered for a target function. * * We can handle this because: diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c index 201a6e547e4a..3bc6527c95af 100644 --- a/arch/sparc/kernel/kprobes.c +++ b/arch/sparc/kernel/kprobes.c @@ -517,7 +517,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) /* * It is possible to have multiple instances associated with a given * task either because an multiple functions in the call path - * have a return probe installed on them, and/or more then one return + * have a return probe installed on them, and/or more than one return * return probe was registered for a target function. * * We can handle this because: diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 6c27679ec6aa..a116e6d5726c 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -694,7 +694,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) /* * It is possible to have multiple instances associated with a given * task either because multiple functions in the call path have - * return probes installed on them, and/or more then one + * return probes installed on them, and/or more than one * return probe was registered for a target function. * * We can handle this because: diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c index c12314c9e86f..8815f3c7fec7 100644 --- a/arch/x86/kernel/mfgpt_32.c +++ b/arch/x86/kernel/mfgpt_32.c @@ -252,7 +252,7 @@ EXPORT_SYMBOL_GPL(geode_mfgpt_alloc_timer); /* * The MFPGT timers on the CS5536 provide us with suitable timers to use * as clock event sources - not as good as a HPET or APIC, but certainly - * better then the PIT. This isn't a general purpose MFGPT driver, but + * better than the PIT. This isn't a general purpose MFGPT driver, but * a simplified one designed specifically to act as a clock event source. * For full details about the MFGPT, please consult the CS5536 data sheet. */ diff --git a/drivers/hwmon/fschmd.c b/drivers/hwmon/fschmd.c index 967170368933..8b2d756595d9 100644 --- a/drivers/hwmon/fschmd.c +++ b/drivers/hwmon/fschmd.c @@ -75,7 +75,7 @@ static const u8 FSCHMD_REG_VOLT[3] = { 0x45, 0x42, 0x48 }; /* minimum pwm at which the fan is driven (pwm can by increased depending on the temp. Notice that for the scy some fans share there minimum speed. - Also notice that with the scy the sensor order is different then with the + Also notice that with the scy the sensor order is different than with the other chips, this order was in the 2.4 driver and kept for consistency. */ static const u8 FSCHMD_REG_FAN_MIN[5][6] = { { 0x55, 0x65 }, /* pos */ diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index a3c5af1d7ec0..de5263beab4a 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -367,7 +367,7 @@ int mlx4_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata) if (err) goto out; } else { - /* Can't be smaller then the number of outstanding CQEs */ + /* Can't be smaller than the number of outstanding CQEs */ outst_cqe = mlx4_ib_get_outstanding_cqes(cq); if (entries < outst_cqe + 1) { err = 0; diff --git a/drivers/message/i2o/i2o_scsi.c b/drivers/message/i2o/i2o_scsi.c index 1bcdbbb9e7d3..3d45817e6dcd 100644 --- a/drivers/message/i2o/i2o_scsi.c +++ b/drivers/message/i2o/i2o_scsi.c @@ -390,7 +390,7 @@ static int i2o_scsi_reply(struct i2o_controller *c, u32 m, * @i2o_dev: the I2O device which was added * * If a I2O device is added we catch the notification, because I2O classes - * other then SCSI peripheral will not be received through + * other than SCSI peripheral will not be received through * i2o_scsi_probe(). */ static void i2o_scsi_notify_device_add(struct i2o_device *i2o_dev) diff --git a/drivers/mtd/devices/pmc551.c b/drivers/mtd/devices/pmc551.c index d38bca64bb15..d2fd550f7e09 100644 --- a/drivers/mtd/devices/pmc551.c +++ b/drivers/mtd/devices/pmc551.c @@ -34,7 +34,7 @@ * aperture size, not the dram size, and the V370PDC supplies no * other method for memory size discovery. This problem is * mostly only relevant when compiled as a module, as the - * unloading of the module with an aperture size smaller then + * unloading of the module with an aperture size smaller than * the ram will cause the driver to detect the onboard memory * size to be equal to the aperture size when the module is * reloaded. Soooo, to help, the module supports an msize diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c index 048a606cebde..25def348e5ba 100644 --- a/drivers/mtd/ubi/eba.c +++ b/drivers/mtd/ubi/eba.c @@ -717,7 +717,7 @@ write_error: * to the real data size, although the @buf buffer has to contain the * alignment. In all other cases, @len has to be aligned. * - * It is prohibited to write more then once to logical eraseblocks of static + * It is prohibited to write more than once to logical eraseblocks of static * volumes. This function returns zero in case of success and a negative error * code in case of failure. */ diff --git a/drivers/mtd/ubi/io.c b/drivers/mtd/ubi/io.c index a74118c05745..fe81039f2a7c 100644 --- a/drivers/mtd/ubi/io.c +++ b/drivers/mtd/ubi/io.c @@ -465,7 +465,7 @@ out: * This function synchronously erases physical eraseblock @pnum. If @torture * flag is not zero, the physical eraseblock is checked by means of writing * different patterns to it and reading them back. If the torturing is enabled, - * the physical eraseblock is erased more then once. + * the physical eraseblock is erased more than once. * * This function returns the number of erasures made in case of success, %-EIO * if the erasure failed or the torturing test failed, and other negative error diff --git a/drivers/mtd/ubi/scan.c b/drivers/mtd/ubi/scan.c index 41d47e1cf15c..ecde202a5a12 100644 --- a/drivers/mtd/ubi/scan.c +++ b/drivers/mtd/ubi/scan.c @@ -478,7 +478,7 @@ int ubi_scan_add_used(struct ubi_device *ubi, struct ubi_scan_info *si, return 0; } else { /* - * This logical eraseblock is older then the one found + * This logical eraseblock is older than the one found * previously. */ if (cmp_res & 4) diff --git a/drivers/mtd/ubi/ubi-media.h b/drivers/mtd/ubi/ubi-media.h index 2ad940409053..8419fdccc79c 100644 --- a/drivers/mtd/ubi/ubi-media.h +++ b/drivers/mtd/ubi/ubi-media.h @@ -135,7 +135,7 @@ enum { * The erase counter header takes 64 bytes and has a plenty of unused space for * future usage. The unused fields are zeroed. The @version field is used to * indicate the version of UBI implementation which is supposed to be able to - * work with this UBI image. If @version is greater then the current UBI + * work with this UBI image. If @version is greater than the current UBI * version, the image is rejected. This may be useful in future if something * is changed radically. This field is duplicated in the volume identifier * header. @@ -187,7 +187,7 @@ struct ubi_ec_hdr { * (sequence number) is used to distinguish between older and newer versions of * logical eraseblocks. * - * There are 2 situations when there may be more then one physical eraseblock + * There are 2 situations when there may be more than one physical eraseblock * corresponding to the same logical eraseblock, i.e., having the same @vol_id * and @lnum values in the volume identifier header. Suppose we have a logical * eraseblock L and it is mapped to the physical eraseblock P. diff --git a/drivers/mtd/ubi/vtbl.c b/drivers/mtd/ubi/vtbl.c index 333c8941552f..1afc61e7455d 100644 --- a/drivers/mtd/ubi/vtbl.c +++ b/drivers/mtd/ubi/vtbl.c @@ -577,7 +577,7 @@ static int init_volumes(struct ubi_device *ubi, const struct ubi_scan_info *si, if (vtbl[i].flags & UBI_VTBL_AUTORESIZE_FLG) { /* Auto re-size flag may be set only for one volume */ if (ubi->autoresize_vol_id != -1) { - ubi_err("more then one auto-resize volume (%d " + ubi_err("more than one auto-resize volume (%d " "and %d)", ubi->autoresize_vol_id, i); kfree(vol); return -EINVAL; diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index 14901cb82c18..891534f8210d 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -128,7 +128,7 @@ * situation when the picked physical eraseblock is constantly erased after the * data is written to it. So, we have a constant which limits the highest erase * counter of the free physical eraseblock to pick. Namely, the WL sub-system - * does not pick eraseblocks with erase counter greater then the lowest erase + * does not pick eraseblocks with erase counter greater than the lowest erase * counter plus %WL_FREE_MAX_DIFF. */ #define WL_FREE_MAX_DIFF (2*UBI_WL_THRESHOLD) @@ -917,7 +917,7 @@ static int ensure_wear_leveling(struct ubi_device *ubi) /* * We schedule wear-leveling only if the difference between the * lowest erase counter of used physical eraseblocks and a high - * erase counter of free physical eraseblocks is greater then + * erase counter of free physical eraseblocks is greater than * %UBI_WL_THRESHOLD. */ e1 = rb_entry(rb_first(&ubi->used), struct ubi_wl_entry, u.rb); diff --git a/drivers/net/bnx2x_link.c b/drivers/net/bnx2x_link.c index 67de94f1f30e..fefa6ab13064 100644 --- a/drivers/net/bnx2x_link.c +++ b/drivers/net/bnx2x_link.c @@ -3359,7 +3359,7 @@ static u8 bnx2x_format_ver(u32 num, u8 *str, u16 len) u8 shift = 8*4; u8 digit; if (len < 10) { - /* Need more then 10chars for this format */ + /* Need more than 10chars for this format */ *str_ptr = '\0'; return -EINVAL; } diff --git a/drivers/net/e1000/e1000_hw.c b/drivers/net/e1000/e1000_hw.c index d04eef53571e..e1a3fc1303ee 100644 --- a/drivers/net/e1000/e1000_hw.c +++ b/drivers/net/e1000/e1000_hw.c @@ -6758,7 +6758,7 @@ static s32 e1000_get_cable_length(struct e1000_hw *hw, u16 *min_length, * returns: - E1000_ERR_XXX * E1000_SUCCESS * - * For phy's older then IGP, this function simply reads the polarity bit in the + * For phy's older than IGP, this function simply reads the polarity bit in the * Phy Status register. For IGP phy's, this bit is valid only if link speed is * 10 Mbps. If the link speed is 100 Mbps there is no polarity so this bit will * return 0. If the link speed is 1000 Mbps the polarity status is in the @@ -6834,7 +6834,7 @@ static s32 e1000_check_polarity(struct e1000_hw *hw, * returns: - E1000_ERR_XXX * E1000_SUCCESS * - * For phy's older then IGP, this function reads the Downshift bit in the Phy + * For phy's older than IGP, this function reads the Downshift bit in the Phy * Specific Status register. For IGP phy's, it reads the Downgrade bit in the * Link Health register. In IGP this bit is latched high, so the driver must * read it immediately after link is established. diff --git a/drivers/net/slip.h b/drivers/net/slip.h index 853e0f6ec710..9ea5c11287d2 100644 --- a/drivers/net/slip.h +++ b/drivers/net/slip.h @@ -75,7 +75,7 @@ struct slip { unsigned long tx_errors; /* Planned stuff */ unsigned long rx_dropped; /* No memory for skb */ unsigned long tx_dropped; /* When MTU change */ - unsigned long rx_over_errors; /* Frame bigger then SLIP buf. */ + unsigned long rx_over_errors; /* Frame bigger than SLIP buf. */ #ifdef SL_INCLUDE_CSLIP unsigned long tx_compressed; unsigned long rx_compressed; diff --git a/drivers/net/tehuti.c b/drivers/net/tehuti.c index a10a83a11d9f..a7a4dc4d6313 100644 --- a/drivers/net/tehuti.c +++ b/drivers/net/tehuti.c @@ -1004,7 +1004,7 @@ static inline void bdx_rxdb_free_elem(struct rxdb *db, int n) * skb for rx. It assumes that Rx is desabled in HW * funcs are grouped for better cache usage * - * RxD fifo is smaller then RxF fifo by design. Upon high load, RxD will be + * RxD fifo is smaller than RxF fifo by design. Upon high load, RxD will be * filled and packets will be dropped by nic without getting into host or * cousing interrupt. Anyway, in that condition, host has no chance to proccess * all packets, but dropping in nic is cheaper, since it takes 0 cpu cycles @@ -1826,7 +1826,7 @@ static void bdx_tx_free(struct bdx_priv *priv) * * Pushes desc to TxD fifo and overlaps it if needed. * NOTE: this func does not check for available space. this is responsibility - * of the caller. Neither does it check that data size is smaller then + * of the caller. Neither does it check that data size is smaller than * fifo size. */ static void bdx_tx_push_desc(struct bdx_priv *priv, void *data, int size) diff --git a/drivers/net/tokenring/smctr.c b/drivers/net/tokenring/smctr.c index a011666342ff..50eb29ce3c87 100644 --- a/drivers/net/tokenring/smctr.c +++ b/drivers/net/tokenring/smctr.c @@ -3064,7 +3064,7 @@ static int smctr_load_node_addr(struct net_device *dev) * will consequently cause a timeout. * * NOTE 1: If the monitor_state is MS_BEACON_TEST_STATE, all transmit - * queues other then the one used for the lobe_media_test should be + * queues other than the one used for the lobe_media_test should be * disabled.!? * * NOTE 2: If the monitor_state is MS_BEACON_TEST_STATE and the receive_mask diff --git a/drivers/net/wireless/ipw2x00/ipw2100.c b/drivers/net/wireless/ipw2x00/ipw2100.c index 1667065b86a7..753de1a9c4b3 100644 --- a/drivers/net/wireless/ipw2x00/ipw2100.c +++ b/drivers/net/wireless/ipw2x00/ipw2100.c @@ -1332,7 +1332,7 @@ static int ipw2100_power_cycle_adapter(struct ipw2100_priv *priv) IPW_AUX_HOST_RESET_REG_STOP_MASTER); /* Step 2. Wait for stop Master Assert - * (not more then 50us, otherwise ret error */ + * (not more than 50us, otherwise ret error */ i = 5; do { udelay(IPW_WAIT_RESET_MASTER_ASSERT_COMPLETE_DELAY); diff --git a/drivers/net/wireless/rt2x00/rt2x00crypto.c b/drivers/net/wireless/rt2x00/rt2x00crypto.c index 37ad0d2fb64c..aee9cba13eb3 100644 --- a/drivers/net/wireless/rt2x00/rt2x00crypto.c +++ b/drivers/net/wireless/rt2x00/rt2x00crypto.c @@ -184,8 +184,8 @@ void rt2x00crypto_rx_insert_iv(struct sk_buff *skb, unsigned int align, * Make room for new data, note that we increase both * headsize and tailsize when required. The tailsize is * only needed when ICV data needs to be inserted and - * the padding is smaller then the ICV data. - * When alignment requirements is greater then the + * the padding is smaller than the ICV data. + * When alignment requirements is greater than the * ICV data we must trim the skb to the correct size * because we need to remove the extra bytes. */ diff --git a/drivers/net/wireless/strip.c b/drivers/net/wireless/strip.c index dd0de3a9ed4e..7015f2480550 100644 --- a/drivers/net/wireless/strip.c +++ b/drivers/net/wireless/strip.c @@ -236,7 +236,7 @@ struct strip { unsigned long tx_errors; /* Planned stuff */ unsigned long rx_dropped; /* No memory for skb */ unsigned long tx_dropped; /* When MTU change */ - unsigned long rx_over_errors; /* Frame bigger then STRIP buf. */ + unsigned long rx_over_errors; /* Frame bigger than STRIP buf. */ unsigned long pps_timer; /* Timer to determine pps */ unsigned long rx_pps_count; /* Counter to determine pps */ diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c index 892e2878d61b..f8e05ce98621 100644 --- a/drivers/s390/block/dasd_eer.c +++ b/drivers/s390/block/dasd_eer.c @@ -535,8 +535,8 @@ static int dasd_eer_open(struct inode *inp, struct file *filp) eerb->buffer_page_count > INT_MAX / PAGE_SIZE) { kfree(eerb); MESSAGE(KERN_WARNING, "can't open device since module " - "parameter eer_pages is smaller then 1 or" - " bigger then %d", (int)(INT_MAX / PAGE_SIZE)); + "parameter eer_pages is smaller than 1 or" + " bigger than %d", (int)(INT_MAX / PAGE_SIZE)); unlock_kernel(); return -EINVAL; } diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c index aabbeb909cc6..d8a2289fcb69 100644 --- a/drivers/s390/char/vmlogrdr.c +++ b/drivers/s390/char/vmlogrdr.c @@ -427,7 +427,7 @@ static int vmlogrdr_receive_data(struct vmlogrdr_priv_t *priv) buffer = priv->buffer + sizeof(int); } /* - * If the record is bigger then our buffer, we receive only + * If the record is bigger than our buffer, we receive only * a part of it. We can get the rest later. */ if (iucv_data_count > NET_BUFFER_SIZE) @@ -437,7 +437,7 @@ static int vmlogrdr_receive_data(struct vmlogrdr_priv_t *priv) 0, buffer, iucv_data_count, &priv->residual_length); spin_unlock_bh(&priv->priv_lock); - /* An rc of 5 indicates that the record was bigger then + /* An rc of 5 indicates that the record was bigger than * the buffer, which is OK for us. A 9 indicates that the * record was purged befor we could receive it. */ diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 8c64494444bf..311ed6dea726 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -1964,10 +1964,10 @@ lpfc_set_disctmo(struct lpfc_vport *vport) uint32_t tmo; if (vport->port_state == LPFC_LOCAL_CFG_LINK) { - /* For FAN, timeout should be greater then edtov */ + /* For FAN, timeout should be greater than edtov */ tmo = (((phba->fc_edtov + 999) / 1000) + 1); } else { - /* Normal discovery timeout should be > then ELS/CT timeout + /* Normal discovery timeout should be > than ELS/CT timeout * FC spec states we need 3 * ratov for CT requests */ tmo = ((phba->fc_ratov * 3) + 3); diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 01dfdc8696f8..a36a120561e2 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -420,7 +420,7 @@ lpfc_sli_next_iocb_slot (struct lpfc_hba *phba, struct lpfc_sli_ring *pring) if (unlikely(pring->local_getidx >= max_cmd_idx)) { lpfc_printf_log(phba, KERN_ERR, LOG_SLI, "0315 Ring %d issue: portCmdGet %d " - "is bigger then cmd ring %d\n", + "is bigger than cmd ring %d\n", pring->ringno, pring->local_getidx, max_cmd_idx); @@ -1628,12 +1628,12 @@ lpfc_sli_rsp_pointers_error(struct lpfc_hba *phba, struct lpfc_sli_ring *pring) { struct lpfc_pgp *pgp = &phba->port_gp[pring->ringno]; /* - * Ring handler: portRspPut is bigger then + * Ring handler: portRspPut is bigger than * rsp ring */ lpfc_printf_log(phba, KERN_ERR, LOG_SLI, "0312 Ring %d handler: portRspPut %d " - "is bigger then rsp ring %d\n", + "is bigger than rsp ring %d\n", pring->ringno, le32_to_cpu(pgp->rspPutInx), pring->numRiocb); @@ -2083,12 +2083,12 @@ lpfc_sli_handle_slow_ring_event(struct lpfc_hba *phba, portRspPut = le32_to_cpu(pgp->rspPutInx); if (portRspPut >= portRspMax) { /* - * Ring handler: portRspPut is bigger then + * Ring handler: portRspPut is bigger than * rsp ring */ lpfc_printf_log(phba, KERN_ERR, LOG_SLI, "0303 Ring %d handler: portRspPut %d " - "is bigger then rsp ring %d\n", + "is bigger than rsp ring %d\n", pring->ringno, portRspPut, portRspMax); phba->link_state = LPFC_HBA_ERROR; diff --git a/drivers/serial/crisv10.c b/drivers/serial/crisv10.c index 8b2c619a09f2..e642c22c80e2 100644 --- a/drivers/serial/crisv10.c +++ b/drivers/serial/crisv10.c @@ -1203,7 +1203,7 @@ static void e100_disable_txdma_channel(struct e100_serial *info) unsigned long flags; /* Disable output DMA channel for the serial port in question - * ( set to something other then serialX) + * ( set to something other than serialX) */ local_irq_save(flags); DFLOW(DEBUG_LOG(info->line, "disable_txdma_channel %i\n", info->line)); @@ -1266,7 +1266,7 @@ static void e100_disable_rxdma_channel(struct e100_serial *info) unsigned long flags; /* Disable input DMA channel for the serial port in question - * ( set to something other then serialX) + * ( set to something other than serialX) */ local_irq_save(flags); if (info->line == 0) { diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c index e6210725b9ab..d012edda6d11 100644 --- a/drivers/video/console/vgacon.c +++ b/drivers/video/console/vgacon.c @@ -1332,7 +1332,7 @@ static void vgacon_save_screen(struct vc_data *c) c->vc_y = screen_info.orig_y; } - /* We can't copy in more then the size of the video buffer, + /* We can't copy in more than the size of the video buffer, * or we'll be copying in VGA BIOS */ if (!vga_is_gfx) diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 6ebaa58e2c03..04697ba7f73e 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -854,7 +854,7 @@ static int o2hb_thread(void *data) while (!kthread_should_stop() && !reg->hr_unclean_stop) { /* We track the time spent inside - * o2hb_do_disk_heartbeat so that we avoid more then + * o2hb_do_disk_heartbeat so that we avoid more than * hr_timeout_ms between disk writes. On busy systems * this should result in a heartbeat which is less * likely to time itself out. */ diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 219bd79ea894..d4a8be32b902 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -9,7 +9,7 @@ /* * Logic: we've got two memory sums for each process, "shared", and - * "non-shared". Shared memory may get counted more then once, for + * "non-shared". Shared memory may get counted more than once, for * each process that owns it. Non-shared memory is counted * accurately. */ diff --git a/fs/ubifs/Kconfig b/fs/ubifs/Kconfig index 91ceeda7e5bf..e35b54d5059d 100644 --- a/fs/ubifs/Kconfig +++ b/fs/ubifs/Kconfig @@ -40,7 +40,7 @@ config UBIFS_FS_ZLIB depends on UBIFS_FS default y help - Zlib copresses better then LZO but it is slower. Say 'Y' if unsure. + Zlib compresses better than LZO but it is slower. Say 'Y' if unsure. # Debugging-related stuff config UBIFS_FS_DEBUG diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c index 0e5e54d82924..175f9c590b77 100644 --- a/fs/ubifs/budget.c +++ b/fs/ubifs/budget.c @@ -142,7 +142,7 @@ static long long get_liability(struct ubifs_info *c) * * This function is called when an operation cannot be budgeted because there * is supposedly no free space. But in most cases there is some free space: - * o budgeting is pessimistic, so it always budgets more then it is actually + * o budgeting is pessimistic, so it always budgets more than it is actually * needed, so shrinking the liability is one way to make free space - the * cached data will take less space then it was budgeted for; * o GC may turn some dark space into free space (budgeting treats dark space @@ -606,7 +606,7 @@ void ubifs_release_budget(struct ubifs_info *c, struct ubifs_budget_req *req) * @c: UBIFS file-system description object * * This function converts budget which was allocated for a new page of data to - * the budget of changing an existing page of data. The latter is smaller then + * the budget of changing an existing page of data. The latter is smaller than * the former, so this function only does simple re-calculation and does not * involve any write-back. */ diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c index 0bef6501d58a..9832f9abe28e 100644 --- a/fs/ubifs/gc.c +++ b/fs/ubifs/gc.c @@ -45,7 +45,7 @@ #define SMALL_NODE_WM UBIFS_MAX_DENT_NODE_SZ /* - * GC may need to move more then one LEB to make progress. The below constants + * GC may need to move more than one LEB to make progress. The below constants * define "soft" and "hard" limits on the number of LEBs the garbage collector * may move. */ diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 10ae25b7d1db..9b7c54e0cd2a 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -191,7 +191,7 @@ again: if (wbuf->lnum != -1 && avail >= len) { /* * Someone else has switched the journal head and we have - * enough space now. This happens when more then one process is + * enough space now. This happens when more than one process is * trying to write to the same journal head at the same time. */ dbg_jnl("return LEB %d back, already have LEB %d:%d", diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c index f248533841a2..e7bab52a1410 100644 --- a/fs/ubifs/shrinker.c +++ b/fs/ubifs/shrinker.c @@ -151,7 +151,7 @@ static int shrink_tnc(struct ubifs_info *c, int nr, int age, int *contention) * @contention: if any contention, this is set to %1 * * This function walks the list of mounted UBIFS file-systems and frees clean - * znodes which are older then @age, until at least @nr znodes are freed. + * znodes which are older than @age, until at least @nr znodes are freed. * Returns the number of freed znodes. */ static int shrink_tnc_trees(int nr, int age, int *contention) diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 36f6cc703ef2..be846d606ae8 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -1348,7 +1348,7 @@ xfs_finish_flags( { int ronly = (mp->m_flags & XFS_MOUNT_RDONLY); - /* Fail a mount where the logbuf is smaller then the log stripe */ + /* Fail a mount where the logbuf is smaller than the log stripe */ if (xfs_sb_version_haslogv2(&mp->m_sb)) { if (mp->m_logbsize <= 0 && mp->m_sb.sb_logsunit > XLOG_BIG_RECORD_BSIZE) { diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index eae26bb6430a..64433eb411d7 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -83,7 +83,7 @@ typedef enum { * @datbuf: data buffer - if NULL only oob data are read/written * @oobbuf: oob data buffer * - * Note, it is allowed to read more then one OOB area at one go, but not write. + * Note, it is allowed to read more than one OOB area at one go, but not write. * The interface assumes that the OOB write requests program only one page's * OOB area. */ diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 82229317753d..68bb1c501d0d 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -327,9 +327,9 @@ extern struct spi_master *spi_busnum_to_master(u16 busnum); * @tx_dma: DMA address of tx_buf, if @spi_message.is_dma_mapped * @rx_dma: DMA address of rx_buf, if @spi_message.is_dma_mapped * @len: size of rx and tx buffers (in bytes) - * @speed_hz: Select a speed other then the device default for this + * @speed_hz: Select a speed other than the device default for this * transfer. If 0 the default (from @spi_device) is used. - * @bits_per_word: select a bits_per_word other then the device default + * @bits_per_word: select a bits_per_word other than the device default * for this transfer. If 0 the default (from @spi_device) is used. * @cs_change: affects chipselect after this transfer completes * @delay_usecs: microseconds to delay after this transfer before diff --git a/include/mtd/ubi-user.h b/include/mtd/ubi-user.h index ccdc562e444e..2dc2eb2b8e22 100644 --- a/include/mtd/ubi-user.h +++ b/include/mtd/ubi-user.h @@ -253,7 +253,7 @@ struct ubi_mkvol_req { * * Re-sizing is possible for both dynamic and static volumes. But while dynamic * volumes may be re-sized arbitrarily, static volumes cannot be made to be - * smaller then the number of bytes they bear. To arbitrarily shrink a static + * smaller than the number of bytes they bear. To arbitrarily shrink a static * volume, it must be wiped out first (by means of volume update operation with * zero number of bytes). */ diff --git a/kernel/pid.c b/kernel/pid.c index 064e76afa507..af9224cdd6c0 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -475,7 +475,7 @@ pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) EXPORT_SYMBOL(task_session_nr_ns); /* - * Used by proc to find the first pid that is greater then or equal to nr. + * Used by proc to find the first pid that is greater than or equal to nr. * * If there is a pid at nr this function is exactly the same as find_pid_ns. */ diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 1ca99557e929..06f197560f3b 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -45,7 +45,7 @@ * * The value 8 is somewhat carefully chosen, as anything * larger can result in overflows. NSEC_PER_JIFFY grows as - * HZ shrinks, so values greater then 8 overflow 32bits when + * HZ shrinks, so values greater than 8 overflow 32bits when * HZ=100. */ #define JIFFIES_SHIFT 8 diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 52db5f60daa0..20c576f530fa 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -141,8 +141,8 @@ void sctp_auth_destroy_keys(struct list_head *keys) /* Compare two byte vectors as numbers. Return values * are: * 0 - vectors are equal - * < 0 - vector 1 is smaller then vector2 - * > 0 - vector 1 is greater then vector2 + * < 0 - vector 1 is smaller than vector2 + * > 0 - vector 1 is greater than vector2 * * Algorithm is: * This is performed by selecting the numerically smaller key vector... diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 1c4e5d6c29c0..3a0cd075914f 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -4268,9 +4268,9 @@ nomem: /* * Handle a protocol violation when the chunk length is invalid. - * "Invalid" length is identified as smaller then the minimal length a + * "Invalid" length is identified as smaller than the minimal length a * given chunk can be. For example, a SACK chunk has invalid length - * if it's length is set to be smaller then the size of sctp_sack_chunk_t. + * if its length is set to be smaller than the size of sctp_sack_chunk_t. * * We inform the other end by sending an ABORT with a Protocol Violation * error code. @@ -4300,7 +4300,7 @@ static sctp_disposition_t sctp_sf_violation_chunklen( /* * Handle a protocol violation when the parameter length is invalid. - * "Invalid" length is identified as smaller then the minimal length a + * "Invalid" length is identified as smaller than the minimal length a * given parameter can be. */ static sctp_disposition_t sctp_sf_violation_paramlen( diff --git a/net/sctp/socket.c b/net/sctp/socket.c index b14a8f33e42d..ff0a8f88de04 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2717,7 +2717,7 @@ static int sctp_setsockopt_associnfo(struct sock *sk, char __user *optval, int o paths++; } - /* Only validate asocmaxrxt if we have more then + /* Only validate asocmaxrxt if we have more than * one path/transport. We do this because path * retransmissions are only counted when we have more * then one path. diff --git a/net/sctp/tsnmap.c b/net/sctp/tsnmap.c index 35c73e82553a..9bd64565021a 100644 --- a/net/sctp/tsnmap.c +++ b/net/sctp/tsnmap.c @@ -227,7 +227,7 @@ void sctp_tsnmap_skip(struct sctp_tsnmap *map, __u32 tsn) */ bitmap_zero(map->tsn_map, map->len); } else { - /* If the gap is smaller then the map size, + /* If the gap is smaller than the map size, * shift the map by 'gap' bits and update further. */ bitmap_shift_right(map->tsn_map, map->tsn_map, gap, map->len); diff --git a/sound/usb/usx2y/usbusx2y.c b/sound/usb/usx2y/usbusx2y.c index ca26c532e77e..11639bd72a51 100644 --- a/sound/usb/usx2y/usbusx2y.c +++ b/sound/usb/usx2y/usbusx2y.c @@ -238,7 +238,7 @@ static void i_usX2Y_In04Int(struct urb *urb) send = 0; for (j = 0; j < URBS_AsyncSeq && !err; ++j) if (0 == usX2Y->AS04.urb[j]->status) { - struct us428_p4out *p4out = us428ctls->p4out + send; // FIXME if more then 1 p4out is new, 1 gets lost. + struct us428_p4out *p4out = us428ctls->p4out + send; // FIXME if more than 1 p4out is new, 1 gets lost. usb_fill_bulk_urb(usX2Y->AS04.urb[j], usX2Y->chip.dev, usb_sndbulkpipe(usX2Y->chip.dev, 0x04), &p4out->val.vol, p4out->type == eLT_Light ? sizeof(struct us428_lights) : 5, -- cgit v1.2.3 From 0211a9c8508b2183e0e539509aad60414f1c3813 Mon Sep 17 00:00:00 2001 From: Frederik Schwarzer Date: Mon, 29 Dec 2008 22:14:56 +0100 Subject: trivial: fix an -> a typos in documentation and comments It is always "an" if there is a vowel _spoken_ (not written). So it is: "an hour" (spoken vowel) but "a uniform" (spoken 'j') Signed-off-by: Frederik Schwarzer Signed-off-by: Jiri Kosina --- Documentation/dell_rbu.txt | 4 ++-- Documentation/laptops/thinkpad-acpi.txt | 2 +- Documentation/networking/tuntap.txt | 2 +- arch/m68k/kernel/traps.c | 2 +- drivers/acpi/executer/exprep.c | 2 +- drivers/acpi/executer/exresolv.c | 2 +- drivers/acpi/executer/exstore.c | 2 +- drivers/acpi/resources/rscreate.c | 2 +- drivers/acpi/utilities/utobject.c | 4 ++-- drivers/char/epca.c | 2 +- drivers/cpufreq/Kconfig | 4 ++-- drivers/input/keyboard/atkbd.c | 2 +- drivers/macintosh/Kconfig | 2 +- drivers/misc/phantom.c | 2 +- fs/ncpfs/ioctl.c | 2 +- include/acpi/acmacros.h | 4 ++-- include/acpi/actypes.h | 2 +- include/linux/ncp_fs.h | 2 +- mm/slub.c | 2 +- sound/oss/aedsp16.c | 2 +- 20 files changed, 24 insertions(+), 24 deletions(-) (limited to 'Documentation') diff --git a/Documentation/dell_rbu.txt b/Documentation/dell_rbu.txt index 2c0d631de0cf..c11b931f8f98 100644 --- a/Documentation/dell_rbu.txt +++ b/Documentation/dell_rbu.txt @@ -81,8 +81,8 @@ Until this step is completed the driver cannot be unloaded. Also echoing either mono ,packet or init in to image_type will free up the memory allocated by the driver. -If an user by accident executes steps 1 and 3 above without executing step 2; -it will make the /sys/class/firmware/dell_rbu/ entries to disappear. +If a user by accident executes steps 1 and 3 above without executing step 2; +it will make the /sys/class/firmware/dell_rbu/ entries disappear. The entries can be recreated by doing the following echo init > /sys/devices/platform/dell_rbu/image_type NOTE: echoing init in image_type does not change it original value. diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt index 71f0fe1fc1b0..898b4987bb80 100644 --- a/Documentation/laptops/thinkpad-acpi.txt +++ b/Documentation/laptops/thinkpad-acpi.txt @@ -1475,7 +1475,7 @@ Sysfs interface changelog: 0x020100: Marker for thinkpad-acpi with hot key NVRAM polling support. If you must, use it to know you should not - start an userspace NVRAM poller (allows to detect when + start a userspace NVRAM poller (allows to detect when NVRAM is compiled out by the user because it is unneeded/undesired in the first place). 0x020101: Marker for thinkpad-acpi with hot key NVRAM polling diff --git a/Documentation/networking/tuntap.txt b/Documentation/networking/tuntap.txt index 839cbb71388b..c0aab985bad9 100644 --- a/Documentation/networking/tuntap.txt +++ b/Documentation/networking/tuntap.txt @@ -118,7 +118,7 @@ As mentioned above, main purpose of TUN/TAP driver is tunneling. It is used by VTun (http://vtun.sourceforge.net). Another interesting application using TUN/TAP is pipsecd -(http://perso.enst.fr/~beyssac/pipsec/), an userspace IPSec +(http://perso.enst.fr/~beyssac/pipsec/), a userspace IPSec implementation that can use complete kernel routing (unlike FreeS/WAN). 3. How does Virtual network device actually work ? diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index 6d813de2baf1..184acc90808d 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -401,7 +401,7 @@ static inline void do_040writebacks(struct frame *fp) * called from sigreturn(), must ensure userspace code didn't * manipulate exception frame to circumvent protection, then complete * pending writebacks - * we just clear TM2 to turn it into an userspace access + * we just clear TM2 to turn it into a userspace access */ asmlinkage void berr_040cleanup(struct frame *fp) { diff --git a/drivers/acpi/executer/exprep.c b/drivers/acpi/executer/exprep.c index 5d438c32989d..a7dc87ecee37 100644 --- a/drivers/acpi/executer/exprep.c +++ b/drivers/acpi/executer/exprep.c @@ -404,7 +404,7 @@ acpi_ex_prep_common_field_object(union acpi_operand_object *obj_desc, * * RETURN: Status * - * DESCRIPTION: Construct an union acpi_operand_object of type def_field and + * DESCRIPTION: Construct a union acpi_operand_object of type def_field and * connect it to the parent Node. * ******************************************************************************/ diff --git a/drivers/acpi/executer/exresolv.c b/drivers/acpi/executer/exresolv.c index 89571b92a522..60e8c47128e9 100644 --- a/drivers/acpi/executer/exresolv.c +++ b/drivers/acpi/executer/exresolv.c @@ -146,7 +146,7 @@ acpi_ex_resolve_object_to_value(union acpi_operand_object **stack_ptr, stack_desc = *stack_ptr; - /* This is an union acpi_operand_object */ + /* This is a union acpi_operand_object */ switch (ACPI_GET_OBJECT_TYPE(stack_desc)) { case ACPI_TYPE_LOCAL_REFERENCE: diff --git a/drivers/acpi/executer/exstore.c b/drivers/acpi/executer/exstore.c index 3318df4cbd98..1c118ba78adb 100644 --- a/drivers/acpi/executer/exstore.c +++ b/drivers/acpi/executer/exstore.c @@ -274,7 +274,7 @@ acpi_ex_do_debug_object(union acpi_operand_object *source_desc, * * PARAMETERS: *source_desc - Value to be stored * *dest_desc - Where to store it. Must be an NS node - * or an union acpi_operand_object of type + * or a union acpi_operand_object of type * Reference; * walk_state - Current walk state * diff --git a/drivers/acpi/resources/rscreate.c b/drivers/acpi/resources/rscreate.c index c0bbfa2c4193..08b8d73e6ee5 100644 --- a/drivers/acpi/resources/rscreate.c +++ b/drivers/acpi/resources/rscreate.c @@ -124,7 +124,7 @@ acpi_rs_create_resource_list(union acpi_operand_object *aml_buffer, * * FUNCTION: acpi_rs_create_pci_routing_table * - * PARAMETERS: package_object - Pointer to an union acpi_operand_object + * PARAMETERS: package_object - Pointer to a union acpi_operand_object * package * output_buffer - Pointer to the user's buffer * diff --git a/drivers/acpi/utilities/utobject.c b/drivers/acpi/utilities/utobject.c index c354e7a42bcd..4bef3cfbaccb 100644 --- a/drivers/acpi/utilities/utobject.c +++ b/drivers/acpi/utilities/utobject.c @@ -297,7 +297,7 @@ union acpi_operand_object *acpi_ut_create_string_object(acpi_size string_size) * * RETURN: TRUE if object is valid, FALSE otherwise * - * DESCRIPTION: Validate a pointer to be an union acpi_operand_object + * DESCRIPTION: Validate a pointer to be a union acpi_operand_object * ******************************************************************************/ @@ -389,7 +389,7 @@ void acpi_ut_delete_object_desc(union acpi_operand_object *object) { ACPI_FUNCTION_TRACE_PTR(ut_delete_object_desc, object); - /* Object must be an union acpi_operand_object */ + /* Object must be a union acpi_operand_object */ if (ACPI_GET_DESCRIPTOR_TYPE(object) != ACPI_DESC_TYPE_OPERAND) { ACPI_ERROR((AE_INFO, diff --git a/drivers/char/epca.c b/drivers/char/epca.c index 39ad820b2350..af7c13ca9493 100644 --- a/drivers/char/epca.c +++ b/drivers/char/epca.c @@ -769,7 +769,7 @@ static int pc_open(struct tty_struct *tty, struct file *filp) /* Check status of board configured in system. */ /* - * I check to see if the epca_setup routine detected an user error. It + * I check to see if the epca_setup routine detected a user error. It * might be better to put this in pc_init, but for the moment it goes * here. */ diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index 5f076aef74fa..a8c8d9c19d74 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -83,7 +83,7 @@ config CPU_FREQ_DEFAULT_GOV_USERSPACE select CPU_FREQ_GOV_USERSPACE help Use the CPUFreq governor 'userspace' as default. This allows - you to set the CPU frequency manually or when an userspace + you to set the CPU frequency manually or when a userspace program shall be able to set the CPU dynamically without having to enable the userspace governor manually. @@ -138,7 +138,7 @@ config CPU_FREQ_GOV_USERSPACE tristate "'userspace' governor for userspace frequency scaling" help Enable this cpufreq governor when you either want to set the - CPU frequency manually or when an userspace program shall + CPU frequency manually or when a userspace program shall be able to set the CPU dynamically, like on LART . diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c index 379b7ff354ec..b9e6bef594ac 100644 --- a/drivers/input/keyboard/atkbd.c +++ b/drivers/input/keyboard/atkbd.c @@ -65,7 +65,7 @@ MODULE_PARM_DESC(extra, "Enable extra LEDs and keys on IBM RapidAcces, EzKey and /* * Scancode to keycode tables. These are just the default setting, and - * are loadable via an userland utility. + * are loadable via a userland utility. */ static const unsigned short atkbd_set2_keycode[512] = { diff --git a/drivers/macintosh/Kconfig b/drivers/macintosh/Kconfig index b52659620d50..173cf55c64d0 100644 --- a/drivers/macintosh/Kconfig +++ b/drivers/macintosh/Kconfig @@ -138,7 +138,7 @@ config PMAC_BACKLIGHT Say Y here to enable Macintosh specific extensions of the generic backlight code. With this enabled, the brightness keys on older PowerBooks will be enabled so you can change the screen brightness. - Newer models should use an userspace daemon like pbbuttonsd. + Newer models should use a userspace daemon like pbbuttonsd. config PMAC_BACKLIGHT_LEGACY bool "Provide legacy ioctl's on /dev/pmu for the backlight" diff --git a/drivers/misc/phantom.c b/drivers/misc/phantom.c index abdebe347383..fa57b67593ae 100644 --- a/drivers/misc/phantom.c +++ b/drivers/misc/phantom.c @@ -6,7 +6,7 @@ * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * - * You need an userspace library to cooperate with this driver. It (and other + * You need a userspace library to cooperate with this driver. It (and other * info) may be obtained here: * http://www.fi.muni.cz/~xslaby/phantom.html * or alternatively, you might use OpenHaptics provided by Sensable. diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c index 6d04e050c74e..f54360f50a9c 100644 --- a/fs/ncpfs/ioctl.c +++ b/fs/ncpfs/ioctl.c @@ -98,7 +98,7 @@ struct compat_ncp_objectname_ioctl { s32 auth_type; u32 object_name_len; - compat_caddr_t object_name; /* an userspace data, in most cases user name */ + compat_caddr_t object_name; /* a userspace data, in most cases user name */ }; struct compat_ncp_fs_info_v2 { diff --git a/include/acpi/acmacros.h b/include/acpi/acmacros.h index a597207e2835..1954c9d1d012 100644 --- a/include/acpi/acmacros.h +++ b/include/acpi/acmacros.h @@ -333,8 +333,8 @@ struct acpi_integer_overlay { #define ACPI_INSERT_BITS(target, mask, source) target = ((target & (~(mask))) | (source & mask)) /* - * An struct acpi_namespace_node can appear in some contexts - * where a pointer to an union acpi_operand_object can also + * A struct acpi_namespace_node can appear in some contexts + * where a pointer to a union acpi_operand_object can also * appear. This macro is used to distinguish them. * * The "Descriptor" field is the first field in both structures. diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index 7220361790b3..8222e8de0d1c 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -467,7 +467,7 @@ typedef u32 acpi_object_type; /* * These are special object types that never appear in - * a Namespace node, only in an union acpi_operand_object + * a Namespace node, only in a union acpi_operand_object */ #define ACPI_TYPE_LOCAL_EXTRA 0x1C #define ACPI_TYPE_LOCAL_DATA 0x1D diff --git a/include/linux/ncp_fs.h b/include/linux/ncp_fs.h index 9f2d76347f19..f69e66d151cc 100644 --- a/include/linux/ncp_fs.h +++ b/include/linux/ncp_fs.h @@ -87,7 +87,7 @@ struct ncp_objectname_ioctl #define NCP_AUTH_NDS 0x32 int auth_type; size_t object_name_len; - void __user * object_name; /* an userspace data, in most cases user name */ + void __user * object_name; /* a userspace data, in most cases user name */ }; struct ncp_privatedata_ioctl diff --git a/mm/slub.c b/mm/slub.c index f0e2892fe403..6392ae5cc6b1 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2254,7 +2254,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * Add some empty padding so that we can catch * overwrites from earlier objects rather than let * tracking information or the free pointer be - * corrupted if an user writes before the start + * corrupted if a user writes before the start * of the object. */ size += sizeof(void *); diff --git a/sound/oss/aedsp16.c b/sound/oss/aedsp16.c index a0274f3dac08..3ee9900ffd7b 100644 --- a/sound/oss/aedsp16.c +++ b/sound/oss/aedsp16.c @@ -157,7 +157,7 @@ Started Fri Mar 17 16:13:18 MET 1995 - v0.1 (ALPHA, was an user-level program called AudioExcelDSP16.c) + v0.1 (ALPHA, was a user-level program called AudioExcelDSP16.c) - Initial code. v0.2 (ALPHA) - Cleanups. -- cgit v1.2.3 From 8b5b8f4cea18cb30f748baa913234c62cdc64541 Mon Sep 17 00:00:00 2001 From: Nick Andrew Date: Sat, 3 Jan 2009 19:00:37 +1100 Subject: trivial: Fix misspelling of "firmware" in docs for ncr53c8xx/sym53c8xx Fix misspelling of "firmware" in docs for ncr53c8xx/sym53c8xx It's spelled "firmware". Signed-off-by: Nick Andrew Signed-off-by: Jiri Kosina --- Documentation/scsi/ChangeLog.ncr53c8xx | 2 +- Documentation/scsi/ChangeLog.sym53c8xx | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/scsi/ChangeLog.ncr53c8xx b/Documentation/scsi/ChangeLog.ncr53c8xx index a9f721aeb11c..8b278c10edfd 100644 --- a/Documentation/scsi/ChangeLog.ncr53c8xx +++ b/Documentation/scsi/ChangeLog.ncr53c8xx @@ -19,7 +19,7 @@ Sun Sep 24 21:30 2000 Gerard Roudier (groudier@club-internet.fr) Wed Jul 26 23:30 2000 Gerard Roudier (groudier@club-internet.fr) * version ncr53c8xx-3.4.1 - - Provide OpenFirmare path through the proc FS on PPC. + - Provide OpenFirmware path through the proc FS on PPC. - Remove trailing argument #2 from a couple of #undefs. Sun Jul 09 16:30 2000 Gerard Roudier (groudier@club-internet.fr) diff --git a/Documentation/scsi/ChangeLog.sym53c8xx b/Documentation/scsi/ChangeLog.sym53c8xx index ef985ec348e6..02ffbc1e8a84 100644 --- a/Documentation/scsi/ChangeLog.sym53c8xx +++ b/Documentation/scsi/ChangeLog.sym53c8xx @@ -81,7 +81,7 @@ Sun Sep 24 21:30 2000 Gerard Roudier (groudier@club-internet.fr) Wed Jul 26 23:30 2000 Gerard Roudier (groudier@club-internet.fr) * version sym53c8xx-1.7.1 - - Provide OpenFirmare path through the proc FS on PPC. + - Provide OpenFirmware path through the proc FS on PPC. - Download of on-chip SRAM using memcpy_toio() doesn't work on PPC. Restore previous method (MEMORY MOVE from SCRIPTS). - Remove trailing argument #2 from a couple of #undefs. -- cgit v1.2.3 From 02c84bde234eee4f2089ac3587d138607aaec777 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 6 Jan 2009 17:21:00 +0100 Subject: ide: update warm-plug HOWTO MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reported-by: Bruno Prémont Signed-off-by: Bartlomiej Zolnierkiewicz --- Documentation/ide/warm-plug-howto.txt | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'Documentation') diff --git a/Documentation/ide/warm-plug-howto.txt b/Documentation/ide/warm-plug-howto.txt index d5885468b072..98152bcd515a 100644 --- a/Documentation/ide/warm-plug-howto.txt +++ b/Documentation/ide/warm-plug-howto.txt @@ -11,3 +11,8 @@ unplug old device(s) and plug new device(s) # echo -n "1" > /sys/class/ide_port/idex/scan done + +NOTE: please make sure that partitions are unmounted and that there are +no other active references to devices before doing "delete_devices" step, +also do not attempt "scan" step on devices currently in use -- otherwise +results may be unpredictable and lead to data loss if you're unlucky -- cgit v1.2.3 From 0732b49c8c40c56033cff8986dbad55aa54a5d40 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 9 Dec 2008 08:32:14 +1030 Subject: kobject: Make Documentation/kobject.txt a little more coherent. While reading Documentation/kobject.txt: Note kobject_rename does perform any locking or have a solid notion of what names are valid so the provide must provide their own sanity checking and serialization. I expect better: You never see me hard with time word making sentence coherent stuff. Ever. Signed-off-by: Rusty Russell Acked-by: Eric W. Biederman Signed-off-by: Greg Kroah-Hartman --- Documentation/kobject.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/kobject.txt b/Documentation/kobject.txt index f5d2aad65a67..b2e374586bd8 100644 --- a/Documentation/kobject.txt +++ b/Documentation/kobject.txt @@ -118,8 +118,8 @@ the name of the kobject, call kobject_rename(): int kobject_rename(struct kobject *kobj, const char *new_name); -Note kobject_rename does perform any locking or have a solid notion of -what names are valid so the provide must provide their own sanity checking +kobject_rename does not perform any locking or have a solid notion of +what names are valid so the caller must provide their own sanity checking and serialization. There is a function called kobject_set_name() but that is legacy cruft and -- cgit v1.2.3 From a2ab3d30005cdce45c2c7e31ad6743ad7975609a Mon Sep 17 00:00:00 2001 From: "Hans J. Koch" Date: Sat, 6 Dec 2008 02:25:13 +0100 Subject: UIO: Documentation for UIO ioport info handling This patch updates UIO documentation with the changes introduced by previous UIO patch. Signed-off-by: Hans J. Koch Signed-off-by: Greg Kroah-Hartman --- Documentation/DocBook/uio-howto.tmpl | 97 ++++++++++++++++++++++++++++++++++++ 1 file changed, 97 insertions(+) (limited to 'Documentation') diff --git a/Documentation/DocBook/uio-howto.tmpl b/Documentation/DocBook/uio-howto.tmpl index df87d1b93605..6116b93608df 100644 --- a/Documentation/DocBook/uio-howto.tmpl +++ b/Documentation/DocBook/uio-howto.tmpl @@ -41,6 +41,12 @@ GPL version 2. + + 0.6 + 2008-12-05 + hjk + Added description of portio sysfs attributes. + 0.5 2008-05-22 @@ -318,6 +324,54 @@ interested in translating it, please email me offset = N * getpagesize(); + + Sometimes there is hardware with memory-like regions that can not be + mapped with the technique described here, but there are still ways to + access them from userspace. The most common example are x86 ioports. + On x86 systems, userspace can access these ioports using + ioperm(), iopl(), + inb(), outb(), and similar + functions. + + + Since these ioport regions can not be mapped, they will not appear under + /sys/class/uio/uioX/maps/ like the normal memory + described above. Without information about the port regions a hardware + has to offer, it becomes difficult for the userspace part of the + driver to find out which ports belong to which UIO device. + + + To address this situation, the new directory + /sys/class/uio/uioX/portio/ was added. It only + exists if the driver wants to pass information about one or more port + regions to userspace. If that is the case, subdirectories named + port0, port1, and so on, + will appear underneath + /sys/class/uio/uioX/portio/. + + + Each portX/ directory contains three read-only + files that show start, size, and type of the port region: + + + + + start: The first port of this region. + + + + + size: The number of ports in this region. + + + + + porttype: A string describing the type of port. + + + + + @@ -355,6 +409,13 @@ mapping you need to fill one of the uio_mem structures. See the description below for details. + +struct uio_port port[ MAX_UIO_PORTS_REGIONS ]: Required +if you want to pass information about ioports to userspace. For each port +region you need to fill one of the uio_port structures. +See the description below for details. + + long irq: Required. If your hardware generates an interrupt, it's your modules task to determine the irq number during @@ -448,6 +509,42 @@ Please do not touch the kobj element of struct uio_mem! It is used by the UIO framework to set up sysfs files for this mapping. Simply leave it alone. + + +Sometimes, your device can have one or more port regions which can not be +mapped to userspace. But if there are other possibilities for userspace to +access these ports, it makes sense to make information about the ports +available in sysfs. For each region, you have to set up a +struct uio_port in the port[] array. +Here's a description of the fields of struct uio_port: + + + + +char *porttype: Required. Set this to one of the predefined +constants. Use UIO_PORT_X86 for the ioports found in x86 +architectures. + + + +unsigned long start: Required if the port region is used. +Fill in the number of the first port of this region. + + + +unsigned long size: Fill in the number of ports in this +region. If size is zero, the region is considered unused. +Note that you must initialize size +with zero for all unused regions. + + + + +Please do not touch the portio element of +struct uio_port! It is used internally by the UIO +framework to set up sysfs files for this region. Simply leave it alone. + + -- cgit v1.2.3 From b8ac9fc0e8cda9f9776019c5b0464b0c6d2d4c90 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Fri, 12 Dec 2008 11:44:21 +0100 Subject: uio: make uio_info's name and version const These are only ever assigned constant strings and never modified. This was noticed because Wolfram Sang needed to cast the result of of_get_property() in order to assign it to the name field of a struct uio_info. Signed-off-by: Stephen Rothwell Signed-off-by: Hans J. Koch Signed-off-by: Greg Kroah-Hartman --- Documentation/DocBook/uio-howto.tmpl | 4 ++-- include/linux/uio_driver.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'Documentation') diff --git a/Documentation/DocBook/uio-howto.tmpl b/Documentation/DocBook/uio-howto.tmpl index 6116b93608df..b787e4721c90 100644 --- a/Documentation/DocBook/uio-howto.tmpl +++ b/Documentation/DocBook/uio-howto.tmpl @@ -393,12 +393,12 @@ offset = N * getpagesize(); -char *name: Required. The name of your driver as +const char *name: Required. The name of your driver as it will appear in sysfs. I recommend using the name of your module for this. -char *version: Required. This string appears in +const char *version: Required. This string appears in /sys/class/uio/uioX/version. diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h index 20be327bfbb4..a0bb6bd2e5c1 100644 --- a/include/linux/uio_driver.h +++ b/include/linux/uio_driver.h @@ -76,8 +76,8 @@ struct uio_device; */ struct uio_info { struct uio_device *uio_dev; - char *name; - char *version; + const char *name; + const char *version; struct uio_mem mem[MAX_UIO_MAPS]; struct uio_port port[MAX_UIO_PORT_REGIONS]; long irq; -- cgit v1.2.3 From 83982b6f47201c4c7767210d24d7d8c99567a0b3 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 6 Jan 2009 14:53:16 -0500 Subject: ext4: Remove "extents" mount option This mount option is largely superfluous, and in fact the way it was implemented was buggy; if a filesystem which did not have the extents feature flag was mounted -o extents, the filesystem would attempt to create and use extents-based file even though the extents feature flag was not eabled. The simplest thing to do is to nuke the mount option entirely. It's not all that useful to force the non-creation of new extent-based files if the filesystem can support it. Signed-off-by: "Theodore Ts'o" --- Documentation/filesystems/ext4.txt | 5 ---- fs/ext4/ext4.h | 1 - fs/ext4/ext4_jbd2.h | 4 ++-- fs/ext4/extents.c | 4 ++-- fs/ext4/ialloc.c | 2 +- fs/ext4/migrate.c | 14 +++++------ fs/ext4/super.c | 48 ++------------------------------------ 7 files changed, 14 insertions(+), 64 deletions(-) (limited to 'Documentation') diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index 8938949b201e..cec829bc7291 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -131,11 +131,6 @@ ro Mount filesystem read only. Note that ext4 will mount options "ro,noload" can be used to prevent writes to the filesystem. -extents (*) ext4 will use extents to address file data. The - file system will no longer be mountable by ext3. - -noextents ext4 will not use extents for newly created files - journal_checksum Enable checksumming of the journal transactions. This will allow the recovery code in e2fsck and the kernel to detect corruption in the kernel. It is a diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 695b45cc34e7..db1718833f58 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -536,7 +536,6 @@ do { \ #define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */ #define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */ #define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */ -#define EXT4_MOUNT_EXTENTS 0x400000 /* Extents support */ #define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */ #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */ #define EXT4_MOUNT_I_VERSION 0x2000000 /* i_version support */ diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 663197adae56..be2f426f6805 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -32,8 +32,8 @@ * 5 levels of tree + root which are stored in the inode. */ #define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \ - (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS) \ - || test_opt(sb, EXTENTS) ? 27U : 8U) + (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS) \ + ? 27U : 8U) /* Extended attribute operations touch at most two data buffers, * two bitmap buffers, and two group summaries, in addition to the inode diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index c64080e49493..240cf0daad4b 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2247,7 +2247,7 @@ void ext4_ext_init(struct super_block *sb) * possible initialization would be here */ - if (test_opt(sb, EXTENTS)) { + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) { printk(KERN_INFO "EXT4-fs: file extents enabled"); #ifdef AGGRESSIVE_TEST printk(", aggressive tests"); @@ -2272,7 +2272,7 @@ void ext4_ext_init(struct super_block *sb) */ void ext4_ext_release(struct super_block *sb) { - if (!test_opt(sb, EXTENTS)) + if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) return; #ifdef EXTENTS_STATS diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 369c34c64292..4fb86a0061d0 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -917,7 +917,7 @@ got: if (err) goto fail_free_drop; - if (test_opt(sb, EXTENTS)) { + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) { /* set extent flag only for directory, file and normal symlink*/ if (S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode)) { EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL; diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index e7cd488da4bb..734abca25e35 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -459,13 +459,13 @@ int ext4_ext_migrate(struct inode *inode) struct list_blocks_struct lb; unsigned long max_entries; - if (!test_opt(inode->i_sb, EXTENTS)) - /* - * if mounted with noextents we don't allow the migrate - */ - return -EINVAL; - - if ((EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) + /* + * If the filesystem does not support extents, or the inode + * already is extent-based, error out. + */ + if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_INCOMPAT_EXTENTS) || + (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) return -EINVAL; if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index b69d09203865..acb69c00fd42 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -829,8 +829,6 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) seq_puts(seq, ",journal_async_commit"); if (test_opt(sb, NOBH)) seq_puts(seq, ",nobh"); - if (!test_opt(sb, EXTENTS)) - seq_puts(seq, ",noextents"); if (test_opt(sb, I_VERSION)) seq_puts(seq, ",i_version"); if (!test_opt(sb, DELALLOC)) @@ -1011,7 +1009,7 @@ enum { Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota, Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota, - Opt_grpquota, Opt_extents, Opt_noextents, Opt_i_version, + Opt_grpquota, Opt_i_version, Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_inode_readahead_blks, Opt_journal_ioprio }; @@ -1066,8 +1064,6 @@ static const match_table_t tokens = { {Opt_quota, "quota"}, {Opt_usrquota, "usrquota"}, {Opt_barrier, "barrier=%u"}, - {Opt_extents, "extents"}, - {Opt_noextents, "noextents"}, {Opt_i_version, "i_version"}, {Opt_stripe, "stripe=%u"}, {Opt_resize, "resize"}, @@ -1115,7 +1111,6 @@ static int parse_options(char *options, struct super_block *sb, int qtype, qfmt; char *qname; #endif - ext4_fsblk_t last_block; if (!options) return 1; @@ -1445,33 +1440,6 @@ set_qf_format: case Opt_bh: clear_opt(sbi->s_mount_opt, NOBH); break; - case Opt_extents: - if (!EXT4_HAS_INCOMPAT_FEATURE(sb, - EXT4_FEATURE_INCOMPAT_EXTENTS)) { - ext4_warning(sb, __func__, - "extents feature not enabled " - "on this filesystem, use tune2fs"); - return 0; - } - set_opt(sbi->s_mount_opt, EXTENTS); - break; - case Opt_noextents: - /* - * When e2fsprogs support resizing an already existing - * ext3 file system to greater than 2**32 we need to - * add support to block allocator to handle growing - * already existing block mapped inode so that blocks - * allocated for them fall within 2**32 - */ - last_block = ext4_blocks_count(sbi->s_es) - 1; - if (last_block > 0xffffffffULL) { - printk(KERN_ERR "EXT4-fs: Filesystem too " - "large to mount with " - "-o noextents options\n"); - return 0; - } - clear_opt(sbi->s_mount_opt, EXTENTS); - break; case Opt_i_version: set_opt(sbi->s_mount_opt, I_VERSION); sb->s_flags |= MS_I_VERSION; @@ -2135,18 +2103,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) set_opt(sbi->s_mount_opt, RESERVATION); set_opt(sbi->s_mount_opt, BARRIER); - /* - * turn on extents feature by default in ext4 filesystem - * only if feature flag already set by mkfs or tune2fs. - * Use -o noextents to turn it off - */ - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) - set_opt(sbi->s_mount_opt, EXTENTS); - else - ext4_warning(sb, __func__, - "extents feature not enabled on this filesystem, " - "use tune2fs."); - /* * enable delayed allocation by default * Use -o nodelalloc to turn it off @@ -3825,7 +3781,7 @@ static void __exit exit_ext4_fs(void) } MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); -MODULE_DESCRIPTION("Fourth Extended Filesystem with extents"); +MODULE_DESCRIPTION("Fourth Extended Filesystem"); MODULE_LICENSE("GPL"); module_init(init_ext4_fs) module_exit(exit_ext4_fs) -- cgit v1.2.3 From c04fc586c1a480ba198f03ae7b6cbd7b57380b91 Mon Sep 17 00:00:00 2001 From: Gary Hade Date: Tue, 6 Jan 2009 14:39:14 -0800 Subject: mm: show node to memory section relationship with symlinks in sysfs Show node to memory section relationship with symlinks in sysfs Add /sys/devices/system/node/nodeX/memoryY symlinks for all the memory sections located on nodeX. For example: /sys/devices/system/node/node1/memory135 -> ../../memory/memory135 indicates that memory section 135 resides on node1. Also revises documentation to cover this change as well as updating Documentation/ABI/testing/sysfs-devices-memory to include descriptions of memory hotremove files 'phys_device', 'phys_index', and 'state' that were previously not described there. In addition to it always being a good policy to provide users with the maximum possible amount of physical location information for resources that can be hot-added and/or hot-removed, the following are some (but likely not all) of the user benefits provided by this change. Immediate: - Provides information needed to determine the specific node on which a defective DIMM is located. This will reduce system downtime when the node or defective DIMM is swapped out. - Prevents unintended onlining of a memory section that was previously offlined due to a defective DIMM. This could happen during node hot-add when the user or node hot-add assist script onlines _all_ offlined sections due to user or script inability to identify the specific memory sections located on the hot-added node. The consequences of reintroducing the defective memory could be ugly. - Provides information needed to vary the amount and distribution of memory on specific nodes for testing or debugging purposes. Future: - Will provide information needed to identify the memory sections that need to be offlined prior to physical removal of a specific node. Symlink creation during boot was tested on 2-node x86_64, 2-node ppc64, and 2-node ia64 systems. Symlink creation during physical memory hot-add tested on a 2-node x86_64 system. Signed-off-by: Gary Hade Signed-off-by: Badari Pulavarty Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/ABI/testing/sysfs-devices-memory | 51 +++++++++++- Documentation/memory-hotplug.txt | 16 +++- arch/ia64/mm/init.c | 2 +- arch/powerpc/mm/mem.c | 2 +- arch/s390/mm/init.c | 2 +- arch/sh/mm/init.c | 3 +- arch/x86/mm/init_32.c | 2 +- arch/x86/mm/init_64.c | 2 +- drivers/base/memory.c | 19 +++-- drivers/base/node.c | 103 +++++++++++++++++++++++++ include/linux/memory.h | 6 +- include/linux/memory_hotplug.h | 2 +- include/linux/node.h | 13 ++++ mm/memory_hotplug.c | 11 +-- 14 files changed, 209 insertions(+), 25 deletions(-) (limited to 'Documentation') diff --git a/Documentation/ABI/testing/sysfs-devices-memory b/Documentation/ABI/testing/sysfs-devices-memory index 7a16fe1e2270..9fe91c02ee40 100644 --- a/Documentation/ABI/testing/sysfs-devices-memory +++ b/Documentation/ABI/testing/sysfs-devices-memory @@ -6,7 +6,6 @@ Description: internal state of the kernel memory blocks. Files could be added or removed dynamically to represent hot-add/remove operations. - Users: hotplug memory add/remove tools https://w3.opensource.ibm.com/projects/powerpc-utils/ @@ -19,6 +18,56 @@ Description: This is useful for a user-level agent to determine identify removable sections of the memory before attempting potentially expensive hot-remove memory operation +Users: hotplug memory remove tools + https://w3.opensource.ibm.com/projects/powerpc-utils/ + +What: /sys/devices/system/memory/memoryX/phys_device +Date: September 2008 +Contact: Badari Pulavarty +Description: + The file /sys/devices/system/memory/memoryX/phys_device + is read-only and is designed to show the name of physical + memory device. Implementation is currently incomplete. +What: /sys/devices/system/memory/memoryX/phys_index +Date: September 2008 +Contact: Badari Pulavarty +Description: + The file /sys/devices/system/memory/memoryX/phys_index + is read-only and contains the section ID in hexadecimal + which is equivalent to decimal X contained in the + memory section directory name. + +What: /sys/devices/system/memory/memoryX/state +Date: September 2008 +Contact: Badari Pulavarty +Description: + The file /sys/devices/system/memory/memoryX/state + is read-write. When read, it's contents show the + online/offline state of the memory section. When written, + root can toggle the the online/offline state of a removable + memory section (see removable file description above) + using the following commands. + # echo online > /sys/devices/system/memory/memoryX/state + # echo offline > /sys/devices/system/memory/memoryX/state + + For example, if /sys/devices/system/memory/memory22/removable + contains a value of 1 and + /sys/devices/system/memory/memory22/state contains the + string "online" the following command can be executed by + by root to offline that section. + # echo offline > /sys/devices/system/memory/memory22/state Users: hotplug memory remove tools https://w3.opensource.ibm.com/projects/powerpc-utils/ + +What: /sys/devices/system/node/nodeX/memoryY +Date: September 2008 +Contact: Gary Hade +Description: + When CONFIG_NUMA is enabled + /sys/devices/system/node/nodeX/memoryY is a symbolic link that + points to the corresponding /sys/devices/system/memory/memoryY + memory section directory. For example, the following symbolic + link is created for memory section 9 on node0. + /sys/devices/system/node/node0/memory9 -> ../../memory/memory9 + diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt index 168117bd6ee8..4c2ecf537a4a 100644 --- a/Documentation/memory-hotplug.txt +++ b/Documentation/memory-hotplug.txt @@ -124,7 +124,7 @@ config options. This option can be kernel module too. -------------------------------- -3 sysfs files for memory hotplug +4 sysfs files for memory hotplug -------------------------------- All sections have their device information under /sys/devices/system/memory as @@ -138,11 +138,12 @@ For example, assume 1GiB section size. A device for a memory starting at (0x100000000 / 1Gib = 4) This device covers address range [0x100000000 ... 0x140000000) -Under each section, you can see 3 files. +Under each section, you can see 4 files. /sys/devices/system/memory/memoryXXX/phys_index /sys/devices/system/memory/memoryXXX/phys_device /sys/devices/system/memory/memoryXXX/state +/sys/devices/system/memory/memoryXXX/removable 'phys_index' : read-only and contains section id, same as XXX. 'state' : read-write @@ -150,10 +151,20 @@ Under each section, you can see 3 files. at write: user can specify "online", "offline" command 'phys_device': read-only: designed to show the name of physical memory device. This is not well implemented now. +'removable' : read-only: contains an integer value indicating + whether the memory section is removable or not + removable. A value of 1 indicates that the memory + section is removable and a value of 0 indicates that + it is not removable. NOTE: These directories/files appear after physical memory hotplug phase. +If CONFIG_NUMA is enabled the +/sys/devices/system/memory/memoryXXX memory section +directories can also be accessed via symbolic links located in +the /sys/devices/system/node/node* directories. For example: +/sys/devices/system/node/node0/memory9 -> ../../memory/memory9 -------------------------------- 4. Physical memory hot-add phase @@ -365,7 +376,6 @@ node if necessary. - allowing memory hot-add to ZONE_MOVABLE. maybe we need some switch like sysctl or new control file. - showing memory section and physical device relationship. - - showing memory section and node relationship (maybe good for NUMA) - showing memory section is under ZONE_MOVABLE or not - test and make it better memory offlining. - support HugeTLB page migration and offlining. diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 054bcd9439aa..56e12903973c 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -692,7 +692,7 @@ int arch_add_memory(int nid, u64 start, u64 size) pgdat = NODE_DATA(nid); zone = pgdat->node_zones + ZONE_NORMAL; - ret = __add_pages(zone, start_pfn, nr_pages); + ret = __add_pages(nid, zone, start_pfn, nr_pages); if (ret) printk("%s: Problem encountered in __add_pages() as ret=%d\n", diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 53b06ebb3f2f..f00f09a77f12 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -132,7 +132,7 @@ int arch_add_memory(int nid, u64 start, u64 size) /* this should work for most non-highmem platforms */ zone = pgdata->node_zones; - return __add_pages(zone, start_pfn, nr_pages); + return __add_pages(nid, zone, start_pfn, nr_pages); } #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 158b0d6d7046..f0258ca3b17e 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -183,7 +183,7 @@ int arch_add_memory(int nid, u64 start, u64 size) rc = vmem_add_mapping(start, size); if (rc) return rc; - rc = __add_pages(zone, PFN_DOWN(start), PFN_DOWN(size)); + rc = __add_pages(nid, zone, PFN_DOWN(start), PFN_DOWN(size)); if (rc) vmem_remove_mapping(start, size); return rc; diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 6cbef8caeb56..3edf297c829b 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -311,7 +311,8 @@ int arch_add_memory(int nid, u64 start, u64 size) pgdat = NODE_DATA(nid); /* We only have ZONE_NORMAL, so this is easy.. */ - ret = __add_pages(pgdat->node_zones + ZONE_NORMAL, start_pfn, nr_pages); + ret = __add_pages(nid, pgdat->node_zones + ZONE_NORMAL, + start_pfn, nr_pages); if (unlikely(ret)) printk("%s: Failed, __add_pages() == %d\n", __func__, ret); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index f99a6c6c432e..544d724caeee 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -1079,7 +1079,7 @@ int arch_add_memory(int nid, u64 start, u64 size) unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - return __add_pages(zone, start_pfn, nr_pages); + return __add_pages(nid, zone, start_pfn, nr_pages); } #endif diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 9f7a0d24d42a..54c437e96541 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -857,7 +857,7 @@ int arch_add_memory(int nid, u64 start, u64 size) if (last_mapped_pfn > max_pfn_mapped) max_pfn_mapped = last_mapped_pfn; - ret = __add_pages(zone, start_pfn, nr_pages); + ret = __add_pages(nid, zone, start_pfn, nr_pages); WARN_ON_ONCE(ret); return ret; diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 5260e9e0df48..989429cfed88 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -347,8 +347,9 @@ static inline int memory_probe_init(void) * section belongs to... */ -static int add_memory_block(unsigned long node_id, struct mem_section *section, - unsigned long state, int phys_device) +static int add_memory_block(int nid, struct mem_section *section, + unsigned long state, int phys_device, + enum mem_add_context context) { struct memory_block *mem = kzalloc(sizeof(*mem), GFP_KERNEL); int ret = 0; @@ -370,6 +371,10 @@ static int add_memory_block(unsigned long node_id, struct mem_section *section, ret = mem_create_simple_file(mem, phys_device); if (!ret) ret = mem_create_simple_file(mem, removable); + if (!ret) { + if (context == HOTPLUG) + ret = register_mem_sect_under_node(mem, nid); + } return ret; } @@ -382,7 +387,7 @@ static int add_memory_block(unsigned long node_id, struct mem_section *section, * * This could be made generic for all sysdev classes. */ -static struct memory_block *find_memory_block(struct mem_section *section) +struct memory_block *find_memory_block(struct mem_section *section) { struct kobject *kobj; struct sys_device *sysdev; @@ -411,6 +416,7 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section, struct memory_block *mem; mem = find_memory_block(section); + unregister_mem_sect_under_nodes(mem); mem_remove_simple_file(mem, phys_index); mem_remove_simple_file(mem, state); mem_remove_simple_file(mem, phys_device); @@ -424,9 +430,9 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section, * need an interface for the VM to add new memory regions, * but without onlining it. */ -int register_new_memory(struct mem_section *section) +int register_new_memory(int nid, struct mem_section *section) { - return add_memory_block(0, section, MEM_OFFLINE, 0); + return add_memory_block(nid, section, MEM_OFFLINE, 0, HOTPLUG); } int unregister_memory_section(struct mem_section *section) @@ -458,7 +464,8 @@ int __init memory_dev_init(void) for (i = 0; i < NR_MEM_SECTIONS; i++) { if (!present_section_nr(i)) continue; - err = add_memory_block(0, __nr_to_section(i), MEM_ONLINE, 0); + err = add_memory_block(0, __nr_to_section(i), MEM_ONLINE, + 0, BOOT); if (!ret) ret = err; } diff --git a/drivers/base/node.c b/drivers/base/node.c index 91636cd8b6c9..43fa90b837ee 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -248,6 +249,105 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid) return 0; } +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#define page_initialized(page) (page->lru.next) + +static int get_nid_for_pfn(unsigned long pfn) +{ + struct page *page; + + if (!pfn_valid_within(pfn)) + return -1; + page = pfn_to_page(pfn); + if (!page_initialized(page)) + return -1; + return pfn_to_nid(pfn); +} + +/* register memory section under specified node if it spans that node */ +int register_mem_sect_under_node(struct memory_block *mem_blk, int nid) +{ + unsigned long pfn, sect_start_pfn, sect_end_pfn; + + if (!mem_blk) + return -EFAULT; + if (!node_online(nid)) + return 0; + sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index); + sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1; + for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) { + int page_nid; + + page_nid = get_nid_for_pfn(pfn); + if (page_nid < 0) + continue; + if (page_nid != nid) + continue; + return sysfs_create_link_nowarn(&node_devices[nid].sysdev.kobj, + &mem_blk->sysdev.kobj, + kobject_name(&mem_blk->sysdev.kobj)); + } + /* mem section does not span the specified node */ + return 0; +} + +/* unregister memory section under all nodes that it spans */ +int unregister_mem_sect_under_nodes(struct memory_block *mem_blk) +{ + nodemask_t unlinked_nodes; + unsigned long pfn, sect_start_pfn, sect_end_pfn; + + if (!mem_blk) + return -EFAULT; + nodes_clear(unlinked_nodes); + sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index); + sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1; + for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) { + unsigned int nid; + + nid = get_nid_for_pfn(pfn); + if (nid < 0) + continue; + if (!node_online(nid)) + continue; + if (node_test_and_set(nid, unlinked_nodes)) + continue; + sysfs_remove_link(&node_devices[nid].sysdev.kobj, + kobject_name(&mem_blk->sysdev.kobj)); + } + return 0; +} + +static int link_mem_sections(int nid) +{ + unsigned long start_pfn = NODE_DATA(nid)->node_start_pfn; + unsigned long end_pfn = start_pfn + NODE_DATA(nid)->node_spanned_pages; + unsigned long pfn; + int err = 0; + + for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) { + unsigned long section_nr = pfn_to_section_nr(pfn); + struct mem_section *mem_sect; + struct memory_block *mem_blk; + int ret; + + if (!present_section_nr(section_nr)) + continue; + mem_sect = __nr_to_section(section_nr); + mem_blk = find_memory_block(mem_sect); + ret = register_mem_sect_under_node(mem_blk, nid); + if (!err) + err = ret; + + /* discard ref obtained in find_memory_block() */ + kobject_put(&mem_blk->sysdev.kobj); + } + return err; +} +#else +static int link_mem_sections(int nid) { return 0; } +#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ + int register_one_node(int nid) { int error = 0; @@ -267,6 +367,9 @@ int register_one_node(int nid) if (cpu_to_node(cpu) == nid) register_cpu_under_node(cpu, nid); } + + /* link memory sections under this node */ + error = link_mem_sections(nid); } return error; diff --git a/include/linux/memory.h b/include/linux/memory.h index 36c82c9e6ea7..3fdc10806d31 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -79,14 +79,14 @@ static inline int memory_notify(unsigned long val, void *v) #else extern int register_memory_notifier(struct notifier_block *nb); extern void unregister_memory_notifier(struct notifier_block *nb); -extern int register_new_memory(struct mem_section *); +extern int register_new_memory(int, struct mem_section *); extern int unregister_memory_section(struct mem_section *); extern int memory_dev_init(void); extern int remove_memory_block(unsigned long, struct mem_section *, int); extern int memory_notify(unsigned long val, void *v); +extern struct memory_block *find_memory_block(struct mem_section *); #define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION< Date: Tue, 6 Jan 2009 14:39:31 -0800 Subject: mm: add dirty_background_bytes and dirty_bytes sysctls This change introduces two new sysctls to /proc/sys/vm: dirty_background_bytes and dirty_bytes. dirty_background_bytes is the counterpart to dirty_background_ratio and dirty_bytes is the counterpart to dirty_ratio. With growing memory capacities of individual machines, it's no longer sufficient to specify dirty thresholds as a percentage of the amount of dirtyable memory over the entire system. dirty_background_bytes and dirty_bytes specify quantities of memory, in bytes, that represent the dirty limits for the entire system. If either of these values is set, its value represents the amount of dirty memory that is needed to commence either background or direct writeback. When a `bytes' or `ratio' file is written, its counterpart becomes a function of the written value. For example, if dirty_bytes is written to be 8096, 8K of memory is required to commence direct writeback. dirty_ratio is then functionally equivalent to 8K / the amount of dirtyable memory: dirtyable_memory = free pages + mapped pages + file cache dirty_background_bytes = dirty_background_ratio * dirtyable_memory -or- dirty_background_ratio = dirty_background_bytes / dirtyable_memory AND dirty_bytes = dirty_ratio * dirtyable_memory -or- dirty_ratio = dirty_bytes / dirtyable_memory Only one of dirty_background_bytes and dirty_background_ratio may be specified at a time, and only one of dirty_bytes and dirty_ratio may be specified. When one sysctl is written, the other appears as 0 when read. The `bytes' files operate on a page size granularity since dirty limits are compared with ZVC values, which are in page units. Prior to this change, the minimum dirty_ratio was 5 as implemented by get_dirty_limits() although /proc/sys/vm/dirty_ratio would show any user written value between 0 and 100. This restriction is maintained, but dirty_bytes has a lower limit of only one page. Also prior to this change, the dirty_background_ratio could not equal or exceed dirty_ratio. This restriction is maintained in addition to restricting dirty_background_bytes. If either background threshold equals or exceeds that of the dirty threshold, it is implicitly set to half the dirty threshold. Acked-by: Peter Zijlstra Cc: Dave Chinner Cc: Christoph Lameter Signed-off-by: David Rientjes Cc: Andrea Righi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.txt | 26 +++++++++- Documentation/sysctl/vm.txt | 3 +- include/linux/writeback.h | 11 ++++ kernel/sysctl.c | 27 ++++++++-- mm/page-writeback.c | 102 +++++++++++++++++++++++++++++++------ 5 files changed, 146 insertions(+), 23 deletions(-) (limited to 'Documentation') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 71df353e367c..32e94635484f 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -1385,6 +1385,15 @@ swapcache reclaim. Decreasing vfs_cache_pressure causes the kernel to prefer to retain dentry and inode caches. Increasing vfs_cache_pressure beyond 100 causes the kernel to prefer to reclaim dentries and inodes. +dirty_background_bytes +---------------------- + +Contains the amount of dirty memory at which the pdflush background writeback +daemon will start writeback. + +If dirty_background_bytes is written, dirty_background_ratio becomes a function +of its value (dirty_background_bytes / the amount of dirtyable system memory). + dirty_background_ratio ---------------------- @@ -1393,14 +1402,29 @@ pages + file cache, not including locked pages and HugePages), the number of pages at which the pdflush background writeback daemon will start writing out dirty data. +If dirty_background_ratio is written, dirty_background_bytes becomes a function +of its value (dirty_background_ratio * the amount of dirtyable system memory). + +dirty_bytes +----------- + +Contains the amount of dirty memory at which a process generating disk writes +will itself start writeback. + +If dirty_bytes is written, dirty_ratio becomes a function of its value +(dirty_bytes / the amount of dirtyable system memory). + dirty_ratio ------------------ +----------- Contains, as a percentage of the dirtyable system memory (free pages + mapped pages + file cache, not including locked pages and HugePages), the number of pages at which a process which is generating disk writes will itself start writing out dirty data. +If dirty_ratio is written, dirty_bytes becomes a function of its value +(dirty_ratio * the amount of dirtyable system memory). + dirty_writeback_centisecs ------------------------- diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index d79eeda7a699..cd05994a49e6 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -41,7 +41,8 @@ Currently, these files are in /proc/sys/vm: ============================================================== -dirty_ratio, dirty_background_ratio, dirty_expire_centisecs, +dirty_bytes, dirty_ratio, dirty_background_bytes, +dirty_background_ratio, dirty_expire_centisecs, dirty_writeback_centisecs, highmem_is_dirtyable, vfs_cache_pressure, laptop_mode, block_dump, swap_token_timeout, drop-caches, hugepages_treat_as_movable: diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 259e9ea58cab..bb28c975c1d7 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -107,7 +107,9 @@ void throttle_vm_writeout(gfp_t gfp_mask); /* These are exported to sysctl. */ extern int dirty_background_ratio; +extern unsigned long dirty_background_bytes; extern int vm_dirty_ratio; +extern unsigned long vm_dirty_bytes; extern int dirty_writeback_interval; extern int dirty_expire_interval; extern int vm_highmem_is_dirtyable; @@ -116,9 +118,18 @@ extern int laptop_mode; extern unsigned long determine_dirtyable_memory(void); +extern int dirty_background_ratio_handler(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos); +extern int dirty_background_bytes_handler(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos); extern int dirty_ratio_handler(struct ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos); +extern int dirty_bytes_handler(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos); struct ctl_table; struct file; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ff6d45c7626f..92f6e5bc3c24 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -87,10 +87,6 @@ extern int rcutorture_runnable; #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */ /* Constants used for minimum and maximum */ -#if defined(CONFIG_HIGHMEM) || defined(CONFIG_DETECT_SOFTLOCKUP) -static int one = 1; -#endif - #ifdef CONFIG_DETECT_SOFTLOCKUP static int sixty = 60; static int neg_one = -1; @@ -101,6 +97,7 @@ static int two = 2; #endif static int zero; +static int one = 1; static int one_hundred = 100; /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ @@ -952,11 +949,21 @@ static struct ctl_table vm_table[] = { .data = &dirty_background_ratio, .maxlen = sizeof(dirty_background_ratio), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = &dirty_background_ratio_handler, .strategy = &sysctl_intvec, .extra1 = &zero, .extra2 = &one_hundred, }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "dirty_background_bytes", + .data = &dirty_background_bytes, + .maxlen = sizeof(dirty_background_bytes), + .mode = 0644, + .proc_handler = &dirty_background_bytes_handler, + .strategy = &sysctl_intvec, + .extra1 = &one, + }, { .ctl_name = VM_DIRTY_RATIO, .procname = "dirty_ratio", @@ -968,6 +975,16 @@ static struct ctl_table vm_table[] = { .extra1 = &zero, .extra2 = &one_hundred, }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "dirty_bytes", + .data = &vm_dirty_bytes, + .maxlen = sizeof(vm_dirty_bytes), + .mode = 0644, + .proc_handler = &dirty_bytes_handler, + .strategy = &sysctl_intvec, + .extra1 = &one, + }, { .procname = "dirty_writeback_centisecs", .data = &dirty_writeback_interval, diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 4d4074cff300..b493db7841dc 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -68,6 +68,12 @@ static inline long sync_writeback_pages(void) */ int dirty_background_ratio = 5; +/* + * dirty_background_bytes starts at 0 (disabled) so that it is a function of + * dirty_background_ratio * the amount of dirtyable memory + */ +unsigned long dirty_background_bytes; + /* * free highmem will not be subtracted from the total free memory * for calculating free ratios if vm_highmem_is_dirtyable is true @@ -79,6 +85,12 @@ int vm_highmem_is_dirtyable; */ int vm_dirty_ratio = 10; +/* + * vm_dirty_bytes starts at 0 (disabled) so that it is a function of + * vm_dirty_ratio * the amount of dirtyable memory + */ +unsigned long vm_dirty_bytes; + /* * The interval between `kupdate'-style writebacks, in jiffies */ @@ -135,23 +147,75 @@ static int calc_period_shift(void) { unsigned long dirty_total; - dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) / 100; + if (vm_dirty_bytes) + dirty_total = vm_dirty_bytes / PAGE_SIZE; + else + dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) / + 100; return 2 + ilog2(dirty_total - 1); } /* - * update the period when the dirty ratio changes. + * update the period when the dirty threshold changes. */ +static void update_completion_period(void) +{ + int shift = calc_period_shift(); + prop_change_shift(&vm_completions, shift); + prop_change_shift(&vm_dirties, shift); +} + +int dirty_background_ratio_handler(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + + ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + if (ret == 0 && write) + dirty_background_bytes = 0; + return ret; +} + +int dirty_background_bytes_handler(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + + ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos); + if (ret == 0 && write) + dirty_background_ratio = 0; + return ret; +} + int dirty_ratio_handler(struct ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { int old_ratio = vm_dirty_ratio; - int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + int ret; + + ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_ratio != old_ratio) { - int shift = calc_period_shift(); - prop_change_shift(&vm_completions, shift); - prop_change_shift(&vm_dirties, shift); + update_completion_period(); + vm_dirty_bytes = 0; + } + return ret; +} + + +int dirty_bytes_handler(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int old_bytes = vm_dirty_bytes; + int ret; + + ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos); + if (ret == 0 && write && vm_dirty_bytes != old_bytes) { + update_completion_period(); + vm_dirty_ratio = 0; } return ret; } @@ -365,23 +429,29 @@ void get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty, unsigned long *pbdi_dirty, struct backing_dev_info *bdi) { - int background_ratio; /* Percentages */ - int dirty_ratio; unsigned long background; unsigned long dirty; unsigned long available_memory = determine_dirtyable_memory(); struct task_struct *tsk; - dirty_ratio = vm_dirty_ratio; - if (dirty_ratio < 5) - dirty_ratio = 5; + if (vm_dirty_bytes) + dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE); + else { + int dirty_ratio; - background_ratio = dirty_background_ratio; - if (background_ratio >= dirty_ratio) - background_ratio = dirty_ratio / 2; + dirty_ratio = vm_dirty_ratio; + if (dirty_ratio < 5) + dirty_ratio = 5; + dirty = (dirty_ratio * available_memory) / 100; + } + + if (dirty_background_bytes) + background = DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE); + else + background = (dirty_background_ratio * available_memory) / 100; - background = (background_ratio * available_memory) / 100; - dirty = (dirty_ratio * available_memory) / 100; + if (background >= dirty) + background = dirty / 2; tsk = current; if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) { background += background / 4; -- cgit v1.2.3 From 63d6c5ad7fc27455ce5cb4706884671fb7e0df08 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 6 Jan 2009 14:39:38 -0800 Subject: mm: remove try_to_munlock from vmscan An unfortunate feature of the Unevictable LRU work was that reclaiming an anonymous page involved an extra scan through the anon_vma: to check that the page is evictable before allocating swap, because the swap could not be freed reliably soon afterwards. Now try_to_free_swap() has replaced remove_exclusive_swap_page(), that's not an issue any more: remove try_to_munlock() call from shrink_page_list(), leaving it to try_to_munmap() to discover if the page is one to be culled to the unevictable list - in which case then try_to_free_swap(). Update unevictable-lru.txt to remove comments on the try_to_munlock() in shrink_page_list(), and shorten some lines over 80 columns. Signed-off-by: Hugh Dickins Cc: Lee Schermerhorn Acked-by: Rik van Riel Cc: Nick Piggin Cc: KAMEZAWA Hiroyuki Cc: Robin Holt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/unevictable-lru.txt | 63 +++++++++++------------------------- mm/vmscan.c | 11 ++----- 2 files changed, 20 insertions(+), 54 deletions(-) (limited to 'Documentation') diff --git a/Documentation/vm/unevictable-lru.txt b/Documentation/vm/unevictable-lru.txt index 125eed560e5a..0706a7282a8c 100644 --- a/Documentation/vm/unevictable-lru.txt +++ b/Documentation/vm/unevictable-lru.txt @@ -137,13 +137,6 @@ shrink_page_list() where they will be detected when vmscan walks the reverse map in try_to_unmap(). If try_to_unmap() returns SWAP_MLOCK, shrink_page_list() will cull the page at that point. -Note that for anonymous pages, shrink_page_list() attempts to add the page to -the swap cache before it tries to unmap the page. To avoid this unnecessary -consumption of swap space, shrink_page_list() calls try_to_munlock() to check -whether any VM_LOCKED vmas map the page without attempting to unmap the page. -If try_to_munlock() returns SWAP_MLOCK, shrink_page_list() will cull the page -without consuming swap space. try_to_munlock() will be described below. - To "cull" an unevictable page, vmscan simply puts the page back on the lru list using putback_lru_page()--the inverse operation to isolate_lru_page()-- after dropping the page lock. Because the condition which makes the page @@ -190,8 +183,8 @@ several places: in the VM_LOCKED flag being set for the vma. 3) in the fault path, if mlocked pages are "culled" in the fault path, and when a VM_LOCKED stack segment is expanded. -4) as mentioned above, in vmscan:shrink_page_list() with attempting to - reclaim a page in a VM_LOCKED vma--via try_to_unmap() or try_to_munlock(). +4) as mentioned above, in vmscan:shrink_page_list() when attempting to + reclaim a page in a VM_LOCKED vma via try_to_unmap(). Mlocked pages become unlocked and rescued from the unevictable list when: @@ -260,9 +253,9 @@ mlock_fixup() filters several classes of "special" vmas: 2) vmas mapping hugetlbfs page are already effectively pinned into memory. We don't need nor want to mlock() these pages. However, to preserve the - prior behavior of mlock()--before the unevictable/mlock changes--mlock_fixup() - will call make_pages_present() in the hugetlbfs vma range to allocate the - huge pages and populate the ptes. + prior behavior of mlock()--before the unevictable/mlock changes-- + mlock_fixup() will call make_pages_present() in the hugetlbfs vma range + to allocate the huge pages and populate the ptes. 3) vmas with VM_DONTEXPAND|VM_RESERVED are generally user space mappings of kernel pages, such as the vdso page, relay channel pages, etc. These pages @@ -322,7 +315,7 @@ __mlock_vma_pages_range()--the same function used to mlock a vma range-- passing a flag to indicate that munlock() is being performed. Because the vma access protections could have been changed to PROT_NONE after -faulting in and mlocking some pages, get_user_pages() was unreliable for visiting +faulting in and mlocking pages, get_user_pages() was unreliable for visiting these pages for munlocking. Because we don't want to leave pages mlocked(), get_user_pages() was enhanced to accept a flag to ignore the permissions when fetching the pages--all of which should be resident as a result of previous @@ -416,8 +409,8 @@ Mlocked Pages: munmap()/exit()/exec() System Call Handling When unmapping an mlocked region of memory, whether by an explicit call to munmap() or via an internal unmap from exit() or exec() processing, we must munlock the pages if we're removing the last VM_LOCKED vma that maps the pages. -Before the unevictable/mlock changes, mlocking did not mark the pages in any way, -so unmapping them required no processing. +Before the unevictable/mlock changes, mlocking did not mark the pages in any +way, so unmapping them required no processing. To munlock a range of memory under the unevictable/mlock infrastructure, the munmap() hander and task address space tear down function call @@ -517,12 +510,10 @@ couldn't be mlocked. Mlocked pages: try_to_munlock() Reverse Map Scan TODO/FIXME: a better name might be page_mlocked()--analogous to the -page_referenced() reverse map walker--especially if we continue to call this -from shrink_page_list(). See related TODO/FIXME below. +page_referenced() reverse map walker. -When munlock_vma_page()--see "Mlocked Pages: munlock()/munlockall() System -Call Handling" above--tries to munlock a page, or when shrink_page_list() -encounters an anonymous page that is not yet in the swap cache, they need to +When munlock_vma_page()--see "Mlocked Pages: munlock()/munlockall() +System Call Handling" above--tries to munlock a page, it needs to determine whether or not the page is mapped by any VM_LOCKED vma, without actually attempting to unmap all ptes from the page. For this purpose, the unevictable/mlock infrastructure introduced a variant of try_to_unmap() called @@ -535,10 +526,7 @@ for VM_LOCKED vmas. When such a vma is found for anonymous pages and file pages mapped in linear VMAs, as in the try_to_unmap() case, the functions attempt to acquire the associated mmap semphore, mlock the page via mlock_vma_page() and return SWAP_MLOCK. This effectively undoes the -pre-clearing of the page's PG_mlocked done by munlock_vma_page() and informs -shrink_page_list() that the anonymous page should be culled rather than added -to the swap cache in preparation for a try_to_unmap() that will almost -certainly fail. +pre-clearing of the page's PG_mlocked done by munlock_vma_page. If try_to_unmap() is unable to acquire a VM_LOCKED vma's associated mmap semaphore, it will return SWAP_AGAIN. This will allow shrink_page_list() @@ -557,10 +545,7 @@ However, the scan can terminate when it encounters a VM_LOCKED vma and can successfully acquire the vma's mmap semphore for read and mlock the page. Although try_to_munlock() can be called many [very many!] times when munlock()ing a large region or tearing down a large address space that has been -mlocked via mlockall(), overall this is a fairly rare event. In addition, -although shrink_page_list() calls try_to_munlock() for every anonymous page that -it handles that is not yet in the swap cache, on average anonymous pages will -have very short reverse map lists. +mlocked via mlockall(), overall this is a fairly rare event. Mlocked Page: Page Reclaim in shrink_*_list() @@ -588,8 +573,8 @@ Some examples of these unevictable pages on the LRU lists are: munlock_vma_page() was forced to let the page back on to the normal LRU list for vmscan to handle. -shrink_inactive_list() also culls any unevictable pages that it finds -on the inactive lists, again diverting them to the appropriate zone's unevictable +shrink_inactive_list() also culls any unevictable pages that it finds on +the inactive lists, again diverting them to the appropriate zone's unevictable lru list. shrink_inactive_list() should only see SHM_LOCKed pages that became SHM_LOCKed after shrink_active_list() had moved them to the inactive list, or pages mapped into VM_LOCKED vmas that munlock_vma_page() couldn't isolate from @@ -597,19 +582,7 @@ the lru to recheck via try_to_munlock(). shrink_inactive_list() won't notice the latter, but will pass on to shrink_page_list(). shrink_page_list() again culls obviously unevictable pages that it could -encounter for similar reason to shrink_inactive_list(). As already discussed, -shrink_page_list() proactively looks for anonymous pages that should have -PG_mlocked set but don't--these would not be detected by page_evictable()--to -avoid adding them to the swap cache unnecessarily. File pages mapped into +encounter for similar reason to shrink_inactive_list(). Pages mapped into VM_LOCKED vmas but without PG_mlocked set will make it all the way to -try_to_unmap(). shrink_page_list() will divert them to the unevictable list when -try_to_unmap() returns SWAP_MLOCK, as discussed above. - -TODO/FIXME: If we can enhance the swap cache to reliably remove entries -with page_count(page) > 2, as long as all ptes are mapped to the page and -not the swap entry, we can probably remove the call to try_to_munlock() in -shrink_page_list() and just remove the page from the swap cache when -try_to_unmap() returns SWAP_MLOCK. Currently, remove_exclusive_swap_page() -doesn't seem to allow that. - - +try_to_unmap(). shrink_page_list() will divert them to the unevictable list +when try_to_unmap() returns SWAP_MLOCK, as discussed above. diff --git a/mm/vmscan.c b/mm/vmscan.c index c8601dd36603..74f875733e2b 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -625,15 +625,6 @@ static unsigned long shrink_page_list(struct list_head *page_list, if (PageAnon(page) && !PageSwapCache(page)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; - switch (try_to_munlock(page)) { - case SWAP_FAIL: /* shouldn't happen */ - case SWAP_AGAIN: - goto keep_locked; - case SWAP_MLOCK: - goto cull_mlocked; - case SWAP_SUCCESS: - ; /* fall thru'; add to swap cache */ - } if (!add_to_swap(page, GFP_ATOMIC)) goto activate_locked; may_enter_fs = 1; @@ -752,6 +743,8 @@ free_it: continue; cull_mlocked: + if (PageSwapCache(page)) + try_to_free_swap(page); unlock_page(page); putback_lru_page(page); continue; -- cgit v1.2.3 From 5f820f648c92a5ecc771a96b3c29aa6e90013bba Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 6 Jan 2009 14:40:59 -0800 Subject: poll: allow f_op->poll to sleep f_op->poll is the only vfs operation which is not allowed to sleep. It's because poll and select implementation used task state to synchronize against wake ups, which doesn't have to be the case anymore as wait/wake interface can now use custom wake up functions. The non-sleep restriction can be a bit tricky because ->poll is not called from an atomic context and the result of accidentally sleeping in ->poll only shows up as temporary busy looping when the timing is right or rather wrong. This patch converts poll/select to use custom wake up function and use separate triggered variable to synchronize against wake up events. The only added overhead is an extra function call during wake up and negligible. This patch removes the one non-sleep exception from vfs locking rules and is beneficial to userland filesystem implementations like FUSE, 9p or peculiar fs like spufs as it's very difficult for those to implement non-sleeping poll method. While at it, make the following cosmetic changes to make poll.h and select.c checkpatch friendly. * s/type * symbol/type *symbol/ : three places in poll.h * remove blank line before EXPORT_SYMBOL() : two places in select.c Oleg: spotted missing barrier in poll_schedule_timeout() Davide: spotted missing write barrier in pollwake() Signed-off-by: Tejun Heo Cc: Eric Van Hensbergen Cc: Ron Minnich Cc: Ingo Molnar Cc: Christoph Hellwig Signed-off-by: Miklos Szeredi Cc: Davide Libenzi Cc: Brad Boyer Cc: Al Viro Cc: Roland McGrath Cc: Mauro Carvalho Chehab Signed-off-by: Andrew Morton Cc: Davide Libenzi Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/Locking | 2 +- drivers/media/video/v4l1-compat.c | 4 +-- fs/select.c | 76 +++++++++++++++++++++++++++++++-------- include/linux/poll.h | 15 ++++++-- 4 files changed, 76 insertions(+), 21 deletions(-) (limited to 'Documentation') diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index ccec55394380..cfbfa15a46ba 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -397,7 +397,7 @@ prototypes: }; locking rules: - All except ->poll() may block. + All may block. BKL llseek: no (see below) read: no diff --git a/drivers/media/video/v4l1-compat.c b/drivers/media/video/v4l1-compat.c index d450cab20be4..b617bf05e2d7 100644 --- a/drivers/media/video/v4l1-compat.c +++ b/drivers/media/video/v4l1-compat.c @@ -203,7 +203,6 @@ static int poll_one(struct file *file, struct poll_wqueues *pwq) table = &pwq->pt; for (;;) { int mask; - set_current_state(TASK_INTERRUPTIBLE); mask = file->f_op->poll(file, table); if (mask & POLLIN) break; @@ -212,9 +211,8 @@ static int poll_one(struct file *file, struct poll_wqueues *pwq) retval = -ERESTARTSYS; break; } - schedule(); + poll_schedule(pwq, TASK_INTERRUPTIBLE); } - set_current_state(TASK_RUNNING); poll_freewait(pwq); return retval; } diff --git a/fs/select.c b/fs/select.c index 87df51eadcf2..08b91beed806 100644 --- a/fs/select.c +++ b/fs/select.c @@ -109,11 +109,11 @@ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, void poll_initwait(struct poll_wqueues *pwq) { init_poll_funcptr(&pwq->pt, __pollwait); + pwq->polling_task = current; pwq->error = 0; pwq->table = NULL; pwq->inline_index = 0; } - EXPORT_SYMBOL(poll_initwait); static void free_poll_entry(struct poll_table_entry *entry) @@ -142,12 +142,10 @@ void poll_freewait(struct poll_wqueues *pwq) free_page((unsigned long) old); } } - EXPORT_SYMBOL(poll_freewait); -static struct poll_table_entry *poll_get_entry(poll_table *_p) +static struct poll_table_entry *poll_get_entry(struct poll_wqueues *p) { - struct poll_wqueues *p = container_of(_p, struct poll_wqueues, pt); struct poll_table_page *table = p->table; if (p->inline_index < N_INLINE_POLL_ENTRIES) @@ -159,7 +157,6 @@ static struct poll_table_entry *poll_get_entry(poll_table *_p) new_table = (struct poll_table_page *) __get_free_page(GFP_KERNEL); if (!new_table) { p->error = -ENOMEM; - __set_current_state(TASK_RUNNING); return NULL; } new_table->entry = new_table->entries; @@ -171,20 +168,75 @@ static struct poll_table_entry *poll_get_entry(poll_table *_p) return table->entry++; } +static int pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key) +{ + struct poll_wqueues *pwq = wait->private; + DECLARE_WAITQUEUE(dummy_wait, pwq->polling_task); + + /* + * Although this function is called under waitqueue lock, LOCK + * doesn't imply write barrier and the users expect write + * barrier semantics on wakeup functions. The following + * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up() + * and is paired with set_mb() in poll_schedule_timeout. + */ + smp_wmb(); + pwq->triggered = 1; + + /* + * Perform the default wake up operation using a dummy + * waitqueue. + * + * TODO: This is hacky but there currently is no interface to + * pass in @sync. @sync is scheduled to be removed and once + * that happens, wake_up_process() can be used directly. + */ + return default_wake_function(&dummy_wait, mode, sync, key); +} + /* Add a new entry */ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p) { - struct poll_table_entry *entry = poll_get_entry(p); + struct poll_wqueues *pwq = container_of(p, struct poll_wqueues, pt); + struct poll_table_entry *entry = poll_get_entry(pwq); if (!entry) return; get_file(filp); entry->filp = filp; entry->wait_address = wait_address; - init_waitqueue_entry(&entry->wait, current); + init_waitqueue_func_entry(&entry->wait, pollwake); + entry->wait.private = pwq; add_wait_queue(wait_address, &entry->wait); } +int poll_schedule_timeout(struct poll_wqueues *pwq, int state, + ktime_t *expires, unsigned long slack) +{ + int rc = -EINTR; + + set_current_state(state); + if (!pwq->triggered) + rc = schedule_hrtimeout_range(expires, slack, HRTIMER_MODE_ABS); + __set_current_state(TASK_RUNNING); + + /* + * Prepare for the next iteration. + * + * The following set_mb() serves two purposes. First, it's + * the counterpart rmb of the wmb in pollwake() such that data + * written before wake up is always visible after wake up. + * Second, the full barrier guarantees that triggered clearing + * doesn't pass event check of the next iteration. Note that + * this problem doesn't exist for the first iteration as + * add_wait_queue() has full barrier semantics. + */ + set_mb(pwq->triggered, 0); + + return rc; +} +EXPORT_SYMBOL(poll_schedule_timeout); + /** * poll_select_set_timeout - helper function to setup the timeout value * @to: pointer to timespec variable for the final timeout @@ -340,8 +392,6 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) for (;;) { unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp; - set_current_state(TASK_INTERRUPTIBLE); - inp = fds->in; outp = fds->out; exp = fds->ex; rinp = fds->res_in; routp = fds->res_out; rexp = fds->res_ex; @@ -411,10 +461,10 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) to = &expire; } - if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) + if (!poll_schedule_timeout(&table, TASK_INTERRUPTIBLE, + to, slack)) timed_out = 1; } - __set_current_state(TASK_RUNNING); poll_freewait(&table); @@ -666,7 +716,6 @@ static int do_poll(unsigned int nfds, struct poll_list *list, for (;;) { struct poll_list *walk; - set_current_state(TASK_INTERRUPTIBLE); for (walk = list; walk != NULL; walk = walk->next) { struct pollfd * pfd, * pfd_end; @@ -709,10 +758,9 @@ static int do_poll(unsigned int nfds, struct poll_list *list, to = &expire; } - if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) + if (!poll_schedule_timeout(wait, TASK_INTERRUPTIBLE, to, slack)) timed_out = 1; } - __set_current_state(TASK_RUNNING); return count; } diff --git a/include/linux/poll.h b/include/linux/poll.h index badd98ab06f6..8c24ef8d9976 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -46,9 +46,9 @@ static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc) } struct poll_table_entry { - struct file * filp; + struct file *filp; wait_queue_t wait; - wait_queue_head_t * wait_address; + wait_queue_head_t *wait_address; }; /* @@ -56,7 +56,9 @@ struct poll_table_entry { */ struct poll_wqueues { poll_table pt; - struct poll_table_page * table; + struct poll_table_page *table; + struct task_struct *polling_task; + int triggered; int error; int inline_index; struct poll_table_entry inline_entries[N_INLINE_POLL_ENTRIES]; @@ -64,6 +66,13 @@ struct poll_wqueues { extern void poll_initwait(struct poll_wqueues *pwq); extern void poll_freewait(struct poll_wqueues *pwq); +extern int poll_schedule_timeout(struct poll_wqueues *pwq, int state, + ktime_t *expires, unsigned long slack); + +static inline int poll_schedule(struct poll_wqueues *pwq, int state) +{ + return poll_schedule_timeout(pwq, state, NULL, 0); +} /* * Scaleable version of the fd_set. -- cgit v1.2.3 From 89fac11cb3e7c5860c425dba14845c09ccede39d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 6 Jan 2009 14:41:34 -0800 Subject: adt7470: make automatic fan control really work It turns out that the adt7470's automatic fan control algorithm only works when the temperature sensors get updated. This in turn happens only when someone tells the chip to read its temperature sensors. Regrettably, this means that we have to drive the chip periodically. Signed-off-by: Darrick J. Wong Cc: Jean Delvare Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/hwmon/adt7470 | 19 +++--- drivers/hwmon/adt7470.c | 156 +++++++++++++++++++++++++++++++++++++------- 2 files changed, 142 insertions(+), 33 deletions(-) (limited to 'Documentation') diff --git a/Documentation/hwmon/adt7470 b/Documentation/hwmon/adt7470 index 75d13ca147cc..8ce4aa0a0f55 100644 --- a/Documentation/hwmon/adt7470 +++ b/Documentation/hwmon/adt7470 @@ -31,15 +31,11 @@ Each of the measured inputs (temperature, fan speed) has corresponding high/low limit values. The ADT7470 will signal an ALARM if any measured value exceeds either limit. -The ADT7470 DOES NOT sample all inputs continuously. A single pin on the -ADT7470 is connected to a multitude of thermal diodes, but the chip must be -instructed explicitly to read the multitude of diodes. If you want to use -automatic fan control mode, you must manually read any of the temperature -sensors or the fan control algorithm will not run. The chip WILL NOT DO THIS -AUTOMATICALLY; this must be done from userspace. This may be a bug in the chip -design, given that many other AD chips take care of this. The driver will not -read the registers more often than once every 5 seconds. Further, -configuration data is only read once per minute. +The ADT7470 samples all inputs continuously. A kernel thread is started up for +the purpose of periodically querying the temperature sensors, thus allowing the +automatic fan pwm control to set the fan speed. The driver will not read the +registers more often than once every 5 seconds. Further, configuration data is +only read once per minute. Special Features ---------------- @@ -72,5 +68,6 @@ pwm#_auto_point2_temp. Notes ----- -As stated above, the temperature inputs must be read periodically from -userspace in order for the automatic pwm algorithm to run. +The temperature inputs no longer need to be read periodically from userspace in +order for the automatic pwm algorithm to run. This was the case for earlier +versions of the driver. diff --git a/drivers/hwmon/adt7470.c b/drivers/hwmon/adt7470.c index ab8d5ebc9f75..633e1a1e9d79 100644 --- a/drivers/hwmon/adt7470.c +++ b/drivers/hwmon/adt7470.c @@ -28,6 +28,7 @@ #include #include #include +#include /* Addresses to scan */ static const unsigned short normal_i2c[] = { 0x2C, 0x2E, 0x2F, I2C_CLIENT_END }; @@ -132,6 +133,9 @@ I2C_CLIENT_INSMOD_1(adt7470); /* Wait at least 200ms per sensor for 10 sensors */ #define TEMP_COLLECTION_TIME 2000 +/* auto update thing won't fire more than every 2s */ +#define AUTO_UPDATE_INTERVAL 2000 + /* datasheet says to divide this number by the fan reading to get fan rpm */ #define FAN_PERIOD_TO_RPM(x) ((90000 * 60) / (x)) #define FAN_RPM_TO_PERIOD FAN_PERIOD_TO_RPM @@ -148,6 +152,7 @@ struct adt7470_data { unsigned long limits_last_updated; /* In jiffies */ int num_temp_sensors; /* -1 = probe */ + int temperatures_probed; s8 temp[ADT7470_TEMP_COUNT]; s8 temp_min[ADT7470_TEMP_COUNT]; @@ -164,6 +169,10 @@ struct adt7470_data { u8 pwm_min[ADT7470_PWM_COUNT]; s8 pwm_tmin[ADT7470_PWM_COUNT]; u8 pwm_auto_temp[ADT7470_PWM_COUNT]; + + struct task_struct *auto_update; + struct completion auto_update_stop; + unsigned int auto_update_interval; }; static int adt7470_probe(struct i2c_client *client, @@ -221,19 +230,13 @@ static void adt7470_init_client(struct i2c_client *client) } } -static struct adt7470_data *adt7470_update_device(struct device *dev) +/* Probe for temperature sensors. Assumes lock is held */ +static int adt7470_read_temperatures(struct i2c_client *client, + struct adt7470_data *data) { - struct i2c_client *client = to_i2c_client(dev); - struct adt7470_data *data = i2c_get_clientdata(client); - unsigned long local_jiffies = jiffies; - u8 cfg, pwm[4], pwm_cfg[2]; + unsigned long res; int i; - - mutex_lock(&data->lock); - if (time_before(local_jiffies, data->sensors_last_updated + - SENSOR_REFRESH_INTERVAL) - && data->sensors_valid) - goto no_sensor_update; + u8 cfg, pwm[4], pwm_cfg[2]; /* save pwm[1-4] config register */ pwm_cfg[0] = i2c_smbus_read_byte_data(client, ADT7470_REG_PWM_CFG(0)); @@ -259,9 +262,9 @@ static struct adt7470_data *adt7470_update_device(struct device *dev) i2c_smbus_write_byte_data(client, ADT7470_REG_CFG, cfg); /* Delay is 200ms * number of temp sensors. */ - msleep((data->num_temp_sensors >= 0 ? - data->num_temp_sensors * 200 : - TEMP_COLLECTION_TIME)); + res = msleep_interruptible((data->num_temp_sensors >= 0 ? + data->num_temp_sensors * 200 : + TEMP_COLLECTION_TIME)); /* done reading temperature sensors */ cfg = i2c_smbus_read_byte_data(client, ADT7470_REG_CFG); @@ -272,15 +275,81 @@ static struct adt7470_data *adt7470_update_device(struct device *dev) i2c_smbus_write_byte_data(client, ADT7470_REG_PWM_CFG(0), pwm_cfg[0]); i2c_smbus_write_byte_data(client, ADT7470_REG_PWM_CFG(2), pwm_cfg[1]); - for (i = 0; i < ADT7470_TEMP_COUNT; i++) + if (res) { + printk(KERN_ERR "ha ha, interrupted"); + return -EAGAIN; + } + + /* Only count fans if we have to */ + if (data->num_temp_sensors >= 0) + return 0; + + for (i = 0; i < ADT7470_TEMP_COUNT; i++) { data->temp[i] = i2c_smbus_read_byte_data(client, ADT7470_TEMP_REG(i)); + if (data->temp[i]) + data->num_temp_sensors = i + 1; + } + data->temperatures_probed = 1; + return 0; +} - /* Figure out the number of temp sensors */ - if (data->num_temp_sensors < 0) +static int adt7470_update_thread(void *p) +{ + struct i2c_client *client = p; + struct adt7470_data *data = i2c_get_clientdata(client); + + while (!kthread_should_stop()) { + mutex_lock(&data->lock); + adt7470_read_temperatures(client, data); + mutex_unlock(&data->lock); + if (kthread_should_stop()) + break; + msleep_interruptible(data->auto_update_interval); + } + + complete_all(&data->auto_update_stop); + return 0; +} + +static struct adt7470_data *adt7470_update_device(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + struct adt7470_data *data = i2c_get_clientdata(client); + unsigned long local_jiffies = jiffies; + u8 cfg; + int i; + int need_sensors = 1; + int need_limits = 1; + + /* + * Figure out if we need to update the shadow registers. + * Lockless means that we may occasionally report out of + * date data. + */ + if (time_before(local_jiffies, data->sensors_last_updated + + SENSOR_REFRESH_INTERVAL) && + data->sensors_valid) + need_sensors = 0; + + if (time_before(local_jiffies, data->limits_last_updated + + LIMIT_REFRESH_INTERVAL) && + data->limits_valid) + need_limits = 0; + + if (!need_sensors && !need_limits) + return data; + + mutex_lock(&data->lock); + if (!need_sensors) + goto no_sensor_update; + + if (!data->temperatures_probed) + adt7470_read_temperatures(client, data); + else for (i = 0; i < ADT7470_TEMP_COUNT; i++) - if (data->temp[i]) - data->num_temp_sensors = i + 1; + data->temp[i] = i2c_smbus_read_byte_data(client, + ADT7470_TEMP_REG(i)); for (i = 0; i < ADT7470_FAN_COUNT; i++) data->fan[i] = adt7470_read_word_data(client, @@ -329,9 +398,7 @@ static struct adt7470_data *adt7470_update_device(struct device *dev) data->sensors_valid = 1; no_sensor_update: - if (time_before(local_jiffies, data->limits_last_updated + - LIMIT_REFRESH_INTERVAL) - && data->limits_valid) + if (!need_limits) goto out; for (i = 0; i < ADT7470_TEMP_COUNT; i++) { @@ -365,6 +432,35 @@ out: return data; } +static ssize_t show_auto_update_interval(struct device *dev, + struct device_attribute *devattr, + char *buf) +{ + struct adt7470_data *data = adt7470_update_device(dev); + return sprintf(buf, "%d\n", data->auto_update_interval); +} + +static ssize_t set_auto_update_interval(struct device *dev, + struct device_attribute *devattr, + const char *buf, + size_t count) +{ + struct i2c_client *client = to_i2c_client(dev); + struct adt7470_data *data = i2c_get_clientdata(client); + long temp; + + if (strict_strtol(buf, 10, &temp)) + return -EINVAL; + + temp = SENSORS_LIMIT(temp, 0, 60000); + + mutex_lock(&data->lock); + data->auto_update_interval = temp; + mutex_unlock(&data->lock); + + return count; +} + static ssize_t show_num_temp_sensors(struct device *dev, struct device_attribute *devattr, char *buf) @@ -389,6 +485,8 @@ static ssize_t set_num_temp_sensors(struct device *dev, mutex_lock(&data->lock); data->num_temp_sensors = temp; + if (temp < 0) + data->temperatures_probed = 0; mutex_unlock(&data->lock); return count; @@ -862,6 +960,8 @@ static ssize_t show_alarm(struct device *dev, static DEVICE_ATTR(alarm_mask, S_IRUGO, show_alarm_mask, NULL); static DEVICE_ATTR(num_temp_sensors, S_IWUSR | S_IRUGO, show_num_temp_sensors, set_num_temp_sensors); +static DEVICE_ATTR(auto_update_interval, S_IWUSR | S_IRUGO, + show_auto_update_interval, set_auto_update_interval); static SENSOR_DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO, show_temp_max, set_temp_max, 0); @@ -1035,6 +1135,7 @@ static struct attribute *adt7470_attr[] = { &dev_attr_alarm_mask.attr, &dev_attr_num_temp_sensors.attr, + &dev_attr_auto_update_interval.attr, &sensor_dev_attr_temp1_max.dev_attr.attr, &sensor_dev_attr_temp2_max.dev_attr.attr, &sensor_dev_attr_temp3_max.dev_attr.attr, @@ -1168,6 +1269,7 @@ static int adt7470_probe(struct i2c_client *client, } data->num_temp_sensors = -1; + data->auto_update_interval = AUTO_UPDATE_INTERVAL; i2c_set_clientdata(client, data); mutex_init(&data->lock); @@ -1188,8 +1290,16 @@ static int adt7470_probe(struct i2c_client *client, goto exit_remove; } + init_completion(&data->auto_update_stop); + data->auto_update = kthread_run(adt7470_update_thread, client, + dev_name(data->hwmon_dev)); + if (IS_ERR(data->auto_update)) + goto exit_unregister; + return 0; +exit_unregister: + hwmon_device_unregister(data->hwmon_dev); exit_remove: sysfs_remove_group(&client->dev.kobj, &data->attrs); exit_free: @@ -1202,6 +1312,8 @@ static int adt7470_remove(struct i2c_client *client) { struct adt7470_data *data = i2c_get_clientdata(client); + kthread_stop(data->auto_update); + wait_for_completion(&data->auto_update_stop); hwmon_device_unregister(data->hwmon_dev); sysfs_remove_group(&client->dev.kobj, &data->attrs); kfree(data); -- cgit v1.2.3 From e8386a0cb22f4a2d439384212c494ad0bda848fe Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 6 Jan 2009 14:41:52 -0800 Subject: kprobes: support probing module __exit function Allows kprobes to probe __exit routine. This adds flags member to struct kprobe. When module is freed(kprobes hooks module_notifier to get this event), kprobes which probe the functions in that module are set to "Gone" flag to the flags member. These "Gone" probes are never be enabled. Users can check the GONE flag through debugfs. This also removes mod_refcounted, because we couldn't free a module if kprobe incremented the refcount of that module. [akpm@linux-foundation.org: document some locking] [mhiramat@redhat.com: bugfix: pass aggr_kprobe to arch_remove_kprobe] [mhiramat@redhat.com: bugfix: release old_p's insn_slot before error return] Signed-off-by: Masami Hiramatsu Acked-by: Ananth N Mavinakayanahalli Cc: Anil S Keshavamurthy Signed-off-by: Masami Hiramatsu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kprobes.txt | 5 +- include/linux/kprobes.h | 14 +++- kernel/kprobes.c | 159 ++++++++++++++++++++++++++++++++++------------ 3 files changed, 134 insertions(+), 44 deletions(-) (limited to 'Documentation') diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt index a79633d702bf..48b3de90eb1e 100644 --- a/Documentation/kprobes.txt +++ b/Documentation/kprobes.txt @@ -497,7 +497,10 @@ The first column provides the kernel address where the probe is inserted. The second column identifies the type of probe (k - kprobe, r - kretprobe and j - jprobe), while the third column specifies the symbol+offset of the probe. If the probed function belongs to a module, the module name -is also specified. +is also specified. Following columns show probe status. If the probe is on +a virtual address that is no longer valid (module init sections, module +virtual addresses that correspond to modules that've been unloaded), +such probes are marked with [GONE]. /debug/kprobes/enabled: Turn kprobes ON/OFF diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index b93e44ce2284..d6ea19e314bb 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -69,9 +69,6 @@ struct kprobe { /* list of kprobes for multi-handler support */ struct list_head list; - /* Indicates that the corresponding module has been ref counted */ - unsigned int mod_refcounted; - /*count the number of times this probe was temporarily disarmed */ unsigned long nmissed; @@ -103,8 +100,19 @@ struct kprobe { /* copy of the original instruction */ struct arch_specific_insn ainsn; + + /* Indicates various status flags. Protected by kprobe_mutex. */ + u32 flags; }; +/* Kprobe status flags */ +#define KPROBE_FLAG_GONE 1 /* breakpoint has already gone */ + +static inline int kprobe_gone(struct kprobe *p) +{ + return p->flags & KPROBE_FLAG_GONE; +} + /* * Special probe type that uses setjmp-longjmp type tricks to resume * execution at a specified entry with a matching prototype corresponding diff --git a/kernel/kprobes.c b/kernel/kprobes.c index a1e233a19586..cb732a9aa55f 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -327,7 +327,7 @@ static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs) struct kprobe *kp; list_for_each_entry_rcu(kp, &p->list, list) { - if (kp->pre_handler) { + if (kp->pre_handler && !kprobe_gone(kp)) { set_kprobe_instance(kp); if (kp->pre_handler(kp, regs)) return 1; @@ -343,7 +343,7 @@ static void __kprobes aggr_post_handler(struct kprobe *p, struct pt_regs *regs, struct kprobe *kp; list_for_each_entry_rcu(kp, &p->list, list) { - if (kp->post_handler) { + if (kp->post_handler && !kprobe_gone(kp)) { set_kprobe_instance(kp); kp->post_handler(kp, regs, flags); reset_kprobe_instance(); @@ -545,9 +545,10 @@ static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p) ap->addr = p->addr; ap->pre_handler = aggr_pre_handler; ap->fault_handler = aggr_fault_handler; - if (p->post_handler) + /* We don't care the kprobe which has gone. */ + if (p->post_handler && !kprobe_gone(p)) ap->post_handler = aggr_post_handler; - if (p->break_handler) + if (p->break_handler && !kprobe_gone(p)) ap->break_handler = aggr_break_handler; INIT_LIST_HEAD(&ap->list); @@ -566,17 +567,41 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p, int ret = 0; struct kprobe *ap; + if (kprobe_gone(old_p)) { + /* + * Attempting to insert new probe at the same location that + * had a probe in the module vaddr area which already + * freed. So, the instruction slot has already been + * released. We need a new slot for the new probe. + */ + ret = arch_prepare_kprobe(old_p); + if (ret) + return ret; + } if (old_p->pre_handler == aggr_pre_handler) { copy_kprobe(old_p, p); ret = add_new_kprobe(old_p, p); + ap = old_p; } else { ap = kzalloc(sizeof(struct kprobe), GFP_KERNEL); - if (!ap) + if (!ap) { + if (kprobe_gone(old_p)) + arch_remove_kprobe(old_p); return -ENOMEM; + } add_aggr_kprobe(ap, old_p); copy_kprobe(ap, p); ret = add_new_kprobe(ap, p); } + if (kprobe_gone(old_p)) { + /* + * If the old_p has gone, its breakpoint has been disarmed. + * We have to arm it again after preparing real kprobes. + */ + ap->flags &= ~KPROBE_FLAG_GONE; + if (kprobe_enabled) + arch_arm_kprobe(ap); + } return ret; } @@ -639,8 +664,7 @@ static int __kprobes __register_kprobe(struct kprobe *p, return -EINVAL; } - p->mod_refcounted = 0; - + p->flags = 0; /* * Check if are we probing a module. */ @@ -649,16 +673,14 @@ static int __kprobes __register_kprobe(struct kprobe *p, struct module *calling_mod; calling_mod = __module_text_address(called_from); /* - * We must allow modules to probe themself and in this case - * avoid incrementing the module refcount, so as to allow - * unloading of self probing modules. + * We must hold a refcount of the probed module while updating + * its code to prohibit unexpected unloading. */ if (calling_mod != probed_mod) { if (unlikely(!try_module_get(probed_mod))) { preempt_enable(); return -EINVAL; } - p->mod_refcounted = 1; } else probed_mod = NULL; } @@ -687,8 +709,9 @@ static int __kprobes __register_kprobe(struct kprobe *p, out: mutex_unlock(&kprobe_mutex); - if (ret && probed_mod) + if (probed_mod) module_put(probed_mod); + return ret; } @@ -716,16 +739,16 @@ valid_p: list_is_singular(&old_p->list))) { /* * Only probe on the hash list. Disarm only if kprobes are - * enabled - otherwise, the breakpoint would already have - * been removed. We save on flushing icache. + * enabled and not gone - otherwise, the breakpoint would + * already have been removed. We save on flushing icache. */ - if (kprobe_enabled) + if (kprobe_enabled && !kprobe_gone(old_p)) arch_disarm_kprobe(p); hlist_del_rcu(&old_p->hlist); } else { - if (p->break_handler) + if (p->break_handler && !kprobe_gone(p)) old_p->break_handler = NULL; - if (p->post_handler) { + if (p->post_handler && !kprobe_gone(p)) { list_for_each_entry_rcu(list_p, &old_p->list, list) { if ((list_p != p) && (list_p->post_handler)) goto noclean; @@ -740,27 +763,16 @@ noclean: static void __kprobes __unregister_kprobe_bottom(struct kprobe *p) { - struct module *mod; struct kprobe *old_p; - if (p->mod_refcounted) { - /* - * Since we've already incremented refcount, - * we don't need to disable preemption. - */ - mod = module_text_address((unsigned long)p->addr); - if (mod) - module_put(mod); - } - - if (list_empty(&p->list) || list_is_singular(&p->list)) { - if (!list_empty(&p->list)) { - /* "p" is the last child of an aggr_kprobe */ - old_p = list_entry(p->list.next, struct kprobe, list); - list_del(&p->list); - kfree(old_p); - } + if (list_empty(&p->list)) arch_remove_kprobe(p); + else if (list_is_singular(&p->list)) { + /* "p" is the last child of an aggr_kprobe */ + old_p = list_entry(p->list.next, struct kprobe, list); + list_del(&p->list); + arch_remove_kprobe(old_p); + kfree(old_p); } } @@ -1074,6 +1086,67 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p, #endif /* CONFIG_KRETPROBES */ +/* Set the kprobe gone and remove its instruction buffer. */ +static void __kprobes kill_kprobe(struct kprobe *p) +{ + struct kprobe *kp; + p->flags |= KPROBE_FLAG_GONE; + if (p->pre_handler == aggr_pre_handler) { + /* + * If this is an aggr_kprobe, we have to list all the + * chained probes and mark them GONE. + */ + list_for_each_entry_rcu(kp, &p->list, list) + kp->flags |= KPROBE_FLAG_GONE; + p->post_handler = NULL; + p->break_handler = NULL; + } + /* + * Here, we can remove insn_slot safely, because no thread calls + * the original probed function (which will be freed soon) any more. + */ + arch_remove_kprobe(p); +} + +/* Module notifier call back, checking kprobes on the module */ +static int __kprobes kprobes_module_callback(struct notifier_block *nb, + unsigned long val, void *data) +{ + struct module *mod = data; + struct hlist_head *head; + struct hlist_node *node; + struct kprobe *p; + unsigned int i; + + if (val != MODULE_STATE_GOING) + return NOTIFY_DONE; + + /* + * module .text section will be freed. We need to + * disable kprobes which have been inserted in the section. + */ + mutex_lock(&kprobe_mutex); + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + head = &kprobe_table[i]; + hlist_for_each_entry_rcu(p, node, head, hlist) + if (within_module_core((unsigned long)p->addr, mod)) { + /* + * The vaddr this probe is installed will soon + * be vfreed buy not synced to disk. Hence, + * disarming the breakpoint isn't needed. + */ + kill_kprobe(p); + } + } + mutex_unlock(&kprobe_mutex); + return NOTIFY_DONE; +} + +static struct notifier_block kprobe_module_nb = { + .notifier_call = kprobes_module_callback, + .priority = 0 +}; + static int __init init_kprobes(void) { int i, err = 0; @@ -1130,6 +1203,9 @@ static int __init init_kprobes(void) err = arch_init_kprobes(); if (!err) err = register_die_notifier(&kprobe_exceptions_nb); + if (!err) + err = register_module_notifier(&kprobe_module_nb); + kprobes_initialized = (err == 0); if (!err) @@ -1150,10 +1226,12 @@ static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p, else kprobe_type = "k"; if (sym) - seq_printf(pi, "%p %s %s+0x%x %s\n", p->addr, kprobe_type, - sym, offset, (modname ? modname : " ")); + seq_printf(pi, "%p %s %s+0x%x %s %s\n", p->addr, kprobe_type, + sym, offset, (modname ? modname : " "), + (kprobe_gone(p) ? "[GONE]" : "")); else - seq_printf(pi, "%p %s %p\n", p->addr, kprobe_type, p->addr); + seq_printf(pi, "%p %s %p %s\n", p->addr, kprobe_type, p->addr, + (kprobe_gone(p) ? "[GONE]" : "")); } static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos) @@ -1234,7 +1312,8 @@ static void __kprobes enable_all_kprobes(void) for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry_rcu(p, node, head, hlist) - arch_arm_kprobe(p); + if (!kprobe_gone(p)) + arch_arm_kprobe(p); } kprobe_enabled = true; @@ -1263,7 +1342,7 @@ static void __kprobes disable_all_kprobes(void) for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry_rcu(p, node, head, hlist) { - if (!arch_trampoline_kprobe(p)) + if (!arch_trampoline_kprobe(p) && !kprobe_gone(p)) arch_disarm_kprobe(p); } } -- cgit v1.2.3 From d78dd070ccda6384efeae142b116bc174f0cd9fa Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 6 Jan 2009 14:42:40 -0800 Subject: docs: document how to write @varargs in kernel-doc Add documentation on how to use kernel-doc for function parameters that are "..." (varargs). Signed-off-by: Randy Dunlap Cc: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-doc-nano-HOWTO.txt | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'Documentation') diff --git a/Documentation/kernel-doc-nano-HOWTO.txt b/Documentation/kernel-doc-nano-HOWTO.txt index c6841eee9598..4115a4a80eb6 100644 --- a/Documentation/kernel-doc-nano-HOWTO.txt +++ b/Documentation/kernel-doc-nano-HOWTO.txt @@ -71,6 +71,11 @@ The @argument descriptions must begin on the very next line following this opening short function description line, with no intervening empty comment lines. +If a function parameter is "..." (varargs), it should be listed in +kernel-doc notation as: + * @...: description + + Example kernel-doc data structure comment. /** -- cgit v1.2.3 From 07983f0e36eab01a5385117e55154a2aa796eafc Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 6 Jan 2009 14:42:41 -0800 Subject: documentation: update header file paths Update several Documentation/ files and a few sub-dir files (only one change in each) to reflect changed header files locations. Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/DMA-mapping.txt | 2 +- Documentation/ioctl/ioctl-number.txt | 8 ++++---- Documentation/kernel-parameters.txt | 4 ++-- Documentation/magic-number.txt | 6 +++--- Documentation/mips/AU1xxx_IDE.README | 2 +- Documentation/powerpc/cpu_features.txt | 2 +- Documentation/x86/zero-page.txt | 2 +- 7 files changed, 13 insertions(+), 13 deletions(-) (limited to 'Documentation') diff --git a/Documentation/DMA-mapping.txt b/Documentation/DMA-mapping.txt index c74fec8c2351..b2a4d6d244d9 100644 --- a/Documentation/DMA-mapping.txt +++ b/Documentation/DMA-mapping.txt @@ -26,7 +26,7 @@ mapped only for the time they are actually used and unmapped after the DMA transfer. The following API will work of course even on platforms where no such -hardware exists, see e.g. include/asm-i386/pci.h for how it is implemented on +hardware exists, see e.g. arch/x86/include/asm/pci.h for how it is implemented on top of the virt_to_bus interface. First of all, you should make sure diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt index 824699174436..f1d639903325 100644 --- a/Documentation/ioctl/ioctl-number.txt +++ b/Documentation/ioctl/ioctl-number.txt @@ -84,7 +84,7 @@ Code Seq# Include File Comments 'B' C0-FF advanced bbus 'C' all linux/soundcard.h -'D' all asm-s390/dasd.h +'D' all arch/s390/include/asm/dasd.h 'E' all linux/input.h 'F' all linux/fb.h 'H' all linux/hiddev.h @@ -105,7 +105,7 @@ Code Seq# Include File Comments 'S' 80-81 scsi/scsi_ioctl.h conflict! 'S' 82-FF scsi/scsi.h conflict! 'T' all linux/soundcard.h conflict! -'T' all asm-i386/ioctls.h conflict! +'T' all arch/x86/include/asm/ioctls.h conflict! 'U' 00-EF linux/drivers/usb/usb.h 'V' all linux/vt.h 'W' 00-1F linux/watchdog.h conflict! @@ -120,7 +120,7 @@ Code Seq# Include File Comments 'c' 00-7F linux/comstats.h conflict! 'c' 00-7F linux/coda.h conflict! -'c' 80-9F asm-s390/chsc.h +'c' 80-9F arch/s390/include/asm/chsc.h 'd' 00-FF linux/char/drm/drm/h conflict! 'd' 00-DF linux/video_decoder.h conflict! 'd' F0-FF linux/digi1.h @@ -170,7 +170,7 @@ Code Seq# Include File Comments 0x80 00-1F linux/fb.h 0x81 00-1F linux/videotext.h -0x89 00-06 asm-i386/sockios.h +0x89 00-06 arch/x86/include/asm/sockios.h 0x89 0B-DF linux/sockios.h 0x89 E0-EF linux/sockios.h SIOCPROTOPRIVATE range 0x89 F0-FF linux/sockios.h SIOCDEVPRIVATE range diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index a2d8805c03d5..7f0b694e02e8 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -469,8 +469,8 @@ and is between 256 and 4096 characters. It is defined in the file clearcpuid=BITNUM [X86] Disable CPUID feature X for the kernel. See - include/asm-x86/cpufeature.h for the valid bit numbers. - Note the Linux specific bits are not necessarily + arch/x86/include/asm/cpufeature.h for the valid bit + numbers. Note the Linux specific bits are not necessarily stable over kernel options, but the vendor specific ones should be. Also note that user programs calling CPUID directly diff --git a/Documentation/magic-number.txt b/Documentation/magic-number.txt index 95070028d15e..505f19607542 100644 --- a/Documentation/magic-number.txt +++ b/Documentation/magic-number.txt @@ -125,14 +125,14 @@ TRIDENT_CARD_MAGIC 0x5072696E trident_card sound/oss/trident.c ROUTER_MAGIC 0x524d4157 wan_device include/linux/wanrouter.h SCC_MAGIC 0x52696368 gs_port drivers/char/scc.h SAVEKMSG_MAGIC1 0x53415645 savekmsg arch/*/amiga/config.c -GDA_MAGIC 0x58464552 gda include/asm-mips64/sn/gda.h +GDA_MAGIC 0x58464552 gda arch/mips/include/asm/sn/gda.h RED_MAGIC1 0x5a2cf071 (any) mm/slab.c STL_PORTMAGIC 0x5a7182c9 stlport include/linux/stallion.h EEPROM_MAGIC_VALUE 0x5ab478d2 lanai_dev drivers/atm/lanai.c HDLCDRV_MAGIC 0x5ac6e778 hdlcdrv_state include/linux/hdlcdrv.h EPCA_MAGIC 0x5c6df104 channel include/linux/epca.h PCXX_MAGIC 0x5c6df104 channel drivers/char/pcxx.h -KV_MAGIC 0x5f4b565f kernel_vars_s include/asm-mips64/sn/klkernvars.h +KV_MAGIC 0x5f4b565f kernel_vars_s arch/mips/include/asm/sn/klkernvars.h I810_STATE_MAGIC 0x63657373 i810_state sound/oss/i810_audio.c TRIDENT_STATE_MAGIC 0x63657373 trient_state sound/oss/trident.c M3_CARD_MAGIC 0x646e6f50 m3_card sound/oss/maestro3.c @@ -158,7 +158,7 @@ CCB_MAGIC 0xf2691ad2 ccb drivers/scsi/ncr53c8xx.c QUEUE_MAGIC_FREE 0xf7e1c9a3 queue_entry drivers/scsi/arm/queue.c QUEUE_MAGIC_USED 0xf7e1cc33 queue_entry drivers/scsi/arm/queue.c HTB_CMAGIC 0xFEFAFEF1 htb_class net/sched/sch_htb.c -NMI_MAGIC 0x48414d4d455201 nmi_s include/asm-mips64/sn/nmi.h +NMI_MAGIC 0x48414d4d455201 nmi_s arch/mips/include/asm/sn/nmi.h Note that there are also defined special per-driver magic numbers in sound memory management. See include/sound/sndmagic.h for complete list of them. Many diff --git a/Documentation/mips/AU1xxx_IDE.README b/Documentation/mips/AU1xxx_IDE.README index 25a6ed1aaa5b..f54962aea84d 100644 --- a/Documentation/mips/AU1xxx_IDE.README +++ b/Documentation/mips/AU1xxx_IDE.README @@ -44,7 +44,7 @@ FILES, CONFIGS AND COMPATABILITY Two files are introduced: - a) 'include/asm-mips/mach-au1x00/au1xxx_ide.h' + a) 'arch/mips/include/asm/mach-au1x00/au1xxx_ide.h' containes : struct _auide_hwif timing parameters for PIO mode 0/1/2/3/4 timing parameters for MWDMA 0/1/2 diff --git a/Documentation/powerpc/cpu_features.txt b/Documentation/powerpc/cpu_features.txt index 472739880e87..ffa4183fdb8b 100644 --- a/Documentation/powerpc/cpu_features.txt +++ b/Documentation/powerpc/cpu_features.txt @@ -31,7 +31,7 @@ anyways). After detecting the processor type, the kernel patches out sections of code that shouldn't be used by writing nop's over it. Using cpufeatures requires -just 2 macros (found in include/asm-ppc/cputable.h), as seen in head.S +just 2 macros (found in arch/powerpc/include/asm/cputable.h), as seen in head.S transfer_to_handler: #ifdef CONFIG_ALTIVEC diff --git a/Documentation/x86/zero-page.txt b/Documentation/x86/zero-page.txt index 169ad423a3d1..4f913857b8a2 100644 --- a/Documentation/x86/zero-page.txt +++ b/Documentation/x86/zero-page.txt @@ -3,7 +3,7 @@ protocol of kernel. These should be filled by bootloader or 16-bit real-mode setup code of the kernel. References/settings to it mainly are in: - include/asm-x86/bootparam.h + arch/x86/include/asm/bootparam.h Offset Proto Name Meaning -- cgit v1.2.3 From 58cc855c395fc22db996cc893134c4c690f0f0dc Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 6 Jan 2009 14:42:42 -0800 Subject: documentation: update s390 header file paths Update Documentation/s390/ files to reflect changed header files locations. Signed-off-by: Randy Dunlap Cc: Martin Schwidefsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/s390/Debugging390.txt | 2 +- Documentation/s390/cds.txt | 2 +- Documentation/s390/s390dbf.txt | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'Documentation') diff --git a/Documentation/s390/Debugging390.txt b/Documentation/s390/Debugging390.txt index d30a281c570f..10711d9f0788 100644 --- a/Documentation/s390/Debugging390.txt +++ b/Documentation/s390/Debugging390.txt @@ -1402,7 +1402,7 @@ Syscalls are implemented on Linux for S390 by the Supervisor call instruction (S possibilities of these as the instruction is made up of a 0xA opcode & the second byte being the syscall number. They are traced using the simple command. TR SVC -the syscalls are defined in linux/include/asm-s390/unistd.h +the syscalls are defined in linux/arch/s390/include/asm/unistd.h e.g. to trace all file opens just do TR SVC 5 ( as this is the syscall number of open ) diff --git a/Documentation/s390/cds.txt b/Documentation/s390/cds.txt index c4b7b2bd369a..480a78ef5a1e 100644 --- a/Documentation/s390/cds.txt +++ b/Documentation/s390/cds.txt @@ -98,7 +98,7 @@ platform. Some of the interface routines are specific to Linux/390 and some of them can be found on other Linux platforms implementations too. Miscellaneous function prototypes, data declarations, and macro definitions can be found in the architecture specific C header file -linux/include/asm-s390/irq.h. +linux/arch/s390/include/asm/irq.h. Overview of CDS interface concepts diff --git a/Documentation/s390/s390dbf.txt b/Documentation/s390/s390dbf.txt index e05420973698..2d10053dd97e 100644 --- a/Documentation/s390/s390dbf.txt +++ b/Documentation/s390/s390dbf.txt @@ -2,7 +2,7 @@ S390 Debug Feature ================== files: arch/s390/kernel/debug.c - include/asm-s390/debug.h + arch/s390/include/asm/debug.h Description: ------------ -- cgit v1.2.3 From 28f4d75a618e52f93d8e4a3e7bc66db8c882d679 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 6 Jan 2009 14:42:43 -0800 Subject: documentation: how to use DOC: section blocks Add info on how to use DOC: sections in kernel-doc. DOC: sections enable the addition of inline source file comments that are general in nature instead of being specific to a function, struct, union, enum, or typedef. Signed-off-by: Randy Dunlap Cc: Johannes Berg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-doc-nano-HOWTO.txt | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'Documentation') diff --git a/Documentation/kernel-doc-nano-HOWTO.txt b/Documentation/kernel-doc-nano-HOWTO.txt index 4115a4a80eb6..d73fbd2b2b45 100644 --- a/Documentation/kernel-doc-nano-HOWTO.txt +++ b/Documentation/kernel-doc-nano-HOWTO.txt @@ -287,6 +287,32 @@ struct my_struct { }; +Including documentation blocks in source files +---------------------------------------------- + +To facilitate having source code and comments close together, you can +include kernel-doc documentation blocks that are free-form comments +instead of being kernel-doc for functions, structures, unions, +enums, or typedefs. This could be used for something like a +theory of operation for a driver or library code, for example. + +This is done by using a DOC: section keyword with a section title. E.g.: + +/** + * DOC: Theory of Operation + * + * The whizbang foobar is a dilly of a gizmo. It can do whatever you + * want it to do, at any time. It reads your mind. Here's how it works. + * + * foo bar splat + * + * The only drawback to this gizmo is that is can sometimes damage + * hardware, software, or its subject(s). + */ + +DOC: sections are used in SGML templates files as indicated below. + + How to make new SGML template files ----------------------------------- @@ -307,6 +333,9 @@ exported using EXPORT_SYMBOL. !F is replaced by the documentation, in , for the functions listed. +!P
is replaced by the contents of the DOC: +section titled
from . +Spaces are allowed in
; do not quote the
. Tim. */ -- cgit v1.2.3 From 7c4be253d3a01ddc92033ec3a3812fddf703ef19 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 6 Jan 2009 14:42:44 -0800 Subject: docs: add more early params to kernel-parameters.txt Add some (more) early_param boot options to kernel-parameters.txt. Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 7f0b694e02e8..0543370e702b 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1117,6 +1117,8 @@ and is between 256 and 4096 characters. It is defined in the file If there are multiple matching configurations changing the same attribute, the last one is used. + lmb=debug [KNL] Enable lmb debug messages. + load_ramdisk= [RAM] List of ramdisks to load from floppy See Documentation/blockdev/ramdisk.txt. @@ -1569,6 +1571,10 @@ and is between 256 and 4096 characters. It is defined in the file nr_uarts= [SERIAL] maximum number of UARTs to be registered. + ohci1394_dma=early [HW] enable debugging via the ohci1394 driver. + See Documentation/debugging-via-ohci1394.txt for more + info. + olpc_ec_timeout= [OLPC] ms delay when issuing EC commands Rather than timing out after 20 ms if an EC command is not properly ACKed, override the length -- cgit v1.2.3 From ecb08d81313a3c015225236775de259d99ab47fe Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 6 Jan 2009 14:42:44 -0800 Subject: doc: reformat some long lines in kernel-parameters.txt Reformat text to (mostly) stay within 80 columns of text. Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 0543370e702b..3ccf1bc5affe 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1799,10 +1799,10 @@ and is between 256 and 4096 characters. It is defined in the file autoconfiguration. Ranges are in pairs (memory base and size). - dynamic_printk - Enables pr_debug()/dev_dbg() calls if - CONFIG_DYNAMIC_PRINTK_DEBUG has been enabled. These can also - be switched on/off via /dynamic_printk/modules + dynamic_printk Enables pr_debug()/dev_dbg() calls if + CONFIG_DYNAMIC_PRINTK_DEBUG has been enabled. + These can also be switched on/off via + /dynamic_printk/modules print-fatal-signals= [KNL] debug: print fatal signals @@ -1890,7 +1890,7 @@ and is between 256 and 4096 characters. It is defined in the file reboot= [BUGS=X86-32,BUGS=ARM,BUGS=IA-64] Rebooting mode Format: [,[,...]] - See arch/*/kernel/reboot.c or arch/*/kernel/process.c + See arch/*/kernel/reboot.c or arch/*/kernel/process.c relax_domain_level= [KNL, SMP] Set scheduler's default relax_domain_level. @@ -2438,8 +2438,8 @@ and is between 256 and 4096 characters. It is defined in the file Format: ,,,,,[,[,[,]]] - norandmaps Don't use address space randomization - Equivalent to echo 0 > /proc/sys/kernel/randomize_va_space + norandmaps Don't use address space randomization. Equivalent to + echo 0 > /proc/sys/kernel/randomize_va_space ______________________________________________________________________ -- cgit v1.2.3 From 4cb0e11b15d2badad455fcd538af0cccf05dc012 Mon Sep 17 00:00:00 2001 From: Hidehiro Kawai Date: Tue, 6 Jan 2009 14:42:47 -0800 Subject: coredump_filter: permit changing of the default filter Introduce a new kernel parameter `coredump_filter'. Setting a value to this parameter causes the default bitmask of coredump_filter to be changed. It is useful for users to change coredump_filter settings for the whole system at boot time. Without this parameter, users have to change coredump_filter settings for each /proc// in an initializing script. Signed-off-by: Hidehiro Kawai Cc: Roland McGrath Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 5 +++++ kernel/fork.c | 15 +++++++++++++-- 2 files changed, 18 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 3ccf1bc5affe..0b3f6711d2f1 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -551,6 +551,11 @@ and is between 256 and 4096 characters. It is defined in the file not work reliably with all consoles, but is known to work with serial and VGA consoles. + coredump_filter= + [KNL] Change the default value for + /proc//coredump_filter. + See also Documentation/filesystems/proc.txt. + cpcihp_generic= [HW,PCI] Generic port I/O CompactPCI driver Format: ,,,[,] diff --git a/kernel/fork.c b/kernel/fork.c index 23b912116675..7b8f2a78be3d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -400,6 +400,18 @@ __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock); #define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL)) #define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) +static unsigned long default_dump_filter = MMF_DUMP_FILTER_DEFAULT; + +static int __init coredump_filter_setup(char *s) +{ + default_dump_filter = + (simple_strtoul(s, NULL, 0) << MMF_DUMP_FILTER_SHIFT) & + MMF_DUMP_FILTER_MASK; + return 1; +} + +__setup("coredump_filter=", coredump_filter_setup); + #include static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) @@ -408,8 +420,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) atomic_set(&mm->mm_count, 1); init_rwsem(&mm->mmap_sem); INIT_LIST_HEAD(&mm->mmlist); - mm->flags = (current->mm) ? current->mm->flags - : MMF_DUMP_FILTER_DEFAULT; + mm->flags = (current->mm) ? current->mm->flags : default_dump_filter; mm->core_state = NULL; mm->nr_ptes = 0; set_mm_counter(mm, file_rss, 0); -- cgit v1.2.3 From 709ac06a148a33493d3e2f9391bb746b067d96d6 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Wed, 7 Jan 2009 09:54:24 -0500 Subject: Btrfs: Add Documentation/filesystem/btrfs.txt, remove old COPYING Signed-off-by: Chris Mason --- Documentation/filesystems/btrfs.txt | 91 +++++++++ fs/btrfs/COPYING | 356 ------------------------------------ fs/btrfs/INSTALL | 48 ----- 3 files changed, 91 insertions(+), 404 deletions(-) create mode 100644 Documentation/filesystems/btrfs.txt delete mode 100644 fs/btrfs/COPYING delete mode 100644 fs/btrfs/INSTALL (limited to 'Documentation') diff --git a/Documentation/filesystems/btrfs.txt b/Documentation/filesystems/btrfs.txt new file mode 100644 index 000000000000..64087c34327f --- /dev/null +++ b/Documentation/filesystems/btrfs.txt @@ -0,0 +1,91 @@ + + BTRFS + ===== + +Btrfs is a new copy on write filesystem for Linux aimed at +implementing advanced features while focusing on fault tolerance, +repair and easy administration. Initially developed by Oracle, Btrfs +is licensed under the GPL and open for contribution from anyone. + +Linux has a wealth of filesystems to choose from, but we are facing a +number of challenges with scaling to the large storage subsystems that +are becoming common in today's data centers. Filesystems need to scale +in their ability to address and manage large storage, and also in +their ability to detect, repair and tolerate errors in the data stored +on disk. Btrfs is under heavy development, and is not suitable for +any uses other than benchmarking and review. The Btrfs disk format is +not yet finalized. + +The main Btrfs features include: + + * Extent based file storage (2^64 max file size) + * Space efficient packing of small files + * Space efficient indexed directories + * Dynamic inode allocation + * Writable snapshots + * Subvolumes (separate internal filesystem roots) + * Object level mirroring and striping + * Checksums on data and metadata (multiple algorithms available) + * Compression + * Integrated multiple device support, with several raid algorithms + * Online filesystem check (not yet implemented) + * Very fast offline filesystem check + * Efficient incremental backup and FS mirroring (not yet implemented) + * Online filesystem defragmentation + + + + MAILING LIST + ============ + +There is a Btrfs mailing list hosted on vger.kernel.org. You can +find details on how to subscribe here: + +http://vger.kernel.org/vger-lists.html#linux-btrfs + +Mailing list archives are available from gmane: + +http://dir.gmane.org/gmane.comp.file-systems.btrfs + + + + IRC + === + +Discussion of Btrfs also occurs on the #btrfs channel of the Freenode +IRC network. + + + + UTILITIES + ========= + +Userspace tools for creating and manipulating Btrfs file systems are +available from the git repository at the following location: + + http://git.kernel.org/?p=linux/kernel/git/mason/btrfs-progs-unstable.git + git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-progs-unstable.git + +These include the following tools: + +mkfs.btrfs: create a filesystem + +btrfsctl: control program to create snapshots and subvolumes: + + mount /dev/sda2 /mnt + btrfsctl -s new_subvol_name /mnt + btrfsctl -s snapshot_of_default /mnt/default + btrfsctl -s snapshot_of_new_subvol /mnt/new_subvol_name + btrfsctl -s snapshot_of_a_snapshot /mnt/snapshot_of_new_subvol + ls /mnt + default snapshot_of_a_snapshot snapshot_of_new_subvol + new_subvol_name snapshot_of_default + + Snapshots and subvolumes cannot be deleted right now, but you can + rm -rf all the files and directories inside them. + +btrfsck: do a limited check of the FS extent trees. + +btrfs-debug-tree: print all of the FS metadata in text form. Example: + + btrfs-debug-tree /dev/sda2 >& big_output_file diff --git a/fs/btrfs/COPYING b/fs/btrfs/COPYING deleted file mode 100644 index ca442d313d86..000000000000 --- a/fs/btrfs/COPYING +++ /dev/null @@ -1,356 +0,0 @@ - - NOTE! This copyright does *not* cover user programs that use kernel - services by normal system calls - this is merely considered normal use - of the kernel, and does *not* fall under the heading of "derived work". - Also note that the GPL below is copyrighted by the Free Software - Foundation, but the instance of code that it refers to (the Linux - kernel) is copyrighted by me and others who actually wrote it. - - Also note that the only valid version of the GPL as far as the kernel - is concerned is _this_ particular version of the license (ie v2, not - v2.2 or v3.x or whatever), unless explicitly otherwise stated. - - Linus Torvalds - ----------------------------------------- - - GNU GENERAL PUBLIC LICENSE - Version 2, June 1991 - - Copyright (C) 1989, 1991 Free Software Foundation, Inc. - 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - Everyone is permitted to copy and distribute verbatim copies - of this license document, but changing it is not allowed. - - Preamble - - The licenses for most software are designed to take away your -freedom to share and change it. By contrast, the GNU General Public -License is intended to guarantee your freedom to share and change free -software--to make sure the software is free for all its users. This -General Public License applies to most of the Free Software -Foundation's software and to any other program whose authors commit to -using it. (Some other Free Software Foundation software is covered by -the GNU Library General Public License instead.) You can apply it to -your programs, too. - - When we speak of free software, we are referring to freedom, not -price. Our General Public Licenses are designed to make sure that you -have the freedom to distribute copies of free software (and charge for -this service if you wish), that you receive source code or can get it -if you want it, that you can change the software or use pieces of it -in new free programs; and that you know you can do these things. - - To protect your rights, we need to make restrictions that forbid -anyone to deny you these rights or to ask you to surrender the rights. -These restrictions translate to certain responsibilities for you if you -distribute copies of the software, or if you modify it. - - For example, if you distribute copies of such a program, whether -gratis or for a fee, you must give the recipients all the rights that -you have. You must make sure that they, too, receive or can get the -source code. And you must show them these terms so they know their -rights. - - We protect your rights with two steps: (1) copyright the software, and -(2) offer you this license which gives you legal permission to copy, -distribute and/or modify the software. - - Also, for each author's protection and ours, we want to make certain -that everyone understands that there is no warranty for this free -software. If the software is modified by someone else and passed on, we -want its recipients to know that what they have is not the original, so -that any problems introduced by others will not reflect on the original -authors' reputations. - - Finally, any free program is threatened constantly by software -patents. We wish to avoid the danger that redistributors of a free -program will individually obtain patent licenses, in effect making the -program proprietary. To prevent this, we have made it clear that any -patent must be licensed for everyone's free use or not licensed at all. - - The precise terms and conditions for copying, distribution and -modification follow. - - GNU GENERAL PUBLIC LICENSE - TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION - - 0. This License applies to any program or other work which contains -a notice placed by the copyright holder saying it may be distributed -under the terms of this General Public License. The "Program", below, -refers to any such program or work, and a "work based on the Program" -means either the Program or any derivative work under copyright law: -that is to say, a work containing the Program or a portion of it, -either verbatim or with modifications and/or translated into another -language. (Hereinafter, translation is included without limitation in -the term "modification".) Each licensee is addressed as "you". - -Activities other than copying, distribution and modification are not -covered by this License; they are outside its scope. The act of -running the Program is not restricted, and the output from the Program -is covered only if its contents constitute a work based on the -Program (independent of having been made by running the Program). -Whether that is true depends on what the Program does. - - 1. You may copy and distribute verbatim copies of the Program's -source code as you receive it, in any medium, provided that you -conspicuously and appropriately publish on each copy an appropriate -copyright notice and disclaimer of warranty; keep intact all the -notices that refer to this License and to the absence of any warranty; -and give any other recipients of the Program a copy of this License -along with the Program. - -You may charge a fee for the physical act of transferring a copy, and -you may at your option offer warranty protection in exchange for a fee. - - 2. You may modify your copy or copies of the Program or any portion -of it, thus forming a work based on the Program, and copy and -distribute such modifications or work under the terms of Section 1 -above, provided that you also meet all of these conditions: - - a) You must cause the modified files to carry prominent notices - stating that you changed the files and the date of any change. - - b) You must cause any work that you distribute or publish, that in - whole or in part contains or is derived from the Program or any - part thereof, to be licensed as a whole at no charge to all third - parties under the terms of this License. - - c) If the modified program normally reads commands interactively - when run, you must cause it, when started running for such - interactive use in the most ordinary way, to print or display an - announcement including an appropriate copyright notice and a - notice that there is no warranty (or else, saying that you provide - a warranty) and that users may redistribute the program under - these conditions, and telling the user how to view a copy of this - License. (Exception: if the Program itself is interactive but - does not normally print such an announcement, your work based on - the Program is not required to print an announcement.) - -These requirements apply to the modified work as a whole. If -identifiable sections of that work are not derived from the Program, -and can be reasonably considered independent and separate works in -themselves, then this License, and its terms, do not apply to those -sections when you distribute them as separate works. But when you -distribute the same sections as part of a whole which is a work based -on the Program, the distribution of the whole must be on the terms of -this License, whose permissions for other licensees extend to the -entire whole, and thus to each and every part regardless of who wrote it. - -Thus, it is not the intent of this section to claim rights or contest -your rights to work written entirely by you; rather, the intent is to -exercise the right to control the distribution of derivative or -collective works based on the Program. - -In addition, mere aggregation of another work not based on the Program -with the Program (or with a work based on the Program) on a volume of -a storage or distribution medium does not bring the other work under -the scope of this License. - - 3. You may copy and distribute the Program (or a work based on it, -under Section 2) in object code or executable form under the terms of -Sections 1 and 2 above provided that you also do one of the following: - - a) Accompany it with the complete corresponding machine-readable - source code, which must be distributed under the terms of Sections - 1 and 2 above on a medium customarily used for software interchange; or, - - b) Accompany it with a written offer, valid for at least three - years, to give any third party, for a charge no more than your - cost of physically performing source distribution, a complete - machine-readable copy of the corresponding source code, to be - distributed under the terms of Sections 1 and 2 above on a medium - customarily used for software interchange; or, - - c) Accompany it with the information you received as to the offer - to distribute corresponding source code. (This alternative is - allowed only for noncommercial distribution and only if you - received the program in object code or executable form with such - an offer, in accord with Subsection b above.) - -The source code for a work means the preferred form of the work for -making modifications to it. For an executable work, complete source -code means all the source code for all modules it contains, plus any -associated interface definition files, plus the scripts used to -control compilation and installation of the executable. However, as a -special exception, the source code distributed need not include -anything that is normally distributed (in either source or binary -form) with the major components (compiler, kernel, and so on) of the -operating system on which the executable runs, unless that component -itself accompanies the executable. - -If distribution of executable or object code is made by offering -access to copy from a designated place, then offering equivalent -access to copy the source code from the same place counts as -distribution of the source code, even though third parties are not -compelled to copy the source along with the object code. - - 4. You may not copy, modify, sublicense, or distribute the Program -except as expressly provided under this License. Any attempt -otherwise to copy, modify, sublicense or distribute the Program is -void, and will automatically terminate your rights under this License. -However, parties who have received copies, or rights, from you under -this License will not have their licenses terminated so long as such -parties remain in full compliance. - - 5. You are not required to accept this License, since you have not -signed it. However, nothing else grants you permission to modify or -distribute the Program or its derivative works. These actions are -prohibited by law if you do not accept this License. Therefore, by -modifying or distributing the Program (or any work based on the -Program), you indicate your acceptance of this License to do so, and -all its terms and conditions for copying, distributing or modifying -the Program or works based on it. - - 6. Each time you redistribute the Program (or any work based on the -Program), the recipient automatically receives a license from the -original licensor to copy, distribute or modify the Program subject to -these terms and conditions. You may not impose any further -restrictions on the recipients' exercise of the rights granted herein. -You are not responsible for enforcing compliance by third parties to -this License. - - 7. If, as a consequence of a court judgment or allegation of patent -infringement or for any other reason (not limited to patent issues), -conditions are imposed on you (whether by court order, agreement or -otherwise) that contradict the conditions of this License, they do not -excuse you from the conditions of this License. If you cannot -distribute so as to satisfy simultaneously your obligations under this -License and any other pertinent obligations, then as a consequence you -may not distribute the Program at all. For example, if a patent -license would not permit royalty-free redistribution of the Program by -all those who receive copies directly or indirectly through you, then -the only way you could satisfy both it and this License would be to -refrain entirely from distribution of the Program. - -If any portion of this section is held invalid or unenforceable under -any particular circumstance, the balance of the section is intended to -apply and the section as a whole is intended to apply in other -circumstances. - -It is not the purpose of this section to induce you to infringe any -patents or other property right claims or to contest validity of any -such claims; this section has the sole purpose of protecting the -integrity of the free software distribution system, which is -implemented by public license practices. Many people have made -generous contributions to the wide range of software distributed -through that system in reliance on consistent application of that -system; it is up to the author/donor to decide if he or she is willing -to distribute software through any other system and a licensee cannot -impose that choice. - -This section is intended to make thoroughly clear what is believed to -be a consequence of the rest of this License. - - 8. If the distribution and/or use of the Program is restricted in -certain countries either by patents or by copyrighted interfaces, the -original copyright holder who places the Program under this License -may add an explicit geographical distribution limitation excluding -those countries, so that distribution is permitted only in or among -countries not thus excluded. In such case, this License incorporates -the limitation as if written in the body of this License. - - 9. The Free Software Foundation may publish revised and/or new versions -of the General Public License from time to time. Such new versions will -be similar in spirit to the present version, but may differ in detail to -address new problems or concerns. - -Each version is given a distinguishing version number. If the Program -specifies a version number of this License which applies to it and "any -later version", you have the option of following the terms and conditions -either of that version or of any later version published by the Free -Software Foundation. If the Program does not specify a version number of -this License, you may choose any version ever published by the Free Software -Foundation. - - 10. If you wish to incorporate parts of the Program into other free -programs whose distribution conditions are different, write to the author -to ask for permission. For software which is copyrighted by the Free -Software Foundation, write to the Free Software Foundation; we sometimes -make exceptions for this. Our decision will be guided by the two goals -of preserving the free status of all derivatives of our free software and -of promoting the sharing and reuse of software generally. - - NO WARRANTY - - 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY -FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN -OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES -PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED -OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF -MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS -TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE -PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, -REPAIR OR CORRECTION. - - 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING -WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR -REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, -INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING -OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED -TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY -YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER -PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE -POSSIBILITY OF SUCH DAMAGES. - - END OF TERMS AND CONDITIONS - - How to Apply These Terms to Your New Programs - - If you develop a new program, and you want it to be of the greatest -possible use to the public, the best way to achieve this is to make it -free software which everyone can redistribute and change under these terms. - - To do so, attach the following notices to the program. It is safest -to attach them to the start of each source file to most effectively -convey the exclusion of warranty; and each file should have at least -the "copyright" line and a pointer to where the full notice is found. - - - Copyright (C) - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - - -Also add information on how to contact you by electronic and paper mail. - -If the program is interactive, make it output a short notice like this -when it starts in an interactive mode: - - Gnomovision version 69, Copyright (C) year name of author - Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. - This is free software, and you are welcome to redistribute it - under certain conditions; type `show c' for details. - -The hypothetical commands `show w' and `show c' should show the appropriate -parts of the General Public License. Of course, the commands you use may -be called something other than `show w' and `show c'; they could even be -mouse-clicks or menu items--whatever suits your program. - -You should also get your employer (if you work as a programmer) or your -school, if any, to sign a "copyright disclaimer" for the program, if -necessary. Here is a sample; alter the names: - - Yoyodyne, Inc., hereby disclaims all copyright interest in the program - `Gnomovision' (which makes passes at compilers) written by James Hacker. - - , 1 April 1989 - Ty Coon, President of Vice - -This General Public License does not permit incorporating your program into -proprietary programs. If your program is a subroutine library, you may -consider it more useful to permit linking proprietary applications with the -library. If this is what you want to do, use the GNU Library General -Public License instead of this License. diff --git a/fs/btrfs/INSTALL b/fs/btrfs/INSTALL deleted file mode 100644 index 16b45a56878d..000000000000 --- a/fs/btrfs/INSTALL +++ /dev/null @@ -1,48 +0,0 @@ -Install Instructions - -Btrfs puts snapshots and subvolumes into the root directory of the FS. This -directory can only be changed by btrfsctl right now, and normal filesystem -operations do not work on it. The default subvolume is called 'default', -and you can create files and directories in mount_point/default - -Btrfs uses libcrc32c in the kernel for file and metadata checksums. You need -to compile the kernel with: - -CONFIG_LIBCRC32C=m - -libcrc32c can be static as well. Once your kernel is setup, typing make in the -btrfs module sources will build against the running kernel. When the build is -complete: - -modprobe libcrc32c -insmod btrfs.ko - -The Btrfs utility programs require libuuid to build. This can be found -in the e2fsprogs sources, and is usually available as libuuid or -e2fsprogs-devel from various distros. - -Building the utilities is just make ; make install. The programs go -into /usr/local/bin. The commands available are: - -mkfs.btrfs: create a filesystem - -btrfsctl: control program to create snapshots and subvolumes: - - mount /dev/sda2 /mnt - btrfsctl -s new_subvol_name /mnt - btrfsctl -s snapshot_of_default /mnt/default - btrfsctl -s snapshot_of_new_subvol /mnt/new_subvol_name - btrfsctl -s snapshot_of_a_snapshot /mnt/snapshot_of_new_subvol - ls /mnt - default snapshot_of_a_snapshot snapshot_of_new_subvol - new_subvol_name snapshot_of_default - - Snapshots and subvolumes cannot be deleted right now, but you can - rm -rf all the files and directories inside them. - -btrfsck: do a limited check of the FS extent trees. - -debug-tree: print all of the FS metadata in text form. Example: - - debug-tree /dev/sda2 >& big_output_file - -- cgit v1.2.3 From 5e6d9f511e0188d34fa7a93ce2d0e6194442b0da Mon Sep 17 00:00:00 2001 From: Graf Yang Date: Wed, 7 Jan 2009 23:14:38 +0800 Subject: Blackfin arch: Add document about bfin-gpio Add document about bfin-gpio when requesting a pin both as gpio and gpio interrupt. Signed-off-by: Graf Yang Signed-off-by: Bryan Wu --- Documentation/blackfin/00-INDEX | 3 ++ Documentation/blackfin/bfin-gpio-notes.txt | 71 ++++++++++++++++++++++++++++++ 2 files changed, 74 insertions(+) create mode 100644 Documentation/blackfin/bfin-gpio-notes.txt (limited to 'Documentation') diff --git a/Documentation/blackfin/00-INDEX b/Documentation/blackfin/00-INDEX index 7cb3b356b249..d6840a91e1e1 100644 --- a/Documentation/blackfin/00-INDEX +++ b/Documentation/blackfin/00-INDEX @@ -9,3 +9,6 @@ cachefeatures.txt Filesystems - Requirements for mounting the root file system. + +bfin-gpio-note.txt + - Notes in developing/using bfin-gpio driver. diff --git a/Documentation/blackfin/bfin-gpio-notes.txt b/Documentation/blackfin/bfin-gpio-notes.txt new file mode 100644 index 000000000000..9898c7ded7d3 --- /dev/null +++ b/Documentation/blackfin/bfin-gpio-notes.txt @@ -0,0 +1,71 @@ +/* + * File: Documentation/blackfin/bfin-gpio-note.txt + * Based on: + * Author: + * + * Created: $Id: bfin-gpio-note.txt 2008-11-24 16:42 grafyang $ + * Description: This file contains the notes in developing/using bfin-gpio. + * + * + * Rev: + * + * Modified: + * Copyright 2004-2008 Analog Devices Inc. + * + * Bugs: Enter bugs at http://blackfin.uclinux.org/ + * + */ + + +1. Blackfin GPIO introduction + + There are many GPIO pins on Blackfin. Most of these pins are muxed to + multi-functions. They can be configured as peripheral, or just as GPIO, + configured to input with interrupt enabled, or output. + + For detailed information, please see "arch/blackfin/kernel/bfin_gpio.c", + or the relevant HRM. + + +2. Avoiding resource conflict + + Followed function groups are used to avoiding resource conflict, + - Use the pin as peripheral, + int peripheral_request(unsigned short per, const char *label); + int peripheral_request_list(const unsigned short per[], const char *label); + void peripheral_free(unsigned short per); + void peripheral_free_list(const unsigned short per[]); + - Use the pin as GPIO, + int bfin_gpio_request(unsigned gpio, const char *label); + void bfin_gpio_free(unsigned gpio); + - Use the pin as GPIO interrupt, + int bfin_gpio_irq_request(unsigned gpio, const char *label); + void bfin_gpio_irq_free(unsigned gpio); + + The request functions will record the function state for a certain pin, + the free functions will clear it's function state. + Once a pin is requested, it can't be requested again before it is freed by + previous caller, otherwise kernel will dump stacks, and the request + function fail. + These functions are wrapped by other functions, most of the users need not + care. + + +3. But there are some exceptions + - Kernel permit the identical GPIO be requested both as GPIO and GPIO + interrut. + Some drivers, like gpio-keys, need this behavior. Kernel only print out + warning messages like, + bfin-gpio: GPIO 24 is already reserved by gpio-keys: BTN0, and you are +configuring it as IRQ! + + Note: Consider the case that, if there are two drivers need the + identical GPIO, one of them use it as GPIO, the other use it as + GPIO interrupt. This will really cause resource conflict. So if + there is any abnormal driver behavior, please check the bfin-gpio + warning messages. + + - Kernel permit the identical GPIO be requested from the same driver twice. + + + -- cgit v1.2.3 From 3b02d332b6f15cc8f7b6a04757c86034669600e0 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 7 Jan 2009 16:37:31 +0100 Subject: hwmon: (f71882fg) Add documentation Add some documentation about the f71882fg driver, and update the Kconfig documentation to report the new supported models. Signed-off-by: Hans de Goede Signed-off-by: Jean Delvare --- Documentation/hwmon/f71882fg | 89 ++++++++++++++++++++++++++++++++++++++++++++ drivers/hwmon/Kconfig | 5 ++- 2 files changed, 92 insertions(+), 2 deletions(-) create mode 100644 Documentation/hwmon/f71882fg (limited to 'Documentation') diff --git a/Documentation/hwmon/f71882fg b/Documentation/hwmon/f71882fg new file mode 100644 index 000000000000..a8321267b5b6 --- /dev/null +++ b/Documentation/hwmon/f71882fg @@ -0,0 +1,89 @@ +Kernel driver f71882fg +====================== + +Supported chips: + * Fintek F71882FG and F71883FG + Prefix: 'f71882fg' + Addresses scanned: none, address read from Super I/O config space + Datasheet: Available from the Fintek website + * Fintek F71862FG and F71863FG + Prefix: 'f71862fg' + Addresses scanned: none, address read from Super I/O config space + Datasheet: Available from the Fintek website + * Fintek F8000 + Prefix: 'f8000' + Addresses scanned: none, address read from Super I/O config space + Datasheet: Not public + +Author: Hans de Goede + + +Description +----------- + +Fintek F718xxFG/F8000 Super I/O chips include complete hardware monitoring +capabilities. They can monitor up to 9 voltages (3 for the F8000), 4 fans and +3 temperature sensors. + +These chips also have fan controlling features, using either DC or PWM, in +three different modes (one manual, two automatic). + +The driver assumes that no more than one chip is present, which seems +reasonable. + + +Monitoring +---------- + +The Voltage, Fan and Temperature Monitoring uses the standard sysfs +interface as documented in sysfs-interface, without any exceptions. + + +Fan Control +----------- + +Both PWM (pulse-width modulation) and DC fan speed control methods are +supported. The right one to use depends on external circuitry on the +motherboard, so the driver assumes that the BIOS set the method +properly. + +There are 2 modes to specify the speed of the fan, PWM duty cycle (or DC +voltage) mode, where 0-100% duty cycle (0-100% of 12V) is specified. And RPM +mode where the actual RPM of the fan (as measured) is controlled and the speed +gets specified as 0-100% of the fan#_full_speed file. + +Since both modes work in a 0-100% (mapped to 0-255) scale, there isn't a +whole lot of a difference when modifying fan control settings. The only +important difference is that in RPM mode the 0-100% controls the fan speed +between 0-100% of fan#_full_speed. It is assumed that if the BIOS programs +RPM mode, it will also set fan#_full_speed properly, if it does not then +fan control will not work properly, unless you set a sane fan#_full_speed +value yourself. + +Switching between these modes requires re-initializing a whole bunch of +registers, so the mode which the BIOS has set is kept. The mode is +printed when loading the driver. + +Three different fan control modes are supported; the mode number is written +to the pwm#_enable file. Note that not all modes are supported on all +chips, and some modes may only be available in RPM / PWM mode on the F8000. +Writing an unsupported mode will result in an invalid parameter error. + +* 1: Manual mode + You ask for a specific PWM duty cycle / DC voltage or a specific % of + fan#_full_speed by writing to the pwm# file. This mode is only + available on the F8000 if the fan channel is in RPM mode. + +* 2: Normal auto mode + You can define a number of temperature/fan speed trip points, which % the + fan should run at at this temp and which temp a fan should follow using the + standard sysfs interface. The number and type of trip points is chip + depended, see which files are available in sysfs. + Fan/PWM channel 3 of the F8000 is always in this mode! + +* 3: Thermostat mode (Only available on the F8000 when in duty cycle mode) + The fan speed is regulated to keep the temp the fan is mapped to between + temp#_auto_point2_temp and temp#_auto_point3_temp. + +Both of the automatic modes require that pwm1 corresponds to fan1, pwm2 to +fan2 and pwm3 to fan3. diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index c709e821f04b..cc611e4b7896 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -284,11 +284,12 @@ config SENSORS_F71805F will be called f71805f. config SENSORS_F71882FG - tristate "Fintek F71882FG and F71883FG" + tristate "Fintek F71862FG, F71882FG and F8000" depends on EXPERIMENTAL help If you say yes here you get support for hardware monitoring - features of the Fintek F71882FG and F71883FG Super-I/O chips. + features of the Fintek F71882FG/F71883FG, F71862FG/71863FG + and F8000 Super-I/O chips. This driver can also be built as a module. If so, the module will be called f71882fg. -- cgit v1.2.3 From 6e34b187bc216fc632769fb8b906d3a29ccd8f14 Mon Sep 17 00:00:00 2001 From: Ira Snyder Date: Wed, 7 Jan 2009 16:37:32 +0100 Subject: hwmon: Add LTC4245 driver Add Linux support for the Linear Technology LTC4245 Multiple Supply Hot Swap controller I2C monitoring interface. Signed-off-by: Ira W. Snyder Acked-by: Hans de Goede Signed-off-by: Jean Delvare --- Documentation/hwmon/ltc4245 | 81 +++++++ drivers/hwmon/Kconfig | 11 + drivers/hwmon/Makefile | 1 + drivers/hwmon/ltc4245.c | 567 ++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 660 insertions(+) create mode 100644 Documentation/hwmon/ltc4245 create mode 100644 drivers/hwmon/ltc4245.c (limited to 'Documentation') diff --git a/Documentation/hwmon/ltc4245 b/Documentation/hwmon/ltc4245 new file mode 100644 index 000000000000..bae7a3adc5d8 --- /dev/null +++ b/Documentation/hwmon/ltc4245 @@ -0,0 +1,81 @@ +Kernel driver ltc4245 +===================== + +Supported chips: + * Linear Technology LTC4245 + Prefix: 'ltc4245' + Addresses scanned: 0x20-0x3f + Datasheet: + http://www.linear.com/pc/downloadDocument.do?navId=H0,C1,C1003,C1006,C1140,P19392,D13517 + +Author: Ira W. Snyder + + +Description +----------- + +The LTC4245 controller allows a board to be safely inserted and removed +from a live backplane in multiple supply systems such as CompactPCI and +PCI Express. + + +Usage Notes +----------- + +This driver does not probe for LTC4245 devices, due to the fact that some +of the possible addresses are unfriendly to probing. You will need to use +the "force" parameter to tell the driver where to find the device. + +Example: the following will load the driver for an LTC4245 at address 0x23 +on I2C bus #1: +$ modprobe ltc4245 force=1,0x23 + + +Sysfs entries +------------- + +The LTC4245 has built-in limits for over and under current warnings. This +makes it very likely that the reference circuit will be used. + +This driver uses the values in the datasheet to change the register values +into the values specified in the sysfs-interface document. The current readings +rely on the sense resistors listed in Table 2: "Sense Resistor Values". + +in1_input 12v input voltage (mV) +in2_input 5v input voltage (mV) +in3_input 3v input voltage (mV) +in4_input Vee (-12v) input voltage (mV) + +in1_min_alarm 12v input undervoltage alarm +in2_min_alarm 5v input undervoltage alarm +in3_min_alarm 3v input undervoltage alarm +in4_min_alarm Vee (-12v) input undervoltage alarm + +curr1_input 12v current (mA) +curr2_input 5v current (mA) +curr3_input 3v current (mA) +curr4_input Vee (-12v) current (mA) + +curr1_max_alarm 12v overcurrent alarm +curr2_max_alarm 5v overcurrent alarm +curr3_max_alarm 3v overcurrent alarm +curr4_max_alarm Vee (-12v) overcurrent alarm + +in5_input 12v output voltage (mV) +in6_input 5v output voltage (mV) +in7_input 3v output voltage (mV) +in8_input Vee (-12v) output voltage (mV) + +in5_min_alarm 12v output undervoltage alarm +in6_min_alarm 5v output undervoltage alarm +in7_min_alarm 3v output undervoltage alarm +in8_min_alarm Vee (-12v) output undervoltage alarm + +in9_input GPIO #1 voltage data +in10_input GPIO #2 voltage data +in11_input GPIO #3 voltage data + +power1_input 12v power usage (mW) +power2_input 5v power usage (mW) +power3_input 3v power usage (mW) +power4_input Vee (-12v) power usage (mW) diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index cc611e4b7896..1ef1205b4e8c 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -549,6 +549,17 @@ config SENSORS_LM93 This driver can also be built as a module. If so, the module will be called lm93. +config SENSORS_LTC4245 + tristate "Linear Technology LTC4245" + depends on I2C && EXPERIMENTAL + default n + help + If you say yes here you get support for Linear Technology LTC4245 + Multiple Supply Hot Swap Controller I2C interface. + + This driver can also be built as a module. If so, the module will + be called ltc4245. + config SENSORS_MAX1111 tristate "Maxim MAX1111 Multichannel, Serial 8-bit ADC chip" depends on SPI_MASTER diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile index 58fc5be5355d..8fd124eff646 100644 --- a/drivers/hwmon/Makefile +++ b/drivers/hwmon/Makefile @@ -62,6 +62,7 @@ obj-$(CONFIG_SENSORS_LM87) += lm87.o obj-$(CONFIG_SENSORS_LM90) += lm90.o obj-$(CONFIG_SENSORS_LM92) += lm92.o obj-$(CONFIG_SENSORS_LM93) += lm93.o +obj-$(CONFIG_SENSORS_LTC4245) += ltc4245.o obj-$(CONFIG_SENSORS_MAX1111) += max1111.o obj-$(CONFIG_SENSORS_MAX1619) += max1619.o obj-$(CONFIG_SENSORS_MAX6650) += max6650.o diff --git a/drivers/hwmon/ltc4245.c b/drivers/hwmon/ltc4245.c new file mode 100644 index 000000000000..034b2c515848 --- /dev/null +++ b/drivers/hwmon/ltc4245.c @@ -0,0 +1,567 @@ +/* + * Driver for Linear Technology LTC4245 I2C Multiple Supply Hot Swap Controller + * + * Copyright (C) 2008 Ira W. Snyder + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * This driver is based on the ds1621 and ina209 drivers. + * + * Datasheet: + * http://www.linear.com/pc/downloadDocument.do?navId=H0,C1,C1003,C1006,C1140,P19392,D13517 + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +/* Valid addresses are 0x20 - 0x3f + * + * For now, we do not probe, since some of these addresses + * are known to be unfriendly to probing */ +static const unsigned short normal_i2c[] = { I2C_CLIENT_END }; + +/* Insmod parameters */ +I2C_CLIENT_INSMOD_1(ltc4245); + +/* Here are names of the chip's registers (a.k.a. commands) */ +enum ltc4245_cmd { + LTC4245_STATUS = 0x00, /* readonly */ + LTC4245_ALERT = 0x01, + LTC4245_CONTROL = 0x02, + LTC4245_ON = 0x03, + LTC4245_FAULT1 = 0x04, + LTC4245_FAULT2 = 0x05, + LTC4245_GPIO = 0x06, + LTC4245_ADCADR = 0x07, + + LTC4245_12VIN = 0x10, + LTC4245_12VSENSE = 0x11, + LTC4245_12VOUT = 0x12, + LTC4245_5VIN = 0x13, + LTC4245_5VSENSE = 0x14, + LTC4245_5VOUT = 0x15, + LTC4245_3VIN = 0x16, + LTC4245_3VSENSE = 0x17, + LTC4245_3VOUT = 0x18, + LTC4245_VEEIN = 0x19, + LTC4245_VEESENSE = 0x1a, + LTC4245_VEEOUT = 0x1b, + LTC4245_GPIOADC1 = 0x1c, + LTC4245_GPIOADC2 = 0x1d, + LTC4245_GPIOADC3 = 0x1e, +}; + +struct ltc4245_data { + struct device *hwmon_dev; + + struct mutex update_lock; + bool valid; + unsigned long last_updated; /* in jiffies */ + + /* Control registers */ + u8 cregs[0x08]; + + /* Voltage registers */ + u8 vregs[0x0f]; +}; + +static struct ltc4245_data *ltc4245_update_device(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + struct ltc4245_data *data = i2c_get_clientdata(client); + s32 val; + int i; + + mutex_lock(&data->update_lock); + + if (time_after(jiffies, data->last_updated + HZ) || !data->valid) { + + dev_dbg(&client->dev, "Starting ltc4245 update\n"); + + /* Read control registers -- 0x00 to 0x07 */ + for (i = 0; i < ARRAY_SIZE(data->cregs); i++) { + val = i2c_smbus_read_byte_data(client, i); + if (unlikely(val < 0)) + data->cregs[i] = 0; + else + data->cregs[i] = val; + } + + /* Read voltage registers -- 0x10 to 0x1f */ + for (i = 0; i < ARRAY_SIZE(data->vregs); i++) { + val = i2c_smbus_read_byte_data(client, i+0x10); + if (unlikely(val < 0)) + data->vregs[i] = 0; + else + data->vregs[i] = val; + } + + data->last_updated = jiffies; + data->valid = 1; + } + + mutex_unlock(&data->update_lock); + + return data; +} + +/* Return the voltage from the given register in millivolts */ +static int ltc4245_get_voltage(struct device *dev, u8 reg) +{ + struct ltc4245_data *data = ltc4245_update_device(dev); + const u8 regval = data->vregs[reg - 0x10]; + u32 voltage = 0; + + switch (reg) { + case LTC4245_12VIN: + case LTC4245_12VOUT: + voltage = regval * 55; + break; + case LTC4245_5VIN: + case LTC4245_5VOUT: + voltage = regval * 22; + break; + case LTC4245_3VIN: + case LTC4245_3VOUT: + voltage = regval * 15; + break; + case LTC4245_VEEIN: + case LTC4245_VEEOUT: + voltage = regval * -55; + break; + case LTC4245_GPIOADC1: + case LTC4245_GPIOADC2: + case LTC4245_GPIOADC3: + voltage = regval * 10; + break; + default: + /* If we get here, the developer messed up */ + WARN_ON_ONCE(1); + break; + } + + return voltage; +} + +/* Return the current in the given sense register in milliAmperes */ +static unsigned int ltc4245_get_current(struct device *dev, u8 reg) +{ + struct ltc4245_data *data = ltc4245_update_device(dev); + const u8 regval = data->vregs[reg - 0x10]; + unsigned int voltage; + unsigned int curr; + + /* The strange looking conversions that follow are fixed-point + * math, since we cannot do floating point in the kernel. + * + * Step 1: convert sense register to microVolts + * Step 2: convert voltage to milliAmperes + * + * If you play around with the V=IR equation, you come up with + * the following: X uV / Y mOhm == Z mA + * + * With the resistors that are fractions of a milliOhm, we multiply + * the voltage and resistance by 10, to shift the decimal point. + * Now we can use the normal division operator again. + */ + + switch (reg) { + case LTC4245_12VSENSE: + voltage = regval * 250; /* voltage in uV */ + curr = voltage / 50; /* sense resistor 50 mOhm */ + break; + case LTC4245_5VSENSE: + voltage = regval * 125; /* voltage in uV */ + curr = (voltage * 10) / 35; /* sense resistor 3.5 mOhm */ + break; + case LTC4245_3VSENSE: + voltage = regval * 125; /* voltage in uV */ + curr = (voltage * 10) / 25; /* sense resistor 2.5 mOhm */ + break; + case LTC4245_VEESENSE: + voltage = regval * 250; /* voltage in uV */ + curr = voltage / 100; /* sense resistor 100 mOhm */ + break; + default: + /* If we get here, the developer messed up */ + WARN_ON_ONCE(1); + curr = 0; + break; + } + + return curr; +} + +static ssize_t ltc4245_show_voltage(struct device *dev, + struct device_attribute *da, + char *buf) +{ + struct sensor_device_attribute *attr = to_sensor_dev_attr(da); + const int voltage = ltc4245_get_voltage(dev, attr->index); + + return snprintf(buf, PAGE_SIZE, "%d\n", voltage); +} + +static ssize_t ltc4245_show_current(struct device *dev, + struct device_attribute *da, + char *buf) +{ + struct sensor_device_attribute *attr = to_sensor_dev_attr(da); + const unsigned int curr = ltc4245_get_current(dev, attr->index); + + return snprintf(buf, PAGE_SIZE, "%u\n", curr); +} + +static ssize_t ltc4245_show_power(struct device *dev, + struct device_attribute *da, + char *buf) +{ + struct sensor_device_attribute *attr = to_sensor_dev_attr(da); + const unsigned int curr = ltc4245_get_current(dev, attr->index); + const int output_voltage = ltc4245_get_voltage(dev, attr->index+1); + + /* current in mA * voltage in mV == power in uW */ + const unsigned int power = abs(output_voltage * curr); + + return snprintf(buf, PAGE_SIZE, "%u\n", power); +} + +static ssize_t ltc4245_show_alarm(struct device *dev, + struct device_attribute *da, + char *buf) +{ + struct sensor_device_attribute_2 *attr = to_sensor_dev_attr_2(da); + struct ltc4245_data *data = ltc4245_update_device(dev); + const u8 reg = data->cregs[attr->index]; + const u32 mask = attr->nr; + + return snprintf(buf, PAGE_SIZE, "%u\n", (reg & mask) ? 1 : 0); +} + +/* These macros are used below in constructing device attribute objects + * for use with sysfs_create_group() to make a sysfs device file + * for each register. + */ + +#define LTC4245_VOLTAGE(name, ltc4245_cmd_idx) \ + static SENSOR_DEVICE_ATTR(name, S_IRUGO, \ + ltc4245_show_voltage, NULL, ltc4245_cmd_idx) + +#define LTC4245_CURRENT(name, ltc4245_cmd_idx) \ + static SENSOR_DEVICE_ATTR(name, S_IRUGO, \ + ltc4245_show_current, NULL, ltc4245_cmd_idx) + +#define LTC4245_POWER(name, ltc4245_cmd_idx) \ + static SENSOR_DEVICE_ATTR(name, S_IRUGO, \ + ltc4245_show_power, NULL, ltc4245_cmd_idx) + +#define LTC4245_ALARM(name, mask, reg) \ + static SENSOR_DEVICE_ATTR_2(name, S_IRUGO, \ + ltc4245_show_alarm, NULL, (mask), reg) + +/* Construct a sensor_device_attribute structure for each register */ + +/* Input voltages */ +LTC4245_VOLTAGE(in1_input, LTC4245_12VIN); +LTC4245_VOLTAGE(in2_input, LTC4245_5VIN); +LTC4245_VOLTAGE(in3_input, LTC4245_3VIN); +LTC4245_VOLTAGE(in4_input, LTC4245_VEEIN); + +/* Input undervoltage alarms */ +LTC4245_ALARM(in1_min_alarm, (1 << 0), LTC4245_FAULT1); +LTC4245_ALARM(in2_min_alarm, (1 << 1), LTC4245_FAULT1); +LTC4245_ALARM(in3_min_alarm, (1 << 2), LTC4245_FAULT1); +LTC4245_ALARM(in4_min_alarm, (1 << 3), LTC4245_FAULT1); + +/* Currents (via sense resistor) */ +LTC4245_CURRENT(curr1_input, LTC4245_12VSENSE); +LTC4245_CURRENT(curr2_input, LTC4245_5VSENSE); +LTC4245_CURRENT(curr3_input, LTC4245_3VSENSE); +LTC4245_CURRENT(curr4_input, LTC4245_VEESENSE); + +/* Overcurrent alarms */ +LTC4245_ALARM(curr1_max_alarm, (1 << 4), LTC4245_FAULT1); +LTC4245_ALARM(curr2_max_alarm, (1 << 5), LTC4245_FAULT1); +LTC4245_ALARM(curr3_max_alarm, (1 << 6), LTC4245_FAULT1); +LTC4245_ALARM(curr4_max_alarm, (1 << 7), LTC4245_FAULT1); + +/* Output voltages */ +LTC4245_VOLTAGE(in5_input, LTC4245_12VOUT); +LTC4245_VOLTAGE(in6_input, LTC4245_5VOUT); +LTC4245_VOLTAGE(in7_input, LTC4245_3VOUT); +LTC4245_VOLTAGE(in8_input, LTC4245_VEEOUT); + +/* Power Bad alarms */ +LTC4245_ALARM(in5_min_alarm, (1 << 0), LTC4245_FAULT2); +LTC4245_ALARM(in6_min_alarm, (1 << 1), LTC4245_FAULT2); +LTC4245_ALARM(in7_min_alarm, (1 << 2), LTC4245_FAULT2); +LTC4245_ALARM(in8_min_alarm, (1 << 3), LTC4245_FAULT2); + +/* GPIO voltages */ +LTC4245_VOLTAGE(in9_input, LTC4245_GPIOADC1); +LTC4245_VOLTAGE(in10_input, LTC4245_GPIOADC2); +LTC4245_VOLTAGE(in11_input, LTC4245_GPIOADC3); + +/* Power Consumption (virtual) */ +LTC4245_POWER(power1_input, LTC4245_12VSENSE); +LTC4245_POWER(power2_input, LTC4245_5VSENSE); +LTC4245_POWER(power3_input, LTC4245_3VSENSE); +LTC4245_POWER(power4_input, LTC4245_VEESENSE); + +/* Finally, construct an array of pointers to members of the above objects, + * as required for sysfs_create_group() + */ +static struct attribute *ltc4245_attributes[] = { + &sensor_dev_attr_in1_input.dev_attr.attr, + &sensor_dev_attr_in2_input.dev_attr.attr, + &sensor_dev_attr_in3_input.dev_attr.attr, + &sensor_dev_attr_in4_input.dev_attr.attr, + + &sensor_dev_attr_in1_min_alarm.dev_attr.attr, + &sensor_dev_attr_in2_min_alarm.dev_attr.attr, + &sensor_dev_attr_in3_min_alarm.dev_attr.attr, + &sensor_dev_attr_in4_min_alarm.dev_attr.attr, + + &sensor_dev_attr_curr1_input.dev_attr.attr, + &sensor_dev_attr_curr2_input.dev_attr.attr, + &sensor_dev_attr_curr3_input.dev_attr.attr, + &sensor_dev_attr_curr4_input.dev_attr.attr, + + &sensor_dev_attr_curr1_max_alarm.dev_attr.attr, + &sensor_dev_attr_curr2_max_alarm.dev_attr.attr, + &sensor_dev_attr_curr3_max_alarm.dev_attr.attr, + &sensor_dev_attr_curr4_max_alarm.dev_attr.attr, + + &sensor_dev_attr_in5_input.dev_attr.attr, + &sensor_dev_attr_in6_input.dev_attr.attr, + &sensor_dev_attr_in7_input.dev_attr.attr, + &sensor_dev_attr_in8_input.dev_attr.attr, + + &sensor_dev_attr_in5_min_alarm.dev_attr.attr, + &sensor_dev_attr_in6_min_alarm.dev_attr.attr, + &sensor_dev_attr_in7_min_alarm.dev_attr.attr, + &sensor_dev_attr_in8_min_alarm.dev_attr.attr, + + &sensor_dev_attr_in9_input.dev_attr.attr, + &sensor_dev_attr_in10_input.dev_attr.attr, + &sensor_dev_attr_in11_input.dev_attr.attr, + + &sensor_dev_attr_power1_input.dev_attr.attr, + &sensor_dev_attr_power2_input.dev_attr.attr, + &sensor_dev_attr_power3_input.dev_attr.attr, + &sensor_dev_attr_power4_input.dev_attr.attr, + + NULL, +}; + +static const struct attribute_group ltc4245_group = { + .attrs = ltc4245_attributes, +}; + +static int ltc4245_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct ltc4245_data *data; + int ret; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) { + ret = -ENOMEM; + goto out_kzalloc; + } + + i2c_set_clientdata(client, data); + mutex_init(&data->update_lock); + + /* Initialize the LTC4245 chip */ + /* TODO */ + + /* Register sysfs hooks */ + ret = sysfs_create_group(&client->dev.kobj, <c4245_group); + if (ret) + goto out_sysfs_create_group; + + data->hwmon_dev = hwmon_device_register(&client->dev); + if (IS_ERR(data->hwmon_dev)) { + ret = PTR_ERR(data->hwmon_dev); + goto out_hwmon_device_register; + } + + return 0; + +out_hwmon_device_register: + sysfs_remove_group(&client->dev.kobj, <c4245_group); +out_sysfs_create_group: + kfree(data); +out_kzalloc: + return ret; +} + +static int ltc4245_remove(struct i2c_client *client) +{ + struct ltc4245_data *data = i2c_get_clientdata(client); + + hwmon_device_unregister(data->hwmon_dev); + sysfs_remove_group(&client->dev.kobj, <c4245_group); + + kfree(data); + + return 0; +} + +/* Check that some bits in a control register appear at all possible + * locations without changing value + * + * @client: the i2c client to use + * @reg: the register to read + * @bits: the bits to check (0xff checks all bits, + * 0x03 checks only the last two bits) + * + * return -ERRNO if the register read failed + * return -ENODEV if the register value doesn't stay constant at all + * possible addresses + * + * return 0 for success + */ +static int ltc4245_check_control_reg(struct i2c_client *client, u8 reg, u8 bits) +{ + int i; + s32 v, voff1, voff2; + + /* Read register and check for error */ + v = i2c_smbus_read_byte_data(client, reg); + if (v < 0) + return v; + + v &= bits; + + for (i = 0x00; i < 0xff; i += 0x20) { + + voff1 = i2c_smbus_read_byte_data(client, reg + i); + if (voff1 < 0) + return voff1; + + voff2 = i2c_smbus_read_byte_data(client, reg + i + 0x08); + if (voff2 < 0) + return voff2; + + voff1 &= bits; + voff2 &= bits; + + if (v != voff1 || v != voff2) + return -ENODEV; + } + + return 0; +} + +static int ltc4245_detect(struct i2c_client *client, + int kind, + struct i2c_board_info *info) +{ + struct i2c_adapter *adapter = client->adapter; + + if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA)) + return -ENODEV; + + if (kind < 0) { /* probed detection - check the chip type */ + s32 v; /* 8 bits from the chip, or -ERRNO */ + + /* Chip registers 0x00-0x07 are control registers + * Chip registers 0x10-0x1f are data registers + * + * Address bits b7-b5 are ignored. This makes the chip "repeat" + * in steps of 0x20. Any control registers should appear with + * the same values across all duplicated addresses. + * + * Register 0x02 bit b2 is reserved, expect 0 + * Register 0x07 bits b7 to b4 are reserved, expect 0 + * + * Registers 0x01, 0x02 are control registers and should not + * change on their own. + * + * Register 0x06 bits b6 and b7 are control bits, and should + * not change on their own. + * + * Register 0x07 bits b3 to b0 are control bits, and should + * not change on their own. + */ + + /* read register 0x02 reserved bit, expect 0 */ + v = i2c_smbus_read_byte_data(client, LTC4245_CONTROL); + if (v < 0 || (v & 0x04) != 0) + return -ENODEV; + + /* read register 0x07 reserved bits, expect 0 */ + v = i2c_smbus_read_byte_data(client, LTC4245_ADCADR); + if (v < 0 || (v & 0xf0) != 0) + return -ENODEV; + + /* check that the alert register appears at all locations */ + if (ltc4245_check_control_reg(client, LTC4245_ALERT, 0xff)) + return -ENODEV; + + /* check that the control register appears at all locations */ + if (ltc4245_check_control_reg(client, LTC4245_CONTROL, 0xff)) + return -ENODEV; + + /* check that register 0x06 bits b6 and b7 stay constant */ + if (ltc4245_check_control_reg(client, LTC4245_GPIO, 0xc0)) + return -ENODEV; + + /* check that register 0x07 bits b3-b0 stay constant */ + if (ltc4245_check_control_reg(client, LTC4245_ADCADR, 0x0f)) + return -ENODEV; + } + + strlcpy(info->type, "ltc4245", I2C_NAME_SIZE); + dev_info(&adapter->dev, "ltc4245 %s at address 0x%02x\n", + kind < 0 ? "probed" : "forced", + client->addr); + + return 0; +} + +static const struct i2c_device_id ltc4245_id[] = { + { "ltc4245", ltc4245 }, + { } +}; +MODULE_DEVICE_TABLE(i2c, ltc4245_id); + +/* This is the driver that will be inserted */ +static struct i2c_driver ltc4245_driver = { + .class = I2C_CLASS_HWMON, + .driver = { + .name = "ltc4245", + }, + .probe = ltc4245_probe, + .remove = ltc4245_remove, + .id_table = ltc4245_id, + .detect = ltc4245_detect, + .address_data = &addr_data, +}; + +static int __init ltc4245_init(void) +{ + return i2c_add_driver(<c4245_driver); +} + +static void __exit ltc4245_exit(void) +{ + i2c_del_driver(<c4245_driver); +} + +MODULE_AUTHOR("Ira W. Snyder "); +MODULE_DESCRIPTION("LTC4245 driver"); +MODULE_LICENSE("GPL"); + +module_init(ltc4245_init); +module_exit(ltc4245_exit); -- cgit v1.2.3 From b4da93e4b0ffc261c3530fe938aefd52854aa84c Mon Sep 17 00:00:00 2001 From: Jean-Marc Spaggiari Date: Wed, 7 Jan 2009 16:37:32 +0100 Subject: hwmon: (it87) Add support for the ITE IT8720F Allow it87.c to handle IT8720 chipset like IT8718 in order to retrieve voltage, temperatures and fans speed from sensors tools. Also updating the related documentation. Signed-off-by: Jean-Marc Spaggiari Signed-off-by: Jean Delvare --- Documentation/hwmon/it87 | 20 ++++++++++++-------- drivers/hwmon/Kconfig | 3 ++- drivers/hwmon/it87.c | 30 +++++++++++++++++++++--------- 3 files changed, 35 insertions(+), 18 deletions(-) (limited to 'Documentation') diff --git a/Documentation/hwmon/it87 b/Documentation/hwmon/it87 index 042c0415140b..659315d98e00 100644 --- a/Documentation/hwmon/it87 +++ b/Documentation/hwmon/it87 @@ -26,6 +26,10 @@ Supported chips: Datasheet: Publicly available at the ITE website http://www.ite.com.tw/product_info/file/pc/IT8718F_V0.2.zip http://www.ite.com.tw/product_info/file/pc/IT8718F_V0%203_(for%20C%20version).zip + * IT8720F + Prefix: 'it8720' + Addresses scanned: from Super I/O config space (8 I/O ports) + Datasheet: Not yet publicly available. * SiS950 [clone of IT8705F] Prefix: 'it87' Addresses scanned: from Super I/O config space (8 I/O ports) @@ -71,7 +75,7 @@ Description ----------- This driver implements support for the IT8705F, IT8712F, IT8716F, -IT8718F, IT8726F and SiS950 chips. +IT8718F, IT8720F, IT8726F and SiS950 chips. These chips are 'Super I/O chips', supporting floppy disks, infrared ports, joysticks and other miscellaneous stuff. For hardware monitoring, they @@ -84,19 +88,19 @@ the IT8716F and late IT8712F have 6. They are shared with other functions though, so the functionality may not be available on a given system. The driver dumbly assume it is there. -The IT8718F also features VID inputs (up to 8 pins) but the value is -stored in the Super-I/O configuration space. Due to technical limitations, +The IT8718F and IT8720F also features VID inputs (up to 8 pins) but the value +is stored in the Super-I/O configuration space. Due to technical limitations, this value can currently only be read once at initialization time, so the driver won't notice and report changes in the VID value. The two upper VID bits share their pins with voltage inputs (in5 and in6) so you can't have both on a given board. -The IT8716F, IT8718F and later IT8712F revisions have support for +The IT8716F, IT8718F, IT8720F and later IT8712F revisions have support for 2 additional fans. The additional fans are supported by the driver. -The IT8716F and IT8718F, and late IT8712F and IT8705F also have optional -16-bit tachometer counters for fans 1 to 3. This is better (no more fan -clock divider mess) but not compatible with the older chips and +The IT8716F, IT8718F and IT8720F, and late IT8712F and IT8705F also have +optional 16-bit tachometer counters for fans 1 to 3. This is better (no more +fan clock divider mess) but not compatible with the older chips and revisions. The 16-bit tachometer mode is enabled by the driver when one of the above chips is detected. @@ -122,7 +126,7 @@ zero'; this is important for negative voltage measurements. All voltage inputs can measure voltages between 0 and 4.08 volts, with a resolution of 0.016 volt. The battery voltage in8 does not have limit registers. -The VID lines (IT8712F/IT8716F/IT8718F) encode the core voltage value: +The VID lines (IT8712F/IT8716F/IT8718F/IT8720F) encode the core voltage value: the voltage level your processor should work with. This is hardcoded by the mainboard and/or processor itself. It is a value in volts. diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 1ef1205b4e8c..aba01b4ceca4 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -400,7 +400,8 @@ config SENSORS_IT87 select HWMON_VID help If you say yes here you get support for ITE IT8705F, IT8712F, - IT8716F, IT8718F and IT8726F sensor chips, and the SiS960 clone. + IT8716F, IT8718F, IT8720F and IT8726F sensor chips, and the + SiS960 clone. This driver can also be built as a module. If so, the module will be called it87. diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c index b74c95735f95..0e0d692f0c9e 100644 --- a/drivers/hwmon/it87.c +++ b/drivers/hwmon/it87.c @@ -14,6 +14,7 @@ IT8712F Super I/O chip w/LPC interface IT8716F Super I/O chip w/LPC interface IT8718F Super I/O chip w/LPC interface + IT8720F Super I/O chip w/LPC interface IT8726F Super I/O chip w/LPC interface Sis950 A clone of the IT8705F @@ -52,7 +53,7 @@ #define DRVNAME "it87" -enum chips { it87, it8712, it8716, it8718 }; +enum chips { it87, it8712, it8716, it8718, it8720 }; static unsigned short force_id; module_param(force_id, ushort, 0); @@ -64,7 +65,10 @@ static struct platform_device *pdev; #define DEV 0x07 /* Register: Logical device select */ #define VAL 0x2f /* The value to read/write */ #define PME 0x04 /* The device with the fan registers in it */ -#define GPIO 0x07 /* The device with the IT8718F VID value in it */ + +/* The device with the IT8718F/IT8720F VID value in it */ +#define GPIO 0x07 + #define DEVID 0x20 /* Register: Device ID */ #define DEVREV 0x22 /* Register: Device Revision */ @@ -113,6 +117,7 @@ superio_exit(void) #define IT8705F_DEVID 0x8705 #define IT8716F_DEVID 0x8716 #define IT8718F_DEVID 0x8718 +#define IT8720F_DEVID 0x8720 #define IT8726F_DEVID 0x8726 #define IT87_ACT_REG 0x30 #define IT87_BASE_REG 0x60 @@ -150,8 +155,8 @@ static int fix_pwm_polarity; #define IT87_REG_ALARM2 0x02 #define IT87_REG_ALARM3 0x03 -/* The IT8718F has the VID value in a different register, in Super-I/O - configuration space. */ +/* The IT8718F and IT8720F have the VID value in a different register, in + Super-I/O configuration space. */ #define IT87_REG_VID 0x0a /* The IT8705F and IT8712F earlier than revision 0x08 use register 0x0b for fan divisors. Later IT8712F revisions must use 16-bit tachometer @@ -282,7 +287,8 @@ static inline int has_16bit_fans(const struct it87_data *data) return (data->type == it87 && data->revision >= 0x03) || (data->type == it8712 && data->revision >= 0x08) || data->type == it8716 - || data->type == it8718; + || data->type == it8718 + || data->type == it8720; } static int it87_probe(struct platform_device *pdev); @@ -992,6 +998,9 @@ static int __init it87_find(unsigned short *address, case IT8718F_DEVID: sio_data->type = it8718; break; + case IT8720F_DEVID: + sio_data->type = it8720; + break; case 0xffff: /* No device at all */ goto exit; default: @@ -1022,7 +1031,8 @@ static int __init it87_find(unsigned short *address, int reg; superio_select(GPIO); - if (chip_type == it8718) + if ((chip_type == it8718) || + (chip_type == it8720)) sio_data->vid_value = superio_inb(IT87_SIO_VID_REG); reg = superio_inb(IT87_SIO_PINX2_REG); @@ -1068,6 +1078,7 @@ static int __devinit it87_probe(struct platform_device *pdev) "it8712", "it8716", "it8718", + "it8720", }; res = platform_get_resource(pdev, IORESOURCE_IO, 0); @@ -1226,7 +1237,7 @@ static int __devinit it87_probe(struct platform_device *pdev) } if (data->type == it8712 || data->type == it8716 - || data->type == it8718) { + || data->type == it8718 || data->type == it8720) { data->vrm = vid_which_vrm(); /* VID reading from Super-I/O config space if available */ data->vid = sio_data->vid_value; @@ -1513,7 +1524,8 @@ static struct it87_data *it87_update_device(struct device *dev) data->sensor = it87_read_value(data, IT87_REG_TEMP_ENABLE); /* The 8705 does not have VID capability. - The 8718 does not use IT87_REG_VID for the same purpose. */ + The 8718 and the 8720 don't use IT87_REG_VID for the + same purpose. */ if (data->type == it8712 || data->type == it8716) { data->vid = it87_read_value(data, IT87_REG_VID); /* The older IT8712F revisions had only 5 VID pins, @@ -1608,7 +1620,7 @@ static void __exit sm_it87_exit(void) MODULE_AUTHOR("Chris Gauthron, " "Jean Delvare "); -MODULE_DESCRIPTION("IT8705F/8712F/8716F/8718F/8726F, SiS950 driver"); +MODULE_DESCRIPTION("IT8705F/8712F/8716F/8718F/8720F/8726F, SiS950 driver"); module_param(update_vbat, bool, 0); MODULE_PARM_DESC(update_vbat, "Update vbat if set else return powerup value"); module_param(fix_pwm_polarity, bool, 0); -- cgit v1.2.3 From 0589c2de643ef71a684ba6d219532f9e2a3e554b Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 7 Jan 2009 16:37:33 +0100 Subject: hwmon: Deprecate the fscher and fscpos drivers Now that the new merged fschmd driver has gained support for the watchdog integrated into these IC's, there is no more reason to keep the old fscher and fscpos drivers around, so mark them as deprecated. Signed-off-by: Hans de Goede Signed-off-by: Jean Delvare --- Documentation/feature-removal-schedule.txt | 8 ++++++++ drivers/hwmon/Kconfig | 20 ++++++++++++++------ 2 files changed, 22 insertions(+), 6 deletions(-) (limited to 'Documentation') diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 2193be53e773..5ddbe350487a 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -318,6 +318,14 @@ Who: Jean Delvare --------------------------- +What: fscher and fscpos drivers +When: June 2009 +Why: Deprecated by the new fschmd driver. +Who: Hans de Goede + Jean Delvare + +--------------------------- + What: SELinux "compat_net" functionality When: 2.6.30 at the earliest Why: In 2.6.18 the Secmark concept was introduced to replace the "compat_net" diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 91975148f4b9..3c34fb5e4194 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -305,9 +305,13 @@ config SENSORS_F75375S will be called f75375s. config SENSORS_FSCHER - tristate "FSC Hermes" + tristate "FSC Hermes (DEPRECATED)" depends on X86 && I2C help + This driver is DEPRECATED please use the new merged fschmd + ("FSC Poseidon, Scylla, Hermes, Heimdall and Heracles") driver + instead. + If you say yes here you get support for Fujitsu Siemens Computers Hermes sensor chips. @@ -315,9 +319,13 @@ config SENSORS_FSCHER will be called fscher. config SENSORS_FSCPOS - tristate "FSC Poseidon" + tristate "FSC Poseidon (DEPRECATED)" depends on X86 && I2C help + This driver is DEPRECATED please use the new merged fschmd + ("FSC Poseidon, Scylla, Hermes, Heimdall and Heracles") driver + instead. + If you say yes here you get support for Fujitsu Siemens Computers Poseidon sensor chips. @@ -326,15 +334,15 @@ config SENSORS_FSCPOS config SENSORS_FSCHMD tristate "FSC Poseidon, Scylla, Hermes, Heimdall and Heracles" - depends on X86 && I2C && EXPERIMENTAL + depends on X86 && I2C help If you say yes here you get support for various Fujitsu Siemens Computers sensor chips, including support for the integrated watchdog. - This is a new merged driver for FSC sensor chips which is intended - as a replacement for the fscpos, fscscy and fscher drivers and adds - support for several other FCS sensor chips. + This is a merged driver for FSC sensor chips replacing the fscpos, + fscscy and fscher drivers and adding support for several other FSC + sensor chips. This driver can also be built as a module. If so, the module will be called fschmd. -- cgit v1.2.3 From 2b7300513b98e05058a803de3beb8a1c0a0c61d9 Mon Sep 17 00:00:00 2001 From: Kaiwan N Billimoria Date: Wed, 7 Jan 2009 16:37:34 +0100 Subject: hwmon: (lm70) Code streamlining and cleanup This fixes a byteswap bug in the LM70 temperature sensor driver, which was previously covered up by a converse bug in the driver for the LM70EVAL-LLP board (which is also fixed). Other fixes: doc updates, remove an annoying msleep(), and improve three-wire protocol handling. Signed-off-by: Kaiwan N Billimoria [ dbrownell@users.sourceforge.net: doc and whitespace tweaks ] Signed-off-by: David Brownell Signed-off-by: Jean Delvare --- Documentation/hwmon/lm70 | 4 ++++ Documentation/spi/spi-lm70llp | 10 ++++++++++ drivers/hwmon/lm70.c | 9 +++++---- drivers/spi/spi_lm70llp.c | 33 ++++++++++++--------------------- 4 files changed, 31 insertions(+), 25 deletions(-) (limited to 'Documentation') diff --git a/Documentation/hwmon/lm70 b/Documentation/hwmon/lm70 index 2bdd3feebf53..b8d1a521e689 100644 --- a/Documentation/hwmon/lm70 +++ b/Documentation/hwmon/lm70 @@ -25,6 +25,10 @@ complement digital temperature (sent via the SIO line), is available in the driver for interpretation. This driver makes use of the kernel's in-core SPI support. +As a real (in-tree) example of this "SPI protocol driver" interfacing +with a "SPI master controller driver", see drivers/spi/spi_lm70llp.c +and its associated documentation. + Thanks to --------- Jean Delvare for mentoring the hwmon-side driver diff --git a/Documentation/spi/spi-lm70llp b/Documentation/spi/spi-lm70llp index 154bd02220b9..34a9cfd746bd 100644 --- a/Documentation/spi/spi-lm70llp +++ b/Documentation/spi/spi-lm70llp @@ -13,10 +13,20 @@ Description This driver provides glue code connecting a National Semiconductor LM70 LLP temperature sensor evaluation board to the kernel's SPI core subsystem. +This is a SPI master controller driver. It can be used in conjunction with +(layered under) the LM70 logical driver (a "SPI protocol driver"). In effect, this driver turns the parallel port interface on the eval board into a SPI bus with a single device, which will be driven by the generic LM70 driver (drivers/hwmon/lm70.c). + +Hardware Interfacing +-------------------- +The schematic for this particular board (the LM70EVAL-LLP) is +available (on page 4) here: + + http://www.national.com/appinfo/tempsensors/files/LM70LLPEVALmanual.pdf + The hardware interfacing on the LM70 LLP eval board is as follows: Parallel LM70 LLP diff --git a/drivers/hwmon/lm70.c b/drivers/hwmon/lm70.c index d435f003292d..9f9741b1d2b5 100644 --- a/drivers/hwmon/lm70.c +++ b/drivers/hwmon/lm70.c @@ -65,10 +65,9 @@ static ssize_t lm70_sense_temp(struct device *dev, "spi_write_then_read failed with status %d\n", status); goto out; } - dev_dbg(dev, "rxbuf[1] : 0x%x rxbuf[0] : 0x%x\n", rxbuf[1], rxbuf[0]); - - raw = (rxbuf[1] << 8) + rxbuf[0]; - dev_dbg(dev, "raw=0x%x\n", raw); + raw = (rxbuf[0] << 8) + rxbuf[1]; + dev_dbg(dev, "rxbuf[0] : 0x%02x rxbuf[1] : 0x%02x raw=0x%04x\n", + rxbuf[0], rxbuf[1], raw); /* * The "raw" temperature read into rxbuf[] is a 16-bit signed 2's @@ -109,6 +108,8 @@ static int __devinit lm70_probe(struct spi_device *spi) if ((spi->mode & (SPI_CPOL|SPI_CPHA)) || !(spi->mode & SPI_3WIRE)) return -EINVAL; + /* NOTE: we assume 8-bit words, and convert to 16 bits manually */ + p_lm70 = kzalloc(sizeof *p_lm70, GFP_KERNEL); if (!p_lm70) return -ENOMEM; diff --git a/drivers/spi/spi_lm70llp.c b/drivers/spi/spi_lm70llp.c index af6526767e2a..568c781ad91c 100644 --- a/drivers/spi/spi_lm70llp.c +++ b/drivers/spi/spi_lm70llp.c @@ -1,5 +1,5 @@ /* - * spi_lm70llp.c - driver for lm70llp eval board for the LM70 sensor + * spi_lm70llp.c - driver for LM70EVAL-LLP board for the LM70 sensor * * Copyright (C) 2006 Kaiwan N Billimoria * @@ -40,8 +40,12 @@ * master controller driver. The hwmon/lm70 driver is a "SPI protocol * driver", layered on top of this one and usable without the lm70llp. * + * Datasheet and Schematic: * The LM70 is a temperature sensor chip from National Semiconductor; its * datasheet is available at http://www.national.com/pf/LM/LM70.html + * The schematic for this particular board (the LM70EVAL-LLP) is + * available (on page 4) here: + * http://www.national.com/appinfo/tempsensors/files/LM70LLPEVALmanual.pdf * * Also see Documentation/spi/spi-lm70llp. The SPI<->parport code here is * (heavily) based on spi-butterfly by David Brownell. @@ -64,7 +68,7 @@ * * Note that parport pin 13 actually gets inverted by the transistor * arrangement which lets either the parport or the LM70 drive the - * SI/SO signal. + * SI/SO signal (see the schematic for details). */ #define DRVNAME "spi-lm70llp" @@ -106,12 +110,16 @@ static inline struct spi_lm70llp *spidev_to_pp(struct spi_device *spi) static inline void deassertCS(struct spi_lm70llp *pp) { u8 data = parport_read_data(pp->port); + + data &= ~0x80; /* pull D7/SI-out low while de-asserted */ parport_write_data(pp->port, data | nCS); } static inline void assertCS(struct spi_lm70llp *pp) { u8 data = parport_read_data(pp->port); + + data |= 0x80; /* pull D7/SI-out high so lm70 drives SO-in */ parport_write_data(pp->port, data & ~nCS); } @@ -184,22 +192,7 @@ static void lm70_chipselect(struct spi_device *spi, int value) */ static u32 lm70_txrx(struct spi_device *spi, unsigned nsecs, u32 word, u8 bits) { - static u32 sio=0; - static int first_time=1; - - /* First time: perform SPI bitbang and return the LSB of - * the result of the SPI call. - */ - if (first_time) { - sio = bitbang_txrx_be_cpha0(spi, nsecs, 0, word, bits); - first_time=0; - return (sio & 0x00ff); - } - /* Return the MSB of the result of the SPI call */ - else { - first_time=1; - return (sio >> 8); - } + return bitbang_txrx_be_cpha0(spi, nsecs, 0, word, bits); } static void spi_lm70llp_attach(struct parport *p) @@ -293,10 +286,9 @@ static void spi_lm70llp_attach(struct parport *p) status = -ENODEV; goto out_bitbang_stop; } - pp->spidev_lm70->bits_per_word = 16; + pp->spidev_lm70->bits_per_word = 8; lm70llp = pp; - return; out_bitbang_stop: @@ -326,7 +318,6 @@ static void spi_lm70llp_detach(struct parport *p) /* power down */ parport_write_data(pp->port, 0); - msleep(10); parport_release(pp->pd); parport_unregister_device(pp->pd); -- cgit v1.2.3 From c8ac32e4711639c81e5f4d4cd78c8f21675a2bae Mon Sep 17 00:00:00 2001 From: Manuel Lauss Date: Wed, 7 Jan 2009 16:37:34 +0100 Subject: hwmon: (lm70) Add TI TMP121 support The Texas Instruments TMP121 is a SPI temperature sensor very similar to the LM70, with slightly higher resolution. This patch extends the LM70 driver to support the TMP121. The TMP123 differs in pin assign- ment. Signed-off-by: Manuel Lauss Signed-off-by: Jean Delvare --- Documentation/hwmon/lm70 | 8 ++++- drivers/hwmon/Kconfig | 5 +-- drivers/hwmon/lm70.c | 84 ++++++++++++++++++++++++++++++++++++++++++------ 3 files changed, 84 insertions(+), 13 deletions(-) (limited to 'Documentation') diff --git a/Documentation/hwmon/lm70 b/Documentation/hwmon/lm70 index b8d1a521e689..0d240291e3cc 100644 --- a/Documentation/hwmon/lm70 +++ b/Documentation/hwmon/lm70 @@ -1,9 +1,11 @@ Kernel driver lm70 ================== -Supported chip: +Supported chips: * National Semiconductor LM70 Datasheet: http://www.national.com/pf/LM/LM70.html + * Texas Instruments TMP121/TMP123 + Information: http://focus.ti.com/docs/prod/folders/print/tmp121.html Author: Kaiwan N Billimoria @@ -29,6 +31,10 @@ As a real (in-tree) example of this "SPI protocol driver" interfacing with a "SPI master controller driver", see drivers/spi/spi_lm70llp.c and its associated documentation. +The TMP121/TMP123 are very similar; main differences are 4 wire SPI inter- +face (read only) and 13-bit temperature data (0.0625 degrees celsius reso- +lution). + Thanks to --------- Jean Delvare for mentoring the hwmon-side driver diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 3c34fb5e4194..4b33bc82cc24 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -428,11 +428,12 @@ config SENSORS_LM63 will be called lm63. config SENSORS_LM70 - tristate "National Semiconductor LM70" + tristate "National Semiconductor LM70 / Texas Instruments TMP121" depends on SPI_MASTER && EXPERIMENTAL help If you say yes here you get support for the National Semiconductor - LM70 digital temperature sensor chip. + LM70 and Texas Instruments TMP121/TMP123 digital temperature + sensor chips. This driver can also be built as a module. If so, the module will be called lm70. diff --git a/drivers/hwmon/lm70.c b/drivers/hwmon/lm70.c index 9f9741b1d2b5..ae6204f33214 100644 --- a/drivers/hwmon/lm70.c +++ b/drivers/hwmon/lm70.c @@ -37,9 +37,13 @@ #define DRVNAME "lm70" +#define LM70_CHIP_LM70 0 /* original NS LM70 */ +#define LM70_CHIP_TMP121 1 /* TI TMP121/TMP123 */ + struct lm70 { struct device *hwmon_dev; struct mutex lock; + unsigned int chip; }; /* sysfs hook function */ @@ -47,7 +51,7 @@ static ssize_t lm70_sense_temp(struct device *dev, struct device_attribute *attr, char *buf) { struct spi_device *spi = to_spi_device(dev); - int status, val; + int status, val = 0; u8 rxbuf[2]; s16 raw=0; struct lm70 *p_lm70 = dev_get_drvdata(&spi->dev); @@ -70,6 +74,7 @@ static ssize_t lm70_sense_temp(struct device *dev, rxbuf[0], rxbuf[1], raw); /* + * LM70: * The "raw" temperature read into rxbuf[] is a 16-bit signed 2's * complement value. Only the MSB 11 bits (1 sign + 10 temperature * bits) are meaningful; the LSB 5 bits are to be discarded. @@ -79,8 +84,21 @@ static ssize_t lm70_sense_temp(struct device *dev, * by 0.25. Also multiply by 1000 to represent in millidegrees * Celsius. * So it's equivalent to multiplying by 0.25 * 1000 = 250. + * + * TMP121/TMP123: + * 13 bits of 2's complement data, discard LSB 3 bits, + * resolution 0.0625 degrees celsius. */ - val = ((int)raw/32) * 250; + switch (p_lm70->chip) { + case LM70_CHIP_LM70: + val = ((int)raw / 32) * 250; + break; + + case LM70_CHIP_TMP121: + val = ((int)raw / 8) * 625 / 10; + break; + } + status = sprintf(buf, "%d\n", val); /* millidegrees Celsius */ out: mutex_unlock(&p_lm70->lock); @@ -92,22 +110,31 @@ static DEVICE_ATTR(temp1_input, S_IRUGO, lm70_sense_temp, NULL); static ssize_t lm70_show_name(struct device *dev, struct device_attribute *devattr, char *buf) { - return sprintf(buf, "lm70\n"); + struct lm70 *p_lm70 = dev_get_drvdata(dev); + int ret; + + switch (p_lm70->chip) { + case LM70_CHIP_LM70: + ret = sprintf(buf, "lm70\n"); + break; + case LM70_CHIP_TMP121: + ret = sprintf(buf, "tmp121\n"); + break; + default: + ret = -EINVAL; + } + return ret; } static DEVICE_ATTR(name, S_IRUGO, lm70_show_name, NULL); /*----------------------------------------------------------------------*/ -static int __devinit lm70_probe(struct spi_device *spi) +static int __devinit common_probe(struct spi_device *spi, int chip) { struct lm70 *p_lm70; int status; - /* signaling is SPI_MODE_0 on a 3-wire link (shared SI/SO) */ - if ((spi->mode & (SPI_CPOL|SPI_CPHA)) || !(spi->mode & SPI_3WIRE)) - return -EINVAL; - /* NOTE: we assume 8-bit words, and convert to 16 bits manually */ p_lm70 = kzalloc(sizeof *p_lm70, GFP_KERNEL); @@ -115,6 +142,7 @@ static int __devinit lm70_probe(struct spi_device *spi) return -ENOMEM; mutex_init(&p_lm70->lock); + p_lm70->chip = chip; /* sysfs hook */ p_lm70->hwmon_dev = hwmon_device_register(&spi->dev); @@ -142,6 +170,24 @@ out_dev_reg_failed: return status; } +static int __devinit lm70_probe(struct spi_device *spi) +{ + /* signaling is SPI_MODE_0 on a 3-wire link (shared SI/SO) */ + if ((spi->mode & (SPI_CPOL | SPI_CPHA)) || !(spi->mode & SPI_3WIRE)) + return -EINVAL; + + return common_probe(spi, LM70_CHIP_LM70); +} + +static int __devinit tmp121_probe(struct spi_device *spi) +{ + /* signaling is SPI_MODE_0 with only MISO connected */ + if (spi->mode & (SPI_CPOL | SPI_CPHA)) + return -EINVAL; + + return common_probe(spi, LM70_CHIP_TMP121); +} + static int __devexit lm70_remove(struct spi_device *spi) { struct lm70 *p_lm70 = dev_get_drvdata(&spi->dev); @@ -155,6 +201,15 @@ static int __devexit lm70_remove(struct spi_device *spi) return 0; } +static struct spi_driver tmp121_driver = { + .driver = { + .name = "tmp121", + .owner = THIS_MODULE, + }, + .probe = tmp121_probe, + .remove = __devexit_p(lm70_remove), +}; + static struct spi_driver lm70_driver = { .driver = { .name = "lm70", @@ -166,17 +221,26 @@ static struct spi_driver lm70_driver = { static int __init init_lm70(void) { - return spi_register_driver(&lm70_driver); + int ret = spi_register_driver(&lm70_driver); + if (ret) + return ret; + + ret = spi_register_driver(&tmp121_driver); + if (ret) + spi_unregister_driver(&lm70_driver); + + return ret; } static void __exit cleanup_lm70(void) { spi_unregister_driver(&lm70_driver); + spi_unregister_driver(&tmp121_driver); } module_init(init_lm70); module_exit(cleanup_lm70); MODULE_AUTHOR("Kaiwan N Billimoria"); -MODULE_DESCRIPTION("National Semiconductor LM70 Linux driver"); +MODULE_DESCRIPTION("NS LM70 / TI TMP121/TMP123 Linux driver"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 77fa49d94a75b5f9702c70b4fbe27b08b21317b9 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Wed, 7 Jan 2009 16:37:35 +0100 Subject: hwmon: Fix various typos Signed-off-by: Jean Delvare Acked-by: Hans de Goede Acked-by: David Hubbard --- Documentation/hwmon/lm85 | 2 +- drivers/hwmon/it87.c | 2 +- drivers/hwmon/w83627ehf.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'Documentation') diff --git a/Documentation/hwmon/lm85 b/Documentation/hwmon/lm85 index 400620741290..a13680871bc7 100644 --- a/Documentation/hwmon/lm85 +++ b/Documentation/hwmon/lm85 @@ -164,7 +164,7 @@ configured individually according to the following options. temperature. (PWM value from 0 to 255) * pwm#_auto_pwm_minctl - this flags selects for temp#_auto_temp_off temperature - the bahaviour of fans. Write 1 to let fans spinning at + the behaviour of fans. Write 1 to let fans spinning at pwm#_auto_pwm_min or write 0 to let them off. NOTE: It has been reported that there is a bug in the LM85 that causes the flag diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c index 88e71f195ec7..95a99c590da2 100644 --- a/drivers/hwmon/it87.c +++ b/drivers/hwmon/it87.c @@ -1386,7 +1386,7 @@ static void __devinit it87_init_device(struct platform_device *pdev) it87_write_value(data, IT87_REG_TEMP_HIGH(i), 127); } - /* Check if temperature channnels are reset manually or by some reason */ + /* Check if temperature channels are reset manually or by some reason */ tmp = it87_read_value(data, IT87_REG_TEMP_ENABLE); if ((tmp & 0x3f) == 0) { /* Temp1,Temp3=thermistor; Temp2=thermal diode */ diff --git a/drivers/hwmon/w83627ehf.c b/drivers/hwmon/w83627ehf.c index a3a01dc35a31..cb808d015361 100644 --- a/drivers/hwmon/w83627ehf.c +++ b/drivers/hwmon/w83627ehf.c @@ -503,7 +503,7 @@ static struct w83627ehf_data *w83627ehf_update_device(struct device *dev) } for (i = 0; i < 4; i++) { - /* pwmcfg, tolarance mapped for i=0, i=1 to same reg */ + /* pwmcfg, tolerance mapped for i=0, i=1 to same reg */ if (i != 1) { pwmcfg = w83627ehf_read_value(data, W83627EHF_REG_PWM_ENABLE[i]); -- cgit v1.2.3 From d4f373e57d3916814110968c5ea1155a8d972b5a Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 10 Nov 2008 14:07:45 -0500 Subject: USB: usb-storage: add "quirks=" module parameter This patch (as1163b) adds a "quirks=" module parameter to usb-storage. This will allow people to make short-term changes to their unusual_devs list without rebuilding the entire driver. Testing will become much easier, and less-sophisticated users will be able to access their buggy devices after a simple config-file change instead of having to wait for a new kernel release. The patch also adds a documentation entry for usb-storage's "delay_use" parameter, which has been around for years but but was never listed among the kernel parameters. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- Documentation/kernel-parameters.txt | 29 +++++++++ drivers/usb/storage/usb.c | 113 ++++++++++++++++++++++++++++++++++++ 2 files changed, 142 insertions(+) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 0b3f6711d2f1..8eb6e35405cd 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -91,6 +91,7 @@ parameter is applicable: SUSPEND System suspend states are enabled. FTRACE Function tracing enabled. TS Appropriate touchscreen support is enabled. + UMS USB Mass Storage support is enabled. USB USB support is enabled. USBHID USB Human Interface Device support is enabled. V4L Video For Linux support is enabled. @@ -2383,6 +2384,34 @@ and is between 256 and 4096 characters. It is defined in the file usbhid.mousepoll= [USBHID] The interval which mice are to be polled at. + usb-storage.delay_use= + [UMS] The delay in seconds before a new device is + scanned for Logical Units (default 5). + + usb-storage.quirks= + [UMS] A list of quirks entries to supplement or + override the built-in unusual_devs list. List + entries are separated by commas. Each entry has + the form VID:PID:Flags where VID and PID are Vendor + and Product ID values (4-digit hex numbers) and + Flags is a set of characters, each corresponding + to a common usb-storage quirk flag as follows: + c = FIX_CAPACITY (decrease the reported + device capacity by one sector); + i = IGNORE_DEVICE (don't bind to this + device); + l = NOT_LOCKABLE (don't try to lock and + unlock ejectable media); + m = MAX_SECTORS_64 (don't transfer more + than 64 sectors = 32 KB at a time); + r = IGNORE_RESIDUE (the device reports + bogus residue values); + s = SINGLE_LUN (the device has only one + Logical Unit); + w = NO_WP_DETECT (don't test whether the + medium is write-protected). + Example: quirks=0419:aaf5:rl,0421:0433:rc + add_efi_memmap [EFI; x86-32,X86-64] Include EFI memory map in kernel's map of available physical RAM. diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c index 27016fd2cad1..eb1a53a3e5ca 100644 --- a/drivers/usb/storage/usb.c +++ b/drivers/usb/storage/usb.c @@ -113,6 +113,16 @@ static unsigned int delay_use = 5; module_param(delay_use, uint, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(delay_use, "seconds to delay before using a new device"); +static char *quirks; +module_param(quirks, charp, S_IRUGO); +MODULE_PARM_DESC(quirks, "supplemental list of device IDs and their quirks"); + +struct quirks_entry { + u16 vid, pid; + u32 fflags; +}; +static struct quirks_entry *quirks_list, *quirks_end; + /* * The entries in this table correspond, line for line, @@ -473,6 +483,30 @@ static int associate_dev(struct us_data *us, struct usb_interface *intf) return 0; } +/* Adjust device flags based on the "quirks=" module parameter */ +static void adjust_quirks(struct us_data *us) +{ + u16 vid, pid; + struct quirks_entry *q; + unsigned int mask = (US_FL_FIX_CAPACITY | US_FL_IGNORE_DEVICE | + US_FL_NOT_LOCKABLE | US_FL_MAX_SECTORS_64 | + US_FL_IGNORE_RESIDUE | US_FL_SINGLE_LUN | + US_FL_NO_WP_DETECT); + + vid = le16_to_cpu(us->pusb_dev->descriptor.idVendor); + pid = le16_to_cpu(us->pusb_dev->descriptor.idProduct); + + for (q = quirks_list; q != quirks_end; ++q) { + if (q->vid == vid && q->pid == pid) { + us->fflags = (us->fflags & ~mask) | q->fflags; + dev_info(&us->pusb_intf->dev, "Quirks match for " + "vid %04x pid %04x: %x\n", + vid, pid, q->fflags); + break; + } + } +} + /* Find an unusual_dev descriptor (always succeeds in the current code) */ static struct us_unusual_dev *find_unusual(const struct usb_device_id *id) { @@ -497,6 +531,7 @@ static int get_device_info(struct us_data *us, const struct usb_device_id *id) idesc->bInterfaceProtocol : unusual_dev->useTransport; us->fflags = USB_US_ORIG_FLAGS(id->driver_info); + adjust_quirks(us); if (us->fflags & US_FL_IGNORE_DEVICE) { printk(KERN_INFO USB_STORAGE "device ignored\n"); @@ -1061,10 +1096,88 @@ static struct usb_driver usb_storage_driver = { .soft_unbind = 1, }; +/* Works only for digits and letters, but small and fast */ +#define TOLOWER(x) ((x) | 0x20) + +static void __init parse_quirks(void) +{ + int n, i; + char *p; + + if (!quirks) + return; + + /* Count the ':' characters to get 2 * the number of entries */ + n = 0; + for (p = quirks; *p; ++p) { + if (*p == ':') + ++n; + } + n /= 2; + if (n == 0) + return; /* Don't allocate 0 bytes */ + + quirks_list = kmalloc(n * sizeof(*quirks_list), GFP_KERNEL); + if (!quirks_list) + return; + + p = quirks; + quirks_end = quirks_list; + for (i = 0; i < n && *p; ++i) { + unsigned f = 0; + + /* Each entry consists of VID:PID:flags */ + quirks_end->vid = simple_strtoul(p, &p, 16); + if (*p != ':') + goto skip_to_next; + quirks_end->pid = simple_strtoul(p+1, &p, 16); + if (*p != ':') + goto skip_to_next; + + while (*++p && *p != ',') { + switch (TOLOWER(*p)) { + case 'c': + f |= US_FL_FIX_CAPACITY; + break; + case 'i': + f |= US_FL_IGNORE_DEVICE; + break; + case 'l': + f |= US_FL_NOT_LOCKABLE; + break; + case 'm': + f |= US_FL_MAX_SECTORS_64; + break; + case 'r': + f |= US_FL_IGNORE_RESIDUE; + break; + case 's': + f |= US_FL_SINGLE_LUN; + break; + case 'w': + f |= US_FL_NO_WP_DETECT; + break; + /* Ignore unrecognized flag characters */ + } + } + quirks_end->fflags = f; + ++quirks_end; + + skip_to_next: + /* Entries are separated by commas */ + while (*p) { + if (*p++ == ',') + break; + } + } /* for (i = 0; ...) */ +} + static int __init usb_stor_init(void) { int retval; + printk(KERN_INFO "Initializing USB Mass Storage driver...\n"); + parse_quirks(); /* register the driver, return usb_register return code if error */ retval = usb_register(&usb_storage_driver); -- cgit v1.2.3 From 9ac39f28b5237a629e41ccfc1f73d3a55723045c Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Wed, 12 Nov 2008 16:19:49 -0500 Subject: USB: add asynchronous autosuspend/autoresume support This patch (as1160b) adds support routines for asynchronous autosuspend and autoresume, with accompanying documentation updates. There already are several potential users of this interface, and others are likely to arise as autosuspend support becomes more widespread. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- Documentation/usb/power-management.txt | 22 +++++++-- drivers/usb/core/driver.c | 86 ++++++++++++++++++++++++++++++++++ drivers/usb/core/hub.c | 5 +- drivers/usb/core/usb.c | 1 + drivers/usb/core/usb.h | 1 + include/linux/usb.h | 9 ++++ 6 files changed, 117 insertions(+), 7 deletions(-) (limited to 'Documentation') diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt index e48ea1d51010..ad642615ad4c 100644 --- a/Documentation/usb/power-management.txt +++ b/Documentation/usb/power-management.txt @@ -313,11 +313,13 @@ three of the methods listed above. In addition, a driver indicates that it supports autosuspend by setting the .supports_autosuspend flag in its usb_driver structure. It is then responsible for informing the USB core whenever one of its interfaces becomes busy or idle. The -driver does so by calling these three functions: +driver does so by calling these five functions: int usb_autopm_get_interface(struct usb_interface *intf); void usb_autopm_put_interface(struct usb_interface *intf); int usb_autopm_set_interface(struct usb_interface *intf); + int usb_autopm_get_interface_async(struct usb_interface *intf); + void usb_autopm_put_interface_async(struct usb_interface *intf); The functions work by maintaining a counter in the usb_interface structure. When intf->pm_usage_count is > 0 then the interface is @@ -330,10 +332,12 @@ associated with the device itself rather than any of its interfaces. This field is used only by the USB core.) The driver owns intf->pm_usage_count; it can modify the value however -and whenever it likes. A nice aspect of the usb_autopm_* routines is -that the changes they make are protected by the usb_device structure's -PM mutex (udev->pm_mutex); however drivers may change pm_usage_count -without holding the mutex. +and whenever it likes. A nice aspect of the non-async usb_autopm_* +routines is that the changes they make are protected by the usb_device +structure's PM mutex (udev->pm_mutex); however drivers may change +pm_usage_count without holding the mutex. Drivers using the async +routines are responsible for their own synchronization and mutual +exclusion. usb_autopm_get_interface() increments pm_usage_count and attempts an autoresume if the new value is > 0 and the @@ -348,6 +352,14 @@ without holding the mutex. is suspended, and it attempts an autosuspend if the value is <= 0 and the device isn't suspended. + usb_autopm_get_interface_async() and + usb_autopm_put_interface_async() do almost the same things as + their non-async counterparts. The differences are: they do + not acquire the PM mutex, and they use a workqueue to do their + jobs. As a result they can be called in an atomic context, + such as an URB's completion handler, but when they return the + device will not generally not yet be in the desired state. + There also are a couple of utility routines drivers can use: usb_autopm_enable() sets pm_usage_cnt to 0 and then calls diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index 8c081308b0e2..23b3c7e79d4b 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -1341,6 +1341,19 @@ void usb_autosuspend_work(struct work_struct *work) usb_autopm_do_device(udev, 0); } +/* usb_autoresume_work - callback routine to autoresume a USB device */ +void usb_autoresume_work(struct work_struct *work) +{ + struct usb_device *udev = + container_of(work, struct usb_device, autoresume); + + /* Wake it up, let the drivers do their thing, and then put it + * back to sleep. + */ + if (usb_autopm_do_device(udev, 1) == 0) + usb_autopm_do_device(udev, -1); +} + /** * usb_autosuspend_device - delayed autosuspend of a USB device and its interfaces * @udev: the usb_device to autosuspend @@ -1491,6 +1504,45 @@ void usb_autopm_put_interface(struct usb_interface *intf) } EXPORT_SYMBOL_GPL(usb_autopm_put_interface); +/** + * usb_autopm_put_interface_async - decrement a USB interface's PM-usage counter + * @intf: the usb_interface whose counter should be decremented + * + * This routine does essentially the same thing as + * usb_autopm_put_interface(): it decrements @intf's usage counter and + * queues a delayed autosuspend request if the counter is <= 0. The + * difference is that it does not acquire the device's pm_mutex; + * callers must handle all synchronization issues themselves. + * + * Typically a driver would call this routine during an URB's completion + * handler, if no more URBs were pending. + * + * This routine can run in atomic context. + */ +void usb_autopm_put_interface_async(struct usb_interface *intf) +{ + struct usb_device *udev = interface_to_usbdev(intf); + int status = 0; + + if (intf->condition == USB_INTERFACE_UNBOUND) { + status = -ENODEV; + } else { + udev->last_busy = jiffies; + --intf->pm_usage_cnt; + if (udev->autosuspend_disabled || udev->autosuspend_delay < 0) + status = -EPERM; + else if (intf->pm_usage_cnt <= 0 && + !timer_pending(&udev->autosuspend.timer)) { + queue_delayed_work(ksuspend_usb_wq, &udev->autosuspend, + round_jiffies_relative( + udev->autosuspend_delay)); + } + } + dev_vdbg(&intf->dev, "%s: status %d cnt %d\n", + __func__, status, intf->pm_usage_cnt); +} +EXPORT_SYMBOL_GPL(usb_autopm_put_interface_async); + /** * usb_autopm_get_interface - increment a USB interface's PM-usage counter * @intf: the usb_interface whose counter should be incremented @@ -1536,6 +1588,37 @@ int usb_autopm_get_interface(struct usb_interface *intf) } EXPORT_SYMBOL_GPL(usb_autopm_get_interface); +/** + * usb_autopm_get_interface_async - increment a USB interface's PM-usage counter + * @intf: the usb_interface whose counter should be incremented + * + * This routine does much the same thing as + * usb_autopm_get_interface(): it increments @intf's usage counter and + * queues an autoresume request if the result is > 0. The differences + * are that it does not acquire the device's pm_mutex (callers must + * handle all synchronization issues themselves), and it does not + * autoresume the device directly (it only queues a request). After a + * successful call, the device will generally not yet be resumed. + * + * This routine can run in atomic context. + */ +int usb_autopm_get_interface_async(struct usb_interface *intf) +{ + struct usb_device *udev = interface_to_usbdev(intf); + int status = 0; + + if (intf->condition == USB_INTERFACE_UNBOUND) + status = -ENODEV; + else if (udev->autoresume_disabled) + status = -EPERM; + else if (++intf->pm_usage_cnt > 0 && udev->state == USB_STATE_SUSPENDED) + queue_work(ksuspend_usb_wq, &udev->autoresume); + dev_vdbg(&intf->dev, "%s: status %d cnt %d\n", + __func__, status, intf->pm_usage_cnt); + return status; +} +EXPORT_SYMBOL_GPL(usb_autopm_get_interface_async); + /** * usb_autopm_set_interface - set a USB interface's autosuspend state * @intf: the usb_interface whose state should be set @@ -1563,6 +1646,9 @@ EXPORT_SYMBOL_GPL(usb_autopm_set_interface); void usb_autosuspend_work(struct work_struct *work) {} +void usb_autoresume_work(struct work_struct *work) +{} + #endif /* CONFIG_USB_SUSPEND */ /** diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index b19cbfcd51da..95fb3104ba4f 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -1374,8 +1374,9 @@ static void usb_stop_pm(struct usb_device *udev) usb_autosuspend_device(udev->parent); usb_pm_unlock(udev); - /* Stop any autosuspend requests already submitted */ - cancel_rearming_delayed_work(&udev->autosuspend); + /* Stop any autosuspend or autoresume requests already submitted */ + cancel_delayed_work_sync(&udev->autosuspend); + cancel_work_sync(&udev->autoresume); } #else diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c index 400fa4cc9a34..44f2fc750b6d 100644 --- a/drivers/usb/core/usb.c +++ b/drivers/usb/core/usb.c @@ -402,6 +402,7 @@ struct usb_device *usb_alloc_dev(struct usb_device *parent, #ifdef CONFIG_PM mutex_init(&dev->pm_mutex); INIT_DELAYED_WORK(&dev->autosuspend, usb_autosuspend_work); + INIT_WORK(&dev->autoresume, usb_autoresume_work); dev->autosuspend_delay = usb_autosuspend_delay * HZ; dev->connect_time = jiffies; dev->active_duration = -jiffies; diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h index 9a1a45ac3add..b60ebb4de1a8 100644 --- a/drivers/usb/core/usb.h +++ b/drivers/usb/core/usb.h @@ -45,6 +45,7 @@ extern int usb_suspend(struct device *dev, pm_message_t msg); extern int usb_resume(struct device *dev); extern void usb_autosuspend_work(struct work_struct *work); +extern void usb_autoresume_work(struct work_struct *work); extern int usb_port_suspend(struct usb_device *dev); extern int usb_port_resume(struct usb_device *dev); extern int usb_external_suspend_device(struct usb_device *udev, diff --git a/include/linux/usb.h b/include/linux/usb.h index f72aa51f7bcd..859a88e6ce9c 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -398,6 +398,7 @@ struct usb_tt; * @urbnum: number of URBs submitted for the whole device * @active_duration: total time device is not suspended * @autosuspend: for delayed autosuspends + * @autoresume: for autoresumes requested while in_interrupt * @pm_mutex: protects PM operations * @last_busy: time of last use * @autosuspend_delay: in jiffies @@ -476,6 +477,7 @@ struct usb_device { #ifdef CONFIG_PM struct delayed_work autosuspend; + struct work_struct autoresume; struct mutex pm_mutex; unsigned long last_busy; @@ -513,6 +515,8 @@ extern struct usb_device *usb_find_device(u16 vendor_id, u16 product_id); extern int usb_autopm_set_interface(struct usb_interface *intf); extern int usb_autopm_get_interface(struct usb_interface *intf); extern void usb_autopm_put_interface(struct usb_interface *intf); +extern int usb_autopm_get_interface_async(struct usb_interface *intf); +extern void usb_autopm_put_interface_async(struct usb_interface *intf); static inline void usb_autopm_enable(struct usb_interface *intf) { @@ -539,8 +543,13 @@ static inline int usb_autopm_set_interface(struct usb_interface *intf) static inline int usb_autopm_get_interface(struct usb_interface *intf) { return 0; } +static inline int usb_autopm_get_interface_async(struct usb_interface *intf) +{ return 0; } + static inline void usb_autopm_put_interface(struct usb_interface *intf) { } +static inline void usb_autopm_put_interface_async(struct usb_interface *intf) +{ } static inline void usb_autopm_enable(struct usb_interface *intf) { } static inline void usb_autopm_disable(struct usb_interface *intf) -- cgit v1.2.3 From c838ea4626d6e982489ff519f9ecf5e1649ca90b Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 15 Dec 2008 10:40:06 -0500 Subject: USB: storage: make the "quirks=" module parameter writable This patch (as1190) makes usb-storage's "quirks=" module parameter writable, so that users can add entries for their devices at runtime with no need to reboot or reload usb-storage. New codes are added for the SANE_SENSE, CAPACITY_HEURISTICS, and CAPACITY_OK flags. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- Documentation/kernel-parameters.txt | 7 ++ drivers/usb/storage/usb.c | 169 +++++++++++++++--------------------- 2 files changed, 76 insertions(+), 100 deletions(-) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 8eb6e35405cd..a58fc8b73398 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2396,14 +2396,21 @@ and is between 256 and 4096 characters. It is defined in the file and Product ID values (4-digit hex numbers) and Flags is a set of characters, each corresponding to a common usb-storage quirk flag as follows: + a = SANE_SENSE (collect more than 18 bytes + of sense data); c = FIX_CAPACITY (decrease the reported device capacity by one sector); + h = CAPACITY_HEURISTICS (decrease the + reported device capacity by one + sector if the number is odd); i = IGNORE_DEVICE (don't bind to this device); l = NOT_LOCKABLE (don't try to lock and unlock ejectable media); m = MAX_SECTORS_64 (don't transfer more than 64 sectors = 32 KB at a time); + o = CAPACITY_OK (accept the capacity + reported by the device); r = IGNORE_RESIDUE (the device reports bogus residue values); s = SINGLE_LUN (the device has only one diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c index 80e234bf4e50..4becf495ca2d 100644 --- a/drivers/usb/storage/usb.c +++ b/drivers/usb/storage/usb.c @@ -111,16 +111,10 @@ static unsigned int delay_use = 5; module_param(delay_use, uint, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(delay_use, "seconds to delay before using a new device"); -static char *quirks; -module_param(quirks, charp, S_IRUGO); +static char quirks[128]; +module_param_string(quirks, quirks, sizeof(quirks), S_IRUGO | S_IWUSR); MODULE_PARM_DESC(quirks, "supplemental list of device IDs and their quirks"); -struct quirks_entry { - u16 vid, pid; - u32 fflags; -}; -static struct quirks_entry *quirks_list, *quirks_end; - /* * The entries in this table correspond, line for line, @@ -481,28 +475,80 @@ static int associate_dev(struct us_data *us, struct usb_interface *intf) return 0; } +/* Works only for digits and letters, but small and fast */ +#define TOLOWER(x) ((x) | 0x20) + /* Adjust device flags based on the "quirks=" module parameter */ static void adjust_quirks(struct us_data *us) { - u16 vid, pid; - struct quirks_entry *q; - unsigned int mask = (US_FL_FIX_CAPACITY | US_FL_IGNORE_DEVICE | + char *p; + u16 vid = le16_to_cpu(us->pusb_dev->descriptor.idVendor); + u16 pid = le16_to_cpu(us->pusb_dev->descriptor.idProduct); + unsigned f = 0; + unsigned int mask = (US_FL_SANE_SENSE | US_FL_FIX_CAPACITY | + US_FL_CAPACITY_HEURISTICS | US_FL_IGNORE_DEVICE | US_FL_NOT_LOCKABLE | US_FL_MAX_SECTORS_64 | - US_FL_IGNORE_RESIDUE | US_FL_SINGLE_LUN | - US_FL_NO_WP_DETECT); - - vid = le16_to_cpu(us->pusb_dev->descriptor.idVendor); - pid = le16_to_cpu(us->pusb_dev->descriptor.idProduct); - - for (q = quirks_list; q != quirks_end; ++q) { - if (q->vid == vid && q->pid == pid) { - us->fflags = (us->fflags & ~mask) | q->fflags; - dev_info(&us->pusb_intf->dev, "Quirks match for " - "vid %04x pid %04x: %x\n", - vid, pid, q->fflags); + US_FL_CAPACITY_OK | US_FL_IGNORE_RESIDUE | + US_FL_SINGLE_LUN | US_FL_NO_WP_DETECT); + + p = quirks; + while (*p) { + /* Each entry consists of VID:PID:flags */ + if (vid == simple_strtoul(p, &p, 16) && + *p == ':' && + pid == simple_strtoul(p+1, &p, 16) && + *p == ':') break; + + /* Move forward to the next entry */ + while (*p) { + if (*p++ == ',') + break; } } + if (!*p) /* No match */ + return; + + /* Collect the flags */ + while (*++p && *p != ',') { + switch (TOLOWER(*p)) { + case 'a': + f |= US_FL_SANE_SENSE; + break; + case 'c': + f |= US_FL_FIX_CAPACITY; + break; + case 'h': + f |= US_FL_CAPACITY_HEURISTICS; + break; + case 'i': + f |= US_FL_IGNORE_DEVICE; + break; + case 'l': + f |= US_FL_NOT_LOCKABLE; + break; + case 'm': + f |= US_FL_MAX_SECTORS_64; + break; + case 'o': + f |= US_FL_CAPACITY_OK; + break; + case 'r': + f |= US_FL_IGNORE_RESIDUE; + break; + case 's': + f |= US_FL_SINGLE_LUN; + break; + case 'w': + f |= US_FL_NO_WP_DETECT; + break; + /* Ignore unrecognized flag characters */ + } + } + us->fflags = (us->fflags & ~mask) | f; + dev_info(&us->pusb_intf->dev, "Quirks match for " + "vid %04x pid %04x: %x\n", + vid, pid, f); } /* Find an unusual_dev descriptor (always succeeds in the current code) */ @@ -1092,88 +1138,11 @@ static struct usb_driver usb_storage_driver = { .soft_unbind = 1, }; -/* Works only for digits and letters, but small and fast */ -#define TOLOWER(x) ((x) | 0x20) - -static void __init parse_quirks(void) -{ - int n, i; - char *p; - - if (!quirks) - return; - - /* Count the ':' characters to get 2 * the number of entries */ - n = 0; - for (p = quirks; *p; ++p) { - if (*p == ':') - ++n; - } - n /= 2; - if (n == 0) - return; /* Don't allocate 0 bytes */ - - quirks_list = kmalloc(n * sizeof(*quirks_list), GFP_KERNEL); - if (!quirks_list) - return; - - p = quirks; - quirks_end = quirks_list; - for (i = 0; i < n && *p; ++i) { - unsigned f = 0; - - /* Each entry consists of VID:PID:flags */ - quirks_end->vid = simple_strtoul(p, &p, 16); - if (*p != ':') - goto skip_to_next; - quirks_end->pid = simple_strtoul(p+1, &p, 16); - if (*p != ':') - goto skip_to_next; - - while (*++p && *p != ',') { - switch (TOLOWER(*p)) { - case 'c': - f |= US_FL_FIX_CAPACITY; - break; - case 'i': - f |= US_FL_IGNORE_DEVICE; - break; - case 'l': - f |= US_FL_NOT_LOCKABLE; - break; - case 'm': - f |= US_FL_MAX_SECTORS_64; - break; - case 'r': - f |= US_FL_IGNORE_RESIDUE; - break; - case 's': - f |= US_FL_SINGLE_LUN; - break; - case 'w': - f |= US_FL_NO_WP_DETECT; - break; - /* Ignore unrecognized flag characters */ - } - } - quirks_end->fflags = f; - ++quirks_end; - - skip_to_next: - /* Entries are separated by commas */ - while (*p) { - if (*p++ == ',') - break; - } - } /* for (i = 0; ...) */ -} - static int __init usb_stor_init(void) { int retval; printk(KERN_INFO "Initializing USB Mass Storage driver...\n"); - parse_quirks(); /* register the driver, return usb_register return code if error */ retval = usb_register(&usb_storage_driver); -- cgit v1.2.3 From 0d695913b0016b362a84a8bb6d6e28f8d90a70e2 Mon Sep 17 00:00:00 2001 From: Inaky Perez-Gonzalez Date: Sat, 20 Dec 2008 16:57:32 -0800 Subject: wimax: documentation for the stack wimax documentation Signed-off-by: Inaky Perez-Gonzalez Signed-off-by: Greg Kroah-Hartman --- Documentation/wimax/README.wimax | 81 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 81 insertions(+) create mode 100644 Documentation/wimax/README.wimax (limited to 'Documentation') diff --git a/Documentation/wimax/README.wimax b/Documentation/wimax/README.wimax new file mode 100644 index 000000000000..b78c4378084e --- /dev/null +++ b/Documentation/wimax/README.wimax @@ -0,0 +1,81 @@ + + Linux kernel WiMAX stack + + (C) 2008 Intel Corporation < linux-wimax@intel.com > + + This provides a basic Linux kernel WiMAX stack to provide a common + control API for WiMAX devices, usable from kernel and user space. + +1. Design + + The WiMAX stack is designed to provide for common WiMAX control + services to current and future WiMAX devices from any vendor. + + Because currently there is only one and we don't know what would be the + common services, the APIs it currently provides are very minimal. + However, it is done in such a way that it is easily extensible to + accommodate future requirements. + + The stack works by embedding a struct wimax_dev in your device's + control structures. This provides a set of callbacks that the WiMAX + stack will call in order to implement control operations requested by + the user. As well, the stack provides API functions that the driver + calls to notify about changes of state in the device. + + The stack exports the API calls needed to control the device to user + space using generic netlink as a marshalling mechanism. You can access + them using your own code or use the wrappers provided for your + convenience in libwimax (in the wimax-tools package). + + For detailed information on the stack, please see + include/linux/wimax.h. + +2. Usage + + For usage in a driver (registration, API, etc) please refer to the + instructions in the header file include/linux/wimax.h. + + When a device is registered with the WiMAX stack, a set of debugfs + files will appear in /sys/kernel/debug/wimax:wmxX can tweak for + control. + +2.1. Obtaining debug information: debugfs entries + + The WiMAX stack is compiled, by default, with debug messages that can + be used to diagnose issues. By default, said messages are disabled. + + The drivers will register debugfs entries that allow the user to tweak + debug settings. + + Each driver, when registering with the stack, will cause a debugfs + directory named wimax:DEVICENAME to be created; optionally, it might + create more subentries below it. + +2.1.1. Increasing debug output + + The files named *dl_* indicate knobs for controlling the debug output + of different submodules of the WiMAX stack: + * +# find /sys/kernel/debug/wimax\:wmx0 -name \*dl_\* +/sys/kernel/debug/wimax:wmx0/wimax_dl_stack +/sys/kernel/debug/wimax:wmx0/wimax_dl_op_rfkill +/sys/kernel/debug/wimax:wmx0/wimax_dl_op_reset +/sys/kernel/debug/wimax:wmx0/wimax_dl_op_msg +/sys/kernel/debug/wimax:wmx0/wimax_dl_id_table +/sys/kernel/debug/wimax:wmx0/wimax_dl_debugfs +/sys/kernel/debug/wimax:wmx0/.... # other driver specific files + + NOTE: Of course, if debugfs is mounted in a directory other than + /sys/kernel/debug, those paths will change. + + By reading the file you can obtain the current value of said debug + level; by writing to it, you can set it. + + To increase the debug level of, for example, the id-table submodule, + just write: + +$ echo 3 > /sys/kernel/debug/wimax:wmx0/wimax_dl_id_table + + Increasing numbers yield increasing debug information; for details of + what is printed and the available levels, check the source. The code + uses 0 for disabled and increasing values until 8. -- cgit v1.2.3 From b0c83ae1de01880075955c7224e751440688ec74 Mon Sep 17 00:00:00 2001 From: Inaky Perez-Gonzalez Date: Tue, 23 Dec 2008 16:18:24 -0800 Subject: wimax: Makefile, Kconfig and docbook linkage for the stack This patch provides Makefile and KConfig for the WiMAX stack, integrating them into the networking stack's Makefile, Kconfig and doc-book templates. Signed-off-by: Inaky Perez-Gonzalez Signed-off-by: Greg Kroah-Hartman --- Documentation/DocBook/networking.tmpl | 8 ++++++++ net/Kconfig | 2 ++ net/Makefile | 1 + net/wimax/Kconfig | 38 +++++++++++++++++++++++++++++++++++ net/wimax/Makefile | 13 ++++++++++++ 5 files changed, 62 insertions(+) create mode 100644 net/wimax/Kconfig create mode 100644 net/wimax/Makefile (limited to 'Documentation') diff --git a/Documentation/DocBook/networking.tmpl b/Documentation/DocBook/networking.tmpl index 627707a3cb9d..59ad69a9d777 100644 --- a/Documentation/DocBook/networking.tmpl +++ b/Documentation/DocBook/networking.tmpl @@ -74,6 +74,14 @@ !Enet/sunrpc/rpcb_clnt.c !Enet/sunrpc/clnt.c + WiMAX +!Enet/wimax/op-msg.c +!Enet/wimax/op-reset.c +!Enet/wimax/op-rfkill.c +!Enet/wimax/stack.c +!Iinclude/net/wimax.h +!Iinclude/linux/wimax.h + diff --git a/net/Kconfig b/net/Kconfig index 6ec2cce7c167..bf2776018f71 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -254,6 +254,8 @@ source "net/mac80211/Kconfig" endif # WIRELESS +source "net/wimax/Kconfig" + source "net/rfkill/Kconfig" source "net/9p/Kconfig" diff --git a/net/Makefile b/net/Makefile index ba4460432b7c..0fcce89d7169 100644 --- a/net/Makefile +++ b/net/Makefile @@ -63,3 +63,4 @@ endif ifeq ($(CONFIG_NET),y) obj-$(CONFIG_SYSCTL) += sysctl_net.o endif +obj-$(CONFIG_WIMAX) += wimax/ diff --git a/net/wimax/Kconfig b/net/wimax/Kconfig new file mode 100644 index 000000000000..0bdbb6928205 --- /dev/null +++ b/net/wimax/Kconfig @@ -0,0 +1,38 @@ +# +# WiMAX LAN device configuration +# + +menuconfig WIMAX + tristate "WiMAX Wireless Broadband support" + help + + Select to configure support for devices that provide + wireless broadband connectivity using the WiMAX protocol + (IEEE 802.16). + + Please note that most of these devices require signing up + for a service plan with a provider. + + The different WiMAX drivers can be enabled in the menu entry + + Device Drivers > Network device support > WiMAX Wireless + Broadband devices + + If unsure, it is safe to select M (module). + +config WIMAX_DEBUG_LEVEL + int "WiMAX debug level" + depends on WIMAX + default 8 + help + + Select the maximum debug verbosity level to be compiled into + the WiMAX stack code. + + By default, debug messages are disabled at runtime and can + be selectively enabled for different parts of the code using + the sysfs debug-levels file. + + If set at zero, this will compile out all the debug code. + + It is recommended that it is left at 8. diff --git a/net/wimax/Makefile b/net/wimax/Makefile new file mode 100644 index 000000000000..5b80b941c2c9 --- /dev/null +++ b/net/wimax/Makefile @@ -0,0 +1,13 @@ + +obj-$(CONFIG_WIMAX) += wimax.o + +wimax-y := \ + id-table.o \ + op-msg.o \ + op-reset.o \ + op-rfkill.o \ + stack.o + +wimax-$(CONFIG_DEBUG_FS) += debugfs.o + + -- cgit v1.2.3 From 3e91029ae049852c153da3fc355ab255ea7e2e0a Mon Sep 17 00:00:00 2001 From: Inaky Perez-Gonzalez Date: Sat, 20 Dec 2008 16:57:42 -0800 Subject: i2400m: documentation and instructions for usage The driver for the i2400m is a stacked driver. There is a core driver, the bus-generic driver that has no knowledge or dependencies on how the device is connected to the system; it only knows how to speak the device protocol. Then there are the bus-specific drivers (for USB and SDIO) that provide backends for the generic driver to communicate with the device. The bus generic driver connects to the network and WiMAX stacks on the top side, and on the bottom to the bus-specific drivers. Signed-off-by: Inaky Perez-Gonzalez Signed-off-by: Greg Kroah-Hartman --- Documentation/wimax/README.i2400m | 260 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 260 insertions(+) create mode 100644 Documentation/wimax/README.i2400m (limited to 'Documentation') diff --git a/Documentation/wimax/README.i2400m b/Documentation/wimax/README.i2400m new file mode 100644 index 000000000000..7dffd8919cb0 --- /dev/null +++ b/Documentation/wimax/README.i2400m @@ -0,0 +1,260 @@ + + Driver for the Intel Wireless Wimax Connection 2400m + + (C) 2008 Intel Corporation < linux-wimax@intel.com > + + This provides a driver for the Intel Wireless WiMAX Connection 2400m + and a basic Linux kernel WiMAX stack. + +1. Requirements + + * Linux installation with Linux kernel 2.6.22 or newer (if building + from a separate tree) + * Intel i2400m Echo Peak or Baxter Peak; this includes the Intel + Wireless WiMAX/WiFi Link 5x50 series. + * build tools: + + Linux kernel development package for the target kernel; to + build against your currently running kernel, you need to have + the kernel development package corresponding to the running + image installed (usually if your kernel is named + linux-VERSION, the development package is called + linux-dev-VERSION or linux-headers-VERSION). + + GNU C Compiler, make + +2. Compilation and installation + +2.1. Compilation of the drivers included in the kernel + + Configure the kernel; to enable the WiMAX drivers select Drivers > + Networking Drivers > WiMAX device support. Enable all of them as + modules (easier). + + If USB or SDIO are not enabled in the kernel configuration, the options + to build the i2400m USB or SDIO drivers will not show. Enable said + subsystems and go back to the WiMAX menu to enable the drivers. + + Compile and install your kernel as usual. + +2.2. Compilation of the drivers distributed as an standalone module + + To compile + +$ cd source/directory +$ make + + Once built you can load and unload using the provided load.sh script; + load.sh will load the modules, load.sh u will unload them. + + To install in the default kernel directories (and enable auto loading + when the device is plugged): + +$ make install +$ depmod -a + + If your kernel development files are located in a non standard + directory or if you want to build for a kernel that is not the + currently running one, set KDIR to the right location: + +$ make KDIR=/path/to/kernel/dev/tree + + For more information, please contact linux-wimax@intel.com. + +3. Installing the firmware + + The firmware can be obtained from http://linuxwimax.org or might have + been supplied with your hardware. + + It has to be installed in the target system: + * +$ cp FIRMWAREFILE.sbcf /lib/firmware/i2400m-fw-BUSTYPE-1.3.sbcf + + * NOTE: if your firmware came in an .rpm or .deb file, just install + it as normal, with the rpm (rpm -i FIRMWARE.rpm) or dpkg + (dpkg -i FIRMWARE.deb) commands. No further action is needed. + * BUSTYPE will be usb or sdio, depending on the hardware you have. + Each hardware type comes with its own firmware and will not work + with other types. + +4. Design + + This package contains two major parts: a WiMAX kernel stack and a + driver for the Intel i2400m. + + The WiMAX stack is designed to provide for common WiMAX control + services to current and future WiMAX devices from any vendor; please + see README.wimax for details. + + The i2400m kernel driver is broken up in two main parts: the bus + generic driver and the bus-specific drivers. The bus generic driver + forms the drivercore and contain no knowledge of the actual method we + use to connect to the device. The bus specific drivers are just the + glue to connect the bus-generic driver and the device. Currently only + USB and SDIO are supported. See drivers/net/wimax/i2400m/i2400m.h for + more information. + + The bus generic driver is logically broken up in two parts: OS-glue and + hardware-glue. The OS-glue interfaces with Linux. The hardware-glue + interfaces with the device on using an interface provided by the + bus-specific driver. The reason for this breakup is to be able to + easily reuse the hardware-glue to write drivers for other OSes; note + the hardware glue part is written as a native Linux driver; no + abstraction layers are used, so to port to another OS, the Linux kernel + API calls should be replaced with the target OS's. + +5. Usage + + To load the driver, follow the instructions in the install section; + once the driver is loaded, plug in the device (unless it is permanently + plugged in). The driver will enumerate the device, upload the firmware + and output messages in the kernel log (dmesg, /var/log/messages or + /var/log/kern.log) such as: + +... +i2400m_usb 5-4:1.0: firmware interface version 8.0.0 +i2400m_usb 5-4:1.0: WiMAX interface wmx0 (00:1d:e1:01:94:2c) ready + + At this point the device is ready to work. + + Current versions require the Intel WiMAX Network Service in userspace + to make things work. See the network service's README for instructions + on how to scan, connect and disconnect. + +5.1. Module parameters + + Module parameters can be set at kernel or module load time or by + echoing values: + +$ echo VALUE > /sys/module/MODULENAME/parameters/PARAMETERNAME + + To make changes permanent, for example, for the i2400m module, you can + also create a file named /etc/modprobe.d/i2400m containing: + +options i2400m idle_mode_disabled=1 + + To find which parameters are supported by a module, run: + +$ modinfo path/to/module.ko + + During kernel bootup (if the driver is linked in the kernel), specify + the following to the kernel command line: + +i2400m.PARAMETER=VALUE + +5.1.1. i2400m: idle_mode_disabled + + The i2400m module supports a parameter to disable idle mode. This + parameter, once set, will take effect only when the device is + reinitialized by the driver (eg: following a reset or a reconnect). + +5.2. Debug operations: debugfs entries + + The driver will register debugfs entries that allow the user to tweak + debug settings. There are three main container directories where + entries are placed, which correspond to the three blocks a i2400m WiMAX + driver has: + * /sys/kernel/debug/wimax:DEVNAME/ for the generic WiMAX stack + controls + * /sys/kernel/debug/wimax:DEVNAME/i2400m for the i2400m generic + driver controls + * /sys/kernel/debug/wimax:DEVNAME/i2400m-usb (or -sdio) for the + bus-specific i2400m-usb or i2400m-sdio controls). + + Of course, if debugfs is mounted in a directory other than + /sys/kernel/debug, those paths will change. + +5.2.1. Increasing debug output + + The files named *dl_* indicate knobs for controlling the debug output + of different submodules: + * +# find /sys/kernel/debug/wimax\:wmx0 -name \*dl_\* +/sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_tx +/sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_rx +/sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_notif +/sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_fw +/sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_usb +/sys/kernel/debug/wimax:wmx0/i2400m/dl_tx +/sys/kernel/debug/wimax:wmx0/i2400m/dl_rx +/sys/kernel/debug/wimax:wmx0/i2400m/dl_rfkill +/sys/kernel/debug/wimax:wmx0/i2400m/dl_netdev +/sys/kernel/debug/wimax:wmx0/i2400m/dl_fw +/sys/kernel/debug/wimax:wmx0/i2400m/dl_debugfs +/sys/kernel/debug/wimax:wmx0/i2400m/dl_driver +/sys/kernel/debug/wimax:wmx0/i2400m/dl_control +/sys/kernel/debug/wimax:wmx0/wimax_dl_stack +/sys/kernel/debug/wimax:wmx0/wimax_dl_op_rfkill +/sys/kernel/debug/wimax:wmx0/wimax_dl_op_reset +/sys/kernel/debug/wimax:wmx0/wimax_dl_op_msg +/sys/kernel/debug/wimax:wmx0/wimax_dl_id_table +/sys/kernel/debug/wimax:wmx0/wimax_dl_debugfs + + By reading the file you can obtain the current value of said debug + level; by writing to it, you can set it. + + To increase the debug level of, for example, the i2400m's generic TX + engine, just write: + +$ echo 3 > /sys/kernel/debug/wimax:wmx0/i2400m/dl_tx + + Increasing numbers yield increasing debug information; for details of + what is printed and the available levels, check the source. The code + uses 0 for disabled and increasing values until 8. + +5.2.2. RX and TX statistics + + The i2400m/rx_stats and i2400m/tx_stats provide statistics about the + data reception/delivery from the device: + +$ cat /sys/kernel/debug/wimax:wmx0/i2400m/rx_stats +45 1 3 34 3104 48 480 + + The numbers reported are + * packets/RX-buffer: total, min, max + * RX-buffers: total RX buffers received, accumulated RX buffer size + in bytes, min size received, max size received + + Thus, to find the average buffer size received, divide accumulated + RX-buffer / total RX-buffers. + + To clear the statistics back to 0, write anything to the rx_stats file: + +$ echo 1 > /sys/kernel/debug/wimax:wmx0/i2400m_rx_stats + + Likewise for TX. + + Note the packets this debug file refers to are not network packet, but + packets in the sense of the device-specific protocol for communication + to the host. See drivers/net/wimax/i2400m/tx.c. + +5.2.3. Tracing messages received from user space + + To echo messages received from user space into the trace pipe that the + i2400m driver creates, set the debug file i2400m/trace_msg_from_user to + 1: + * +$ echo 1 > /sys/kernel/debug/wimax:wmx0/i2400m/trace_msg_from_user + +5.2.4. Performing a device reset + + By writing a 0, a 1 or a 2 to the file + /sys/kernel/debug/wimax:wmx0/reset, the driver performs a warm (without + disconnecting from the bus), cold (disconnecting from the bus) or bus + (bus specific) reset on the device. + +5.2.5. Asking the device to enter power saving mode + + By writing any value to the /sys/kernel/debug/wimax:wmx0 file, the + device will attempt to enter power saving mode. + +6. Troubleshooting + +6.1. Driver complains about 'i2400m-fw-usb-1.2.sbcf: request failed' + + If upon connecting the device, the following is output in the kernel + log: + +i2400m_usb 5-4:1.0: fw i2400m-fw-usb-1.3.sbcf: request failed: -2 + + This means that the driver cannot locate the firmware file named + /lib/firmware/i2400m-fw-usb-1.2.sbcf. Check that the file is present in + the right location. -- cgit v1.2.3 From e8de1481fd7126ee9e93d6889da6f00c05e1e019 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Wed, 22 Oct 2008 19:55:31 -0700 Subject: resource: allow MMIO exclusivity for device drivers Device drivers that use pci_request_regions() (and similar APIs) have a reasonable expectation that they are the only ones accessing their device. As part of the e1000e hunt, we were afraid that some userland (X or some bootsplash stuff) was mapping the MMIO region that the driver thought it had exclusively via /dev/mem or via various sysfs resource mappings. This patch adds the option for device drivers to cause their reserved regions to the "banned from /dev/mem use" list, so now both kernel memory and device-exclusive MMIO regions are banned. NOTE: This is only active when CONFIG_STRICT_DEVMEM is set. In addition to the config option, a kernel parameter iomem=relaxed is provided for the cases where developers want to diagnose, in the field, drivers issues from userspace. Reviewed-by: Matthew Wilcox Signed-off-by: Arjan van de Ven Signed-off-by: Jesse Barnes --- Documentation/kernel-parameters.txt | 4 ++ arch/x86/mm/init_32.c | 2 + arch/x86/mm/init_64.c | 2 + drivers/net/e1000e/netdev.c | 2 +- drivers/pci/pci-sysfs.c | 3 + drivers/pci/pci.c | 107 ++++++++++++++++++++++++++++++++---- include/linux/ioport.h | 11 +++- include/linux/pci.h | 3 + kernel/resource.c | 61 +++++++++++++++++++- 9 files changed, 176 insertions(+), 19 deletions(-) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 0b3f6711d2f1..0072fabb1dd1 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -918,6 +918,10 @@ and is between 256 and 4096 characters. It is defined in the file inttest= [IA64] + iomem= Disable strict checking of access to MMIO memory + strict regions from userspace. + relaxed + iommu= [x86] off force diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 544d724caeee..88f1b10de3be 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -328,6 +328,8 @@ int devmem_is_allowed(unsigned long pagenr) { if (pagenr <= 256) return 1; + if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) + return 0; if (!page_is_ram(pagenr)) return 1; return 0; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 54c437e96541..23f68e77ad1f 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -888,6 +888,8 @@ int devmem_is_allowed(unsigned long pagenr) { if (pagenr <= 256) return 1; + if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) + return 0; if (!page_is_ram(pagenr)) return 1; return 0; diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index d4639facd1bd..91817d0afcaf 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -4807,7 +4807,7 @@ static int __devinit e1000_probe(struct pci_dev *pdev, } } - err = pci_request_selected_regions(pdev, + err = pci_request_selected_regions_exclusive(pdev, pci_select_bars(pdev, IORESOURCE_MEM), e1000e_driver_name); if (err) diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 388440e0d222..d5cdccf27a69 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -620,6 +620,9 @@ pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr, vma->vm_pgoff += start >> PAGE_SHIFT; mmap_type = res->flags & IORESOURCE_MEM ? pci_mmap_mem : pci_mmap_io; + if (res->flags & IORESOURCE_MEM && iomem_is_exclusive(start)) + return -EINVAL; + return pci_mmap_page_range(pdev, vma, mmap_type, write_combine); } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 2cfa41e367a7..47663dc0daf7 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1395,7 +1395,8 @@ void pci_release_region(struct pci_dev *pdev, int bar) * Returns 0 on success, or %EBUSY on error. A warning * message is also printed on failure. */ -int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name) +static int __pci_request_region(struct pci_dev *pdev, int bar, const char *res_name, + int exclusive) { struct pci_devres *dr; @@ -1408,8 +1409,9 @@ int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name) goto err_out; } else if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) { - if (!request_mem_region(pci_resource_start(pdev, bar), - pci_resource_len(pdev, bar), res_name)) + if (!__request_mem_region(pci_resource_start(pdev, bar), + pci_resource_len(pdev, bar), res_name, + exclusive)) goto err_out; } @@ -1427,6 +1429,47 @@ err_out: return -EBUSY; } +/** + * pci_request_region - Reserved PCI I/O and memory resource + * @pdev: PCI device whose resources are to be reserved + * @bar: BAR to be reserved + * @res_name: Name to be associated with resource. + * + * Mark the PCI region associated with PCI device @pdev BR @bar as + * being reserved by owner @res_name. Do not access any + * address inside the PCI regions unless this call returns + * successfully. + * + * Returns 0 on success, or %EBUSY on error. A warning + * message is also printed on failure. + */ +int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name) +{ + return __pci_request_region(pdev, bar, res_name, 0); +} + +/** + * pci_request_region_exclusive - Reserved PCI I/O and memory resource + * @pdev: PCI device whose resources are to be reserved + * @bar: BAR to be reserved + * @res_name: Name to be associated with resource. + * + * Mark the PCI region associated with PCI device @pdev BR @bar as + * being reserved by owner @res_name. Do not access any + * address inside the PCI regions unless this call returns + * successfully. + * + * Returns 0 on success, or %EBUSY on error. A warning + * message is also printed on failure. + * + * The key difference that _exclusive makes it that userspace is + * explicitly not allowed to map the resource via /dev/mem or + * sysfs. + */ +int pci_request_region_exclusive(struct pci_dev *pdev, int bar, const char *res_name) +{ + return __pci_request_region(pdev, bar, res_name, IORESOURCE_EXCLUSIVE); +} /** * pci_release_selected_regions - Release selected PCI I/O and memory resources * @pdev: PCI device whose resources were previously reserved @@ -1444,20 +1487,14 @@ void pci_release_selected_regions(struct pci_dev *pdev, int bars) pci_release_region(pdev, i); } -/** - * pci_request_selected_regions - Reserve selected PCI I/O and memory resources - * @pdev: PCI device whose resources are to be reserved - * @bars: Bitmask of BARs to be requested - * @res_name: Name to be associated with resource - */ -int pci_request_selected_regions(struct pci_dev *pdev, int bars, - const char *res_name) +int __pci_request_selected_regions(struct pci_dev *pdev, int bars, + const char *res_name, int excl) { int i; for (i = 0; i < 6; i++) if (bars & (1 << i)) - if(pci_request_region(pdev, i, res_name)) + if (__pci_request_region(pdev, i, res_name, excl)) goto err_out; return 0; @@ -1469,6 +1506,26 @@ err_out: return -EBUSY; } + +/** + * pci_request_selected_regions - Reserve selected PCI I/O and memory resources + * @pdev: PCI device whose resources are to be reserved + * @bars: Bitmask of BARs to be requested + * @res_name: Name to be associated with resource + */ +int pci_request_selected_regions(struct pci_dev *pdev, int bars, + const char *res_name) +{ + return __pci_request_selected_regions(pdev, bars, res_name, 0); +} + +int pci_request_selected_regions_exclusive(struct pci_dev *pdev, + int bars, const char *res_name) +{ + return __pci_request_selected_regions(pdev, bars, res_name, + IORESOURCE_EXCLUSIVE); +} + /** * pci_release_regions - Release reserved PCI I/O and memory resources * @pdev: PCI device whose resources were previously reserved by pci_request_regions @@ -1501,6 +1558,29 @@ int pci_request_regions(struct pci_dev *pdev, const char *res_name) return pci_request_selected_regions(pdev, ((1 << 6) - 1), res_name); } +/** + * pci_request_regions_exclusive - Reserved PCI I/O and memory resources + * @pdev: PCI device whose resources are to be reserved + * @res_name: Name to be associated with resource. + * + * Mark all PCI regions associated with PCI device @pdev as + * being reserved by owner @res_name. Do not access any + * address inside the PCI regions unless this call returns + * successfully. + * + * pci_request_regions_exclusive() will mark the region so that + * /dev/mem and the sysfs MMIO access will not be allowed. + * + * Returns 0 on success, or %EBUSY on error. A warning + * message is also printed on failure. + */ +int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name) +{ + return pci_request_selected_regions_exclusive(pdev, + ((1 << 6) - 1), res_name); +} + + /** * pci_set_master - enables bus-mastering for device dev * @dev: the PCI device to enable @@ -2149,10 +2229,13 @@ EXPORT_SYMBOL(pci_find_capability); EXPORT_SYMBOL(pci_bus_find_capability); EXPORT_SYMBOL(pci_release_regions); EXPORT_SYMBOL(pci_request_regions); +EXPORT_SYMBOL(pci_request_regions_exclusive); EXPORT_SYMBOL(pci_release_region); EXPORT_SYMBOL(pci_request_region); +EXPORT_SYMBOL(pci_request_region_exclusive); EXPORT_SYMBOL(pci_release_selected_regions); EXPORT_SYMBOL(pci_request_selected_regions); +EXPORT_SYMBOL(pci_request_selected_regions_exclusive); EXPORT_SYMBOL(pci_set_master); EXPORT_SYMBOL(pci_set_mwi); EXPORT_SYMBOL(pci_try_set_mwi); diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 041e95aac2bf..f6bb2ca8e3ba 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -49,6 +49,7 @@ struct resource_list { #define IORESOURCE_SIZEALIGN 0x00020000 /* size indicates alignment */ #define IORESOURCE_STARTALIGN 0x00040000 /* start field is alignment */ +#define IORESOURCE_EXCLUSIVE 0x08000000 /* Userland may not map this resource */ #define IORESOURCE_DISABLED 0x10000000 #define IORESOURCE_UNSET 0x20000000 #define IORESOURCE_AUTO 0x40000000 @@ -133,13 +134,16 @@ static inline unsigned long resource_type(struct resource *res) } /* Convenience shorthand with allocation */ -#define request_region(start,n,name) __request_region(&ioport_resource, (start), (n), (name)) -#define request_mem_region(start,n,name) __request_region(&iomem_resource, (start), (n), (name)) +#define request_region(start,n,name) __request_region(&ioport_resource, (start), (n), (name), 0) +#define __request_mem_region(start,n,name, excl) __request_region(&iomem_resource, (start), (n), (name), excl) +#define request_mem_region(start,n,name) __request_region(&iomem_resource, (start), (n), (name), 0) +#define request_mem_region_exclusive(start,n,name) \ + __request_region(&iomem_resource, (start), (n), (name), IORESOURCE_EXCLUSIVE) #define rename_region(region, newname) do { (region)->name = (newname); } while (0) extern struct resource * __request_region(struct resource *, resource_size_t start, - resource_size_t n, const char *name); + resource_size_t n, const char *name, int relaxed); /* Compatibility cruft */ #define release_region(start,n) __release_region(&ioport_resource, (start), (n)) @@ -175,6 +179,7 @@ extern struct resource * __devm_request_region(struct device *dev, extern void __devm_release_region(struct device *dev, struct resource *parent, resource_size_t start, resource_size_t n); extern int iomem_map_sanity_check(resource_size_t addr, unsigned long size); +extern int iomem_is_exclusive(u64 addr); #endif /* __ASSEMBLY__ */ #endif /* _LINUX_IOPORT_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 59a3dc2059d3..bfcb39ca8879 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -686,10 +686,13 @@ void pci_fixup_irqs(u8 (*)(struct pci_dev *, u8 *), int (*)(struct pci_dev *, u8, u8)); #define HAVE_PCI_REQ_REGIONS 2 int __must_check pci_request_regions(struct pci_dev *, const char *); +int __must_check pci_request_regions_exclusive(struct pci_dev *, const char *); void pci_release_regions(struct pci_dev *); int __must_check pci_request_region(struct pci_dev *, int, const char *); +int __must_check pci_request_region_exclusive(struct pci_dev *, int, const char *); void pci_release_region(struct pci_dev *, int); int pci_request_selected_regions(struct pci_dev *, int, const char *); +int pci_request_selected_regions_exclusive(struct pci_dev *, int, const char *); void pci_release_selected_regions(struct pci_dev *, int); /* drivers/pci/bus.c */ diff --git a/kernel/resource.c b/kernel/resource.c index e633106b12f6..ca6a1536b205 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -623,7 +623,7 @@ resource_size_t resource_alignment(struct resource *res) */ struct resource * __request_region(struct resource *parent, resource_size_t start, resource_size_t n, - const char *name) + const char *name, int flags) { struct resource *res = kzalloc(sizeof(*res), GFP_KERNEL); @@ -634,6 +634,7 @@ struct resource * __request_region(struct resource *parent, res->start = start; res->end = start + n - 1; res->flags = IORESOURCE_BUSY; + res->flags |= flags; write_lock(&resource_lock); @@ -679,7 +680,7 @@ int __check_region(struct resource *parent, resource_size_t start, { struct resource * res; - res = __request_region(parent, start, n, "check-region"); + res = __request_region(parent, start, n, "check-region", 0); if (!res) return -EBUSY; @@ -776,7 +777,7 @@ struct resource * __devm_request_region(struct device *dev, dr->start = start; dr->n = n; - res = __request_region(parent, start, n, name); + res = __request_region(parent, start, n, name, 0); if (res) devres_add(dev, dr); else @@ -876,3 +877,57 @@ int iomem_map_sanity_check(resource_size_t addr, unsigned long size) return err; } + +#ifdef CONFIG_STRICT_DEVMEM +static int strict_iomem_checks = 1; +#else +static int strict_iomem_checks; +#endif + +/* + * check if an address is reserved in the iomem resource tree + * returns 1 if reserved, 0 if not reserved. + */ +int iomem_is_exclusive(u64 addr) +{ + struct resource *p = &iomem_resource; + int err = 0; + loff_t l; + int size = PAGE_SIZE; + + if (!strict_iomem_checks) + return 0; + + addr = addr & PAGE_MASK; + + read_lock(&resource_lock); + for (p = p->child; p ; p = r_next(NULL, p, &l)) { + /* + * We can probably skip the resources without + * IORESOURCE_IO attribute? + */ + if (p->start >= addr + size) + break; + if (p->end < addr) + continue; + if (p->flags & IORESOURCE_BUSY && + p->flags & IORESOURCE_EXCLUSIVE) { + err = 1; + break; + } + } + read_unlock(&resource_lock); + + return err; +} + +static int __init strict_iomem(char *str) +{ + if (strstr(str, "relaxed")) + strict_iomem_checks = 0; + if (strstr(str, "strict")) + strict_iomem_checks = 1; + return 1; +} + +__setup("iomem=", strict_iomem); -- cgit v1.2.3 From 6a479079c07211bf348ac8a79754f26bea258f26 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 23 Dec 2008 03:08:29 +0000 Subject: PCI: Add pci_clear_master() as opposite of pci_set_master() During an online device reset it may be useful to disable bus-mastering. pci_disable_device() does that, and far more besides, so is not suitable for an online reset. Add pci_clear_master() which does just this. Signed-off-by: Ben Hutchings Reviewed-by: Matthew Wilcox Signed-off-by: Jesse Barnes --- Documentation/PCI/pci.txt | 3 ++- drivers/pci/pci.c | 39 ++++++++++++++++++++++++++++----------- include/linux/pci.h | 1 + 3 files changed, 31 insertions(+), 12 deletions(-) (limited to 'Documentation') diff --git a/Documentation/PCI/pci.txt b/Documentation/PCI/pci.txt index fd4907a2968c..7f6de6ea5b47 100644 --- a/Documentation/PCI/pci.txt +++ b/Documentation/PCI/pci.txt @@ -294,7 +294,8 @@ NOTE: pci_enable_device() can fail! Check the return value. pci_set_master() will enable DMA by setting the bus master bit in the PCI_COMMAND register. It also fixes the latency timer value if -it's set to something bogus by the BIOS. +it's set to something bogus by the BIOS. pci_clear_master() will +disable DMA by clearing the bus master bit. If the PCI device can use the PCI Memory-Write-Invalidate transaction, call pci_set_mwi(). This enables the PCI_COMMAND bit for Mem-Wr-Inval diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index c824dc8d617c..f3fd55df67db 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1667,6 +1667,22 @@ int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name) ((1 << 6) - 1), res_name); } +static void __pci_set_master(struct pci_dev *dev, bool enable) +{ + u16 old_cmd, cmd; + + pci_read_config_word(dev, PCI_COMMAND, &old_cmd); + if (enable) + cmd = old_cmd | PCI_COMMAND_MASTER; + else + cmd = old_cmd & ~PCI_COMMAND_MASTER; + if (cmd != old_cmd) { + dev_dbg(&dev->dev, "%s bus mastering\n", + enable ? "enabling" : "disabling"); + pci_write_config_word(dev, PCI_COMMAND, cmd); + } + dev->is_busmaster = enable; +} /** * pci_set_master - enables bus-mastering for device dev @@ -1675,21 +1691,21 @@ int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name) * Enables bus-mastering on the device and calls pcibios_set_master() * to do the needed arch specific settings. */ -void -pci_set_master(struct pci_dev *dev) +void pci_set_master(struct pci_dev *dev) { - u16 cmd; - - pci_read_config_word(dev, PCI_COMMAND, &cmd); - if (! (cmd & PCI_COMMAND_MASTER)) { - dev_dbg(&dev->dev, "enabling bus mastering\n"); - cmd |= PCI_COMMAND_MASTER; - pci_write_config_word(dev, PCI_COMMAND, cmd); - } - dev->is_busmaster = 1; + __pci_set_master(dev, true); pcibios_set_master(dev); } +/** + * pci_clear_master - disables bus-mastering for device dev + * @dev: the PCI device to disable + */ +void pci_clear_master(struct pci_dev *dev) +{ + __pci_set_master(dev, false); +} + #ifdef PCI_DISABLE_MWI int pci_set_mwi(struct pci_dev *dev) { @@ -2346,6 +2362,7 @@ EXPORT_SYMBOL(pci_release_selected_regions); EXPORT_SYMBOL(pci_request_selected_regions); EXPORT_SYMBOL(pci_request_selected_regions_exclusive); EXPORT_SYMBOL(pci_set_master); +EXPORT_SYMBOL(pci_clear_master); EXPORT_SYMBOL(pci_set_mwi); EXPORT_SYMBOL(pci_try_set_mwi); EXPORT_SYMBOL(pci_clear_mwi); diff --git a/include/linux/pci.h b/include/linux/pci.h index 7cbecef19bb6..0f6d2bb1df9c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -642,6 +642,7 @@ static inline int pci_is_managed(struct pci_dev *pdev) void pci_disable_device(struct pci_dev *dev); void pci_set_master(struct pci_dev *dev); +void pci_clear_master(struct pci_dev *dev); int pci_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state); #define HAVE_PCI_SET_MWI int __must_check pci_set_mwi(struct pci_dev *dev); -- cgit v1.2.3 From 4f628248a578585472e19e4cba2c604643af8c6c Mon Sep 17 00:00:00 2001 From: Jike Song Date: Mon, 5 Jan 2009 14:57:03 +0800 Subject: kbuild: reintroduce ALLSOURCE_ARCHS support for tags/cscope This patch reintroduce the ALLSOURCE_ARCHS support for tags/TAGS/ cscope targets. The Kbuild previously has this feature, but after moving the targets into scripts/tags.sh, ALLSOURCE_ARCHS disappears. It's something like this: $ make ALLSOURCE_ARCHS="x86 mips arm" tags cscope Signed-off-by: Jike Song Signed-off-by: Sam Ravnborg --- Documentation/kbuild/kbuild.txt | 7 +++++++ scripts/tags.sh | 18 +++++++++++++----- 2 files changed, 20 insertions(+), 5 deletions(-) (limited to 'Documentation') diff --git a/Documentation/kbuild/kbuild.txt b/Documentation/kbuild/kbuild.txt index 51771847e816..923f9ddee8f6 100644 --- a/Documentation/kbuild/kbuild.txt +++ b/Documentation/kbuild/kbuild.txt @@ -124,3 +124,10 @@ KBUILD_EXTRA_SYMBOLS -------------------------------------------------- For modules use symbols from another modules. See more details in modules.txt. + +ALLSOURCE_ARCHS +-------------------------------------------------- +For tags/TAGS/cscope targets, you can specify more than one archs +to be included in the databases, separated by blankspace. e.g. + + $ make ALLSOURCE_ARCHS="x86 mips arm" tags diff --git a/scripts/tags.sh b/scripts/tags.sh index 9e3451d2c3a1..fdbe78bb5e2b 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -24,6 +24,11 @@ else tree=${srctree}/ fi +# Detect if ALLSOURCE_ARCHS is set. If not, we assume SRCARCH +if [ "${ALLSOURCE_ARCHS}" = "" ]; then + ALLSOURCE_ARCHS=${SRCARCH} +fi + # find sources in arch/$ARCH find_arch_sources() { @@ -54,26 +59,29 @@ find_other_sources() find_sources() { find_arch_sources $1 "$2" - find_include_sources "$2" - find_other_sources "$2" } all_sources() { - find_sources $SRCARCH '*.[chS]' + for arch in $ALLSOURCE_ARCHS + do + find_sources $arch '*.[chS]' + done if [ ! -z "$archinclude" ]; then find_arch_include_sources $archinclude '*.[chS]' fi + find_include_sources '*.[chS]' + find_other_sources '*.[chS]' } all_kconfigs() { - find_sources $SRCARCH 'Kconfig*' + find_sources $ALLSOURCE_ARCHS 'Kconfig*' } all_defconfigs() { - find_sources $SRCARCH "defconfig" + find_sources $ALLSOURCE_ARCHS "defconfig" } docscope() -- cgit v1.2.3 From baa91878ab9b0f1cdb7ab03b53ee2e4389245644 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 6 Jan 2009 15:12:27 +0100 Subject: kbuild: fix typos (s/bin_shipped/bin.o_shipped/) in Documentation The text always mentions ...bin.o_shipped, just the example makefiles actually use ...bin_shipped. It was corrected in one place some time ago, these ones seem to have been forgotten. Signed-off-by: Wolfram Sang Signed-off-by: Sam Ravnborg --- Documentation/kbuild/modules.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/kbuild/modules.txt b/Documentation/kbuild/modules.txt index 1821c077b435..b1096da953c8 100644 --- a/Documentation/kbuild/modules.txt +++ b/Documentation/kbuild/modules.txt @@ -253,7 +253,7 @@ following files: # Module specific targets genbin: - echo "X" > 8123_bin_shipped + echo "X" > 8123_bin.o_shipped In example 2, we are down to two fairly simple files and for simple @@ -279,7 +279,7 @@ following files: # Module specific targets genbin: - echo "X" > 8123_bin_shipped + echo "X" > 8123_bin.o_shipped endif -- cgit v1.2.3 From 8feae13110d60cc6287afabc2887366b0eb226c2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 8 Jan 2009 12:04:47 +0000 Subject: NOMMU: Make VMAs per MM as for MMU-mode linux Make VMAs per mm_struct as for MMU-mode linux. This solves two problems: (1) In SYSV SHM where nattch for a segment does not reflect the number of shmat's (and forks) done. (2) In mmap() where the VMA's vm_mm is set to point to the parent mm by an exec'ing process when VM_EXECUTABLE is specified, regardless of the fact that a VMA might be shared and already have its vm_mm assigned to another process or a dead process. A new struct (vm_region) is introduced to track a mapped region and to remember the circumstances under which it may be shared and the vm_list_struct structure is discarded as it's no longer required. This patch makes the following additional changes: (1) Regions are now allocated with alloc_pages() rather than kmalloc() and with no recourse to __GFP_COMP, so the pages are not composite. Instead, each page has a reference on it held by the region. Anything else that is interested in such a page will have to get a reference on it to retain it. When the pages are released due to unmapping, each page is passed to put_page() and will be freed when the page usage count reaches zero. (2) Excess pages are trimmed after an allocation as the allocation must be made as a power-of-2 quantity of pages. (3) VMAs are added to the parent MM's R/B tree and mmap lists. As an MM may end up with overlapping VMAs within the tree, the VMA struct address is appended to the sort key. (4) Non-anonymous VMAs are now added to the backing inode's prio list. (5) Holes may be punched in anonymous VMAs with munmap(), releasing parts of the backing region. The VMA and region structs will be split if necessary. (6) sys_shmdt() only releases one attachment to a SYSV IPC shared memory segment instead of all the attachments at that addresss. Multiple shmat()'s return the same address under NOMMU-mode instead of different virtual addresses as under MMU-mode. (7) Core dumping for ELF-FDPIC requires fewer exceptions for NOMMU-mode. (8) /proc/maps is now the global list of mapped regions, and may list bits that aren't actually mapped anywhere. (9) /proc/meminfo gains a line (tagged "MmapCopy") that indicates the amount of RAM currently allocated by mmap to hold mappable regions that can't be mapped directly. These are copies of the backing device or file if not anonymous. These changes make NOMMU mode more similar to MMU mode. The downside is that NOMMU mode requires some extra memory to track things over NOMMU without this patch (VMAs are no longer shared, and there are now region structs). Signed-off-by: David Howells Tested-by: Mike Frysinger Acked-by: Paul Mundt --- Documentation/nommu-mmap.txt | 18 +- arch/arm/include/asm/mmu.h | 1 - arch/blackfin/include/asm/mmu.h | 1 - arch/blackfin/kernel/ptrace.c | 6 +- arch/blackfin/kernel/traps.c | 11 +- arch/frv/kernel/ptrace.c | 11 +- arch/h8300/include/asm/mmu.h | 1 - arch/m68knommu/include/asm/mmu.h | 1 - arch/sh/include/asm/mmu.h | 1 - fs/binfmt_elf_fdpic.c | 27 +- fs/proc/internal.h | 2 - fs/proc/meminfo.c | 6 + fs/proc/nommu.c | 71 ++- fs/proc/task_nommu.c | 108 +++-- include/asm-frv/mmu.h | 1 - include/asm-m32r/mmu.h | 1 - include/linux/mm.h | 18 +- include/linux/mm_types.h | 18 +- ipc/shm.c | 12 + kernel/fork.c | 4 +- lib/Kconfig.debug | 7 + mm/mmap.c | 10 + mm/nommu.c | 960 +++++++++++++++++++++++++++------------ 23 files changed, 860 insertions(+), 436 deletions(-) (limited to 'Documentation') diff --git a/Documentation/nommu-mmap.txt b/Documentation/nommu-mmap.txt index 7714f57caad5..02b89dcf38ac 100644 --- a/Documentation/nommu-mmap.txt +++ b/Documentation/nommu-mmap.txt @@ -109,12 +109,18 @@ and it's also much more restricted in the latter case: FURTHER NOTES ON NO-MMU MMAP ============================ - (*) A request for a private mapping of less than a page in size may not return - a page-aligned buffer. This is because the kernel calls kmalloc() to - allocate the buffer, not get_free_page(). - - (*) A list of all the mappings on the system is visible through /proc/maps in - no-MMU mode. + (*) A request for a private mapping of a file may return a buffer that is not + page-aligned. This is because XIP may take place, and the data may not be + paged aligned in the backing store. + + (*) A request for an anonymous mapping will always be page aligned. If + possible the size of the request should be a power of two otherwise some + of the space may be wasted as the kernel must allocate a power-of-2 + granule but will only discard the excess if appropriately configured as + this has an effect on fragmentation. + + (*) A list of all the private copy and anonymous mappings on the system is + visible through /proc/maps in no-MMU mode. (*) A list of all the mappings in use by a process is visible through /proc//maps in no-MMU mode. diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h index 53099d4ee421..b561584d04a1 100644 --- a/arch/arm/include/asm/mmu.h +++ b/arch/arm/include/asm/mmu.h @@ -24,7 +24,6 @@ typedef struct { * modified for 2.6 by Hyok S. Choi */ typedef struct { - struct vm_list_struct *vmlist; unsigned long end_brk; } mm_context_t; diff --git a/arch/blackfin/include/asm/mmu.h b/arch/blackfin/include/asm/mmu.h index 757e43906ed4..dbfd686360e6 100644 --- a/arch/blackfin/include/asm/mmu.h +++ b/arch/blackfin/include/asm/mmu.h @@ -10,7 +10,6 @@ struct sram_list_struct { }; typedef struct { - struct vm_list_struct *vmlist; unsigned long end_brk; unsigned long stack_start; diff --git a/arch/blackfin/kernel/ptrace.c b/arch/blackfin/kernel/ptrace.c index d2d388536630..594e325b40e4 100644 --- a/arch/blackfin/kernel/ptrace.c +++ b/arch/blackfin/kernel/ptrace.c @@ -160,15 +160,15 @@ put_reg(struct task_struct *task, int regno, unsigned long data) static inline int is_user_addr_valid(struct task_struct *child, unsigned long start, unsigned long len) { - struct vm_list_struct *vml; + struct vm_area_struct *vma; struct sram_list_struct *sraml; /* overflow */ if (start + len < start) return -EIO; - for (vml = child->mm->context.vmlist; vml; vml = vml->next) - if (start >= vml->vma->vm_start && start + len < vml->vma->vm_end) + vma = find_vma(child->mm, start); + if (vma && start >= vma->vm_start && start + len <= vma->vm_end) return 0; for (sraml = child->mm->context.sram_list; sraml; sraml = sraml->next) diff --git a/arch/blackfin/kernel/traps.c b/arch/blackfin/kernel/traps.c index 17d8e4172896..5b0667da8d05 100644 --- a/arch/blackfin/kernel/traps.c +++ b/arch/blackfin/kernel/traps.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include @@ -83,6 +84,7 @@ static void decode_address(char *buf, unsigned long address) struct mm_struct *mm; unsigned long flags, offset; unsigned char in_atomic = (bfin_read_IPEND() & 0x10) || in_atomic(); + struct rb_node *n; #ifdef CONFIG_KALLSYMS unsigned long symsize; @@ -128,9 +130,10 @@ static void decode_address(char *buf, unsigned long address) if (!mm) continue; - vml = mm->context.vmlist; - while (vml) { - struct vm_area_struct *vma = vml->vma; + for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) { + struct vm_area_struct *vma; + + vma = rb_entry(n, struct vm_area_struct, vm_rb); if (address >= vma->vm_start && address < vma->vm_end) { char _tmpbuf[256]; @@ -176,8 +179,6 @@ static void decode_address(char *buf, unsigned long address) goto done; } - - vml = vml->next; } if (!in_atomic) mmput(mm); diff --git a/arch/frv/kernel/ptrace.c b/arch/frv/kernel/ptrace.c index 709e9bdc6126..5e7d401d21e7 100644 --- a/arch/frv/kernel/ptrace.c +++ b/arch/frv/kernel/ptrace.c @@ -69,7 +69,8 @@ static inline int put_reg(struct task_struct *task, int regno, } /* - * check that an address falls within the bounds of the target process's memory mappings + * check that an address falls within the bounds of the target process's memory + * mappings */ static inline int is_user_addr_valid(struct task_struct *child, unsigned long start, unsigned long len) @@ -79,11 +80,11 @@ static inline int is_user_addr_valid(struct task_struct *child, return -EIO; return 0; #else - struct vm_list_struct *vml; + struct vm_area_struct *vma; - for (vml = child->mm->context.vmlist; vml; vml = vml->next) - if (start >= vml->vma->vm_start && start + len <= vml->vma->vm_end) - return 0; + vma = find_vma(child->mm, start); + if (vma && start >= vma->vm_start && start + len <= vma->vm_end) + return 0; return -EIO; #endif diff --git a/arch/h8300/include/asm/mmu.h b/arch/h8300/include/asm/mmu.h index 2ce06ea46104..31309969df70 100644 --- a/arch/h8300/include/asm/mmu.h +++ b/arch/h8300/include/asm/mmu.h @@ -4,7 +4,6 @@ /* Copyright (C) 2002, David McCullough */ typedef struct { - struct vm_list_struct *vmlist; unsigned long end_brk; } mm_context_t; diff --git a/arch/m68knommu/include/asm/mmu.h b/arch/m68knommu/include/asm/mmu.h index 5fa6b68353ba..e2da1e6f09fe 100644 --- a/arch/m68knommu/include/asm/mmu.h +++ b/arch/m68knommu/include/asm/mmu.h @@ -4,7 +4,6 @@ /* Copyright (C) 2002, David McCullough */ typedef struct { - struct vm_list_struct *vmlist; unsigned long end_brk; } mm_context_t; diff --git a/arch/sh/include/asm/mmu.h b/arch/sh/include/asm/mmu.h index fdcb93bc6d11..6c43625bb1a5 100644 --- a/arch/sh/include/asm/mmu.h +++ b/arch/sh/include/asm/mmu.h @@ -9,7 +9,6 @@ typedef struct { mm_context_id_t id; void *vdso; #else - struct vm_list_struct *vmlist; unsigned long end_brk; #endif #ifdef CONFIG_BINFMT_ELF_FDPIC diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index aa5b43205e37..22baf1b13493 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1567,11 +1567,9 @@ end_coredump: static int elf_fdpic_dump_segments(struct file *file, size_t *size, unsigned long *limit, unsigned long mm_flags) { - struct vm_list_struct *vml; - - for (vml = current->mm->context.vmlist; vml; vml = vml->next) { - struct vm_area_struct *vma = vml->vma; + struct vm_area_struct *vma; + for (vma = current->mm->mmap; vma; vma = vma->vm_next) { if (!maydump(vma, mm_flags)) continue; @@ -1617,9 +1615,6 @@ static int elf_fdpic_core_dump(long signr, struct pt_regs *regs, elf_fpxregset_t *xfpu = NULL; #endif int thread_status_size = 0; -#ifndef CONFIG_MMU - struct vm_list_struct *vml; -#endif elf_addr_t *auxv; unsigned long mm_flags; @@ -1685,13 +1680,7 @@ static int elf_fdpic_core_dump(long signr, struct pt_regs *regs, fill_prstatus(prstatus, current, signr); elf_core_copy_regs(&prstatus->pr_reg, regs); -#ifdef CONFIG_MMU segs = current->mm->map_count; -#else - segs = 0; - for (vml = current->mm->context.vmlist; vml; vml = vml->next) - segs++; -#endif #ifdef ELF_CORE_EXTRA_PHDRS segs += ELF_CORE_EXTRA_PHDRS; #endif @@ -1766,20 +1755,10 @@ static int elf_fdpic_core_dump(long signr, struct pt_regs *regs, mm_flags = current->mm->flags; /* write program headers for segments dump */ - for ( -#ifdef CONFIG_MMU - vma = current->mm->mmap; vma; vma = vma->vm_next -#else - vml = current->mm->context.vmlist; vml; vml = vml->next -#endif - ) { + for (vma = current->mm->mmap; vma; vma = vma->vm_next) { struct elf_phdr phdr; size_t sz; -#ifndef CONFIG_MMU - vma = vml->vma; -#endif - sz = vma->vm_end - vma->vm_start; phdr.p_type = PT_LOAD; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 3e8aeb8b61ce..cd53ff838498 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -41,8 +41,6 @@ do { \ (vmi)->used = 0; \ (vmi)->largest_chunk = 0; \ } while(0) - -extern int nommu_vma_show(struct seq_file *, struct vm_area_struct *); #endif extern int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns, diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index b1675c4e66da..43d23948384a 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -73,6 +73,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v) "HighFree: %8lu kB\n" "LowTotal: %8lu kB\n" "LowFree: %8lu kB\n" +#endif +#ifndef CONFIG_MMU + "MmapCopy: %8lu kB\n" #endif "SwapTotal: %8lu kB\n" "SwapFree: %8lu kB\n" @@ -115,6 +118,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v) K(i.freehigh), K(i.totalram-i.totalhigh), K(i.freeram-i.freehigh), +#endif +#ifndef CONFIG_MMU + K((unsigned long) atomic_read(&mmap_pages_allocated)), #endif K(i.totalswap), K(i.freeswap), diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index 3f87d2632947..b446d7ad0b0d 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -33,33 +33,33 @@ #include "internal.h" /* - * display a single VMA to a sequenced file + * display a single region to a sequenced file */ -int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) +static int nommu_region_show(struct seq_file *m, struct vm_region *region) { unsigned long ino = 0; struct file *file; dev_t dev = 0; int flags, len; - flags = vma->vm_flags; - file = vma->vm_file; + flags = region->vm_flags; + file = region->vm_file; if (file) { - struct inode *inode = vma->vm_file->f_path.dentry->d_inode; + struct inode *inode = region->vm_file->f_path.dentry->d_inode; dev = inode->i_sb->s_dev; ino = inode->i_ino; } seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n", - vma->vm_start, - vma->vm_end, + region->vm_start, + region->vm_end, flags & VM_READ ? 'r' : '-', flags & VM_WRITE ? 'w' : '-', flags & VM_EXEC ? 'x' : '-', flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p', - ((loff_t)vma->vm_pgoff) << PAGE_SHIFT, + ((loff_t)region->vm_pgoff) << PAGE_SHIFT, MAJOR(dev), MINOR(dev), ino, &len); if (file) { @@ -75,61 +75,54 @@ int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) } /* - * display a list of all the VMAs the kernel knows about + * display a list of all the REGIONs the kernel knows about * - nommu kernals have a single flat list */ -static int nommu_vma_list_show(struct seq_file *m, void *v) +static int nommu_region_list_show(struct seq_file *m, void *_p) { - struct vm_area_struct *vma; + struct rb_node *p = _p; - vma = rb_entry((struct rb_node *) v, struct vm_area_struct, vm_rb); - return nommu_vma_show(m, vma); + return nommu_region_show(m, rb_entry(p, struct vm_region, vm_rb)); } -static void *nommu_vma_list_start(struct seq_file *m, loff_t *_pos) +static void *nommu_region_list_start(struct seq_file *m, loff_t *_pos) { - struct rb_node *_rb; + struct rb_node *p; loff_t pos = *_pos; - void *next = NULL; - down_read(&nommu_vma_sem); + down_read(&nommu_region_sem); - for (_rb = rb_first(&nommu_vma_tree); _rb; _rb = rb_next(_rb)) { - if (pos == 0) { - next = _rb; - break; - } - pos--; - } - - return next; + for (p = rb_first(&nommu_region_tree); p; p = rb_next(p)) + if (pos-- == 0) + return p; + return NULL; } -static void nommu_vma_list_stop(struct seq_file *m, void *v) +static void nommu_region_list_stop(struct seq_file *m, void *v) { - up_read(&nommu_vma_sem); + up_read(&nommu_region_sem); } -static void *nommu_vma_list_next(struct seq_file *m, void *v, loff_t *pos) +static void *nommu_region_list_next(struct seq_file *m, void *v, loff_t *pos) { (*pos)++; return rb_next((struct rb_node *) v); } -static const struct seq_operations proc_nommu_vma_list_seqop = { - .start = nommu_vma_list_start, - .next = nommu_vma_list_next, - .stop = nommu_vma_list_stop, - .show = nommu_vma_list_show +static struct seq_operations proc_nommu_region_list_seqop = { + .start = nommu_region_list_start, + .next = nommu_region_list_next, + .stop = nommu_region_list_stop, + .show = nommu_region_list_show }; -static int proc_nommu_vma_list_open(struct inode *inode, struct file *file) +static int proc_nommu_region_list_open(struct inode *inode, struct file *file) { - return seq_open(file, &proc_nommu_vma_list_seqop); + return seq_open(file, &proc_nommu_region_list_seqop); } -static const struct file_operations proc_nommu_vma_list_operations = { - .open = proc_nommu_vma_list_open, +static const struct file_operations proc_nommu_region_list_operations = { + .open = proc_nommu_region_list_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, @@ -137,7 +130,7 @@ static const struct file_operations proc_nommu_vma_list_operations = { static int __init proc_nommu_init(void) { - proc_create("maps", S_IRUGO, NULL, &proc_nommu_vma_list_operations); + proc_create("maps", S_IRUGO, NULL, &proc_nommu_region_list_operations); return 0; } diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index d4a8be32b902..ca4a48d0d311 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -15,25 +15,25 @@ */ void task_mem(struct seq_file *m, struct mm_struct *mm) { - struct vm_list_struct *vml; + struct vm_area_struct *vma; + struct rb_node *p; unsigned long bytes = 0, sbytes = 0, slack = 0; down_read(&mm->mmap_sem); - for (vml = mm->context.vmlist; vml; vml = vml->next) { - if (!vml->vma) - continue; + for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) { + vma = rb_entry(p, struct vm_area_struct, vm_rb); - bytes += kobjsize(vml); + bytes += kobjsize(vma); if (atomic_read(&mm->mm_count) > 1 || - atomic_read(&vml->vma->vm_usage) > 1 - ) { - sbytes += kobjsize((void *) vml->vma->vm_start); - sbytes += kobjsize(vml->vma); + vma->vm_region || + vma->vm_flags & VM_MAYSHARE) { + sbytes += kobjsize((void *) vma->vm_start); + if (vma->vm_region) + sbytes += kobjsize(vma->vm_region); } else { - bytes += kobjsize((void *) vml->vma->vm_start); - bytes += kobjsize(vml->vma); - slack += kobjsize((void *) vml->vma->vm_start) - - (vml->vma->vm_end - vml->vma->vm_start); + bytes += kobjsize((void *) vma->vm_start); + slack += kobjsize((void *) vma->vm_start) - + (vma->vm_end - vma->vm_start); } } @@ -70,13 +70,14 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) unsigned long task_vsize(struct mm_struct *mm) { - struct vm_list_struct *tbp; + struct vm_area_struct *vma; + struct rb_node *p; unsigned long vsize = 0; down_read(&mm->mmap_sem); - for (tbp = mm->context.vmlist; tbp; tbp = tbp->next) { - if (tbp->vma) - vsize += kobjsize((void *) tbp->vma->vm_start); + for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) { + vma = rb_entry(p, struct vm_area_struct, vm_rb); + vsize += vma->vm_region->vm_end - vma->vm_region->vm_start; } up_read(&mm->mmap_sem); return vsize; @@ -85,16 +86,15 @@ unsigned long task_vsize(struct mm_struct *mm) int task_statm(struct mm_struct *mm, int *shared, int *text, int *data, int *resident) { - struct vm_list_struct *tbp; + struct vm_area_struct *vma; + struct rb_node *p; int size = kobjsize(mm); down_read(&mm->mmap_sem); - for (tbp = mm->context.vmlist; tbp; tbp = tbp->next) { - size += kobjsize(tbp); - if (tbp->vma) { - size += kobjsize(tbp->vma); - size += kobjsize((void *) tbp->vma->vm_start); - } + for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) { + vma = rb_entry(p, struct vm_area_struct, vm_rb); + size += kobjsize(vma); + size += kobjsize((void *) vma->vm_start); } size += (*text = mm->end_code - mm->start_code); @@ -104,21 +104,63 @@ int task_statm(struct mm_struct *mm, int *shared, int *text, return size; } +/* + * display a single VMA to a sequenced file + */ +static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) +{ + unsigned long ino = 0; + struct file *file; + dev_t dev = 0; + int flags, len; + + flags = vma->vm_flags; + file = vma->vm_file; + + if (file) { + struct inode *inode = vma->vm_file->f_path.dentry->d_inode; + dev = inode->i_sb->s_dev; + ino = inode->i_ino; + } + + seq_printf(m, + "%08lx-%08lx %c%c%c%c %08lx %02x:%02x %lu %n", + vma->vm_start, + vma->vm_end, + flags & VM_READ ? 'r' : '-', + flags & VM_WRITE ? 'w' : '-', + flags & VM_EXEC ? 'x' : '-', + flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p', + vma->vm_pgoff << PAGE_SHIFT, + MAJOR(dev), MINOR(dev), ino, &len); + + if (file) { + len = 25 + sizeof(void *) * 6 - len; + if (len < 1) + len = 1; + seq_printf(m, "%*c", len, ' '); + seq_path(m, &file->f_path, ""); + } + + seq_putc(m, '\n'); + return 0; +} + /* * display mapping lines for a particular process's /proc/pid/maps */ -static int show_map(struct seq_file *m, void *_vml) +static int show_map(struct seq_file *m, void *_p) { - struct vm_list_struct *vml = _vml; + struct rb_node *p = _p; - return nommu_vma_show(m, vml->vma); + return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb)); } static void *m_start(struct seq_file *m, loff_t *pos) { struct proc_maps_private *priv = m->private; - struct vm_list_struct *vml; struct mm_struct *mm; + struct rb_node *p; loff_t n = *pos; /* pin the task and mm whilst we play with them */ @@ -134,9 +176,9 @@ static void *m_start(struct seq_file *m, loff_t *pos) } /* start from the Nth VMA */ - for (vml = mm->context.vmlist; vml; vml = vml->next) + for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) if (n-- == 0) - return vml; + return p; return NULL; } @@ -152,12 +194,12 @@ static void m_stop(struct seq_file *m, void *_vml) } } -static void *m_next(struct seq_file *m, void *_vml, loff_t *pos) +static void *m_next(struct seq_file *m, void *_p, loff_t *pos) { - struct vm_list_struct *vml = _vml; + struct rb_node *p = _p; (*pos)++; - return vml ? vml->next : NULL; + return p ? rb_next(p) : NULL; } static const struct seq_operations proc_pid_maps_ops = { diff --git a/include/asm-frv/mmu.h b/include/asm-frv/mmu.h index 22c03714fb14..86ca0e86e7d2 100644 --- a/include/asm-frv/mmu.h +++ b/include/asm-frv/mmu.h @@ -22,7 +22,6 @@ typedef struct { unsigned long dtlb_ptd_mapping; /* [DAMR5] PTD mapping for dtlb cached PGE */ #else - struct vm_list_struct *vmlist; unsigned long end_brk; #endif diff --git a/include/asm-m32r/mmu.h b/include/asm-m32r/mmu.h index d9bd724479cf..150cb92bb666 100644 --- a/include/asm-m32r/mmu.h +++ b/include/asm-m32r/mmu.h @@ -4,7 +4,6 @@ #if !defined(CONFIG_MMU) typedef struct { - struct vm_list_struct *vmlist; unsigned long end_brk; } mm_context_t; diff --git a/include/linux/mm.h b/include/linux/mm.h index 4a3d28c86443..b91a73fd1bcc 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -56,19 +56,9 @@ extern unsigned long mmap_min_addr; extern struct kmem_cache *vm_area_cachep; -/* - * This struct defines the per-mm list of VMAs for uClinux. If CONFIG_MMU is - * disabled, then there's a single shared list of VMAs maintained by the - * system, and mm's subscribe to these individually - */ -struct vm_list_struct { - struct vm_list_struct *next; - struct vm_area_struct *vma; -}; - #ifndef CONFIG_MMU -extern struct rb_root nommu_vma_tree; -extern struct rw_semaphore nommu_vma_sem; +extern struct rb_root nommu_region_tree; +extern struct rw_semaphore nommu_region_sem; extern unsigned int kobjsize(const void *objp); #endif @@ -1061,6 +1051,7 @@ extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, enum memmap_context); extern void setup_per_zone_pages_min(void); extern void mem_init(void); +extern void __init mmap_init(void); extern void show_mem(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); @@ -1072,6 +1063,9 @@ extern void setup_per_cpu_pageset(void); static inline void setup_per_cpu_pageset(void) {} #endif +/* nommu.c */ +extern atomic_t mmap_pages_allocated; + /* prio_tree.c */ void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old); void vma_prio_tree_insert(struct vm_area_struct *, struct prio_tree_root *); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 9cfc9b627fdd..1c1e0d3a1714 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -96,6 +96,22 @@ struct page { #endif /* WANT_PAGE_VIRTUAL */ }; +/* + * A region containing a mapping of a non-memory backed file under NOMMU + * conditions. These are held in a global tree and are pinned by the VMAs that + * map parts of them. + */ +struct vm_region { + struct rb_node vm_rb; /* link in global region tree */ + unsigned long vm_flags; /* VMA vm_flags */ + unsigned long vm_start; /* start address of region */ + unsigned long vm_end; /* region initialised to here */ + unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */ + struct file *vm_file; /* the backing file or NULL */ + + atomic_t vm_usage; /* region usage count */ +}; + /* * This struct defines a memory VMM memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory @@ -152,7 +168,7 @@ struct vm_area_struct { unsigned long vm_truncate_count;/* truncate_count or restart_addr */ #ifndef CONFIG_MMU - atomic_t vm_usage; /* refcount (VMAs shared if !MMU) */ + struct vm_region *vm_region; /* NOMMU mapping region */ #endif #ifdef CONFIG_NUMA struct mempolicy *vm_policy; /* NUMA policy for the VMA */ diff --git a/ipc/shm.c b/ipc/shm.c index b125b560240e..d0ab5527bf45 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -990,6 +990,7 @@ asmlinkage long sys_shmdt(char __user *shmaddr) */ vma = find_vma(mm, addr); +#ifdef CONFIG_MMU while (vma) { next = vma->vm_next; @@ -1034,6 +1035,17 @@ asmlinkage long sys_shmdt(char __user *shmaddr) vma = next; } +#else /* CONFIG_MMU */ + /* under NOMMU conditions, the exact address to be destroyed must be + * given */ + retval = -EINVAL; + if (vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) { + do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start); + retval = 0; + } + +#endif + up_write(&mm->mmap_sem); return retval; } diff --git a/kernel/fork.c b/kernel/fork.c index 7b8f2a78be3d..0bce4a43bb37 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1481,12 +1481,10 @@ void __init proc_caches_init(void) fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); - vm_area_cachep = kmem_cache_create("vm_area_struct", - sizeof(struct vm_area_struct), 0, - SLAB_PANIC, NULL); mm_cachep = kmem_cache_create("mm_struct", sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + mmap_init(); } /* diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2e75478e9c69..d0a32aab03ff 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -512,6 +512,13 @@ config DEBUG_VIRTUAL If unsure, say N. +config DEBUG_NOMMU_REGIONS + bool "Debug the global anon/private NOMMU mapping region tree" + depends on DEBUG_KERNEL && !MMU + help + This option causes the global tree of anonymous and private mapping + regions to be regularly checked for invalid topology. + config DEBUG_WRITECOUNT bool "Debug filesystem writers count" depends on DEBUG_KERNEL diff --git a/mm/mmap.c b/mm/mmap.c index a910c045cfd4..749623196cb9 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2472,3 +2472,13 @@ void mm_drop_all_locks(struct mm_struct *mm) mutex_unlock(&mm_all_locks_mutex); } + +/* + * initialise the VMA slab + */ +void __init mmap_init(void) +{ + vm_area_cachep = kmem_cache_create("vm_area_struct", + sizeof(struct vm_area_struct), 0, + SLAB_PANIC, NULL); +} diff --git a/mm/nommu.c b/mm/nommu.c index 23f355bbe262..0d363dfcf10e 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -6,7 +6,7 @@ * * See Documentation/nommu-mmap.txt * - * Copyright (c) 2004-2005 David Howells + * Copyright (c) 2004-2008 David Howells * Copyright (c) 2000-2003 David McCullough * Copyright (c) 2000-2001 D Jeff Dionne * Copyright (c) 2002 Greg Ungerer @@ -33,6 +33,28 @@ #include #include #include +#include "internal.h" + +static inline __attribute__((format(printf, 1, 2))) +void no_printk(const char *fmt, ...) +{ +} + +#if 0 +#define kenter(FMT, ...) \ + printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__) +#define kleave(FMT, ...) \ + printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__) +#define kdebug(FMT, ...) \ + printk(KERN_DEBUG "xxx" FMT"yyy\n", ##__VA_ARGS__) +#else +#define kenter(FMT, ...) \ + no_printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__) +#define kleave(FMT, ...) \ + no_printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__) +#define kdebug(FMT, ...) \ + no_printk(KERN_DEBUG FMT"\n", ##__VA_ARGS__) +#endif #include "internal.h" @@ -46,12 +68,15 @@ int sysctl_overcommit_ratio = 50; /* default is 50% */ int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT; int heap_stack_gap = 0; +atomic_t mmap_pages_allocated; + EXPORT_SYMBOL(mem_map); EXPORT_SYMBOL(num_physpages); -/* list of shareable VMAs */ -struct rb_root nommu_vma_tree = RB_ROOT; -DECLARE_RWSEM(nommu_vma_sem); +/* list of mapped, potentially shareable regions */ +static struct kmem_cache *vm_region_jar; +struct rb_root nommu_region_tree = RB_ROOT; +DECLARE_RWSEM(nommu_region_sem); struct vm_operations_struct generic_file_vm_ops = { }; @@ -400,129 +425,174 @@ asmlinkage unsigned long sys_brk(unsigned long brk) return mm->brk = brk; } -#ifdef DEBUG -static void show_process_blocks(void) +/* + * initialise the VMA and region record slabs + */ +void __init mmap_init(void) { - struct vm_list_struct *vml; - - printk("Process blocks %d:", current->pid); - - for (vml = ¤t->mm->context.vmlist; vml; vml = vml->next) { - printk(" %p: %p", vml, vml->vma); - if (vml->vma) - printk(" (%d @%lx #%d)", - kobjsize((void *) vml->vma->vm_start), - vml->vma->vm_start, - atomic_read(&vml->vma->vm_usage)); - printk(vml->next ? " ->" : ".\n"); - } + vm_region_jar = kmem_cache_create("vm_region_jar", + sizeof(struct vm_region), 0, + SLAB_PANIC, NULL); + vm_area_cachep = kmem_cache_create("vm_area_struct", + sizeof(struct vm_area_struct), 0, + SLAB_PANIC, NULL); } -#endif /* DEBUG */ /* - * add a VMA into a process's mm_struct in the appropriate place in the list - * - should be called with mm->mmap_sem held writelocked + * validate the region tree + * - the caller must hold the region lock */ -static void add_vma_to_mm(struct mm_struct *mm, struct vm_list_struct *vml) +#ifdef CONFIG_DEBUG_NOMMU_REGIONS +static noinline void validate_nommu_regions(void) { - struct vm_list_struct **ppv; + struct vm_region *region, *last; + struct rb_node *p, *lastp; - for (ppv = ¤t->mm->context.vmlist; *ppv; ppv = &(*ppv)->next) - if ((*ppv)->vma->vm_start > vml->vma->vm_start) - break; + lastp = rb_first(&nommu_region_tree); + if (!lastp) + return; + + last = rb_entry(lastp, struct vm_region, vm_rb); + if (unlikely(last->vm_end <= last->vm_start)) + BUG(); + + while ((p = rb_next(lastp))) { + region = rb_entry(p, struct vm_region, vm_rb); + last = rb_entry(lastp, struct vm_region, vm_rb); + + if (unlikely(region->vm_end <= region->vm_start)) + BUG(); + if (unlikely(region->vm_start < last->vm_end)) + BUG(); - vml->next = *ppv; - *ppv = vml; + lastp = p; + } } +#else +#define validate_nommu_regions() do {} while(0) +#endif /* - * look up the first VMA in which addr resides, NULL if none - * - should be called with mm->mmap_sem at least held readlocked + * add a region into the global tree */ -struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) +static void add_nommu_region(struct vm_region *region) { - struct vm_list_struct *loop, *vml; + struct vm_region *pregion; + struct rb_node **p, *parent; - /* search the vm_start ordered list */ - vml = NULL; - for (loop = mm->context.vmlist; loop; loop = loop->next) { - if (loop->vma->vm_start > addr) - break; - vml = loop; + validate_nommu_regions(); + + BUG_ON(region->vm_start & ~PAGE_MASK); + + parent = NULL; + p = &nommu_region_tree.rb_node; + while (*p) { + parent = *p; + pregion = rb_entry(parent, struct vm_region, vm_rb); + if (region->vm_start < pregion->vm_start) + p = &(*p)->rb_left; + else if (region->vm_start > pregion->vm_start) + p = &(*p)->rb_right; + else if (pregion == region) + return; + else + BUG(); } - if (vml && vml->vma->vm_end > addr) - return vml->vma; + rb_link_node(®ion->vm_rb, parent, p); + rb_insert_color(®ion->vm_rb, &nommu_region_tree); - return NULL; + validate_nommu_regions(); } -EXPORT_SYMBOL(find_vma); /* - * find a VMA - * - we don't extend stack VMAs under NOMMU conditions + * delete a region from the global tree */ -struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr) +static void delete_nommu_region(struct vm_region *region) { - return find_vma(mm, addr); -} + BUG_ON(!nommu_region_tree.rb_node); -int expand_stack(struct vm_area_struct *vma, unsigned long address) -{ - return -ENOMEM; + validate_nommu_regions(); + rb_erase(®ion->vm_rb, &nommu_region_tree); + validate_nommu_regions(); } /* - * look up the first VMA exactly that exactly matches addr - * - should be called with mm->mmap_sem at least held readlocked + * free a contiguous series of pages */ -static inline struct vm_area_struct *find_vma_exact(struct mm_struct *mm, - unsigned long addr) +static void free_page_series(unsigned long from, unsigned long to) { - struct vm_list_struct *vml; - - /* search the vm_start ordered list */ - for (vml = mm->context.vmlist; vml; vml = vml->next) { - if (vml->vma->vm_start == addr) - return vml->vma; - if (vml->vma->vm_start > addr) - break; + for (; from < to; from += PAGE_SIZE) { + struct page *page = virt_to_page(from); + + kdebug("- free %lx", from); + atomic_dec(&mmap_pages_allocated); + if (page_count(page) != 1) + kdebug("free page %p [%d]", page, page_count(page)); + put_page(page); } - - return NULL; } /* - * find a VMA in the global tree + * release a reference to a region + * - the caller must hold the region semaphore, which this releases + * - the region may not have been added to the tree yet, in which case vm_end + * will equal vm_start */ -static inline struct vm_area_struct *find_nommu_vma(unsigned long start) +static void __put_nommu_region(struct vm_region *region) + __releases(nommu_region_sem) { - struct vm_area_struct *vma; - struct rb_node *n = nommu_vma_tree.rb_node; + kenter("%p{%d}", region, atomic_read(®ion->vm_usage)); - while (n) { - vma = rb_entry(n, struct vm_area_struct, vm_rb); + BUG_ON(!nommu_region_tree.rb_node); - if (start < vma->vm_start) - n = n->rb_left; - else if (start > vma->vm_start) - n = n->rb_right; - else - return vma; + if (atomic_dec_and_test(®ion->vm_usage)) { + if (region->vm_end > region->vm_start) + delete_nommu_region(region); + up_write(&nommu_region_sem); + + if (region->vm_file) + fput(region->vm_file); + + /* IO memory and memory shared directly out of the pagecache + * from ramfs/tmpfs mustn't be released here */ + if (region->vm_flags & VM_MAPPED_COPY) { + kdebug("free series"); + free_page_series(region->vm_start, region->vm_end); + } + kmem_cache_free(vm_region_jar, region); + } else { + up_write(&nommu_region_sem); } +} - return NULL; +/* + * release a reference to a region + */ +static void put_nommu_region(struct vm_region *region) +{ + down_write(&nommu_region_sem); + __put_nommu_region(region); } /* - * add a VMA in the global tree + * add a VMA into a process's mm_struct in the appropriate place in the list + * and tree and add to the address space's page tree also if not an anonymous + * page + * - should be called with mm->mmap_sem held writelocked */ -static void add_nommu_vma(struct vm_area_struct *vma) +static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma) { - struct vm_area_struct *pvma; + struct vm_area_struct *pvma, **pp; struct address_space *mapping; - struct rb_node **p = &nommu_vma_tree.rb_node; - struct rb_node *parent = NULL; + struct rb_node **p, *parent; + + kenter(",%p", vma); + + BUG_ON(!vma->vm_region); + + mm->map_count++; + vma->vm_mm = mm; /* add the VMA to the mapping */ if (vma->vm_file) { @@ -533,42 +603,62 @@ static void add_nommu_vma(struct vm_area_struct *vma) flush_dcache_mmap_unlock(mapping); } - /* add the VMA to the master list */ + /* add the VMA to the tree */ + parent = NULL; + p = &mm->mm_rb.rb_node; while (*p) { parent = *p; pvma = rb_entry(parent, struct vm_area_struct, vm_rb); - if (vma->vm_start < pvma->vm_start) { + /* sort by: start addr, end addr, VMA struct addr in that order + * (the latter is necessary as we may get identical VMAs) */ + if (vma->vm_start < pvma->vm_start) p = &(*p)->rb_left; - } - else if (vma->vm_start > pvma->vm_start) { + else if (vma->vm_start > pvma->vm_start) p = &(*p)->rb_right; - } - else { - /* mappings are at the same address - this can only - * happen for shared-mem chardevs and shared file - * mappings backed by ramfs/tmpfs */ - BUG_ON(!(pvma->vm_flags & VM_SHARED)); - - if (vma < pvma) - p = &(*p)->rb_left; - else if (vma > pvma) - p = &(*p)->rb_right; - else - BUG(); - } + else if (vma->vm_end < pvma->vm_end) + p = &(*p)->rb_left; + else if (vma->vm_end > pvma->vm_end) + p = &(*p)->rb_right; + else if (vma < pvma) + p = &(*p)->rb_left; + else if (vma > pvma) + p = &(*p)->rb_right; + else + BUG(); } rb_link_node(&vma->vm_rb, parent, p); - rb_insert_color(&vma->vm_rb, &nommu_vma_tree); + rb_insert_color(&vma->vm_rb, &mm->mm_rb); + + /* add VMA to the VMA list also */ + for (pp = &mm->mmap; (pvma = *pp); pp = &(*pp)->vm_next) { + if (pvma->vm_start > vma->vm_start) + break; + if (pvma->vm_start < vma->vm_start) + continue; + if (pvma->vm_end < vma->vm_end) + break; + } + + vma->vm_next = *pp; + *pp = vma; } /* - * delete a VMA from the global list + * delete a VMA from its owning mm_struct and address space */ -static void delete_nommu_vma(struct vm_area_struct *vma) +static void delete_vma_from_mm(struct vm_area_struct *vma) { + struct vm_area_struct **pp; struct address_space *mapping; + struct mm_struct *mm = vma->vm_mm; + + kenter("%p", vma); + + mm->map_count--; + if (mm->mmap_cache == vma) + mm->mmap_cache = NULL; /* remove the VMA from the mapping */ if (vma->vm_file) { @@ -579,8 +669,115 @@ static void delete_nommu_vma(struct vm_area_struct *vma) flush_dcache_mmap_unlock(mapping); } - /* remove from the master list */ - rb_erase(&vma->vm_rb, &nommu_vma_tree); + /* remove from the MM's tree and list */ + rb_erase(&vma->vm_rb, &mm->mm_rb); + for (pp = &mm->mmap; *pp; pp = &(*pp)->vm_next) { + if (*pp == vma) { + *pp = vma->vm_next; + break; + } + } + + vma->vm_mm = NULL; +} + +/* + * destroy a VMA record + */ +static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma) +{ + kenter("%p", vma); + if (vma->vm_ops && vma->vm_ops->close) + vma->vm_ops->close(vma); + if (vma->vm_file) { + fput(vma->vm_file); + if (vma->vm_flags & VM_EXECUTABLE) + removed_exe_file_vma(mm); + } + put_nommu_region(vma->vm_region); + kmem_cache_free(vm_area_cachep, vma); +} + +/* + * look up the first VMA in which addr resides, NULL if none + * - should be called with mm->mmap_sem at least held readlocked + */ +struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) +{ + struct vm_area_struct *vma; + struct rb_node *n = mm->mm_rb.rb_node; + + /* check the cache first */ + vma = mm->mmap_cache; + if (vma && vma->vm_start <= addr && vma->vm_end > addr) + return vma; + + /* trawl the tree (there may be multiple mappings in which addr + * resides) */ + for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) { + vma = rb_entry(n, struct vm_area_struct, vm_rb); + if (vma->vm_start > addr) + return NULL; + if (vma->vm_end > addr) { + mm->mmap_cache = vma; + return vma; + } + } + + return NULL; +} +EXPORT_SYMBOL(find_vma); + +/* + * find a VMA + * - we don't extend stack VMAs under NOMMU conditions + */ +struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr) +{ + return find_vma(mm, addr); +} + +/* + * expand a stack to a given address + * - not supported under NOMMU conditions + */ +int expand_stack(struct vm_area_struct *vma, unsigned long address) +{ + return -ENOMEM; +} + +/* + * look up the first VMA exactly that exactly matches addr + * - should be called with mm->mmap_sem at least held readlocked + */ +static struct vm_area_struct *find_vma_exact(struct mm_struct *mm, + unsigned long addr, + unsigned long len) +{ + struct vm_area_struct *vma; + struct rb_node *n = mm->mm_rb.rb_node; + unsigned long end = addr + len; + + /* check the cache first */ + vma = mm->mmap_cache; + if (vma && vma->vm_start == addr && vma->vm_end == end) + return vma; + + /* trawl the tree (there may be multiple mappings in which addr + * resides) */ + for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) { + vma = rb_entry(n, struct vm_area_struct, vm_rb); + if (vma->vm_start < addr) + continue; + if (vma->vm_start > addr) + return NULL; + if (vma->vm_end == end) { + mm->mmap_cache = vma; + return vma; + } + } + + return NULL; } /* @@ -595,7 +792,7 @@ static int validate_mmap_request(struct file *file, unsigned long pgoff, unsigned long *_capabilities) { - unsigned long capabilities; + unsigned long capabilities, rlen; unsigned long reqprot = prot; int ret; @@ -615,12 +812,12 @@ static int validate_mmap_request(struct file *file, return -EINVAL; /* Careful about overflows.. */ - len = PAGE_ALIGN(len); - if (!len || len > TASK_SIZE) + rlen = PAGE_ALIGN(len); + if (!rlen || rlen > TASK_SIZE) return -ENOMEM; /* offset overflow? */ - if ((pgoff + (len >> PAGE_SHIFT)) < pgoff) + if ((pgoff + (rlen >> PAGE_SHIFT)) < pgoff) return -EOVERFLOW; if (file) { @@ -794,9 +991,10 @@ static unsigned long determine_vm_flags(struct file *file, } /* - * set up a shared mapping on a file + * set up a shared mapping on a file (the driver or filesystem provides and + * pins the storage) */ -static int do_mmap_shared_file(struct vm_area_struct *vma, unsigned long len) +static int do_mmap_shared_file(struct vm_area_struct *vma) { int ret; @@ -814,10 +1012,14 @@ static int do_mmap_shared_file(struct vm_area_struct *vma, unsigned long len) /* * set up a private mapping or an anonymous shared mapping */ -static int do_mmap_private(struct vm_area_struct *vma, unsigned long len) +static int do_mmap_private(struct vm_area_struct *vma, + struct vm_region *region, + unsigned long len) { + struct page *pages; + unsigned long total, point, n, rlen; void *base; - int ret; + int ret, order; /* invoke the file's mapping function so that it can keep track of * shared mappings on devices or memory @@ -836,23 +1038,46 @@ static int do_mmap_private(struct vm_area_struct *vma, unsigned long len) * make a private copy of the data and map that instead */ } + rlen = PAGE_ALIGN(len); + /* allocate some memory to hold the mapping * - note that this may not return a page-aligned address if the object * we're allocating is smaller than a page */ - base = kmalloc(len, GFP_KERNEL|__GFP_COMP); - if (!base) + order = get_order(rlen); + kdebug("alloc order %d for %lx", order, len); + + pages = alloc_pages(GFP_KERNEL, order); + if (!pages) goto enomem; - vma->vm_start = (unsigned long) base; - vma->vm_end = vma->vm_start + len; - vma->vm_flags |= VM_MAPPED_COPY; + /* we allocated a power-of-2 sized page set, so we need to trim off the + * excess */ + total = 1 << order; + atomic_add(total, &mmap_pages_allocated); + + point = rlen >> PAGE_SHIFT; + while (total > point) { + order = ilog2(total - point); + n = 1 << order; + kdebug("shave %lu/%lu @%lu", n, total - point, total); + atomic_sub(n, &mmap_pages_allocated); + total -= n; + set_page_refcounted(pages + total); + __free_pages(pages + total, order); + } + + total = rlen >> PAGE_SHIFT; + for (point = 1; point < total; point++) + set_page_refcounted(&pages[point]); -#ifdef WARN_ON_SLACK - if (len + WARN_ON_SLACK <= kobjsize(result)) - printk("Allocation of %lu bytes from process %d has %lu bytes of slack\n", - len, current->pid, kobjsize(result) - len); -#endif + base = page_address(pages); + region->vm_flags = vma->vm_flags |= VM_MAPPED_COPY; + region->vm_start = (unsigned long) base; + region->vm_end = region->vm_start + rlen; + + vma->vm_start = region->vm_start; + vma->vm_end = region->vm_start + len; if (vma->vm_file) { /* read the contents of a file into the copy */ @@ -864,26 +1089,27 @@ static int do_mmap_private(struct vm_area_struct *vma, unsigned long len) old_fs = get_fs(); set_fs(KERNEL_DS); - ret = vma->vm_file->f_op->read(vma->vm_file, base, len, &fpos); + ret = vma->vm_file->f_op->read(vma->vm_file, base, rlen, &fpos); set_fs(old_fs); if (ret < 0) goto error_free; /* clear the last little bit */ - if (ret < len) - memset(base + ret, 0, len - ret); + if (ret < rlen) + memset(base + ret, 0, rlen - ret); } else { /* if it's an anonymous mapping, then just clear it */ - memset(base, 0, len); + memset(base, 0, rlen); } return 0; error_free: - kfree(base); - vma->vm_start = 0; + free_page_series(region->vm_start, region->vm_end); + region->vm_start = vma->vm_start = 0; + region->vm_end = vma->vm_end = 0; return ret; enomem: @@ -903,13 +1129,14 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long flags, unsigned long pgoff) { - struct vm_list_struct *vml = NULL; - struct vm_area_struct *vma = NULL; + struct vm_area_struct *vma; + struct vm_region *region; struct rb_node *rb; - unsigned long capabilities, vm_flags; - void *result; + unsigned long capabilities, vm_flags, result; int ret; + kenter(",%lx,%lx,%lx,%lx,%lx", addr, len, prot, flags, pgoff); + if (!(flags & MAP_FIXED)) addr = round_hint_to_min(addr); @@ -917,73 +1144,120 @@ unsigned long do_mmap_pgoff(struct file *file, * mapping */ ret = validate_mmap_request(file, addr, len, prot, flags, pgoff, &capabilities); - if (ret < 0) + if (ret < 0) { + kleave(" = %d [val]", ret); return ret; + } /* we've determined that we can make the mapping, now translate what we * now know into VMA flags */ vm_flags = determine_vm_flags(file, prot, flags, capabilities); - /* we're going to need to record the mapping if it works */ - vml = kzalloc(sizeof(struct vm_list_struct), GFP_KERNEL); - if (!vml) - goto error_getting_vml; + /* we're going to need to record the mapping */ + region = kmem_cache_zalloc(vm_region_jar, GFP_KERNEL); + if (!region) + goto error_getting_region; + + vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + if (!vma) + goto error_getting_vma; + + atomic_set(®ion->vm_usage, 1); + region->vm_flags = vm_flags; + region->vm_pgoff = pgoff; - down_write(&nommu_vma_sem); + INIT_LIST_HEAD(&vma->anon_vma_node); + vma->vm_flags = vm_flags; + vma->vm_pgoff = pgoff; - /* if we want to share, we need to check for VMAs created by other + if (file) { + region->vm_file = file; + get_file(file); + vma->vm_file = file; + get_file(file); + if (vm_flags & VM_EXECUTABLE) { + added_exe_file_vma(current->mm); + vma->vm_mm = current->mm; + } + } + + down_write(&nommu_region_sem); + + /* if we want to share, we need to check for regions created by other * mmap() calls that overlap with our proposed mapping - * - we can only share with an exact match on most regular files + * - we can only share with a superset match on most regular files * - shared mappings on character devices and memory backed files are * permitted to overlap inexactly as far as we are concerned for in * these cases, sharing is handled in the driver or filesystem rather * than here */ if (vm_flags & VM_MAYSHARE) { - unsigned long pglen = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; - unsigned long vmpglen; + struct vm_region *pregion; + unsigned long pglen, rpglen, pgend, rpgend, start; - /* suppress VMA sharing for shared regions */ - if (vm_flags & VM_SHARED && - capabilities & BDI_CAP_MAP_DIRECT) - goto dont_share_VMAs; + pglen = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; + pgend = pgoff + pglen; - for (rb = rb_first(&nommu_vma_tree); rb; rb = rb_next(rb)) { - vma = rb_entry(rb, struct vm_area_struct, vm_rb); + for (rb = rb_first(&nommu_region_tree); rb; rb = rb_next(rb)) { + pregion = rb_entry(rb, struct vm_region, vm_rb); - if (!(vma->vm_flags & VM_MAYSHARE)) + if (!(pregion->vm_flags & VM_MAYSHARE)) continue; /* search for overlapping mappings on the same file */ - if (vma->vm_file->f_path.dentry->d_inode != file->f_path.dentry->d_inode) + if (pregion->vm_file->f_path.dentry->d_inode != + file->f_path.dentry->d_inode) continue; - if (vma->vm_pgoff >= pgoff + pglen) + if (pregion->vm_pgoff >= pgend) continue; - vmpglen = vma->vm_end - vma->vm_start + PAGE_SIZE - 1; - vmpglen >>= PAGE_SHIFT; - if (pgoff >= vma->vm_pgoff + vmpglen) + rpglen = pregion->vm_end - pregion->vm_start; + rpglen = (rpglen + PAGE_SIZE - 1) >> PAGE_SHIFT; + rpgend = pregion->vm_pgoff + rpglen; + if (pgoff >= rpgend) continue; - /* handle inexactly overlapping matches between mappings */ - if (vma->vm_pgoff != pgoff || vmpglen != pglen) { + /* handle inexactly overlapping matches between + * mappings */ + if ((pregion->vm_pgoff != pgoff || rpglen != pglen) && + !(pgoff >= pregion->vm_pgoff && pgend <= rpgend)) { + /* new mapping is not a subset of the region */ if (!(capabilities & BDI_CAP_MAP_DIRECT)) goto sharing_violation; continue; } - /* we've found a VMA we can share */ - atomic_inc(&vma->vm_usage); - - vml->vma = vma; - result = (void *) vma->vm_start; - goto shared; + /* we've found a region we can share */ + atomic_inc(&pregion->vm_usage); + vma->vm_region = pregion; + start = pregion->vm_start; + start += (pgoff - pregion->vm_pgoff) << PAGE_SHIFT; + vma->vm_start = start; + vma->vm_end = start + len; + + if (pregion->vm_flags & VM_MAPPED_COPY) { + kdebug("share copy"); + vma->vm_flags |= VM_MAPPED_COPY; + } else { + kdebug("share mmap"); + ret = do_mmap_shared_file(vma); + if (ret < 0) { + vma->vm_region = NULL; + vma->vm_start = 0; + vma->vm_end = 0; + atomic_dec(&pregion->vm_usage); + pregion = NULL; + goto error_just_free; + } + } + fput(region->vm_file); + kmem_cache_free(vm_region_jar, region); + region = pregion; + result = start; + goto share; } - dont_share_VMAs: - vma = NULL; - /* obtain the address at which to make a shared mapping * - this is the hook for quasi-memory character devices to * tell us the location of a shared mapping @@ -994,102 +1268,93 @@ unsigned long do_mmap_pgoff(struct file *file, if (IS_ERR((void *) addr)) { ret = addr; if (ret != (unsigned long) -ENOSYS) - goto error; + goto error_just_free; /* the driver refused to tell us where to site * the mapping so we'll have to attempt to copy * it */ ret = (unsigned long) -ENODEV; if (!(capabilities & BDI_CAP_MAP_COPY)) - goto error; + goto error_just_free; capabilities &= ~BDI_CAP_MAP_DIRECT; + } else { + vma->vm_start = region->vm_start = addr; + vma->vm_end = region->vm_end = addr + len; } } } - /* we're going to need a VMA struct as well */ - vma = kzalloc(sizeof(struct vm_area_struct), GFP_KERNEL); - if (!vma) - goto error_getting_vma; - - INIT_LIST_HEAD(&vma->anon_vma_node); - atomic_set(&vma->vm_usage, 1); - if (file) { - get_file(file); - if (vm_flags & VM_EXECUTABLE) { - added_exe_file_vma(current->mm); - vma->vm_mm = current->mm; - } - } - vma->vm_file = file; - vma->vm_flags = vm_flags; - vma->vm_start = addr; - vma->vm_end = addr + len; - vma->vm_pgoff = pgoff; - - vml->vma = vma; + vma->vm_region = region; /* set up the mapping */ if (file && vma->vm_flags & VM_SHARED) - ret = do_mmap_shared_file(vma, len); + ret = do_mmap_shared_file(vma); else - ret = do_mmap_private(vma, len); + ret = do_mmap_private(vma, region, len); if (ret < 0) - goto error; + goto error_put_region; + + add_nommu_region(region); /* okay... we have a mapping; now we have to register it */ - result = (void *) vma->vm_start; + result = vma->vm_start; current->mm->total_vm += len >> PAGE_SHIFT; - add_nommu_vma(vma); +share: + add_vma_to_mm(current->mm, vma); - shared: - add_vma_to_mm(current->mm, vml); - - up_write(&nommu_vma_sem); + up_write(&nommu_region_sem); if (prot & PROT_EXEC) - flush_icache_range((unsigned long) result, - (unsigned long) result + len); + flush_icache_range(result, result + len); -#ifdef DEBUG - printk("do_mmap:\n"); - show_process_blocks(); -#endif + kleave(" = %lx", result); + return result; - return (unsigned long) result; - - error: - up_write(&nommu_vma_sem); - kfree(vml); +error_put_region: + __put_nommu_region(region); if (vma) { if (vma->vm_file) { fput(vma->vm_file); if (vma->vm_flags & VM_EXECUTABLE) removed_exe_file_vma(vma->vm_mm); } - kfree(vma); + kmem_cache_free(vm_area_cachep, vma); } + kleave(" = %d [pr]", ret); return ret; - sharing_violation: - up_write(&nommu_vma_sem); - printk("Attempt to share mismatched mappings\n"); - kfree(vml); - return -EINVAL; +error_just_free: + up_write(&nommu_region_sem); +error: + fput(region->vm_file); + kmem_cache_free(vm_region_jar, region); + fput(vma->vm_file); + if (vma->vm_flags & VM_EXECUTABLE) + removed_exe_file_vma(vma->vm_mm); + kmem_cache_free(vm_area_cachep, vma); + kleave(" = %d", ret); + return ret; + +sharing_violation: + up_write(&nommu_region_sem); + printk(KERN_WARNING "Attempt to share mismatched mappings\n"); + ret = -EINVAL; + goto error; - error_getting_vma: - up_write(&nommu_vma_sem); - kfree(vml); - printk("Allocation of vma for %lu byte allocation from process %d failed\n", +error_getting_vma: + kmem_cache_free(vm_region_jar, region); + printk(KERN_WARNING "Allocation of vma for %lu byte allocation" + " from process %d failed\n", len, current->pid); show_free_areas(); return -ENOMEM; - error_getting_vml: - printk("Allocation of vml for %lu byte allocation from process %d failed\n", +error_getting_region: + printk(KERN_WARNING "Allocation of vm region for %lu byte allocation" + " from process %d failed\n", len, current->pid); show_free_areas(); return -ENOMEM; @@ -1097,77 +1362,180 @@ unsigned long do_mmap_pgoff(struct file *file, EXPORT_SYMBOL(do_mmap_pgoff); /* - * handle mapping disposal for uClinux + * split a vma into two pieces at address 'addr', a new vma is allocated either + * for the first part or the tail. */ -static void put_vma(struct mm_struct *mm, struct vm_area_struct *vma) +int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, int new_below) { - if (vma) { - down_write(&nommu_vma_sem); + struct vm_area_struct *new; + struct vm_region *region; + unsigned long npages; - if (atomic_dec_and_test(&vma->vm_usage)) { - delete_nommu_vma(vma); + kenter(""); - if (vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); + /* we're only permitted to split anonymous regions that have a single + * owner */ + if (vma->vm_file || + atomic_read(&vma->vm_region->vm_usage) != 1) + return -ENOMEM; - /* IO memory and memory shared directly out of the pagecache from - * ramfs/tmpfs mustn't be released here */ - if (vma->vm_flags & VM_MAPPED_COPY) - kfree((void *) vma->vm_start); + if (mm->map_count >= sysctl_max_map_count) + return -ENOMEM; - if (vma->vm_file) { - fput(vma->vm_file); - if (vma->vm_flags & VM_EXECUTABLE) - removed_exe_file_vma(mm); - } - kfree(vma); - } + region = kmem_cache_alloc(vm_region_jar, GFP_KERNEL); + if (!region) + return -ENOMEM; + + new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + if (!new) { + kmem_cache_free(vm_region_jar, region); + return -ENOMEM; + } + + /* most fields are the same, copy all, and then fixup */ + *new = *vma; + *region = *vma->vm_region; + new->vm_region = region; + + npages = (addr - vma->vm_start) >> PAGE_SHIFT; + + if (new_below) { + region->vm_end = new->vm_end = addr; + } else { + region->vm_start = new->vm_start = addr; + region->vm_pgoff = new->vm_pgoff += npages; + } - up_write(&nommu_vma_sem); + if (new->vm_ops && new->vm_ops->open) + new->vm_ops->open(new); + + delete_vma_from_mm(vma); + down_write(&nommu_region_sem); + delete_nommu_region(vma->vm_region); + if (new_below) { + vma->vm_region->vm_start = vma->vm_start = addr; + vma->vm_region->vm_pgoff = vma->vm_pgoff += npages; + } else { + vma->vm_region->vm_end = vma->vm_end = addr; } + add_nommu_region(vma->vm_region); + add_nommu_region(new->vm_region); + up_write(&nommu_region_sem); + add_vma_to_mm(mm, vma); + add_vma_to_mm(mm, new); + return 0; } /* - * release a mapping - * - under NOMMU conditions the parameters must match exactly to the mapping to - * be removed + * shrink a VMA by removing the specified chunk from either the beginning or + * the end */ -int do_munmap(struct mm_struct *mm, unsigned long addr, size_t len) +static int shrink_vma(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long from, unsigned long to) { - struct vm_list_struct *vml, **parent; - unsigned long end = addr + len; + struct vm_region *region; -#ifdef DEBUG - printk("do_munmap:\n"); -#endif + kenter(""); - for (parent = &mm->context.vmlist; *parent; parent = &(*parent)->next) { - if ((*parent)->vma->vm_start > addr) - break; - if ((*parent)->vma->vm_start == addr && - ((len == 0) || ((*parent)->vma->vm_end == end))) - goto found; - } + /* adjust the VMA's pointers, which may reposition it in the MM's tree + * and list */ + delete_vma_from_mm(vma); + if (from > vma->vm_start) + vma->vm_end = from; + else + vma->vm_start = to; + add_vma_to_mm(mm, vma); - printk("munmap of non-mmaped memory by process %d (%s): %p\n", - current->pid, current->comm, (void *) addr); - return -EINVAL; + /* cut the backing region down to size */ + region = vma->vm_region; + BUG_ON(atomic_read(®ion->vm_usage) != 1); - found: - vml = *parent; + down_write(&nommu_region_sem); + delete_nommu_region(region); + if (from > region->vm_start) + region->vm_end = from; + else + region->vm_start = to; + add_nommu_region(region); + up_write(&nommu_region_sem); - put_vma(mm, vml->vma); + free_page_series(from, to); + return 0; +} - *parent = vml->next; - kfree(vml); +/* + * release a mapping + * - under NOMMU conditions the chunk to be unmapped must be backed by a single + * VMA, though it need not cover the whole VMA + */ +int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) +{ + struct vm_area_struct *vma; + struct rb_node *rb; + unsigned long end = start + len; + int ret; - update_hiwater_vm(mm); - mm->total_vm -= len >> PAGE_SHIFT; + kenter(",%lx,%zx", start, len); -#ifdef DEBUG - show_process_blocks(); -#endif + if (len == 0) + return -EINVAL; + + /* find the first potentially overlapping VMA */ + vma = find_vma(mm, start); + if (!vma) { + printk(KERN_WARNING + "munmap of memory not mmapped by process %d (%s):" + " 0x%lx-0x%lx\n", + current->pid, current->comm, start, start + len - 1); + return -EINVAL; + } + /* we're allowed to split an anonymous VMA but not a file-backed one */ + if (vma->vm_file) { + do { + if (start > vma->vm_start) { + kleave(" = -EINVAL [miss]"); + return -EINVAL; + } + if (end == vma->vm_end) + goto erase_whole_vma; + rb = rb_next(&vma->vm_rb); + vma = rb_entry(rb, struct vm_area_struct, vm_rb); + } while (rb); + kleave(" = -EINVAL [split file]"); + return -EINVAL; + } else { + /* the chunk must be a subset of the VMA found */ + if (start == vma->vm_start && end == vma->vm_end) + goto erase_whole_vma; + if (start < vma->vm_start || end > vma->vm_end) { + kleave(" = -EINVAL [superset]"); + return -EINVAL; + } + if (start & ~PAGE_MASK) { + kleave(" = -EINVAL [unaligned start]"); + return -EINVAL; + } + if (end != vma->vm_end && end & ~PAGE_MASK) { + kleave(" = -EINVAL [unaligned split]"); + return -EINVAL; + } + if (start != vma->vm_start && end != vma->vm_end) { + ret = split_vma(mm, vma, start, 1); + if (ret < 0) { + kleave(" = %d [split]", ret); + return ret; + } + } + return shrink_vma(mm, vma, start, end); + } + +erase_whole_vma: + delete_vma_from_mm(vma); + delete_vma(mm, vma); + kleave(" = 0"); return 0; } EXPORT_SYMBOL(do_munmap); @@ -1184,29 +1552,26 @@ asmlinkage long sys_munmap(unsigned long addr, size_t len) } /* - * Release all mappings + * release all the mappings made in a process's VM space */ -void exit_mmap(struct mm_struct * mm) +void exit_mmap(struct mm_struct *mm) { - struct vm_list_struct *tmp; + struct vm_area_struct *vma; - if (mm) { -#ifdef DEBUG - printk("Exit_mmap:\n"); -#endif + if (!mm) + return; - mm->total_vm = 0; + kenter(""); - while ((tmp = mm->context.vmlist)) { - mm->context.vmlist = tmp->next; - put_vma(mm, tmp->vma); - kfree(tmp); - } + mm->total_vm = 0; -#ifdef DEBUG - show_process_blocks(); -#endif + while ((vma = mm->mmap)) { + mm->mmap = vma->vm_next; + delete_vma_from_mm(vma); + delete_vma(mm, vma); } + + kleave(""); } unsigned long do_brk(unsigned long addr, unsigned long len) @@ -1219,8 +1584,8 @@ unsigned long do_brk(unsigned long addr, unsigned long len) * time (controlled by the MREMAP_MAYMOVE flag and available VM space) * * under NOMMU conditions, we only permit changing a mapping's size, and only - * as long as it stays within the hole allocated by the kmalloc() call in - * do_mmap_pgoff() and the block is not shareable + * as long as it stays within the region allocated by do_mmap_private() and the + * block is not shareable * * MREMAP_FIXED is not supported under NOMMU conditions */ @@ -1231,13 +1596,16 @@ unsigned long do_mremap(unsigned long addr, struct vm_area_struct *vma; /* insanity checks first */ - if (new_len == 0) + if (old_len == 0 || new_len == 0) return (unsigned long) -EINVAL; + if (addr & ~PAGE_MASK) + return -EINVAL; + if (flags & MREMAP_FIXED && new_addr != addr) return (unsigned long) -EINVAL; - vma = find_vma_exact(current->mm, addr); + vma = find_vma_exact(current->mm, addr, old_len); if (!vma) return (unsigned long) -EINVAL; @@ -1247,19 +1615,19 @@ unsigned long do_mremap(unsigned long addr, if (vma->vm_flags & VM_MAYSHARE) return (unsigned long) -EPERM; - if (new_len > kobjsize((void *) addr)) + if (new_len > vma->vm_region->vm_end - vma->vm_region->vm_start) return (unsigned long) -ENOMEM; /* all checks complete - do it */ vma->vm_end = vma->vm_start + new_len; - return vma->vm_start; } EXPORT_SYMBOL(do_mremap); -asmlinkage unsigned long sys_mremap(unsigned long addr, - unsigned long old_len, unsigned long new_len, - unsigned long flags, unsigned long new_addr) +asmlinkage +unsigned long sys_mremap(unsigned long addr, + unsigned long old_len, unsigned long new_len, + unsigned long flags, unsigned long new_addr) { unsigned long ret; -- cgit v1.2.3 From dd8632a12e500a684478fea0951f380478d56fed Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Thu, 8 Jan 2009 12:04:47 +0000 Subject: NOMMU: Make mmap allocation page trimming behaviour configurable. NOMMU mmap allocates a piece of memory for an mmap that's rounded up in size to the nearest power-of-2 number of pages. Currently it then discards the excess pages back to the page allocator, making that memory available for use by other things. This can, however, cause greater amount of fragmentation. To counter this, a sysctl is added in order to fine-tune the trimming behaviour. The default behaviour remains to trim pages aggressively, while this can either be disabled completely or set to a higher page-granular watermark in order to have finer-grained control. vm region vm_top bits taken from an earlier patch by David Howells. Signed-off-by: Paul Mundt Signed-off-by: David Howells Tested-by: Mike Frysinger --- Documentation/nommu-mmap.txt | 15 ++++++++++ Documentation/sysctl/vm.txt | 18 ++++++++++++ include/linux/mm_types.h | 1 + kernel/sysctl.c | 14 ++++++++++ mm/nommu.c | 65 ++++++++++++++++++++++++++++---------------- 5 files changed, 90 insertions(+), 23 deletions(-) (limited to 'Documentation') diff --git a/Documentation/nommu-mmap.txt b/Documentation/nommu-mmap.txt index 02b89dcf38ac..b565e8279d13 100644 --- a/Documentation/nommu-mmap.txt +++ b/Documentation/nommu-mmap.txt @@ -248,3 +248,18 @@ PROVIDING SHAREABLE BLOCK DEVICE SUPPORT Provision of shared mappings on block device files is exactly the same as for character devices. If there isn't a real device underneath, then the driver should allocate sufficient contiguous memory to honour any supported mapping. + + +================================= +ADJUSTING PAGE TRIMMING BEHAVIOUR +================================= + +NOMMU mmap automatically rounds up to the nearest power-of-2 number of pages +when performing an allocation. This can have adverse effects on memory +fragmentation, and as such, is left configurable. The default behaviour is to +aggressively trim allocations and discard any excess pages back in to the page +allocator. In order to retain finer-grained control over fragmentation, this +behaviour can either be disabled completely, or bumped up to a higher page +watermark where trimming begins. + +Page trimming behaviour is configurable via the sysctl `vm.nr_trim_pages'. diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index cd05994a49e6..a3415070bcac 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -38,6 +38,7 @@ Currently, these files are in /proc/sys/vm: - numa_zonelist_order - nr_hugepages - nr_overcommit_hugepages +- nr_trim_pages (only if CONFIG_MMU=n) ============================================================== @@ -348,3 +349,20 @@ Change the maximum size of the hugepage pool. The maximum is nr_hugepages + nr_overcommit_hugepages. See Documentation/vm/hugetlbpage.txt + +============================================================== + +nr_trim_pages + +This is available only on NOMMU kernels. + +This value adjusts the excess page trimming behaviour of power-of-2 aligned +NOMMU mmap allocations. + +A value of 0 disables trimming of allocations entirely, while a value of 1 +trims excess pages aggressively. Any value >= 1 acts as the watermark where +trimming of allocations is initiated. + +The default value is 1. + +See Documentation/nommu-mmap.txt for more information. diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 1c1e0d3a1714..92915e81443f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -106,6 +106,7 @@ struct vm_region { unsigned long vm_flags; /* VMA vm_flags */ unsigned long vm_start; /* start address of region */ unsigned long vm_end; /* region initialised to here */ + unsigned long vm_top; /* region allocated to here */ unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */ struct file *vm_file; /* the backing file or NULL */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 92f6e5bc3c24..89d74436318c 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -82,6 +82,9 @@ extern int percpu_pagelist_fraction; extern int compat_log; extern int latencytop_enabled; extern int sysctl_nr_open_min, sysctl_nr_open_max; +#ifndef CONFIG_MMU +extern int sysctl_nr_trim_pages; +#endif #ifdef CONFIG_RCU_TORTURE_TEST extern int rcutorture_runnable; #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */ @@ -1102,6 +1105,17 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = &proc_dointvec }, +#else + { + .ctl_name = CTL_UNNUMBERED, + .procname = "nr_trim_pages", + .data = &sysctl_nr_trim_pages, + .maxlen = sizeof(sysctl_nr_trim_pages), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &zero, + }, #endif { .ctl_name = VM_LAPTOP_MODE, diff --git a/mm/nommu.c b/mm/nommu.c index 0d363dfcf10e..a6e8ccfbd400 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -10,7 +10,7 @@ * Copyright (c) 2000-2003 David McCullough * Copyright (c) 2000-2001 D Jeff Dionne * Copyright (c) 2002 Greg Ungerer - * Copyright (c) 2007 Paul Mundt + * Copyright (c) 2007-2008 Paul Mundt */ #include @@ -66,6 +66,7 @@ atomic_long_t vm_committed_space = ATOMIC_LONG_INIT(0); int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */ int sysctl_overcommit_ratio = 50; /* default is 50% */ int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT; +int sysctl_nr_trim_pages = 1; /* page trimming behaviour */ int heap_stack_gap = 0; atomic_t mmap_pages_allocated; @@ -455,6 +456,8 @@ static noinline void validate_nommu_regions(void) last = rb_entry(lastp, struct vm_region, vm_rb); if (unlikely(last->vm_end <= last->vm_start)) BUG(); + if (unlikely(last->vm_top < last->vm_end)) + BUG(); while ((p = rb_next(lastp))) { region = rb_entry(p, struct vm_region, vm_rb); @@ -462,7 +465,9 @@ static noinline void validate_nommu_regions(void) if (unlikely(region->vm_end <= region->vm_start)) BUG(); - if (unlikely(region->vm_start < last->vm_end)) + if (unlikely(region->vm_top < region->vm_end)) + BUG(); + if (unlikely(region->vm_start < last->vm_top)) BUG(); lastp = p; @@ -536,7 +541,7 @@ static void free_page_series(unsigned long from, unsigned long to) /* * release a reference to a region * - the caller must hold the region semaphore, which this releases - * - the region may not have been added to the tree yet, in which case vm_end + * - the region may not have been added to the tree yet, in which case vm_top * will equal vm_start */ static void __put_nommu_region(struct vm_region *region) @@ -547,7 +552,7 @@ static void __put_nommu_region(struct vm_region *region) BUG_ON(!nommu_region_tree.rb_node); if (atomic_dec_and_test(®ion->vm_usage)) { - if (region->vm_end > region->vm_start) + if (region->vm_top > region->vm_start) delete_nommu_region(region); up_write(&nommu_region_sem); @@ -558,7 +563,7 @@ static void __put_nommu_region(struct vm_region *region) * from ramfs/tmpfs mustn't be released here */ if (region->vm_flags & VM_MAPPED_COPY) { kdebug("free series"); - free_page_series(region->vm_start, region->vm_end); + free_page_series(region->vm_start, region->vm_top); } kmem_cache_free(vm_region_jar, region); } else { @@ -999,6 +1004,10 @@ static int do_mmap_shared_file(struct vm_area_struct *vma) int ret; ret = vma->vm_file->f_op->mmap(vma->vm_file, vma); + if (ret == 0) { + vma->vm_region->vm_top = vma->vm_region->vm_end; + return ret; + } if (ret != -ENOSYS) return ret; @@ -1027,11 +1036,14 @@ static int do_mmap_private(struct vm_area_struct *vma, */ if (vma->vm_file) { ret = vma->vm_file->f_op->mmap(vma->vm_file, vma); - if (ret != -ENOSYS) { + if (ret == 0) { /* shouldn't return success if we're not sharing */ - BUG_ON(ret == 0 && !(vma->vm_flags & VM_MAYSHARE)); - return ret; /* success or a real error */ + BUG_ON(!(vma->vm_flags & VM_MAYSHARE)); + vma->vm_region->vm_top = vma->vm_region->vm_end; + return ret; } + if (ret != -ENOSYS) + return ret; /* getting an ENOSYS error indicates that direct mmap isn't * possible (as opposed to tried but failed) so we'll try to @@ -1051,23 +1063,25 @@ static int do_mmap_private(struct vm_area_struct *vma, if (!pages) goto enomem; - /* we allocated a power-of-2 sized page set, so we need to trim off the - * excess */ total = 1 << order; atomic_add(total, &mmap_pages_allocated); point = rlen >> PAGE_SHIFT; - while (total > point) { - order = ilog2(total - point); - n = 1 << order; - kdebug("shave %lu/%lu @%lu", n, total - point, total); - atomic_sub(n, &mmap_pages_allocated); - total -= n; - set_page_refcounted(pages + total); - __free_pages(pages + total, order); + + /* we allocated a power-of-2 sized page set, so we may want to trim off + * the excess */ + if (sysctl_nr_trim_pages && total - point >= sysctl_nr_trim_pages) { + while (total > point) { + order = ilog2(total - point); + n = 1 << order; + kdebug("shave %lu/%lu @%lu", n, total - point, total); + atomic_sub(n, &mmap_pages_allocated); + total -= n; + set_page_refcounted(pages + total); + __free_pages(pages + total, order); + } } - total = rlen >> PAGE_SHIFT; for (point = 1; point < total; point++) set_page_refcounted(&pages[point]); @@ -1075,6 +1089,7 @@ static int do_mmap_private(struct vm_area_struct *vma, region->vm_flags = vma->vm_flags |= VM_MAPPED_COPY; region->vm_start = (unsigned long) base; region->vm_end = region->vm_start + rlen; + region->vm_top = region->vm_start + (total << PAGE_SHIFT); vma->vm_start = region->vm_start; vma->vm_end = region->vm_start + len; @@ -1110,6 +1125,7 @@ error_free: free_page_series(region->vm_start, region->vm_end); region->vm_start = vma->vm_start = 0; region->vm_end = vma->vm_end = 0; + region->vm_top = 0; return ret; enomem: @@ -1401,7 +1417,7 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, npages = (addr - vma->vm_start) >> PAGE_SHIFT; if (new_below) { - region->vm_end = new->vm_end = addr; + region->vm_top = region->vm_end = new->vm_end = addr; } else { region->vm_start = new->vm_start = addr; region->vm_pgoff = new->vm_pgoff += npages; @@ -1418,6 +1434,7 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, vma->vm_region->vm_pgoff = vma->vm_pgoff += npages; } else { vma->vm_region->vm_end = vma->vm_end = addr; + vma->vm_region->vm_top = addr; } add_nommu_region(vma->vm_region); add_nommu_region(new->vm_region); @@ -1454,10 +1471,12 @@ static int shrink_vma(struct mm_struct *mm, down_write(&nommu_region_sem); delete_nommu_region(region); - if (from > region->vm_start) - region->vm_end = from; - else + if (from > region->vm_start) { + to = region->vm_top; + region->vm_top = region->vm_end = from; + } else { region->vm_start = to; + } add_nommu_region(region); up_write(&nommu_region_sem); -- cgit v1.2.3 From 18e7f1f0d34be4a39f7f47324a3e26b43fddb714 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 7 Jan 2009 18:07:32 -0800 Subject: cgroups: documentation updates - remove 'releasable' since it has been moved to the debug subsys. - update lock requirements of subsys callbacks. Signed-off-by: Li Zefan Cc: Paul Menage Cc: KAMEZAWA Hiroyuki Cc: Balbir Singh Cc: Pavel Emelyanov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/cgroups.txt | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'Documentation') diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index d9014aa0eb68..60287e9e9d27 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -227,7 +227,6 @@ Each cgroup is represented by a directory in the cgroup file system containing the following files describing that cgroup: - tasks: list of tasks (by pid) attached to that cgroup - - releasable flag: cgroup currently removeable? - notify_on_release flag: run the release agent on exit? - release_agent: the path to use for release notifications (this file exists in the top cgroup only) @@ -360,7 +359,7 @@ Now you want to do something with this cgroup. In this directory you can find several files: # ls -notify_on_release releasable tasks +notify_on_release tasks (plus whatever files added by the attached subsystems) Now attach your shell to this cgroup: @@ -479,7 +478,6 @@ newly-created cgroup if an error occurs after this subsystem's create() method has been called for the new cgroup). void pre_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp); -(cgroup_mutex held by caller) Called before checking the reference count on each subsystem. This may be useful for subsystems which have some extra references even if @@ -498,6 +496,7 @@ remain valid while the caller holds cgroup_mutex. void attach(struct cgroup_subsys *ss, struct cgroup *cgrp, struct cgroup *old_cgrp, struct task_struct *task) +(cgroup_mutex held by caller) Called after the task has been attached to the cgroup, to allow any post-attachment activity that requires memory allocations or blocking. @@ -511,6 +510,7 @@ void exit(struct cgroup_subsys *ss, struct task_struct *task) Called during task exit. int populate(struct cgroup_subsys *ss, struct cgroup *cgrp) +(cgroup_mutex held by caller) Called after creation of a cgroup to allow a subsystem to populate the cgroup directory with file entries. The subsystem should make @@ -520,6 +520,7 @@ method can return an error code, the error code is currently not always handled well. void post_clone(struct cgroup_subsys *ss, struct cgroup *cgrp) +(cgroup_mutex held by caller) Called at the end of cgroup_clone() to do any paramater initialization which might be required before a task could attach. For -- cgit v1.2.3 From f817ed48535ac6510ebae7c4116f24a5f9268834 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 7 Jan 2009 18:07:53 -0800 Subject: memcg: move all acccounting to parent at rmdir() This patch provides a function to move account information of a page between mem_cgroups and rewrite force_empty to make use of this. This moving of page_cgroup is done under - lru_lock of source/destination mem_cgroup is held. - lock_page_cgroup() is held. Then, a routine which touches pc->mem_cgroup without lock_page_cgroup() should confirm pc->mem_cgroup is still valid or not. Typical code can be following. (while page is not under lock_page()) mem = pc->mem_cgroup; mz = page_cgroup_zoneinfo(pc) spin_lock_irqsave(&mz->lru_lock); if (pc->mem_cgroup == mem) ...../* some list handling */ spin_unlock_irqrestore(&mz->lru_lock); Of course, better way is lock_page_cgroup(pc); .... unlock_page_cgroup(pc); But you should confirm the nest of lock and avoid deadlock. If you treats page_cgroup from mem_cgroup's LRU under mz->lru_lock, you don't have to worry about what pc->mem_cgroup points to. moved pages are added to head of lru, not to tail. Expected users of this routine is: - force_empty (rmdir) - moving tasks between cgroup (for moving account information.) - hierarchy (maybe useful.) force_empty(rmdir) uses this move_account and move pages to its parent. This "move" will not cause OOM (I added "oom" parameter to try_charge().) If the parent is busy (not enough memory), force_empty calls try_to_free_page() and reduce usage. Purpose of this behavior is - Fix "forget all" behavior of force_empty and avoid leak of accounting. - By "moving first, free if necessary", keep pages on memory as much as possible. Adding a switch to change behavior of force_empty to - free first, move if necessary - free all, if there is mlocked/busy pages, return -EBUSY. is under consideration. (I'll add if someone requtests.) This patch also removes memory.force_empty file, a brutal debug-only interface. Reviewed-by: Daisuke Nishimura Tested-by: Daisuke Nishimura Signed-off-by: KAMEZAWA Hiroyuki Cc: Balbir Singh Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/controllers/memory.txt | 12 +- mm/memcontrol.c | 277 ++++++++++++++++++++++++++--------- 2 files changed, 214 insertions(+), 75 deletions(-) (limited to 'Documentation') diff --git a/Documentation/controllers/memory.txt b/Documentation/controllers/memory.txt index 1c07547d3f81..58f32c166fac 100644 --- a/Documentation/controllers/memory.txt +++ b/Documentation/controllers/memory.txt @@ -207,12 +207,6 @@ exceeded. The memory.stat file gives accounting information. Now, the number of caches, RSS and Active pages/Inactive pages are shown. -The memory.force_empty gives an interface to drop *all* charges by force. - -# echo 1 > memory.force_empty - -will drop all charges in cgroup. Currently, this is maintained for test. - 4. Testing Balbir posted lmbench, AIM9, LTP and vmmstress results [10] and [11]. @@ -242,8 +236,10 @@ reclaimed. A cgroup can be removed by rmdir, but as discussed in sections 4.1 and 4.2, a cgroup might have some charge associated with it, even though all -tasks have migrated away from it. Such charges are automatically dropped at -rmdir() if there are no tasks. +tasks have migrated away from it. +Such charges are moved to its parent as much as possible and freed if parent +is full. Both of RSS and CACHES are moved to parent. +If both of them are busy, rmdir() returns -EBUSY. 5. TODO diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b71195e8198b..49234d93988a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -257,7 +257,7 @@ static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz, } static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz, - struct page_cgroup *pc) + struct page_cgroup *pc, bool hot) { int lru = LRU_BASE; @@ -271,7 +271,10 @@ static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz, } MEM_CGROUP_ZSTAT(mz, lru) += 1; - list_add(&pc->lru, &mz->lists[lru]); + if (hot) + list_add(&pc->lru, &mz->lists[lru]); + else + list_add_tail(&pc->lru, &mz->lists[lru]); mem_cgroup_charge_statistics(pc->mem_cgroup, pc, true); } @@ -467,21 +470,12 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, return nr_taken; } - -/** - * mem_cgroup_try_charge - get charge of PAGE_SIZE. - * @mm: an mm_struct which is charged against. (when *memcg is NULL) - * @gfp_mask: gfp_mask for reclaim. - * @memcg: a pointer to memory cgroup which is charged against. - * - * charge against memory cgroup pointed by *memcg. if *memcg == NULL, estimated - * memory cgroup from @mm is got and stored in *memcg. - * - * Returns 0 if success. -ENOMEM at failure. +/* + * Unlike exported interface, "oom" parameter is added. if oom==true, + * oom-killer can be invoked. */ - -int mem_cgroup_try_charge(struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcg) +static int __mem_cgroup_try_charge(struct mm_struct *mm, + gfp_t gfp_mask, struct mem_cgroup **memcg, bool oom) { struct mem_cgroup *mem; int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; @@ -528,7 +522,8 @@ int mem_cgroup_try_charge(struct mm_struct *mm, continue; if (!nr_retries--) { - mem_cgroup_out_of_memory(mem, gfp_mask); + if (oom) + mem_cgroup_out_of_memory(mem, gfp_mask); goto nomem; } } @@ -538,6 +533,25 @@ nomem: return -ENOMEM; } +/** + * mem_cgroup_try_charge - get charge of PAGE_SIZE. + * @mm: an mm_struct which is charged against. (when *memcg is NULL) + * @gfp_mask: gfp_mask for reclaim. + * @memcg: a pointer to memory cgroup which is charged against. + * + * charge against memory cgroup pointed by *memcg. if *memcg == NULL, estimated + * memory cgroup from @mm is got and stored in *memcg. + * + * Returns 0 if success. -ENOMEM at failure. + * This call can invoke OOM-Killer. + */ + +int mem_cgroup_try_charge(struct mm_struct *mm, + gfp_t mask, struct mem_cgroup **memcg) +{ + return __mem_cgroup_try_charge(mm, mask, memcg, true); +} + /* * commit a charge got by mem_cgroup_try_charge() and makes page_cgroup to be * USED state. If already USED, uncharge and return. @@ -571,11 +585,109 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, mz = page_cgroup_zoneinfo(pc); spin_lock_irqsave(&mz->lru_lock, flags); - __mem_cgroup_add_list(mz, pc); + __mem_cgroup_add_list(mz, pc, true); spin_unlock_irqrestore(&mz->lru_lock, flags); unlock_page_cgroup(pc); } +/** + * mem_cgroup_move_account - move account of the page + * @pc: page_cgroup of the page. + * @from: mem_cgroup which the page is moved from. + * @to: mem_cgroup which the page is moved to. @from != @to. + * + * The caller must confirm following. + * 1. disable irq. + * 2. lru_lock of old mem_cgroup(@from) should be held. + * + * returns 0 at success, + * returns -EBUSY when lock is busy or "pc" is unstable. + * + * This function does "uncharge" from old cgroup but doesn't do "charge" to + * new cgroup. It should be done by a caller. + */ + +static int mem_cgroup_move_account(struct page_cgroup *pc, + struct mem_cgroup *from, struct mem_cgroup *to) +{ + struct mem_cgroup_per_zone *from_mz, *to_mz; + int nid, zid; + int ret = -EBUSY; + + VM_BUG_ON(!irqs_disabled()); + VM_BUG_ON(from == to); + + nid = page_cgroup_nid(pc); + zid = page_cgroup_zid(pc); + from_mz = mem_cgroup_zoneinfo(from, nid, zid); + to_mz = mem_cgroup_zoneinfo(to, nid, zid); + + + if (!trylock_page_cgroup(pc)) + return ret; + + if (!PageCgroupUsed(pc)) + goto out; + + if (pc->mem_cgroup != from) + goto out; + + if (spin_trylock(&to_mz->lru_lock)) { + __mem_cgroup_remove_list(from_mz, pc); + css_put(&from->css); + res_counter_uncharge(&from->res, PAGE_SIZE); + pc->mem_cgroup = to; + css_get(&to->css); + __mem_cgroup_add_list(to_mz, pc, false); + ret = 0; + spin_unlock(&to_mz->lru_lock); + } +out: + unlock_page_cgroup(pc); + return ret; +} + +/* + * move charges to its parent. + */ + +static int mem_cgroup_move_parent(struct page_cgroup *pc, + struct mem_cgroup *child, + gfp_t gfp_mask) +{ + struct cgroup *cg = child->css.cgroup; + struct cgroup *pcg = cg->parent; + struct mem_cgroup *parent; + struct mem_cgroup_per_zone *mz; + unsigned long flags; + int ret; + + /* Is ROOT ? */ + if (!pcg) + return -EINVAL; + + parent = mem_cgroup_from_cont(pcg); + + ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false); + if (ret) + return ret; + + mz = mem_cgroup_zoneinfo(child, + page_cgroup_nid(pc), page_cgroup_zid(pc)); + + spin_lock_irqsave(&mz->lru_lock, flags); + ret = mem_cgroup_move_account(pc, child, parent); + spin_unlock_irqrestore(&mz->lru_lock, flags); + + /* drop extra refcnt */ + css_put(&parent->css); + /* uncharge if move fails */ + if (ret) + res_counter_uncharge(&parent->res, PAGE_SIZE); + + return ret; +} + /* * Charge the memory controller for page usage. * Return @@ -597,7 +709,7 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, prefetchw(pc); mem = memcg; - ret = mem_cgroup_try_charge(mm, gfp_mask, &mem); + ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true); if (ret) return ret; @@ -899,46 +1011,52 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, * This routine traverse page_cgroup in given list and drop them all. * *And* this routine doesn't reclaim page itself, just removes page_cgroup. */ -#define FORCE_UNCHARGE_BATCH (128) -static void mem_cgroup_force_empty_list(struct mem_cgroup *mem, +static int mem_cgroup_force_empty_list(struct mem_cgroup *mem, struct mem_cgroup_per_zone *mz, enum lru_list lru) { - struct page_cgroup *pc; - struct page *page; - int count = FORCE_UNCHARGE_BATCH; + struct page_cgroup *pc, *busy; unsigned long flags; + unsigned long loop; struct list_head *list; + int ret = 0; list = &mz->lists[lru]; - spin_lock_irqsave(&mz->lru_lock, flags); - while (!list_empty(list)) { - pc = list_entry(list->prev, struct page_cgroup, lru); - page = pc->page; - if (!PageCgroupUsed(pc)) + loop = MEM_CGROUP_ZSTAT(mz, lru); + /* give some margin against EBUSY etc...*/ + loop += 256; + busy = NULL; + while (loop--) { + ret = 0; + spin_lock_irqsave(&mz->lru_lock, flags); + if (list_empty(list)) { + spin_unlock_irqrestore(&mz->lru_lock, flags); break; - get_page(page); + } + pc = list_entry(list->prev, struct page_cgroup, lru); + if (busy == pc) { + list_move(&pc->lru, list); + busy = 0; + spin_unlock_irqrestore(&mz->lru_lock, flags); + continue; + } spin_unlock_irqrestore(&mz->lru_lock, flags); - /* - * Check if this page is on LRU. !LRU page can be found - * if it's under page migration. - */ - if (PageLRU(page)) { - __mem_cgroup_uncharge_common(page, - MEM_CGROUP_CHARGE_TYPE_FORCE); - put_page(page); - if (--count <= 0) { - count = FORCE_UNCHARGE_BATCH; - cond_resched(); - } - } else { - spin_lock_irqsave(&mz->lru_lock, flags); + + ret = mem_cgroup_move_parent(pc, mem, GFP_HIGHUSER_MOVABLE); + if (ret == -ENOMEM) break; - } - spin_lock_irqsave(&mz->lru_lock, flags); + + if (ret == -EBUSY || ret == -EINVAL) { + /* found lock contention or "pc" is obsolete. */ + busy = pc; + cond_resched(); + } else + busy = NULL; } - spin_unlock_irqrestore(&mz->lru_lock, flags); + if (!ret && !list_empty(list)) + return -EBUSY; + return ret; } /* @@ -947,34 +1065,68 @@ static void mem_cgroup_force_empty_list(struct mem_cgroup *mem, */ static int mem_cgroup_force_empty(struct mem_cgroup *mem) { - int ret = -EBUSY; - int node, zid; + int ret; + int node, zid, shrink; + int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; css_get(&mem->css); - /* - * page reclaim code (kswapd etc..) will move pages between - * active_list <-> inactive_list while we don't take a lock. - * So, we have to do loop here until all lists are empty. - */ + + shrink = 0; +move_account: while (mem->res.usage > 0) { + ret = -EBUSY; if (atomic_read(&mem->css.cgroup->count) > 0) goto out; + /* This is for making all *used* pages to be on LRU. */ lru_add_drain_all(); - for_each_node_state(node, N_POSSIBLE) - for (zid = 0; zid < MAX_NR_ZONES; zid++) { + ret = 0; + for_each_node_state(node, N_POSSIBLE) { + for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) { struct mem_cgroup_per_zone *mz; enum lru_list l; mz = mem_cgroup_zoneinfo(mem, node, zid); - for_each_lru(l) - mem_cgroup_force_empty_list(mem, mz, l); + for_each_lru(l) { + ret = mem_cgroup_force_empty_list(mem, + mz, l); + if (ret) + break; + } } + if (ret) + break; + } + /* it seems parent cgroup doesn't have enough mem */ + if (ret == -ENOMEM) + goto try_to_free; cond_resched(); } ret = 0; out: css_put(&mem->css); return ret; + +try_to_free: + /* returns EBUSY if we come here twice. */ + if (shrink) { + ret = -EBUSY; + goto out; + } + /* try to free all pages in this cgroup */ + shrink = 1; + while (nr_retries && mem->res.usage > 0) { + int progress; + progress = try_to_free_mem_cgroup_pages(mem, + GFP_HIGHUSER_MOVABLE); + if (!progress) + nr_retries--; + + } + /* try move_account...there may be some *locked* pages. */ + if (mem->res.usage) + goto move_account; + ret = 0; + goto out; } static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft) @@ -1023,11 +1175,6 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) return 0; } -static int mem_force_empty_write(struct cgroup *cont, unsigned int event) -{ - return mem_cgroup_force_empty(mem_cgroup_from_cont(cont)); -} - static const struct mem_cgroup_stat_desc { const char *msg; u64 unit; @@ -1103,10 +1250,6 @@ static struct cftype mem_cgroup_files[] = { .trigger = mem_cgroup_reset, .read_u64 = mem_cgroup_read, }, - { - .name = "force_empty", - .trigger = mem_force_empty_write, - }, { .name = "stat", .read_map = mem_control_stat_show, -- cgit v1.2.3 From c1e862c1f5ad34771b6d0a528cf681e0dcad7c86 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 7 Jan 2009 18:07:55 -0800 Subject: memcg: new force_empty to free pages under group By memcg-move-all-accounts-to-parent-at-rmdir.patch, there is no leak of memory usage and force_empty is removed. This patch adds "force_empty" again, in reasonable manner. memory.force_empty file works when #echo 0 (or some) > memory.force_empty and have following function. 1. only works when there are no task in this cgroup. 2. free all page under this cgroup as much as possible. 3. page which cannot be freed will be moved up to parent. 4. Then, memcg will be empty after above echo returns. This is much better behavior than old "force_empty" which just forget all accounts. This patch also check signal_pending() and above "echo" can be stopped by "Ctrl-C". [akpm@linux-foundation.org: cleanup] Signed-off-by: KAMEZAWA Hiroyuki Cc: Li Zefan Cc: Balbir Singh Cc: Pavel Emelyanov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/controllers/memory.txt | 27 ++++++++++++++++++++---- mm/memcontrol.c | 41 ++++++++++++++++++++++++++++++------ 2 files changed, 57 insertions(+), 11 deletions(-) (limited to 'Documentation') diff --git a/Documentation/controllers/memory.txt b/Documentation/controllers/memory.txt index 58f32c166fac..54253b7a8db2 100644 --- a/Documentation/controllers/memory.txt +++ b/Documentation/controllers/memory.txt @@ -237,11 +237,30 @@ reclaimed. A cgroup can be removed by rmdir, but as discussed in sections 4.1 and 4.2, a cgroup might have some charge associated with it, even though all tasks have migrated away from it. -Such charges are moved to its parent as much as possible and freed if parent -is full. Both of RSS and CACHES are moved to parent. -If both of them are busy, rmdir() returns -EBUSY. +Such charges are freed(at default) or moved to its parent. When moved, +both of RSS and CACHES are moved to parent. +If both of them are busy, rmdir() returns -EBUSY. See 5.1 Also. -5. TODO +5. Misc. interfaces. + +5.1 force_empty + memory.force_empty interface is provided to make cgroup's memory usage empty. + You can use this interface only when the cgroup has no tasks. + When writing anything to this + + # echo 0 > memory.force_empty + + Almost all pages tracked by this memcg will be unmapped and freed. Some of + pages cannot be freed because it's locked or in-use. Such pages are moved + to parent and this cgroup will be empty. But this may return -EBUSY in + some too busy case. + + Typical use case of this interface is that calling this before rmdir(). + Because rmdir() moves all pages to parent, some out-of-use page caches can be + moved to the parent. If you want to avoid that, force_empty will be useful. + + +6. TODO 1. Add support for accounting huge pages (as a separate controller) 2. Make per-cgroup scanner reclaim not-shared pages first diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e00f25e6545f..decace3bb57e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1062,21 +1062,27 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *mem, * make mem_cgroup's charge to be 0 if there is no task. * This enables deleting this mem_cgroup. */ -static int mem_cgroup_force_empty(struct mem_cgroup *mem) +static int mem_cgroup_force_empty(struct mem_cgroup *mem, bool free_all) { int ret; int node, zid, shrink; int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; + struct cgroup *cgrp = mem->css.cgroup; css_get(&mem->css); shrink = 0; + /* should free all ? */ + if (free_all) + goto try_to_free; move_account: while (mem->res.usage > 0) { ret = -EBUSY; - if (atomic_read(&mem->css.cgroup->count) > 0) + if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children)) + goto out; + ret = -EINTR; + if (signal_pending(current)) goto out; - /* This is for making all *used* pages to be on LRU. */ lru_add_drain_all(); ret = 0; @@ -1106,19 +1112,29 @@ out: return ret; try_to_free: - /* returns EBUSY if we come here twice. */ - if (shrink) { + /* returns EBUSY if there is a task or if we come here twice. */ + if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children) || shrink) { ret = -EBUSY; goto out; } + /* we call try-to-free pages for make this cgroup empty */ + lru_add_drain_all(); /* try to free all pages in this cgroup */ shrink = 1; while (nr_retries && mem->res.usage > 0) { int progress; + + if (signal_pending(current)) { + ret = -EINTR; + goto out; + } progress = try_to_free_mem_cgroup_pages(mem, GFP_HIGHUSER_MOVABLE); - if (!progress) + if (!progress) { nr_retries--; + /* maybe some writeback is necessary */ + congestion_wait(WRITE, HZ/10); + } } /* try move_account...there may be some *locked* pages. */ @@ -1128,6 +1144,12 @@ try_to_free: goto out; } +int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event) +{ + return mem_cgroup_force_empty(mem_cgroup_from_cont(cont), true); +} + + static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft) { return res_counter_read_u64(&mem_cgroup_from_cont(cont)->res, @@ -1225,6 +1247,7 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, return 0; } + static struct cftype mem_cgroup_files[] = { { .name = "usage_in_bytes", @@ -1253,6 +1276,10 @@ static struct cftype mem_cgroup_files[] = { .name = "stat", .read_map = mem_control_stat_show, }, + { + .name = "force_empty", + .trigger = mem_cgroup_force_empty_write, + }, }; static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) @@ -1350,7 +1377,7 @@ static void mem_cgroup_pre_destroy(struct cgroup_subsys *ss, struct cgroup *cont) { struct mem_cgroup *mem = mem_cgroup_from_cont(cont); - mem_cgroup_force_empty(mem); + mem_cgroup_force_empty(mem, false); } static void mem_cgroup_destroy(struct cgroup_subsys *ss, -- cgit v1.2.3 From d13d144309d2e5a3e6ad978b16c1d0226ddc9231 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 7 Jan 2009 18:07:56 -0800 Subject: memcg: handle swap caches SwapCache support for memory resource controller (memcg) Before mem+swap controller, memcg itself should handle SwapCache in proper way. This is cut-out from it. In current memcg, SwapCache is just leaked and the user can create tons of SwapCache. This is a leak of account and should be handled. SwapCache accounting is done as following. charge (anon) - charged when it's mapped. (because of readahead, charge at add_to_swap_cache() is not sane) uncharge (anon) - uncharged when it's dropped from swapcache and fully unmapped. means it's not uncharged at unmap. Note: delete from swap cache at swap-in is done after rmap information is established. charge (shmem) - charged at swap-in. this prevents charge at add_to_page_cache(). uncharge (shmem) - uncharged when it's dropped from swapcache and not on shmem's radix-tree. at migration, check against 'old page' is modified to handle shmem. Comparing to the old version discussed (and caused troubles), we have advantages of - PCG_USED bit. - simple migrating handling. So, situation is much easier than several months ago, maybe. [hugh@veritas.com: memcg: handle swap caches build fix] Reviewed-by: Daisuke Nishimura Tested-by: Daisuke Nishimura Signed-off-by: KAMEZAWA Hiroyuki Cc: Hugh Dickins Cc: Li Zefan Cc: Balbir Singh Cc: Pavel Emelyanov Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/controllers/memory.txt | 5 +++ include/linux/swap.h | 22 ++++++++++++ mm/memcontrol.c | 67 ++++++++++++++++++++++++++++++++---- mm/shmem.c | 18 ++++++++-- mm/swap_state.c | 1 + 5 files changed, 105 insertions(+), 8 deletions(-) (limited to 'Documentation') diff --git a/Documentation/controllers/memory.txt b/Documentation/controllers/memory.txt index 54253b7a8db2..9fe2d0eabe05 100644 --- a/Documentation/controllers/memory.txt +++ b/Documentation/controllers/memory.txt @@ -137,6 +137,11 @@ behind this approach is that a cgroup that aggressively uses a shared page will eventually get charged for it (once it is uncharged from the cgroup that brought it in -- this will happen on memory pressure). +Exception: When you do swapoff and make swapped-out pages of shmem(tmpfs) to +be backed into memory in force, charges for pages are accounted against the +caller of swapoff rather than the users of shmem. + + 2.4 Reclaim Each cgroup maintains a per cgroup LRU that consists of an active diff --git a/include/linux/swap.h b/include/linux/swap.h index 91dee50fe260..f8f3907533f0 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -333,6 +333,22 @@ static inline void disable_swap_token(void) put_swap_token(swap_token_mm); } +#ifdef CONFIG_CGROUP_MEM_RES_CTLR +extern int mem_cgroup_cache_charge_swapin(struct page *page, + struct mm_struct *mm, gfp_t mask, bool locked); +extern void mem_cgroup_uncharge_swapcache(struct page *page); +#else +static inline +int mem_cgroup_cache_charge_swapin(struct page *page, + struct mm_struct *mm, gfp_t mask, bool locked) +{ + return 0; +} +static inline void mem_cgroup_uncharge_swapcache(struct page *page) +{ +} +#endif + #else /* CONFIG_SWAP */ #define nr_swap_pages 0L @@ -409,6 +425,12 @@ static inline swp_entry_t get_swap_page(void) #define has_swap_token(x) 0 #define disable_swap_token() do { } while(0) +static inline int mem_cgroup_cache_charge_swapin(struct page *page, + struct mm_struct *mm, gfp_t mask, bool locked) +{ + return 0; +} + #endif /* CONFIG_SWAP */ #endif /* __KERNEL__*/ #endif /* _LINUX_SWAP_H */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index decace3bb57e..7288e9d85ca7 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -139,6 +140,7 @@ enum charge_type { MEM_CGROUP_CHARGE_TYPE_MAPPED, MEM_CGROUP_CHARGE_TYPE_SHMEM, /* used by page migration of shmem */ MEM_CGROUP_CHARGE_TYPE_FORCE, /* used by force_empty */ + MEM_CGROUP_CHARGE_TYPE_SWAPOUT, /* for accounting swapcache */ NR_CHARGE_TYPE, }; @@ -780,6 +782,33 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, MEM_CGROUP_CHARGE_TYPE_SHMEM, NULL); } +#ifdef CONFIG_SWAP +int mem_cgroup_cache_charge_swapin(struct page *page, + struct mm_struct *mm, gfp_t mask, bool locked) +{ + int ret = 0; + + if (mem_cgroup_subsys.disabled) + return 0; + if (unlikely(!mm)) + mm = &init_mm; + if (!locked) + lock_page(page); + /* + * If not locked, the page can be dropped from SwapCache until + * we reach here. + */ + if (PageSwapCache(page)) { + ret = mem_cgroup_charge_common(page, mm, mask, + MEM_CGROUP_CHARGE_TYPE_SHMEM, NULL); + } + if (!locked) + unlock_page(page); + + return ret; +} +#endif + void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr) { struct page_cgroup *pc; @@ -817,6 +846,9 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) if (mem_cgroup_subsys.disabled) return; + if (PageSwapCache(page)) + return; + /* * Check if our page_cgroup is valid */ @@ -825,12 +857,26 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) return; lock_page_cgroup(pc); - if ((ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED && page_mapped(page)) - || !PageCgroupUsed(pc)) { - /* This happens at race in zap_pte_range() and do_swap_page()*/ - unlock_page_cgroup(pc); - return; + + if (!PageCgroupUsed(pc)) + goto unlock_out; + + switch (ctype) { + case MEM_CGROUP_CHARGE_TYPE_MAPPED: + if (page_mapped(page)) + goto unlock_out; + break; + case MEM_CGROUP_CHARGE_TYPE_SWAPOUT: + if (!PageAnon(page)) { /* Shared memory */ + if (page->mapping && !page_is_file_cache(page)) + goto unlock_out; + } else if (page_mapped(page)) /* Anon */ + goto unlock_out; + break; + default: + break; } + ClearPageCgroupUsed(pc); mem = pc->mem_cgroup; @@ -844,6 +890,10 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) css_put(&mem->css); return; + +unlock_out: + unlock_page_cgroup(pc); + return; } void mem_cgroup_uncharge_page(struct page *page) @@ -863,6 +913,11 @@ void mem_cgroup_uncharge_cache_page(struct page *page) __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE); } +void mem_cgroup_uncharge_swapcache(struct page *page) +{ + __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_SWAPOUT); +} + /* * Before starting migration, account PAGE_SIZE to mem_cgroup that the old * page belongs to. @@ -920,7 +975,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem, ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM; /* unused page is not on radix-tree now. */ - if (unused && ctype != MEM_CGROUP_CHARGE_TYPE_MAPPED) + if (unused) __mem_cgroup_uncharge_common(unused, ctype); pc = lookup_page_cgroup(target); diff --git a/mm/shmem.c b/mm/shmem.c index bd9b4ea307b2..adf5c3eedbc9 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -928,8 +928,12 @@ found: error = 1; if (!inode) goto out; - /* Charge page using GFP_HIGHUSER_MOVABLE while we can wait */ - error = mem_cgroup_cache_charge(page, current->mm, GFP_HIGHUSER_MOVABLE); + /* + * Charge page using GFP_HIGHUSER_MOVABLE while we can wait. + * charged back to the user(not to caller) when swap account is used. + */ + error = mem_cgroup_cache_charge_swapin(page, + current->mm, GFP_HIGHUSER_MOVABLE, true); if (error) goto out; error = radix_tree_preload(GFP_KERNEL); @@ -1266,6 +1270,16 @@ repeat: goto repeat; } wait_on_page_locked(swappage); + /* + * We want to avoid charge at add_to_page_cache(). + * charge against this swap cache here. + */ + if (mem_cgroup_cache_charge_swapin(swappage, + current->mm, gfp, false)) { + page_cache_release(swappage); + error = -ENOMEM; + goto failed; + } page_cache_release(swappage); goto repeat; } diff --git a/mm/swap_state.c b/mm/swap_state.c index 81c825f67a7f..09291ca11f5f 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -118,6 +118,7 @@ void __delete_from_swap_cache(struct page *page) total_swapcache_pages--; __dec_zone_page_state(page, NR_FILE_PAGES); INC_CACHE_INFO(del_total); + mem_cgroup_uncharge_swapcache(page); } /** -- cgit v1.2.3 From c077719be8e9e6b55702117513d1b5f41d80404a Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 7 Jan 2009 18:07:57 -0800 Subject: memcg: mem+swap controller Kconfig Config and control variable for mem+swap controller. This patch adds CONFIG_CGROUP_MEM_RES_CTLR_SWAP (memory resource controller swap extension.) For accounting swap, it's obvious that we have to use additional memory to remember "who uses swap". This adds more overhead. So, it's better to offer "choice" to users. This patch adds 2 choices. This patch adds 2 parameters to enable swap extension or not. - CONFIG - boot option Reviewed-by: Daisuke Nishimura Signed-off-by: KAMEZAWA Hiroyuki Cc: Li Zefan Cc: Balbir Singh Cc: Pavel Emelyanov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 3 +++ include/linux/memcontrol.h | 3 +++ init/Kconfig | 17 +++++++++++++++++ mm/memcontrol.c | 34 ++++++++++++++++++++++++++++++++++ 4 files changed, 57 insertions(+) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 532eacbbed62..fb849020aea9 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1562,6 +1562,9 @@ and is between 256 and 4096 characters. It is defined in the file nosoftlockup [KNL] Disable the soft-lockup detector. + noswapaccount [KNL] Disable accounting of swap in memory resource + controller. (See Documentation/controllers/memory.txt) + nosync [HW,M68K] Disables sync negotiation for all devices. notsc [BUGS=X86-32] Disable Time Stamp Counter diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b095f5f6ecf7..41b46cc9d1f1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -77,6 +77,9 @@ extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, extern long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone, int priority, enum lru_list lru); +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +extern int do_swap_account; +#endif #else /* CONFIG_CGROUP_MEM_RES_CTLR */ struct mem_cgroup; diff --git a/init/Kconfig b/init/Kconfig index 7cbe1f43ca22..a724a149bf3f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -428,6 +428,23 @@ config CGROUP_MEM_RES_CTLR config MM_OWNER bool +config CGROUP_MEM_RES_CTLR_SWAP + bool "Memory Resource Controller Swap Extension(EXPERIMENTAL)" + depends on CGROUP_MEM_RES_CTLR && SWAP && EXPERIMENTAL + help + Add swap management feature to memory resource controller. When you + enable this, you can limit mem+swap usage per cgroup. In other words, + when you disable this, memory resource controller has no cares to + usage of swap...a process can exhaust all of the swap. This extension + is useful when you want to avoid exhaustion swap but this itself + adds more overheads and consumes memory for remembering information. + Especially if you use 32bit system or small memory system, please + be careful about enabling this. When memory resource controller + is disabled by boot option, this will be automatically disabled and + there will be no overhead from this. Even when you set this config=y, + if boot option "noswapaccount" is set, swap will not be accounted. + + endmenu config SYSFS_DEPRECATED diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7288e9d85ca7..59dd8c116372 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -41,6 +41,15 @@ struct cgroup_subsys mem_cgroup_subsys __read_mostly; #define MEM_CGROUP_RECLAIM_RETRIES 5 +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +/* Turned on only when memory cgroup is enabled && really_do_swap_account = 0 */ +int do_swap_account __read_mostly; +static int really_do_swap_account __initdata = 1; /* for remember boot option*/ +#else +#define do_swap_account (0) +#endif + + /* * Statistics for memory cgroup. */ @@ -1404,6 +1413,18 @@ static void mem_cgroup_free(struct mem_cgroup *mem) } +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +static void __init enable_swap_cgroup(void) +{ + if (!mem_cgroup_subsys.disabled && really_do_swap_account) + do_swap_account = 1; +} +#else +static void __init enable_swap_cgroup(void) +{ +} +#endif + static struct cgroup_subsys_state * mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) { @@ -1419,6 +1440,9 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) for_each_node_state(node, N_POSSIBLE) if (alloc_mem_cgroup_per_zone_info(mem, node)) goto free_out; + /* root ? */ + if (cont->parent == NULL) + enable_swap_cgroup(); return &mem->css; free_out: @@ -1490,3 +1514,13 @@ struct cgroup_subsys mem_cgroup_subsys = { .attach = mem_cgroup_move_task, .early_init = 0, }; + +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP + +static int __init disable_swap_account(char *s) +{ + really_do_swap_account = 0; + return 1; +} +__setup("noswapaccount", disable_swap_account); +#endif -- cgit v1.2.3 From 8c7c6e34a1256a5082d38c8e9bd1474476912715 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 7 Jan 2009 18:08:00 -0800 Subject: memcg: mem+swap controller core This patch implements per cgroup limit for usage of memory+swap. However there are SwapCache, double counting of swap-cache and swap-entry is avoided. Mem+Swap controller works as following. - memory usage is limited by memory.limit_in_bytes. - memory + swap usage is limited by memory.memsw_limit_in_bytes. This has following benefits. - A user can limit total resource usage of mem+swap. Without this, because memory resource controller doesn't take care of usage of swap, a process can exhaust all the swap (by memory leak.) We can avoid this case. And Swap is shared resource but it cannot be reclaimed (goes back to memory) until it's used. This characteristic can be trouble when the memory is divided into some parts by cpuset or memcg. Assume group A and group B. After some application executes, the system can be.. Group A -- very large free memory space but occupy 99% of swap. Group B -- under memory shortage but cannot use swap...it's nearly full. Ability to set appropriate swap limit for each group is required. Maybe someone wonder "why not swap but mem+swap ?" - The global LRU(kswapd) can swap out arbitrary pages. Swap-out means to move account from memory to swap...there is no change in usage of mem+swap. In other words, when we want to limit the usage of swap without affecting global LRU, mem+swap limit is better than just limiting swap. Accounting target information is stored in swap_cgroup which is per swap entry record. Charge is done as following. map - charge page and memsw. unmap - uncharge page/memsw if not SwapCache. swap-out (__delete_from_swap_cache) - uncharge page - record mem_cgroup information to swap_cgroup. swap-in (do_swap_page) - charged as page and memsw. record in swap_cgroup is cleared. memsw accounting is decremented. swap-free (swap_free()) - if swap entry is freed, memsw is uncharged by PAGE_SIZE. There are people work under never-swap environments and consider swap as something bad. For such people, this mem+swap controller extension is just an overhead. This overhead is avoided by config or boot option. (see Kconfig. detail is not in this patch.) TODO: - maybe more optimization can be don in swap-in path. (but not very safe.) But we just do simple accounting at this stage. [nishimura@mxp.nes.nec.co.jp: make resize limit hold mutex] [hugh@veritas.com: memswap controller core swapcache fixes] Signed-off-by: KAMEZAWA Hiroyuki Cc: Li Zefan Cc: Balbir Singh Cc: Pavel Emelyanov Signed-off-by: Daisuke Nishimura Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/controllers/memory.txt | 29 ++- include/linux/memcontrol.h | 11 +- include/linux/swap.h | 14 +- mm/memcontrol.c | 400 +++++++++++++++++++++++++++++++---- mm/memory.c | 18 +- mm/swap_state.c | 5 +- mm/swapfile.c | 11 +- mm/vmscan.c | 6 +- 8 files changed, 440 insertions(+), 54 deletions(-) (limited to 'Documentation') diff --git a/Documentation/controllers/memory.txt b/Documentation/controllers/memory.txt index 9fe2d0eabe05..05fe29ab1e58 100644 --- a/Documentation/controllers/memory.txt +++ b/Documentation/controllers/memory.txt @@ -137,12 +137,32 @@ behind this approach is that a cgroup that aggressively uses a shared page will eventually get charged for it (once it is uncharged from the cgroup that brought it in -- this will happen on memory pressure). -Exception: When you do swapoff and make swapped-out pages of shmem(tmpfs) to +Exception: If CONFIG_CGROUP_CGROUP_MEM_RES_CTLR_SWAP is not used.. +When you do swapoff and make swapped-out pages of shmem(tmpfs) to be backed into memory in force, charges for pages are accounted against the caller of swapoff rather than the users of shmem. -2.4 Reclaim +2.4 Swap Extension (CONFIG_CGROUP_MEM_RES_CTLR_SWAP) +Swap Extension allows you to record charge for swap. A swapped-in page is +charged back to original page allocator if possible. + +When swap is accounted, following files are added. + - memory.memsw.usage_in_bytes. + - memory.memsw.limit_in_bytes. + +usage of mem+swap is limited by memsw.limit_in_bytes. + +Note: why 'mem+swap' rather than swap. +The global LRU(kswapd) can swap out arbitrary pages. Swap-out means +to move account from memory to swap...there is no change in usage of +mem+swap. + +In other words, when we want to limit the usage of swap without affecting +global LRU, mem+swap limit is better than just limiting swap from OS point +of view. + +2.5 Reclaim Each cgroup maintains a per cgroup LRU that consists of an active and inactive list. When a cgroup goes over its limit, we first try @@ -246,6 +266,11 @@ Such charges are freed(at default) or moved to its parent. When moved, both of RSS and CACHES are moved to parent. If both of them are busy, rmdir() returns -EBUSY. See 5.1 Also. +Charges recorded in swap information is not updated at removal of cgroup. +Recorded information is discarded and a cgroup which uses swap (swapcache) +will be charged as a new owner of it. + + 5. Misc. interfaces. 5.1 force_empty diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 41b46cc9d1f1..ca51ac72d6c0 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -32,6 +32,8 @@ extern int mem_cgroup_newpage_charge(struct page *page, struct mm_struct *mm, /* for swap handling */ extern int mem_cgroup_try_charge(struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **ptr); +extern int mem_cgroup_try_charge_swapin(struct mm_struct *mm, + struct page *page, gfp_t mask, struct mem_cgroup **ptr); extern void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr); extern void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *ptr); @@ -80,7 +82,6 @@ extern long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone, #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP extern int do_swap_account; #endif - #else /* CONFIG_CGROUP_MEM_RES_CTLR */ struct mem_cgroup; @@ -97,7 +98,13 @@ static inline int mem_cgroup_cache_charge(struct page *page, } static inline int mem_cgroup_try_charge(struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **ptr) + gfp_t gfp_mask, struct mem_cgroup **ptr) +{ + return 0; +} + +static inline int mem_cgroup_try_charge_swapin(struct mm_struct *mm, + struct page *page, gfp_t gfp_mask, struct mem_cgroup **ptr) { return 0; } diff --git a/include/linux/swap.h b/include/linux/swap.h index f8f3907533f0..be938ce4895a 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -214,7 +214,7 @@ static inline void lru_cache_add_active_file(struct page *page) extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask); extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem, - gfp_t gfp_mask); + gfp_t gfp_mask, bool noswap); extern int __isolate_lru_page(struct page *page, int mode, int file); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; @@ -336,7 +336,7 @@ static inline void disable_swap_token(void) #ifdef CONFIG_CGROUP_MEM_RES_CTLR extern int mem_cgroup_cache_charge_swapin(struct page *page, struct mm_struct *mm, gfp_t mask, bool locked); -extern void mem_cgroup_uncharge_swapcache(struct page *page); +extern void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent); #else static inline int mem_cgroup_cache_charge_swapin(struct page *page, @@ -344,7 +344,15 @@ int mem_cgroup_cache_charge_swapin(struct page *page, { return 0; } -static inline void mem_cgroup_uncharge_swapcache(struct page *page) +static inline void +mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent) +{ +} +#endif +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +extern void mem_cgroup_uncharge_swap(swp_entry_t ent); +#else +static inline void mem_cgroup_uncharge_swap(swp_entry_t ent) { } #endif diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 59dd8c116372..2efcf38f3b73 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -131,6 +132,10 @@ struct mem_cgroup { * the counter to account for memory usage */ struct res_counter res; + /* + * the counter to account for mem+swap usage. + */ + struct res_counter memsw; /* * Per cgroup active and inactive list, similar to the * per zone LRU lists. @@ -138,6 +143,8 @@ struct mem_cgroup { struct mem_cgroup_lru_info info; int prev_priority; /* for recording reclaim priority */ + int obsolete; + atomic_t refcnt; /* * statistics. This must be placed at the end of memcg. */ @@ -167,6 +174,17 @@ pcg_default_flags[NR_CHARGE_TYPE] = { 0, /* FORCE */ }; + +/* for encoding cft->private value on file */ +#define _MEM (0) +#define _MEMSWAP (1) +#define MEMFILE_PRIVATE(x, val) (((x) << 16) | (val)) +#define MEMFILE_TYPE(val) (((val) >> 16) & 0xffff) +#define MEMFILE_ATTR(val) ((val) & 0xffff) + +static void mem_cgroup_get(struct mem_cgroup *mem); +static void mem_cgroup_put(struct mem_cgroup *mem); + /* * Always modified under lru lock. Then, not necessary to preempt_disable() */ @@ -485,7 +503,8 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, * oom-killer can be invoked. */ static int __mem_cgroup_try_charge(struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcg, bool oom) + gfp_t gfp_mask, struct mem_cgroup **memcg, + bool oom) { struct mem_cgroup *mem; int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; @@ -513,12 +532,25 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, css_get(&mem->css); } + while (1) { + int ret; + bool noswap = false; - while (unlikely(res_counter_charge(&mem->res, PAGE_SIZE))) { + ret = res_counter_charge(&mem->res, PAGE_SIZE); + if (likely(!ret)) { + if (!do_swap_account) + break; + ret = res_counter_charge(&mem->memsw, PAGE_SIZE); + if (likely(!ret)) + break; + /* mem+swap counter fails */ + res_counter_uncharge(&mem->res, PAGE_SIZE); + noswap = true; + } if (!(gfp_mask & __GFP_WAIT)) goto nomem; - if (try_to_free_mem_cgroup_pages(mem, gfp_mask)) + if (try_to_free_mem_cgroup_pages(mem, gfp_mask, noswap)) continue; /* @@ -527,8 +559,13 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, * moved to swap cache or just unmapped from the cgroup. * Check the limit again to see if the reclaim reduced the * current usage of the cgroup before giving up + * */ - if (res_counter_check_under_limit(&mem->res)) + if (!do_swap_account && + res_counter_check_under_limit(&mem->res)) + continue; + if (do_swap_account && + res_counter_check_under_limit(&mem->memsw)) continue; if (!nr_retries--) { @@ -582,6 +619,8 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, if (unlikely(PageCgroupUsed(pc))) { unlock_page_cgroup(pc); res_counter_uncharge(&mem->res, PAGE_SIZE); + if (do_swap_account) + res_counter_uncharge(&mem->memsw, PAGE_SIZE); css_put(&mem->css); return; } @@ -646,6 +685,8 @@ static int mem_cgroup_move_account(struct page_cgroup *pc, __mem_cgroup_remove_list(from_mz, pc); css_put(&from->css); res_counter_uncharge(&from->res, PAGE_SIZE); + if (do_swap_account) + res_counter_uncharge(&from->memsw, PAGE_SIZE); pc->mem_cgroup = to; css_get(&to->css); __mem_cgroup_add_list(to_mz, pc, false); @@ -692,8 +733,11 @@ static int mem_cgroup_move_parent(struct page_cgroup *pc, /* drop extra refcnt */ css_put(&parent->css); /* uncharge if move fails */ - if (ret) + if (ret) { res_counter_uncharge(&parent->res, PAGE_SIZE); + if (do_swap_account) + res_counter_uncharge(&parent->memsw, PAGE_SIZE); + } return ret; } @@ -791,7 +835,42 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, MEM_CGROUP_CHARGE_TYPE_SHMEM, NULL); } +int mem_cgroup_try_charge_swapin(struct mm_struct *mm, + struct page *page, + gfp_t mask, struct mem_cgroup **ptr) +{ + struct mem_cgroup *mem; + swp_entry_t ent; + + if (mem_cgroup_subsys.disabled) + return 0; + + if (!do_swap_account) + goto charge_cur_mm; + + /* + * A racing thread's fault, or swapoff, may have already updated + * the pte, and even removed page from swap cache: return success + * to go on to do_swap_page()'s pte_same() test, which should fail. + */ + if (!PageSwapCache(page)) + return 0; + + ent.val = page_private(page); + + mem = lookup_swap_cgroup(ent); + if (!mem || mem->obsolete) + goto charge_cur_mm; + *ptr = mem; + return __mem_cgroup_try_charge(NULL, mask, ptr, true); +charge_cur_mm: + if (unlikely(!mm)) + mm = &init_mm; + return __mem_cgroup_try_charge(mm, mask, ptr, true); +} + #ifdef CONFIG_SWAP + int mem_cgroup_cache_charge_swapin(struct page *page, struct mm_struct *mm, gfp_t mask, bool locked) { @@ -808,8 +887,28 @@ int mem_cgroup_cache_charge_swapin(struct page *page, * we reach here. */ if (PageSwapCache(page)) { + struct mem_cgroup *mem = NULL; + swp_entry_t ent; + + ent.val = page_private(page); + if (do_swap_account) { + mem = lookup_swap_cgroup(ent); + if (mem && mem->obsolete) + mem = NULL; + if (mem) + mm = NULL; + } ret = mem_cgroup_charge_common(page, mm, mask, - MEM_CGROUP_CHARGE_TYPE_SHMEM, NULL); + MEM_CGROUP_CHARGE_TYPE_SHMEM, mem); + + if (!ret && do_swap_account) { + /* avoid double counting */ + mem = swap_cgroup_record(ent, NULL); + if (mem) { + res_counter_uncharge(&mem->memsw, PAGE_SIZE); + mem_cgroup_put(mem); + } + } } if (!locked) unlock_page(page); @@ -828,6 +927,23 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr) return; pc = lookup_page_cgroup(page); __mem_cgroup_commit_charge(ptr, pc, MEM_CGROUP_CHARGE_TYPE_MAPPED); + /* + * Now swap is on-memory. This means this page may be + * counted both as mem and swap....double count. + * Fix it by uncharging from memsw. This SwapCache is stable + * because we're still under lock_page(). + */ + if (do_swap_account) { + swp_entry_t ent = {.val = page_private(page)}; + struct mem_cgroup *memcg; + memcg = swap_cgroup_record(ent, NULL); + if (memcg) { + /* If memcg is obsolete, memcg can be != ptr */ + res_counter_uncharge(&memcg->memsw, PAGE_SIZE); + mem_cgroup_put(memcg); + } + + } } void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem) @@ -837,6 +953,8 @@ void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem) if (!mem) return; res_counter_uncharge(&mem->res, PAGE_SIZE); + if (do_swap_account) + res_counter_uncharge(&mem->memsw, PAGE_SIZE); css_put(&mem->css); } @@ -844,29 +962,31 @@ void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem) /* * uncharge if !page_mapped(page) */ -static void +static struct mem_cgroup * __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) { struct page_cgroup *pc; - struct mem_cgroup *mem; + struct mem_cgroup *mem = NULL; struct mem_cgroup_per_zone *mz; unsigned long flags; if (mem_cgroup_subsys.disabled) - return; + return NULL; if (PageSwapCache(page)) - return; + return NULL; /* * Check if our page_cgroup is valid */ pc = lookup_page_cgroup(page); if (unlikely(!pc || !PageCgroupUsed(pc))) - return; + return NULL; lock_page_cgroup(pc); + mem = pc->mem_cgroup; + if (!PageCgroupUsed(pc)) goto unlock_out; @@ -886,8 +1006,11 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) break; } + res_counter_uncharge(&mem->res, PAGE_SIZE); + if (do_swap_account && (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT)) + res_counter_uncharge(&mem->memsw, PAGE_SIZE); + ClearPageCgroupUsed(pc); - mem = pc->mem_cgroup; mz = page_cgroup_zoneinfo(pc); spin_lock_irqsave(&mz->lru_lock, flags); @@ -895,14 +1018,13 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) spin_unlock_irqrestore(&mz->lru_lock, flags); unlock_page_cgroup(pc); - res_counter_uncharge(&mem->res, PAGE_SIZE); css_put(&mem->css); - return; + return mem; unlock_out: unlock_page_cgroup(pc); - return; + return NULL; } void mem_cgroup_uncharge_page(struct page *page) @@ -922,10 +1044,42 @@ void mem_cgroup_uncharge_cache_page(struct page *page) __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE); } -void mem_cgroup_uncharge_swapcache(struct page *page) +/* + * called from __delete_from_swap_cache() and drop "page" account. + * memcg information is recorded to swap_cgroup of "ent" + */ +void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent) +{ + struct mem_cgroup *memcg; + + memcg = __mem_cgroup_uncharge_common(page, + MEM_CGROUP_CHARGE_TYPE_SWAPOUT); + /* record memcg information */ + if (do_swap_account && memcg) { + swap_cgroup_record(ent, memcg); + mem_cgroup_get(memcg); + } +} + +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +/* + * called from swap_entry_free(). remove record in swap_cgroup and + * uncharge "memsw" account. + */ +void mem_cgroup_uncharge_swap(swp_entry_t ent) { - __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_SWAPOUT); + struct mem_cgroup *memcg; + + if (!do_swap_account) + return; + + memcg = swap_cgroup_record(ent, NULL); + if (memcg) { + res_counter_uncharge(&memcg->memsw, PAGE_SIZE); + mem_cgroup_put(memcg); + } } +#endif /* * Before starting migration, account PAGE_SIZE to mem_cgroup that the old @@ -1034,7 +1188,7 @@ int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask) rcu_read_unlock(); do { - progress = try_to_free_mem_cgroup_pages(mem, gfp_mask); + progress = try_to_free_mem_cgroup_pages(mem, gfp_mask, true); progress += res_counter_check_under_limit(&mem->res); } while (!progress && --retry); @@ -1044,26 +1198,84 @@ int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask) return 0; } +static DEFINE_MUTEX(set_limit_mutex); + static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, - unsigned long long val) + unsigned long long val) { int retry_count = MEM_CGROUP_RECLAIM_RETRIES; int progress; + u64 memswlimit; int ret = 0; - while (res_counter_set_limit(&memcg->res, val)) { + while (retry_count) { if (signal_pending(current)) { ret = -EINTR; break; } - if (!retry_count) { - ret = -EBUSY; + /* + * Rather than hide all in some function, I do this in + * open coded manner. You see what this really does. + * We have to guarantee mem->res.limit < mem->memsw.limit. + */ + mutex_lock(&set_limit_mutex); + memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT); + if (memswlimit < val) { + ret = -EINVAL; + mutex_unlock(&set_limit_mutex); break; } + ret = res_counter_set_limit(&memcg->res, val); + mutex_unlock(&set_limit_mutex); + + if (!ret) + break; + progress = try_to_free_mem_cgroup_pages(memcg, - GFP_HIGHUSER_MOVABLE); - if (!progress) + GFP_HIGHUSER_MOVABLE, false); + if (!progress) retry_count--; + } + return ret; +} + +int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, + unsigned long long val) +{ + int retry_count = MEM_CGROUP_RECLAIM_RETRIES; + u64 memlimit, oldusage, curusage; + int ret; + + if (!do_swap_account) + return -EINVAL; + + while (retry_count) { + if (signal_pending(current)) { + ret = -EINTR; + break; + } + /* + * Rather than hide all in some function, I do this in + * open coded manner. You see what this really does. + * We have to guarantee mem->res.limit < mem->memsw.limit. + */ + mutex_lock(&set_limit_mutex); + memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT); + if (memlimit > val) { + ret = -EINVAL; + mutex_unlock(&set_limit_mutex); + break; + } + ret = res_counter_set_limit(&memcg->memsw, val); + mutex_unlock(&set_limit_mutex); + + if (!ret) + break; + + oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); + try_to_free_mem_cgroup_pages(memcg, GFP_HIGHUSER_MOVABLE, true); + curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); + if (curusage >= oldusage) retry_count--; } return ret; @@ -1193,7 +1405,7 @@ try_to_free: goto out; } progress = try_to_free_mem_cgroup_pages(mem, - GFP_HIGHUSER_MOVABLE); + GFP_HIGHUSER_MOVABLE, false); if (!progress) { nr_retries--; /* maybe some writeback is necessary */ @@ -1216,8 +1428,25 @@ int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event) static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft) { - return res_counter_read_u64(&mem_cgroup_from_cont(cont)->res, - cft->private); + struct mem_cgroup *mem = mem_cgroup_from_cont(cont); + u64 val = 0; + int type, name; + + type = MEMFILE_TYPE(cft->private); + name = MEMFILE_ATTR(cft->private); + switch (type) { + case _MEM: + val = res_counter_read_u64(&mem->res, name); + break; + case _MEMSWAP: + if (do_swap_account) + val = res_counter_read_u64(&mem->memsw, name); + break; + default: + BUG(); + break; + } + return val; } /* * The user of this function is... @@ -1227,15 +1456,22 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, const char *buffer) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + int type, name; unsigned long long val; int ret; - switch (cft->private) { + type = MEMFILE_TYPE(cft->private); + name = MEMFILE_ATTR(cft->private); + switch (name) { case RES_LIMIT: /* This function does all necessary parse...reuse it */ ret = res_counter_memparse_write_strategy(buffer, &val); - if (!ret) + if (ret) + break; + if (type == _MEM) ret = mem_cgroup_resize_limit(memcg, val); + else + ret = mem_cgroup_resize_memsw_limit(memcg, val); break; default: ret = -EINVAL; /* should be BUG() ? */ @@ -1247,14 +1483,23 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) { struct mem_cgroup *mem; + int type, name; mem = mem_cgroup_from_cont(cont); - switch (event) { + type = MEMFILE_TYPE(event); + name = MEMFILE_ATTR(event); + switch (name) { case RES_MAX_USAGE: - res_counter_reset_max(&mem->res); + if (type == _MEM) + res_counter_reset_max(&mem->res); + else + res_counter_reset_max(&mem->memsw); break; case RES_FAILCNT: - res_counter_reset_failcnt(&mem->res); + if (type == _MEM) + res_counter_reset_failcnt(&mem->res); + else + res_counter_reset_failcnt(&mem->memsw); break; } return 0; @@ -1315,24 +1560,24 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, static struct cftype mem_cgroup_files[] = { { .name = "usage_in_bytes", - .private = RES_USAGE, + .private = MEMFILE_PRIVATE(_MEM, RES_USAGE), .read_u64 = mem_cgroup_read, }, { .name = "max_usage_in_bytes", - .private = RES_MAX_USAGE, + .private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE), .trigger = mem_cgroup_reset, .read_u64 = mem_cgroup_read, }, { .name = "limit_in_bytes", - .private = RES_LIMIT, + .private = MEMFILE_PRIVATE(_MEM, RES_LIMIT), .write_string = mem_cgroup_write, .read_u64 = mem_cgroup_read, }, { .name = "failcnt", - .private = RES_FAILCNT, + .private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT), .trigger = mem_cgroup_reset, .read_u64 = mem_cgroup_read, }, @@ -1346,6 +1591,47 @@ static struct cftype mem_cgroup_files[] = { }, }; +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +static struct cftype memsw_cgroup_files[] = { + { + .name = "memsw.usage_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), + .read_u64 = mem_cgroup_read, + }, + { + .name = "memsw.max_usage_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE), + .trigger = mem_cgroup_reset, + .read_u64 = mem_cgroup_read, + }, + { + .name = "memsw.limit_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT), + .write_string = mem_cgroup_write, + .read_u64 = mem_cgroup_read, + }, + { + .name = "memsw.failcnt", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT), + .trigger = mem_cgroup_reset, + .read_u64 = mem_cgroup_read, + }, +}; + +static int register_memsw_files(struct cgroup *cont, struct cgroup_subsys *ss) +{ + if (!do_swap_account) + return 0; + return cgroup_add_files(cont, ss, memsw_cgroup_files, + ARRAY_SIZE(memsw_cgroup_files)); +}; +#else +static int register_memsw_files(struct cgroup *cont, struct cgroup_subsys *ss) +{ + return 0; +} +#endif + static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) { struct mem_cgroup_per_node *pn; @@ -1404,14 +1690,44 @@ static struct mem_cgroup *mem_cgroup_alloc(void) return mem; } +/* + * At destroying mem_cgroup, references from swap_cgroup can remain. + * (scanning all at force_empty is too costly...) + * + * Instead of clearing all references at force_empty, we remember + * the number of reference from swap_cgroup and free mem_cgroup when + * it goes down to 0. + * + * When mem_cgroup is destroyed, mem->obsolete will be set to 0 and + * entry which points to this memcg will be ignore at swapin. + * + * Removal of cgroup itself succeeds regardless of refs from swap. + */ + static void mem_cgroup_free(struct mem_cgroup *mem) { + if (atomic_read(&mem->refcnt) > 0) + return; if (mem_cgroup_size() < PAGE_SIZE) kfree(mem); else vfree(mem); } +static void mem_cgroup_get(struct mem_cgroup *mem) +{ + atomic_inc(&mem->refcnt); +} + +static void mem_cgroup_put(struct mem_cgroup *mem) +{ + if (atomic_dec_and_test(&mem->refcnt)) { + if (!mem->obsolete) + return; + mem_cgroup_free(mem); + } +} + #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP static void __init enable_swap_cgroup(void) @@ -1436,6 +1752,7 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) return ERR_PTR(-ENOMEM); res_counter_init(&mem->res); + res_counter_init(&mem->memsw); for_each_node_state(node, N_POSSIBLE) if (alloc_mem_cgroup_per_zone_info(mem, node)) @@ -1456,6 +1773,7 @@ static void mem_cgroup_pre_destroy(struct cgroup_subsys *ss, struct cgroup *cont) { struct mem_cgroup *mem = mem_cgroup_from_cont(cont); + mem->obsolete = 1; mem_cgroup_force_empty(mem, false); } @@ -1474,8 +1792,14 @@ static void mem_cgroup_destroy(struct cgroup_subsys *ss, static int mem_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont) { - return cgroup_add_files(cont, ss, mem_cgroup_files, - ARRAY_SIZE(mem_cgroup_files)); + int ret; + + ret = cgroup_add_files(cont, ss, mem_cgroup_files, + ARRAY_SIZE(mem_cgroup_files)); + + if (!ret) + ret = register_memsw_files(cont, ss); + return ret; } static void mem_cgroup_move_task(struct cgroup_subsys *ss, diff --git a/mm/memory.c b/mm/memory.c index ba5189e322e6..1358012ffa73 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2431,7 +2431,8 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, lock_page(page); delayacct_clear_flag(DELAYACCT_PF_SWAPIN); - if (mem_cgroup_try_charge(mm, GFP_HIGHUSER_MOVABLE, &ptr) == -ENOMEM) { + if (mem_cgroup_try_charge_swapin(mm, page, + GFP_HIGHUSER_MOVABLE, &ptr) == -ENOMEM) { ret = VM_FAULT_OOM; unlock_page(page); goto out; @@ -2449,8 +2450,20 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, goto out_nomap; } - /* The page isn't present yet, go ahead with the fault. */ + /* + * The page isn't present yet, go ahead with the fault. + * + * Be careful about the sequence of operations here. + * To get its accounting right, reuse_swap_page() must be called + * while the page is counted on swap but not yet in mapcount i.e. + * before page_add_anon_rmap() and swap_free(); try_to_free_swap() + * must be called after the swap_free(), or it will never succeed. + * And mem_cgroup_commit_charge_swapin(), which uses the swp_entry + * in page->private, must be called before reuse_swap_page(), + * which may delete_from_swap_cache(). + */ + mem_cgroup_commit_charge_swapin(page, ptr); inc_mm_counter(mm, anon_rss); pte = mk_pte(page, vma->vm_page_prot); if (write_access && reuse_swap_page(page)) { @@ -2461,7 +2474,6 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, flush_icache_page(vma, page); set_pte_at(mm, address, page_table, pte); page_add_anon_rmap(page, vma, address); - mem_cgroup_commit_charge_swapin(page, ptr); swap_free(entry); if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) diff --git a/mm/swap_state.c b/mm/swap_state.c index 09291ca11f5f..3ecea98ecb45 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -17,6 +17,7 @@ #include #include #include +#include #include @@ -108,6 +109,8 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask) */ void __delete_from_swap_cache(struct page *page) { + swp_entry_t ent = {.val = page_private(page)}; + VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(!PageSwapCache(page)); VM_BUG_ON(PageWriteback(page)); @@ -118,7 +121,7 @@ void __delete_from_swap_cache(struct page *page) total_swapcache_pages--; __dec_zone_page_state(page, NR_FILE_PAGES); INC_CACHE_INFO(del_total); - mem_cgroup_uncharge_swapcache(page); + mem_cgroup_uncharge_swapcache(page, ent); } /** diff --git a/mm/swapfile.c b/mm/swapfile.c index 1e7a715a3866..0579d9069b61 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -471,8 +471,9 @@ out: return NULL; } -static int swap_entry_free(struct swap_info_struct *p, unsigned long offset) +static int swap_entry_free(struct swap_info_struct *p, swp_entry_t ent) { + unsigned long offset = swp_offset(ent); int count = p->swap_map[offset]; if (count < SWAP_MAP_MAX) { @@ -487,6 +488,7 @@ static int swap_entry_free(struct swap_info_struct *p, unsigned long offset) swap_list.next = p - swap_info; nr_swap_pages++; p->inuse_pages--; + mem_cgroup_uncharge_swap(ent); } } return count; @@ -502,7 +504,7 @@ void swap_free(swp_entry_t entry) p = swap_info_get(entry); if (p) { - swap_entry_free(p, swp_offset(entry)); + swap_entry_free(p, entry); spin_unlock(&swap_lock); } } @@ -582,7 +584,7 @@ int free_swap_and_cache(swp_entry_t entry) p = swap_info_get(entry); if (p) { - if (swap_entry_free(p, swp_offset(entry)) == 1) { + if (swap_entry_free(p, entry) == 1) { page = find_get_page(&swapper_space, entry.val); if (page && !trylock_page(page)) { page_cache_release(page); @@ -696,7 +698,8 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, pte_t *pte; int ret = 1; - if (mem_cgroup_try_charge(vma->vm_mm, GFP_HIGHUSER_MOVABLE, &ptr)) + if (mem_cgroup_try_charge_swapin(vma->vm_mm, page, + GFP_HIGHUSER_MOVABLE, &ptr)) ret = -ENOMEM; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); diff --git a/mm/vmscan.c b/mm/vmscan.c index b07c48b09a93..f63b20dd7714 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1661,7 +1661,8 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, #ifdef CONFIG_CGROUP_MEM_RES_CTLR unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, - gfp_t gfp_mask) + gfp_t gfp_mask, + bool noswap) { struct scan_control sc = { .may_writepage = !laptop_mode, @@ -1674,6 +1675,9 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, }; struct zonelist *zonelist; + if (noswap) + sc.may_swap = 0; + sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); zonelist = NODE_DATA(numa_node_id())->node_zonelists; -- cgit v1.2.3 From 52bc0d82100cd896213a9a25ec01c1ba87b939db Mon Sep 17 00:00:00 2001 From: Balbir Singh Date: Wed, 7 Jan 2009 18:08:03 -0800 Subject: memcg: memory cgroup hierarchy documentation Documentation updates for hierarchy support Signed-off-by: Balbir Singh Cc: YAMAMOTO Takashi Cc: Paul Menage Cc: Li Zefan Cc: David Rientjes Cc: Pavel Emelianov Cc: Dhaval Giani Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/controllers/memory.txt | 38 +++++++++++++++++++++++++++++++++++- 1 file changed, 37 insertions(+), 1 deletion(-) (limited to 'Documentation') diff --git a/Documentation/controllers/memory.txt b/Documentation/controllers/memory.txt index 05fe29ab1e58..09e1c737d285 100644 --- a/Documentation/controllers/memory.txt +++ b/Documentation/controllers/memory.txt @@ -289,8 +289,44 @@ will be charged as a new owner of it. Because rmdir() moves all pages to parent, some out-of-use page caches can be moved to the parent. If you want to avoid that, force_empty will be useful. +6. Hierarchy support -6. TODO +The memory controller supports a deep hierarchy and hierarchical accounting. +The hierarchy is created by creating the appropriate cgroups in the +cgroup filesystem. Consider for example, the following cgroup filesystem +hierarchy + + root + / | \ + / | \ + a b c + | \ + | \ + d e + +In the diagram above, with hierarchical accounting enabled, all memory +usage of e, is accounted to its ancestors up until the root (i.e, c and root), +that has memory.use_hierarchy enabled. If one of the ancestors goes over its +limit, the reclaim algorithm reclaims from the tasks in the ancestor and the +children of the ancestor. + +6.1 Enabling hierarchical accounting and reclaim + +The memory controller by default disables the hierarchy feature. Support +can be enabled by writing 1 to memory.use_hierarchy file of the root cgroup + +# echo 1 > memory.use_hierarchy + +The feature can be disabled by + +# echo 0 > memory.use_hierarchy + +NOTE1: Enabling/disabling will fail if the cgroup already has other +cgroups created below it. + +NOTE2: This feature can be enabled/disabled per subtree. + +7. TODO 1. Add support for accounting huge pages (as a separate controller) 2. Make per-cgroup scanner reclaim not-shared pages first -- cgit v1.2.3 From 7f016ee8b6a9a43f768e6252021f169abec4fa1f Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Wed, 7 Jan 2009 18:08:22 -0800 Subject: memcg: show reclaim stat Add the following four fields to memory.stat file: - inactive_ratio - recent_rotated_anon - recent_rotated_file - recent_scanned_anon - recent_scanned_file Acked-by: Rik van Riel Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: KOSAKI Motohiro Cc: Balbir Singh Cc: Daisuke Nishimura Cc: Hugh Dickins Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/controllers/memory.txt | 25 +++++++++++++++++++++++++ mm/memcontrol.c | 30 ++++++++++++++++++++++++++++++ 2 files changed, 55 insertions(+) (limited to 'Documentation') diff --git a/Documentation/controllers/memory.txt b/Documentation/controllers/memory.txt index 09e1c737d285..d71745cc2f00 100644 --- a/Documentation/controllers/memory.txt +++ b/Documentation/controllers/memory.txt @@ -289,6 +289,31 @@ will be charged as a new owner of it. Because rmdir() moves all pages to parent, some out-of-use page caches can be moved to the parent. If you want to avoid that, force_empty will be useful. +5.2 stat file + memory.stat file includes following statistics (now) + cache - # of pages from page-cache and shmem. + rss - # of pages from anonymous memory. + pgpgin - # of event of charging + pgpgout - # of event of uncharging + active_anon - # of pages on active lru of anon, shmem. + inactive_anon - # of pages on active lru of anon, shmem + active_file - # of pages on active lru of file-cache + inactive_file - # of pages on inactive lru of file cache + unevictable - # of pages cannot be reclaimed.(mlocked etc) + + Below is depend on CONFIG_DEBUG_VM. + inactive_ratio - VM inernal parameter. (see mm/page_alloc.c) + recent_rotated_anon - VM internal parameter. (see mm/vmscan.c) + recent_rotated_file - VM internal parameter. (see mm/vmscan.c) + recent_scanned_anon - VM internal parameter. (see mm/vmscan.c) + recent_scanned_file - VM internal parameter. (see mm/vmscan.c) + + Memo: + recent_rotated means recent frequency of lru rotation. + recent_scanned means recent # of scans to lru. + showing for better debug please see the code for meanings. + + 6. Hierarchy support The memory controller supports a deep hierarchy and hierarchical accounting. diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b8c1e5acc25a..af28e128b749 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1816,6 +1816,36 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, cb->fill(cb, "unevictable", unevictable * PAGE_SIZE); } + +#ifdef CONFIG_DEBUG_VM + cb->fill(cb, "inactive_ratio", mem_cont->inactive_ratio); + + { + int nid, zid; + struct mem_cgroup_per_zone *mz; + unsigned long recent_rotated[2] = {0, 0}; + unsigned long recent_scanned[2] = {0, 0}; + + for_each_online_node(nid) + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + mz = mem_cgroup_zoneinfo(mem_cont, nid, zid); + + recent_rotated[0] += + mz->reclaim_stat.recent_rotated[0]; + recent_rotated[1] += + mz->reclaim_stat.recent_rotated[1]; + recent_scanned[0] += + mz->reclaim_stat.recent_scanned[0]; + recent_scanned[1] += + mz->reclaim_stat.recent_scanned[1]; + } + cb->fill(cb, "recent_rotated_anon", recent_rotated[0]); + cb->fill(cb, "recent_rotated_file", recent_rotated[1]); + cb->fill(cb, "recent_scanned_anon", recent_scanned[0]); + cb->fill(cb, "recent_scanned_file", recent_scanned[1]); + } +#endif + return 0; } -- cgit v1.2.3 From a7885eb8ad465ec9db99ac5b5e6680f0ca8e11c8 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Wed, 7 Jan 2009 18:08:24 -0800 Subject: memcg: swappiness Currently, /proc/sys/vm/swappiness can change swappiness ratio for global reclaim. However, memcg reclaim doesn't have tuning parameter for itself. In general, the optimal swappiness depend on workload. (e.g. hpc workload need to low swappiness than the others.) Then, per cgroup swappiness improve administrator tunability. Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: KOSAKI Motohiro Cc: Balbir Singh Cc: Daisuke Nishimura Cc: Hugh Dickins Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/controllers/memory.txt | 9 +++++ include/linux/swap.h | 3 +- mm/memcontrol.c | 78 ++++++++++++++++++++++++++++++++---- mm/vmscan.c | 7 ++-- 4 files changed, 86 insertions(+), 11 deletions(-) (limited to 'Documentation') diff --git a/Documentation/controllers/memory.txt b/Documentation/controllers/memory.txt index d71745cc2f00..e1501964df1e 100644 --- a/Documentation/controllers/memory.txt +++ b/Documentation/controllers/memory.txt @@ -314,6 +314,15 @@ will be charged as a new owner of it. showing for better debug please see the code for meanings. +5.3 swappiness + Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only. + + Following cgroup's swapiness can't be changed. + - root cgroup (uses /proc/sys/vm/swappiness). + - a cgroup which uses hierarchy and it has child cgroup. + - a cgroup which uses hierarchy and not the root of hierarchy. + + 6. Hierarchy support The memory controller supports a deep hierarchy and hierarchical accounting. diff --git a/include/linux/swap.h b/include/linux/swap.h index be938ce4895a..4ccca25d0f05 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -214,7 +214,8 @@ static inline void lru_cache_add_active_file(struct page *page) extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask); extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem, - gfp_t gfp_mask, bool noswap); + gfp_t gfp_mask, bool noswap, + unsigned int swappiness); extern int __isolate_lru_page(struct page *page, int mode, int file); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 027c0dd7a83e..ab2ecbb95b8d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -164,6 +164,9 @@ struct mem_cgroup { int obsolete; atomic_t refcnt; + unsigned int swappiness; + + unsigned int inactive_ratio; /* @@ -636,6 +639,22 @@ static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem) return false; } +static unsigned int get_swappiness(struct mem_cgroup *memcg) +{ + struct cgroup *cgrp = memcg->css.cgroup; + unsigned int swappiness; + + /* root ? */ + if (cgrp->parent == NULL) + return vm_swappiness; + + spin_lock(&memcg->reclaim_param_lock); + swappiness = memcg->swappiness; + spin_unlock(&memcg->reclaim_param_lock); + + return swappiness; +} + /* * Dance down the hierarchy if needed to reclaim memory. We remember the * last child we reclaimed from, so that we don't end up penalizing @@ -656,7 +675,8 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, * but there might be left over accounting, even after children * have left. */ - ret = try_to_free_mem_cgroup_pages(root_mem, gfp_mask, noswap); + ret = try_to_free_mem_cgroup_pages(root_mem, gfp_mask, noswap, + get_swappiness(root_mem)); if (mem_cgroup_check_under_limit(root_mem)) return 0; if (!root_mem->use_hierarchy) @@ -672,7 +692,8 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, cgroup_unlock(); continue; } - ret = try_to_free_mem_cgroup_pages(next_mem, gfp_mask, noswap); + ret = try_to_free_mem_cgroup_pages(next_mem, gfp_mask, noswap, + get_swappiness(next_mem)); if (mem_cgroup_check_under_limit(root_mem)) return 0; cgroup_lock(); @@ -1400,7 +1421,8 @@ int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask) rcu_read_unlock(); do { - progress = try_to_free_mem_cgroup_pages(mem, gfp_mask, true); + progress = try_to_free_mem_cgroup_pages(mem, gfp_mask, true, + get_swappiness(mem)); progress += mem_cgroup_check_under_limit(mem); } while (!progress && --retry); @@ -1468,7 +1490,9 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, break; progress = try_to_free_mem_cgroup_pages(memcg, - GFP_KERNEL, false); + GFP_KERNEL, + false, + get_swappiness(memcg)); if (!progress) retry_count--; } @@ -1512,7 +1536,8 @@ int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, break; oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); - try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL, true); + try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL, true, + get_swappiness(memcg)); curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); if (curusage >= oldusage) retry_count--; @@ -1643,8 +1668,8 @@ try_to_free: ret = -EINTR; goto out; } - progress = try_to_free_mem_cgroup_pages(mem, - GFP_KERNEL, false); + progress = try_to_free_mem_cgroup_pages(mem, GFP_KERNEL, + false, get_swappiness(mem)); if (!progress) { nr_retries--; /* maybe some writeback is necessary */ @@ -1864,6 +1889,37 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, return 0; } +static u64 mem_cgroup_swappiness_read(struct cgroup *cgrp, struct cftype *cft) +{ + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + + return get_swappiness(memcg); +} + +static int mem_cgroup_swappiness_write(struct cgroup *cgrp, struct cftype *cft, + u64 val) +{ + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *parent; + if (val > 100) + return -EINVAL; + + if (cgrp->parent == NULL) + return -EINVAL; + + parent = mem_cgroup_from_cont(cgrp->parent); + /* If under hierarchy, only empty-root can set this value */ + if ((parent->use_hierarchy) || + (memcg->use_hierarchy && !list_empty(&cgrp->children))) + return -EINVAL; + + spin_lock(&memcg->reclaim_param_lock); + memcg->swappiness = val; + spin_unlock(&memcg->reclaim_param_lock); + + return 0; +} + static struct cftype mem_cgroup_files[] = { { @@ -1902,6 +1958,11 @@ static struct cftype mem_cgroup_files[] = { .write_u64 = mem_cgroup_hierarchy_write, .read_u64 = mem_cgroup_hierarchy_read, }, + { + .name = "swappiness", + .read_u64 = mem_cgroup_swappiness_read, + .write_u64 = mem_cgroup_swappiness_write, + }, }; #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP @@ -2093,6 +2154,9 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) mem->last_scanned_child = NULL; spin_lock_init(&mem->reclaim_param_lock); + if (parent) + mem->swappiness = get_swappiness(parent); + return &mem->css; free_out: for_each_node_state(node, N_POSSIBLE) diff --git a/mm/vmscan.c b/mm/vmscan.c index f03c239440ad..ece2f405187f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1707,14 +1707,15 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, #ifdef CONFIG_CGROUP_MEM_RES_CTLR unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, - gfp_t gfp_mask, - bool noswap) + gfp_t gfp_mask, + bool noswap, + unsigned int swappiness) { struct scan_control sc = { .may_writepage = !laptop_mode, .may_swap = 1, .swap_cluster_max = SWAP_CLUSTER_MAX, - .swappiness = vm_swappiness, + .swappiness = swappiness, .order = 0, .mem_cgroup = mem_cont, .isolate_pages = mem_cgroup_isolate_pages, -- cgit v1.2.3 From 9836d89191edd4887ed026a9ce53d9dfac62ec1c Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 7 Jan 2009 18:08:27 -0800 Subject: memcg: explain details and test document Documentation for implementation details and how to test. Just an example. feel free to modify, add, remove lines. Signed-off-by: KAMEZAWA Hiroyuki Cc: Balbir Singh Cc: Daisuke Nishimura Cc: Hugh Dickins Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/controllers/memcg_test.txt | 311 +++++++++++++++++++++++++++++++ 1 file changed, 311 insertions(+) create mode 100644 Documentation/controllers/memcg_test.txt (limited to 'Documentation') diff --git a/Documentation/controllers/memcg_test.txt b/Documentation/controllers/memcg_test.txt new file mode 100644 index 000000000000..c91f69b0b549 --- /dev/null +++ b/Documentation/controllers/memcg_test.txt @@ -0,0 +1,311 @@ +Memory Resource Controller(Memcg) Implementation Memo. +Last Updated: 2008/12/10 +Base Kernel Version: based on 2.6.28-rc7-mm. + +Because VM is getting complex (one of reasons is memcg...), memcg's behavior +is complex. This is a document for memcg's internal behavior. +Please note that implementation details can be changed. + +(*) Topics on API should be in Documentation/controllers/memory.txt) + +0. How to record usage ? + 2 objects are used. + + page_cgroup ....an object per page. + Allocated at boot or memory hotplug. Freed at memory hot removal. + + swap_cgroup ... an entry per swp_entry. + Allocated at swapon(). Freed at swapoff(). + + The page_cgroup has USED bit and double count against a page_cgroup never + occurs. swap_cgroup is used only when a charged page is swapped-out. + +1. Charge + + a page/swp_entry may be charged (usage += PAGE_SIZE) at + + mem_cgroup_newpage_charge() + Called at new page fault and Copy-On-Write. + + mem_cgroup_try_charge_swapin() + Called at do_swap_page() (page fault on swap entry) and swapoff. + Followed by charge-commit-cancel protocol. (With swap accounting) + At commit, a charge recorded in swap_cgroup is removed. + + mem_cgroup_cache_charge() + Called at add_to_page_cache() + + mem_cgroup_cache_charge_swapin() + Called at shmem's swapin. + + mem_cgroup_prepare_migration() + Called before migration. "extra" charge is done and followed by + charge-commit-cancel protocol. + At commit, charge against oldpage or newpage will be committed. + +2. Uncharge + a page/swp_entry may be uncharged (usage -= PAGE_SIZE) by + + mem_cgroup_uncharge_page() + Called when an anonymous page is fully unmapped. I.e., mapcount goes + to 0. If the page is SwapCache, uncharge is delayed until + mem_cgroup_uncharge_swapcache(). + + mem_cgroup_uncharge_cache_page() + Called when a page-cache is deleted from radix-tree. If the page is + SwapCache, uncharge is delayed until mem_cgroup_uncharge_swapcache(). + + mem_cgroup_uncharge_swapcache() + Called when SwapCache is removed from radix-tree. The charge itself + is moved to swap_cgroup. (If mem+swap controller is disabled, no + charge to swap occurs.) + + mem_cgroup_uncharge_swap() + Called when swp_entry's refcnt goes down to 0. A charge against swap + disappears. + + mem_cgroup_end_migration(old, new) + At success of migration old is uncharged (if necessary), a charge + to new page is committed. At failure, charge to old page is committed. + +3. charge-commit-cancel + In some case, we can't know this "charge" is valid or not at charging + (because of races). + To handle such case, there are charge-commit-cancel functions. + mem_cgroup_try_charge_XXX + mem_cgroup_commit_charge_XXX + mem_cgroup_cancel_charge_XXX + these are used in swap-in and migration. + + At try_charge(), there are no flags to say "this page is charged". + at this point, usage += PAGE_SIZE. + + At commit(), the function checks the page should be charged or not + and set flags or avoid charging.(usage -= PAGE_SIZE) + + At cancel(), simply usage -= PAGE_SIZE. + +Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y. + +4. Anonymous + Anonymous page is newly allocated at + - page fault into MAP_ANONYMOUS mapping. + - Copy-On-Write. + It is charged right after it's allocated before doing any page table + related operations. Of course, it's uncharged when another page is used + for the fault address. + + At freeing anonymous page (by exit() or munmap()), zap_pte() is called + and pages for ptes are freed one by one.(see mm/memory.c). Uncharges + are done at page_remove_rmap() when page_mapcount() goes down to 0. + + Another page freeing is by page-reclaim (vmscan.c) and anonymous + pages are swapped out. In this case, the page is marked as + PageSwapCache(). uncharge() routine doesn't uncharge the page marked + as SwapCache(). It's delayed until __delete_from_swap_cache(). + + 4.1 Swap-in. + At swap-in, the page is taken from swap-cache. There are 2 cases. + + (a) If the SwapCache is newly allocated and read, it has no charges. + (b) If the SwapCache has been mapped by processes, it has been + charged already. + + In case (a), we charge it. In case (b), we don't charge it. + (But racy state between (a) and (b) exists. We do check it.) + At charging, a charge recorded in swap_cgroup is moved to page_cgroup. + + 4.2 Swap-out. + At swap-out, typical state transition is below. + + (a) add to swap cache. (marked as SwapCache) + swp_entry's refcnt += 1. + (b) fully unmapped. + swp_entry's refcnt += # of ptes. + (c) write back to swap. + (d) delete from swap cache. (remove from SwapCache) + swp_entry's refcnt -= 1. + + + At (b), the page is marked as SwapCache and not uncharged. + At (d), the page is removed from SwapCache and a charge in page_cgroup + is moved to swap_cgroup. + + Finally, at task exit, + (e) zap_pte() is called and swp_entry's refcnt -=1 -> 0. + Here, a charge in swap_cgroup disappears. + +5. Page Cache + Page Cache is charged at + - add_to_page_cache_locked(). + + uncharged at + - __remove_from_page_cache(). + + The logic is very clear. (About migration, see below) + Note: __remove_from_page_cache() is called by remove_from_page_cache() + and __remove_mapping(). + +6. Shmem(tmpfs) Page Cache + Memcg's charge/uncharge have special handlers of shmem. The best way + to understand shmem's page state transition is to read mm/shmem.c. + But brief explanation of the behavior of memcg around shmem will be + helpful to understand the logic. + + Shmem's page (just leaf page, not direct/indirect block) can be on + - radix-tree of shmem's inode. + - SwapCache. + - Both on radix-tree and SwapCache. This happens at swap-in + and swap-out, + + It's charged when... + - A new page is added to shmem's radix-tree. + - A swp page is read. (move a charge from swap_cgroup to page_cgroup) + It's uncharged when + - A page is removed from radix-tree and not SwapCache. + - When SwapCache is removed, a charge is moved to swap_cgroup. + - When swp_entry's refcnt goes down to 0, a charge in swap_cgroup + disappears. + +7. Page Migration + One of the most complicated functions is page-migration-handler. + Memcg has 2 routines. Assume that we are migrating a page's contents + from OLDPAGE to NEWPAGE. + + Usual migration logic is.. + (a) remove the page from LRU. + (b) allocate NEWPAGE (migration target) + (c) lock by lock_page(). + (d) unmap all mappings. + (e-1) If necessary, replace entry in radix-tree. + (e-2) move contents of a page. + (f) map all mappings again. + (g) pushback the page to LRU. + (-) OLDPAGE will be freed. + + Before (g), memcg should complete all necessary charge/uncharge to + NEWPAGE/OLDPAGE. + + The point is.... + - If OLDPAGE is anonymous, all charges will be dropped at (d) because + try_to_unmap() drops all mapcount and the page will not be + SwapCache. + + - If OLDPAGE is SwapCache, charges will be kept at (g) because + __delete_from_swap_cache() isn't called at (e-1) + + - If OLDPAGE is page-cache, charges will be kept at (g) because + remove_from_swap_cache() isn't called at (e-1) + + memcg provides following hooks. + + - mem_cgroup_prepare_migration(OLDPAGE) + Called after (b) to account a charge (usage += PAGE_SIZE) against + memcg which OLDPAGE belongs to. + + - mem_cgroup_end_migration(OLDPAGE, NEWPAGE) + Called after (f) before (g). + If OLDPAGE is used, commit OLDPAGE again. If OLDPAGE is already + charged, a charge by prepare_migration() is automatically canceled. + If NEWPAGE is used, commit NEWPAGE and uncharge OLDPAGE. + + But zap_pte() (by exit or munmap) can be called while migration, + we have to check if OLDPAGE/NEWPAGE is a valid page after commit(). + +8. LRU + Each memcg has its own private LRU. Now, it's handling is under global + VM's control (means that it's handled under global zone->lru_lock). + Almost all routines around memcg's LRU is called by global LRU's + list management functions under zone->lru_lock(). + + A special function is mem_cgroup_isolate_pages(). This scans + memcg's private LRU and call __isolate_lru_page() to extract a page + from LRU. + (By __isolate_lru_page(), the page is removed from both of global and + private LRU.) + + +9. Typical Tests. + + Tests for racy cases. + + 9.1 Small limit to memcg. + When you do test to do racy case, it's good test to set memcg's limit + to be very small rather than GB. Many races found in the test under + xKB or xxMB limits. + (Memory behavior under GB and Memory behavior under MB shows very + different situation.) + + 9.2 Shmem + Historically, memcg's shmem handling was poor and we saw some amount + of troubles here. This is because shmem is page-cache but can be + SwapCache. Test with shmem/tmpfs is always good test. + + 9.3 Migration + For NUMA, migration is an another special case. To do easy test, cpuset + is useful. Following is a sample script to do migration. + + mount -t cgroup -o cpuset none /opt/cpuset + + mkdir /opt/cpuset/01 + echo 1 > /opt/cpuset/01/cpuset.cpus + echo 0 > /opt/cpuset/01/cpuset.mems + echo 1 > /opt/cpuset/01/cpuset.memory_migrate + mkdir /opt/cpuset/02 + echo 1 > /opt/cpuset/02/cpuset.cpus + echo 1 > /opt/cpuset/02/cpuset.mems + echo 1 > /opt/cpuset/02/cpuset.memory_migrate + + In above set, when you moves a task from 01 to 02, page migration to + node 0 to node 1 will occur. Following is a script to migrate all + under cpuset. + -- + move_task() + { + for pid in $1 + do + /bin/echo $pid >$2/tasks 2>/dev/null + echo -n $pid + echo -n " " + done + echo END + } + + G1_TASK=`cat ${G1}/tasks` + G2_TASK=`cat ${G2}/tasks` + move_task "${G1_TASK}" ${G2} & + -- + 9.4 Memory hotplug. + memory hotplug test is one of good test. + to offline memory, do following. + # echo offline > /sys/devices/system/memory/memoryXXX/state + (XXX is the place of memory) + This is an easy way to test page migration, too. + + 9.5 mkdir/rmdir + When using hierarchy, mkdir/rmdir test should be done. + Use tests like the following. + + echo 1 >/opt/cgroup/01/memory/use_hierarchy + mkdir /opt/cgroup/01/child_a + mkdir /opt/cgroup/01/child_b + + set limit to 01. + add limit to 01/child_b + run jobs under child_a and child_b + + create/delete following groups at random while jobs are running. + /opt/cgroup/01/child_a/child_aa + /opt/cgroup/01/child_b/child_bb + /opt/cgroup/01/child_c + + running new jobs in new group is also good. + + 9.6 Mount with other subsystems. + Mounting with other subsystems is a good test because there is a + race and lock dependency with other cgroup subsystems. + + example) + # mount -t cgroup none /cgroup -t cpuset,memory,cpu,devices + + and do task move, mkdir, rmdir etc...under this. -- cgit v1.2.3 From 03f3c433648a97ae7c86be789edba67690f6ea60 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 7 Jan 2009 18:08:31 -0800 Subject: memcg: fix swap accounting leak Fix swapin charge operation of memcg. Now, memcg has hooks to swap-out operation and checks SwapCache is really unused or not. That check depends on contents of struct page. I.e. If PageAnon(page) && page_mapped(page), the page is recoginized as still-in-use. Now, reuse_swap_page() calles delete_from_swap_cache() before establishment of any rmap. Then, in followinig sequence (Page fault with WRITE) try_charge() (charge += PAGESIZE) commit_charge() (Check page_cgroup is used or not..) reuse_swap_page() -> delete_from_swapcache() -> mem_cgroup_uncharge_swapcache() (charge -= PAGESIZE) ...... New charge is uncharged soon.... To avoid this, move commit_charge() after page_mapcount() goes up to 1. By this, try_charge() (usage += PAGESIZE) reuse_swap_page() (may usage -= PAGESIZE if PCG_USED is set) commit_charge() (If page_cgroup is not marked as PCG_USED, add new charge.) Accounting will be correct. Changelog (v2) -> (v3) - fixed invalid charge to swp_entry==0. - updated documentation. Changelog (v1) -> (v2) - fixed comment. [nishimura@mxp.nes.nec.co.jp: swap accounting leak doc fix] Signed-off-by: KAMEZAWA Hiroyuki Acked-by: Balbir Singh Tested-by: Balbir Singh Cc: Hugh Dickins Cc: Daisuke Nishimura Signed-off-by: Daisuke Nishimura Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/controllers/memcg_test.txt | 41 ++++++++++++++++++++++++++++---- mm/memcontrol.c | 7 +++--- mm/memory.c | 11 +++++---- 3 files changed, 46 insertions(+), 13 deletions(-) (limited to 'Documentation') diff --git a/Documentation/controllers/memcg_test.txt b/Documentation/controllers/memcg_test.txt index c91f69b0b549..08d4d3ea0d79 100644 --- a/Documentation/controllers/memcg_test.txt +++ b/Documentation/controllers/memcg_test.txt @@ -1,6 +1,6 @@ Memory Resource Controller(Memcg) Implementation Memo. -Last Updated: 2008/12/10 -Base Kernel Version: based on 2.6.28-rc7-mm. +Last Updated: 2008/12/15 +Base Kernel Version: based on 2.6.28-rc8-mm. Because VM is getting complex (one of reasons is memcg...), memcg's behavior is complex. This is a document for memcg's internal behavior. @@ -111,9 +111,40 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y. (b) If the SwapCache has been mapped by processes, it has been charged already. - In case (a), we charge it. In case (b), we don't charge it. - (But racy state between (a) and (b) exists. We do check it.) - At charging, a charge recorded in swap_cgroup is moved to page_cgroup. + This swap-in is one of the most complicated work. In do_swap_page(), + following events occur when pte is unchanged. + + (1) the page (SwapCache) is looked up. + (2) lock_page() + (3) try_charge_swapin() + (4) reuse_swap_page() (may call delete_swap_cache()) + (5) commit_charge_swapin() + (6) swap_free(). + + Considering following situation for example. + + (A) The page has not been charged before (2) and reuse_swap_page() + doesn't call delete_from_swap_cache(). + (B) The page has not been charged before (2) and reuse_swap_page() + calls delete_from_swap_cache(). + (C) The page has been charged before (2) and reuse_swap_page() doesn't + call delete_from_swap_cache(). + (D) The page has been charged before (2) and reuse_swap_page() calls + delete_from_swap_cache(). + + memory.usage/memsw.usage changes to this page/swp_entry will be + Case (A) (B) (C) (D) + Event + Before (2) 0/ 1 0/ 1 1/ 1 1/ 1 + =========================================== + (3) +1/+1 +1/+1 +1/+1 +1/+1 + (4) - 0/ 0 - -1/ 0 + (5) 0/-1 0/ 0 -1/-1 0/ 0 + (6) - 0/-1 - 0/-1 + =========================================== + Result 1/ 1 1/ 1 1/ 1 1/ 1 + + In any cases, charges to this page should be 1/ 1. 4.2 Swap-out. At swap-out, typical state transition is below. diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a7ecf23150c5..0ed61e27d526 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1169,10 +1169,11 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr) /* * Now swap is on-memory. This means this page may be * counted both as mem and swap....double count. - * Fix it by uncharging from memsw. This SwapCache is stable - * because we're still under lock_page(). + * Fix it by uncharging from memsw. Basically, this SwapCache is stable + * under lock_page(). But in do_swap_page()::memory.c, reuse_swap_page() + * may call delete_from_swap_cache() before reach here. */ - if (do_swap_account) { + if (do_swap_account && PageSwapCache(page)) { swp_entry_t ent = {.val = page_private(page)}; struct mem_cgroup *memcg; memcg = swap_cgroup_record(ent, NULL); diff --git a/mm/memory.c b/mm/memory.c index e5bfbe6b594c..e009ce870859 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2457,22 +2457,23 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, * while the page is counted on swap but not yet in mapcount i.e. * before page_add_anon_rmap() and swap_free(); try_to_free_swap() * must be called after the swap_free(), or it will never succeed. - * And mem_cgroup_commit_charge_swapin(), which uses the swp_entry - * in page->private, must be called before reuse_swap_page(), - * which may delete_from_swap_cache(). + * Because delete_from_swap_page() may be called by reuse_swap_page(), + * mem_cgroup_commit_charge_swapin() may not be able to find swp_entry + * in page->private. In this case, a record in swap_cgroup is silently + * discarded at swap_free(). */ - mem_cgroup_commit_charge_swapin(page, ptr); inc_mm_counter(mm, anon_rss); pte = mk_pte(page, vma->vm_page_prot); if (write_access && reuse_swap_page(page)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); write_access = 0; } - flush_icache_page(vma, page); set_pte_at(mm, address, page_table, pte); page_add_anon_rmap(page, vma, address); + /* It's better to call commit-charge after rmap is established */ + mem_cgroup_commit_charge_swapin(page, ptr); swap_free(entry); if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) -- cgit v1.2.3 From 999cd8a450f8f93701669a61cac4d3b19eca07e8 Mon Sep 17 00:00:00 2001 From: Paul Menage Date: Wed, 7 Jan 2009 18:08:36 -0800 Subject: cgroups: add a per-subsystem hierarchy_mutex These patches introduce new locking/refcount support for cgroups to reduce the need for subsystems to call cgroup_lock(). This will ultimately allow the atomicity of cgroup_rmdir() (which was removed recently) to be restored. These three patches give: 1/3 - introduce a per-subsystem hierarchy_mutex which a subsystem can use to prevent changes to its own cgroup tree 2/3 - use hierarchy_mutex in place of calling cgroup_lock() in the memory controller 3/3 - introduce a css_tryget() function similar to the one recently proposed by Kamezawa, but avoiding spurious refcount failures in the event of a race between a css_tryget() and an unsuccessful cgroup_rmdir() Future patches will likely involve: - using hierarchy mutex in place of cgroup_lock() in more subsystems where appropriate - restoring the atomicity of cgroup_rmdir() with respect to cgroup_create() This patch: Add a hierarchy_mutex to the cgroup_subsys object that protects changes to the hierarchy observed by that subsystem. It is taken by the cgroup subsystem (in addition to cgroup_mutex) for the following operations: - linking a cgroup into that subsystem's cgroup tree - unlinking a cgroup from that subsystem's cgroup tree - moving the subsystem to/from a hierarchy (including across the bind() callback) Thus if the subsystem holds its own hierarchy_mutex, it can safely traverse its own hierarchy. Signed-off-by: Paul Menage Tested-by: KAMEZAWA Hiroyuki Cc: Li Zefan Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/cgroups.txt | 2 +- include/linux/cgroup.h | 17 ++++++++++++++++- kernel/cgroup.c | 37 +++++++++++++++++++++++++++++++++++-- 3 files changed, 52 insertions(+), 4 deletions(-) (limited to 'Documentation') diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index 60287e9e9d27..e33ee74eee77 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -528,7 +528,7 @@ example in cpusets, no task may attach before 'cpus' and 'mems' are set up. void bind(struct cgroup_subsys *ss, struct cgroup *root) -(cgroup_mutex held by caller) +(cgroup_mutex and ss->hierarchy_mutex held by caller) Called when a cgroup subsystem is rebound to a different hierarchy and root cgroup. Currently this will only involve movement between diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 73d1c730c3c4..ce1c1f34c30c 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -340,8 +340,23 @@ struct cgroup_subsys { #define MAX_CGROUP_TYPE_NAMELEN 32 const char *name; - struct cgroupfs_root *root; + /* + * Protects sibling/children links of cgroups in this + * hierarchy, plus protects which hierarchy (or none) the + * subsystem is a part of (i.e. root/sibling). To avoid + * potential deadlocks, the following operations should not be + * undertaken while holding any hierarchy_mutex: + * + * - allocating memory + * - initiating hotplug events + */ + struct mutex hierarchy_mutex; + /* + * Link to parent, and list entry in parent's children. + * Protected by this->hierarchy_mutex and cgroup_lock() + */ + struct cgroupfs_root *root; struct list_head sibling; }; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 83ea4f524be5..8b6379cdf637 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -722,23 +722,26 @@ static int rebind_subsystems(struct cgroupfs_root *root, BUG_ON(cgrp->subsys[i]); BUG_ON(!dummytop->subsys[i]); BUG_ON(dummytop->subsys[i]->cgroup != dummytop); + mutex_lock(&ss->hierarchy_mutex); cgrp->subsys[i] = dummytop->subsys[i]; cgrp->subsys[i]->cgroup = cgrp; list_move(&ss->sibling, &root->subsys_list); ss->root = root; if (ss->bind) ss->bind(ss, cgrp); - + mutex_unlock(&ss->hierarchy_mutex); } else if (bit & removed_bits) { /* We're removing this subsystem */ BUG_ON(cgrp->subsys[i] != dummytop->subsys[i]); BUG_ON(cgrp->subsys[i]->cgroup != cgrp); + mutex_lock(&ss->hierarchy_mutex); if (ss->bind) ss->bind(ss, dummytop); dummytop->subsys[i]->cgroup = dummytop; cgrp->subsys[i] = NULL; subsys[i]->root = &rootnode; list_move(&ss->sibling, &rootnode.subsys_list); + mutex_unlock(&ss->hierarchy_mutex); } else if (bit & final_bits) { /* Subsystem state should already exist */ BUG_ON(!cgrp->subsys[i]); @@ -2338,6 +2341,29 @@ static void init_cgroup_css(struct cgroup_subsys_state *css, cgrp->subsys[ss->subsys_id] = css; } +static void cgroup_lock_hierarchy(struct cgroupfs_root *root) +{ + /* We need to take each hierarchy_mutex in a consistent order */ + int i; + + for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { + struct cgroup_subsys *ss = subsys[i]; + if (ss->root == root) + mutex_lock_nested(&ss->hierarchy_mutex, i); + } +} + +static void cgroup_unlock_hierarchy(struct cgroupfs_root *root) +{ + int i; + + for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { + struct cgroup_subsys *ss = subsys[i]; + if (ss->root == root) + mutex_unlock(&ss->hierarchy_mutex); + } +} + /* * cgroup_create - create a cgroup * @parent: cgroup that will be parent of the new cgroup @@ -2386,7 +2412,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, init_cgroup_css(css, ss, cgrp); } + cgroup_lock_hierarchy(root); list_add(&cgrp->sibling, &cgrp->parent->children); + cgroup_unlock_hierarchy(root); root->number_of_cgroups++; err = cgroup_create_dir(cgrp, dentry, mode); @@ -2504,8 +2532,12 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) if (!list_empty(&cgrp->release_list)) list_del(&cgrp->release_list); spin_unlock(&release_list_lock); - /* delete my sibling from parent->children */ + + cgroup_lock_hierarchy(cgrp->root); + /* delete this cgroup from parent->children */ list_del(&cgrp->sibling); + cgroup_unlock_hierarchy(cgrp->root); + spin_lock(&cgrp->dentry->d_lock); d = dget(cgrp->dentry); spin_unlock(&d->d_lock); @@ -2547,6 +2579,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss) * need to invoke fork callbacks here. */ BUG_ON(!list_empty(&init_task.tasks)); + mutex_init(&ss->hierarchy_mutex); ss->active = 1; } -- cgit v1.2.3 From a5fd9139f74c722a190b3bd69bbd611a8d91b388 Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Wed, 7 Jan 2009 18:08:58 -0800 Subject: w1: add 1-wire master driver for i.MX27 / i.MX31 This patch adds support for the 1-wire master interface for i.MX27 and i.MX31. Signed-off-by: Luotao Fu Signed-off-by: Sascha Hauer Signed-off-by: Evgeniy Polyakov Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/w1/masters/00-INDEX | 2 + Documentation/w1/masters/mxc-w1 | 11 ++ drivers/w1/masters/Kconfig | 6 ++ drivers/w1/masters/Makefile | 2 + drivers/w1/masters/mxc_w1.c | 211 ++++++++++++++++++++++++++++++++++++++ 5 files changed, 232 insertions(+) create mode 100644 Documentation/w1/masters/mxc-w1 create mode 100644 drivers/w1/masters/mxc_w1.c (limited to 'Documentation') diff --git a/Documentation/w1/masters/00-INDEX b/Documentation/w1/masters/00-INDEX index 7b0ceaaad7af..d63fa024ac05 100644 --- a/Documentation/w1/masters/00-INDEX +++ b/Documentation/w1/masters/00-INDEX @@ -4,5 +4,7 @@ ds2482 - The Maxim/Dallas Semiconductor DS2482 provides 1-wire busses. ds2490 - The Maxim/Dallas Semiconductor DS2490 builds USB <-> W1 bridges. +mxc_w1 + - W1 master controller driver found on Freescale MX2/MX3 SoCs w1-gpio - GPIO 1-wire bus master driver. diff --git a/Documentation/w1/masters/mxc-w1 b/Documentation/w1/masters/mxc-w1 new file mode 100644 index 000000000000..97f6199a7f39 --- /dev/null +++ b/Documentation/w1/masters/mxc-w1 @@ -0,0 +1,11 @@ +Kernel driver mxc_w1 +==================== + +Supported chips: + * Freescale MX27, MX31 and probably other i.MX SoCs + Datasheets: + http://www.freescale.com/files/32bit/doc/data_sheet/MCIMX31.pdf?fpsp=1 + http://www.freescale.com/files/dsp/MCIMX27.pdf?fpsp=1 + +Author: Originally based on Freescale code, prepared for mainline by + Sascha Hauer diff --git a/drivers/w1/masters/Kconfig b/drivers/w1/masters/Kconfig index 90616822cd20..96d2f8e4c275 100644 --- a/drivers/w1/masters/Kconfig +++ b/drivers/w1/masters/Kconfig @@ -34,6 +34,12 @@ config W1_MASTER_DS2482 This driver can also be built as a module. If so, the module will be called ds2482. +config W1_MASTER_MXC + tristate "Freescale MXC 1-wire busmaster" + depends on W1 && ARCH_MXC + help + Say Y here to enable MXC 1-wire host + config W1_MASTER_DS1WM tristate "Maxim DS1WM 1-wire busmaster" depends on W1 && ARM && HAVE_CLK diff --git a/drivers/w1/masters/Makefile b/drivers/w1/masters/Makefile index bc4714a75f3a..c5a3e96fcbab 100644 --- a/drivers/w1/masters/Makefile +++ b/drivers/w1/masters/Makefile @@ -5,6 +5,8 @@ obj-$(CONFIG_W1_MASTER_MATROX) += matrox_w1.o obj-$(CONFIG_W1_MASTER_DS2490) += ds2490.o obj-$(CONFIG_W1_MASTER_DS2482) += ds2482.o +obj-$(CONFIG_W1_MASTER_MXC) += mxc_w1.o + obj-$(CONFIG_W1_MASTER_DS1WM) += ds1wm.o obj-$(CONFIG_W1_MASTER_GPIO) += w1-gpio.o obj-$(CONFIG_HDQ_MASTER_OMAP) += omap_hdq.o diff --git a/drivers/w1/masters/mxc_w1.c b/drivers/w1/masters/mxc_w1.c new file mode 100644 index 000000000000..b9d74d0b353e --- /dev/null +++ b/drivers/w1/masters/mxc_w1.c @@ -0,0 +1,211 @@ +/* + * Copyright 2005-2008 Freescale Semiconductor, Inc. All Rights Reserved. + * Copyright 2008 Luotao Fu, kernel@pengutronix.de + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + */ + +#include +#include +#include +#include +#include +#include + +#include "../w1.h" +#include "../w1_int.h" +#include "../w1_log.h" + +/* According to the mx27 Datasheet the reset procedure should take up to about + * 1350us. We set the timeout to 500*100us = 50ms for sure */ +#define MXC_W1_RESET_TIMEOUT 500 + +/* + * MXC W1 Register offsets + */ +#define MXC_W1_CONTROL 0x00 +#define MXC_W1_TIME_DIVIDER 0x02 +#define MXC_W1_RESET 0x04 +#define MXC_W1_COMMAND 0x06 +#define MXC_W1_TXRX 0x08 +#define MXC_W1_INTERRUPT 0x0A +#define MXC_W1_INTERRUPT_EN 0x0C + +struct mxc_w1_device { + void __iomem *regs; + unsigned int clkdiv; + struct clk *clk; + struct w1_bus_master bus_master; +}; + +/* + * this is the low level routine to + * reset the device on the One Wire interface + * on the hardware + */ +static u8 mxc_w1_ds2_reset_bus(void *data) +{ + u8 reg_val; + unsigned int timeout_cnt = 0; + struct mxc_w1_device *dev = data; + + __raw_writeb(0x80, (dev->regs + MXC_W1_CONTROL)); + + while (1) { + reg_val = __raw_readb(dev->regs + MXC_W1_CONTROL); + + if (((reg_val >> 7) & 0x1) == 0 || + timeout_cnt > MXC_W1_RESET_TIMEOUT) + break; + else + timeout_cnt++; + + udelay(100); + } + return (reg_val >> 7) & 0x1; +} + +/* + * this is the low level routine to read/write a bit on the One Wire + * interface on the hardware. It does write 0 if parameter bit is set + * to 0, otherwise a write 1/read. + */ +static u8 mxc_w1_ds2_touch_bit(void *data, u8 bit) +{ + struct mxc_w1_device *mdev = data; + void __iomem *ctrl_addr = mdev->regs + MXC_W1_CONTROL; + unsigned int timeout_cnt = 400; /* Takes max. 120us according to + * datasheet. + */ + + __raw_writeb((1 << (5 - bit)), ctrl_addr); + + while (timeout_cnt--) { + if (!((__raw_readb(ctrl_addr) >> (5 - bit)) & 0x1)) + break; + + udelay(1); + } + + return ((__raw_readb(ctrl_addr)) >> 3) & 0x1; +} + +static int __init mxc_w1_probe(struct platform_device *pdev) +{ + struct mxc_w1_device *mdev; + struct resource *res; + int err = 0; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) + return -ENODEV; + + mdev = kzalloc(sizeof(struct mxc_w1_device), GFP_KERNEL); + if (!mdev) + return -ENOMEM; + + mdev->clk = clk_get(&pdev->dev, "owire_clk"); + if (!mdev->clk) { + err = -ENODEV; + goto failed_clk; + } + + mdev->clkdiv = (clk_get_rate(mdev->clk) / 1000000) - 1; + + res = request_mem_region(res->start, resource_size(res), + "mxc_w1"); + if (!res) { + err = -EBUSY; + goto failed_req; + } + + mdev->regs = ioremap(res->start, resource_size(res)); + if (!mdev->regs) { + printk(KERN_ERR "Cannot map frame buffer registers\n"); + goto failed_ioremap; + } + + clk_enable(mdev->clk); + __raw_writeb(mdev->clkdiv, mdev->regs + MXC_W1_TIME_DIVIDER); + + mdev->bus_master.data = mdev; + mdev->bus_master.reset_bus = mxc_w1_ds2_reset_bus; + mdev->bus_master.touch_bit = mxc_w1_ds2_touch_bit; + + err = w1_add_master_device(&mdev->bus_master); + + if (err) + goto failed_add; + + platform_set_drvdata(pdev, mdev); + return 0; + +failed_add: + iounmap(mdev->regs); +failed_ioremap: + release_mem_region(res->start, resource_size(res)); +failed_req: + clk_put(mdev->clk); +failed_clk: + kfree(mdev); + return err; +} + +/* + * disassociate the w1 device from the driver + */ +static int mxc_w1_remove(struct platform_device *pdev) +{ + struct mxc_w1_device *mdev = platform_get_drvdata(pdev); + struct resource *res; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + + w1_remove_master_device(&mdev->bus_master); + + iounmap(mdev->regs); + release_mem_region(res->start, resource_size(res)); + clk_disable(mdev->clk); + clk_put(mdev->clk); + + platform_set_drvdata(pdev, NULL); + + return 0; +} + +static struct platform_driver mxc_w1_driver = { + .driver = { + .name = "mxc_w1", + }, + .probe = mxc_w1_probe, + .remove = mxc_w1_remove, +}; + +static int __init mxc_w1_init(void) +{ + return platform_driver_register(&mxc_w1_driver); +} + +static void mxc_w1_exit(void) +{ + platform_driver_unregister(&mxc_w1_driver); +} + +module_init(mxc_w1_init); +module_exit(mxc_w1_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Freescale Semiconductors Inc"); +MODULE_DESCRIPTION("Driver for One-Wire on MXC"); -- cgit v1.2.3 From e4e056aa3518197830c884b85268799b1868e8e3 Mon Sep 17 00:00:00 2001 From: Evgeniy Polyakov Date: Wed, 7 Jan 2009 18:09:02 -0800 Subject: w1: documentation update Signed-off-by: Evgeniy Polyakov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/w1/w1.netlink | 129 +++++++++++++++++++++++++++++++------------- 1 file changed, 91 insertions(+), 38 deletions(-) (limited to 'Documentation') diff --git a/Documentation/w1/w1.netlink b/Documentation/w1/w1.netlink index 3640c7c87d45..d596d406e0a5 100644 --- a/Documentation/w1/w1.netlink +++ b/Documentation/w1/w1.netlink @@ -5,69 +5,122 @@ Message types. ============= There are three types of messages between w1 core and userspace: -1. Events. They are generated each time new master or slave device found - either due to automatic or requested search. -2. Userspace commands. Includes read/write and search/alarm search comamnds. +1. Events. They are generated each time new master or slave device + found either due to automatic or requested search. +2. Userspace commands. 3. Replies to userspace commands. Protocol. ======== -[struct cn_msg] - connector header. It's length field is equal to size of the attached data. +[struct cn_msg] - connector header. + Its length field is equal to size of the attached data [struct w1_netlink_msg] - w1 netlink header. __u8 type - message type. - W1_SLAVE_ADD/W1_SLAVE_REMOVE - slave add/remove events. - W1_MASTER_ADD/W1_MASTER_REMOVE - master add/remove events. - W1_MASTER_CMD - userspace command for bus master device (search/alarm search). - W1_SLAVE_CMD - userspace command for slave device (read/write/ search/alarm search - for bus master device where given slave device found). + W1_LIST_MASTERS + list current bus masters + W1_SLAVE_ADD/W1_SLAVE_REMOVE + slave add/remove events + W1_MASTER_ADD/W1_MASTER_REMOVE + master add/remove events + W1_MASTER_CMD + userspace command for bus master + device (search/alarm search) + W1_SLAVE_CMD + userspace command for slave device + (read/write/touch) __u8 res - reserved - __u16 len - size of attached to this header data. + __u16 len - size of data attached to this header data union { - __u8 id; - slave unique device id + __u8 id[8]; - slave unique device id struct w1_mst { - __u32 id; - master's id. + __u32 id; - master's id __u32 res; - reserved } mst; } id; -[strucrt w1_netlink_cmd] - command for gived master or slave device. +[struct w1_netlink_cmd] - command for given master or slave device. __u8 cmd - command opcode. - W1_CMD_READ - read command. - W1_CMD_WRITE - write command. - W1_CMD_SEARCH - search command. - W1_CMD_ALARM_SEARCH - alarm search command. + W1_CMD_READ - read command + W1_CMD_WRITE - write command + W1_CMD_TOUCH - touch command + (write and sample data back to userspace) + W1_CMD_SEARCH - search command + W1_CMD_ALARM_SEARCH - alarm search command __u8 res - reserved - __u16 len - length of data for this command. - For read command data must be allocated like for write command. - __u8 data[0] - data for this command. + __u16 len - length of data for this command + For read command data must be allocated like for write command + __u8 data[0] - data for this command -Each connector message can include one or more w1_netlink_msg with zero of more attached w1_netlink_cmd messages. +Each connector message can include one or more w1_netlink_msg with +zero or more attached w1_netlink_cmd messages. -For event messages there are no w1_netlink_cmd embedded structures, only connector header -and w1_netlink_msg strucutre with "len" field being zero and filled type (one of event types) -and id - either 8 bytes of slave unique id in host order, or master's id, which is assigned -to bus master device when it is added to w1 core. +For event messages there are no w1_netlink_cmd embedded structures, +only connector header and w1_netlink_msg strucutre with "len" field +being zero and filled type (one of event types) and id: +either 8 bytes of slave unique id in host order, +or master's id, which is assigned to bus master device +when it is added to w1 core. + +Currently replies to userspace commands are only generated for read +command request. One reply is generated exactly for one w1_netlink_cmd +read request. Replies are not combined when sent - i.e. typical reply +messages looks like the following: -Currently replies to userspace commands are only generated for read command request. -One reply is generated exactly for one w1_netlink_cmd read request. -Replies are not combined when sent - i.e. typical reply messages looks like the following: [cn_msg][w1_netlink_msg][w1_netlink_cmd] -cn_msg.len = sizeof(struct w1_netlink_msg) + sizeof(struct w1_netlink_cmd) + cmd->len; +cn_msg.len = sizeof(struct w1_netlink_msg) + + sizeof(struct w1_netlink_cmd) + + cmd->len; w1_netlink_msg.len = sizeof(struct w1_netlink_cmd) + cmd->len; w1_netlink_cmd.len = cmd->len; +Replies to W1_LIST_MASTERS should send a message back to the userspace +which will contain list of all registered master ids in the following +format: + + cn_msg (CN_W1_IDX.CN_W1_VAL as id, len is equal to sizeof(struct + w1_netlink_msg) plus number of masters multipled by 4) + w1_netlink_msg (type: W1_LIST_MASTERS, len is equal to + number of masters multiplied by 4 (u32 size)) + id0 ... idN + + Each message is at most 4k in size, so if number of master devices + exceeds this, it will be split into several messages, + cn.seq will be increased for each one. + +W1 search and alarm search commands. +request: +[cn_msg] + [w1_netlink_msg type = W1_MASTER_CMD + id is equal to the bus master id to use for searching] + [w1_netlink_cmd cmd = W1_CMD_SEARCH or W1_CMD_ALARM_SEARCH] + +reply: + [cn_msg, ack = 1 and increasing, 0 means the last message, + seq is equal to the request seq] + [w1_netlink_msg type = W1_MASTER_CMD] + [w1_netlink_cmd cmd = W1_CMD_SEARCH or W1_CMD_ALARM_SEARCH + len is equal to number of IDs multiplied by 8] + [64bit-id0 ... 64bit-idN] +Length in each header corresponds to the size of the data behind it, so +w1_netlink_cmd->len = N * 8; where N is number of IDs in this message. + Can be zero. +w1_netlink_msg->len = sizeof(struct w1_netlink_cmd) + N * 8; +cn_msg->len = sizeof(struct w1_netlink_msg) + + sizeof(struct w1_netlink_cmd) + + N*8; Operation steps in w1 core when new command is received. ======================================================= -When new message (w1_netlink_msg) is received w1 core detects if it is master of slave request, -according to w1_netlink_msg.type field. +When new message (w1_netlink_msg) is received w1 core detects if it is +master or slave request, according to w1_netlink_msg.type field. Then master or slave device is searched for. -When found, master device (requested or those one on where slave device is found) is locked. -If slave command is requested, then reset/select procedure is started to select given device. +When found, master device (requested or those one on where slave device +is found) is locked. If slave command is requested, then reset/select +procedure is started to select given device. Then all requested in w1_netlink_msg operations are performed one by one. If command requires reply (like read command) it is sent on command completion. @@ -82,8 +135,8 @@ Connector [1] specific documentation. Each connector message includes two u32 fields as "address". w1 uses CN_W1_IDX and CN_W1_VAL defined in include/linux/connector.h header. Each message also includes sequence and acknowledge numbers. -Sequence number for event messages is appropriate bus master sequence number increased with -each event message sent "through" this master. +Sequence number for event messages is appropriate bus master sequence number +increased with each event message sent "through" this master. Sequence number for userspace requests is set by userspace application. Sequence number for reply is the same as was in request, and acknowledge number is set to seq+1. @@ -93,6 +146,6 @@ Additional documantion, source code examples. ============================================ 1. Documentation/connector -2. http://tservice.net.ru/~s0mbre/archive/w1 -This archive includes userspace application w1d.c which -uses read/write/search commands for all master/slave devices found on the bus. +2. http://www.ioremap.net/archive/w1 +This archive includes userspace application w1d.c which uses +read/write/search commands for all master/slave devices found on the bus. -- cgit v1.2.3 From f89735c4e281e8642907b38640c076ae5048f3a6 Mon Sep 17 00:00:00 2001 From: Evgeniy Polyakov Date: Wed, 7 Jan 2009 18:09:04 -0800 Subject: w1: added w1 reset command Command which allows to reset the bus. Signed-off-by: Evgeniy Polyakov Cc: Paul Alfille Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/w1/w1.netlink | 6 ++++++ drivers/w1/w1_netlink.c | 3 +++ drivers/w1/w1_netlink.h | 1 + 3 files changed, 10 insertions(+) (limited to 'Documentation') diff --git a/Documentation/w1/w1.netlink b/Documentation/w1/w1.netlink index d596d406e0a5..2756681b6ef5 100644 --- a/Documentation/w1/w1.netlink +++ b/Documentation/w1/w1.netlink @@ -112,6 +112,12 @@ cn_msg->len = sizeof(struct w1_netlink_msg) + sizeof(struct w1_netlink_cmd) + N*8; +W1 reset command. +[cn_msg] + [w1_netlink_msg type = W1_MASTER_CMD + id is equal to the bus master id to use for searching] + [w1_netlink_cmd cmd = W1_CMD_RESET] + Operation steps in w1 core when new command is received. ======================================================= diff --git a/drivers/w1/w1_netlink.c b/drivers/w1/w1_netlink.c index a94336be7654..f978c7504004 100644 --- a/drivers/w1/w1_netlink.c +++ b/drivers/w1/w1_netlink.c @@ -197,6 +197,9 @@ static int w1_process_command_master(struct w1_master *dev, struct cn_msg *req_m case W1_CMD_TOUCH: err = w1_process_command_io(dev, msg, hdr, cmd); break; + case W1_CMD_RESET: + err = w1_reset_bus(dev); + break; default: cmd->res = EINVAL; cn_netlink_send(msg, 0, GFP_KERNEL); diff --git a/drivers/w1/w1_netlink.h b/drivers/w1/w1_netlink.h index 01d86a71cf32..68a4ff46cb96 100644 --- a/drivers/w1/w1_netlink.h +++ b/drivers/w1/w1_netlink.h @@ -58,6 +58,7 @@ enum w1_commands { W1_CMD_SEARCH, W1_CMD_ALARM_SEARCH, W1_CMD_TOUCH, + W1_CMD_RESET, W1_CMD_MAX, }; -- cgit v1.2.3 From 4037014e3fb71e998189374e19ca141c59d15323 Mon Sep 17 00:00:00 2001 From: Evgeniy Polyakov Date: Wed, 7 Jan 2009 18:09:05 -0800 Subject: w1: send status messages after command processing Send completion status of the commands to the userspace. Message and protocol are described in the documentation. Signed-off-by: Evgeniy Polyakov Cc: Paul Alfille Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/w1/w1.netlink | 29 +++++++++++++++++++++++++ drivers/w1/w1_netlink.c | 53 +++++++++++++++++++++++++++++++++++++++------ drivers/w1/w1_netlink.h | 2 +- 3 files changed, 76 insertions(+), 8 deletions(-) (limited to 'Documentation') diff --git a/Documentation/w1/w1.netlink b/Documentation/w1/w1.netlink index 2756681b6ef5..804445f745ed 100644 --- a/Documentation/w1/w1.netlink +++ b/Documentation/w1/w1.netlink @@ -118,6 +118,35 @@ W1 reset command. id is equal to the bus master id to use for searching] [w1_netlink_cmd cmd = W1_CMD_RESET] + +Command status replies. +====================== + +Each command (either root, master or slave with or without w1_netlink_cmd +structure) will be 'acked' by the w1 core. Format of the reply is the same +as request message except that length parameters do not account for data +requested by the user, i.e. read/write/touch IO requests will not contain +data, so w1_netlink_cmd.len will be 0, w1_netlink_msg.len will be size +of the w1_netlink_cmd structure and cn_msg.len will be equal to the sum +of the sizeof(struct w1_netlink_msg) and sizeof(struct w1_netlink_cmd). +If reply is generated for master or root command (which do not have +w1_netlink_cmd attached), reply will contain only cn_msg and w1_netlink_msg +structires. + +w1_netlink_msg.status field will carry positive error value +(EINVAL for example) or zero in case of success. + +All other fields in every structure will mirror the same parameters in the +request message (except lengths as described above). + +Status reply is generated for every w1_netlink_cmd embedded in the +w1_netlink_msg, if there are no w1_netlink_cmd structures, +reply will be generated for the w1_netlink_msg. + +All w1_netlink_cmd command structures are handled in every w1_netlink_msg, +even if there were errors, only length mismatch interrupts message processing. + + Operation steps in w1 core when new command is received. ======================================================= diff --git a/drivers/w1/w1_netlink.c b/drivers/w1/w1_netlink.c index f978c7504004..fdf72851c574 100644 --- a/drivers/w1/w1_netlink.c +++ b/drivers/w1/w1_netlink.c @@ -152,7 +152,7 @@ static int w1_process_command_io(struct w1_master *dev, struct cn_msg *msg, w1_write_block(dev, cmd->data, cmd->len); break; default: - err = -1; + err = -EINVAL; break; } @@ -195,14 +195,13 @@ static int w1_process_command_master(struct w1_master *dev, struct cn_msg *req_m case W1_CMD_READ: case W1_CMD_WRITE: case W1_CMD_TOUCH: - err = w1_process_command_io(dev, msg, hdr, cmd); + err = w1_process_command_io(dev, req_msg, req_hdr, req_cmd); break; case W1_CMD_RESET: err = w1_reset_bus(dev); break; default: - cmd->res = EINVAL; - cn_netlink_send(msg, 0, GFP_KERNEL); + err = -EINVAL; break; } @@ -246,7 +245,7 @@ static int w1_process_command_root(struct cn_msg *msg, struct w1_netlink_msg *mc w = (struct w1_netlink_msg *)(cn + 1); w->type = W1_LIST_MASTERS; - w->reserved = 0; + w->status = 0; w->len = 0; id = (u32 *)(w + 1); @@ -273,6 +272,40 @@ static int w1_process_command_root(struct cn_msg *msg, struct w1_netlink_msg *mc return 0; } +static int w1_netlink_send_error(struct cn_msg *rcmsg, struct w1_netlink_msg *rmsg, + struct w1_netlink_cmd *rcmd, int error) +{ + struct cn_msg *cmsg; + struct w1_netlink_msg *msg; + struct w1_netlink_cmd *cmd; + + cmsg = kzalloc(sizeof(*msg) + sizeof(*cmd) + sizeof(*cmsg), GFP_KERNEL); + if (!cmsg) + return -ENOMEM; + + msg = (struct w1_netlink_msg *)(cmsg + 1); + cmd = (struct w1_netlink_cmd *)(msg + 1); + + memcpy(cmsg, rcmsg, sizeof(*cmsg)); + cmsg->len = sizeof(*msg); + + memcpy(msg, rmsg, sizeof(*msg)); + msg->len = 0; + msg->status = (short)-error; + + if (rcmd) { + memcpy(cmd, rcmd, sizeof(*cmd)); + cmd->len = 0; + msg->len += sizeof(*cmd); + cmsg->len += sizeof(*cmd); + } + + error = cn_netlink_send(cmsg, 0, GFP_KERNEL); + kfree(cmsg); + + return error; +} + static void w1_cn_callback(void *data) { struct cn_msg *msg = data; @@ -289,6 +322,7 @@ static void w1_cn_callback(void *data) dev = NULL; sl = NULL; + cmd = NULL; memcpy(&id, m->id.id, sizeof(id)); #if 0 @@ -336,9 +370,12 @@ static void w1_cn_callback(void *data) } if (sl) - w1_process_command_slave(sl, msg, m, cmd); + err = w1_process_command_slave(sl, msg, m, cmd); else - w1_process_command_master(dev, msg, m, cmd); + err = w1_process_command_master(dev, msg, m, cmd); + + w1_netlink_send_error(msg, m, cmd, err); + err = 0; cmd_data += cmd->len + sizeof(struct w1_netlink_cmd); mlen -= cmd->len + sizeof(struct w1_netlink_cmd); @@ -349,6 +386,8 @@ out_up: atomic_dec(&sl->refcnt); mutex_unlock(&dev->mutex); out_cont: + if (!cmd || err) + w1_netlink_send_error(msg, m, cmd, err); msg->len -= sizeof(struct w1_netlink_msg) + m->len; m = (struct w1_netlink_msg *)(((u8 *)m) + sizeof(struct w1_netlink_msg) + m->len); diff --git a/drivers/w1/w1_netlink.h b/drivers/w1/w1_netlink.h index 68a4ff46cb96..27e950f935b1 100644 --- a/drivers/w1/w1_netlink.h +++ b/drivers/w1/w1_netlink.h @@ -40,7 +40,7 @@ enum w1_netlink_message_types { struct w1_netlink_msg { __u8 type; - __u8 reserved; + __u8 status; __u16 len; union { __u8 id[8]; -- cgit v1.2.3 From 73ac36ea14fd18ea3dc057e41b16ff31a3c0bd5a Mon Sep 17 00:00:00 2001 From: Coly Li Date: Wed, 7 Jan 2009 18:09:16 -0800 Subject: fix similar typos to successfull When I review ocfs2 code, find there are 2 typos to "successfull". After doing grep "successfull " in kernel tree, 22 typos found totally -- great minds always think alike :) This patch fixes all the similar typos. Thanks for Randy's ack and comments. Signed-off-by: Coly Li Acked-by: Randy Dunlap Acked-by: Roland Dreier Cc: Jeremy Kerr Cc: Jeff Garzik Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: Theodore Ts'o Cc: Mark Fasheh Cc: Vlad Yasevich Cc: Sridhar Samudrala Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/hwmon/abituguru-datasheet | 4 ++-- Documentation/scsi/scsi_fc_transport.txt | 4 ++-- arch/powerpc/platforms/cell/spufs/spufs.h | 2 +- drivers/infiniband/hw/nes/nes_cm.c | 2 +- drivers/isdn/hardware/eicon/debuglib.h | 2 +- drivers/isdn/hardware/eicon/os_4bri.c | 2 +- drivers/isdn/hardware/eicon/os_bri.c | 2 +- drivers/isdn/hardware/eicon/os_pri.c | 2 +- drivers/mtd/ubi/kapi.c | 2 +- drivers/net/wireless/ath5k/dma.c | 2 +- drivers/net/wireless/zd1211rw/zd_mac.c | 2 +- drivers/s390/block/dasd_3990_erp.c | 2 +- drivers/s390/block/dasd_int.h | 2 +- drivers/s390/char/tape_3590.c | 2 +- drivers/s390/cio/cio.c | 2 +- drivers/s390/cio/qdio_main.c | 2 +- fs/ext4/extents.c | 2 +- fs/ocfs2/dlmglue.c | 4 ++-- net/sctp/auth.c | 2 +- 19 files changed, 22 insertions(+), 22 deletions(-) (limited to 'Documentation') diff --git a/Documentation/hwmon/abituguru-datasheet b/Documentation/hwmon/abituguru-datasheet index 4d184f2db0ea..d9251efdcec7 100644 --- a/Documentation/hwmon/abituguru-datasheet +++ b/Documentation/hwmon/abituguru-datasheet @@ -121,7 +121,7 @@ Once all bytes have been read data will hold 0x09, but there is no reason to test for this. Notice that the number of bytes is bank address dependent see above and below. -After completing a successfull read it is advised to put the uGuru back in +After completing a successful read it is advised to put the uGuru back in ready mode, so that it is ready for the next read / write cycle. This way if your program / driver is unloaded and later loaded again the detection algorithm described above will still work. @@ -141,7 +141,7 @@ don't ask why this is the way it is. Once DATA holds 0x01 read CMD it should hold 0xAC now. -After completing a successfull write it is advised to put the uGuru back in +After completing a successful write it is advised to put the uGuru back in ready mode, so that it is ready for the next read / write cycle. This way if your program / driver is unloaded and later loaded again the detection algorithm described above will still work. diff --git a/Documentation/scsi/scsi_fc_transport.txt b/Documentation/scsi/scsi_fc_transport.txt index 38d324d62b25..e5b071d46619 100644 --- a/Documentation/scsi/scsi_fc_transport.txt +++ b/Documentation/scsi/scsi_fc_transport.txt @@ -191,7 +191,7 @@ Vport States: This is equivalent to a driver "attach" on an adapter, which is independent of the adapter's link state. - Instantiation of the vport on the FC link via ELS traffic, etc. - This is equivalent to a "link up" and successfull link initialization. + This is equivalent to a "link up" and successful link initialization. Further information can be found in the interfaces section below for Vport Creation. @@ -320,7 +320,7 @@ Vport Creation: This is equivalent to a driver "attach" on an adapter, which is independent of the adapter's link state. - Instantiation of the vport on the FC link via ELS traffic, etc. - This is equivalent to a "link up" and successfull link initialization. + This is equivalent to a "link up" and successful link initialization. The LLDD's vport_create() function will not synchronously wait for both parts to be fully completed before returning. It must validate that the diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h index 15c62d3ca129..3bf908e2873a 100644 --- a/arch/powerpc/platforms/cell/spufs/spufs.h +++ b/arch/powerpc/platforms/cell/spufs/spufs.h @@ -314,7 +314,7 @@ extern char *isolated_loader; * we need to call spu_release(ctx) before sleeping, and * then spu_acquire(ctx) when awoken. * - * Returns with state_mutex re-acquired when successfull or + * Returns with state_mutex re-acquired when successful or * with -ERESTARTSYS and the state_mutex dropped when interrupted. */ diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c index a812db243477..6ba57e91d7ab 100644 --- a/drivers/infiniband/hw/nes/nes_cm.c +++ b/drivers/infiniband/hw/nes/nes_cm.c @@ -2705,7 +2705,7 @@ int nes_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) sizeof(struct ietf_mpa_frame)); - /* notify OF layer that accept event was successfull */ + /* notify OF layer that accept event was successful */ cm_id->add_ref(cm_id); cm_event.event = IW_CM_EVENT_ESTABLISHED; diff --git a/drivers/isdn/hardware/eicon/debuglib.h b/drivers/isdn/hardware/eicon/debuglib.h index 016410cf2273..8ea587783e14 100644 --- a/drivers/isdn/hardware/eicon/debuglib.h +++ b/drivers/isdn/hardware/eicon/debuglib.h @@ -235,7 +235,7 @@ typedef void ( * DbgOld) (unsigned short, char *, va_list) ; typedef void ( * DbgEv) (unsigned short, unsigned long, va_list) ; typedef void ( * DbgIrq) (unsigned short, int, char *, va_list) ; typedef struct _DbgHandle_ -{ char Registered ; /* driver successfull registered */ +{ char Registered ; /* driver successfully registered */ #define DBG_HANDLE_REG_NEW 0x01 /* this (new) structure */ #define DBG_HANDLE_REG_OLD 0x7f /* old structure (see below) */ char Version; /* version of this structure */ diff --git a/drivers/isdn/hardware/eicon/os_4bri.c b/drivers/isdn/hardware/eicon/os_4bri.c index 7b4ec3f60dbf..c964b8d91ada 100644 --- a/drivers/isdn/hardware/eicon/os_4bri.c +++ b/drivers/isdn/hardware/eicon/os_4bri.c @@ -997,7 +997,7 @@ diva_4bri_start_adapter(PISDN_ADAPTER IoAdapter, diva_xdi_display_adapter_features(IoAdapter->ANum); for (i = 0; i < IoAdapter->tasks; i++) { - DBG_LOG(("A(%d) %s adapter successfull started", + DBG_LOG(("A(%d) %s adapter successfully started", IoAdapter->QuadroList->QuadroAdapter[i]->ANum, (IoAdapter->tasks == 1) ? "BRI 2.0" : "4BRI")) diva_xdi_didd_register_adapter(IoAdapter->QuadroList->QuadroAdapter[i]->ANum); diff --git a/drivers/isdn/hardware/eicon/os_bri.c b/drivers/isdn/hardware/eicon/os_bri.c index f31bba5b16ff..08f01993f46b 100644 --- a/drivers/isdn/hardware/eicon/os_bri.c +++ b/drivers/isdn/hardware/eicon/os_bri.c @@ -736,7 +736,7 @@ diva_bri_start_adapter(PISDN_ADAPTER IoAdapter, IoAdapter->Properties.Features = (word) features; diva_xdi_display_adapter_features(IoAdapter->ANum); - DBG_LOG(("A(%d) BRI adapter successfull started", IoAdapter->ANum)) + DBG_LOG(("A(%d) BRI adapter successfully started", IoAdapter->ANum)) /* Register with DIDD */ diff --git a/drivers/isdn/hardware/eicon/os_pri.c b/drivers/isdn/hardware/eicon/os_pri.c index 903356547b79..5d65405c75f4 100644 --- a/drivers/isdn/hardware/eicon/os_pri.c +++ b/drivers/isdn/hardware/eicon/os_pri.c @@ -513,7 +513,7 @@ diva_pri_start_adapter(PISDN_ADAPTER IoAdapter, diva_xdi_display_adapter_features(IoAdapter->ANum); - DBG_LOG(("A(%d) PRI adapter successfull started", IoAdapter->ANum)) + DBG_LOG(("A(%d) PRI adapter successfully started", IoAdapter->ANum)) /* Register with DIDD */ diff --git a/drivers/mtd/ubi/kapi.c b/drivers/mtd/ubi/kapi.c index 5d9bcf109c13..4abbe573fa40 100644 --- a/drivers/mtd/ubi/kapi.c +++ b/drivers/mtd/ubi/kapi.c @@ -564,7 +564,7 @@ EXPORT_SYMBOL_GPL(ubi_leb_unmap); * @dtype: expected data type * * This function maps an un-mapped logical eraseblock @lnum to a physical - * eraseblock. This means, that after a successfull invocation of this + * eraseblock. This means, that after a successful invocation of this * function the logical eraseblock @lnum will be empty (contain only %0xFF * bytes) and be mapped to a physical eraseblock, even if an unclean reboot * happens. diff --git a/drivers/net/wireless/ath5k/dma.c b/drivers/net/wireless/ath5k/dma.c index 7e2b1a67e5da..b65b4feb2d28 100644 --- a/drivers/net/wireless/ath5k/dma.c +++ b/drivers/net/wireless/ath5k/dma.c @@ -594,7 +594,7 @@ int ath5k_hw_get_isr(struct ath5k_hw *ah, enum ath5k_int *interrupt_mask) * XXX: BMISS interrupts may occur after association. * I found this on 5210 code but it needs testing. If this is * true we should disable them before assoc and re-enable them - * after a successfull assoc + some jiffies. + * after a successful assoc + some jiffies. interrupt_mask &= ~AR5K_INT_BMISS; */ } diff --git a/drivers/net/wireless/zd1211rw/zd_mac.c b/drivers/net/wireless/zd1211rw/zd_mac.c index 9caa96a13586..a611ad857983 100644 --- a/drivers/net/wireless/zd1211rw/zd_mac.c +++ b/drivers/net/wireless/zd1211rw/zd_mac.c @@ -287,7 +287,7 @@ static void zd_op_stop(struct ieee80211_hw *hw) * @skb - a sk-buffer * @flags: extra flags to set in the TX status info * @ackssi: ACK signal strength - * @success - True for successfull transmission of the frame + * @success - True for successful transmission of the frame * * This information calls ieee80211_tx_status_irqsafe() if required by the * control information. It copies the control information into the status diff --git a/drivers/s390/block/dasd_3990_erp.c b/drivers/s390/block/dasd_3990_erp.c index b8f9c00633f3..d82aad5224f0 100644 --- a/drivers/s390/block/dasd_3990_erp.c +++ b/drivers/s390/block/dasd_3990_erp.c @@ -2621,7 +2621,7 @@ dasd_3990_erp_action(struct dasd_ccw_req * cqr) } } - /* double-check if current erp/cqr was successfull */ + /* double-check if current erp/cqr was successful */ if ((cqr->irb.scsw.cmd.cstat == 0x00) && (cqr->irb.scsw.cmd.dstat == (DEV_STAT_CHN_END | DEV_STAT_DEV_END))) { diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 05a14536c369..4a39084d9c95 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -199,7 +199,7 @@ struct dasd_ccw_req { #define DASD_CQR_ERROR 0x82 /* request is completed with error */ #define DASD_CQR_CLEAR_PENDING 0x83 /* request is clear pending */ #define DASD_CQR_CLEARED 0x84 /* request was cleared */ -#define DASD_CQR_SUCCESS 0x85 /* request was successfull */ +#define DASD_CQR_SUCCESS 0x85 /* request was successful */ /* per dasd_ccw_req flags */ diff --git a/drivers/s390/char/tape_3590.c b/drivers/s390/char/tape_3590.c index 4005c44a404c..71605a179d65 100644 --- a/drivers/s390/char/tape_3590.c +++ b/drivers/s390/char/tape_3590.c @@ -801,7 +801,7 @@ tape_3590_done(struct tape_device *device, struct tape_request *request) static inline int tape_3590_erp_succeded(struct tape_device *device, struct tape_request *request) { - DBF_EVENT(3, "Error Recovery successfull for %s\n", + DBF_EVENT(3, "Error Recovery successful for %s\n", tape_op_verbose[request->op]); return tape_3590_done(device, request); } diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c index 06b71823f399..659f8a791656 100644 --- a/drivers/s390/cio/cio.c +++ b/drivers/s390/cio/cio.c @@ -379,7 +379,7 @@ int cio_commit_config(struct subchannel *sch) if (ccode < 0) /* -EIO if msch gets a program check. */ return ccode; switch (ccode) { - case 0: /* successfull */ + case 0: /* successful */ if (stsch(sch->schid, &schib) || !css_sch_is_valid(&schib)) return -ENODEV; diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 744f928a59ea..10cb0f8726e5 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -114,7 +114,7 @@ static inline int qdio_check_ccq(struct qdio_q *q, unsigned int ccq) * @count: count of buffers to examine * @auto_ack: automatically acknowledge buffers * - * Returns the number of successfull extracted equal buffer states. + * Returns the number of successfully extracted equal buffer states. * Stops processing if a state is different from the last buffers state. */ static int qdio_do_eqbs(struct qdio_q *q, unsigned char *state, diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index ea2ce3c0ae66..3f54db31cdc2 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2536,7 +2536,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, */ newdepth = ext_depth(inode); /* - * update the extent length after successfull insert of the + * update the extent length after successful insert of the * split extent */ orig_ex.ee_len = cpu_to_le16(ee_len - diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index f731ab491795..b0c4cadd4c45 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -1324,7 +1324,7 @@ again: goto out; } - mlog(0, "lock %s, successfull return from ocfs2_dlm_lock\n", + mlog(0, "lock %s, successful return from ocfs2_dlm_lock\n", lockres->l_name); /* At this point we've gone inside the dlm and need to @@ -2951,7 +2951,7 @@ static int ocfs2_drop_lock(struct ocfs2_super *osb, ocfs2_dlm_dump_lksb(&lockres->l_lksb); BUG(); } - mlog(0, "lock %s, successfull return from ocfs2_dlm_unlock\n", + mlog(0, "lock %s, successful return from ocfs2_dlm_unlock\n", lockres->l_name); ocfs2_wait_on_busy_lock(lockres); diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 20c576f530fa..56935bbc1496 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -489,7 +489,7 @@ int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp) return 0; out_err: - /* Clean up any successfull allocations */ + /* Clean up any successful allocations */ sctp_auth_destroy_hmacs(ep->auth_hmacs); return -ENOMEM; } -- cgit v1.2.3 From 7ad68e2f970fd84d15ad67ce3216aed05f944a9c Mon Sep 17 00:00:00 2001 From: David Brownell Date: Tue, 11 Nov 2008 17:39:02 -0800 Subject: regulator: sysfs attribute reduction (v2) Clean up the sysfs interface to regulators by only exposing the attributes that can be properly displayed. For example: when a particular regulator method is needed to display the value, only create that attribute when that method exists. This cleaned-up interface is much more comprehensible. Most regulators only support a subset of the possible methods, so often more than half the attributes would be meaningless. Many "not defined" values are no longer necessary. (But handling of out-of-range values still looks a bit iffy.) Documentation is updated to reflect that few of the attributes are *always* present, and to briefly explain why a regulator may not have a given attribute. This adds object code, about a dozen bytes more than was removed by the preceding patch, but saves a bunch of per-regulator data associated with the now-removed attributes. So there's a net reduction in memory footprint. Signed-off-by: David Brownell Signed-off-by: Liam Girdwood --- Documentation/ABI/testing/sysfs-class-regulator | 136 ++++++++-------- drivers/regulator/core.c | 196 ++++++++++++++++++------ 2 files changed, 208 insertions(+), 124 deletions(-) (limited to 'Documentation') diff --git a/Documentation/ABI/testing/sysfs-class-regulator b/Documentation/ABI/testing/sysfs-class-regulator index 3731f6f29bcb..873ef1fc1569 100644 --- a/Documentation/ABI/testing/sysfs-class-regulator +++ b/Documentation/ABI/testing/sysfs-class-regulator @@ -3,8 +3,9 @@ Date: April 2008 KernelVersion: 2.6.26 Contact: Liam Girdwood Description: - Each regulator directory will contain a field called - state. This holds the regulator output state. + Some regulator directories will contain a field called + state. This reports the regulator enable status, for + regulators which can report that value. This will be one of the following strings: @@ -18,7 +19,8 @@ Description: 'disabled' means the regulator output is OFF and is not supplying power to the system.. - 'unknown' means software cannot determine the state. + 'unknown' means software cannot determine the state, or + the reported state is invalid. NOTE: this field can be used in conjunction with microvolts and microamps to determine regulator output levels. @@ -53,9 +55,10 @@ Date: April 2008 KernelVersion: 2.6.26 Contact: Liam Girdwood Description: - Each regulator directory will contain a field called + Some regulator directories will contain a field called microvolts. This holds the regulator output voltage setting - measured in microvolts (i.e. E-6 Volts). + measured in microvolts (i.e. E-6 Volts), for regulators + which can report that voltage. NOTE: This value should not be used to determine the regulator output voltage level as this value is the same regardless of @@ -67,9 +70,10 @@ Date: April 2008 KernelVersion: 2.6.26 Contact: Liam Girdwood Description: - Each regulator directory will contain a field called + Some regulator directories will contain a field called microamps. This holds the regulator output current limit - setting measured in microamps (i.e. E-6 Amps). + setting measured in microamps (i.e. E-6 Amps), for regulators + which can report that current. NOTE: This value should not be used to determine the regulator output current level as this value is the same regardless of @@ -81,8 +85,9 @@ Date: April 2008 KernelVersion: 2.6.26 Contact: Liam Girdwood Description: - Each regulator directory will contain a field called - opmode. This holds the regulator operating mode setting. + Some regulator directories will contain a field called + opmode. This holds the current regulator operating mode, + for regulators which can report it. The opmode value can be one of the following strings: @@ -92,7 +97,7 @@ Description: 'standby' 'unknown' - The modes are described in include/linux/regulator/regulator.h + The modes are described in include/linux/regulator/consumer.h NOTE: This value should not be used to determine the regulator output operating mode as this value is the same regardless of @@ -104,9 +109,10 @@ Date: April 2008 KernelVersion: 2.6.26 Contact: Liam Girdwood Description: - Each regulator directory will contain a field called + Some regulator directories will contain a field called min_microvolts. This holds the minimum safe working regulator - output voltage setting for this domain measured in microvolts. + output voltage setting for this domain measured in microvolts, + for regulators which support voltage constraints. NOTE: this will return the string 'constraint not defined' if the power domain has no min microvolts constraint defined by @@ -118,9 +124,10 @@ Date: April 2008 KernelVersion: 2.6.26 Contact: Liam Girdwood Description: - Each regulator directory will contain a field called + Some regulator directories will contain a field called max_microvolts. This holds the maximum safe working regulator - output voltage setting for this domain measured in microvolts. + output voltage setting for this domain measured in microvolts, + for regulators which support voltage constraints. NOTE: this will return the string 'constraint not defined' if the power domain has no max microvolts constraint defined by @@ -132,10 +139,10 @@ Date: April 2008 KernelVersion: 2.6.26 Contact: Liam Girdwood Description: - Each regulator directory will contain a field called + Some regulator directories will contain a field called min_microamps. This holds the minimum safe working regulator output current limit setting for this domain measured in - microamps. + microamps, for regulators which support current constraints. NOTE: this will return the string 'constraint not defined' if the power domain has no min microamps constraint defined by @@ -147,10 +154,10 @@ Date: April 2008 KernelVersion: 2.6.26 Contact: Liam Girdwood Description: - Each regulator directory will contain a field called + Some regulator directories will contain a field called max_microamps. This holds the maximum safe working regulator output current limit setting for this domain measured in - microamps. + microamps, for regulators which support current constraints. NOTE: this will return the string 'constraint not defined' if the power domain has no max microamps constraint defined by @@ -185,7 +192,7 @@ Date: April 2008 KernelVersion: 2.6.26 Contact: Liam Girdwood Description: - Each regulator directory will contain a field called + Some regulator directories will contain a field called requested_microamps. This holds the total requested load current in microamps for this regulator from all its consumer devices. @@ -204,125 +211,102 @@ Date: May 2008 KernelVersion: 2.6.26 Contact: Liam Girdwood Description: - Each regulator directory will contain a field called + Some regulator directories will contain a field called suspend_mem_microvolts. This holds the regulator output voltage setting for this domain measured in microvolts when - the system is suspended to memory. - - NOTE: this will return the string 'not defined' if - the power domain has no suspend to memory voltage defined by - platform code. + the system is suspended to memory, for voltage regulators + implementing suspend voltage configuration constraints. What: /sys/class/regulator/.../suspend_disk_microvolts Date: May 2008 KernelVersion: 2.6.26 Contact: Liam Girdwood Description: - Each regulator directory will contain a field called + Some regulator directories will contain a field called suspend_disk_microvolts. This holds the regulator output voltage setting for this domain measured in microvolts when - the system is suspended to disk. - - NOTE: this will return the string 'not defined' if - the power domain has no suspend to disk voltage defined by - platform code. + the system is suspended to disk, for voltage regulators + implementing suspend voltage configuration constraints. What: /sys/class/regulator/.../suspend_standby_microvolts Date: May 2008 KernelVersion: 2.6.26 Contact: Liam Girdwood Description: - Each regulator directory will contain a field called + Some regulator directories will contain a field called suspend_standby_microvolts. This holds the regulator output voltage setting for this domain measured in microvolts when - the system is suspended to standby. - - NOTE: this will return the string 'not defined' if - the power domain has no suspend to standby voltage defined by - platform code. + the system is suspended to standby, for voltage regulators + implementing suspend voltage configuration constraints. What: /sys/class/regulator/.../suspend_mem_mode Date: May 2008 KernelVersion: 2.6.26 Contact: Liam Girdwood Description: - Each regulator directory will contain a field called + Some regulator directories will contain a field called suspend_mem_mode. This holds the regulator operating mode setting for this domain when the system is suspended to - memory. - - NOTE: this will return the string 'not defined' if - the power domain has no suspend to memory mode defined by - platform code. + memory, for regulators implementing suspend mode + configuration constraints. What: /sys/class/regulator/.../suspend_disk_mode Date: May 2008 KernelVersion: 2.6.26 Contact: Liam Girdwood Description: - Each regulator directory will contain a field called + Some regulator directories will contain a field called suspend_disk_mode. This holds the regulator operating mode - setting for this domain when the system is suspended to disk. - - NOTE: this will return the string 'not defined' if - the power domain has no suspend to disk mode defined by - platform code. + setting for this domain when the system is suspended to disk, + for regulators implementing suspend mode configuration + constraints. What: /sys/class/regulator/.../suspend_standby_mode Date: May 2008 KernelVersion: 2.6.26 Contact: Liam Girdwood Description: - Each regulator directory will contain a field called + Some regulator directories will contain a field called suspend_standby_mode. This holds the regulator operating mode setting for this domain when the system is suspended to - standby. - - NOTE: this will return the string 'not defined' if - the power domain has no suspend to standby mode defined by - platform code. + standby, for regulators implementing suspend mode + configuration constraints. What: /sys/class/regulator/.../suspend_mem_state Date: May 2008 KernelVersion: 2.6.26 Contact: Liam Girdwood Description: - Each regulator directory will contain a field called + Some regulator directories will contain a field called suspend_mem_state. This holds the regulator operating state - when suspended to memory. - - This will be one of the following strings: + when suspended to memory, for regulators implementing suspend + configuration constraints. - 'enabled' - 'disabled' - 'not defined' + This will be one of the same strings reported by + the "state" attribute. What: /sys/class/regulator/.../suspend_disk_state Date: May 2008 KernelVersion: 2.6.26 Contact: Liam Girdwood Description: - Each regulator directory will contain a field called + Some regulator directories will contain a field called suspend_disk_state. This holds the regulator operating state - when suspended to disk. - - This will be one of the following strings: + when suspended to disk, for regulators implementing + suspend configuration constraints. - 'enabled' - 'disabled' - 'not defined' + This will be one of the same strings reported by + the "state" attribute. What: /sys/class/regulator/.../suspend_standby_state Date: May 2008 KernelVersion: 2.6.26 Contact: Liam Girdwood Description: - Each regulator directory will contain a field called + Some regulator directories will contain a field called suspend_standby_state. This holds the regulator operating - state when suspended to standby. - - This will be one of the following strings: + state when suspended to standby, for regulators implementing + suspend configuration constraints. - 'enabled' - 'disabled' - 'not defined' + This will be one of the same strings reported by + the "state" attribute. diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 5109f7d4809a..9a5ff97d158d 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -242,6 +242,7 @@ static ssize_t regulator_uV_show(struct device *dev, return ret; } +static DEVICE_ATTR(microvolts, 0444, regulator_uV_show, NULL); static ssize_t regulator_uA_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -250,6 +251,7 @@ static ssize_t regulator_uA_show(struct device *dev, return sprintf(buf, "%d\n", _regulator_get_current_limit(rdev)); } +static DEVICE_ATTR(microamps, 0444, regulator_uA_show, NULL); static ssize_t regulator_name_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -289,6 +291,7 @@ static ssize_t regulator_opmode_show(struct device *dev, return regulator_print_opmode(buf, _regulator_get_mode(rdev)); } +static DEVICE_ATTR(opmode, 0444, regulator_opmode_show, NULL); static ssize_t regulator_print_state(char *buf, int state) { @@ -307,6 +310,7 @@ static ssize_t regulator_state_show(struct device *dev, return regulator_print_state(buf, _regulator_is_enabled(rdev)); } +static DEVICE_ATTR(state, 0444, regulator_state_show, NULL); static ssize_t regulator_min_uA_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -318,6 +322,7 @@ static ssize_t regulator_min_uA_show(struct device *dev, return sprintf(buf, "%d\n", rdev->constraints->min_uA); } +static DEVICE_ATTR(min_microamps, 0444, regulator_min_uA_show, NULL); static ssize_t regulator_max_uA_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -329,6 +334,7 @@ static ssize_t regulator_max_uA_show(struct device *dev, return sprintf(buf, "%d\n", rdev->constraints->max_uA); } +static DEVICE_ATTR(max_microamps, 0444, regulator_max_uA_show, NULL); static ssize_t regulator_min_uV_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -340,6 +346,7 @@ static ssize_t regulator_min_uV_show(struct device *dev, return sprintf(buf, "%d\n", rdev->constraints->min_uV); } +static DEVICE_ATTR(min_microvolts, 0444, regulator_min_uV_show, NULL); static ssize_t regulator_max_uV_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -351,6 +358,7 @@ static ssize_t regulator_max_uV_show(struct device *dev, return sprintf(buf, "%d\n", rdev->constraints->max_uV); } +static DEVICE_ATTR(max_microvolts, 0444, regulator_max_uV_show, NULL); static ssize_t regulator_total_uA_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -365,6 +373,7 @@ static ssize_t regulator_total_uA_show(struct device *dev, mutex_unlock(&rdev->mutex); return sprintf(buf, "%d\n", uA); } +static DEVICE_ATTR(requested_microamps, 0444, regulator_total_uA_show, NULL); static ssize_t regulator_num_users_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -392,131 +401,106 @@ static ssize_t regulator_suspend_mem_uV_show(struct device *dev, { struct regulator_dev *rdev = dev_get_drvdata(dev); - if (!rdev->constraints) - return sprintf(buf, "not defined\n"); return sprintf(buf, "%d\n", rdev->constraints->state_mem.uV); } +static DEVICE_ATTR(suspend_mem_microvolts, 0444, + regulator_suspend_mem_uV_show, NULL); static ssize_t regulator_suspend_disk_uV_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); - if (!rdev->constraints) - return sprintf(buf, "not defined\n"); return sprintf(buf, "%d\n", rdev->constraints->state_disk.uV); } +static DEVICE_ATTR(suspend_disk_microvolts, 0444, + regulator_suspend_disk_uV_show, NULL); static ssize_t regulator_suspend_standby_uV_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); - if (!rdev->constraints) - return sprintf(buf, "not defined\n"); return sprintf(buf, "%d\n", rdev->constraints->state_standby.uV); } +static DEVICE_ATTR(suspend_standby_microvolts, 0444, + regulator_suspend_standby_uV_show, NULL); static ssize_t regulator_suspend_mem_mode_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); - if (!rdev->constraints) - return sprintf(buf, "not defined\n"); return regulator_print_opmode(buf, rdev->constraints->state_mem.mode); } +static DEVICE_ATTR(suspend_mem_mode, 0444, + regulator_suspend_mem_mode_show, NULL); static ssize_t regulator_suspend_disk_mode_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); - if (!rdev->constraints) - return sprintf(buf, "not defined\n"); return regulator_print_opmode(buf, rdev->constraints->state_disk.mode); } +static DEVICE_ATTR(suspend_disk_mode, 0444, + regulator_suspend_disk_mode_show, NULL); static ssize_t regulator_suspend_standby_mode_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); - if (!rdev->constraints) - return sprintf(buf, "not defined\n"); return regulator_print_opmode(buf, rdev->constraints->state_standby.mode); } +static DEVICE_ATTR(suspend_standby_mode, 0444, + regulator_suspend_standby_mode_show, NULL); static ssize_t regulator_suspend_mem_state_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); - if (!rdev->constraints) - return sprintf(buf, "not defined\n"); - return regulator_print_state(buf, rdev->constraints->state_mem.enabled); } +static DEVICE_ATTR(suspend_mem_state, 0444, + regulator_suspend_mem_state_show, NULL); static ssize_t regulator_suspend_disk_state_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); - if (!rdev->constraints) - return sprintf(buf, "not defined\n"); - return regulator_print_state(buf, rdev->constraints->state_disk.enabled); } +static DEVICE_ATTR(suspend_disk_state, 0444, + regulator_suspend_disk_state_show, NULL); static ssize_t regulator_suspend_standby_state_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); - if (!rdev->constraints) - return sprintf(buf, "not defined\n"); - return regulator_print_state(buf, rdev->constraints->state_standby.enabled); } +static DEVICE_ATTR(suspend_standby_state, 0444, + regulator_suspend_standby_state_show, NULL); + +/* + * These are the only attributes are present for all regulators. + * Other attributes are a function of regulator functionality. + */ static struct device_attribute regulator_dev_attrs[] = { __ATTR(name, 0444, regulator_name_show, NULL), - __ATTR(microvolts, 0444, regulator_uV_show, NULL), - __ATTR(microamps, 0444, regulator_uA_show, NULL), - __ATTR(opmode, 0444, regulator_opmode_show, NULL), - __ATTR(state, 0444, regulator_state_show, NULL), - __ATTR(min_microvolts, 0444, regulator_min_uV_show, NULL), - __ATTR(min_microamps, 0444, regulator_min_uA_show, NULL), - __ATTR(max_microvolts, 0444, regulator_max_uV_show, NULL), - __ATTR(max_microamps, 0444, regulator_max_uA_show, NULL), - __ATTR(requested_microamps, 0444, regulator_total_uA_show, NULL), __ATTR(num_users, 0444, regulator_num_users_show, NULL), __ATTR(type, 0444, regulator_type_show, NULL), - __ATTR(suspend_mem_microvolts, 0444, - regulator_suspend_mem_uV_show, NULL), - __ATTR(suspend_disk_microvolts, 0444, - regulator_suspend_disk_uV_show, NULL), - __ATTR(suspend_standby_microvolts, 0444, - regulator_suspend_standby_uV_show, NULL), - __ATTR(suspend_mem_mode, 0444, - regulator_suspend_mem_mode_show, NULL), - __ATTR(suspend_disk_mode, 0444, - regulator_suspend_disk_mode_show, NULL), - __ATTR(suspend_standby_mode, 0444, - regulator_suspend_standby_mode_show, NULL), - __ATTR(suspend_mem_state, 0444, - regulator_suspend_mem_state_show, NULL), - __ATTR(suspend_disk_state, 0444, - regulator_suspend_disk_state_show, NULL), - __ATTR(suspend_standby_state, 0444, - regulator_suspend_standby_state_show, NULL), __ATTR_NULL, }; @@ -1711,6 +1695,117 @@ int regulator_notifier_call_chain(struct regulator_dev *rdev, } EXPORT_SYMBOL_GPL(regulator_notifier_call_chain); +/* + * To avoid cluttering sysfs (and memory) with useless state, only + * create attributes that can be meaningfully displayed. + */ +static int add_regulator_attributes(struct regulator_dev *rdev) +{ + struct device *dev = &rdev->dev; + struct regulator_ops *ops = rdev->desc->ops; + int status = 0; + + /* some attributes need specific methods to be displayed */ + if (ops->get_voltage) { + status = device_create_file(dev, &dev_attr_microvolts); + if (status < 0) + return status; + } + if (ops->get_current_limit) { + status = device_create_file(dev, &dev_attr_microamps); + if (status < 0) + return status; + } + if (ops->get_mode) { + status = device_create_file(dev, &dev_attr_opmode); + if (status < 0) + return status; + } + if (ops->is_enabled) { + status = device_create_file(dev, &dev_attr_state); + if (status < 0) + return status; + } + + /* some attributes are type-specific */ + if (rdev->desc->type == REGULATOR_CURRENT) { + status = device_create_file(dev, &dev_attr_requested_microamps); + if (status < 0) + return status; + } + + /* all the other attributes exist to support constraints; + * don't show them if there are no constraints, or if the + * relevant supporting methods are missing. + */ + if (!rdev->constraints) + return status; + + /* constraints need specific supporting methods */ + if (ops->set_voltage) { + status = device_create_file(dev, &dev_attr_min_microvolts); + if (status < 0) + return status; + status = device_create_file(dev, &dev_attr_max_microvolts); + if (status < 0) + return status; + } + if (ops->set_current_limit) { + status = device_create_file(dev, &dev_attr_min_microamps); + if (status < 0) + return status; + status = device_create_file(dev, &dev_attr_max_microamps); + if (status < 0) + return status; + } + + /* suspend mode constraints need multiple supporting methods */ + if (!(ops->set_suspend_enable && ops->set_suspend_disable)) + return status; + + status = device_create_file(dev, &dev_attr_suspend_standby_state); + if (status < 0) + return status; + status = device_create_file(dev, &dev_attr_suspend_mem_state); + if (status < 0) + return status; + status = device_create_file(dev, &dev_attr_suspend_disk_state); + if (status < 0) + return status; + + if (ops->set_suspend_voltage) { + status = device_create_file(dev, + &dev_attr_suspend_standby_microvolts); + if (status < 0) + return status; + status = device_create_file(dev, + &dev_attr_suspend_mem_microvolts); + if (status < 0) + return status; + status = device_create_file(dev, + &dev_attr_suspend_disk_microvolts); + if (status < 0) + return status; + } + + if (ops->set_suspend_mode) { + status = device_create_file(dev, + &dev_attr_suspend_standby_mode); + if (status < 0) + return status; + status = device_create_file(dev, + &dev_attr_suspend_mem_mode); + if (status < 0) + return status; + status = device_create_file(dev, + &dev_attr_suspend_disk_mode); + if (status < 0) + return status; + } + + return status; +} + /** * regulator_register - register regulator * @regulator: regulator source @@ -1779,6 +1874,11 @@ struct regulator_dev *regulator_register(struct regulator_desc *regulator_desc, dev_set_drvdata(&rdev->dev, rdev); + /* add attributes supported by this regulator */ + ret = add_regulator_attributes(rdev); + if (ret < 0) + goto scrub; + /* set supply regulator if it exists */ if (init_data->supply_regulator_dev) { ret = set_supply(rdev, -- cgit v1.2.3 From 9fe5817f196054142b9a13ed78c73b76a29f2ea3 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 31 Dec 2008 12:52:44 +0000 Subject: regulator: Add basic DocBook manual Add a basic DocBook manual for the regulator API. This is much more skeletal than the existing text documentation, the main benefit is to provide a skeleton for automatic generation of a manual based on the kerneldoc for the API. Since large portions of the text are lifted from the existing text format documentation written by Liam Girdwood much of the credit belongs to him. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- Documentation/DocBook/Makefile | 2 +- Documentation/DocBook/regulator.tmpl | 304 +++++++++++++++++++++++++++++++++++ 2 files changed, 305 insertions(+), 1 deletion(-) create mode 100644 Documentation/DocBook/regulator.tmpl (limited to 'Documentation') diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile index 0a08126d3094..dc3154e49279 100644 --- a/Documentation/DocBook/Makefile +++ b/Documentation/DocBook/Makefile @@ -12,7 +12,7 @@ DOCBOOKS := z8530book.xml mcabook.xml \ kernel-api.xml filesystems.xml lsm.xml usb.xml kgdb.xml \ gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \ genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \ - mac80211.xml debugobjects.xml sh.xml + mac80211.xml debugobjects.xml sh.xml regulator.xml ### # The build process is as follows (targets): diff --git a/Documentation/DocBook/regulator.tmpl b/Documentation/DocBook/regulator.tmpl new file mode 100644 index 000000000000..53f4f8d3b810 --- /dev/null +++ b/Documentation/DocBook/regulator.tmpl @@ -0,0 +1,304 @@ + + + + + + Voltage and current regulator API + + + + Liam + Girdwood + +
+ lrg@slimlogic.co.uk +
+ + + + Mark + Brown + + Wolfson Microelectronics +
+ broonie@opensource.wolfsonmicro.com +
+ + + + + + 2007-2008 + Wolfson Microelectronics + + + 2008 + Liam Girdwood + + + + + This documentation is free software; you can redistribute + it and/or modify it under the terms of the GNU General Public + License version 2 as published by the Free Software Foundation. + + + + This program is distributed in the hope that it will be + useful, but WITHOUT ANY WARRANTY; without even the implied + warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + See the GNU General Public License for more details. + + + + You should have received a copy of the GNU General Public + License along with this program; if not, write to the Free + Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, + MA 02111-1307 USA + + + + For more details see the file COPYING in the source + distribution of Linux. + + + + + + + + Introduction + + This framework is designed to provide a standard kernel + interface to control voltage and current regulators. + + + The intention is to allow systems to dynamically control + regulator power output in order to save power and prolong + battery life. This applies to both voltage regulators (where + voltage output is controllable) and current sinks (where current + limit is controllable). + + + Note that additional (and currently more complete) documentation + is available in the Linux kernel source under + Documentation/power/regulator. + + + + Glossary + + The regulator API uses a number of terms which may not be + familiar: + + + + + Regulator + + + Electronic device that supplies power to other devices. Most + regulators can enable and disable their output and some can also + control their output voltage or current. + + + + + + Consumer + + + Electronic device which consumes power provided by a regulator. + These may either be static, requiring only a fixed supply, or + dynamic, requiring active management of the regulator at + runtime. + + + + + + Power Domain + + + The electronic circuit supplied by a given regulator, including + the regulator and all consumer devices. The configuration of + the regulator is shared between all the components in the + circuit. + + + + + + Power Management Integrated Circuit + PMIC + + + An IC which contains numerous regulators and often also other + subsystems. In an embedded system the primary PMIC is often + equivalent to a combination of the PSU and southbridge in a + desktop system. + + + + + + + + + Consumer driver interface + + This offers a similar API to the kernel clock framework. + Consumer drivers use get and put operations to acquire and + release regulators. Functions are + provided to enable + and disable the + reguator and to get and set the runtime parameters of the + regulator. + + + When requesting regulators consumers use symbolic names for their + supplies, such as "Vcc", which are mapped into actual regulator + devices by the machine interface. + + + A stub version of this API is provided when the regulator + framework is not in use in order to minimise the need to use + ifdefs. + + + + Enabling and disabling + + The regulator API provides reference counted enabling and + disabling of regulators. Consumer devices use the regulator_enable + and regulator_disable + functions to enable and disable regulators. Calls + to the two functions must be balanced. + + + Note that since multiple consumers may be using a regulator and + machine constraints may not allow the regulator to be disabled + there is no guarantee that calling + regulator_disable will actually cause the + supply provided by the regulator to be disabled. Consumer + drivers should assume that the regulator may be enabled at all + times. + + + + + Configuration + + Some consumer devices may need to be able to dynamically + configure their supplies. For example, MMC drivers may need to + select the correct operating voltage for their cards. This may + be done while the regulator is enabled or disabled. + + + The regulator_set_voltage + and regulator_set_current_limit + functions provide the primary interface for this. + Both take ranges of voltages and currents, supporting drivers + that do not require a specific value (eg, CPU frequency scaling + normally permits the CPU to use a wider range of supply + voltages at lower frequencies but does not require that the + supply voltage be lowered). Where an exact value is required + both minimum and maximum values should be identical. + + + + + Callbacks + + Callbacks may also be registered + for events such as regulation failures. + + + + + + Regulator driver interface + + Drivers for regulator chips register the regulators + with the regulator core, providing operations structures to the + core. A notifier interface + allows error conditions to be reported to the core. + + + Registration should be triggered by explicit setup done by the + platform, supplying a struct + regulator_init_data for the regulator containing + constraint and + supply information. + + + + + Machine interface + + This interface provides a way to define how regulators are + connected to consumers on a given system and what the valid + operating parameters are for the system. + + + + Supplies + + Regulator supplies are specified using struct + regulator_consumer_supply. This is done at + driver registration + time as part of the machine constraints. + + + + + Constraints + + As well as definining the connections the machine interface + also provides constraints definining the operations that + clients are allowed to perform and the parameters that may be + set. This is required since generally regulator devices will + offer more flexibility than it is safe to use on a given + system, for example supporting higher supply voltages than the + consumers are rated for. + + + This is done at driver + registration time by providing a struct + regulation_constraints. + + + The constraints may also specify an initial configuration for the + regulator in the constraints, which is particularly useful for + use with static consumers. + + + + + + API reference + + Due to limitations of the kernel documentation framework and the + existing layout of the source code the entire regulator API is + documented here. + +!Iinclude/linux/regulator/consumer.h +!Iinclude/linux/regulator/machine.h +!Iinclude/linux/regulator/driver.h +!Edrivers/regulator/core.c + + -- cgit v1.2.3 From d5b524327b2a482dddae3839ced8f8825074730d Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Thu, 8 Jan 2009 16:32:13 -0700 Subject: Fix a typo in the development process document. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reported-by: Aníbal Monsalve Salazar Signed-off-by: Jonathan Corbet --- Documentation/development-process/4.Coding | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'Documentation') diff --git a/Documentation/development-process/4.Coding b/Documentation/development-process/4.Coding index 014aca8f14e2..a5a3450faaa0 100644 --- a/Documentation/development-process/4.Coding +++ b/Documentation/development-process/4.Coding @@ -375,10 +375,10 @@ say, this can be a large job, so it is best to be sure that the justification is solid. When making an incompatible API change, one should, whenever possible, -ensure that code which has not been updated is caught by the compiler. +ensure that code which has not been updated is caught by the compiler. This will help you to be sure that you have found all in-tree uses of that interface. It will also alert developers of out-of-tree code that there is a change that they need to respond to. Supporting out-of-tree code is not something that kernel developers need to be worried about, but we also do -not have to make life harder for out-of-tree developers than it it needs to -be. +not have to make life harder for out-of-tree developers than it needs to +be. -- cgit v1.2.3 From 237889bf0a62f1399fb2ba0c2a259e6a96597131 Mon Sep 17 00:00:00 2001 From: Zhao Yakui Date: Wed, 17 Dec 2008 16:55:18 +0800 Subject: ACPI : Use RSDT instead of XSDT by adding boot option of "acpi=rsdt" On some boxes there exist both RSDT and XSDT table. But unfortunately sometimes there exists the following error when XSDT table is used: a. 32/64X address mismatch b. The 32/64X FACS address mismatch In such case the boot option of "acpi=rsdt" is provided so that RSDT is tried instead of XSDT table when the system can't work well. http://bugzilla.kernel.org/show_bug.cgi?id=8246 Signed-off-by: Zhao Yakui cc:Thomas Renninger Signed-off-by: Len Brown --- Documentation/kernel-parameters.txt | 1 + arch/ia64/kernel/acpi.c | 1 + arch/x86/kernel/acpi/boot.c | 6 +++++- drivers/acpi/tables/tbutils.c | 3 ++- include/acpi/acpixf.h | 1 + 5 files changed, 10 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index c9115c1b672c..136f02842de9 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -139,6 +139,7 @@ and is between 256 and 4096 characters. It is defined in the file ht -- run only enough ACPI to enable Hyper Threading strict -- Be less tolerant of platforms that are not strictly ACPI specification compliant. + rsdt -- prefer RSDT over (default) XSDT See also Documentation/power/pm.txt, pci=noacpi diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index bd7acc71e8a9..c19b686db9b8 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -65,6 +65,7 @@ EXPORT_SYMBOL(pm_idle); void (*pm_power_off) (void); EXPORT_SYMBOL(pm_power_off); +u32 acpi_rsdt_forced; unsigned int acpi_cpei_override; unsigned int acpi_cpei_phys_cpuid; diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 4c51a2f8fd31..db1a90a76b3e 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -47,7 +47,7 @@ #endif static int __initdata acpi_force = 0; - +u32 acpi_rsdt_forced; #ifdef CONFIG_ACPI int acpi_disabled = 0; #else @@ -1783,6 +1783,10 @@ static int __init parse_acpi(char *arg) disable_acpi(); acpi_ht = 1; } + /* acpi=rsdt use RSDT instead of XSDT */ + else if (strcmp(arg, "rsdt") == 0) { + acpi_rsdt_forced = 1; + } /* "acpi=noirq" disables ACPI interrupt routing */ else if (strcmp(arg, "noirq") == 0) { acpi_noirq_set(); diff --git a/drivers/acpi/tables/tbutils.c b/drivers/acpi/tables/tbutils.c index 0cc92ef5236f..da9f240186e8 100644 --- a/drivers/acpi/tables/tbutils.c +++ b/drivers/acpi/tables/tbutils.c @@ -420,7 +420,8 @@ acpi_tb_parse_root_table(acpi_physical_address rsdp_address, u8 flags) /* Differentiate between RSDT and XSDT root tables */ - if (rsdp->revision > 1 && rsdp->xsdt_physical_address) { + if (rsdp->revision > 1 && rsdp->xsdt_physical_address + && !acpi_rsdt_forced) { /* * Root table is an XSDT (64-bit physical addresses). We must use the * XSDT if the revision is > 1 and the XSDT pointer is present, as per diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 33bc0e3b1954..05d2614e0078 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -48,6 +48,7 @@ #include "actypes.h" #include "actbl.h" +extern u32 acpi_rsdt_forced; /* * Global interfaces */ -- cgit v1.2.3 From 555d61d6542d51563e50532ff604dcd31c96fb24 Mon Sep 17 00:00:00 2001 From: Hendrik Brueckner Date: Fri, 9 Jan 2009 12:15:02 +0100 Subject: [S390] update documentation for hvc_iucv kernel parameter. Signed-off-by: Hendrik Brueckner Signed-off-by: Martin Schwidefsky --- Documentation/kernel-parameters.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index fb849020aea9..ed0a72442cf3 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -829,8 +829,8 @@ and is between 256 and 4096 characters. It is defined in the file hlt [BUGS=ARM,SH] - hvc_iucv= [S390] Number of z/VM IUCV Hypervisor console (HVC) - back-ends. Valid parameters: 0..8 + hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC) + terminal devices. Valid values: 0..8 i8042.debug [HW] Toggle i8042 debug mode i8042.direct [HW] Put keyboard port into non-translated mode -- cgit v1.2.3 From c4be0c1dc4cdc37b175579be1460f15ac6495e9a Mon Sep 17 00:00:00 2001 From: Takashi Sato Date: Fri, 9 Jan 2009 16:40:58 -0800 Subject: filesystem freeze: add error handling of write_super_lockfs/unlockfs Currently, ext3 in mainline Linux doesn't have the freeze feature which suspends write requests. So, we cannot take a backup which keeps the filesystem's consistency with the storage device's features (snapshot and replication) while it is mounted. In many case, a commercial filesystem (e.g. VxFS) has the freeze feature and it would be used to get the consistent backup. If Linux's standard filesystem ext3 has the freeze feature, we can do it without a commercial filesystem. So I have implemented the ioctls of the freeze feature. I think we can take the consistent backup with the following steps. 1. Freeze the filesystem with the freeze ioctl. 2. Separate the replication volume or create the snapshot with the storage device's feature. 3. Unfreeze the filesystem with the unfreeze ioctl. 4. Take the backup from the separated replication volume or the snapshot. This patch: VFS: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they can return an error. Rename write_super_lockfs and unlockfs of the super block operation freeze_fs and unfreeze_fs to avoid a confusion. ext3, ext4, xfs, gfs2, jfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that write_super_lockfs returns an error if needed, and unlockfs always returns 0. reiserfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they always return 0 (success) to keep a current behavior. Signed-off-by: Takashi Sato Signed-off-by: Masayuki Hamaguchi Cc: Cc: Cc: Christoph Hellwig Cc: Dave Kleikamp Cc: Dave Chinner Cc: Alasdair G Kergon Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/Locking | 8 +++---- Documentation/filesystems/vfs.txt | 8 +++---- fs/buffer.c | 8 +++---- fs/ext3/super.c | 45 +++++++++++++++++++++++++-------------- fs/ext4/super.c | 45 +++++++++++++++++++++++++++------------ fs/gfs2/ops_super.c | 16 ++++++++------ fs/jfs/super.c | 10 +++++---- fs/reiserfs/super.c | 10 +++++---- fs/xfs/linux-2.6/xfs_super.c | 8 +++---- fs/xfs/xfs_fsops.c | 11 ++++++---- fs/xfs/xfs_fsops.h | 2 +- include/linux/fs.h | 4 ++-- 12 files changed, 107 insertions(+), 68 deletions(-) (limited to 'Documentation') diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index cfbfa15a46ba..ec6a9392a173 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -97,8 +97,8 @@ prototypes: void (*put_super) (struct super_block *); void (*write_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); - void (*write_super_lockfs) (struct super_block *); - void (*unlockfs) (struct super_block *); + int (*freeze_fs) (struct super_block *); + int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); void (*clear_inode) (struct inode *); @@ -119,8 +119,8 @@ delete_inode: no put_super: yes yes no write_super: no yes read sync_fs: no no read -write_super_lockfs: ? -unlockfs: ? +freeze_fs: ? +unfreeze_fs: ? statfs: no no no remount_fs: yes yes maybe (see below) clear_inode: no diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index ef19afa186a9..deeeed0faa8f 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -210,8 +210,8 @@ struct super_operations { void (*put_super) (struct super_block *); void (*write_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); - void (*write_super_lockfs) (struct super_block *); - void (*unlockfs) (struct super_block *); + int (*freeze_fs) (struct super_block *); + int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); void (*clear_inode) (struct inode *); @@ -270,11 +270,11 @@ or bottom half). a superblock. The second parameter indicates whether the method should wait until the write out has been completed. Optional. - write_super_lockfs: called when VFS is locking a filesystem and + freeze_fs: called when VFS is locking a filesystem and forcing it into a consistent state. This method is currently used by the Logical Volume Manager (LVM). - unlockfs: called when VFS is unlocking a filesystem and making it writable + unfreeze_fs: called when VFS is unlocking a filesystem and making it writable again. statfs: called when the VFS needs to get filesystem statistics. This diff --git a/fs/buffer.c b/fs/buffer.c index c26da785938a..87f9e537b8c3 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -221,8 +221,8 @@ struct super_block *freeze_bdev(struct block_device *bdev) sync_blockdev(sb->s_bdev); - if (sb->s_op->write_super_lockfs) - sb->s_op->write_super_lockfs(sb); + if (sb->s_op->freeze_fs) + sb->s_op->freeze_fs(sb); } sync_blockdev(bdev); @@ -242,8 +242,8 @@ void thaw_bdev(struct block_device *bdev, struct super_block *sb) if (sb) { BUG_ON(sb->s_bdev != bdev); - if (sb->s_op->unlockfs) - sb->s_op->unlockfs(sb); + if (sb->s_op->unfreeze_fs) + sb->s_op->unfreeze_fs(sb); sb->s_frozen = SB_UNFROZEN; smp_wmb(); wake_up(&sb->s_wait_unfrozen); diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 5d047a030a73..b70d90e08a3c 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -48,8 +48,8 @@ static int ext3_load_journal(struct super_block *, struct ext3_super_block *, unsigned long journal_devnum); static int ext3_create_journal(struct super_block *, struct ext3_super_block *, unsigned int); -static void ext3_commit_super (struct super_block * sb, - struct ext3_super_block * es, +static int ext3_commit_super(struct super_block *sb, + struct ext3_super_block *es, int sync); static void ext3_mark_recovery_complete(struct super_block * sb, struct ext3_super_block * es); @@ -60,9 +60,9 @@ static const char *ext3_decode_error(struct super_block * sb, int errno, char nbuf[16]); static int ext3_remount (struct super_block * sb, int * flags, char * data); static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf); -static void ext3_unlockfs(struct super_block *sb); +static int ext3_unfreeze(struct super_block *sb); static void ext3_write_super (struct super_block * sb); -static void ext3_write_super_lockfs(struct super_block *sb); +static int ext3_freeze(struct super_block *sb); /* * Wrappers for journal_start/end. @@ -759,8 +759,8 @@ static const struct super_operations ext3_sops = { .put_super = ext3_put_super, .write_super = ext3_write_super, .sync_fs = ext3_sync_fs, - .write_super_lockfs = ext3_write_super_lockfs, - .unlockfs = ext3_unlockfs, + .freeze_fs = ext3_freeze, + .unfreeze_fs = ext3_unfreeze, .statfs = ext3_statfs, .remount_fs = ext3_remount, .clear_inode = ext3_clear_inode, @@ -2311,21 +2311,23 @@ static int ext3_create_journal(struct super_block * sb, return 0; } -static void ext3_commit_super (struct super_block * sb, - struct ext3_super_block * es, +static int ext3_commit_super(struct super_block *sb, + struct ext3_super_block *es, int sync) { struct buffer_head *sbh = EXT3_SB(sb)->s_sbh; + int error = 0; if (!sbh) - return; + return error; es->s_wtime = cpu_to_le32(get_seconds()); es->s_free_blocks_count = cpu_to_le32(ext3_count_free_blocks(sb)); es->s_free_inodes_count = cpu_to_le32(ext3_count_free_inodes(sb)); BUFFER_TRACE(sbh, "marking dirty"); mark_buffer_dirty(sbh); if (sync) - sync_dirty_buffer(sbh); + error = sync_dirty_buffer(sbh); + return error; } @@ -2439,12 +2441,14 @@ static int ext3_sync_fs(struct super_block *sb, int wait) * LVM calls this function before a (read-only) snapshot is created. This * gives us a chance to flush the journal completely and mark the fs clean. */ -static void ext3_write_super_lockfs(struct super_block *sb) +static int ext3_freeze(struct super_block *sb) { + int error = 0; + journal_t *journal; sb->s_dirt = 0; if (!(sb->s_flags & MS_RDONLY)) { - journal_t *journal = EXT3_SB(sb)->s_journal; + journal = EXT3_SB(sb)->s_journal; /* Now we set up the journal barrier. */ journal_lock_updates(journal); @@ -2453,20 +2457,28 @@ static void ext3_write_super_lockfs(struct super_block *sb) * We don't want to clear needs_recovery flag when we failed * to flush the journal. */ - if (journal_flush(journal) < 0) - return; + error = journal_flush(journal); + if (error < 0) + goto out; /* Journal blocked and flushed, clear needs_recovery flag. */ EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER); - ext3_commit_super(sb, EXT3_SB(sb)->s_es, 1); + error = ext3_commit_super(sb, EXT3_SB(sb)->s_es, 1); + if (error) + goto out; } + return 0; + +out: + journal_unlock_updates(journal); + return error; } /* * Called by LVM after the snapshot is done. We need to reset the RECOVER * flag here, even though the filesystem is not technically dirty yet. */ -static void ext3_unlockfs(struct super_block *sb) +static int ext3_unfreeze(struct super_block *sb) { if (!(sb->s_flags & MS_RDONLY)) { lock_super(sb); @@ -2476,6 +2488,7 @@ static void ext3_unlockfs(struct super_block *sb) unlock_super(sb); journal_unlock_updates(EXT3_SB(sb)->s_journal); } + return 0; } static int ext3_remount (struct super_block * sb, int * flags, char * data) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8f7e0be8ab1b..e5f06a5f045e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -51,7 +51,7 @@ struct proc_dir_entry *ext4_proc_root; static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); -static void ext4_commit_super(struct super_block *sb, +static int ext4_commit_super(struct super_block *sb, struct ext4_super_block *es, int sync); static void ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es); @@ -62,9 +62,9 @@ static const char *ext4_decode_error(struct super_block *sb, int errno, char nbuf[16]); static int ext4_remount(struct super_block *sb, int *flags, char *data); static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf); -static void ext4_unlockfs(struct super_block *sb); +static int ext4_unfreeze(struct super_block *sb); static void ext4_write_super(struct super_block *sb); -static void ext4_write_super_lockfs(struct super_block *sb); +static int ext4_freeze(struct super_block *sb); ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, @@ -978,8 +978,8 @@ static const struct super_operations ext4_sops = { .put_super = ext4_put_super, .write_super = ext4_write_super, .sync_fs = ext4_sync_fs, - .write_super_lockfs = ext4_write_super_lockfs, - .unlockfs = ext4_unlockfs, + .freeze_fs = ext4_freeze, + .unfreeze_fs = ext4_unfreeze, .statfs = ext4_statfs, .remount_fs = ext4_remount, .clear_inode = ext4_clear_inode, @@ -2888,13 +2888,14 @@ static int ext4_load_journal(struct super_block *sb, return 0; } -static void ext4_commit_super(struct super_block *sb, +static int ext4_commit_super(struct super_block *sb, struct ext4_super_block *es, int sync) { struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; + int error = 0; if (!sbh) - return; + return error; if (buffer_write_io_error(sbh)) { /* * Oh, dear. A previous attempt to write the @@ -2918,14 +2919,19 @@ static void ext4_commit_super(struct super_block *sb, BUFFER_TRACE(sbh, "marking dirty"); mark_buffer_dirty(sbh); if (sync) { - sync_dirty_buffer(sbh); - if (buffer_write_io_error(sbh)) { + error = sync_dirty_buffer(sbh); + if (error) + return error; + + error = buffer_write_io_error(sbh); + if (error) { printk(KERN_ERR "EXT4-fs: I/O error while writing " "superblock for %s.\n", sb->s_id); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } } + return error; } @@ -3058,12 +3064,14 @@ static int ext4_sync_fs(struct super_block *sb, int wait) * LVM calls this function before a (read-only) snapshot is created. This * gives us a chance to flush the journal completely and mark the fs clean. */ -static void ext4_write_super_lockfs(struct super_block *sb) +static int ext4_freeze(struct super_block *sb) { + int error = 0; + journal_t *journal; sb->s_dirt = 0; if (!(sb->s_flags & MS_RDONLY)) { - journal_t *journal = EXT4_SB(sb)->s_journal; + journal = EXT4_SB(sb)->s_journal; if (journal) { /* Now we set up the journal barrier. */ @@ -3073,21 +3081,29 @@ static void ext4_write_super_lockfs(struct super_block *sb) * We don't want to clear needs_recovery flag when we * failed to flush the journal. */ - if (jbd2_journal_flush(journal) < 0) - return; + error = jbd2_journal_flush(journal); + if (error < 0) + goto out; } /* Journal blocked and flushed, clear needs_recovery flag. */ EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1); + error = ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1); + if (error) + goto out; } + return 0; +out: + jbd2_journal_unlock_updates(journal); + return error; } /* * Called by LVM after the snapshot is done. We need to reset the RECOVER * flag here, even though the filesystem is not technically dirty yet. */ -static void ext4_unlockfs(struct super_block *sb) +static int ext4_unfreeze(struct super_block *sb) { if (EXT4_SB(sb)->s_journal && !(sb->s_flags & MS_RDONLY)) { lock_super(sb); @@ -3097,6 +3113,7 @@ static void ext4_unlockfs(struct super_block *sb) unlock_super(sb); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); } + return 0; } static int ext4_remount(struct super_block *sb, int *flags, char *data) diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c index 777783deddcb..320323d03479 100644 --- a/fs/gfs2/ops_super.c +++ b/fs/gfs2/ops_super.c @@ -211,18 +211,18 @@ static int gfs2_sync_fs(struct super_block *sb, int wait) } /** - * gfs2_write_super_lockfs - prevent further writes to the filesystem + * gfs2_freeze - prevent further writes to the filesystem * @sb: the VFS structure for the filesystem * */ -static void gfs2_write_super_lockfs(struct super_block *sb) +static int gfs2_freeze(struct super_block *sb) { struct gfs2_sbd *sdp = sb->s_fs_info; int error; if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) - return; + return -EINVAL; for (;;) { error = gfs2_freeze_fs(sdp); @@ -242,17 +242,19 @@ static void gfs2_write_super_lockfs(struct super_block *sb) fs_err(sdp, "retrying...\n"); msleep(1000); } + return 0; } /** - * gfs2_unlockfs - reallow writes to the filesystem + * gfs2_unfreeze - reallow writes to the filesystem * @sb: the VFS structure for the filesystem * */ -static void gfs2_unlockfs(struct super_block *sb) +static int gfs2_unfreeze(struct super_block *sb) { gfs2_unfreeze_fs(sb->s_fs_info); + return 0; } /** @@ -688,8 +690,8 @@ const struct super_operations gfs2_super_ops = { .put_super = gfs2_put_super, .write_super = gfs2_write_super, .sync_fs = gfs2_sync_fs, - .write_super_lockfs = gfs2_write_super_lockfs, - .unlockfs = gfs2_unlockfs, + .freeze_fs = gfs2_freeze, + .unfreeze_fs = gfs2_unfreeze, .statfs = gfs2_statfs, .remount_fs = gfs2_remount_fs, .clear_inode = gfs2_clear_inode, diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 0dae345e481b..b37d1f78b854 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -543,7 +543,7 @@ out_kfree: return ret; } -static void jfs_write_super_lockfs(struct super_block *sb) +static int jfs_freeze(struct super_block *sb) { struct jfs_sb_info *sbi = JFS_SBI(sb); struct jfs_log *log = sbi->log; @@ -553,9 +553,10 @@ static void jfs_write_super_lockfs(struct super_block *sb) lmLogShutdown(log); updateSuper(sb, FM_CLEAN); } + return 0; } -static void jfs_unlockfs(struct super_block *sb) +static int jfs_unfreeze(struct super_block *sb) { struct jfs_sb_info *sbi = JFS_SBI(sb); struct jfs_log *log = sbi->log; @@ -568,6 +569,7 @@ static void jfs_unlockfs(struct super_block *sb) else txResume(sb); } + return 0; } static int jfs_get_sb(struct file_system_type *fs_type, @@ -735,8 +737,8 @@ static const struct super_operations jfs_super_operations = { .delete_inode = jfs_delete_inode, .put_super = jfs_put_super, .sync_fs = jfs_sync_fs, - .write_super_lockfs = jfs_write_super_lockfs, - .unlockfs = jfs_unlockfs, + .freeze_fs = jfs_freeze, + .unfreeze_fs = jfs_unfreeze, .statfs = jfs_statfs, .remount_fs = jfs_remount, .show_options = jfs_show_options, diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index c55651f1407c..f3c820b75829 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -83,7 +83,7 @@ static void reiserfs_write_super(struct super_block *s) reiserfs_sync_fs(s, 1); } -static void reiserfs_write_super_lockfs(struct super_block *s) +static int reiserfs_freeze(struct super_block *s) { struct reiserfs_transaction_handle th; reiserfs_write_lock(s); @@ -101,11 +101,13 @@ static void reiserfs_write_super_lockfs(struct super_block *s) } s->s_dirt = 0; reiserfs_write_unlock(s); + return 0; } -static void reiserfs_unlockfs(struct super_block *s) +static int reiserfs_unfreeze(struct super_block *s) { reiserfs_allow_writes(s); + return 0; } extern const struct in_core_key MAX_IN_CORE_KEY; @@ -613,8 +615,8 @@ static const struct super_operations reiserfs_sops = { .put_super = reiserfs_put_super, .write_super = reiserfs_write_super, .sync_fs = reiserfs_sync_fs, - .write_super_lockfs = reiserfs_write_super_lockfs, - .unlockfs = reiserfs_unlockfs, + .freeze_fs = reiserfs_freeze, + .unfreeze_fs = reiserfs_unfreeze, .statfs = reiserfs_statfs, .remount_fs = reiserfs_remount, .show_options = generic_show_options, diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index be846d606ae8..95a971080368 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -1269,14 +1269,14 @@ xfs_fs_remount( * need to take care of the metadata. Once that's done write a dummy * record to dirty the log in case of a crash while frozen. */ -STATIC void -xfs_fs_lockfs( +STATIC int +xfs_fs_freeze( struct super_block *sb) { struct xfs_mount *mp = XFS_M(sb); xfs_quiesce_attr(mp); - xfs_fs_log_dummy(mp); + return -xfs_fs_log_dummy(mp); } STATIC int @@ -1557,7 +1557,7 @@ static struct super_operations xfs_super_operations = { .put_super = xfs_fs_put_super, .write_super = xfs_fs_write_super, .sync_fs = xfs_fs_sync_super, - .write_super_lockfs = xfs_fs_lockfs, + .freeze_fs = xfs_fs_freeze, .statfs = xfs_fs_statfs, .remount_fs = xfs_fs_remount, .show_options = xfs_fs_show_options, diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 852b6d32e8d0..680d0e0ec932 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -595,17 +595,19 @@ out: return 0; } -void +int xfs_fs_log_dummy( xfs_mount_t *mp) { xfs_trans_t *tp; xfs_inode_t *ip; + int error; tp = _xfs_trans_alloc(mp, XFS_TRANS_DUMMY1); - if (xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0)) { + error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0); + if (error) { xfs_trans_cancel(tp, 0); - return; + return error; } ip = mp->m_rootip; @@ -615,9 +617,10 @@ xfs_fs_log_dummy( xfs_trans_ihold(tp, ip); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); xfs_trans_set_sync(tp); - xfs_trans_commit(tp, 0); + error = xfs_trans_commit(tp, 0); xfs_iunlock(ip, XFS_ILOCK_EXCL); + return error; } int diff --git a/fs/xfs/xfs_fsops.h b/fs/xfs/xfs_fsops.h index 300d0c9d61ad..88435e0a77c9 100644 --- a/fs/xfs/xfs_fsops.h +++ b/fs/xfs/xfs_fsops.h @@ -25,6 +25,6 @@ extern int xfs_fs_counts(xfs_mount_t *mp, xfs_fsop_counts_t *cnt); extern int xfs_reserve_blocks(xfs_mount_t *mp, __uint64_t *inval, xfs_fsop_resblks_t *outval); extern int xfs_fs_goingdown(xfs_mount_t *mp, __uint32_t inflags); -extern void xfs_fs_log_dummy(xfs_mount_t *mp); +extern int xfs_fs_log_dummy(xfs_mount_t *mp); #endif /* __XFS_FSOPS_H__ */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 0b87b29f4797..3e59182de9df 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1377,8 +1377,8 @@ struct super_operations { void (*put_super) (struct super_block *); void (*write_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); - void (*write_super_lockfs) (struct super_block *); - void (*unlockfs) (struct super_block *); + int (*freeze_fs) (struct super_block *); + int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); void (*clear_inode) (struct inode *); -- cgit v1.2.3