diff options
Diffstat (limited to 'Documentation')
| -rw-r--r-- | Documentation/auxdisplay/cfag12864b-example.c | 1 | ||||
| -rw-r--r-- | Documentation/cgroups/cgroups.txt | 32 | ||||
| -rw-r--r-- | Documentation/cgroups/memory.txt | 41 | ||||
| -rw-r--r-- | Documentation/crypto/async-tx-api.txt | 75 | ||||
| -rw-r--r-- | Documentation/filesystems/sharedsubtree.txt | 220 | ||||
| -rw-r--r-- | Documentation/filesystems/vfs.txt | 7 | ||||
| -rw-r--r-- | Documentation/ioctl/ioctl-number.txt | 1 | ||||
| -rw-r--r-- | Documentation/sysctl/fs.txt | 17 | ||||
| -rw-r--r-- | Documentation/sysctl/kernel.txt | 22 | ||||
| -rw-r--r-- | Documentation/sysctl/vm.txt | 41 | ||||
| -rw-r--r-- | Documentation/vm/.gitignore | 1 | ||||
| -rw-r--r-- | Documentation/vm/locking | 2 | ||||
| -rw-r--r-- | Documentation/vm/page-types.c | 200 |
13 files changed, 418 insertions, 242 deletions
diff --git a/Documentation/auxdisplay/cfag12864b-example.c b/Documentation/auxdisplay/cfag12864b-example.c index 1d2c010bae1..e7823ffb1ca 100644 --- a/Documentation/auxdisplay/cfag12864b-example.c +++ b/Documentation/auxdisplay/cfag12864b-example.c @@ -194,7 +194,6 @@ static void cfag12864b_blit(void) */ #include <stdio.h> -#include <string.h> #define EXAMPLES 6 diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index 6eb1a97e88c..455d4e6d346 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -408,6 +408,26 @@ You can attach the current shell task by echoing 0: # echo 0 > tasks +2.3 Mounting hierarchies by name +-------------------------------- + +Passing the name=<x> option when mounting a cgroups hierarchy +associates the given name with the hierarchy. This can be used when +mounting a pre-existing hierarchy, in order to refer to it by name +rather than by its set of active subsystems. Each hierarchy is either +nameless, or has a unique name. + +The name should match [\w.-]+ + +When passing a name=<x> option for a new hierarchy, you need to +specify subsystems manually; the legacy behaviour of mounting all +subsystems when none are explicitly specified is not supported when +you give a subsystem a name. + +The name of the subsystem appears as part of the hierarchy description +in /proc/mounts and /proc/<pid>/cgroups. + + 3. Kernel API ============= @@ -501,7 +521,7 @@ rmdir() will fail with it. From this behavior, pre_destroy() can be called multiple times against a cgroup. int can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct task_struct *task) + struct task_struct *task, bool threadgroup) (cgroup_mutex held by caller) Called prior to moving a task into a cgroup; if the subsystem @@ -509,14 +529,20 @@ returns an error, this will abort the attach operation. If a NULL task is passed, then a successful result indicates that *any* unspecified task can be moved into the cgroup. Note that this isn't called on a fork. If this method returns 0 (success) then this should -remain valid while the caller holds cgroup_mutex. +remain valid while the caller holds cgroup_mutex. If threadgroup is +true, then a successful result indicates that all threads in the given +thread's threadgroup can be moved together. void attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup *old_cgrp, struct task_struct *task) + struct cgroup *old_cgrp, struct task_struct *task, + bool threadgroup) (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. +If threadgroup is true, the subsystem should take care of all threads +in the specified thread's threadgroup. Currently does not support any +subsystem that might need the old_cgrp for every thread in the group. void fork(struct cgroup_subsy *ss, struct task_struct *task) diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index 23d1262c077..b871f2552b4 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -179,6 +179,9 @@ The reclaim algorithm has not been modified for cgroups, except that pages that are selected for reclaiming come from the per cgroup LRU list. +NOTE: Reclaim does not work for the root cgroup, since we cannot set any +limits on the root cgroup. + 2. Locking The memory controller uses the following hierarchy @@ -210,6 +213,7 @@ We can alter the memory limit: NOTE: We can use a suffix (k, K, m, M, g or G) to indicate values in kilo, mega or gigabytes. NOTE: We can write "-1" to reset the *.limit_in_bytes(unlimited). +NOTE: We cannot set limits on the root cgroup any more. # cat /cgroups/0/memory.limit_in_bytes 4194304 @@ -375,7 +379,42 @@ cgroups created below it. NOTE2: This feature can be enabled/disabled per subtree. -7. TODO +7. Soft limits + +Soft limits allow for greater sharing of memory. The idea behind soft limits +is to allow control groups to use as much of the memory as needed, provided + +a. There is no memory contention +b. They do not exceed their hard limit + +When the system detects memory contention or low memory control groups +are pushed back to their soft limits. If the soft limit of each control +group is very high, they are pushed back as much as possible to make +sure that one control group does not starve the others of memory. + +Please note that soft limits is a best effort feature, it comes with +no guarantees, but it does its best to make sure that when memory is +heavily contended for, memory is allocated based on the soft limit +hints/setup. Currently soft limit based reclaim is setup such that +it gets invoked from balance_pgdat (kswapd). + +7.1 Interface + +Soft limits can be setup by using the following commands (in this example we +assume a soft limit of 256 megabytes) + +# echo 256M > memory.soft_limit_in_bytes + +If we want to change this to 1G, we can at any time use + +# echo 1G > memory.soft_limit_in_bytes + +NOTE1: Soft limits take effect over a long period of time, since they involve + reclaiming memory for balancing between memory cgroups +NOTE2: It is recommended to set the soft limit always below the hard limit, + otherwise the hard limit will take precedence. + +8. 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/Documentation/crypto/async-tx-api.txt b/Documentation/crypto/async-tx-api.txt index 9f59fcbf5d8..ba046b8fa92 100644 --- a/Documentation/crypto/async-tx-api.txt +++ b/Documentation/crypto/async-tx-api.txt @@ -54,20 +54,23 @@ features surfaced as a result: 3.1 General format of the API: struct dma_async_tx_descriptor * -async_<operation>(<op specific parameters>, - enum async_tx_flags flags, - struct dma_async_tx_descriptor *dependency, - dma_async_tx_callback callback_routine, - void *callback_parameter); +async_<operation>(<op specific parameters>, struct async_submit ctl *submit) 3.2 Supported operations: -memcpy - memory copy between a source and a destination buffer -memset - fill a destination buffer with a byte value -xor - xor a series of source buffers and write the result to a - destination buffer -xor_zero_sum - xor a series of source buffers and set a flag if the - result is zero. The implementation attempts to prevent - writes to memory +memcpy - memory copy between a source and a destination buffer +memset - fill a destination buffer with a byte value +xor - xor a series of source buffers and write the result to a + destination buffer +xor_val - xor a series of source buffers and set a flag if the + result is zero. The implementation attempts to prevent + writes to memory +pq - generate the p+q (raid6 syndrome) from a series of source buffers +pq_val - validate that a p and or q buffer are in sync with a given series of + sources +datap - (raid6_datap_recov) recover a raid6 data block and the p block + from the given sources +2data - (raid6_2data_recov) recover 2 raid6 data blocks from the given + sources 3.3 Descriptor management: The return value is non-NULL and points to a 'descriptor' when the operation @@ -80,8 +83,8 @@ acknowledged by the application before the offload engine driver is allowed to recycle (or free) the descriptor. A descriptor can be acked by one of the following methods: 1/ setting the ASYNC_TX_ACK flag if no child operations are to be submitted -2/ setting the ASYNC_TX_DEP_ACK flag to acknowledge the parent - descriptor of a new operation. +2/ submitting an unacknowledged descriptor as a dependency to another + async_tx call will implicitly set the acknowledged state. 3/ calling async_tx_ack() on the descriptor. 3.4 When does the operation execute? @@ -119,30 +122,42 @@ of an operation. Perform a xor->copy->xor operation where each operation depends on the result from the previous operation: -void complete_xor_copy_xor(void *param) +void callback(void *param) { - printk("complete\n"); + struct completion *cmp = param; + + complete(cmp); } -int run_xor_copy_xor(struct page **xor_srcs, - int xor_src_cnt, - struct page *xor_dest, - size_t xor_len, - struct page *copy_src, - struct page *copy_dest, - size_t copy_len) +void run_xor_copy_xor(struct page **xor_srcs, + int xor_src_cnt, + struct page *xor_dest, + size_t xor_len, + struct page *copy_src, + struct page *copy_dest, + size_t copy_len) { struct dma_async_tx_descriptor *tx; + addr_conv_t addr_conv[xor_src_cnt]; + struct async_submit_ctl submit; + addr_conv_t addr_conv[NDISKS]; + struct completion cmp; + + init_async_submit(&submit, ASYNC_TX_XOR_DROP_DST, NULL, NULL, NULL, + addr_conv); + tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len, &submit) - tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len, - ASYNC_TX_XOR_DROP_DST, NULL, NULL, NULL); - tx = async_memcpy(copy_dest, copy_src, 0, 0, copy_len, - ASYNC_TX_DEP_ACK, tx, NULL, NULL); - tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len, - ASYNC_TX_XOR_DROP_DST | ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, - tx, complete_xor_copy_xor, NULL); + submit->depend_tx = tx; + tx = async_memcpy(copy_dest, copy_src, 0, 0, copy_len, &submit); + + init_completion(&cmp); + init_async_submit(&submit, ASYNC_TX_XOR_DROP_DST | ASYNC_TX_ACK, tx, + callback, &cmp, addr_conv); + tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len, &submit); async_tx_issue_pending_all(); + + wait_for_completion(&cmp); } See include/linux/async_tx.h for more information on the flags. See the diff --git a/Documentation/filesystems/sharedsubtree.txt b/Documentation/filesystems/sharedsubtree.txt index 736540045dc..23a181074f9 100644 --- a/Documentation/filesystems/sharedsubtree.txt +++ b/Documentation/filesystems/sharedsubtree.txt @@ -4,7 +4,7 @@ Shared Subtrees Contents: 1) Overview 2) Features - 3) smount command + 3) Setting mount states 4) Use-case 5) Detailed semantics 6) Quiz @@ -41,14 +41,14 @@ replicas continue to be exactly same. Here is an example: - Lets say /mnt has a mount that is shared. + Let's say /mnt has a mount that is shared. mount --make-shared /mnt - note: mount command does not yet support the --make-shared flag. - I have included a small C program which does the same by executing - 'smount /mnt shared' + Note: mount(8) command now supports the --make-shared flag, + so the sample 'smount' program is no longer needed and has been + removed. - #mount --bind /mnt /tmp + # mount --bind /mnt /tmp The above command replicates the mount at /mnt to the mountpoint /tmp and the contents of both the mounts remain identical. @@ -58,8 +58,8 @@ replicas continue to be exactly same. #ls /tmp a b c - Now lets say we mount a device at /tmp/a - #mount /dev/sd0 /tmp/a + Now let's say we mount a device at /tmp/a + # mount /dev/sd0 /tmp/a #ls /tmp/a t1 t2 t2 @@ -80,21 +80,20 @@ replicas continue to be exactly same. Here is an example: - Lets say /mnt has a mount which is shared. - #mount --make-shared /mnt + Let's say /mnt has a mount which is shared. + # mount --make-shared /mnt - Lets bind mount /mnt to /tmp - #mount --bind /mnt /tmp + Let's bind mount /mnt to /tmp + # mount --bind /mnt /tmp the new mount at /tmp becomes a shared mount and it is a replica of the mount at /mnt. - Now lets make the mount at /tmp; a slave of /mnt - #mount --make-slave /tmp - [or smount /tmp slave] + Now let's make the mount at /tmp; a slave of /mnt + # mount --make-slave /tmp - lets mount /dev/sd0 on /mnt/a - #mount /dev/sd0 /mnt/a + let's mount /dev/sd0 on /mnt/a + # mount /dev/sd0 /mnt/a #ls /mnt/a t1 t2 t3 @@ -104,9 +103,9 @@ replicas continue to be exactly same. Note the mount event has propagated to the mount at /tmp - However lets see what happens if we mount something on the mount at /tmp + However let's see what happens if we mount something on the mount at /tmp - #mount /dev/sd1 /tmp/b + # mount /dev/sd1 /tmp/b #ls /tmp/b s1 s2 s3 @@ -124,12 +123,11 @@ replicas continue to be exactly same. 2d) A unbindable mount is a unbindable private mount - lets say we have a mount at /mnt and we make is unbindable + let's say we have a mount at /mnt and we make is unbindable - #mount --make-unbindable /mnt - [ smount /mnt unbindable ] + # mount --make-unbindable /mnt - Lets try to bind mount this mount somewhere else. + Let's try to bind mount this mount somewhere else. # mount --bind /mnt /tmp mount: wrong fs type, bad option, bad superblock on /mnt, or too many mounted file systems @@ -137,149 +135,15 @@ replicas continue to be exactly same. Binding a unbindable mount is a invalid operation. -3) smount command +3) Setting mount states - Currently the mount command is not aware of shared subtree features. - Work is in progress to add the support in mount ( util-linux package ). - Till then use the following program. + The mount command (util-linux package) can be used to set mount + states: - ------------------------------------------------------------------------ - // - //this code was developed my Miklos Szeredi <miklos@szeredi.hu> - //and modified by Ram Pai <linuxram@us.ibm.com> - // sample usage: - // smount /tmp shared - // - #include <stdio.h> - #include <stdlib.h> - #include <unistd.h> - #include <string.h> - #include <sys/mount.h> - #include <sys/fsuid.h> - - #ifndef MS_REC - #define MS_REC 0x4000 /* 16384: Recursive loopback */ - #endif - - #ifndef MS_SHARED - #define MS_SHARED 1<<20 /* Shared */ - #endif - - #ifndef MS_PRIVATE - #define MS_PRIVATE 1<<18 /* Private */ - #endif - - #ifndef MS_SLAVE - #define MS_SLAVE 1<<19 /* Slave */ - #endif - - #ifndef MS_UNBINDABLE - #define MS_UNBINDABLE 1<<17 /* Unbindable */ - #endif - - int main(int argc, char *argv[]) - { - int type; - if(argc != 3) { - fprintf(stderr, "usage: %s dir " - "<rshared|rslave|rprivate|runbindable|shared|slave" - "|private|unbindable>\n" , argv[0]); - return 1; - } - - fprintf(stdout, "%s %s %s\n", argv[0], argv[1], argv[2]); - - if (strcmp(argv[2],"rshared")==0) - type=(MS_SHARED|MS_REC); - else if (strcmp(argv[2],"rslave")==0) - type=(MS_SLAVE|MS_REC); - else if (strcmp(argv[2],"rprivate")==0) - type=(MS_PRIVATE|MS_REC); - else if (strcmp(argv[2],"runbindable")==0) - type=(MS_UNBINDABLE|MS_REC); - else if (strcmp(argv[2],"shared")==0) - type=MS_SHARED; - else if (strcmp(argv[2],"slave")==0) - type=MS_SLAVE; - else if (strcmp(argv[2],"private")==0) - type=MS_PRIVATE; - else if (strcmp(argv[2],"unbindable")==0) - type=MS_UNBINDABLE; - else { - fprintf(stderr, "invalid operation: %s\n", argv[2]); - return 1; - } - setfsuid(getuid()); - - if(mount("", argv[1], "dontcare", type, "") == -1) { - perror("mount"); - return 1; - } - return 0; - } - ----------------------------------------------------------------------- - - Copy the above code snippet into smount.c - gcc -o smount smount.c - - - (i) To mark all the mounts under /mnt as shared execute the following - command: - - smount /mnt rshared - the corresponding syntax planned for mount command is - mount --make-rshared /mnt - - just to mark a mount /mnt as shared, execute the following - command: - smount /mnt shared - the corresponding syntax planned for mount command is - mount --make-shared /mnt - - (ii) To mark all the shared mounts under /mnt as slave execute the - following - - command: - smount /mnt rslave - the corresponding syntax planned for mount command is - mount --make-rslave /mnt - - just to mark a mount /mnt as slave, execute the following - command: - smount /mnt slave - the corresponding syntax planned for mount command is - mount --make-slave /mnt - - (iii) To mark all the mounts under /mnt as private execute the - following command: - - smount /mnt rprivate - the corresponding syntax planned for mount command is - mount --make-rprivate /mnt - - just to mark a mount /mnt as private, execute the following - command: - smount /mnt private - the corresponding syntax planned for mount command is - mount --make-private /mnt - - NOTE: by default all the mounts are created as private. But if - you want to change some shared/slave/unbindable mount as - private at a later point in time, this command can help. - - (iv) To mark all the mounts under /mnt as unbindable execute the - following - - command: - smount /mnt runbindable - the corresponding syntax planned for mount command is - mount --make-runbindable /mnt - - just to mark a mount /mnt as unbindable, execute the following - command: - smount /mnt unbindable - the corresponding syntax planned for mount command is - mount --make-unbindable /mnt + mount --make-shared mountpoint + mount --make-slave mountpoint + mount --make-private mountpoint + mount --make-unbindable mountpoint 4) Use cases @@ -350,7 +214,7 @@ replicas continue to be exactly same. mount --rbind / /view/v3 mount --rbind / /view/v4 - and if /usr has a versioning filesystem mounted, than that + and if /usr has a versioning filesystem mounted, then that mount appears at /view/v1/usr, /view/v2/usr, /view/v3/usr and /view/v4/usr too @@ -390,7 +254,7 @@ replicas continue to be exactly same. For example: mount --make-shared /mnt - mount --bin /mnt /tmp + mount --bind /mnt /tmp The mount at /mnt and that at /tmp are both shared and belong to the same peer group. Anything mounted or unmounted under @@ -558,7 +422,7 @@ replicas continue to be exactly same. then the subtree under the unbindable mount is pruned in the new location. - eg: lets say we have the following mount tree. + eg: let's say we have the following mount tree. A / \ @@ -566,7 +430,7 @@ replicas continue to be exactly same. / \ / \ D E F G - Lets say all the mount except the mount C in the tree are + Let's say all the mount except the mount C in the tree are of a type other than unbindable. If this tree is rbound to say Z @@ -683,13 +547,13 @@ replicas continue to be exactly same. 'b' on mounts that receive propagation from mount 'B' and does not have sub-mounts within them are unmounted. - Example: Lets say 'B1', 'B2', 'B3' are shared mounts that propagate to + Example: Let's say 'B1', 'B2', 'B3' are shared mounts that propagate to each other. - lets say 'A1', 'A2', 'A3' are first mounted at dentry 'b' on mount + let's say 'A1', 'A2', 'A3' are first mounted at dentry 'b' on mount 'B1', 'B2' and 'B3' respectively. - lets say 'C1', 'C2', 'C3' are next mounted at the same dentry 'b' on + let's say 'C1', 'C2', 'C3' are next mounted at the same dentry 'b' on mount 'B1', 'B2' and 'B3' respectively. if 'C1' is unmounted, all the mounts that are most-recently-mounted on @@ -710,7 +574,7 @@ replicas continue to be exactly same. A cloned namespace contains all the mounts as that of the parent namespace. - Lets say 'A' and 'B' are the corresponding mounts in the parent and the + Let's say 'A' and 'B' are the corresponding mounts in the parent and the child namespace. If 'A' is shared, then 'B' is also shared and 'A' and 'B' propagate to @@ -759,11 +623,11 @@ replicas continue to be exactly same. mount --make-slave /mnt At this point we have the first mount at /tmp and - its root dentry is 1. Lets call this mount 'A' + its root dentry is 1. Let's call this mount 'A' And then we have a second mount at /tmp1 with root - dentry 2. Lets call this mount 'B' + dentry 2. Let's call this mount 'B' Next we have a third mount at /mnt with root dentry - mnt. Lets call this mount 'C' + mnt. Let's call this mount 'C' 'B' is the slave of 'A' and 'C' is a slave of 'B' A -> B -> C @@ -794,7 +658,7 @@ replicas continue to be exactly same. Q3 Why is unbindable mount needed? - Lets say we want to replicate the mount tree at multiple + Let's say we want to replicate the mount tree at multiple locations within the same subtree. if one rbind mounts a tree within the same subtree 'n' times @@ -803,7 +667,7 @@ replicas continue to be exactly same. mounts. Here is a example. step 1: - lets say the root tree has just two directories with + let's say the root tree has just two directories with one vfsmount. root / \ @@ -875,7 +739,7 @@ replicas continue to be exactly same. Unclonable mounts come in handy here. step 1: - lets say the root tree has just two directories with + let's say the root tree has just two directories with one vfsmount. root / \ diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index f49eecf2e57..623f094c9d8 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -536,6 +536,7 @@ struct address_space_operations { /* migrate the contents of a page to the specified target */ int (*migratepage) (struct page *, struct page *); int (*launder_page) (struct page *); + int (*error_remove_page) (struct mapping *mapping, struct page *page); }; writepage: called by the VM to write a dirty page to backing store. @@ -694,6 +695,12 @@ struct address_space_operations { prevent redirtying the page, it is kept locked during the whole operation. + error_remove_page: normally set to generic_error_remove_page if truncation + is ok for this address space. Used for memory failure handling. + Setting this implies you deal with pages going away under you, + unless you have them locked or reference counts increased. + + The File Object =============== diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt index aafca0a8f66..947374977ca 100644 --- a/Documentation/ioctl/ioctl-number.txt +++ b/Documentation/ioctl/ioctl-number.txt @@ -135,6 +135,7 @@ Code Seq# Include File Comments <http://mikonos.dia.unisa.it/tcfs> 'l' 40-7F linux/udf_fs_i.h in development: <http://sourceforge.net/projects/linux-udf/> +'m' 00-09 linux/mmtimer.h 'm' all linux/mtio.h conflict! 'm' all linux/soundcard.h conflict! 'm' all linux/synclink.h conflict! diff --git a/Documentation/sysctl/fs.txt b/Documentation/sysctl/fs.txt index 1458448436c..62682500878 100644 --- a/Documentation/sysctl/fs.txt +++ b/Documentation/sysctl/fs.txt @@ -96,13 +96,16 @@ handles that the Linux kernel will allocate. When you get lots of error messages about running out of file handles, you might want to increase this limit. -The three values in file-nr denote the number of allocated -file handles, the number of unused file handles and the maximum -number of file handles. When the allocated file handles come -close to the maximum, but the number of unused file handles is -significantly greater than 0, you've encountered a peak in your -usage of file handles and you don't need to increase the maximum. - +Historically, the three values in file-nr denoted the number of +allocated file handles, the number of allocated but unused file +handles, and the maximum number of file handles. Linux 2.6 always +reports 0 as the number of free file handles -- this is not an +error, it just means that the number of allocated file handles +exactly matches the number of used file handles. + +Attempts to allocate more file descriptors than file-max are +reported with printk, look for "VFS: file-max limit <number> +reached". ============================================================== nr_open: diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index b3d8b492274..a028b92001e 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -22,6 +22,7 @@ show up in /proc/sys/kernel: - callhome [ S390 only ] - auto_msgmni - core_pattern +- core_pipe_limit - core_uses_pid - ctrl-alt-del - dentry-state @@ -135,6 +136,27 @@ core_pattern is used to specify a core dumpfile pattern name. ============================================================== +core_pipe_limit: + +This sysctl is only applicable when core_pattern is configured to pipe core +files to user space helper a (when the first character of core_pattern is a '|', +see above). When collecting cores via a pipe to an application, it is +occasionally usefull for the collecting application to gather data about the +crashing process from its /proc/pid directory. In order to do this safely, the +kernel must wait for the collecting process to exit, so as not to remove the +crashing processes proc files prematurely. This in turn creates the possibility +that a misbehaving userspace collecting process can block the reaping of a +crashed process simply by never exiting. This sysctl defends against that. It +defines how many concurrent crashing processes may be piped to user space +applications in parallel. If this value is exceeded, then those crashing +processes above that value are noted via the kernel log and their cores are +skipped. 0 is a special value, indicating that unlimited processes may be +captured in parallel, but that no waiting will take place (i.e. the collecting +process is not guaranteed access to /proc/<crahing pid>/). This value defaults +to 0. + +============================================================== + core_uses_pid: The default coredump filename is "core". By setting diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index e6fb1ec2744..a6e360d2055 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -32,6 +32,8 @@ Currently, these files are in /proc/sys/vm: - legacy_va_layout - lowmem_reserve_ratio - max_map_count +- memory_failure_early_kill +- memory_failure_recovery - min_free_kbytes - min_slab_ratio - min_unmapped_ratio @@ -53,7 +55,6 @@ Currently, these files are in /proc/sys/vm: - vfs_cache_pressure - zone_reclaim_mode - ============================================================== block_dump @@ -275,6 +276,44 @@ e.g., up to one or two maps per allocation. The default value is 65536. +============================================================= + +memory_failure_early_kill: + +Control how to kill processes when uncorrected memory error (typically +a 2bit error in a memory module) is detected in the background by hardware +that cannot be handled by the kernel. In some cases (like the page +still having a valid copy on disk) the kernel will handle the failure +transparently without affecting any applications. But if there is +no other uptodate copy of the data it will kill to prevent any data +corruptions from propagating. + +1: Kill all processes that have the corrupted and not reloadable page mapped +as soon as the corruption is detected. Note this is not supported +for a few types of pages, like kernel internally allocated data or +the swap cache, but works for the majority of user pages. + +0: Only unmap the corrupted page from all processes and only kill a process +who tries to access it. + +The kill is done using a catchable SIGBUS with BUS_MCEERR_AO, so processes can +handle this if they want to. + +This is only active on architectures/platforms with advanced machine +check handling and depends on the hardware capabilities. + +Applications can override this setting individually with the PR_MCE_KILL prctl + +============================================================== + +memory_failure_recovery + +Enable memory failure recovery (when supported by the platform) + +1: Attempt recovery. + +0: Always panic on a memory failure. + ============================================================== min_free_kbytes: diff --git a/Documentation/vm/.gitignore b/Documentation/vm/.gitignore index 33e8a023df0..09b164a5700 100644 --- a/Documentation/vm/.gitignore +++ b/Documentation/vm/.gitignore @@ -1 +1,2 @@ +page-types slabinfo diff --git a/Documentation/vm/locking b/Documentation/vm/locking index f366fa95617..25fadb44876 100644 --- a/Documentation/vm/locking +++ b/Documentation/vm/locking @@ -80,7 +80,7 @@ Note: PTL can also be used to guarantee that no new clones using the mm start up ... this is a loose form of stability on mm_users. For example, it is used in copy_mm to protect against a racing tlb_gather_mmu single address space optimization, so that the zap_page_range (from -vmtruncate) does not lose sending ipi's to cloned threads that might +truncate) does not lose sending ipi's to cloned threads that might be spawned underneath it and go to user mode to drag in pte's into tlbs. swap_lock diff --git a/Documentation/vm/page-types.c b/Documentation/vm/page-types.c index 3eda8ea0085..fa1a30d9e9d 100644 --- a/Documentation/vm/page-types.c +++ b/Documentation/vm/page-types.c @@ -5,6 +5,7 @@ * Copyright (C) 2009 Wu Fengguang <fengguang.wu@intel.com> */ +#define _LARGEFILE64_SOURCE #include <stdio.h> #include <stdlib.h> #include <unistd.h> @@ -13,12 +14,33 @@ #include <string.h> #include <getopt.h> #include <limits.h> +#include <assert.h> #include <sys/types.h> #include <sys/errno.h> #include <sys/fcntl.h> /* + * pagemap kernel ABI bits + */ + +#define PM_ENTRY_BYTES sizeof(uint64_t) +#define PM_STATUS_BITS 3 +#define PM_STATUS_OFFSET (64 - PM_STATUS_BITS) +#define PM_STATUS_MASK (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET) +#define PM_STATUS(nr) (((nr) << PM_STATUS_OFFSET) & PM_STATUS_MASK) +#define PM_PSHIFT_BITS 6 +#define PM_PSHIFT_OFFSET (PM_STATUS_OFFSET - PM_PSHIFT_BITS) +#define PM_PSHIFT_MASK (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET) +#define PM_PSHIFT(x) (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK) +#define PM_PFRAME_MASK ((1LL << PM_PSHIFT_OFFSET) - 1) +#define PM_PFRAME(x) ((x) & PM_PFRAME_MASK) + +#define PM_PRESENT PM_STATUS(4LL) +#define PM_SWAP PM_STATUS(2LL) + + +/* * kernel page flags */ @@ -126,6 +148,14 @@ static int nr_addr_ranges; static unsigned long opt_offset[MAX_ADDR_RANGES]; static unsigned long opt_size[MAX_ADDR_RANGES]; +#define MAX_VMAS 10240 +static int nr_vmas; +static unsigned long pg_start[MAX_VMAS]; +static unsigned long pg_end[MAX_VMAS]; +static unsigned long voffset; + +static int pagemap_fd; + #define MAX_BIT_FILTERS 64 static int nr_bit_filters; static uint64_t opt_mask[MAX_BIT_FILTERS]; @@ -135,7 +165,6 @@ static int page_size; #define PAGES_BATCH (64 << 10) /* 64k pages */ static int kpageflags_fd; -static uint64_t kpageflags_buf[KPF_BYTES * PAGES_BATCH]; #define HASH_SHIFT 13 #define HASH_SIZE (1 << HASH_SHIFT) @@ -158,6 +187,11 @@ static uint64_t page_flags[HASH_SIZE]; type __min2 = (y); \ __min1 < __min2 ? __min1 : __min2; }) +#define max_t(type, x, y) ({ \ + type __max1 = (x); \ + type __max2 = (y); \ + __max1 > __max2 ? __max1 : __max2; }) + static unsigned long pages2mb(unsigned long pages) { return (pages * page_size) >> 20; @@ -224,26 +258,34 @@ static char *page_flag_longname(uint64_t flags) static void show_page_range(unsigned long offset, uint64_t flags) { static uint64_t flags0; + static unsigned long voff; static unsigned long index; static unsigned long count; - if (flags == flags0 && offset == index + count) { + if (flags == flags0 && offset == index + count && + (!opt_pid || voffset == voff + count)) { count++; return; } - if (count) - printf("%lu\t%lu\t%s\n", + if (count) { + if (opt_pid) + printf("%lx\t", voff); + printf("%lx\t%lx\t%s\n", index, count, page_flag_name(flags0)); + } flags0 = flags; index = offset; + voff = voffset; count = 1; } static void show_page(unsigned long offset, uint64_t flags) { - printf("%lu\t%s\n", offset, page_flag_name(flags)); + if (opt_pid) + printf("%lx\t", voffset); + printf("%lx\t%s\n", offset, page_flag_name(flags)); } static void show_summary(void) @@ -383,6 +425,8 @@ static void walk_pfn(unsigned long index, unsigned long count) lseek(kpageflags_fd, index * KPF_BYTES, SEEK_SET); while (count) { + uint64_t kpageflags_buf[KPF_BYTES * PAGES_BATCH]; + batch = min_t(unsigned long, count, PAGES_BATCH); n = read(kpageflags_fd, kpageflags_buf, batch * KPF_BYTES); if (n == 0) @@ -404,6 +448,81 @@ static void walk_pfn(unsigned long index, unsigned long count) } } + +#define PAGEMAP_BATCH 4096 +static unsigned long task_pfn(unsigned long pgoff) +{ + static uint64_t buf[PAGEMAP_BATCH]; + static unsigned long start; + static long count; + uint64_t pfn; + + if (pgoff < start || pgoff >= start + count) { + if (lseek64(pagemap_fd, + (uint64_t)pgoff * PM_ENTRY_BYTES, + SEEK_SET) < 0) { + perror("pagemap seek"); + exit(EXIT_FAILURE); + } + count = read(pagemap_fd, buf, sizeof(buf)); + if (count == 0) + return 0; + if (count < 0) { + perror("pagemap read"); + exit(EXIT_FAILURE); + } + if (count % PM_ENTRY_BYTES) { + fatal("pagemap read not aligned.\n"); + exit(EXIT_FAILURE); + } + count /= PM_ENTRY_BYTES; + start = pgoff; + } + + pfn = buf[pgoff - start]; + if (pfn & PM_PRESENT) + pfn = PM_PFRAME(pfn); + else + pfn = 0; + + return pfn; +} + +static void walk_task(unsigned long index, unsigned long count) +{ + int i = 0; + const unsigned long end = index + count; + + while (index < end) { + + while (pg_end[i] <= index) + if (++i >= nr_vmas) + return; + if (pg_start[i] >= end) + return; + + voffset = max_t(unsigned long, pg_start[i], index); + index = min_t(unsigned long, pg_end[i], end); + + assert(voffset < index); + for (; voffset < index; voffset++) { + unsigned long pfn = task_pfn(voffset); + if (pfn) + walk_pfn(pfn, 1); + } + } +} + +static void add_addr_range(unsigned long offset, unsigned long size) +{ + if (nr_addr_ranges >= MAX_ADDR_RANGES) + fatal("too many addr ranges\n"); + + opt_offset[nr_addr_ranges] = offset; + opt_size[nr_addr_ranges] = min_t(unsigned long, size, ULONG_MAX-offset); + nr_addr_ranges++; +} + static void walk_addr_ranges(void) { int i; @@ -415,10 +534,13 @@ static void walk_addr_ranges(void) } if (!nr_addr_ranges) - walk_pfn(0, ULONG_MAX); + add_addr_range(0, ULONG_MAX); for (i = 0; i < nr_addr_ranges; i++) - walk_pfn(opt_offset[i], opt_size[i]); + if (!opt_pid) + walk_pfn(opt_offset[i], opt_size[i]); + else + walk_task(opt_offset[i], opt_size[i]); close(kpageflags_fd); } @@ -446,8 +568,8 @@ static void usage(void) " -r|--raw Raw mode, for kernel developers\n" " -a|--addr addr-spec Walk a range of pages\n" " -b|--bits bits-spec Walk pages with specified bits\n" -#if 0 /* planned features */ " -p|--pid pid Walk process address space\n" +#if 0 /* planned features */ " -f|--file filename Walk file address space\n" #endif " -l|--list Show page details in ranges\n" @@ -459,7 +581,7 @@ static void usage(void) " N+M pages range from N to N+M-1\n" " N,M pages range from N to M-1\n" " N, pages range from N to end\n" -" ,M pages range from 0 to M\n" +" ,M pages range from 0 to M-1\n" "bits-spec:\n" " bit1,bit2 (flags & (bit1|bit2)) != 0\n" " bit1,bit2=bit1 (flags & (bit1|bit2)) == bit1\n" @@ -496,21 +618,57 @@ static unsigned long long parse_number(const char *str) static void parse_pid(const char *str) { + FILE *file; + char buf[5000]; + opt_pid = parse_number(str); -} -static void parse_file(const char *name) -{ + sprintf(buf, "/proc/%d/pagemap", opt_pid); + pagemap_fd = open(buf, O_RDONLY); + if (pagemap_fd < 0) { + perror(buf); + exit(EXIT_FAILURE); + } + + sprintf(buf, "/proc/%d/maps", opt_pid); + file = fopen(buf, "r"); + if (!file) { + perror(buf); + exit(EXIT_FAILURE); + } + + while (fgets(buf, sizeof(buf), file) != NULL) { + unsigned long vm_start; + unsigned long vm_end; + unsigned long long pgoff; + int major, minor; + char r, w, x, s; + unsigned long ino; + int n; + + n = sscanf(buf, "%lx-%lx %c%c%c%c %llx %x:%x %lu", + &vm_start, + &vm_end, + &r, &w, &x, &s, + &pgoff, + &major, &minor, + &ino); + if (n < 10) { + fprintf(stderr, "unexpected line: %s\n", buf); + continue; + } + pg_start[nr_vmas] = vm_start / page_size; + pg_end[nr_vmas] = vm_end / page_size; + if (++nr_vmas >= MAX_VMAS) { + fprintf(stderr, "too many VMAs\n"); + break; + } + } + fclose(file); } -static void add_addr_range(unsigned long offset, unsigned long size) +static void parse_file(const char *name) { - if (nr_addr_ranges >= MAX_ADDR_RANGES) - fatal("too much addr ranges\n"); - - opt_offset[nr_addr_ranges] = offset; - opt_size[nr_addr_ranges] = size; - nr_addr_ranges++; } static void parse_addr_range(const char *optarg) @@ -676,8 +834,10 @@ int main(int argc, char *argv[]) } } + if (opt_list && opt_pid) + printf("voffset\t"); if (opt_list == 1) - printf("offset\tcount\tflags\n"); + printf("offset\tlen\tflags\n"); if (opt_list == 2) printf("offset\tflags\n"); |