diff options
91 files changed, 2089 insertions, 362 deletions
diff --git a/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870 b/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870 new file mode 100644 index 0000000..aa11dbd --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870 @@ -0,0 +1,56 @@ +What: /sys/class/backlight/<backlight>/<ambient light zone>_max +What: /sys/class/backlight/<backlight>/l1_daylight_max +What: /sys/class/backlight/<backlight>/l2_bright_max +What: /sys/class/backlight/<backlight>/l3_office_max +What: /sys/class/backlight/<backlight>/l4_indoor_max +What: /sys/class/backlight/<backlight>/l5_dark_max +Date: Mai 2011 +KernelVersion: 2.6.40 +Contact: device-drivers-devel@blackfin.uclinux.org +Description: + Control the maximum brightness for <ambient light zone> + on this <backlight>. Values are between 0 and 127. This file + will also show the brightness level stored for this + <ambient light zone>. + +What: /sys/class/backlight/<backlight>/<ambient light zone>_dim +What: /sys/class/backlight/<backlight>/l2_bright_dim +What: /sys/class/backlight/<backlight>/l3_office_dim +What: /sys/class/backlight/<backlight>/l4_indoor_dim +What: /sys/class/backlight/<backlight>/l5_dark_dim +Date: Mai 2011 +KernelVersion: 2.6.40 +Contact: device-drivers-devel@blackfin.uclinux.org +Description: + Control the dim brightness for <ambient light zone> + on this <backlight>. Values are between 0 and 127, typically + set to 0. Full off when the backlight is disabled. + This file will also show the dim brightness level stored for + this <ambient light zone>. + +What: /sys/class/backlight/<backlight>/ambient_light_level +Date: Mai 2011 +KernelVersion: 2.6.40 +Contact: device-drivers-devel@blackfin.uclinux.org +Description: + Get conversion value of the light sensor. + This value is updated every 80 ms (when the light sensor + is enabled). Returns integer between 0 (dark) and + 8000 (max ambient brightness) + +What: /sys/class/backlight/<backlight>/ambient_light_zone +Date: Mai 2011 +KernelVersion: 2.6.40 +Contact: device-drivers-devel@blackfin.uclinux.org +Description: + Get/Set current ambient light zone. Reading returns + integer between 1..5 (1 = daylight, 2 = bright, ..., 5 = dark). + Writing a value between 1..5 forces the backlight controller + to enter the corresponding ambient light zone. + Writing 0 returns to normal/automatic ambient light level + operation. The ambient light sensing feature on these devices + is an extension to the API documented in + Documentation/ABI/stable/sysfs-class-backlight. + It can be enabled by writing the value stored in + /sys/class/backlight/<backlight>/max_brightness to + /sys/class/backlight/<backlight>/brightness.
\ No newline at end of file diff --git a/Documentation/accounting/cgroupstats.txt b/Documentation/accounting/cgroupstats.txt index eda40fd..d16a984 100644 --- a/Documentation/accounting/cgroupstats.txt +++ b/Documentation/accounting/cgroupstats.txt @@ -21,7 +21,7 @@ information will not be available. To extract cgroup statistics a utility very similar to getdelays.c has been developed, the sample output of the utility is shown below -~/balbir/cgroupstats # ./getdelays -C "/cgroup/a" +~/balbir/cgroupstats # ./getdelays -C "/sys/fs/cgroup/a" sleeping 1, blocked 0, running 1, stopped 0, uninterruptible 0 -~/balbir/cgroupstats # ./getdelays -C "/cgroup" +~/balbir/cgroupstats # ./getdelays -C "/sys/fs/cgroup" sleeping 155, blocked 0, running 1, stopped 0, uninterruptible 2 diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt index 465351d..cd45c8e 100644 --- a/Documentation/cgroups/blkio-controller.txt +++ b/Documentation/cgroups/blkio-controller.txt @@ -28,16 +28,19 @@ cgroups. Here is what you can do. - Enable group scheduling in CFQ CONFIG_CFQ_GROUP_IOSCHED=y -- Compile and boot into kernel and mount IO controller (blkio). +- Compile and boot into kernel and mount IO controller (blkio); see + cgroups.txt, Why are cgroups needed?. - mount -t cgroup -o blkio none /cgroup + mount -t tmpfs cgroup_root /sys/fs/cgroup + mkdir /sys/fs/cgroup/blkio + mount -t cgroup -o blkio none /sys/fs/cgroup/blkio - Create two cgroups - mkdir -p /cgroup/test1/ /cgroup/test2 + mkdir -p /sys/fs/cgroup/blkio/test1/ /sys/fs/cgroup/blkio/test2 - Set weights of group test1 and test2 - echo 1000 > /cgroup/test1/blkio.weight - echo 500 > /cgroup/test2/blkio.weight + echo 1000 > /sys/fs/cgroup/blkio/test1/blkio.weight + echo 500 > /sys/fs/cgroup/blkio/test2/blkio.weight - Create two same size files (say 512MB each) on same disk (file1, file2) and launch two dd threads in different cgroup to read those files. @@ -46,12 +49,12 @@ cgroups. Here is what you can do. echo 3 > /proc/sys/vm/drop_caches dd if=/mnt/sdb/zerofile1 of=/dev/null & - echo $! > /cgroup/test1/tasks - cat /cgroup/test1/tasks + echo $! > /sys/fs/cgroup/blkio/test1/tasks + cat /sys/fs/cgroup/blkio/test1/tasks dd if=/mnt/sdb/zerofile2 of=/dev/null & - echo $! > /cgroup/test2/tasks - cat /cgroup/test2/tasks + echo $! > /sys/fs/cgroup/blkio/test2/tasks + cat /sys/fs/cgroup/blkio/test2/tasks - At macro level, first dd should finish first. To get more precise data, keep on looking at (with the help of script), at blkio.disk_time and @@ -68,13 +71,13 @@ Throttling/Upper Limit policy - Enable throttling in block layer CONFIG_BLK_DEV_THROTTLING=y -- Mount blkio controller - mount -t cgroup -o blkio none /cgroup/blkio +- Mount blkio controller (see cgroups.txt, Why are cgroups needed?) + mount -t cgroup -o blkio none /sys/fs/cgroup/blkio - Specify a bandwidth rate on particular device for root group. The format for policy is "<major>:<minor> <byes_per_second>". - echo "8:16 1048576" > /cgroup/blkio/blkio.read_bps_device + echo "8:16 1048576" > /sys/fs/cgroup/blkio/blkio.read_bps_device Above will put a limit of 1MB/second on reads happening for root group on device having major/minor number 8:16. @@ -108,7 +111,7 @@ Hierarchical Cgroups CFQ and throttling will practically treat all groups at same level. pivot - / | \ \ + / / \ \ root test1 test2 test3 Down the line we can implement hierarchical accounting/control support @@ -149,7 +152,7 @@ Proportional weight policy files Following is the format. - #echo dev_maj:dev_minor weight > /path/to/cgroup/blkio.weight_device + # echo dev_maj:dev_minor weight > blkio.weight_device Configure weight=300 on /dev/sdb (8:16) in this cgroup # echo 8:16 300 > blkio.weight_device # cat blkio.weight_device diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index 0ed99f0..cd67e90 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -138,11 +138,11 @@ With the ability to classify tasks differently for different resources the admin can easily set up a script which receives exec notifications and depending on who is launching the browser he can - # echo browser_pid > /mnt/<restype>/<userclass>/tasks + # echo browser_pid > /sys/fs/cgroup/<restype>/<userclass>/tasks With only a single hierarchy, he now would potentially have to create a separate cgroup for every browser launched and associate it with -approp network and other resource class. This may lead to +appropriate network and other resource class. This may lead to proliferation of such cgroups. Also lets say that the administrator would like to give enhanced network @@ -153,9 +153,9 @@ apps enhanced CPU power, With ability to write pids directly to resource classes, it's just a matter of : - # echo pid > /mnt/network/<new_class>/tasks + # echo pid > /sys/fs/cgroup/network/<new_class>/tasks (after some time) - # echo pid > /mnt/network/<orig_class>/tasks + # echo pid > /sys/fs/cgroup/network/<orig_class>/tasks Without this ability, he would have to split the cgroup into multiple separate ones and then associate the new cgroups with the @@ -310,21 +310,24 @@ subsystem, this is the case for the cpuset. To start a new job that is to be contained within a cgroup, using the "cpuset" cgroup subsystem, the steps are something like: - 1) mkdir /dev/cgroup - 2) mount -t cgroup -ocpuset cpuset /dev/cgroup - 3) Create the new cgroup by doing mkdir's and write's (or echo's) in - the /dev/cgroup virtual file system. - 4) Start a task that will be the "founding father" of the new job. - 5) Attach that task to the new cgroup by writing its pid to the - /dev/cgroup tasks file for that cgroup. - 6) fork, exec or clone the job tasks from this founding father task. + 1) mount -t tmpfs cgroup_root /sys/fs/cgroup + 2) mkdir /sys/fs/cgroup/cpuset + 3) mount -t cgroup -ocpuset cpuset /sys/fs/cgroup/cpuset + 4) Create the new cgroup by doing mkdir's and write's (or echo's) in + the /sys/fs/cgroup virtual file system. + 5) Start a task that will be the "founding father" of the new job. + 6) Attach that task to the new cgroup by writing its pid to the + /sys/fs/cgroup/cpuset/tasks file for that cgroup. + 7) fork, exec or clone the job tasks from this founding father task. For example, the following sequence of commands will setup a cgroup named "Charlie", containing just CPUs 2 and 3, and Memory Node 1, and then start a subshell 'sh' in that cgroup: - mount -t cgroup cpuset -ocpuset /dev/cgroup - cd /dev/cgroup + mount -t tmpfs cgroup_root /sys/fs/cgroup + mkdir /sys/fs/cgroup/cpuset + mount -t cgroup cpuset -ocpuset /sys/fs/cgroup/cpuset + cd /sys/fs/cgroup/cpuset mkdir Charlie cd Charlie /bin/echo 2-3 > cpuset.cpus @@ -345,7 +348,7 @@ Creating, modifying, using the cgroups can be done through the cgroup virtual filesystem. To mount a cgroup hierarchy with all available subsystems, type: -# mount -t cgroup xxx /dev/cgroup +# mount -t cgroup xxx /sys/fs/cgroup The "xxx" is not interpreted by the cgroup code, but will appear in /proc/mounts so may be any useful identifying string that you like. @@ -354,23 +357,32 @@ Note: Some subsystems do not work without some user input first. For instance, if cpusets are enabled the user will have to populate the cpus and mems files for each new cgroup created before that group can be used. +As explained in section `1.2 Why are cgroups needed?' you should create +different hierarchies of cgroups for each single resource or group of +resources you want to control. Therefore, you should mount a tmpfs on +/sys/fs/cgroup and create directories for each cgroup resource or resource +group. + +# mount -t tmpfs cgroup_root /sys/fs/cgroup +# mkdir /sys/fs/cgroup/rg1 + To mount a cgroup hierarchy with just the cpuset and memory subsystems, type: -# mount -t cgroup -o cpuset,memory hier1 /dev/cgroup +# mount -t cgroup -o cpuset,memory hier1 /sys/fs/cgroup/rg1 To change the set of subsystems bound to a mounted hierarchy, just remount with different options: -# mount -o remount,cpuset,blkio hier1 /dev/cgroup +# mount -o remount,cpuset,blkio hier1 /sys/fs/cgroup/rg1 Now memory is removed from the hierarchy and blkio is added. Note this will add blkio to the hierarchy but won't remove memory or cpuset, because the new options are appended to the old ones: -# mount -o remount,blkio /dev/cgroup +# mount -o remount,blkio /sys/fs/cgroup/rg1 To Specify a hierarchy's release_agent: # mount -t cgroup -o cpuset,release_agent="/sbin/cpuset_release_agent" \ - xxx /dev/cgroup + xxx /sys/fs/cgroup/rg1 Note that specifying 'release_agent' more than once will return failure. @@ -379,17 +391,17 @@ when the hierarchy consists of a single (root) cgroup. Supporting the ability to arbitrarily bind/unbind subsystems from an existing cgroup hierarchy is intended to be implemented in the future. -Then under /dev/cgroup you can find a tree that corresponds to the -tree of the cgroups in the system. For instance, /dev/cgroup +Then under /sys/fs/cgroup/rg1 you can find a tree that corresponds to the +tree of the cgroups in the system. For instance, /sys/fs/cgroup/rg1 is the cgroup that holds the whole system. If you want to change the value of release_agent: -# echo "/sbin/new_release_agent" > /dev/cgroup/release_agent +# echo "/sbin/new_release_agent" > /sys/fs/cgroup/rg1/release_agent It can also be changed via remount. -If you want to create a new cgroup under /dev/cgroup: -# cd /dev/cgroup +If you want to create a new cgroup under /sys/fs/cgroup/rg1: +# cd /sys/fs/cgroup/rg1 # mkdir my_cgroup Now you want to do something with this cgroup. diff --git a/Documentation/cgroups/cpuacct.txt b/Documentation/cgroups/cpuacct.txt index 8b93094..9ad85df 100644 --- a/Documentation/cgroups/cpuacct.txt +++ b/Documentation/cgroups/cpuacct.txt @@ -10,26 +10,25 @@ directly present in its group. Accounting groups can be created by first mounting the cgroup filesystem. -# mkdir /cgroups -# mount -t cgroup -ocpuacct none /cgroups - -With the above step, the initial or the parent accounting group -becomes visible at /cgroups. At bootup, this group includes all the -tasks in the system. /cgroups/tasks lists the tasks in this cgroup. -/cgroups/cpuacct.usage gives the CPU time (in nanoseconds) obtained by -this group which is essentially the CPU time obtained by all the tasks +# mount -t cgroup -ocpuacct none /sys/fs/cgroup + +With the above step, the initial or the parent accounting group becomes +visible at /sys/fs/cgroup. At bootup, this group includes all the tasks in +the system. /sys/fs/cgroup/tasks lists the tasks in this cgroup. +/sys/fs/cgroup/cpuacct.usage gives the CPU time (in nanoseconds) obtained +by this group which is essentially the CPU time obtained by all the tasks in the system. -New accounting groups can be created under the parent group /cgroups. +New accounting groups can be created under the parent group /sys/fs/cgroup. -# cd /cgroups +# cd /sys/fs/cgroup # mkdir g1 # echo $$ > g1 The above steps create a new group g1 and move the current shell process (bash) into it. CPU time consumed by this bash and its children can be obtained from g1/cpuacct.usage and the same is accumulated in -/cgroups/cpuacct.usage also. +/sys/fs/cgroup/cpuacct.usage also. cpuacct.stat file lists a few statistics which further divide the CPU time obtained by the cgroup into user and system times. Currently diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt index 98a3082..5b0d78e 100644 --- a/Documentation/cgroups/cpusets.txt +++ b/Documentation/cgroups/cpusets.txt @@ -661,21 +661,21 @@ than stress the kernel. To start a new job that is to be contained within a cpuset, the steps are: - 1) mkdir /dev/cpuset - 2) mount -t cgroup -ocpuset cpuset /dev/cpuset + 1) mkdir /sys/fs/cgroup/cpuset + 2) mount -t cgroup -ocpuset cpuset /sys/fs/cgroup/cpuset 3) Create the new cpuset by doing mkdir's and write's (or echo's) in - the /dev/cpuset virtual file system. + the /sys/fs/cgroup/cpuset virtual file system. 4) Start a task that will be the "founding father" of the new job. 5) Attach that task to the new cpuset by writing its pid to the - /dev/cpuset tasks file for that cpuset. + /sys/fs/cgroup/cpuset tasks file for that cpuset. 6) fork, exec or clone the job tasks from this founding father task. For example, the following sequence of commands will setup a cpuset named "Charlie", containing just CPUs 2 and 3, and Memory Node 1, and then start a subshell 'sh' in that cpuset: - mount -t cgroup -ocpuset cpuset /dev/cpuset - cd /dev/cpuset + mount -t cgroup -ocpuset cpuset /sys/fs/cgroup/cpuset + cd /sys/fs/cgroup/cpuset mkdir Charlie cd Charlie /bin/echo 2-3 > cpuset.cpus @@ -710,14 +710,14 @@ Creating, modifying, using the cpusets can be done through the cpuset virtual filesystem. To mount it, type: -# mount -t cgroup -o cpuset cpuset /dev/cpuset +# mount -t cgroup -o cpuset cpuset /sys/fs/cgroup/cpuset -Then under /dev/cpuset you can find a tree that corresponds to the -tree of the cpusets in the system. For instance, /dev/cpuset +Then under /sys/fs/cgroup/cpuset you can find a tree that corresponds to the +tree of the cpusets in the system. For instance, /sys/fs/cgroup/cpuset is the cpuset that holds the whole system. -If you want to create a new cpuset under /dev/cpuset: -# cd /dev/cpuset +If you want to create a new cpuset under /sys/fs/cgroup/cpuset: +# cd /sys/fs/cgroup/cpuset # mkdir my_cpuset Now you want to do something with this cpuset. @@ -765,12 +765,12 @@ wrapper around the cgroup filesystem. The command -mount -t cpuset X /dev/cpuset +mount -t cpuset X /sys/fs/cgroup/cpuset is equivalent to -mount -t cgroup -ocpuset,noprefix X /dev/cpuset -echo "/sbin/cpuset_release_agent" > /dev/cpuset/release_agent +mount -t cgroup -ocpuset,noprefix X /sys/fs/cgroup/cpuset +echo "/sbin/cpuset_release_agent" > /sys/fs/cgroup/cpuset/release_agent 2.2 Adding/removing cpus ------------------------ diff --git a/Documentation/cgroups/devices.txt b/Documentation/cgroups/devices.txt index 57ca4c8..16624a7f8 100644 --- a/Documentation/cgroups/devices.txt +++ b/Documentation/cgroups/devices.txt @@ -22,16 +22,16 @@ removed from the child(ren). An entry is added using devices.allow, and removed using devices.deny. For instance - echo 'c 1:3 mr' > /cgroups/1/devices.allow + echo 'c 1:3 mr' > /sys/fs/cgroup/1/devices.allow allows cgroup 1 to read and mknod the device usually known as /dev/null. Doing - echo a > /cgroups/1/devices.deny + echo a > /sys/fs/cgroup/1/devices.deny will remove the default 'a *:* rwm' entry. Doing - echo a > /cgroups/1/devices.allow + echo a > /sys/fs/cgroup/1/devices.allow will add the 'a *:* rwm' entry to the whitelist. diff --git a/Documentation/cgroups/freezer-subsystem.txt b/Documentation/cgroups/freezer-subsystem.txt index 41f37fe..c21d777 100644 --- a/Documentation/cgroups/freezer-subsystem.txt +++ b/Documentation/cgroups/freezer-subsystem.txt @@ -59,28 +59,28 @@ is non-freezable. * Examples of usage : - # mkdir /containers - # mount -t cgroup -ofreezer freezer /containers - # mkdir /containers/0 - # echo $some_pid > /containers/0/tasks + # mkdir /sys/fs/cgroup/freezer + # mount -t cgroup -ofreezer freezer /sys/fs/cgroup/freezer + # mkdir /sys/fs/cgroup/freezer/0 + # echo $some_pid > /sys/fs/cgroup/freezer/0/tasks to get status of the freezer subsystem : - # cat /containers/0/freezer.state + # cat /sys/fs/cgroup/freezer/0/freezer.state THAWED to freeze all tasks in the container : - # echo FROZEN > /containers/0/freezer.state - # cat /containers/0/freezer.state + # echo FROZEN > /sys/fs/cgroup/freezer/0/freezer.state + # cat /sys/fs/cgroup/freezer/0/freezer.state FREEZING - # cat /containers/0/freezer.state + # cat /sys/fs/cgroup/freezer/0/freezer.state FROZEN to unfreeze all tasks in the container : - # echo THAWED > /containers/0/freezer.state - # cat /containers/0/freezer.state + # echo THAWED > /sys/fs/cgroup/freezer/0/freezer.state + # cat /sys/fs/cgroup/freezer/0/freezer.state THAWED This is the basic mechanism which should do the right thing for user space task diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index 7c16347..06eb6d9 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -1,8 +1,8 @@ Memory Resource Controller -NOTE: The Memory Resource Controller has been generically been referred - to as the memory controller in this document. Do not confuse memory - controller used here with the memory controller that is used in hardware. +NOTE: The Memory Resource Controller has generically been referred to as the + memory controller in this document. Do not confuse memory controller + used here with the memory controller that is used in hardware. (For editors) In this document: @@ -70,6 +70,7 @@ Brief summary of control files. (See sysctl's vm.swappiness) memory.move_charge_at_immigrate # set/show controls of moving charges memory.oom_control # set/show oom controls. + memory.numa_stat # show the number of memory usage per numa node 1. History @@ -181,7 +182,7 @@ 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: If CONFIG_CGROUP_CGROUP_MEM_RES_CTLR_SWAP is not used.. +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. @@ -213,7 +214,7 @@ affecting global LRU, memory+swap limit is better than just limiting swap from OS point of view. * What happens when a cgroup hits memory.memsw.limit_in_bytes -When a cgroup his memory.memsw.limit_in_bytes, it's useless to do swap-out +When a cgroup hits memory.memsw.limit_in_bytes, it's useless to do swap-out in this cgroup. Then, swap-out will not be done by cgroup routine and file caches are dropped. But as mentioned above, global LRU can do swapout memory from it for sanity of the system's memory management state. You can't forbid @@ -263,16 +264,17 @@ b. Enable CONFIG_RESOURCE_COUNTERS c. Enable CONFIG_CGROUP_MEM_RES_CTLR d. Enable CONFIG_CGROUP_MEM_RES_CTLR_SWAP (to use swap extension) -1. Prepare the cgroups -# mkdir -p /cgroups -# mount -t cgroup none /cgroups -o memory +1. Prepare the cgroups (see cgroups.txt, Why are cgroups needed?) +# mount -t tmpfs none /sys/fs/cgroup +# mkdir /sys/fs/cgroup/memory +# mount -t cgroup none /sys/fs/cgroup/memory -o memory 2. Make the new group and move bash into it -# mkdir /cgroups/0 -# echo $$ > /cgroups/0/tasks +# mkdir /sys/fs/cgroup/memory/0 +# echo $$ > /sys/fs/cgroup/memory/0/tasks Since now we're in the 0 cgroup, we can alter the memory limit: -# echo 4M > /cgroups/0/memory.limit_in_bytes +# echo 4M > /sys/fs/cgroup/memory/0/memory.limit_in_bytes NOTE: We can use a suffix (k, K, m, M, g or G) to indicate values in kilo, mega or gigabytes. (Here, Kilo, Mega, Giga are Kibibytes, Mebibytes, Gibibytes.) @@ -280,11 +282,11 @@ mega or gigabytes. (Here, Kilo, Mega, Giga are Kibibytes, Mebibytes, Gibibytes.) 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 +# cat /sys/fs/cgroup/memory/0/memory.limit_in_bytes 4194304 We can check the usage: -# cat /cgroups/0/memory.usage_in_bytes +# cat /sys/fs/cgroup/memory/0/memory.usage_in_bytes 1216512 A successful write to this file does not guarantee a successful set of @@ -464,6 +466,24 @@ value for efficient access. (Of course, when necessary, it's synchronized.) If you want to know more exact memory usage, you should use RSS+CACHE(+SWAP) value in memory.stat(see 5.2). +5.6 numa_stat + +This is similar to numa_maps but operates on a per-memcg basis. This is +useful for providing visibility into the numa locality information within +an memcg since the pages are allowed to be allocated from any physical +node. One of the usecases is evaluating application performance by +combining this information with the application's cpu allocation. + +We export "total", "file", "anon" and "unevictable" pages per-node for +each memcg. The ouput format of memory.numa_stat is: + +total=<total pages> N0=<node 0 pages> N1=<node 1 pages> ... +file=<total file pages> N0=<node 0 pages> N1=<node 1 pages> ... +anon=<total anon pages> N0=<node 0 pages> N1=<node 1 pages> ... +unevictable=<total anon pages> N0=<node 0 pages> N1=<node 1 pages> ... + +And we have total = file + anon + unevictable. + 6. Hierarchy support The memory controller supports a deep hierarchy and hierarchical accounting. @@ -471,13 +491,13 @@ The hierarchy is created by creating the appropriate cgroups in the cgroup filesystem. Consider for example, the following cgroup filesystem hierarchy - root + root / | \ - / | \ - a b c - | \ - | \ - d e + / | \ + 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), diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 1a9446b..72e2384 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -481,23 +481,6 @@ Who: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> ---------------------------- -What: namespace cgroup (ns_cgroup) -When: 2.6.38 -Why: The ns_cgroup leads to some problems: - * cgroup creation is out-of-control - * cgroup name can conflict when pids are looping - * it is not possible to have a single process handling - a lot of namespaces without falling in a exponential creation time - * we may want to create a namespace without creating a cgroup - - The ns_cgroup is replaced by a compatibility flag 'clone_children', - where a newly created cgroup will copy the parent cgroup values. - The userspace has to manually create a cgroup and add a task to - the 'tasks' file. -Who: Daniel Lezcano <daniel.lezcano@free.fr> - ----------------------------- - What: iwlwifi disable_hw_scan module parameters When: 2.6.40 Why: Hareware scan is the prefer method for iwlwifi devices for diff --git a/Documentation/kmemleak.txt b/Documentation/kmemleak.txt index 090e6ee..51063e6 100644 --- a/Documentation/kmemleak.txt +++ b/Documentation/kmemleak.txt @@ -11,7 +11,9 @@ with the difference that the orphan objects are not freed but only reported via /sys/kernel/debug/kmemleak. A similar method is used by the Valgrind tool (memcheck --leak-check) to detect the memory leaks in user-space applications. -Kmemleak is supported on x86, arm, powerpc, sparc, sh, microblaze and tile. + +Please check DEBUG_KMEMLEAK dependencies in lib/Kconfig.debug for supported +architectures. Usage ----- diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt index 1b5a5dd..5df176e 100644 --- a/Documentation/printk-formats.txt +++ b/Documentation/printk-formats.txt @@ -9,7 +9,121 @@ If variable is of Type, use printk format specifier: size_t %zu or %zx ssize_t %zd or %zx -Raw pointer value SHOULD be printed with %p. +Raw pointer value SHOULD be printed with %p. The kernel supports +the following extended format specifiers for pointer types: + +Symbols/Function Pointers: + + %pF versatile_init+0x0/0x110 + %pf versatile_init + %pS versatile_init+0x0/0x110 + %ps versatile_init + %pB prev_fn_of_versatile_init+0x88/0x88 + + For printing symbols and function pointers. The 'S' and 's' specifiers + result in the symbol name with ('S') or without ('s') offsets. Where + this is used on a kernel without KALLSYMS - the symbol address is + printed instead. + + The 'B' specifier results in the symbol name with offsets and should be + used when printing stack backtraces. The specifier takes into + consideration the effect of compiler optimisations which may occur + when tail-call's are used and marked with the noreturn GCC attribute. + + On ia64, ppc64 and parisc64 architectures function pointers are + actually function descriptors which must first be resolved. The 'F' and + 'f' specifiers perform this resolution and then provide the same + functionality as the 'S' and 's' specifiers. + +Kernel Pointers: + + %pK 0x01234567 or 0x0123456789abcdef + + For printing kernel pointers which should be hidden from unprivileged + users. The behaviour of %pK depends on the kptr_restrict sysctl - see + Documentation/sysctl/kernel.txt for more details. + +Struct Resources: + + %pr [mem 0x60000000-0x6fffffff flags 0x2200] or + [mem 0x0000000060000000-0x000000006fffffff flags 0x2200] + %pR [mem 0x60000000-0x6fffffff pref] or + [mem 0x0000000060000000-0x000000006fffffff pref] + + For printing struct resources. The 'R' and 'r' specifiers result in a + printed resource with ('R') or without ('r') a decoded flags member. + +MAC/FDDI addresses: + + %pM 00:01:02:03:04:05 + %pMF 00-01-02-03-04-05 + %pm 000102030405 + + For printing 6-byte MAC/FDDI addresses in hex notation. The 'M' and 'm' + specifiers result in a printed address with ('M') or without ('m') byte + separators. The default byte separator is the colon (':'). + + Where FDDI addresses are concerned the 'F' specifier can be used after + the 'M' specifier to use dash ('-') separators instead of the default + separator. + +IPv4 addresses: + + %pI4 1.2.3.4 + %pi4 001.002.003.004 + %p[Ii][hnbl] + + For printing IPv4 dot-separated decimal addresses. The 'I4' and 'i4' + specifiers result in a printed address with ('i4') or without ('I4') + leading zeros. + + The additional 'h', 'n', 'b', and 'l' specifiers are used to specify + host, network, big or little endian order addresses respectively. Where + no specifier is provided the default network/big endian order is used. + +IPv6 addresses: + + %pI6 0001:0002:0003:0004:0005:0006:0007:0008 + %pi6 00010002000300040005000600070008 + %pI6c 1:2:3:4:5:6:7:8 + + For printing IPv6 network-order 16-bit hex addresses. The 'I6' and 'i6' + specifiers result in a printed address with ('I6') or without ('i6') + colon-separators. Leading zeros are always used. + + The additional 'c' specifier can be used with the 'I' specifier to + print a compressed IPv6 address as described by + http://tools.ietf.org/html/rfc5952 + +UUID/GUID addresses: + + %pUb 00010203-0405-0607-0809-0a0b0c0d0e0f + %pUB 00010203-0405-0607-0809-0A0B0C0D0E0F + %pUl 03020100-0504-0706-0809-0a0b0c0e0e0f + %pUL 03020100-0504-0706-0809-0A0B0C0E0E0F + + For printing 16-byte UUID/GUIDs addresses. The additional 'l', 'L', + 'b' and 'B' specifiers are used to specify a little endian order in + lower ('l') or upper case ('L') hex characters - and big endian order + in lower ('b') or upper case ('B') hex characters. + + Where no additional specifiers are used the default little endian + order with lower case hex characters will be printed. + +struct va_format: + + %pV + + For printing struct va_format structures. These contain a format string + and va_list as follows: + + struct va_format { + const char *fmt; + va_list *va; + }; + + Do not use this feature without some mechanism to verify the + correctness of the format string and va_list arguments. u64 SHOULD be printed with %llu/%llx, (unsigned long long): @@ -32,4 +146,5 @@ Reminder: sizeof() result is of type size_t. Thank you for your cooperation and attention. -By Randy Dunlap <rdunlap@xenotime.net> +By Randy Dunlap <rdunlap@xenotime.net> and +Andrew Murray <amurray@mpc-data.co.uk> diff --git a/Documentation/scheduler/sched-design-CFS.txt b/Documentation/scheduler/sched-design-CFS.txt index 9996199..91ecff0 100644 --- a/Documentation/scheduler/sched-design-CFS.txt +++ b/Documentation/scheduler/sched-design-CFS.txt @@ -223,9 +223,10 @@ When CONFIG_FAIR_GROUP_SCHED is defined, a "cpu.shares" file is created for each group created using the pseudo filesystem. See example steps below to create task groups and modify their CPU share using the "cgroups" pseudo filesystem. - # mkdir /dev/cpuctl - # mount -t cgroup -ocpu none /dev/cpuctl - # cd /dev/cpuctl + # mount -t tmpfs cgroup_root /sys/fs/cgroup + # mkdir /sys/fs/cgroup/cpu + # mount -t cgroup -ocpu none /sys/fs/cgroup/cpu + # cd /sys/fs/cgroup/cpu # mkdir multimedia # create "multimedia" group of tasks # mkdir browser # create "browser" group of tasks diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt index 605b0d4..71b54d5 100644 --- a/Documentation/scheduler/sched-rt-group.txt +++ b/Documentation/scheduler/sched-rt-group.txt @@ -129,9 +129,8 @@ priority! Enabling CONFIG_RT_GROUP_SCHED lets you explicitly allocate real CPU bandwidth to task groups. -This uses the /cgroup virtual file system and -"/cgroup/<cgroup>/cpu.rt_runtime_us" to control the CPU time reserved for each -control group. +This uses the cgroup virtual file system and "<cgroup>/cpu.rt_runtime_us" +to control the CPU time reserved for each control group. For more information on working with control groups, you should read Documentation/cgroups/cgroups.txt as well. @@ -150,7 +149,7 @@ For now, this can be simplified to just the following (but see Future plans): =============== There is work in progress to make the scheduling period for each group -("/cgroup/<cgroup>/cpu.rt_period_us") configurable as well. +("<cgroup>/cpu.rt_period_us") configurable as well. The constraint on the period is that a subgroup must have a smaller or equal period to its parent. But realistically its not very useful _yet_ diff --git a/Documentation/vm/hwpoison.txt b/Documentation/vm/hwpoison.txt index 12f9ba2..5500684 100644 --- a/Documentation/vm/hwpoison.txt +++ b/Documentation/vm/hwpoison.txt @@ -129,12 +129,12 @@ Limit injection to pages owned by memgroup. Specified by inode number of the memcg. Example: - mkdir /cgroup/hwpoison + mkdir /sys/fs/cgroup/mem/hwpoison usemem -m 100 -s 1000 & - echo `jobs -p` > /cgroup/hwpoison/tasks + echo `jobs -p` > /sys/fs/cgroup/mem/hwpoison/tasks - memcg_ino=$(ls -id /cgroup/hwpoison | cut -f1 -d' ') + memcg_ino=$(ls -id /sys/fs/cgroup/mem/hwpoison | cut -f1 -d' ') echo $memcg_ino > /debug/hwpoison/corrupt-filter-memcg page-types -p `pidof init` --hwpoison # shall do nothing diff --git a/MAINTAINERS b/MAINTAINERS index 2cc3a94..6c59eb9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3819,6 +3819,12 @@ S: Maintained F: drivers/leds/ F: include/linux/leds.h +LEGACY EEPROM DRIVER +M: Jean Delvare <khali@linux-fr.org> +S: Maintained +F: Documentation/misc-devices/eeprom +F: drivers/misc/eeprom/eeprom.c + LEGO USB Tower driver M: Juergen Stuber <starblue@users.sourceforge.net> L: legousb-devel@lists.sourceforge.net @@ -4144,7 +4150,7 @@ F: include/linux/mm.h F: mm/ MEMORY RESOURCE CONTROLLER -M: Balbir Singh <balbir@linux.vnet.ibm.com> +M: Balbir Singh <bsingharora@gmail.com> M: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> M: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> L: linux-mm@kvack.org @@ -4889,7 +4895,7 @@ F: mm/percpu*.c F: arch/*/include/asm/percpu.h PER-TASK DELAY ACCOUNTING -M: Balbir Singh <balbir@linux.vnet.ibm.com> +M: Balbir Singh <bsingharora@gmail.com> S: Maintained F: include/linux/delayacct.h F: kernel/delayacct.c @@ -6097,7 +6103,7 @@ F: include/target/ F: Documentation/target/ TASKSTATS STATISTICS INTERFACE -M: Balbir Singh <balbir@linux.vnet.ibm.com> +M: Balbir Singh <bsingharora@gmail.com> S: Maintained F: Documentation/accounting/taskstats* F: include/linux/taskstats* @@ -6716,6 +6722,14 @@ S: Maintained F: Documentation/filesystems/vfat.txt F: fs/fat/ +VIDEOBUF2 FRAMEWORK +M: Pawel Osciak <pawel@osciak.com> +M: Marek Szyprowski <m.szyprowski@samsung.com> +L: linux-media@vger.kernel.org +S: Maintained +F: drivers/media/video/videobuf2-* +F: include/media/videobuf2-* + VIRTIO CONSOLE DRIVER M: Amit Shah <amit.shah@redhat.com> L: virtualization@lists.linux-foundation.org diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 376f221..326f0a2 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -409,7 +409,7 @@ SYSCALL_DEFINE2(osf_getdomainname, char __user *, name, int, namelen) return -EFAULT; len = namelen; - if (namelen > 32) + if (len > 32) len = 32; down_read(&uts_sem); @@ -594,7 +594,7 @@ SYSCALL_DEFINE3(osf_sysinfo, int, command, char __user *, buf, long, count) down_read(&uts_sem); res = sysinfo_table[offset]; len = strlen(res)+1; - if (len > count) + if ((unsigned long)len > (unsigned long)count) len = count; if (copy_to_user(buf, res, len)) err = -EFAULT; @@ -649,7 +649,7 @@ SYSCALL_DEFINE5(osf_getsysinfo, unsigned long, op, void __user *, buffer, return 1; case GSI_GET_HWRPB: - if (nbytes < sizeof(*hwrpb)) + if (nbytes > sizeof(*hwrpb)) return -EINVAL; if (copy_to_user(buffer, hwrpb, nbytes) != 0) return -EFAULT; @@ -1008,6 +1008,7 @@ SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options, { struct rusage r; long ret, err; + unsigned int status = 0; mm_segment_t old_fs; if (!ur) @@ -1016,13 +1017,15 @@ SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options, old_fs = get_fs(); set_fs (KERNEL_DS); - ret = sys_wait4(pid, ustatus, options, (struct rusage __user *) &r); + ret = sys_wait4(pid, (unsigned int __user *) &status, options, + (struct rusage __user *) &r); set_fs (old_fs); if (!access_ok(VERIFY_WRITE, ur, sizeof(*ur))) return -EFAULT; err = 0; + err |= put_user(status, ustatus); err |= __put_user(r.ru_utime.tv_sec, &ur->ru_utime.tv_sec); err |= __put_user(r.ru_utime.tv_usec, &ur->ru_utime.tv_usec); err |= __put_user(r.ru_stime.tv_sec, &ur->ru_stime.tv_sec); diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index f9da419..942fad9 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -691,9 +691,9 @@ proc_types: .word 0x41069260 @ ARM926EJ-S (v5TEJ) .word 0xff0ffff0 - b __arm926ejs_mmu_cache_on - b __armv4_mmu_cache_off - b __armv5tej_mmu_cache_flush + W(b) __arm926ejs_mmu_cache_on + W(b) __armv4_mmu_cache_off + W(b) __armv5tej_mmu_cache_flush .word 0x00007000 @ ARM7 IDs .word 0x0000f000 diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig index 889922a..67b5abb6 100644 --- a/arch/arm/configs/davinci_all_defconfig +++ b/arch/arm/configs/davinci_all_defconfig @@ -157,7 +157,7 @@ CONFIG_LEDS_GPIO=m CONFIG_LEDS_TRIGGERS=y CONFIG_LEDS_TRIGGER_TIMER=m CONFIG_LEDS_TRIGGER_HEARTBEAT=m -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y CONFIG_XFS_FS=m diff --git a/arch/arm/configs/netx_defconfig b/arch/arm/configs/netx_defconfig index 316af54..9c0ad79 100644 --- a/arch/arm/configs/netx_defconfig +++ b/arch/arm/configs/netx_defconfig @@ -60,7 +60,7 @@ CONFIG_FB_ARMCLCD=y # CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_INOTIFY=y CONFIG_TMPFS=y CONFIG_JFFS2_FS=y diff --git a/arch/arm/configs/viper_defconfig b/arch/arm/configs/viper_defconfig index 8b0c717..1d01ddd 100644 --- a/arch/arm/configs/viper_defconfig +++ b/arch/arm/configs/viper_defconfig @@ -142,7 +142,7 @@ CONFIG_USB_GADGETFS=m CONFIG_USB_FILE_STORAGE=m CONFIG_USB_G_SERIAL=m CONFIG_USB_G_PRINTER=m -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_DS1307=m CONFIG_RTC_DRV_SA1100=m CONFIG_EXT2_FS=m diff --git a/arch/arm/configs/xcep_defconfig b/arch/arm/configs/xcep_defconfig index 5b55041..721832f 100644 --- a/arch/arm/configs/xcep_defconfig +++ b/arch/arm/configs/xcep_defconfig @@ -73,7 +73,7 @@ CONFIG_SENSORS_MAX6650=m # CONFIG_VGA_CONSOLE is not set # CONFIG_HID_SUPPORT is not set # CONFIG_USB_SUPPORT is not set -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_SA1100=m CONFIG_DMADEVICES=y # CONFIG_DNOTIFY is not set diff --git a/arch/arm/configs/zeus_defconfig b/arch/arm/configs/zeus_defconfig index 960f655..59577ad 100644 --- a/arch/arm/configs/zeus_defconfig +++ b/arch/arm/configs/zeus_defconfig @@ -158,7 +158,7 @@ CONFIG_LEDS_TRIGGER_HEARTBEAT=m CONFIG_LEDS_TRIGGER_BACKLIGHT=m CONFIG_LEDS_TRIGGER_GPIO=m CONFIG_LEDS_TRIGGER_DEFAULT_ON=m -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_ISL1208=m CONFIG_RTC_DRV_PXA=m CONFIG_EXT2_FS=y diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c index a701e42..0cdd7b4 100644 --- a/arch/arm/kernel/devtree.c +++ b/arch/arm/kernel/devtree.c @@ -76,6 +76,9 @@ struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys) unsigned long dt_root; const char *model; + if (!dt_phys) + return NULL; + devtree = phys_to_virt(dt_phys); /* check device tree validity */ diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index e8d8856..90c62cd 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -435,6 +435,10 @@ __irq_usr: usr_entry kuser_cmpxchg_check +#ifdef CONFIG_IRQSOFF_TRACER + bl trace_hardirqs_off +#endif + get_thread_info tsk #ifdef CONFIG_PREEMPT ldr r8, [tsk, #TI_PREEMPT] @ get preempt count @@ -453,7 +457,7 @@ __irq_usr: #endif mov why, #0 - b ret_to_user + b ret_to_user_from_irq UNWIND(.fnend ) ENDPROC(__irq_usr) diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 1e7b04a..b2a27b6 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -64,6 +64,7 @@ work_resched: ENTRY(ret_to_user) ret_slow_syscall: disable_irq @ disable interrupts +ENTRY(ret_to_user_from_irq) ldr r1, [tsk, #TI_FLAGS] tst r1, #_TIF_WORK_MASK bne work_pending @@ -75,6 +76,7 @@ no_work_pending: arch_ret_to_user r1, lr restore_user_regs fast = 0, offset = 0 +ENDPROC(ret_to_user_from_irq) ENDPROC(ret_to_user) /* diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index d52eec2..6807cb1 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -139,7 +139,7 @@ static void dump_instr(const char *lvl, struct pt_regs *regs) fs = get_fs(); set_fs(KERNEL_DS); - for (i = -4; i < 1; i++) { + for (i = -4; i < 1 + !!thumb; i++) { unsigned int val, bad; if (thumb) @@ -563,7 +563,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs) if (!pmd_present(*pmd)) goto bad_access; pte = pte_offset_map_lock(mm, pmd, addr, &ptl); - if (!pte_present(*pte) || !pte_dirty(*pte)) { + if (!pte_present(*pte) || !pte_write(*pte) || !pte_dirty(*pte)) { pte_unmap_unlock(pte, ptl); goto bad_access; } diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c index 4e66881..fc4e98e 100644 --- a/arch/arm/mach-davinci/devices-da8xx.c +++ b/arch/arm/mach-davinci/devices-da8xx.c @@ -494,7 +494,7 @@ static struct platform_device da850_mcasp_device = { .resource = da850_mcasp_resources, }; -struct platform_device davinci_pcm_device = { +static struct platform_device davinci_pcm_device = { .name = "davinci-pcm-audio", .id = -1, }; diff --git a/arch/arm/mach-davinci/devices.c b/arch/arm/mach-davinci/devices.c index 8f4f736..806a2f0 100644 --- a/arch/arm/mach-davinci/devices.c +++ b/arch/arm/mach-davinci/devices.c @@ -298,7 +298,7 @@ static void davinci_init_wdt(void) /*-------------------------------------------------------------------------*/ -struct platform_device davinci_pcm_device = { +static struct platform_device davinci_pcm_device = { .name = "davinci-pcm-audio", .id = -1, }; diff --git a/arch/arm/mach-davinci/gpio.c b/arch/arm/mach-davinci/gpio.c index a0b8388..e722139 100644 --- a/arch/arm/mach-davinci/gpio.c +++ b/arch/arm/mach-davinci/gpio.c @@ -252,9 +252,11 @@ static struct irq_chip gpio_irqchip = { static void gpio_irq_handler(unsigned irq, struct irq_desc *desc) { - struct davinci_gpio_regs __iomem *g = irq2regs(irq); + struct davinci_gpio_regs __iomem *g; u32 mask = 0xffff; + g = (__force struct davinci_gpio_regs __iomem *) irq_desc_get_handler_data(desc); + /* we only care about one bank */ if (irq & 1) mask <<= 16; @@ -422,8 +424,7 @@ static int __init davinci_gpio_irq_setup(void) /* set up all irqs in this bank */ irq_set_chained_handler(bank_irq, gpio_irq_handler); - irq_set_chip_data(bank_irq, (__force void *)g); - irq_set_handler_data(bank_irq, (void *)irq); + irq_set_handler_data(bank_irq, (__force void *)g); for (i = 0; i < 16 && gpio < ngpio; i++, irq++, gpio++) { irq_set_chip(irq, &gpio_irqchip); diff --git a/arch/arm/mach-footbridge/dc21285-timer.c b/arch/arm/mach-footbridge/dc21285-timer.c index 5f1f986..121ad1d 100644 --- a/arch/arm/mach-footbridge/dc21285-timer.c +++ b/arch/arm/mach-footbridge/dc21285-timer.c @@ -103,6 +103,7 @@ static void __init footbridge_timer_init(void) clockevents_calc_mult_shift(ce, mem_fclk_21285, 5); ce->max_delta_ns = clockevent_delta2ns(0xffffff, ce); ce->min_delta_ns = clockevent_delta2ns(0x000004, ce); + ce->cpumask = cpumask_of(smp_processor_id()); clockevents_register_device(ce); } diff --git a/arch/arm/mach-footbridge/include/mach/debug-macro.S b/arch/arm/mach-footbridge/include/mach/debug-macro.S index 30b971d..1be2eeb 100644 --- a/arch/arm/mach-footbridge/include/mach/debug-macro.S +++ b/arch/arm/mach-footbridge/include/mach/debug-macro.S @@ -26,6 +26,7 @@ #include <asm/hardware/debug-8250.S> #else +#include <mach/hardware.h> /* For EBSA285 debugging */ .equ dc21285_high, ARMCSR_BASE & 0xff000000 .equ dc21285_low, ARMCSR_BASE & 0x00ffffff @@ -36,8 +37,8 @@ .else mov \rp, #0 .endif - orr \rv, \rp, #0x42000000 - orr \rp, \rp, #dc21285_high + orr \rv, \rp, #dc21285_high + orr \rp, \rp, #0x42000000 .endm .macro senduart,rd,rx diff --git a/arch/arm/mach-mxs/ocotp.c b/arch/arm/mach-mxs/ocotp.c index 65157a3..54add60 100644 --- a/arch/arm/mach-mxs/ocotp.c +++ b/arch/arm/mach-mxs/ocotp.c @@ -16,6 +16,8 @@ #include <linux/err.h> #include <linux/mutex.h> +#include <asm/processor.h> /* for cpu_relax() */ + #include <mach/mxs.h> #define OCOTP_WORD_OFFSET 0x20 diff --git a/arch/arm/mach-u300/clock.h b/arch/arm/mach-u300/clock.h index c34f3ea..4f50ca8 100644 --- a/arch/arm/mach-u300/clock.h +++ b/arch/arm/mach-u300/clock.h @@ -31,7 +31,7 @@ struct clk { bool reset; __u16 clk_val; __s8 usecount; - __u32 res_reg; + void __iomem * res_reg; __u16 res_mask; bool hw_ctrld; diff --git a/arch/arm/mach-u300/include/mach/u300-regs.h b/arch/arm/mach-u300/include/mach/u300-regs.h index 8b85df4..035fdc9 100644 --- a/arch/arm/mach-u300/include/mach/u300-regs.h +++ b/arch/arm/mach-u300/include/mach/u300-regs.h @@ -18,6 +18,12 @@ * the defines are used for setting up the I/O memory mapping. */ +#ifdef __ASSEMBLER__ +#define IOMEM(a) (a) +#else +#define IOMEM(a) (void __iomem *) a +#endif + /* NAND Flash CS0 */ #define U300_NAND_CS0_PHYS_BASE 0x80000000 @@ -48,13 +54,6 @@ #endif /* - * All the following peripherals are specified at their PHYSICAL address, - * so if you need to access them (in the kernel), you MUST use the macros - * defined in <asm/io.h> to map to the IO_ADDRESS_AHB() IO_ADDRESS_FAST() - * etc. - */ - -/* * AHB peripherals */ @@ -63,11 +62,11 @@ /* Vectored Interrupt Controller 0, servicing 32 interrupts */ #define U300_INTCON0_BASE (U300_AHB_PER_PHYS_BASE+0x1000) -#define U300_INTCON0_VBASE (U300_AHB_PER_VIRT_BASE+0x1000) +#define U300_INTCON0_VBASE IOMEM(U300_AHB_PER_VIRT_BASE+0x1000) /* Vectored Interrupt Controller 1, servicing 32 interrupts */ #define U300_INTCON1_BASE (U300_AHB_PER_PHYS_BASE+0x2000) -#define U300_INTCON1_VBASE (U300_AHB_PER_VIRT_BASE+0x2000) +#define U300_INTCON1_VBASE IOMEM(U300_AHB_PER_VIRT_BASE+0x2000) /* Memory Stick Pro (MSPRO) controller */ #define U300_MSPRO_BASE (U300_AHB_PER_PHYS_BASE+0x3000) @@ -115,7 +114,7 @@ /* SYSCON */ #define U300_SYSCON_BASE (U300_SLOW_PER_PHYS_BASE+0x1000) -#define U300_SYSCON_VBASE (U300_SLOW_PER_VIRT_BASE+0x1000) +#define U300_SYSCON_VBASE IOMEM(U300_SLOW_PER_VIRT_BASE+0x1000) /* Watchdog */ #define U300_WDOG_BASE (U300_SLOW_PER_PHYS_BASE+0x2000) @@ -125,7 +124,7 @@ /* APP side special timer */ #define U300_TIMER_APP_BASE (U300_SLOW_PER_PHYS_BASE+0x4000) -#define U300_TIMER_APP_VBASE (U300_SLOW_PER_VIRT_BASE+0x4000) +#define U300_TIMER_APP_VBASE IOMEM(U300_SLOW_PER_VIRT_BASE+0x4000) /* Keypad */ #define U300_KEYPAD_BASE (U300_SLOW_PER_PHYS_BASE+0x5000) @@ -181,5 +180,4 @@ * Virtual accessor macros for static devices */ - #endif diff --git a/arch/arm/mach-u300/timer.c b/arch/arm/mach-u300/timer.c index 891cf44..18d7fa0 100644 --- a/arch/arm/mach-u300/timer.c +++ b/arch/arm/mach-u300/timer.c @@ -411,8 +411,7 @@ static void __init u300_timer_init(void) /* Use general purpose timer 2 as clock source */ if (clocksource_mmio_init(U300_TIMER_APP_VBASE + U300_TIMER_APP_GPT2CC, "GPT2", rate, 300, 32, clocksource_mmio_readl_up)) - printk(KERN_ERR "timer: failed to initialize clock " - "source %s\n", clocksource_u300_1mhz.name); + pr_err("timer: failed to initialize U300 clock source\n"); clockevents_calc_mult_shift(&clockevent_u300_1mhz, rate, APPTIMER_MIN_RANGE); diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c index 285edcd..9e6b93b 100644 --- a/arch/arm/mach-vexpress/v2m.c +++ b/arch/arm/mach-vexpress/v2m.c @@ -46,12 +46,6 @@ static struct map_desc v2m_io_desc[] __initdata = { }, }; -static void __init v2m_init_early(void) -{ - ct_desc->init_early(); - versatile_sched_clock_init(MMIO_P2V(V2M_SYS_24MHZ), 24000000); -} - static void __init v2m_timer_init(void) { u32 scctrl; @@ -365,6 +359,13 @@ static struct clk_lookup v2m_lookups[] = { }, }; +static void __init v2m_init_early(void) +{ + ct_desc->init_early(); + clkdev_add_table(v2m_lookups, ARRAY_SIZE(v2m_lookups)); + versatile_sched_clock_init(MMIO_P2V(V2M_SYS_24MHZ), 24000000); +} + static void v2m_power_off(void) { if (v2m_cfg_write(SYS_CFG_SHUTDOWN | SYS_CFG_SITE_MB, 0)) @@ -418,8 +419,6 @@ static void __init v2m_init(void) { int i; - clkdev_add_table(v2m_lookups, ARRAY_SIZE(v2m_lookups)); - platform_device_register(&v2m_pcie_i2c_device); platform_device_register(&v2m_ddc_i2c_device); platform_device_register(&v2m_flash_device); diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index 8bfae96..b0ee9ba 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -24,7 +24,9 @@ DEFINE_PER_CPU(struct mm_struct *, current_mm); /* * We fork()ed a process, and we need a new context for the child - * to run in. + * to run in. We reserve version 0 for initial tasks so we will + * always allocate an ASID. The ASID 0 is reserved for the TTBR + * register changing sequence. */ void __init_new_context(struct task_struct *tsk, struct mm_struct *mm) { @@ -34,11 +36,8 @@ void __init_new_context(struct task_struct *tsk, struct mm_struct *mm) static void flush_context(void) { - u32 ttb; - /* Copy TTBR1 into TTBR0 */ - asm volatile("mrc p15, 0, %0, c2, c0, 1\n" - "mcr p15, 0, %0, c2, c0, 0" - : "=r" (ttb)); + /* set the reserved ASID before flushing the TLB */ + asm("mcr p15, 0, %0, c13, c0, 1\n" : : "r" (0)); isb(); local_flush_tlb_all(); if (icache_is_vivt_asid_tagged()) { @@ -94,7 +93,7 @@ static void reset_context(void *info) return; smp_rmb(); - asid = cpu_last_asid + cpu; + asid = cpu_last_asid + cpu + 1; flush_context(); set_mm_context(mm, asid); @@ -144,13 +143,13 @@ void __new_context(struct mm_struct *mm) * to start a new version and flush the TLB. */ if (unlikely((asid & ~ASID_MASK) == 0)) { - asid = cpu_last_asid + smp_processor_id(); + asid = cpu_last_asid + smp_processor_id() + 1; flush_context(); #ifdef CONFIG_SMP smp_wmb(); smp_call_function(reset_context, NULL, 1); #endif - cpu_last_asid += NR_CPUS - 1; + cpu_last_asid += NR_CPUS; } set_mm_context(mm, asid); diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 2c2cce9..c19571c 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -331,6 +331,12 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc) #endif #ifdef CONFIG_BLK_DEV_INITRD if (phys_initrd_size && + !memblock_is_region_memory(phys_initrd_start, phys_initrd_size)) { + pr_err("INITRD: 0x%08lx+0x%08lx is not a memory region - disabling initrd\n", + phys_initrd_start, phys_initrd_size); + phys_initrd_start = phys_initrd_size = 0; + } + if (phys_initrd_size && memblock_is_region_reserved(phys_initrd_start, phys_initrd_size)) { pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region - disabling initrd\n", phys_initrd_start, phys_initrd_size); @@ -635,7 +641,8 @@ void __init mem_init(void) " modules : 0x%08lx - 0x%08lx (%4ld MB)\n" " .init : 0x%p" " - 0x%p" " (%4d kB)\n" " .text : 0x%p" " - 0x%p" " (%4d kB)\n" - " .data : 0x%p" " - 0x%p" " (%4d kB)\n", + " .data : 0x%p" " - 0x%p" " (%4d kB)\n" + " .bss : 0x%p" " - 0x%p" " (%4d kB)\n", MLK(UL(CONFIG_VECTORS_BASE), UL(CONFIG_VECTORS_BASE) + (PAGE_SIZE)), @@ -657,7 +664,8 @@ void __init mem_init(void) MLK_ROUNDUP(__init_begin, __init_end), MLK_ROUNDUP(_text, _etext), - MLK_ROUNDUP(_sdata, _edata)); + MLK_ROUNDUP(_sdata, _edata), + MLK_ROUNDUP(__bss_start, __bss_stop)); #undef MLK #undef MLM diff --git a/arch/arm/mm/proc-arm7tdmi.S b/arch/arm/mm/proc-arm7tdmi.S index e4c165c..537ffcb 100644 --- a/arch/arm/mm/proc-arm7tdmi.S +++ b/arch/arm/mm/proc-arm7tdmi.S @@ -146,7 +146,7 @@ __arm7tdmi_proc_info: .long 0 .long 0 .long v4_cache_fns - .size __arm7tdmi_proc_info, . - __arm7dmi_proc_info + .size __arm7tdmi_proc_info, . - __arm7tdmi_proc_info .type __triscenda7_proc_info, #object __triscenda7_proc_info: diff --git a/arch/arm/mm/proc-arm9tdmi.S b/arch/arm/mm/proc-arm9tdmi.S index 7b7ebd4..546b54d 100644 --- a/arch/arm/mm/proc-arm9tdmi.S +++ b/arch/arm/mm/proc-arm9tdmi.S @@ -116,7 +116,7 @@ __arm9tdmi_proc_info: .long 0 .long 0 .long v4_cache_fns - .size __arm9tdmi_proc_info, . - __arm9dmi_proc_info + .size __arm9tdmi_proc_info, . - __arm9tdmi_proc_info .type __p2001_proc_info, #object __p2001_proc_info: diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index b3b566e..3c38678 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -108,16 +108,18 @@ ENTRY(cpu_v7_switch_mm) #ifdef CONFIG_ARM_ERRATA_430973 mcr p15, 0, r2, c7, c5, 6 @ flush BTAC/BTB #endif - mrc p15, 0, r2, c2, c0, 1 @ load TTB 1 - mcr p15, 0, r2, c2, c0, 0 @ into TTB 0 +#ifdef CONFIG_ARM_ERRATA_754322 + dsb +#endif + mcr p15, 0, r2, c13, c0, 1 @ set reserved context ID + isb +1: mcr p15, 0, r0, c2, c0, 0 @ set TTB 0 isb #ifdef CONFIG_ARM_ERRATA_754322 dsb #endif mcr p15, 0, r1, c13, c0, 1 @ set context ID isb - mcr p15, 0, r0, c2, c0, 0 @ set TTB 0 - isb #endif mov pc, lr ENDPROC(cpu_v7_switch_mm) diff --git a/arch/arm/plat-mxc/devices/platform-imx-dma.c b/arch/arm/plat-mxc/devices/platform-imx-dma.c index 3538b85e..b130f60 100644 --- a/arch/arm/plat-mxc/devices/platform-imx-dma.c +++ b/arch/arm/plat-mxc/devices/platform-imx-dma.c @@ -139,7 +139,7 @@ static struct sdma_script_start_addrs addr_imx35_to2 = { #endif #ifdef CONFIG_SOC_IMX51 -static struct sdma_script_start_addrs addr_imx51_to1 = { +static struct sdma_script_start_addrs addr_imx51 = { .ap_2_ap_addr = 642, .uart_2_mcu_addr = 817, .mcu_2_app_addr = 747, @@ -196,7 +196,9 @@ static int __init imxXX_add_imx_dma(void) #if defined(CONFIG_SOC_IMX51) if (cpu_is_mx51()) { - imx51_imx_sdma_data.pdata.script_addrs = &addr_imx51_to1; + int to_version = mx51_revision() >> 4; + imx51_imx_sdma_data.pdata.to_version = to_version; + imx51_imx_sdma_data.pdata.script_addrs = &addr_imx51; ret = imx_add_imx_sdma(&imx51_imx_sdma_data); } else #endif diff --git a/arch/avr32/configs/atngw100_mrmt_defconfig b/arch/avr32/configs/atngw100_mrmt_defconfig index 6cb786c..77ca4f9 100644 --- a/arch/avr32/configs/atngw100_mrmt_defconfig +++ b/arch/avr32/configs/atngw100_mrmt_defconfig @@ -110,7 +110,7 @@ CONFIG_LEDS_GPIO=y CONFIG_LEDS_TRIGGERS=y CONFIG_LEDS_TRIGGER_TIMER=y CONFIG_LEDS_TRIGGER_HEARTBEAT=y -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_S35390A=m CONFIG_RTC_DRV_AT32AP700X=m CONFIG_DMADEVICES=y diff --git a/arch/blackfin/configs/CM-BF548_defconfig b/arch/blackfin/configs/CM-BF548_defconfig index 31d9542..9f1d084 100644 --- a/arch/blackfin/configs/CM-BF548_defconfig +++ b/arch/blackfin/configs/CM-BF548_defconfig @@ -112,7 +112,7 @@ CONFIG_USB_G_SERIAL=m CONFIG_USB_G_PRINTER=m CONFIG_MMC=m CONFIG_SDH_BFIN=m -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_BFIN=m CONFIG_EXT2_FS=m # CONFIG_DNOTIFY is not set diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig index 37862b2..807c97e 100644 --- a/arch/mips/configs/mtx1_defconfig +++ b/arch/mips/configs/mtx1_defconfig @@ -678,7 +678,7 @@ CONFIG_LEDS_TRIGGERS=y CONFIG_LEDS_TRIGGER_TIMER=y CONFIG_LEDS_TRIGGER_HEARTBEAT=y CONFIG_LEDS_TRIGGER_DEFAULT_ON=y -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_INTF_DEV_UIE_EMUL=y CONFIG_RTC_DRV_TEST=m CONFIG_RTC_DRV_DS1307=m diff --git a/arch/powerpc/configs/52xx/pcm030_defconfig b/arch/powerpc/configs/52xx/pcm030_defconfig index 7f7e4a8..22e7195 100644 --- a/arch/powerpc/configs/52xx/pcm030_defconfig +++ b/arch/powerpc/configs/52xx/pcm030_defconfig @@ -85,7 +85,7 @@ CONFIG_USB_OHCI_HCD=m CONFIG_USB_OHCI_HCD_PPC_OF_BE=y # CONFIG_USB_OHCI_HCD_PCI is not set CONFIG_USB_STORAGE=m -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_PCF8563=m CONFIG_EXT2_FS=m CONFIG_EXT3_FS=m diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index 6472322..185c292 100644 --- a/arch/powerpc/configs/ps3_defconfig +++ b/arch/powerpc/configs/ps3_defconfig @@ -141,7 +141,7 @@ CONFIG_USB_EHCI_TT_NEWSCHED=y # CONFIG_USB_EHCI_HCD_PPC_OF is not set CONFIG_USB_OHCI_HCD=m CONFIG_USB_STORAGE=m -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_PS3=m CONFIG_EXT2_FS=m CONFIG_EXT3_FS=m diff --git a/arch/sh/configs/titan_defconfig b/arch/sh/configs/titan_defconfig index 0f55891..e2cbd92 100644 --- a/arch/sh/configs/titan_defconfig +++ b/arch/sh/configs/titan_defconfig @@ -227,7 +227,7 @@ CONFIG_USB_SERIAL=m CONFIG_USB_SERIAL_GENERIC=y CONFIG_USB_SERIAL_ARK3116=m CONFIG_USB_SERIAL_PL2303=m -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_SH=m CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index 051474c..34d6a1c 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -163,11 +163,32 @@ static irqreturn_t hpet_interrupt(int irq, void *data) * This has the effect of treating non-periodic like periodic. */ if ((devp->hd_flags & (HPET_IE | HPET_PERIODIC)) == HPET_IE) { - unsigned long m, t; + unsigned long m, t, mc, base, k; + struct hpet __iomem *hpet = devp->hd_hpet; + struct hpets *hpetp = devp->hd_hpets; t = devp->hd_ireqfreq; m = read_counter(&devp->hd_timer->hpet_compare); - write_counter(t + m, &devp->hd_timer->hpet_compare); + mc = read_counter(&hpet->hpet_mc); + /* The time for the next interrupt would logically be t + m, + * however, if we are very unlucky and the interrupt is delayed + * for longer than t then we will completely miss the next + * interrupt if we set t + m and an application will hang. + * Therefore we need to make a more complex computation assuming + * that there exists a k for which the following is true: + * k * t + base < mc + delta + * (k + 1) * t + base > mc + delta + * where t is the interval in hpet ticks for the given freq, + * base is the theoretical start value 0 < base < t, + * mc is the main counter value at the time of the interrupt, + * delta is the time it takes to write the a value to the + * comparator. + * k may then be computed as (mc - base + delta) / t . + */ + base = mc % t; + k = (mc - base + hpetp->hp_delta) / t; + write_counter(t * (k + 1) + base, + &devp->hd_timer->hpet_compare); } if (devp->hd_flags & HPET_SHARED_IRQ) diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index 23f0d5e..713d43b 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -1,3 +1,10 @@ +config LEDS_GPIO_REGISTER + bool + help + This option provides the function gpio_led_register_device. + As this function is used by arch code it must not be compiled as a + module. + menuconfig NEW_LEDS bool "LED Support" help @@ -7,22 +14,14 @@ menuconfig NEW_LEDS This is not related to standard keyboard LEDs which are controlled via the input system. +if NEW_LEDS + config LEDS_CLASS bool "LED Class Support" - depends on NEW_LEDS help This option enables the led sysfs class in /sys/class/leds. You'll need this to do anything useful with LEDs. If unsure, say N. -config LEDS_GPIO_REGISTER - bool - help - This option provides the function gpio_led_register_device. - As this function is used by arch code it must not be compiled as a - module. - -if NEW_LEDS - comment "LED drivers" config LEDS_88PM860X @@ -391,6 +390,7 @@ config LEDS_NETXBIG config LEDS_ASIC3 bool "LED support for the HTC ASIC3" + depends on LEDS_CLASS depends on MFD_ASIC3 default y help diff --git a/drivers/misc/apds990x.c b/drivers/misc/apds990x.c index 200311f..e2a52e5 100644 --- a/drivers/misc/apds990x.c +++ b/drivers/misc/apds990x.c @@ -609,6 +609,7 @@ static int apds990x_detect(struct apds990x_chip *chip) return ret; } +#if defined(CONFIG_PM) || defined(CONFIG_PM_RUNTIME) static int apds990x_chip_on(struct apds990x_chip *chip) { int err = regulator_bulk_enable(ARRAY_SIZE(chip->regs), @@ -624,6 +625,7 @@ static int apds990x_chip_on(struct apds990x_chip *chip) apds990x_mode_on(chip); return 0; } +#endif static int apds990x_chip_off(struct apds990x_chip *chip) { diff --git a/drivers/misc/cs5535-mfgpt.c b/drivers/misc/cs5535-mfgpt.c index e01e08c..bc685bf 100644 --- a/drivers/misc/cs5535-mfgpt.c +++ b/drivers/misc/cs5535-mfgpt.c @@ -174,7 +174,7 @@ struct cs5535_mfgpt_timer *cs5535_mfgpt_alloc_timer(int timer_nr, int domain) timer_nr = t < max ? (int) t : -1; } else { /* check if the requested timer's available */ - if (test_bit(timer_nr, mfgpt->avail)) + if (!test_bit(timer_nr, mfgpt->avail)) timer_nr = -1; } diff --git a/drivers/misc/spear13xx_pcie_gadget.c b/drivers/misc/spear13xx_pcie_gadget.c index 7aded90..cfbddbe 100644 --- a/drivers/misc/spear13xx_pcie_gadget.c +++ b/drivers/misc/spear13xx_pcie_gadget.c @@ -845,7 +845,7 @@ err_iounmap: err_iounmap_app: iounmap(config->va_app_base); err_kzalloc: - kfree(config); + kfree(target); err_rel_res: release_mem_region(res1->start, resource_size(res1)); err_rel_res0: diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index 5da5bea..7721de9 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -1144,9 +1144,17 @@ static int __devinit mmci_probe(struct amba_device *dev, else if (ret != -ENOSYS) goto err_gpio_cd; + /* + * A gpio pin that will detect cards when inserted and removed + * will most likely want to trigger on the edges if it is + * 0 when ejected and 1 when inserted (or mutatis mutandis + * for the inverted case) so we request triggers on both + * edges. + */ ret = request_any_context_irq(gpio_to_irq(plat->gpio_cd), - mmci_cd_irq, 0, - DRIVER_NAME " (cd)", host); + mmci_cd_irq, + IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING, + DRIVER_NAME " (cd)", host); if (ret >= 0) host->gpio_cd_irq = gpio_to_irq(plat->gpio_cd); } diff --git a/drivers/staging/iio/accel/adis16201.h b/drivers/staging/iio/accel/adis16201.h index 0b9b854..4cc1a5b 100644 --- a/drivers/staging/iio/accel/adis16201.h +++ b/drivers/staging/iio/accel/adis16201.h @@ -81,7 +81,6 @@ struct adis16201_state { int adis16201_set_irq(struct iio_dev *indio_dev, bool enable); -#ifdef CONFIG_IIO_RING_BUFFER enum adis16201_scan { ADIS16201_SCAN_SUPPLY, ADIS16201_SCAN_ACC_X, @@ -92,6 +91,7 @@ enum adis16201_scan { ADIS16201_SCAN_INCLI_Y, }; +#ifdef CONFIG_IIO_RING_BUFFER void adis16201_remove_trigger(struct iio_dev *indio_dev); int adis16201_probe_trigger(struct iio_dev *indio_dev); diff --git a/drivers/staging/iio/accel/adis16203.h b/drivers/staging/iio/accel/adis16203.h index 8bb8ce5..175e21b 100644 --- a/drivers/staging/iio/accel/adis16203.h +++ b/drivers/staging/iio/accel/adis16203.h @@ -76,7 +76,6 @@ struct adis16203_state { int adis16203_set_irq(struct iio_dev *indio_dev, bool enable); -#ifdef CONFIG_IIO_RING_BUFFER enum adis16203_scan { ADIS16203_SCAN_SUPPLY, ADIS16203_SCAN_AUX_ADC, @@ -85,6 +84,7 @@ enum adis16203_scan { ADIS16203_SCAN_INCLI_Y, }; +#ifdef CONFIG_IIO_RING_BUFFER void adis16203_remove_trigger(struct iio_dev *indio_dev); int adis16203_probe_trigger(struct iio_dev *indio_dev); diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c index f2cb750..4652109 100644 --- a/drivers/tty/serial/pch_uart.c +++ b/drivers/tty/serial/pch_uart.c @@ -1397,6 +1397,7 @@ static struct eg20t_port *pch_uart_init_port(struct pci_dev *pdev, int fifosize, base_baud; int port_type; struct pch_uart_driver_data *board; + const char *board_name; board = &drv_dat[id->driver_data]; port_type = board->port_type; @@ -1412,7 +1413,8 @@ static struct eg20t_port *pch_uart_init_port(struct pci_dev *pdev, base_baud = 1843200; /* 1.8432MHz */ /* quirk for CM-iTC board */ - if (strstr(dmi_get_system_info(DMI_BOARD_NAME), "CM-iTC")) + board_name = dmi_get_system_info(DMI_BOARD_NAME); + if (board_name && strstr(board_name, "CM-iTC")) base_baud = 192000000; /* 192.0MHz */ switch (port_type) { diff --git a/drivers/video/backlight/Kconfig b/drivers/video/backlight/Kconfig index 0c9373b..2d93c8d 100644 --- a/drivers/video/backlight/Kconfig +++ b/drivers/video/backlight/Kconfig @@ -302,6 +302,18 @@ config BACKLIGHT_ADP8860 To compile this driver as a module, choose M here: the module will be called adp8860_bl. +config BACKLIGHT_ADP8870 + tristate "Backlight Driver for ADP8870 using WLED" + depends on BACKLIGHT_CLASS_DEVICE && I2C + select NEW_LEDS + select LEDS_CLASS + help + If you have a LCD backlight connected to the ADP8870, + say Y here to enable this driver. + + To compile this driver as a module, choose M here: the module will + be called adp8870_bl. + config BACKLIGHT_88PM860X tristate "Backlight Driver for 88PM8606 using WLED" depends on MFD_88PM860X diff --git a/drivers/video/backlight/Makefile b/drivers/video/backlight/Makefile index b9ca849..ee72adb 100644 --- a/drivers/video/backlight/Makefile +++ b/drivers/video/backlight/Makefile @@ -34,6 +34,7 @@ obj-$(CONFIG_BACKLIGHT_WM831X) += wm831x_bl.o obj-$(CONFIG_BACKLIGHT_ADX) += adx_bl.o obj-$(CONFIG_BACKLIGHT_ADP5520) += adp5520_bl.o obj-$(CONFIG_BACKLIGHT_ADP8860) += adp8860_bl.o +obj-$(CONFIG_BACKLIGHT_ADP8870) += adp8870_bl.o obj-$(CONFIG_BACKLIGHT_88PM860X) += 88pm860x_bl.o obj-$(CONFIG_BACKLIGHT_PCF50633) += pcf50633-backlight.o diff --git a/drivers/video/backlight/adp8870_bl.c b/drivers/video/backlight/adp8870_bl.c new file mode 100644 index 0000000..05a8832 --- /dev/null +++ b/drivers/video/backlight/adp8870_bl.c @@ -0,0 +1,1012 @@ +/* + * Backlight driver for Analog Devices ADP8870 Backlight Devices + * + * Copyright 2009-2011 Analog Devices Inc. + * + * Licensed under the GPL-2 or later. + */ + +#include <linux/module.h> +#include <linux/version.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/pm.h> +#include <linux/platform_device.h> +#include <linux/i2c.h> +#include <linux/fb.h> +#include <linux/backlight.h> +#include <linux/leds.h> +#include <linux/workqueue.h> +#include <linux/slab.h> + +#include <linux/i2c/adp8870.h> +#define ADP8870_EXT_FEATURES +#define ADP8870_USE_LEDS + + +#define ADP8870_MFDVID 0x00 /* Manufacturer and device ID */ +#define ADP8870_MDCR 0x01 /* Device mode and status */ +#define ADP8870_INT_STAT 0x02 /* Interrupts status */ +#define ADP8870_INT_EN 0x03 /* Interrupts enable */ +#define ADP8870_CFGR 0x04 /* Configuration register */ +#define ADP8870_BLSEL 0x05 /* Sink enable backlight or independent */ +#define ADP8870_PWMLED 0x06 /* PWM Enable Selection Register */ +#define ADP8870_BLOFF 0x07 /* Backlight off timeout */ +#define ADP8870_BLDIM 0x08 /* Backlight dim timeout */ +#define ADP8870_BLFR 0x09 /* Backlight fade in and out rates */ +#define ADP8870_BLMX1 0x0A /* Backlight (Brightness Level 1-daylight) maximum current */ +#define ADP8870_BLDM1 0x0B /* Backlight (Brightness Level 1-daylight) dim current */ +#define ADP8870_BLMX2 0x0C /* Backlight (Brightness Level 2-bright) maximum current */ +#define ADP8870_BLDM2 0x0D /* Backlight (Brightness Level 2-bright) dim current */ +#define ADP8870_BLMX3 0x0E /* Backlight (Brightness Level 3-office) maximum current */ +#define ADP8870_BLDM3 0x0F /* Backlight (Brightness Level 3-office) dim current */ +#define ADP8870_BLMX4 0x10 /* Backlight (Brightness Level 4-indoor) maximum current */ +#define ADP8870_BLDM4 0x11 /* Backlight (Brightness Level 4-indoor) dim current */ +#define ADP8870_BLMX5 0x12 /* Backlight (Brightness Level 5-dark) maximum current */ +#define ADP8870_BLDM5 0x13 /* Backlight (Brightness Level 5-dark) dim current */ +#define ADP8870_ISCLAW 0x1A /* Independent sink current fade law register */ +#define ADP8870_ISCC 0x1B /* Independent sink current control register */ +#define ADP8870_ISCT1 0x1C /* Independent Sink Current Timer Register LED[7:5] */ +#define ADP8870_ISCT2 0x1D /* Independent Sink Current Timer Register LED[4:1] */ +#define ADP8870_ISCF 0x1E /* Independent sink current fade register */ +#define ADP8870_ISC1 0x1F /* Independent Sink Current LED1 */ +#define ADP8870_ISC2 0x20 /* Independent Sink Current LED2 */ +#define ADP8870_ISC3 0x21 /* Independent Sink Current LED3 */ +#define ADP8870_ISC4 0x22 /* Independent Sink Current LED4 */ +#define ADP8870_ISC5 0x23 /* Independent Sink Current LED5 */ +#define ADP8870_ISC6 0x24 /* Independent Sink Current LED6 */ +#define ADP8870_ISC7 0x25 /* Independent Sink Current LED7 (Brightness Level 1-daylight) */ +#define ADP8870_ISC7_L2 0x26 /* Independent Sink Current LED7 (Brightness Level 2-bright) */ +#define ADP8870_ISC7_L3 0x27 /* Independent Sink Current LED7 (Brightness Level 3-office) */ +#define ADP8870_ISC7_L4 0x28 /* Independent Sink Current LED7 (Brightness Level 4-indoor) */ +#define ADP8870_ISC7_L5 0x29 /* Independent Sink Current LED7 (Brightness Level 5-dark) */ +#define ADP8870_CMP_CTL 0x2D /* ALS Comparator Control Register */ +#define ADP8870_ALS1_EN 0x2E /* Main ALS comparator level enable */ +#define ADP8870_ALS2_EN 0x2F /* Second ALS comparator level enable */ +#define ADP8870_ALS1_STAT 0x30 /* Main ALS Comparator Status Register */ +#define ADP8870_ALS2_STAT 0x31 /* Second ALS Comparator Status Register */ +#define ADP8870_L2TRP 0x32 /* L2 comparator reference */ +#define ADP8870_L2HYS 0x33 /* L2 hysteresis */ +#define ADP8870_L3TRP 0x34 /* L3 comparator reference */ +#define ADP8870_L3HYS 0x35 /* L3 hysteresis */ +#define ADP8870_L4TRP 0x36 /* L4 comparator reference */ +#define ADP8870_L4HYS 0x37 /* L4 hysteresis */ +#define ADP8870_L5TRP 0x38 /* L5 comparator reference */ +#define ADP8870_L5HYS 0x39 /* L5 hysteresis */ +#define ADP8870_PH1LEVL 0x40 /* First phototransistor ambient light level-low byte register */ +#define ADP8870_PH1LEVH 0x41 /* First phototransistor ambient light level-high byte register */ +#define ADP8870_PH2LEVL 0x42 /* Second phototransistor ambient light level-low byte register */ +#define ADP8870_PH2LEVH 0x43 /* Second phototransistor ambient light level-high byte register */ + +#define ADP8870_MANUFID 0x3 /* Analog Devices AD8870 Manufacturer and device ID */ +#define ADP8870_DEVID(x) ((x) & 0xF) +#define ADP8870_MANID(x) ((x) >> 4) + +/* MDCR Device mode and status */ +#define D7ALSEN (1 << 7) +#define INT_CFG (1 << 6) +#define NSTBY (1 << 5) +#define DIM_EN (1 << 4) +#define GDWN_DIS (1 << 3) +#define SIS_EN (1 << 2) +#define CMP_AUTOEN (1 << 1) +#define BLEN (1 << 0) + +/* ADP8870_ALS1_EN Main ALS comparator level enable */ +#define L5_EN (1 << 3) +#define L4_EN (1 << 2) +#define L3_EN (1 << 1) +#define L2_EN (1 << 0) + +#define CFGR_BLV_SHIFT 3 +#define CFGR_BLV_MASK 0x7 +#define ADP8870_FLAG_LED_MASK 0xFF + +#define FADE_VAL(in, out) ((0xF & (in)) | ((0xF & (out)) << 4)) +#define BL_CFGR_VAL(law, blv) ((((blv) & CFGR_BLV_MASK) << CFGR_BLV_SHIFT) | ((0x3 & (law)) << 1)) +#define ALS_CMPR_CFG_VAL(filt) ((0x7 & (filt)) << 1) + +struct adp8870_bl { + struct i2c_client *client; + struct backlight_device *bl; + struct adp8870_led *led; + struct adp8870_backlight_platform_data *pdata; + struct mutex lock; + unsigned long cached_daylight_max; + int id; + int revid; + int current_brightness; +}; + +struct adp8870_led { + struct led_classdev cdev; + struct work_struct work; + struct i2c_client *client; + enum led_brightness new_brightness; + int id; + int flags; +}; + +static int adp8870_read(struct i2c_client *client, int reg, uint8_t *val) +{ + int ret; + + ret = i2c_smbus_read_byte_data(client, reg); + if (ret < 0) { + dev_err(&client->dev, "failed reading at 0x%02x\n", reg); + return ret; + } + + *val = ret; + return 0; +} + + +static int adp8870_write(struct i2c_client *client, u8 reg, u8 val) +{ + int ret = i2c_smbus_write_byte_data(client, reg, val); + if (ret) + dev_err(&client->dev, "failed to write\n"); + + return ret; +} + +static int adp8870_set_bits(struct i2c_client *client, int reg, uint8_t bit_mask) +{ + struct adp8870_bl *data = i2c_get_clientdata(client); + uint8_t reg_val; + int ret; + + mutex_lock(&data->lock); + + ret = adp8870_read(client, reg, ®_val); + + if (!ret && ((reg_val & bit_mask) == 0)) { + reg_val |= bit_mask; + ret = adp8870_write(client, reg, reg_val); + } + + mutex_unlock(&data->lock); + return ret; +} + +static int adp8870_clr_bits(struct i2c_client *client, int reg, uint8_t bit_mask) +{ + struct adp8870_bl *data = i2c_get_clientdata(client); + uint8_t reg_val; + int ret; + + mutex_lock(&data->lock); + + ret = adp8870_read(client, reg, ®_val); + + if (!ret && (reg_val & bit_mask)) { + reg_val &= ~bit_mask; + ret = adp8870_write(client, reg, reg_val); + } + + mutex_unlock(&data->lock); + return ret; +} + +/* + * Independent sink / LED + */ +#if defined(ADP8870_USE_LEDS) +static void adp8870_led_work(struct work_struct *work) +{ + struct adp8870_led *led = container_of(work, struct adp8870_led, work); + adp8870_write(led->client, ADP8870_ISC1 + led->id - 1, + led->new_brightness >> 1); +} + +static void adp8870_led_set(struct led_classdev *led_cdev, + enum led_brightness value) +{ + struct adp8870_led *led; + + led = container_of(led_cdev, struct adp8870_led, cdev); + led->new_brightness = value; + /* + * Use workqueue for IO since I2C operations can sleep. + */ + schedule_work(&led->work); +} + +static int adp8870_led_setup(struct adp8870_led *led) +{ + struct i2c_client *client = led->client; + int ret = 0; + + ret = adp8870_write(client, ADP8870_ISC1 + led->id - 1, 0); + if (ret) + return ret; + + ret = adp8870_set_bits(client, ADP8870_ISCC, 1 << (led->id - 1)); + if (ret) + return ret; + + if (led->id > 4) + ret = adp8870_set_bits(client, ADP8870_ISCT1, + (led->flags & 0x3) << ((led->id - 5) * 2)); + else + ret = adp8870_set_bits(client, ADP8870_ISCT2, + (led->flags & 0x3) << ((led->id - 1) * 2)); + + return ret; +} + +static int __devinit adp8870_led_probe(struct i2c_client *client) +{ + struct adp8870_backlight_platform_data *pdata = + client->dev.platform_data; + struct adp8870_bl *data = i2c_get_clientdata(client); + struct adp8870_led *led, *led_dat; + struct led_info *cur_led; + int ret, i; + + + led = kcalloc(pdata->num_leds, sizeof(*led), GFP_KERNEL); + if (led == NULL) { + dev_err(&client->dev, "failed to alloc memory\n"); + return -ENOMEM; + } + + ret = adp8870_write(client, ADP8870_ISCLAW, pdata->led_fade_law); + if (ret) + goto err_free; + + ret = adp8870_write(client, ADP8870_ISCT1, + (pdata->led_on_time & 0x3) << 6); + if (ret) + goto err_free; + + ret = adp8870_write(client, ADP8870_ISCF, + FADE_VAL(pdata->led_fade_in, pdata->led_fade_out)); + if (ret) + goto err_free; + + for (i = 0; i < pdata->num_leds; ++i) { + cur_led = &pdata->leds[i]; + led_dat = &led[i]; + + led_dat->id = cur_led->flags & ADP8870_FLAG_LED_MASK; + + if (led_dat->id > 7 || led_dat->id < 1) { + dev_err(&client->dev, "Invalid LED ID %d\n", + led_dat->id); + goto err; + } + + if (pdata->bl_led_assign & (1 << (led_dat->id - 1))) { + dev_err(&client->dev, "LED %d used by Backlight\n", + led_dat->id); + goto err; + } + + led_dat->cdev.name = cur_led->name; + led_dat->cdev.default_trigger = cur_led->default_trigger; + led_dat->cdev.brightness_set = adp8870_led_set; + led_dat->cdev.brightness = LED_OFF; + led_dat->flags = cur_led->flags >> FLAG_OFFT_SHIFT; + led_dat->client = client; + led_dat->new_brightness = LED_OFF; + INIT_WORK(&led_dat->work, adp8870_led_work); + + ret = led_classdev_register(&client->dev, &led_dat->cdev); + if (ret) { + dev_err(&client->dev, "failed to register LED %d\n", + led_dat->id); + goto err; + } + + ret = adp8870_led_setup(led_dat); + if (ret) { + dev_err(&client->dev, "failed to write\n"); + i++; + goto err; + } + } + + data->led = led; + + return 0; + + err: + for (i = i - 1; i >= 0; --i) { + led_classdev_unregister(&led[i].cdev); + cancel_work_sync(&led[i].work); + } + + err_free: + kfree(led); + + return ret; +} + +static int __devexit adp8870_led_remove(struct i2c_client *client) +{ + struct adp8870_backlight_platform_data *pdata = + client->dev.platform_data; + struct adp8870_bl *data = i2c_get_clientdata(client); + int i; + + for (i = 0; i < pdata->num_leds; i++) { + led_classdev_unregister(&data->led[i].cdev); + cancel_work_sync(&data->led[i].work); + } + + kfree(data->led); + return 0; +} +#else +static int __devinit adp8870_led_probe(struct i2c_client *client) +{ + return 0; +} + +static int __devexit adp8870_led_remove(struct i2c_client *client) +{ + return 0; +} +#endif + +static int adp8870_bl_set(struct backlight_device *bl, int brightness) +{ + struct adp8870_bl *data = bl_get_data(bl); + struct i2c_client *client = data->client; + int ret = 0; + + if (data->pdata->en_ambl_sens) { + if ((brightness > 0) && (brightness < ADP8870_MAX_BRIGHTNESS)) { + /* Disable Ambient Light auto adjust */ + ret = adp8870_clr_bits(client, ADP8870_MDCR, + CMP_AUTOEN); + if (ret) + return ret; + ret = adp8870_write(client, ADP8870_BLMX1, brightness); + if (ret) + return ret; + } else { + /* + * MAX_BRIGHTNESS -> Enable Ambient Light auto adjust + * restore daylight l1 sysfs brightness + */ + ret = adp8870_write(client, ADP8870_BLMX1, + data->cached_daylight_max); + if (ret) + return ret; + + ret = adp8870_set_bits(client, ADP8870_MDCR, + CMP_AUTOEN); + if (ret) + return ret; + } + } else { + ret = adp8870_write(client, ADP8870_BLMX1, brightness); + if (ret) + return ret; + } + + if (data->current_brightness && brightness == 0) + ret = adp8870_set_bits(client, + ADP8870_MDCR, DIM_EN); + else if (data->current_brightness == 0 && brightness) + ret = adp8870_clr_bits(client, + ADP8870_MDCR, DIM_EN); + + if (!ret) + data->current_brightness = brightness; + + return ret; +} + +static int adp8870_bl_update_status(struct backlight_device *bl) +{ + int brightness = bl->props.brightness; + if (bl->props.power != FB_BLANK_UNBLANK) + brightness = 0; + + if (bl->props.fb_blank != FB_BLANK_UNBLANK) + brightness = 0; + + return adp8870_bl_set(bl, brightness); +} + +static int adp8870_bl_get_brightness(struct backlight_device *bl) +{ + struct adp8870_bl *data = bl_get_data(bl); + + return data->current_brightness; +} + +static const struct backlight_ops adp8870_bl_ops = { + .update_status = adp8870_bl_update_status, + .get_brightness = adp8870_bl_get_brightness, +}; + +static int adp8870_bl_setup(struct backlight_device *bl) +{ + struct adp8870_bl *data = bl_get_data(bl); + struct i2c_client *client = data->client; + struct adp8870_backlight_platform_data *pdata = data->pdata; + int ret = 0; + + ret = adp8870_write(client, ADP8870_BLSEL, ~pdata->bl_led_assign); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_PWMLED, pdata->pwm_assign); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_BLMX1, pdata->l1_daylight_max); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_BLDM1, pdata->l1_daylight_dim); + if (ret) + return ret; + + if (pdata->en_ambl_sens) { + data->cached_daylight_max = pdata->l1_daylight_max; + ret = adp8870_write(client, ADP8870_BLMX2, + pdata->l2_bright_max); + if (ret) + return ret; + ret = adp8870_write(client, ADP8870_BLDM2, + pdata->l2_bright_dim); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_BLMX3, + pdata->l3_office_max); + if (ret) + return ret; + ret = adp8870_write(client, ADP8870_BLDM3, + pdata->l3_office_dim); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_BLMX4, + pdata->l4_indoor_max); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_BLDM4, + pdata->l4_indor_dim); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_BLMX5, + pdata->l5_dark_max); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_BLDM5, + pdata->l5_dark_dim); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_L2TRP, pdata->l2_trip); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_L2HYS, pdata->l2_hyst); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_L3TRP, pdata->l3_trip); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_L3HYS, pdata->l3_hyst); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_L4TRP, pdata->l4_trip); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_L4HYS, pdata->l4_hyst); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_L5TRP, pdata->l5_trip); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_L5HYS, pdata->l5_hyst); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_ALS1_EN, L5_EN | L4_EN | + L3_EN | L2_EN); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_CMP_CTL, + ALS_CMPR_CFG_VAL(pdata->abml_filt)); + if (ret) + return ret; + } + + ret = adp8870_write(client, ADP8870_CFGR, + BL_CFGR_VAL(pdata->bl_fade_law, 0)); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_BLFR, FADE_VAL(pdata->bl_fade_in, + pdata->bl_fade_out)); + if (ret) + return ret; + /* + * ADP8870 Rev0 requires GDWN_DIS bit set + */ + + ret = adp8870_set_bits(client, ADP8870_MDCR, BLEN | DIM_EN | NSTBY | + (data->revid == 0 ? GDWN_DIS : 0)); + + return ret; +} + +static ssize_t adp8870_show(struct device *dev, char *buf, int reg) +{ + struct adp8870_bl *data = dev_get_drvdata(dev); + int error; + uint8_t reg_val; + + mutex_lock(&data->lock); + error = adp8870_read(data->client, reg, ®_val); + mutex_unlock(&data->lock); + + if (error < 0) + return error; + + return sprintf(buf, "%u\n", reg_val); +} + +static ssize_t adp8870_store(struct device *dev, const char *buf, + size_t count, int reg) +{ + struct adp8870_bl *data = dev_get_drvdata(dev); + unsigned long val; + int ret; + + ret = strict_strtoul(buf, 10, &val); + if (ret) + return ret; + + mutex_lock(&data->lock); + adp8870_write(data->client, reg, val); + mutex_unlock(&data->lock); + + return count; +} + +static ssize_t adp8870_bl_l5_dark_max_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLMX5); +} + +static ssize_t adp8870_bl_l5_dark_max_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + return adp8870_store(dev, buf, count, ADP8870_BLMX5); +} +static DEVICE_ATTR(l5_dark_max, 0664, adp8870_bl_l5_dark_max_show, + adp8870_bl_l5_dark_max_store); + + +static ssize_t adp8870_bl_l4_indoor_max_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLMX4); +} + +static ssize_t adp8870_bl_l4_indoor_max_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + return adp8870_store(dev, buf, count, ADP8870_BLMX4); +} +static DEVICE_ATTR(l4_indoor_max, 0664, adp8870_bl_l4_indoor_max_show, + adp8870_bl_l4_indoor_max_store); + + +static ssize_t adp8870_bl_l3_office_max_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLMX3); +} + +static ssize_t adp8870_bl_l3_office_max_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + return adp8870_store(dev, buf, count, ADP8870_BLMX3); +} + +static DEVICE_ATTR(l3_office_max, 0664, adp8870_bl_l3_office_max_show, + adp8870_bl_l3_office_max_store); + +static ssize_t adp8870_bl_l2_bright_max_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLMX2); +} + +static ssize_t adp8870_bl_l2_bright_max_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + return adp8870_store(dev, buf, count, ADP8870_BLMX2); +} +static DEVICE_ATTR(l2_bright_max, 0664, adp8870_bl_l2_bright_max_show, + adp8870_bl_l2_bright_max_store); + +static ssize_t adp8870_bl_l1_daylight_max_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLMX1); +} + +static ssize_t adp8870_bl_l1_daylight_max_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct adp8870_bl *data = dev_get_drvdata(dev); + int ret = strict_strtoul(buf, 10, &data->cached_daylight_max); + if (ret) + return ret; + + return adp8870_store(dev, buf, count, ADP8870_BLMX1); +} +static DEVICE_ATTR(l1_daylight_max, 0664, adp8870_bl_l1_daylight_max_show, + adp8870_bl_l1_daylight_max_store); + +static ssize_t adp8870_bl_l5_dark_dim_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLDM5); +} + +static ssize_t adp8870_bl_l5_dark_dim_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + return adp8870_store(dev, buf, count, ADP8870_BLDM5); +} +static DEVICE_ATTR(l5_dark_dim, 0664, adp8870_bl_l5_dark_dim_show, + adp8870_bl_l5_dark_dim_store); + +static ssize_t adp8870_bl_l4_indoor_dim_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLDM4); +} + +static ssize_t adp8870_bl_l4_indoor_dim_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + return adp8870_store(dev, buf, count, ADP8870_BLDM4); +} +static DEVICE_ATTR(l4_indoor_dim, 0664, adp8870_bl_l4_indoor_dim_show, + adp8870_bl_l4_indoor_dim_store); + + +static ssize_t adp8870_bl_l3_office_dim_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLDM3); +} + +static ssize_t adp8870_bl_l3_office_dim_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + return adp8870_store(dev, buf, count, ADP8870_BLDM3); +} +static DEVICE_ATTR(l3_office_dim, 0664, adp8870_bl_l3_office_dim_show, + adp8870_bl_l3_office_dim_store); + +static ssize_t adp8870_bl_l2_bright_dim_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLDM2); +} + +static ssize_t adp8870_bl_l2_bright_dim_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + return adp8870_store(dev, buf, count, ADP8870_BLDM2); +} +static DEVICE_ATTR(l2_bright_dim, 0664, adp8870_bl_l2_bright_dim_show, + adp8870_bl_l2_bright_dim_store); + +static ssize_t adp8870_bl_l1_daylight_dim_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLDM1); +} + +static ssize_t adp8870_bl_l1_daylight_dim_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + return adp8870_store(dev, buf, count, ADP8870_BLDM1); +} +static DEVICE_ATTR(l1_daylight_dim, 0664, adp8870_bl_l1_daylight_dim_show, + adp8870_bl_l1_daylight_dim_store); + +#ifdef ADP8870_EXT_FEATURES +static ssize_t adp8870_bl_ambient_light_level_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct adp8870_bl *data = dev_get_drvdata(dev); + int error; + uint8_t reg_val; + uint16_t ret_val; + + mutex_lock(&data->lock); + error = adp8870_read(data->client, ADP8870_PH1LEVL, ®_val); + if (error < 0) { + mutex_unlock(&data->lock); + return error; + } + ret_val = reg_val; + error = adp8870_read(data->client, ADP8870_PH1LEVH, ®_val); + mutex_unlock(&data->lock); + + if (error < 0) + return error; + + /* Return 13-bit conversion value for the first light sensor */ + ret_val += (reg_val & 0x1F) << 8; + + return sprintf(buf, "%u\n", ret_val); +} +static DEVICE_ATTR(ambient_light_level, 0444, + adp8870_bl_ambient_light_level_show, NULL); + +static ssize_t adp8870_bl_ambient_light_zone_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct adp8870_bl *data = dev_get_drvdata(dev); + int error; + uint8_t reg_val; + + mutex_lock(&data->lock); + error = adp8870_read(data->client, ADP8870_CFGR, ®_val); + mutex_unlock(&data->lock); + + if (error < 0) + return error; + + return sprintf(buf, "%u\n", + ((reg_val >> CFGR_BLV_SHIFT) & CFGR_BLV_MASK) + 1); +} + +static ssize_t adp8870_bl_ambient_light_zone_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct adp8870_bl *data = dev_get_drvdata(dev); + unsigned long val; + uint8_t reg_val; + int ret; + + ret = strict_strtoul(buf, 10, &val); + if (ret) + return ret; + + if (val == 0) { + /* Enable automatic ambient light sensing */ + adp8870_set_bits(data->client, ADP8870_MDCR, CMP_AUTOEN); + } else if ((val > 0) && (val < 6)) { + /* Disable automatic ambient light sensing */ + adp8870_clr_bits(data->client, ADP8870_MDCR, CMP_AUTOEN); + + /* Set user supplied ambient light zone */ + mutex_lock(&data->lock); + adp8870_read(data->client, ADP8870_CFGR, ®_val); + reg_val &= ~(CFGR_BLV_MASK << CFGR_BLV_SHIFT); + reg_val |= (val - 1) << CFGR_BLV_SHIFT; + adp8870_write(data->client, ADP8870_CFGR, reg_val); + mutex_unlock(&data->lock); + } + + return count; +} +static DEVICE_ATTR(ambient_light_zone, 0664, + adp8870_bl_ambient_light_zone_show, + adp8870_bl_ambient_light_zone_store); +#endif + +static struct attribute *adp8870_bl_attributes[] = { + &dev_attr_l5_dark_max.attr, + &dev_attr_l5_dark_dim.attr, + &dev_attr_l4_indoor_max.attr, + &dev_attr_l4_indoor_dim.attr, + &dev_attr_l3_office_max.attr, + &dev_attr_l3_office_dim.attr, + &dev_attr_l2_bright_max.attr, + &dev_attr_l2_bright_dim.attr, + &dev_attr_l1_daylight_max.attr, + &dev_attr_l1_daylight_dim.attr, +#ifdef ADP8870_EXT_FEATURES + &dev_attr_ambient_light_level.attr, + &dev_attr_ambient_light_zone.attr, +#endif + NULL +}; + +static const struct attribute_group adp8870_bl_attr_group = { + .attrs = adp8870_bl_attributes, +}; + +static int __devinit adp8870_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct backlight_properties props; + struct backlight_device *bl; + struct adp8870_bl *data; + struct adp8870_backlight_platform_data *pdata = + client->dev.platform_data; + uint8_t reg_val; + int ret; + + if (!i2c_check_functionality(client->adapter, + I2C_FUNC_SMBUS_BYTE_DATA)) { + dev_err(&client->dev, "SMBUS Byte Data not Supported\n"); + return -EIO; + } + + if (!pdata) { + dev_err(&client->dev, "no platform data?\n"); + return -EINVAL; + } + + ret = adp8870_read(client, ADP8870_MFDVID, ®_val); + if (ret < 0) + return -EIO; + + if (ADP8870_MANID(reg_val) != ADP8870_MANUFID) { + dev_err(&client->dev, "failed to probe\n"); + return -ENODEV; + } + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (data == NULL) + return -ENOMEM; + + data->revid = ADP8870_DEVID(reg_val); + data->client = client; + data->pdata = pdata; + data->id = id->driver_data; + data->current_brightness = 0; + i2c_set_clientdata(client, data); + + mutex_init(&data->lock); + + memset(&props, 0, sizeof(props)); + props.type = BACKLIGHT_RAW; + props.max_brightness = props.brightness = ADP8870_MAX_BRIGHTNESS; + bl = backlight_device_register(dev_driver_string(&client->dev), + &client->dev, data, &adp8870_bl_ops, &props); + if (IS_ERR(bl)) { + dev_err(&client->dev, "failed to register backlight\n"); + ret = PTR_ERR(bl); + goto out2; + } + + data->bl = bl; + + if (pdata->en_ambl_sens) + ret = sysfs_create_group(&bl->dev.kobj, + &adp8870_bl_attr_group); + + if (ret) { + dev_err(&client->dev, "failed to register sysfs\n"); + goto out1; + } + + ret = adp8870_bl_setup(bl); + if (ret) { + ret = -EIO; + goto out; + } + + backlight_update_status(bl); + + dev_info(&client->dev, "Rev.%d Backlight\n", data->revid); + + if (pdata->num_leds) + adp8870_led_probe(client); + + return 0; + +out: + if (data->pdata->en_ambl_sens) + sysfs_remove_group(&data->bl->dev.kobj, + &adp8870_bl_attr_group); +out1: + backlight_device_unregister(bl); +out2: + i2c_set_clientdata(client, NULL); + kfree(data); + + return ret; +} + +static int __devexit adp8870_remove(struct i2c_client *client) +{ + struct adp8870_bl *data = i2c_get_clientdata(client); + + adp8870_clr_bits(client, ADP8870_MDCR, NSTBY); + + if (data->led) + adp8870_led_remove(client); + + if (data->pdata->en_ambl_sens) + sysfs_remove_group(&data->bl->dev.kobj, + &adp8870_bl_attr_group); + + backlight_device_unregister(data->bl); + i2c_set_clientdata(client, NULL); + kfree(data); + + return 0; +} + +#ifdef CONFIG_PM +static int adp8870_i2c_suspend(struct i2c_client *client, pm_message_t message) +{ + adp8870_clr_bits(client, ADP8870_MDCR, NSTBY); + + return 0; +} + +static int adp8870_i2c_resume(struct i2c_client *client) +{ + adp8870_set_bits(client, ADP8870_MDCR, NSTBY); + + return 0; +} +#else +#define adp8870_i2c_suspend NULL +#define adp8870_i2c_resume NULL +#endif + +static const struct i2c_device_id adp8870_id[] = { + { "adp8870", 0 }, + { } +}; +MODULE_DEVICE_TABLE(i2c, adp8870_id); + +static struct i2c_driver adp8870_driver = { + .driver = { + .name = KBUILD_MODNAME, + }, + .probe = adp8870_probe, + .remove = __devexit_p(adp8870_remove), + .suspend = adp8870_i2c_suspend, + .resume = adp8870_i2c_resume, + .id_table = adp8870_id, +}; + +static int __init adp8870_init(void) +{ + return i2c_add_driver(&adp8870_driver); +} +module_init(adp8870_init); + +static void __exit adp8870_exit(void) +{ + i2c_del_driver(&adp8870_driver); +} +module_exit(adp8870_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Michael Hennerich <hennerich@blackfin.uclinux.org>"); +MODULE_DESCRIPTION("ADP8870 Backlight driver"); +MODULE_ALIAS("platform:adp8870-backlight"); diff --git a/drivers/w1/masters/Kconfig b/drivers/w1/masters/Kconfig index 00d615d..979d6ee 100644 --- a/drivers/w1/masters/Kconfig +++ b/drivers/w1/masters/Kconfig @@ -42,7 +42,7 @@ config W1_MASTER_MXC config W1_MASTER_DS1WM tristate "Maxim DS1WM 1-wire busmaster" - depends on W1 + depends on W1 && GENERIC_HARDIRQS help Say Y here to enable the DS1WM 1-wire driver, such as that in HP iPAQ devices like h5xxx, h2200, and ASIC3-based like diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index e9b8e59..76bff2b 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -88,7 +88,7 @@ static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, pmd_t pmd = *pmdp; pmd_clear(mm, address, pmdp); return pmd; -}) +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif diff --git a/include/linux/i2c/adp8870.h b/include/linux/i2c/adp8870.h new file mode 100644 index 0000000..624dcec --- /dev/null +++ b/include/linux/i2c/adp8870.h @@ -0,0 +1,153 @@ +/* + * Definitions and platform data for Analog Devices + * Backlight drivers ADP8870 + * + * Copyright 2009-2010 Analog Devices Inc. + * + * Licensed under the GPL-2 or later. + */ + +#ifndef __LINUX_I2C_ADP8870_H +#define __LINUX_I2C_ADP8870_H + +#define ID_ADP8870 8870 + +#define ADP8870_MAX_BRIGHTNESS 0x7F +#define FLAG_OFFT_SHIFT 8 + +/* + * LEDs subdevice platform data + */ + +#define ADP8870_LED_DIS_BLINK (0 << FLAG_OFFT_SHIFT) +#define ADP8870_LED_OFFT_600ms (1 << FLAG_OFFT_SHIFT) +#define ADP8870_LED_OFFT_1200ms (2 << FLAG_OFFT_SHIFT) +#define ADP8870_LED_OFFT_1800ms (3 << FLAG_OFFT_SHIFT) + +#define ADP8870_LED_ONT_200ms 0 +#define ADP8870_LED_ONT_600ms 1 +#define ADP8870_LED_ONT_800ms 2 +#define ADP8870_LED_ONT_1200ms 3 + +#define ADP8870_LED_D7 (7) +#define ADP8870_LED_D6 (6) +#define ADP8870_LED_D5 (5) +#define ADP8870_LED_D4 (4) +#define ADP8870_LED_D3 (3) +#define ADP8870_LED_D2 (2) +#define ADP8870_LED_D1 (1) + +/* + * Backlight subdevice platform data + */ + +#define ADP8870_BL_D7 (1 << 6) +#define ADP8870_BL_D6 (1 << 5) +#define ADP8870_BL_D5 (1 << 4) +#define ADP8870_BL_D4 (1 << 3) +#define ADP8870_BL_D3 (1 << 2) +#define ADP8870_BL_D2 (1 << 1) +#define ADP8870_BL_D1 (1 << 0) + +#define ADP8870_FADE_T_DIS 0 /* Fade Timer Disabled */ +#define ADP8870_FADE_T_300ms 1 /* 0.3 Sec */ +#define ADP8870_FADE_T_600ms 2 +#define ADP8870_FADE_T_900ms 3 +#define ADP8870_FADE_T_1200ms 4 +#define ADP8870_FADE_T_1500ms 5 +#define ADP8870_FADE_T_1800ms 6 +#define ADP8870_FADE_T_2100ms 7 +#define ADP8870_FADE_T_2400ms 8 +#define ADP8870_FADE_T_2700ms 9 +#define ADP8870_FADE_T_3000ms 10 +#define ADP8870_FADE_T_3500ms 11 +#define ADP8870_FADE_T_4000ms 12 +#define ADP8870_FADE_T_4500ms 13 +#define ADP8870_FADE_T_5000ms 14 +#define ADP8870_FADE_T_5500ms 15 /* 5.5 Sec */ + +#define ADP8870_FADE_LAW_LINEAR 0 +#define ADP8870_FADE_LAW_SQUARE 1 +#define ADP8870_FADE_LAW_CUBIC1 2 +#define ADP8870_FADE_LAW_CUBIC2 3 + +#define ADP8870_BL_AMBL_FILT_80ms 0 /* Light sensor filter time */ +#define ADP8870_BL_AMBL_FILT_160ms 1 +#define ADP8870_BL_AMBL_FILT_320ms 2 +#define ADP8870_BL_AMBL_FILT_640ms 3 +#define ADP8870_BL_AMBL_FILT_1280ms 4 +#define ADP8870_BL_AMBL_FILT_2560ms 5 +#define ADP8870_BL_AMBL_FILT_5120ms 6 +#define ADP8870_BL_AMBL_FILT_10240ms 7 /* 10.24 sec */ + +/* + * Blacklight current 0..30mA + */ +#define ADP8870_BL_CUR_mA(I) ((I * 127) / 30) + +/* + * L2 comparator current 0..1106uA + */ +#define ADP8870_L2_COMP_CURR_uA(I) ((I * 255) / 1106) + +/* + * L3 comparator current 0..551uA + */ +#define ADP8870_L3_COMP_CURR_uA(I) ((I * 255) / 551) + +/* + * L4 comparator current 0..275uA + */ +#define ADP8870_L4_COMP_CURR_uA(I) ((I * 255) / 275) + +/* + * L5 comparator current 0..138uA + */ +#define ADP8870_L5_COMP_CURR_uA(I) ((I * 255) / 138) + +struct adp8870_backlight_platform_data { + u8 bl_led_assign; /* 1 = Backlight 0 = Individual LED */ + u8 pwm_assign; /* 1 = Enables PWM mode */ + + u8 bl_fade_in; /* Backlight Fade-In Timer */ + u8 bl_fade_out; /* Backlight Fade-Out Timer */ + u8 bl_fade_law; /* fade-on/fade-off transfer characteristic */ + + u8 en_ambl_sens; /* 1 = enable ambient light sensor */ + u8 abml_filt; /* Light sensor filter time */ + + u8 l1_daylight_max; /* use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l1_daylight_dim; /* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l2_bright_max; /* use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l2_bright_dim; /* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l3_office_max; /* use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l3_office_dim; /* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l4_indoor_max; /* use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l4_indor_dim; /* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l5_dark_max; /* use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l5_dark_dim; /* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */ + + u8 l2_trip; /* use L2_COMP_CURR_uA(I) 0 <= I <= 1106 uA */ + u8 l2_hyst; /* use L2_COMP_CURR_uA(I) 0 <= I <= 1106 uA */ + u8 l3_trip; /* use L3_COMP_CURR_uA(I) 0 <= I <= 551 uA */ + u8 l3_hyst; /* use L3_COMP_CURR_uA(I) 0 <= I <= 551 uA */ + u8 l4_trip; /* use L4_COMP_CURR_uA(I) 0 <= I <= 275 uA */ + u8 l4_hyst; /* use L4_COMP_CURR_uA(I) 0 <= I <= 275 uA */ + u8 l5_trip; /* use L5_COMP_CURR_uA(I) 0 <= I <= 138 uA */ + u8 l5_hyst; /* use L6_COMP_CURR_uA(I) 0 <= I <= 138 uA */ + + /** + * Independent Current Sinks / LEDS + * Sinks not assigned to the Backlight can be exposed to + * user space using the LEDS CLASS interface + */ + + int num_leds; + struct led_info *leds; + u8 led_fade_in; /* LED Fade-In Timer */ + u8 led_fade_out; /* LED Fade-Out Timer */ + u8 led_fade_law; /* fade-on/fade-off transfer characteristic */ + u8 led_on_time; +}; + +#endif /* __LINUX_I2C_ADP8870_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index fb0e732..953352a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -671,8 +671,8 @@ struct sysinfo { #ifdef __CHECKER__ #define BUILD_BUG_ON_NOT_POWER_OF_2(n) -#define BUILD_BUG_ON_ZERO(e) -#define BUILD_BUG_ON_NULL(e) +#define BUILD_BUG_ON_ZERO(e) (0) +#define BUILD_BUG_ON_NULL(e) ((void*)0) #define BUILD_BUG_ON(condition) #else /* __CHECKER__ */ diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index 2a0d7d6..ee0c952 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -12,6 +12,7 @@ #ifndef _LINUX_KMSG_DUMP_H #define _LINUX_KMSG_DUMP_H +#include <linux/errno.h> #include <linux/list.h> enum kmsg_dump_reason { diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 9724a38..50940da 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -84,6 +84,7 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem); extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page); extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); +extern struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm); static inline int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup) @@ -246,6 +247,11 @@ static inline struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) return NULL; } +static inline struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) +{ + return NULL; +} + static inline int mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *mem) { return 1; diff --git a/include/linux/swap.h b/include/linux/swap.h index 384eb5f..e705646 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -358,6 +358,7 @@ struct backing_dev_info; extern struct mm_struct *swap_token_mm; extern void grab_swap_token(struct mm_struct *); extern void __put_swap_token(struct mm_struct *); +extern void disable_swap_token(struct mem_cgroup *memcg); static inline int has_swap_token(struct mm_struct *mm) { @@ -370,11 +371,6 @@ static inline void put_swap_token(struct mm_struct *mm) __put_swap_token(mm); } -static inline void disable_swap_token(void) -{ - put_swap_token(swap_token_mm); -} - #ifdef CONFIG_CGROUP_MEM_RES_CTLR extern void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout); @@ -500,7 +496,7 @@ static inline int has_swap_token(struct mm_struct *mm) return 0; } -static inline void disable_swap_token(void) +static inline void disable_swap_token(struct mem_cgroup *memcg) { } diff --git a/include/linux/topology.h b/include/linux/topology.h index b91a40e..fc839bf 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -60,7 +60,7 @@ int arch_update_cpu_topology(void); * (in whatever arch specific measurement units returned by node_distance()) * then switch on zone reclaim on boot. */ -#define RECLAIM_DISTANCE 20 +#define RECLAIM_DISTANCE 30 #endif #ifndef PENALTY_FOR_NODE_WITH_CPUS #define PENALTY_FOR_NODE_WITH_CPUS (1) diff --git a/include/linux/uts.h b/include/linux/uts.h index 73eb1ed..6ddbd86 100644 --- a/include/linux/uts.h +++ b/include/linux/uts.h @@ -9,7 +9,7 @@ #endif #ifndef UTS_NODENAME -#define UTS_NODENAME "(none)" /* set by sethostname() */ +#define UTS_NODENAME CONFIG_DEFAULT_HOSTNAME /* set by sethostname() */ #endif #ifndef UTS_DOMAINNAME diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index ea422aa..b2c33bd 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -6,6 +6,8 @@ #include <linux/types.h> #include <linux/tracepoint.h> +#include <linux/mm.h> +#include <linux/memcontrol.h> #include "gfpflags.h" #define RECLAIM_WB_ANON 0x0001u @@ -310,6 +312,87 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive, show_reclaim_flags(__entry->reclaim_flags)) ); +TRACE_EVENT(replace_swap_token, + TP_PROTO(struct mm_struct *old_mm, + struct mm_struct *new_mm), + + TP_ARGS(old_mm, new_mm), + + TP_STRUCT__entry( + __field(struct mm_struct*, old_mm) + __field(unsigned int, old_prio) + __field(struct mm_struct*, new_mm) + __field(unsigned int, new_prio) + ), + + TP_fast_assign( + __entry->old_mm = old_mm; + __entry->old_prio = old_mm ? old_mm->token_priority : 0; + __entry->new_mm = new_mm; + __entry->new_prio = new_mm->token_priority; + ), + + TP_printk("old_token_mm=%p old_prio=%u new_token_mm=%p new_prio=%u", + __entry->old_mm, __entry->old_prio, + __entry->new_mm, __entry->new_prio) +); + +DECLARE_EVENT_CLASS(put_swap_token_template, + TP_PROTO(struct mm_struct *swap_token_mm), + + TP_ARGS(swap_token_mm), + + TP_STRUCT__entry( + __field(struct mm_struct*, swap_token_mm) + ), + + TP_fast_assign( + __entry->swap_token_mm = swap_token_mm; + ), + + TP_printk("token_mm=%p", __entry->swap_token_mm) +); + +DEFINE_EVENT(put_swap_token_template, put_swap_token, + TP_PROTO(struct mm_struct *swap_token_mm), + TP_ARGS(swap_token_mm) +); + +DEFINE_EVENT_CONDITION(put_swap_token_template, disable_swap_token, + TP_PROTO(struct mm_struct *swap_token_mm), + TP_ARGS(swap_token_mm), + TP_CONDITION(swap_token_mm != NULL) +); + +TRACE_EVENT_CONDITION(update_swap_token_priority, + TP_PROTO(struct mm_struct *mm, + unsigned int old_prio, + struct mm_struct *swap_token_mm), + + TP_ARGS(mm, old_prio, swap_token_mm), + + TP_CONDITION(mm->token_priority != old_prio), + + TP_STRUCT__entry( + __field(struct mm_struct*, mm) + __field(unsigned int, old_prio) + __field(unsigned int, new_prio) + __field(struct mm_struct*, swap_token_mm) + __field(unsigned int, swap_token_prio) + ), + + TP_fast_assign( + __entry->mm = mm; + __entry->old_prio = old_prio; + __entry->new_prio = mm->token_priority; + __entry->swap_token_mm = swap_token_mm; + __entry->swap_token_prio = swap_token_mm ? swap_token_mm->token_priority : 0; + ), + + TP_printk("mm=%p old_prio=%u new_prio=%u swap_token_mm=%p token_prio=%u", + __entry->mm, __entry->old_prio, __entry->new_prio, + __entry->swap_token_mm, __entry->swap_token_prio) +); #endif /* _TRACE_VMSCAN_H */ diff --git a/init/Kconfig b/init/Kconfig index ebafac4..412c21b 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -19,7 +19,6 @@ config DEFCONFIG_LIST config CONSTRUCTORS bool depends on !UML - default y config HAVE_IRQ_WORK bool @@ -204,6 +203,15 @@ config KERNEL_LZO endchoice +config DEFAULT_HOSTNAME + string "Default hostname" + default "(none)" + help + This option determines the default system hostname before userspace + calls sethostname(2). The kernel traditionally uses "(none)" here, + but you may wish to use a different default here to make a minimal + system more usable with less configuration. + config SWAP bool "Support for paging of anonymous memory (swap)" depends on MMU && BLOCK diff --git a/init/calibrate.c b/init/calibrate.c index cfd7000..2568d22 100644 --- a/init/calibrate.c +++ b/init/calibrate.c @@ -93,9 +93,6 @@ static unsigned long __cpuinit calibrate_delay_direct(void) * If the upper limit and lower limit of the timer_rate is * >= 12.5% apart, redo calibration. */ - printk(KERN_DEBUG "calibrate_delay_direct() timer_rate_max=%lu " - "timer_rate_min=%lu pre_start=%lu pre_end=%lu\n", - timer_rate_max, timer_rate_min, pre_start, pre_end); if (start >= post_end) printk(KERN_NOTICE "calibrate_delay_direct() ignoring " "timer_rate as we had a TSC wrap around" diff --git a/kernel/exit.c b/kernel/exit.c index 20a4064..f2b321b 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -561,29 +561,28 @@ void exit_files(struct task_struct *tsk) #ifdef CONFIG_MM_OWNER /* - * Task p is exiting and it owned mm, lets find a new owner for it + * A task is exiting. If it owned this mm, find a new owner for the mm. */ -static inline int -mm_need_new_owner(struct mm_struct *mm, struct task_struct *p) -{ - /* - * If there are other users of the mm and the owner (us) is exiting - * we need to find a new owner to take on the responsibility. - */ - if (atomic_read(&mm->mm_users) <= 1) - return 0; - if (mm->owner != p) - return 0; - return 1; -} - void mm_update_next_owner(struct mm_struct *mm) { struct task_struct *c, *g, *p = current; retry: - if (!mm_need_new_owner(mm, p)) + /* + * If the exiting or execing task is not the owner, it's + * someone else's problem. + */ + if (mm->owner != p) return; + /* + * The current owner is exiting/execing and there are no other + * candidates. Do not leave the mm pointing to a possibly + * freed task structure. + */ + if (atomic_read(&mm->mm_users) <= 1) { + mm->owner = NULL; + return; + } read_lock(&tasklist_lock); /* diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig index b8cadf7..5bf924d 100644 --- a/kernel/gcov/Kconfig +++ b/kernel/gcov/Kconfig @@ -2,7 +2,8 @@ menu "GCOV-based kernel profiling" config GCOV_KERNEL bool "Enable gcov-based kernel profiling" - depends on DEBUG_FS && CONSTRUCTORS + depends on DEBUG_FS + select CONSTRUCTORS default n ---help--- This option enables gcov-based code profiling (e.g. for code coverage diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 88725c9..10d0182 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -1096,7 +1096,7 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag * to move current somewhere else, making room for our non-migratable * task. */ - if (p->prio == rq->curr->prio && !need_resched()) + if (p->prio == rq->curr->prio && !test_tsk_need_resched(rq->curr)) check_preempt_equal_prio(rq, p); #endif } @@ -1239,6 +1239,10 @@ static int find_lowest_rq(struct task_struct *task) int this_cpu = smp_processor_id(); int cpu = task_cpu(task); + /* Make sure the mask is initialized first */ + if (unlikely(!lowest_mask)) + return -1; + if (task->rt.nr_cpus_allowed == 1) return -1; /* No other targets possible */ diff --git a/kernel/signal.c b/kernel/signal.c index 86c32b8..ff76786 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2365,7 +2365,7 @@ int sigprocmask(int how, sigset_t *set, sigset_t *oldset) /** * sys_rt_sigprocmask - change the list of currently blocked signals * @how: whether to add, remove, or set signals - * @set: stores pending signals + * @nset: stores pending signals * @oset: previous value of signal mask if non-null * @sigsetsize: size of sigset_t type */ diff --git a/lib/bitmap.c b/lib/bitmap.c index 41baf02..3f3b681 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -572,7 +572,7 @@ EXPORT_SYMBOL(bitmap_scnlistprintf); /** * __bitmap_parselist - convert list format ASCII string to bitmap - * @bp: read nul-terminated user string from this buffer + * @buf: read nul-terminated user string from this buffer * @buflen: buffer size in bytes. If string is smaller than this * then it must be terminated with a \0. * @is_user: location of buffer, 0 indicates kernel space diff --git a/mm/compaction.c b/mm/compaction.c index 021a296..6cc604b 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -144,9 +144,20 @@ static void isolate_freepages(struct zone *zone, int nr_freepages = cc->nr_freepages; struct list_head *freelist = &cc->freepages; + /* + * Initialise the free scanner. The starting point is where we last + * scanned from (or the end of the zone if starting). The low point + * is the end of the pageblock the migration scanner is using. + */ pfn = cc->free_pfn; low_pfn = cc->migrate_pfn + pageblock_nr_pages; - high_pfn = low_pfn; + + /* + * Take care that if the migration scanner is at the end of the zone + * that the free scanner does not accidentally move to the next zone + * in the next isolation cycle. + */ + high_pfn = min(low_pfn, pfn); /* * Isolate free pages until enough are available to migrate the @@ -240,11 +251,18 @@ static bool too_many_isolated(struct zone *zone) return isolated > (inactive + active) / 2; } +/* possible outcome of isolate_migratepages */ +typedef enum { + ISOLATE_ABORT, /* Abort compaction now */ + ISOLATE_NONE, /* No pages isolated, continue scanning */ + ISOLATE_SUCCESS, /* Pages isolated, migrate */ +} isolate_migrate_t; + /* * Isolate all pages that can be migrated from the block pointed to by * the migrate scanner within compact_control. */ -static unsigned long isolate_migratepages(struct zone *zone, +static isolate_migrate_t isolate_migratepages(struct zone *zone, struct compact_control *cc) { unsigned long low_pfn, end_pfn; @@ -261,7 +279,7 @@ static unsigned long isolate_migratepages(struct zone *zone, /* Do not cross the free scanner or scan within a memory hole */ if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) { cc->migrate_pfn = end_pfn; - return 0; + return ISOLATE_NONE; } /* @@ -270,10 +288,14 @@ static unsigned long isolate_migratepages(struct zone *zone, * delay for some time until fewer pages are isolated */ while (unlikely(too_many_isolated(zone))) { + /* async migration should just abort */ + if (!cc->sync) + return ISOLATE_ABORT; + congestion_wait(BLK_RW_ASYNC, HZ/10); if (fatal_signal_pending(current)) - return 0; + return ISOLATE_ABORT; } /* Time to isolate some pages for migration */ @@ -358,7 +380,7 @@ static unsigned long isolate_migratepages(struct zone *zone, trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated); - return cc->nr_migratepages; + return ISOLATE_SUCCESS; } /* @@ -420,13 +442,6 @@ static int compact_finished(struct zone *zone, if (cc->free_pfn <= cc->migrate_pfn) return COMPACT_COMPLETE; - /* Compaction run is not finished if the watermark is not met */ - watermark = low_wmark_pages(zone); - watermark += (1 << cc->order); - - if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0)) - return COMPACT_CONTINUE; - /* * order == -1 is expected when compacting via * /proc/sys/vm/compact_memory @@ -434,6 +449,13 @@ static int compact_finished(struct zone *zone, if (cc->order == -1) return COMPACT_CONTINUE; + /* Compaction run is not finished if the watermark is not met */ + watermark = low_wmark_pages(zone); + watermark += (1 << cc->order); + + if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0)) + return COMPACT_CONTINUE; + /* Direct compactor: Is a suitable page free? */ for (order = cc->order; order < MAX_ORDER; order++) { /* Job done if page is free of the right migratetype */ @@ -461,6 +483,13 @@ unsigned long compaction_suitable(struct zone *zone, int order) unsigned long watermark; /* + * order == -1 is expected when compacting via + * /proc/sys/vm/compact_memory + */ + if (order == -1) + return COMPACT_CONTINUE; + + /* * Watermarks for order-0 must be met for compaction. Note the 2UL. * This is because during migration, copies of pages need to be * allocated and for a short time, the footprint is higher @@ -470,17 +499,11 @@ unsigned long compaction_suitable(struct zone *zone, int order) return COMPACT_SKIPPED; /* - * order == -1 is expected when compacting via - * /proc/sys/vm/compact_memory - */ - if (order == -1) - return COMPACT_CONTINUE; - - /* * fragmentation index determines if allocation failures are due to * low memory or external fragmentation * - * index of -1 implies allocations might succeed dependingon watermarks + * index of -1000 implies allocations might succeed depending on + * watermarks * index towards 0 implies failure is due to lack of memory * index towards 1000 implies failure is due to fragmentation * @@ -490,7 +513,8 @@ unsigned long compaction_suitable(struct zone *zone, int order) if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold) return COMPACT_SKIPPED; - if (fragindex == -1 && zone_watermark_ok(zone, order, watermark, 0, 0)) + if (fragindex == -1000 && zone_watermark_ok(zone, order, watermark, + 0, 0)) return COMPACT_PARTIAL; return COMPACT_CONTINUE; @@ -522,8 +546,15 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) unsigned long nr_migrate, nr_remaining; int err; - if (!isolate_migratepages(zone, cc)) + switch (isolate_migratepages(zone, cc)) { + case ISOLATE_ABORT: + ret = COMPACT_PARTIAL; + goto out; + case ISOLATE_NONE: continue; + case ISOLATE_SUCCESS: + ; + } nr_migrate = cc->nr_migratepages; err = migrate_pages(&cc->migratepages, compaction_alloc, @@ -547,6 +578,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) } +out: /* Release free pages and check accounting */ cc->nr_freepages -= release_freepages(&cc->freepages); VM_BUG_ON(cc->nr_freepages != 0); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 615d974..81532f2 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2234,11 +2234,8 @@ static void khugepaged_loop(void) while (likely(khugepaged_enabled())) { #ifndef CONFIG_NUMA hpage = khugepaged_alloc_hugepage(); - if (unlikely(!hpage)) { - count_vm_event(THP_COLLAPSE_ALLOC_FAILED); + if (unlikely(!hpage)) break; - } - count_vm_event(THP_COLLAPSE_ALLOC); #else if (IS_ERR(hpage)) { khugepaged_alloc_sleep(); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6402458..bfcf153 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1111,6 +1111,14 @@ static void __init gather_bootmem_prealloc(void) WARN_ON(page_count(page) != 1); prep_compound_huge_page(page, h->order); prep_new_huge_page(h, page, page_to_nid(page)); + /* + * If we had gigantic hugepages allocated at boot time, we need + * to restore the 'stolen' pages to totalram_pages in order to + * fix confusing memory reports from free(1) and another + * side-effects, like CommitLimit going negative. + */ + if (h->order > (MAX_ORDER - 1)) + totalram_pages += 1 << h->order; } } @@ -1302,6 +1302,12 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page) slot = list_entry(slot->mm_list.next, struct mm_slot, mm_list); ksm_scan.mm_slot = slot; spin_unlock(&ksm_mmlist_lock); + /* + * Although we tested list_empty() above, a racing __ksm_exit + * of the last mm on the list may have removed it since then. + */ + if (slot == &ksm_mm_head) + return NULL; next_mm: ksm_scan.address = 0; ksm_scan.rmap_list = &slot->rmap_list; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bd9052a..cf7d027 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -359,7 +359,7 @@ enum charge_type { static void mem_cgroup_get(struct mem_cgroup *mem); static void mem_cgroup_put(struct mem_cgroup *mem); static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem); -static void drain_all_stock_async(void); +static void drain_all_stock_async(struct mem_cgroup *mem); static struct mem_cgroup_per_zone * mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid) @@ -735,7 +735,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) struct mem_cgroup, css); } -static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) +struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) { struct mem_cgroup *mem = NULL; @@ -1663,15 +1663,21 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, excess = res_counter_soft_limit_excess(&root_mem->res) >> PAGE_SHIFT; /* If memsw_is_minimum==1, swap-out is of-no-use. */ - if (root_mem->memsw_is_minimum) + if (!check_soft && root_mem->memsw_is_minimum) noswap = true; while (1) { victim = mem_cgroup_select_victim(root_mem); if (victim == root_mem) { loop++; - if (loop >= 1) - drain_all_stock_async(); + /* + * We are not draining per cpu cached charges during + * soft limit reclaim because global reclaim doesn't + * care about charges. It tries to free some memory and + * charges will not give any. + */ + if (!check_soft && loop >= 1) + drain_all_stock_async(root_mem); if (loop >= 2) { /* * If we have not been able to reclaim @@ -1934,9 +1940,11 @@ struct memcg_stock_pcp { struct mem_cgroup *cached; /* this never be root cgroup */ unsigned int nr_pages; struct work_struct work; + unsigned long flags; +#define FLUSHING_CACHED_CHARGE (0) }; static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock); -static atomic_t memcg_drain_count; +static DEFINE_MUTEX(percpu_charge_mutex); /* * Try to consume stocked charge on this cpu. If success, one page is consumed @@ -1984,6 +1992,7 @@ static void drain_local_stock(struct work_struct *dummy) { struct memcg_stock_pcp *stock = &__get_cpu_var(memcg_stock); drain_stock(stock); + clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags); } /* @@ -2008,26 +2017,45 @@ static void refill_stock(struct mem_cgroup *mem, unsigned int nr_pages) * expects some charges will be back to res_counter later but cannot wait for * it. */ -static void drain_all_stock_async(void) +static void drain_all_stock_async(struct mem_cgroup *root_mem) { - int cpu; - /* This function is for scheduling "drain" in asynchronous way. - * The result of "drain" is not directly handled by callers. Then, - * if someone is calling drain, we don't have to call drain more. - * Anyway, WORK_STRUCT_PENDING check in queue_work_on() will catch if - * there is a race. We just do loose check here. + int cpu, curcpu; + /* + * If someone calls draining, avoid adding more kworker runs. */ - if (atomic_read(&memcg_drain_count)) + if (!mutex_trylock(&percpu_charge_mutex)) return; /* Notify other cpus that system-wide "drain" is running */ - atomic_inc(&memcg_drain_count); get_online_cpus(); + /* + * Get a hint for avoiding draining charges on the current cpu, + * which must be exhausted by our charging. It is not required that + * this be a precise check, so we use raw_smp_processor_id() instead of + * getcpu()/putcpu(). + */ + curcpu = raw_smp_processor_id(); for_each_online_cpu(cpu) { struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); - schedule_work_on(cpu, &stock->work); + struct mem_cgroup *mem; + + if (cpu == curcpu) + continue; + + mem = stock->cached; + if (!mem) + continue; + if (mem != root_mem) { + if (!root_mem->use_hierarchy) + continue; + /* check whether "mem" is under tree of "root_mem" */ + if (!css_is_ancestor(&mem->css, &root_mem->css)) + continue; + } + if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) + schedule_work_on(cpu, &stock->work); } put_online_cpus(); - atomic_dec(&memcg_drain_count); + mutex_unlock(&percpu_charge_mutex); /* We don't wait for flush_work */ } @@ -2035,9 +2063,9 @@ static void drain_all_stock_async(void) static void drain_all_stock_sync(void) { /* called when force_empty is called */ - atomic_inc(&memcg_drain_count); + mutex_lock(&percpu_charge_mutex); schedule_on_each_cpu(drain_local_stock); - atomic_dec(&memcg_drain_count); + mutex_unlock(&percpu_charge_mutex); } /* @@ -4640,6 +4668,7 @@ static struct cftype mem_cgroup_files[] = { { .name = "numa_stat", .open = mem_control_numa_stat_open, + .mode = S_IRUGO, }, #endif }; @@ -5414,18 +5443,16 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss, struct cgroup *old_cont, struct task_struct *p) { - struct mm_struct *mm; + struct mm_struct *mm = get_task_mm(p); - if (!mc.to) - /* no need to move charge */ - return; - - mm = get_task_mm(p); if (mm) { - mem_cgroup_move_charge(mm); + if (mc.to) + mem_cgroup_move_charge(mm); + put_swap_token(mm); mmput(mm); } - mem_cgroup_clear_mc(); + if (mc.to) + mem_cgroup_clear_mc(); } #else /* !CONFIG_MMU */ static int mem_cgroup_can_attach(struct cgroup_subsys *ss, diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 5c8f7e0..eac0ba5 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -52,6 +52,7 @@ #include <linux/swapops.h> #include <linux/hugetlb.h> #include <linux/memory_hotplug.h> +#include <linux/mm_inline.h> #include "internal.h" int sysctl_memory_failure_early_kill __read_mostly = 0; @@ -1468,7 +1469,8 @@ int soft_offline_page(struct page *page, int flags) put_page(page); if (!ret) { LIST_HEAD(pagelist); - + inc_zone_page_state(page, NR_ISOLATED_ANON + + page_is_file_cache(page)); list_add(&page->lru, &pagelist); ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0, true); diff --git a/mm/memory.c b/mm/memory.c index 6953d39..87d9353 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1112,11 +1112,13 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, int force_flush = 0; int rss[NR_MM_COUNTERS]; spinlock_t *ptl; + pte_t *start_pte; pte_t *pte; again: init_rss_vec(rss); - pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + pte = start_pte; arch_enter_lazy_mmu_mode(); do { pte_t ptent = *pte; @@ -1196,7 +1198,7 @@ again: add_mm_rss_vec(mm, rss); arch_leave_lazy_mmu_mode(); - pte_unmap_unlock(pte - 1, ptl); + pte_unmap_unlock(start_pte, ptl); /* * mmu_gather ran out of room to batch pages, we break out of @@ -1296,7 +1298,7 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb, /** * unmap_vmas - unmap a range of memory covered by a list of vma's - * @tlbp: address of the caller's struct mmu_gather + * @tlb: address of the caller's struct mmu_gather * @vma: the starting vma * @start_addr: virtual address at which to start unmapping * @end_addr: virtual address at which to end unmapping diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9f64637..02159c7 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -494,6 +494,12 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) /* init node's zones as empty zones, we don't have any present pages.*/ free_area_init_node(nid, zones_size, start_pfn, zholes_size); + /* + * The node we allocated has no zone fallback lists. For avoiding + * to access not-initialized zonelist, build here. + */ + build_all_zonelists(NULL); + return pgdat; } @@ -906,14 +906,7 @@ struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma) if (anon_vma) return anon_vma; try_prev: - /* - * It is potentially slow to have to call find_vma_prev here. - * But it's only on the first write fault on the vma, not - * every time, and we could devise a way to avoid it later - * (e.g. stash info in next's anon_vma_node when assigning - * an anon_vma, or when trying vma_merge). Another time. - */ - BUG_ON(find_vma_prev(vma->vm_mm, vma->vm_start, &near) != vma); + near = vma->vm_prev; if (!near) goto none; @@ -2044,9 +2037,10 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) return -EINVAL; /* Find the first overlapping VMA */ - vma = find_vma_prev(mm, start, &prev); + vma = find_vma(mm, start); if (!vma) return 0; + prev = vma->vm_prev; /* we have start < vma->vm_end */ /* if it doesn't overlap, we have nothing.. */ diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 74ccff6..53bffc6 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -162,13 +162,13 @@ static void free_page_cgroup(void *addr) } #endif -static int __meminit init_section_page_cgroup(unsigned long pfn) +static int __meminit init_section_page_cgroup(unsigned long pfn, int nid) { struct page_cgroup *base, *pc; struct mem_section *section; unsigned long table_size; unsigned long nr; - int nid, index; + int index; nr = pfn_to_section_nr(pfn); section = __nr_to_section(nr); @@ -176,7 +176,6 @@ static int __meminit init_section_page_cgroup(unsigned long pfn) if (section->page_cgroup) return 0; - nid = page_to_nid(pfn_to_page(pfn)); table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION; base = alloc_page_cgroup(table_size, nid); @@ -196,7 +195,11 @@ static int __meminit init_section_page_cgroup(unsigned long pfn) pc = base + index; init_page_cgroup(pc, nr); } - + /* + * The passed "pfn" may not be aligned to SECTION. For the calculation + * we need to apply a mask. + */ + pfn &= PAGE_SECTION_MASK; section->page_cgroup = base - pfn; total_usage += table_size; return 0; @@ -225,10 +228,20 @@ int __meminit online_page_cgroup(unsigned long start_pfn, start = start_pfn & ~(PAGES_PER_SECTION - 1); end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION); + if (nid == -1) { + /* + * In this case, "nid" already exists and contains valid memory. + * "start_pfn" passed to us is a pfn which is an arg for + * online__pages(), and start_pfn should exist. + */ + nid = pfn_to_nid(start_pfn); + VM_BUG_ON(!node_state(nid, N_ONLINE)); + } + for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) { if (!pfn_present(pfn)) continue; - fail = init_section_page_cgroup(pfn); + fail = init_section_page_cgroup(pfn, nid); } if (!fail) return 0; @@ -284,25 +297,47 @@ static int __meminit page_cgroup_callback(struct notifier_block *self, void __init page_cgroup_init(void) { unsigned long pfn; - int fail = 0; + int nid; if (mem_cgroup_disabled()) return; - for (pfn = 0; !fail && pfn < max_pfn; pfn += PAGES_PER_SECTION) { - if (!pfn_present(pfn)) - continue; - fail = init_section_page_cgroup(pfn); - } - if (fail) { - printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n"); - panic("Out of memory"); - } else { - hotplug_memory_notifier(page_cgroup_callback, 0); + for_each_node_state(nid, N_HIGH_MEMORY) { + unsigned long start_pfn, end_pfn; + + start_pfn = node_start_pfn(nid); + end_pfn = node_end_pfn(nid); + /* + * start_pfn and end_pfn may not be aligned to SECTION and the + * page->flags of out of node pages are not initialized. So we + * scan [start_pfn, the biggest section's pfn < end_pfn) here. + */ + for (pfn = start_pfn; + pfn < end_pfn; + pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) { + + if (!pfn_valid(pfn)) + continue; + /* + * Nodes's pfns can be overlapping. + * We know some arch can have a nodes layout such as + * -------------pfn--------------> + * N0 | N1 | N2 | N0 | N1 | N2|.... + */ + if (pfn_to_nid(pfn) != nid) + continue; + if (init_section_page_cgroup(pfn, nid)) + goto oom; + } } + hotplug_memory_notifier(page_cgroup_callback, 0); printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage); - printk(KERN_INFO "please try 'cgroup_disable=memory' option if you don't" - " want memory cgroups\n"); + printk(KERN_INFO "please try 'cgroup_disable=memory' option if you " + "don't want memory cgroups\n"); + return; +oom: + printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n"); + panic("Out of memory"); } void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat) diff --git a/mm/thrash.c b/mm/thrash.c index 2372d4e..fabf2d0 100644 --- a/mm/thrash.c +++ b/mm/thrash.c @@ -21,14 +21,40 @@ #include <linux/mm.h> #include <linux/sched.h> #include <linux/swap.h> +#include <linux/memcontrol.h> + +#include <trace/events/vmscan.h> + +#define TOKEN_AGING_INTERVAL (0xFF) static DEFINE_SPINLOCK(swap_token_lock); struct mm_struct *swap_token_mm; +struct mem_cgroup *swap_token_memcg; static unsigned int global_faults; +static unsigned int last_aging; + +#ifdef CONFIG_CGROUP_MEM_RES_CTLR +static struct mem_cgroup *swap_token_memcg_from_mm(struct mm_struct *mm) +{ + struct mem_cgroup *memcg; + + memcg = try_get_mem_cgroup_from_mm(mm); + if (memcg) + css_put(mem_cgroup_css(memcg)); + + return memcg; +} +#else +static struct mem_cgroup *swap_token_memcg_from_mm(struct mm_struct *mm) +{ + return NULL; +} +#endif void grab_swap_token(struct mm_struct *mm) { int current_interval; + unsigned int old_prio = mm->token_priority; global_faults++; @@ -38,40 +64,81 @@ void grab_swap_token(struct mm_struct *mm) return; /* First come first served */ - if (swap_token_mm == NULL) { - mm->token_priority = mm->token_priority + 2; - swap_token_mm = mm; - goto out; + if (!swap_token_mm) + goto replace_token; + + if ((global_faults - last_aging) > TOKEN_AGING_INTERVAL) { + swap_token_mm->token_priority /= 2; + last_aging = global_faults; } - if (mm != swap_token_mm) { - if (current_interval < mm->last_interval) - mm->token_priority++; - else { - if (likely(mm->token_priority > 0)) - mm->token_priority--; - } - /* Check if we deserve the token */ - if (mm->token_priority > swap_token_mm->token_priority) { - mm->token_priority += 2; - swap_token_mm = mm; - } - } else { - /* Token holder came in again! */ + if (mm == swap_token_mm) { mm->token_priority += 2; + goto update_priority; + } + + if (current_interval < mm->last_interval) + mm->token_priority++; + else { + if (likely(mm->token_priority > 0)) + mm->token_priority--; } + /* Check if we deserve the token */ + if (mm->token_priority > swap_token_mm->token_priority) + goto replace_token; + +update_priority: + trace_update_swap_token_priority(mm, old_prio, swap_token_mm); + out: mm->faultstamp = global_faults; mm->last_interval = current_interval; spin_unlock(&swap_token_lock); + return; + +replace_token: + mm->token_priority += 2; + trace_replace_swap_token(swap_token_mm, mm); + swap_token_mm = mm; + swap_token_memcg = swap_token_memcg_from_mm(mm); + last_aging = global_faults; + goto out; } /* Called on process exit. */ void __put_swap_token(struct mm_struct *mm) { spin_lock(&swap_token_lock); - if (likely(mm == swap_token_mm)) + if (likely(mm == swap_token_mm)) { + trace_put_swap_token(swap_token_mm); swap_token_mm = NULL; + swap_token_memcg = NULL; + } spin_unlock(&swap_token_lock); } + +static bool match_memcg(struct mem_cgroup *a, struct mem_cgroup *b) +{ + if (!a) + return true; + if (!b) + return true; + if (a == b) + return true; + return false; +} + +void disable_swap_token(struct mem_cgroup *memcg) +{ + /* memcg reclaim don't disable unrelated mm token. */ + if (match_memcg(memcg, swap_token_memcg)) { + spin_lock(&swap_token_lock); + if (match_memcg(memcg, swap_token_memcg)) { + trace_disable_swap_token(swap_token_mm); + swap_token_mm = NULL; + swap_token_memcg = NULL; + } + spin_unlock(&swap_token_lock); + } +} diff --git a/mm/vmscan.c b/mm/vmscan.c index faa0a08..8ff834e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1124,8 +1124,20 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, nr_lumpy_dirty++; scan++; } else { - /* the page is freed already. */ - if (!page_count(cursor_page)) + /* + * Check if the page is freed already. + * + * We can't use page_count() as that + * requires compound_head and we don't + * have a pin on the page here. If a + * page is tail, we may or may not + * have isolated the head, so assume + * it's not free, it'd be tricky to + * track the head status without a + * page pin. + */ + if (!PageTail(cursor_page) && + !atomic_read(&cursor_page->_count)) continue; break; } @@ -2081,7 +2093,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, for (priority = DEF_PRIORITY; priority >= 0; priority--) { sc->nr_scanned = 0; if (!priority) - disable_swap_token(); + disable_swap_token(sc->mem_cgroup); total_scanned += shrink_zones(priority, zonelist, sc); /* * Don't shrink slabs when reclaiming memory from @@ -2407,7 +2419,7 @@ loop_again: /* The swap token gets in the way of swapout... */ if (!priority) - disable_swap_token(); + disable_swap_token(NULL); all_zones_ok = 1; balanced = 0; diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 8657f99..b0aa2c6 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -1943,6 +1943,11 @@ sub process { WARN("LINUX_VERSION_CODE should be avoided, code should be for the version to which it is merged\n" . $herecurr); } +# check for uses of printk_ratelimit + if ($line =~ /\bprintk_ratelimit\s*\(/) { + WARN("Prefer printk_ratelimited or pr_<level>_ratelimited to printk_ratelimit\n" . $herecurr); + } + # printk should use KERN_* levels. Note that follow on printk's on the # same line do not need a level, so we use the current block context # to try and find and validate the current printk. In summary the current |