diff options
81 files changed, 919 insertions, 545 deletions
diff --git a/Documentation/accounting/cgroupstats.txt b/Documentation/accounting/cgroupstats.txt index eda40fd39cad..d16a9849e60e 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 465351d4cf85..cd45c8ea7463 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 0ed99f08f1f3..cd67e90003c0 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 8b930946c52a..9ad85df4b983 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 98a30829af7a..5b0d78e55ccc 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 57ca4c89fe5c..16624a7f8222 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 41f37fea1276..c21d77742a07 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 510d64570d60..06eb6d957c83 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: @@ -182,7 +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. @@ -214,7 +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 @@ -264,16 +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.) @@ -281,11 +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 @@ -490,13 +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/kmemleak.txt b/Documentation/kmemleak.txt index 090e6ee04536..51063e681ca4 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 1b5a5ddbc3ef..5df176ed59b8 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 99961993257a..91ecff07cede 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 605b0d40329d..71b54d549987 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 12f9ba20ccb7..550068466605 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 @@ -1526,7 +1526,8 @@ quiet_cmd_rmfiles = $(if $(wildcard $(rm-files)),CLEAN $(wildcard $(rm-files)) # Run depmod only if we have System.map and depmod is executable quiet_cmd_depmod = DEPMOD $(KERNELRELEASE) - cmd_depmod = $(srctree)/scripts/depmod.sh $(DEPMOD) $(KERNELRELEASE) + cmd_depmod = $(CONFIG_SHELL) $(srctree)/scripts/depmod.sh $(DEPMOD) \ + $(KERNELRELEASE) # Create temporary dir for module support files # clean it up only when building all modules diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index f9da41921c52..942fad97e447 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/kernel/devtree.c b/arch/arm/kernel/devtree.c index a701e4226a6c..0cdd7b456cb2 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 e8d885676807..90c62cd51ca9 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 1e7b04a40a31..b2a27b6b0046 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 d52eec268b47..6807cb1e76dd 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 4e66881c7aee..fc4e98ea7543 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 8f4f736aa267..806a2f02b980 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 a0b838894ac9..e7221398e5af 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 5f1f9867fc70..121ad1d4fa39 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 30b971d65815..1be2eeb7a0a0 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 65157a35dbba..54add60f94c9 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-shmobile/board-ag5evm.c b/arch/arm/mach-shmobile/board-ag5evm.c index c95258c274c1..1e2aba23e0d6 100644 --- a/arch/arm/mach-shmobile/board-ag5evm.c +++ b/arch/arm/mach-shmobile/board-ag5evm.c @@ -382,10 +382,8 @@ void ag5evm_sdhi1_set_pwr(struct platform_device *pdev, int state) } static struct sh_mobile_sdhi_info sh_sdhi1_platdata = { - .dma_slave_tx = SHDMA_SLAVE_SDHI1_TX, - .dma_slave_rx = SHDMA_SLAVE_SDHI1_RX, .tmio_flags = TMIO_MMC_WRPROTECT_DISABLE, - .tmio_caps = MMC_CAP_NONREMOVABLE, + .tmio_caps = MMC_CAP_NONREMOVABLE | MMC_CAP_SDIO_IRQ, .tmio_ocr_mask = MMC_VDD_32_33 | MMC_VDD_33_34, .set_pwr = ag5evm_sdhi1_set_pwr, }; diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c index 776f20560e72..7e1d37584321 100644 --- a/arch/arm/mach-shmobile/board-mackerel.c +++ b/arch/arm/mach-shmobile/board-mackerel.c @@ -126,7 +126,7 @@ * ------+--------------------+--------------------+------- * IRQ0 | ICR1A.IRQ0SA=0010 | SDHI2 card detect | Low * IRQ6 | ICR1A.IRQ6SA=0011 | Ether(LAN9220) | High - * IRQ7 | ICR1A.IRQ7SA=0010 | LCD Tuch Panel | Low + * IRQ7 | ICR1A.IRQ7SA=0010 | LCD Touch Panel | Low * IRQ8 | ICR2A.IRQ8SA=0010 | MMC/SD card detect | Low * IRQ9 | ICR2A.IRQ9SA=0010 | KEY(TCA6408) | Low * IRQ21 | ICR4A.IRQ21SA=0011 | Sensor(ADXL345) | High @@ -165,10 +165,10 @@ * USB1 can become Host by r8a66597, and become Function by renesas_usbhs. * But don't select both drivers in same time. * These uses same IRQ number for request_irq(), and aren't supporting - * IRQF_SHARD / IORESOURCE_IRQ_SHAREABLE. + * IRQF_SHARED / IORESOURCE_IRQ_SHAREABLE. * * Actually these are old/new version of USB driver. - * This mean its register will be broken if it supports SHARD IRQ, + * This mean its register will be broken if it supports shared IRQ, */ /* @@ -562,7 +562,121 @@ out: clk_put(hdmi_ick); } -/* USB1 (Host) */ +/* USBHS0 is connected to CN22 which takes a USB Mini-B plug + * + * The sh7372 SoC has IRQ7 set aside for USBHS0 hotplug, + * but on this particular board IRQ7 is already used by + * the touch screen. This leaves us with software polling. + */ +#define USBHS0_POLL_INTERVAL (HZ * 5) + +struct usbhs_private { + unsigned int usbphyaddr; + unsigned int usbcrcaddr; + struct renesas_usbhs_platform_info info; + struct delayed_work work; + struct platform_device *pdev; +}; + +#define usbhs_get_priv(pdev) \ + container_of(renesas_usbhs_get_info(pdev), \ + struct usbhs_private, info) + +#define usbhs_is_connected(priv) \ + (!((1 << 7) & __raw_readw(priv->usbcrcaddr))) + +static int usbhs_get_vbus(struct platform_device *pdev) +{ + return usbhs_is_connected(usbhs_get_priv(pdev)); +} + +static void usbhs_phy_reset(struct platform_device *pdev) +{ + struct usbhs_private *priv = usbhs_get_priv(pdev); + + /* init phy */ + __raw_writew(0x8a0a, priv->usbcrcaddr); +} + +static int usbhs0_get_id(struct platform_device *pdev) +{ + return USBHS_GADGET; +} + +static void usbhs0_work_function(struct work_struct *work) +{ + struct usbhs_private *priv = container_of(work, struct usbhs_private, + work.work); + + renesas_usbhs_call_notify_hotplug(priv->pdev); + schedule_delayed_work(&priv->work, USBHS0_POLL_INTERVAL); +} + +static int usbhs0_hardware_init(struct platform_device *pdev) +{ + struct usbhs_private *priv = usbhs_get_priv(pdev); + + priv->pdev = pdev; + INIT_DELAYED_WORK(&priv->work, usbhs0_work_function); + schedule_delayed_work(&priv->work, USBHS0_POLL_INTERVAL); + return 0; +} + +static void usbhs0_hardware_exit(struct platform_device *pdev) +{ + struct usbhs_private *priv = usbhs_get_priv(pdev); + + cancel_delayed_work_sync(&priv->work); +} + +static struct usbhs_private usbhs0_private = { + .usbcrcaddr = 0xe605810c, /* USBCR2 */ + .info = { + .platform_callback = { + .hardware_init = usbhs0_hardware_init, + .hardware_exit = usbhs0_hardware_exit, + .phy_reset = usbhs_phy_reset, + .get_id = usbhs0_get_id, + .get_vbus = usbhs_get_vbus, + }, + .driver_param = { + .buswait_bwait = 4, + }, + }, +}; + +static struct resource usbhs0_resources[] = { + [0] = { + .name = "USBHS0", + .start = 0xe6890000, + .end = 0xe68900e6 - 1, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = evt2irq(0x1ca0) /* USB0_USB0I0 */, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device usbhs0_device = { + .name = "renesas_usbhs", + .id = 0, + .dev = { + .platform_data = &usbhs0_private.info, + }, + .num_resources = ARRAY_SIZE(usbhs0_resources), + .resource = usbhs0_resources, +}; + +/* USBHS1 is connected to CN31 which takes a USB Mini-AB plug + * + * Use J30 to select between Host and Function. This setting + * can however not be detected by software. Hotplug of USBHS1 + * is provided via IRQ8. + */ +#define IRQ8 evt2irq(0x0300) + +/* USBHS1 USB Host support via r8a66597_hcd */ static void usb1_host_port_power(int port, int power) { if (!power) /* only power-on is supported for now */ @@ -579,9 +693,9 @@ static struct r8a66597_platdata usb1_host_data = { static struct resource usb1_host_resources[] = { [0] = { - .name = "USBHS", - .start = 0xE68B0000, - .end = 0xE68B00E6 - 1, + .name = "USBHS1", + .start = 0xe68b0000, + .end = 0xe68b00e6 - 1, .flags = IORESOURCE_MEM, }, [1] = { @@ -602,37 +716,14 @@ static struct platform_device usb1_host_device = { .resource = usb1_host_resources, }; -/* USB1 (Function) */ +/* USBHS1 USB Function support via renesas_usbhs */ + #define USB_PHY_MODE (1 << 4) #define USB_PHY_INT_EN ((1 << 3) | (1 << 2)) #define USB_PHY_ON (1 << 1) #define USB_PHY_OFF (1 << 0) #define USB_PHY_INT_CLR (USB_PHY_ON | USB_PHY_OFF) -struct usbhs_private { - unsigned int irq; - unsigned int usbphyaddr; - unsigned int usbcrcaddr; - struct renesas_usbhs_platform_info info; -}; - -#define usbhs_get_priv(pdev) \ - container_of(renesas_usbhs_get_info(pdev), \ - struct usbhs_private, info) - -#define usbhs_is_connected(priv) \ - (!((1 << 7) & __raw_readw(priv->usbcrcaddr))) - -static int usbhs1_get_id(struct platform_device *pdev) -{ - return USBHS_GADGET; -} - -static int usbhs1_get_vbus(struct platform_device *pdev) -{ - return usbhs_is_connected(usbhs_get_priv(pdev)); -} - static irqreturn_t usbhs1_interrupt(int irq, void *data) { struct platform_device *pdev = data; @@ -654,12 +745,10 @@ static int usbhs1_hardware_init(struct platform_device *pdev) struct usbhs_private *priv = usbhs_get_priv(pdev); int ret; - irq_set_irq_type(priv->irq, IRQ_TYPE_LEVEL_HIGH); - /* clear interrupt status */ __raw_writew(USB_PHY_MODE | USB_PHY_INT_CLR, priv->usbphyaddr); - ret = request_irq(priv->irq, usbhs1_interrupt, 0, + ret = request_irq(IRQ8, usbhs1_interrupt, IRQF_TRIGGER_HIGH, dev_name(&pdev->dev), pdev); if (ret) { dev_err(&pdev->dev, "request_irq err\n"); @@ -679,15 +768,12 @@ static void usbhs1_hardware_exit(struct platform_device *pdev) /* clear interrupt status */ __raw_writew(USB_PHY_MODE | USB_PHY_INT_CLR, priv->usbphyaddr); - free_irq(priv->irq, pdev); + free_irq(IRQ8, pdev); } -static void usbhs1_phy_reset(struct platform_device *pdev) +static int usbhs1_get_id(struct platform_device *pdev) { - struct usbhs_private *priv = usbhs_get_priv(pdev); - - /* init phy */ - __raw_writew(0x8a0a, priv->usbcrcaddr); + return USBHS_GADGET; } static u32 usbhs1_pipe_cfg[] = { @@ -710,16 +796,15 @@ static u32 usbhs1_pipe_cfg[] = { }; static struct usbhs_private usbhs1_private = { - .irq = evt2irq(0x0300), /* IRQ8 */ - .usbphyaddr = 0xE60581E2, /* USBPHY1INTAP */ - .usbcrcaddr = 0xE6058130, /* USBCR4 */ + .usbphyaddr = 0xe60581e2, /* USBPHY1INTAP */ + .usbcrcaddr = 0xe6058130, /* USBCR4 */ .info = { .platform_callback = { .hardware_init = usbhs1_hardware_init, .hardware_exit = usbhs1_hardware_exit, - .phy_reset = usbhs1_phy_reset, .get_id = usbhs1_get_id, - .get_vbus = usbhs1_get_vbus, + .phy_reset = usbhs_phy_reset, + .get_vbus = usbhs_get_vbus, }, .driver_param = { .buswait_bwait = 4, @@ -731,9 +816,9 @@ static struct usbhs_private usbhs1_private = { static struct resource usbhs1_resources[] = { [0] = { - .name = "USBHS", - .start = 0xE68B0000, - .end = 0xE68B00E6 - 1, + .name = "USBHS1", + .start = 0xe68b0000, + .end = 0xe68b00e6 - 1, .flags = IORESOURCE_MEM, }, [1] = { @@ -752,7 +837,6 @@ static struct platform_device usbhs1_device = { .resource = usbhs1_resources, }; - /* LED */ static struct gpio_led mackerel_leds[] = { { @@ -1203,6 +1287,7 @@ static struct platform_device *mackerel_devices[] __initdata = { &nor_flash_device, &smc911x_device, &lcdc_device, + &usbhs0_device, &usb1_host_device, &usbhs1_device, &leds_device, @@ -1301,6 +1386,7 @@ static void __init mackerel_map_io(void) #define GPIO_PORT9CR 0xE6051009 #define GPIO_PORT10CR 0xE605100A +#define GPIO_PORT167CR 0xE60520A7 #define GPIO_PORT168CR 0xE60520A8 #define SRCR4 0xe61580bc #define USCCR1 0xE6058144 @@ -1354,17 +1440,17 @@ static void __init mackerel_init(void) gpio_request(GPIO_PORT151, NULL); /* LCDDON */ gpio_direction_output(GPIO_PORT151, 1); - /* USB enable */ - gpio_request(GPIO_FN_VBUS0_1, NULL); - gpio_request(GPIO_FN_IDIN_1_18, NULL); - gpio_request(GPIO_FN_PWEN_1_115, NULL); - gpio_request(GPIO_FN_OVCN_1_114, NULL); - gpio_request(GPIO_FN_EXTLP_1, NULL); - gpio_request(GPIO_FN_OVCN2_1, NULL); - gpio_pull_down(GPIO_PORT168CR); - - /* setup USB phy */ - __raw_writew(0x8a0a, 0xE6058130); /* USBCR4 */ + /* USBHS0 */ + gpio_request(GPIO_FN_VBUS0_0, NULL); + gpio_pull_down(GPIO_PORT168CR); /* VBUS0_0 pull down */ + + /* USBHS1 */ + gpio_request(GPIO_FN_VBUS0_1, NULL); + gpio_pull_down(GPIO_PORT167CR); /* VBUS0_1 pull down */ + gpio_request(GPIO_FN_IDIN_1_113, NULL); + + /* USB phy tweak to make the r8a66597_hcd host driver work */ + __raw_writew(0x8a0a, 0xe6058130); /* USBCR4 */ /* enable FSI2 port A (ak4643) */ gpio_request(GPIO_FN_FSIAIBT, NULL); diff --git a/arch/arm/mach-shmobile/intc-sh73a0.c b/arch/arm/mach-shmobile/intc-sh73a0.c index 5d0e1503ece6..a911a60e7719 100644 --- a/arch/arm/mach-shmobile/intc-sh73a0.c +++ b/arch/arm/mach-shmobile/intc-sh73a0.c @@ -250,6 +250,11 @@ static irqreturn_t sh73a0_intcs_demux(int irq, void *dev_id) return IRQ_HANDLED; } +static int sh73a0_set_wake(struct irq_data *data, unsigned int on) +{ + return 0; /* always allow wakeup */ +} + void __init sh73a0_init_irq(void) { void __iomem *gic_dist_base = __io(0xf0001000); @@ -257,6 +262,7 @@ void __init sh73a0_init_irq(void) void __iomem *intevtsa = ioremap_nocache(0xffd20100, PAGE_SIZE); gic_init(0, 29, gic_dist_base, gic_cpu_base); + gic_arch_extn.irq_set_wake = sh73a0_set_wake; register_intc_controller(&intcs_desc); diff --git a/arch/arm/mach-shmobile/setup-sh7367.c b/arch/arm/mach-shmobile/setup-sh7367.c index 2c10190dbb55..e546017f15de 100644 --- a/arch/arm/mach-shmobile/setup-sh7367.c +++ b/arch/arm/mach-shmobile/setup-sh7367.c @@ -38,7 +38,7 @@ static struct plat_sci_port scif0_platform_data = { .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE, .scbrr_algo_id = SCBRR_ALGO_4, - .type = PORT_SCIF, + .type = PORT_SCIFA, .irqs = { evt2irq(0xc00), evt2irq(0xc00), evt2irq(0xc00), evt2irq(0xc00) }, }; @@ -57,7 +57,7 @@ static struct plat_sci_port scif1_platform_data = { .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE, .scbrr_algo_id = SCBRR_ALGO_4, - .type = PORT_SCIF, + .type = PORT_SCIFA, .irqs = { evt2irq(0xc20), evt2irq(0xc20), evt2irq(0xc20), evt2irq(0xc20) }, }; @@ -76,7 +76,7 @@ static struct plat_sci_port scif2_platform_data = { .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE, .scbrr_algo_id = SCBRR_ALGO_4, - .type = PORT_SCIF, + .type = PORT_SCIFA, .irqs = { evt2irq(0xc40), evt2irq(0xc40), evt2irq(0xc40), evt2irq(0xc40) }, }; @@ -95,7 +95,7 @@ static struct plat_sci_port scif3_platform_data = { .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE, .scbrr_algo_id = SCBRR_ALGO_4, - .type = PORT_SCIF, + .type = PORT_SCIFA, .irqs = { evt2irq(0xc60), evt2irq(0xc60), evt2irq(0xc60), evt2irq(0xc60) }, }; @@ -114,7 +114,7 @@ static struct plat_sci_port scif4_platform_data = { .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE, .scbrr_algo_id = SCBRR_ALGO_4, - .type = PORT_SCIF, + .type = PORT_SCIFA, .irqs = { evt2irq(0xd20), evt2irq(0xd20), evt2irq(0xd20), evt2irq(0xd20) }, }; @@ -133,7 +133,7 @@ static struct plat_sci_port scif5_platform_data = { .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE, .scbrr_algo_id = SCBRR_ALGO_4, - .type = PORT_SCIF, + .type = PORT_SCIFA, .irqs = { evt2irq(0xd40), evt2irq(0xd40), evt2irq(0xd40), evt2irq(0xd40) }, }; @@ -152,7 +152,7 @@ static struct plat_sci_port scif6_platform_data = { .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE, .scbrr_algo_id = SCBRR_ALGO_4, - .type = PORT_SCIF, + .type = PORT_SCIFB, .irqs = { evt2irq(0xd60), evt2irq(0xd60), evt2irq(0xd60), evt2irq(0xd60) }, }; diff --git a/arch/arm/mach-u300/clock.h b/arch/arm/mach-u300/clock.h index c34f3ea3017c..4f50ca8f901e 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 8b85df4c8d8f..035fdc9dbdb0 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 891cf44591e0..18d7fa0603c2 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 285edcd2da2a..9e6b93b1a043 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 8bfae964b133..b0ee9ba3cfab 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 2c2cce9cd8c8..c19571c40a21 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 e4c165ca6696..537ffcb0646d 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 7b7ebd4d096d..546b54da1005 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 b3b566ec83d3..3c3867850a30 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 3538b85ede91..b130f60ca6b7 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/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c index 3a32741cc0ac..513cb1a2e6c8 100644 --- a/arch/sh/boards/mach-ecovec24/setup.c +++ b/arch/sh/boards/mach-ecovec24/setup.c @@ -20,6 +20,7 @@ #include <linux/io.h> #include <linux/delay.h> #include <linux/usb/r8a66597.h> +#include <linux/usb/renesas_usbhs.h> #include <linux/i2c.h> #include <linux/i2c/tsc2007.h> #include <linux/spi/spi.h> @@ -232,6 +233,52 @@ static struct platform_device usb1_common_device = { .resource = usb1_common_resources, }; +/* + * USBHS + */ +static int usbhs_get_id(struct platform_device *pdev) +{ + return gpio_get_value(GPIO_PTB3); +} + +static struct renesas_usbhs_platform_info usbhs_info = { + .platform_callback = { + .get_id = usbhs_get_id, + }, + .driver_param = { + .buswait_bwait = 4, + .detection_delay = 5, + }, +}; + +static struct resource usbhs_resources[] = { + [0] = { + .start = 0xa4d90000, + .end = 0xa4d90124 - 1, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = 66, + .end = 66, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device usbhs_device = { + .name = "renesas_usbhs", + .id = 1, + .dev = { + .dma_mask = NULL, /* not use dma */ + .coherent_dma_mask = 0xffffffff, + .platform_data = &usbhs_info, + }, + .num_resources = ARRAY_SIZE(usbhs_resources), + .resource = usbhs_resources, + .archdata = { + .hwblk_id = HWBLK_USB1, + }, +}; + /* LCDC */ const static struct fb_videomode ecovec_lcd_modes[] = { { @@ -897,6 +944,7 @@ static struct platform_device *ecovec_devices[] __initdata = { &sh_eth_device, &usb0_host_device, &usb1_common_device, + &usbhs_device, &lcdc_device, &ceu0_device, &ceu1_device, diff --git a/arch/sh/boot/compressed/Makefile b/arch/sh/boot/compressed/Makefile index 780e083e4d17..23bc849d9c64 100644 --- a/arch/sh/boot/compressed/Makefile +++ b/arch/sh/boot/compressed/Makefile @@ -27,8 +27,6 @@ IMAGE_OFFSET := $(shell /bin/bash -c 'printf "0x%08x" \ $(CONFIG_BOOT_LINK_OFFSET)]') endif -LIBGCC := $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name) - ifeq ($(CONFIG_MCOUNT),y) ORIG_CFLAGS := $(KBUILD_CFLAGS) KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS)) @@ -37,7 +35,25 @@ endif LDFLAGS_vmlinux := --oformat $(ld-bfd) -Ttext $(IMAGE_OFFSET) -e startup \ -T $(obj)/../../kernel/vmlinux.lds -$(obj)/vmlinux: $(OBJECTS) $(obj)/piggy.o $(LIBGCC) FORCE +# +# Pull in the necessary libgcc bits from the in-kernel implementation. +# +lib1funcs-$(CONFIG_SUPERH32) := ashiftrt.S ashldi3.c ashrsi3.S ashlsi3.S \ + lshrsi3.S +lib1funcs-obj := \ + $(addsuffix .o, $(basename $(addprefix $(obj)/, $(lib1funcs-y)))) + +lib1funcs-dir := $(srctree)/arch/$(SRCARCH)/lib +ifeq ($(BITS),64) + lib1funcs-dir := $(addsuffix $(BITS), $(lib1funcs-dir)) +endif + +KBUILD_CFLAGS += -I$(lib1funcs-dir) + +$(addprefix $(obj)/,$(lib1funcs-y)): $(obj)/%: $(lib1funcs-dir)/% FORCE + $(call cmd,shipped) + +$(obj)/vmlinux: $(OBJECTS) $(obj)/piggy.o $(lib1funcs-obj) FORCE $(call if_changed,ld) @: diff --git a/arch/sh/include/asm/cmpxchg-grb.h b/arch/sh/include/asm/cmpxchg-grb.h index 4676bf57693a..f848dec9e483 100644 --- a/arch/sh/include/asm/cmpxchg-grb.h +++ b/arch/sh/include/asm/cmpxchg-grb.h @@ -15,8 +15,9 @@ static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val) " mov.l %2, @%1 \n\t" /* store new value */ "1: mov r1, r15 \n\t" /* LOGOUT */ : "=&r" (retval), - "+r" (m) - : "r" (val) + "+r" (m), + "+r" (val) /* inhibit r15 overloading */ + : : "memory", "r0", "r1"); return retval; @@ -36,8 +37,9 @@ static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val) " mov.b %2, @%1 \n\t" /* store new value */ "1: mov r1, r15 \n\t" /* LOGOUT */ : "=&r" (retval), - "+r" (m) - : "r" (val) + "+r" (m), + "+r" (val) /* inhibit r15 overloading */ + : : "memory" , "r0", "r1"); return retval; @@ -54,13 +56,14 @@ static inline unsigned long __cmpxchg_u32(volatile int *m, unsigned long old, " nop \n\t" " mov r15, r1 \n\t" /* r1 = saved sp */ " mov #-8, r15 \n\t" /* LOGIN */ - " mov.l @%1, %0 \n\t" /* load old value */ - " cmp/eq %0, %2 \n\t" + " mov.l @%3, %0 \n\t" /* load old value */ + " cmp/eq %0, %1 \n\t" " bf 1f \n\t" /* if not equal */ - " mov.l %3, @%1 \n\t" /* store new value */ + " mov.l %2, @%3 \n\t" /* store new value */ "1: mov r1, r15 \n\t" /* LOGOUT */ - : "=&r" (retval) - : "r" (m), "r" (old), "r" (new) + : "=&r" (retval), + "+r" (old), "+r" (new) /* old or new can be r15 */ + : "r" (m) : "memory" , "r0", "r1", "t"); return retval; diff --git a/arch/sh/include/asm/processor_64.h b/arch/sh/include/asm/processor_64.h index 2a541ddb5a1b..e25c4c7d6b63 100644 --- a/arch/sh/include/asm/processor_64.h +++ b/arch/sh/include/asm/processor_64.h @@ -150,7 +150,6 @@ struct thread_struct { #define SR_USER (SR_MMU | SR_FD) #define start_thread(_regs, new_pc, new_sp) \ - set_fs(USER_DS); \ _regs->sr = SR_USER; /* User mode. */ \ _regs->pc = new_pc - 4; /* Compensate syscall exit */ \ _regs->pc |= 1; /* Set SHmedia ! */ \ diff --git a/arch/sh/include/cpu-sh4/cpu/sh7724.h b/arch/sh/include/cpu-sh4/cpu/sh7724.h index 3daef8ecbc63..cbc47e6bcab5 100644 --- a/arch/sh/include/cpu-sh4/cpu/sh7724.h +++ b/arch/sh/include/cpu-sh4/cpu/sh7724.h @@ -298,6 +298,14 @@ enum { SHDMA_SLAVE_SCIF4_RX, SHDMA_SLAVE_SCIF5_TX, SHDMA_SLAVE_SCIF5_RX, + SHDMA_SLAVE_USB0D0_TX, + SHDMA_SLAVE_USB0D0_RX, + SHDMA_SLAVE_USB0D1_TX, + SHDMA_SLAVE_USB0D1_RX, + SHDMA_SLAVE_USB1D0_TX, + SHDMA_SLAVE_USB1D0_RX, + SHDMA_SLAVE_USB1D1_TX, + SHDMA_SLAVE_USB1D1_RX, SHDMA_SLAVE_SDHI0_TX, SHDMA_SLAVE_SDHI0_RX, SHDMA_SLAVE_SDHI1_TX, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7724.c b/arch/sh/kernel/cpu/sh4a/setup-sh7724.c index 0333fe9e3881..134a397b1918 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7724.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7724.c @@ -93,6 +93,46 @@ static const struct sh_dmae_slave_config sh7724_dmae_slaves[] = { .chcr = DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_8BIT), .mid_rid = 0x36, }, { + .slave_id = SHDMA_SLAVE_USB0D0_TX, + .addr = 0xA4D80100, + .chcr = DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT), + .mid_rid = 0x73, + }, { + .slave_id = SHDMA_SLAVE_USB0D0_RX, + .addr = 0xA4D80100, + .chcr = DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT), + .mid_rid = 0x73, + }, { + .slave_id = SHDMA_SLAVE_USB0D1_TX, + .addr = 0xA4D80120, + .chcr = DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT), + .mid_rid = 0x77, + }, { + .slave_id = SHDMA_SLAVE_USB0D1_RX, + .addr = 0xA4D80120, + .chcr = DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT), + .mid_rid = 0x77, + }, { + .slave_id = SHDMA_SLAVE_USB1D0_TX, + .addr = 0xA4D90100, + .chcr = DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT), + .mid_rid = 0xab, + }, { + .slave_id = SHDMA_SLAVE_USB1D0_RX, + .addr = 0xA4D90100, + .chcr = DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT), + .mid_rid = 0xab, + }, { + .slave_id = SHDMA_SLAVE_USB1D1_TX, + .addr = 0xA4D90120, + .chcr = DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT), + .mid_rid = 0xaf, + }, { + .slave_id = SHDMA_SLAVE_USB1D1_RX, + .addr = 0xA4D90120, + .chcr = DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT), + .mid_rid = 0xaf, + }, { .slave_id = SHDMA_SLAVE_SDHI0_TX, .addr = 0x04ce0030, .chcr = DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_16BIT), diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index b473f0c06fbc..aaf6d59c2012 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -102,8 +102,6 @@ EXPORT_SYMBOL(kernel_thread); void start_thread(struct pt_regs *regs, unsigned long new_pc, unsigned long new_sp) { - set_fs(USER_DS); - regs->pr = 0; regs->sr = SR_FD; regs->pc = new_pc; diff --git a/arch/sh/mm/cache-debugfs.c b/arch/sh/mm/cache-debugfs.c index 52411462c409..115725198038 100644 --- a/arch/sh/mm/cache-debugfs.c +++ b/arch/sh/mm/cache-debugfs.c @@ -26,9 +26,9 @@ static int cache_seq_show(struct seq_file *file, void *iter) { unsigned int cache_type = (unsigned int)file->private; struct cache_info *cache; - unsigned int waysize, way, cache_size; - unsigned long ccr, base; - static unsigned long addrstart = 0; + unsigned int waysize, way; + unsigned long ccr; + unsigned long addrstart = 0; /* * Go uncached immediately so we don't skew the results any @@ -45,28 +45,13 @@ static int cache_seq_show(struct seq_file *file, void *iter) } if (cache_type == CACHE_TYPE_DCACHE) { - base = CACHE_OC_ADDRESS_ARRAY; + addrstart = CACHE_OC_ADDRESS_ARRAY; cache = ¤t_cpu_data.dcache; } else { - base = CACHE_IC_ADDRESS_ARRAY; + addrstart = CACHE_IC_ADDRESS_ARRAY; cache = ¤t_cpu_data.icache; } - /* - * Due to the amount of data written out (depending on the cache size), - * we may be iterated over multiple times. In this case, keep track of - * the entry position in addrstart, and rewind it when we've hit the - * end of the cache. - * - * Likewise, the same code is used for multiple caches, so care must - * be taken for bouncing addrstart back and forth so the appropriate - * cache is hit. - */ - cache_size = cache->ways * cache->sets * cache->linesz; - if (((addrstart & 0xff000000) != base) || - (addrstart & 0x00ffffff) > cache_size) - addrstart = base; - waysize = cache->sets; /* diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c index 2a638f9f09a2..028330044201 100644 --- a/drivers/dma/shdma.c +++ b/drivers/dma/shdma.c @@ -1221,6 +1221,11 @@ static int __init sh_dmae_probe(struct platform_device *pdev) } else { do { for (i = chanirq_res->start; i <= chanirq_res->end; i++) { + if (irq_cnt >= SH_DMAC_MAX_CHANNELS) { + irq_cap = 1; + break; + } + if ((errirq_res->flags & IORESOURCE_BITS) == IORESOURCE_IRQ_SHAREABLE) chan_flag[irq_cnt] = IRQF_SHARED; @@ -1230,15 +1235,11 @@ static int __init sh_dmae_probe(struct platform_device *pdev) "Found IRQ %d for channel %d\n", i, irq_cnt); chan_irq[irq_cnt++] = i; - - if (irq_cnt >= SH_DMAC_MAX_CHANNELS) - break; } - if (irq_cnt >= SH_DMAC_MAX_CHANNELS) { - irq_cap = 1; + if (irq_cnt >= SH_DMAC_MAX_CHANNELS) break; - } + chanirq_res = platform_get_resource(pdev, IORESOURCE_IRQ, ++irqres); } while (irq_cnt < pdata->channel_num && chanirq_res); diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index 5da5bea0f9f0..7721de942c69 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/sh/clk/core.c b/drivers/sh/clk/core.c index 4f64183b27fa..7e9c39951ecb 100644 --- a/drivers/sh/clk/core.c +++ b/drivers/sh/clk/core.c @@ -635,7 +635,7 @@ static void clks_core_resume(void) struct clk *clkp; list_for_each_entry(clkp, &clock_list, node) { - if (likely(clkp->ops)) { + if (likely(clkp->usecount && clkp->ops)) { unsigned long rate = clkp->rate; if (likely(clkp->ops->set_parent)) diff --git a/drivers/staging/iio/accel/adis16201.h b/drivers/staging/iio/accel/adis16201.h index 0b9b85424dfa..4cc1a5bfab40 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 8bb8ce50c248..175e21bb9b40 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/video/aty/atyfb_base.c b/drivers/video/aty/atyfb_base.c index ebb893c49e90..d7aaec5667bf 100644 --- a/drivers/video/aty/atyfb_base.c +++ b/drivers/video/aty/atyfb_base.c @@ -248,10 +248,6 @@ static int atyfb_sync(struct fb_info *info); static int aty_init(struct fb_info *info); -#ifdef CONFIG_ATARI -static int store_video_par(char *videopar, unsigned char m64_num); -#endif - static void aty_get_crtc(const struct atyfb_par *par, struct crtc *crtc); static void aty_set_crtc(const struct atyfb_par *par, const struct crtc *crtc); @@ -2268,11 +2264,13 @@ error: return; } +#ifdef CONFIG_PCI static void aty_bl_exit(struct backlight_device *bd) { backlight_device_unregister(bd); printk("aty: Backlight unloaded\n"); } +#endif /* CONFIG_PCI */ #endif /* CONFIG_FB_ATY_BACKLIGHT */ @@ -2789,7 +2787,7 @@ aty_init_exit: return ret; } -#ifdef CONFIG_ATARI +#if defined(CONFIG_ATARI) && !defined(MODULE) static int __devinit store_video_par(char *video_str, unsigned char m64_num) { char *p; @@ -2818,7 +2816,7 @@ static int __devinit store_video_par(char *video_str, unsigned char m64_num) phys_vmembase[m64_num] = 0; return -1; } -#endif /* CONFIG_ATARI */ +#endif /* CONFIG_ATARI && !MODULE */ /* * Blank the display. diff --git a/drivers/video/efifb.c b/drivers/video/efifb.c index 69c49dfce9cf..784139aed079 100644 --- a/drivers/video/efifb.c +++ b/drivers/video/efifb.c @@ -541,7 +541,7 @@ static int __init efifb_init(void) */ ret = platform_driver_probe(&efifb_driver, efifb_probe); if (ret) { - platform_device_unregister(&efifb_driver); + platform_device_unregister(&efifb_device); return ret; } diff --git a/drivers/video/s3c-fb.c b/drivers/video/s3c-fb.c index 0352afa49a39..4aecf213c9be 100644 --- a/drivers/video/s3c-fb.c +++ b/drivers/video/s3c-fb.c @@ -235,13 +235,12 @@ static int s3c_fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) { struct s3c_fb_win *win = info->par; - struct s3c_fb_pd_win *windata = win->windata; struct s3c_fb *sfb = win->parent; dev_dbg(sfb->dev, "checking parameters\n"); - var->xres_virtual = max((unsigned int)windata->virtual_x, var->xres); - var->yres_virtual = max((unsigned int)windata->virtual_y, var->yres); + var->xres_virtual = max(var->xres_virtual, var->xres); + var->yres_virtual = max(var->yres_virtual, var->yres); if (!s3c_fb_validate_win_bpp(win, var->bits_per_pixel)) { dev_dbg(sfb->dev, "win %d: unsupported bpp %d\n", @@ -558,6 +557,13 @@ static int s3c_fb_set_par(struct fb_info *info) vidosd_set_alpha(win, alpha); vidosd_set_size(win, data); + /* Enable DMA channel for this window */ + if (sfb->variant.has_shadowcon) { + data = readl(sfb->regs + SHADOWCON); + data |= SHADOWCON_CHx_ENABLE(win_no); + writel(data, sfb->regs + SHADOWCON); + } + data = WINCONx_ENWIN; /* note, since we have to round up the bits-per-pixel, we end up @@ -637,13 +643,6 @@ static int s3c_fb_set_par(struct fb_info *info) writel(data, regs + sfb->variant.wincon + (win_no * 4)); writel(0x0, regs + sfb->variant.winmap + (win_no * 4)); - /* Enable DMA channel for this window */ - if (sfb->variant.has_shadowcon) { - data = readl(sfb->regs + SHADOWCON); - data |= SHADOWCON_CHx_ENABLE(win_no); - writel(data, sfb->regs + SHADOWCON); - } - shadow_protect_win(win, 0); return 0; @@ -1487,11 +1486,10 @@ static int __devexit s3c_fb_remove(struct platform_device *pdev) release_mem_region(sfb->regs_res->start, resource_size(sfb->regs_res)); - kfree(sfb); - pm_runtime_put_sync(sfb->dev); pm_runtime_disable(sfb->dev); + kfree(sfb); return 0; } diff --git a/drivers/video/sh_mobile_hdmi.c b/drivers/video/sh_mobile_hdmi.c index 6ae40b630dc9..7d54e2c612f7 100644 --- a/drivers/video/sh_mobile_hdmi.c +++ b/drivers/video/sh_mobile_hdmi.c @@ -1127,23 +1127,16 @@ static void sh_hdmi_edid_work_fn(struct work_struct *work) struct fb_info *info = hdmi->info; unsigned long parent_rate = 0, hdmi_rate; - /* A device has been plugged in */ - pm_runtime_get_sync(hdmi->dev); - ret = sh_hdmi_read_edid(hdmi, &hdmi_rate, &parent_rate); - if (ret < 0) { - pm_runtime_put(hdmi->dev); + if (ret < 0) goto out; - } hdmi->hp_state = HDMI_HOTPLUG_EDID_DONE; /* Reconfigure the clock */ ret = sh_hdmi_clk_configure(hdmi, hdmi_rate, parent_rate); - if (ret < 0) { - pm_runtime_put(hdmi->dev); + if (ret < 0) goto out; - } msleep(10); sh_hdmi_configure(hdmi); @@ -1191,7 +1184,6 @@ static void sh_hdmi_edid_work_fn(struct work_struct *work) fb_set_suspend(hdmi->info, 1); console_unlock(); - pm_runtime_put(hdmi->dev); } out: @@ -1312,7 +1304,7 @@ static int __init sh_hdmi_probe(struct platform_device *pdev) INIT_DELAYED_WORK(&hdmi->edid_work, sh_hdmi_edid_work_fn); pm_runtime_enable(&pdev->dev); - pm_runtime_resume(&pdev->dev); + pm_runtime_get_sync(&pdev->dev); /* Product and revision IDs are 0 in sh-mobile version */ dev_info(&pdev->dev, "Detected HDMI controller 0x%x:0x%x\n", @@ -1340,7 +1332,7 @@ static int __init sh_hdmi_probe(struct platform_device *pdev) ecodec: free_irq(irq, hdmi); ereqirq: - pm_runtime_suspend(&pdev->dev); + pm_runtime_put(&pdev->dev); pm_runtime_disable(&pdev->dev); iounmap(hdmi->base); emap: @@ -1377,7 +1369,7 @@ static int __exit sh_hdmi_remove(struct platform_device *pdev) free_irq(irq, hdmi); /* Wait for already scheduled work */ cancel_delayed_work_sync(&hdmi->edid_work); - pm_runtime_suspend(&pdev->dev); + pm_runtime_put(&pdev->dev); pm_runtime_disable(&pdev->dev); clk_disable(hdmi->hdmi_clk); clk_put(hdmi->hdmi_clk); diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 20c106f24927..1b0b19550015 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -584,11 +584,11 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, success: d_add(dentry, inode); - _leave(" = 0 { vn=%u u=%u } -> { ino=%lu v=%llu }", + _leave(" = 0 { vn=%u u=%u } -> { ino=%lu v=%u }", fid.vnode, fid.unique, dentry->d_inode->i_ino, - (unsigned long long)dentry->d_inode->i_version); + dentry->d_inode->i_generation); return NULL; } @@ -671,10 +671,10 @@ static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd) * been deleted and replaced, and the original vnode ID has * been reused */ if (fid.unique != vnode->fid.unique) { - _debug("%s: file deleted (uq %u -> %u I:%llu)", + _debug("%s: file deleted (uq %u -> %u I:%u)", dentry->d_name.name, fid.unique, vnode->fid.unique, - (unsigned long long)dentry->d_inode->i_version); + dentry->d_inode->i_generation); spin_lock(&vnode->lock); set_bit(AFS_VNODE_DELETED, &vnode->flags); spin_unlock(&vnode->lock); diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 4bd0218473a9..346e3289abd7 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -89,7 +89,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp, i_size_write(&vnode->vfs_inode, size); vnode->vfs_inode.i_uid = status->owner; vnode->vfs_inode.i_gid = status->group; - vnode->vfs_inode.i_version = vnode->fid.unique; + vnode->vfs_inode.i_generation = vnode->fid.unique; vnode->vfs_inode.i_nlink = status->nlink; mode = vnode->vfs_inode.i_mode; @@ -102,6 +102,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp, vnode->vfs_inode.i_ctime.tv_sec = status->mtime_server; vnode->vfs_inode.i_mtime = vnode->vfs_inode.i_ctime; vnode->vfs_inode.i_atime = vnode->vfs_inode.i_ctime; + vnode->vfs_inode.i_version = data_version; } expected_version = status->data_version; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index db66c5201474..0fdab6e03d87 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -75,7 +75,8 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key) inode->i_ctime.tv_nsec = 0; inode->i_atime = inode->i_mtime = inode->i_ctime; inode->i_blocks = 0; - inode->i_version = vnode->fid.unique; + inode->i_generation = vnode->fid.unique; + inode->i_version = vnode->status.data_version; inode->i_mapping->a_ops = &afs_fs_aops; /* check to see whether a symbolic link is really a mountpoint */ @@ -100,7 +101,7 @@ static int afs_iget5_test(struct inode *inode, void *opaque) struct afs_iget_data *data = opaque; return inode->i_ino == data->fid.vnode && - inode->i_version == data->fid.unique; + inode->i_generation == data->fid.unique; } /* @@ -122,7 +123,7 @@ static int afs_iget5_set(struct inode *inode, void *opaque) struct afs_vnode *vnode = AFS_FS_I(inode); inode->i_ino = data->fid.vnode; - inode->i_version = data->fid.unique; + inode->i_generation = data->fid.unique; vnode->fid = data->fid; vnode->volume = data->volume; @@ -380,8 +381,7 @@ int afs_getattr(struct vfsmount *mnt, struct dentry *dentry, inode = dentry->d_inode; - _enter("{ ino=%lu v=%llu }", inode->i_ino, - (unsigned long long)inode->i_version); + _enter("{ ino=%lu v=%u }", inode->i_ino, inode->i_generation); generic_fillattr(inode, stat); return 0; diff --git a/fs/afs/super.c b/fs/afs/super.c index fb240e8766d6..356dcf0929e8 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -31,8 +31,8 @@ static void afs_i_init_once(void *foo); static struct dentry *afs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data); +static void afs_kill_super(struct super_block *sb); static struct inode *afs_alloc_inode(struct super_block *sb); -static void afs_put_super(struct super_block *sb); static void afs_destroy_inode(struct inode *inode); static int afs_statfs(struct dentry *dentry, struct kstatfs *buf); @@ -40,7 +40,7 @@ struct file_system_type afs_fs_type = { .owner = THIS_MODULE, .name = "afs", .mount = afs_mount, - .kill_sb = kill_anon_super, + .kill_sb = afs_kill_super, .fs_flags = 0, }; @@ -50,7 +50,6 @@ static const struct super_operations afs_super_ops = { .drop_inode = afs_drop_inode, .destroy_inode = afs_destroy_inode, .evict_inode = afs_evict_inode, - .put_super = afs_put_super, .show_options = generic_show_options, }; @@ -282,19 +281,25 @@ static int afs_parse_device_name(struct afs_mount_params *params, */ static int afs_test_super(struct super_block *sb, void *data) { - struct afs_mount_params *params = data; + struct afs_super_info *as1 = data; struct afs_super_info *as = sb->s_fs_info; - return as->volume == params->volume; + return as->volume == as1->volume; +} + +static int afs_set_super(struct super_block *sb, void *data) +{ + sb->s_fs_info = data; + return set_anon_super(sb, NULL); } /* * fill in the superblock */ -static int afs_fill_super(struct super_block *sb, void *data) +static int afs_fill_super(struct super_block *sb, + struct afs_mount_params *params) { - struct afs_mount_params *params = data; - struct afs_super_info *as = NULL; + struct afs_super_info *as = sb->s_fs_info; struct afs_fid fid; struct dentry *root = NULL; struct inode *inode = NULL; @@ -302,23 +307,13 @@ static int afs_fill_super(struct super_block *sb, void *data) _enter(""); - /* allocate a superblock info record */ - as = kzalloc(sizeof(struct afs_super_info), GFP_KERNEL); - if (!as) { - _leave(" = -ENOMEM"); - return -ENOMEM; - } - - afs_get_volume(params->volume); - as->volume = params->volume; - /* fill in the superblock */ sb->s_blocksize = PAGE_CACHE_SIZE; sb->s_blocksize_bits = PAGE_CACHE_SHIFT; sb->s_magic = AFS_FS_MAGIC; sb->s_op = &afs_super_ops; - sb->s_fs_info = as; sb->s_bdi = &as->volume->bdi; + strlcpy(sb->s_id, as->volume->vlocation->vldb.name, sizeof(sb->s_id)); /* allocate the root inode and dentry */ fid.vid = as->volume->vid; @@ -326,7 +321,7 @@ static int afs_fill_super(struct super_block *sb, void *data) fid.unique = 1; inode = afs_iget(sb, params->key, &fid, NULL, NULL); if (IS_ERR(inode)) - goto error_inode; + return PTR_ERR(inode); if (params->autocell) set_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(inode)->flags); @@ -342,16 +337,8 @@ static int afs_fill_super(struct super_block *sb, void *data) _leave(" = 0"); return 0; -error_inode: - ret = PTR_ERR(inode); - inode = NULL; error: iput(inode); - afs_put_volume(as->volume); - kfree(as); - - sb->s_fs_info = NULL; - _leave(" = %d", ret); return ret; } @@ -367,6 +354,7 @@ static struct dentry *afs_mount(struct file_system_type *fs_type, struct afs_volume *vol; struct key *key; char *new_opts = kstrdup(options, GFP_KERNEL); + struct afs_super_info *as; int ret; _enter(",,%s,%p", dev_name, options); @@ -399,12 +387,22 @@ static struct dentry *afs_mount(struct file_system_type *fs_type, ret = PTR_ERR(vol); goto error; } - params.volume = vol; + + /* allocate a superblock info record */ + as = kzalloc(sizeof(struct afs_super_info), GFP_KERNEL); + if (!as) { + ret = -ENOMEM; + afs_put_volume(vol); + goto error; + } + as->volume = vol; /* allocate a deviceless superblock */ - sb = sget(fs_type, afs_test_super, set_anon_super, ¶ms); + sb = sget(fs_type, afs_test_super, afs_set_super, as); if (IS_ERR(sb)) { ret = PTR_ERR(sb); + afs_put_volume(vol); + kfree(as); goto error; } @@ -422,16 +420,16 @@ static struct dentry *afs_mount(struct file_system_type *fs_type, } else { _debug("reuse"); ASSERTCMP(sb->s_flags, &, MS_ACTIVE); + afs_put_volume(vol); + kfree(as); } - afs_put_volume(params.volume); afs_put_cell(params.cell); kfree(new_opts); _leave(" = 0 [%p]", sb); return dget(sb->s_root); error: - afs_put_volume(params.volume); afs_put_cell(params.cell); key_put(params.key); kfree(new_opts); @@ -439,18 +437,12 @@ error: return ERR_PTR(ret); } -/* - * finish the unmounting process on the superblock - */ -static void afs_put_super(struct super_block *sb) +static void afs_kill_super(struct super_block *sb) { struct afs_super_info *as = sb->s_fs_info; - - _enter(""); - + kill_anon_super(sb); afs_put_volume(as->volume); - - _leave(""); + kfree(as); } /* diff --git a/fs/afs/write.c b/fs/afs/write.c index 789b3afb3423..b806285ff853 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -84,23 +84,21 @@ void afs_put_writeback(struct afs_writeback *wb) * partly or wholly fill a page that's under preparation for writing */ static int afs_fill_page(struct afs_vnode *vnode, struct key *key, - loff_t pos, unsigned len, struct page *page) + loff_t pos, struct page *page) { loff_t i_size; - unsigned eof; int ret; + int len; - _enter(",,%llu,%u", (unsigned long long)pos, len); - - ASSERTCMP(len, <=, PAGE_CACHE_SIZE); + _enter(",,%llu", (unsigned long long)pos); i_size = i_size_read(&vnode->vfs_inode); - if (pos + len > i_size) - eof = i_size; + if (pos + PAGE_CACHE_SIZE > i_size) + len = i_size - pos; else - eof = PAGE_CACHE_SIZE; + len = PAGE_CACHE_SIZE; - ret = afs_vnode_fetch_data(vnode, key, 0, eof, page); + ret = afs_vnode_fetch_data(vnode, key, pos, len, page); if (ret < 0) { if (ret == -ENOENT) { _debug("got NOENT from server" @@ -153,9 +151,8 @@ int afs_write_begin(struct file *file, struct address_space *mapping, *pagep = page; /* page won't leak in error case: it eventually gets cleaned off LRU */ - if (!PageUptodate(page)) { - _debug("not up to date"); - ret = afs_fill_page(vnode, key, pos, len, page); + if (!PageUptodate(page) && len != PAGE_CACHE_SIZE) { + ret = afs_fill_page(vnode, key, index << PAGE_CACHE_SHIFT, page); if (ret < 0) { kfree(candidate); _leave(" = %d [prep]", ret); diff --git a/fs/buffer.c b/fs/buffer.c index 49c9aada0374..1a80b048ade8 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1902,10 +1902,8 @@ int __block_write_begin(struct page *page, loff_t pos, unsigned len, if (!buffer_uptodate(*wait_bh)) err = -EIO; } - if (unlikely(err)) { + if (unlikely(err)) page_zero_new_buffers(page, from, to); - ClearPageUptodate(page); - } return err; } EXPORT_SYMBOL(__block_write_begin); diff --git a/fs/exec.c b/fs/exec.c index b54f74f3cd80..97e0d52d72fd 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -277,7 +277,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm) * use STACK_TOP because that can depend on attributes which aren't * configured yet. */ - BUILD_BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP); + BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP); vma->vm_end = STACK_TOP_MAX; vma->vm_start = vma->vm_end - PAGE_SIZE; vma->vm_flags = VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP; diff --git a/fs/namei.c b/fs/namei.c index 9802345df5e7..9e425e7e6c8f 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -812,6 +812,11 @@ static int follow_automount(struct path *path, unsigned flags, if (!mnt) /* mount collision */ return 0; + if (!*need_mntput) { + /* lock_mount() may release path->mnt on error */ + mntget(path->mnt); + *need_mntput = true; + } err = finish_automount(mnt, path); switch (err) { @@ -819,12 +824,9 @@ static int follow_automount(struct path *path, unsigned flags, /* Someone else made a mount here whilst we were busy */ return 0; case 0: - dput(path->dentry); - if (*need_mntput) - mntput(path->mnt); + path_put(path); path->mnt = mnt; path->dentry = dget(mnt->mnt_root); - *need_mntput = true; return 0; default: return err; @@ -844,9 +846,10 @@ static int follow_automount(struct path *path, unsigned flags, */ static int follow_managed(struct path *path, unsigned flags) { + struct vfsmount *mnt = path->mnt; /* held by caller, must be left alone */ unsigned managed; bool need_mntput = false; - int ret; + int ret = 0; /* Given that we're not holding a lock here, we retain the value in a * local variable for each dentry as we look at it so that we don't see @@ -861,7 +864,7 @@ static int follow_managed(struct path *path, unsigned flags) BUG_ON(!path->dentry->d_op->d_manage); ret = path->dentry->d_op->d_manage(path->dentry, false); if (ret < 0) - return ret == -EISDIR ? 0 : ret; + break; } /* Transit to a mounted filesystem. */ @@ -887,14 +890,19 @@ static int follow_managed(struct path *path, unsigned flags) if (managed & DCACHE_NEED_AUTOMOUNT) { ret = follow_automount(path, flags, &need_mntput); if (ret < 0) - return ret == -EISDIR ? 0 : ret; + break; continue; } /* We didn't change the current path point */ break; } - return 0; + + if (need_mntput && path->mnt == mnt) + mntput(path->mnt); + if (ret == -EISDIR) + ret = 0; + return ret; } int follow_down_one(struct path *path) @@ -2713,8 +2721,10 @@ static long do_unlinkat(int dfd, const char __user *pathname) error = PTR_ERR(dentry); if (!IS_ERR(dentry)) { /* Why not before? Because we want correct error value */ + if (nd.last.name[nd.last.len]) + goto slashes; inode = dentry->d_inode; - if (nd.last.name[nd.last.len] || !inode) + if (!inode) goto slashes; ihold(inode); error = mnt_want_write(nd.path.mnt); diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index 781dec5bd682..be177f702acb 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -38,18 +38,21 @@ static struct dentry *proc_ns_instantiate(struct inode *dir, struct inode *inode; struct proc_inode *ei; struct dentry *error = ERR_PTR(-ENOENT); + void *ns; inode = proc_pid_make_inode(dir->i_sb, task); if (!inode) goto out; + ns = ns_ops->get(task); + if (!ns) + goto out_iput; + ei = PROC_I(inode); inode->i_mode = S_IFREG|S_IRUSR; inode->i_fop = &ns_file_operations; ei->ns_ops = ns_ops; - ei->ns = ns_ops->get(task); - if (!ei->ns) - goto out_iput; + ei->ns = ns; dentry->d_op = &pid_dentry_operations; d_add(dentry, inode); diff --git a/fs/proc/root.c b/fs/proc/root.c index a9000e9cfee5..d6c3b416529b 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -28,11 +28,12 @@ static int proc_test_super(struct super_block *sb, void *data) static int proc_set_super(struct super_block *sb, void *data) { - struct pid_namespace *ns; - - ns = (struct pid_namespace *)data; - sb->s_fs_info = get_pid_ns(ns); - return set_anon_super(sb, NULL); + int err = set_anon_super(sb, NULL); + if (!err) { + struct pid_namespace *ns = (struct pid_namespace *)data; + sb->s_fs_info = get_pid_ns(ns); + } + return err; } static struct dentry *proc_mount(struct file_system_type *fs_type, diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 266895783b47..e34f0d99ea4e 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -95,6 +95,14 @@ static int sysfs_set_super(struct super_block *sb, void *data) return error; } +static void free_sysfs_super_info(struct sysfs_super_info *info) +{ + int type; + for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++) + kobj_ns_drop(type, info->ns[type]); + kfree(info); +} + static struct dentry *sysfs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { @@ -108,11 +116,11 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, return ERR_PTR(-ENOMEM); for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++) - info->ns[type] = kobj_ns_current(type); + info->ns[type] = kobj_ns_grab_current(type); sb = sget(fs_type, sysfs_test_super, sysfs_set_super, info); if (IS_ERR(sb) || sb->s_fs_info != info) - kfree(info); + free_sysfs_super_info(info); if (IS_ERR(sb)) return ERR_CAST(sb); if (!sb->s_root) { @@ -131,12 +139,11 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, static void sysfs_kill_sb(struct super_block *sb) { struct sysfs_super_info *info = sysfs_info(sb); - /* Remove the superblock from fs_supers/s_instances * so we can't find it, before freeing sysfs_super_info. */ kill_anon_super(sb); - kfree(info); + free_sysfs_super_info(info); } static struct file_system_type sysfs_fs_type = { @@ -145,28 +152,6 @@ static struct file_system_type sysfs_fs_type = { .kill_sb = sysfs_kill_sb, }; -void sysfs_exit_ns(enum kobj_ns_type type, const void *ns) -{ - struct super_block *sb; - - mutex_lock(&sysfs_mutex); - spin_lock(&sb_lock); - list_for_each_entry(sb, &sysfs_fs_type.fs_supers, s_instances) { - struct sysfs_super_info *info = sysfs_info(sb); - /* - * If we see a superblock on the fs_supers/s_instances - * list the unmount has not completed and sb->s_fs_info - * points to a valid struct sysfs_super_info. - */ - /* Ignore superblocks with the wrong ns */ - if (info->ns[type] != ns) - continue; - info->ns[type] = NULL; - } - spin_unlock(&sb_lock); - mutex_unlock(&sysfs_mutex); -} - int __init sysfs_init(void) { int err = -ENOMEM; diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h index 3d28af31d863..2ed2404f3113 100644 --- a/fs/sysfs/sysfs.h +++ b/fs/sysfs/sysfs.h @@ -136,7 +136,7 @@ struct sysfs_addrm_cxt { * instance). */ struct sysfs_super_info { - const void *ns[KOBJ_NS_TYPES]; + void *ns[KOBJ_NS_TYPES]; }; #define sysfs_info(SB) ((struct sysfs_super_info *)(SB->s_fs_info)) extern struct sysfs_dirent sysfs_root; diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index b5aeb5a8ebed..8c892c2d5300 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1848,7 +1848,6 @@ static void ubifs_put_super(struct super_block *sb) bdi_destroy(&c->bdi); ubi_close_volume(c->ubi); mutex_unlock(&c->umount_mutex); - kfree(c); } static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data) @@ -1971,61 +1970,65 @@ static struct ubi_volume_desc *open_ubi(const char *name, int mode) return ERR_PTR(-EINVAL); } -static int ubifs_fill_super(struct super_block *sb, void *data, int silent) +static struct ubifs_info *alloc_ubifs_info(struct ubi_volume_desc *ubi) { - struct ubi_volume_desc *ubi = sb->s_fs_info; struct ubifs_info *c; - struct inode *root; - int err; c = kzalloc(sizeof(struct ubifs_info), GFP_KERNEL); - if (!c) - return -ENOMEM; + if (c) { + spin_lock_init(&c->cnt_lock); + spin_lock_init(&c->cs_lock); + spin_lock_init(&c->buds_lock); + spin_lock_init(&c->space_lock); + spin_lock_init(&c->orphan_lock); + init_rwsem(&c->commit_sem); + mutex_init(&c->lp_mutex); + mutex_init(&c->tnc_mutex); + mutex_init(&c->log_mutex); + mutex_init(&c->mst_mutex); + mutex_init(&c->umount_mutex); + mutex_init(&c->bu_mutex); + mutex_init(&c->write_reserve_mutex); + init_waitqueue_head(&c->cmt_wq); + c->buds = RB_ROOT; + c->old_idx = RB_ROOT; + c->size_tree = RB_ROOT; + c->orph_tree = RB_ROOT; + INIT_LIST_HEAD(&c->infos_list); + INIT_LIST_HEAD(&c->idx_gc); + INIT_LIST_HEAD(&c->replay_list); + INIT_LIST_HEAD(&c->replay_buds); + INIT_LIST_HEAD(&c->uncat_list); + INIT_LIST_HEAD(&c->empty_list); + INIT_LIST_HEAD(&c->freeable_list); + INIT_LIST_HEAD(&c->frdi_idx_list); + INIT_LIST_HEAD(&c->unclean_leb_list); + INIT_LIST_HEAD(&c->old_buds); + INIT_LIST_HEAD(&c->orph_list); + INIT_LIST_HEAD(&c->orph_new); + c->no_chk_data_crc = 1; + + c->highest_inum = UBIFS_FIRST_INO; + c->lhead_lnum = c->ltail_lnum = UBIFS_LOG_LNUM; + + ubi_get_volume_info(ubi, &c->vi); + ubi_get_device_info(c->vi.ubi_num, &c->di); + } + return c; +} - spin_lock_init(&c->cnt_lock); - spin_lock_init(&c->cs_lock); - spin_lock_init(&c->buds_lock); - spin_lock_init(&c->space_lock); - spin_lock_init(&c->orphan_lock); - init_rwsem(&c->commit_sem); - mutex_init(&c->lp_mutex); - mutex_init(&c->tnc_mutex); - mutex_init(&c->log_mutex); - mutex_init(&c->mst_mutex); - mutex_init(&c->umount_mutex); - mutex_init(&c->bu_mutex); - mutex_init(&c->write_reserve_mutex); - init_waitqueue_head(&c->cmt_wq); - c->buds = RB_ROOT; - c->old_idx = RB_ROOT; - c->size_tree = RB_ROOT; - c->orph_tree = RB_ROOT; - INIT_LIST_HEAD(&c->infos_list); - INIT_LIST_HEAD(&c->idx_gc); - INIT_LIST_HEAD(&c->replay_list); - INIT_LIST_HEAD(&c->replay_buds); - INIT_LIST_HEAD(&c->uncat_list); - INIT_LIST_HEAD(&c->empty_list); - INIT_LIST_HEAD(&c->freeable_list); - INIT_LIST_HEAD(&c->frdi_idx_list); - INIT_LIST_HEAD(&c->unclean_leb_list); - INIT_LIST_HEAD(&c->old_buds); - INIT_LIST_HEAD(&c->orph_list); - INIT_LIST_HEAD(&c->orph_new); - c->no_chk_data_crc = 1; +static int ubifs_fill_super(struct super_block *sb, void *data, int silent) +{ + struct ubifs_info *c = sb->s_fs_info; + struct inode *root; + int err; c->vfs_sb = sb; - c->highest_inum = UBIFS_FIRST_INO; - c->lhead_lnum = c->ltail_lnum = UBIFS_LOG_LNUM; - - ubi_get_volume_info(ubi, &c->vi); - ubi_get_device_info(c->vi.ubi_num, &c->di); - /* Re-open the UBI device in read-write mode */ c->ubi = ubi_open_volume(c->vi.ubi_num, c->vi.vol_id, UBI_READWRITE); if (IS_ERR(c->ubi)) { err = PTR_ERR(c->ubi); - goto out_free; + goto out; } /* @@ -2091,24 +2094,29 @@ out_bdi: bdi_destroy(&c->bdi); out_close: ubi_close_volume(c->ubi); -out_free: - kfree(c); +out: return err; } static int sb_test(struct super_block *sb, void *data) { - dev_t *dev = data; + struct ubifs_info *c1 = data; struct ubifs_info *c = sb->s_fs_info; - return c->vi.cdev == *dev; + return c->vi.cdev == c1->vi.cdev; +} + +static int sb_set(struct super_block *sb, void *data) +{ + sb->s_fs_info = data; + return set_anon_super(sb, NULL); } static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, const char *name, void *data) { struct ubi_volume_desc *ubi; - struct ubi_volume_info vi; + struct ubifs_info *c; struct super_block *sb; int err; @@ -2125,19 +2133,24 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, name, (int)PTR_ERR(ubi)); return ERR_CAST(ubi); } - ubi_get_volume_info(ubi, &vi); - dbg_gen("opened ubi%d_%d", vi.ubi_num, vi.vol_id); + c = alloc_ubifs_info(ubi); + if (!c) { + err = -ENOMEM; + goto out_close; + } + + dbg_gen("opened ubi%d_%d", c->vi.ubi_num, c->vi.vol_id); - sb = sget(fs_type, &sb_test, &set_anon_super, &vi.cdev); + sb = sget(fs_type, sb_test, sb_set, c); if (IS_ERR(sb)) { err = PTR_ERR(sb); - goto out_close; + kfree(c); } if (sb->s_root) { struct ubifs_info *c1 = sb->s_fs_info; - + kfree(c); /* A new mount point for already mounted UBIFS */ dbg_gen("this ubi volume is already mounted"); if (!!(flags & MS_RDONLY) != c1->ro_mount) { @@ -2146,11 +2159,6 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, } } else { sb->s_flags = flags; - /* - * Pass 'ubi' to 'fill_super()' in sb->s_fs_info where it is - * replaced by 'c'. - */ - sb->s_fs_info = ubi; err = ubifs_fill_super(sb, data, flags & MS_SILENT ? 1 : 0); if (err) goto out_deact; @@ -2170,11 +2178,18 @@ out_close: return ERR_PTR(err); } +static void kill_ubifs_super(struct super_block *s) +{ + struct ubifs_info *c = s->s_fs_info; + kill_anon_super(s); + kfree(c); +} + static struct file_system_type ubifs_fs_type = { .name = "ubifs", .owner = THIS_MODULE, .mount = ubifs_mount, - .kill_sb = kill_anon_super, + .kill_sb = kill_ubifs_super, }; /* diff --git a/include/linux/kobject_ns.h b/include/linux/kobject_ns.h index 82cb5bf461fb..f66b065a8b5f 100644 --- a/include/linux/kobject_ns.h +++ b/include/linux/kobject_ns.h @@ -32,15 +32,17 @@ enum kobj_ns_type { /* * Callbacks so sysfs can determine namespaces - * @current_ns: return calling task's namespace + * @grab_current_ns: return a new reference to calling task's namespace * @netlink_ns: return namespace to which a sock belongs (right?) * @initial_ns: return the initial namespace (i.e. init_net_ns) + * @drop_ns: drops a reference to namespace */ struct kobj_ns_type_operations { enum kobj_ns_type type; - const void *(*current_ns)(void); + void *(*grab_current_ns)(void); const void *(*netlink_ns)(struct sock *sk); const void *(*initial_ns)(void); + void (*drop_ns)(void *); }; int kobj_ns_type_register(const struct kobj_ns_type_operations *ops); @@ -48,9 +50,9 @@ int kobj_ns_type_registered(enum kobj_ns_type type); const struct kobj_ns_type_operations *kobj_child_ns_ops(struct kobject *parent); const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj); -const void *kobj_ns_current(enum kobj_ns_type type); +void *kobj_ns_grab_current(enum kobj_ns_type type); const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk); const void *kobj_ns_initial(enum kobj_ns_type type); -void kobj_ns_exit(enum kobj_ns_type type, const void *ns); +void kobj_ns_drop(enum kobj_ns_type type, void *ns); #endif /* _LINUX_KOBJECT_NS_H */ diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index c3acda60eee0..e2696d76a599 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -177,9 +177,6 @@ struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd, struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd); void sysfs_put(struct sysfs_dirent *sd); -/* Called to clear a ns tag when it is no longer valid */ -void sysfs_exit_ns(enum kobj_ns_type type, const void *tag); - int __must_check sysfs_init(void); #else /* CONFIG_SYSFS */ @@ -338,10 +335,6 @@ static inline void sysfs_put(struct sysfs_dirent *sd) { } -static inline void sysfs_exit_ns(int type, const void *tag) -{ -} - static inline int __must_check sysfs_init(void) { return 0; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 2bf9ed9ef26b..aef430d779bd 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -35,8 +35,11 @@ struct netns_ipvs; #define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS) struct net { + atomic_t passive; /* To decided when the network + * namespace should be freed. + */ atomic_t count; /* To decided when the network - * namespace should be freed. + * namespace should be shut down. */ #ifdef NETNS_REFCNT_DEBUG atomic_t use_count; /* To track references we @@ -154,6 +157,9 @@ int net_eq(const struct net *net1, const struct net *net2) { return net1 == net2; } + +extern void net_drop_ns(void *); + #else static inline struct net *get_net(struct net *net) @@ -175,6 +181,8 @@ int net_eq(const struct net *net1, const struct net *net2) { return 1; } + +#define net_drop_ns NULL #endif diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 88725c939e0b..10d018212bab 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/lib/kobject.c b/lib/kobject.c index 82dc34c095c2..640bd98a4c8a 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -948,14 +948,14 @@ const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj) } -const void *kobj_ns_current(enum kobj_ns_type type) +void *kobj_ns_grab_current(enum kobj_ns_type type) { - const void *ns = NULL; + void *ns = NULL; spin_lock(&kobj_ns_type_lock); if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) && kobj_ns_ops_tbl[type]) - ns = kobj_ns_ops_tbl[type]->current_ns(); + ns = kobj_ns_ops_tbl[type]->grab_current_ns(); spin_unlock(&kobj_ns_type_lock); return ns; @@ -987,23 +987,15 @@ const void *kobj_ns_initial(enum kobj_ns_type type) return ns; } -/* - * kobj_ns_exit - invalidate a namespace tag - * - * @type: the namespace type (i.e. KOBJ_NS_TYPE_NET) - * @ns: the actual namespace being invalidated - * - * This is called when a tag is no longer valid. For instance, - * when a network namespace exits, it uses this helper to - * make sure no sb's sysfs_info points to the now-invalidated - * netns. - */ -void kobj_ns_exit(enum kobj_ns_type type, const void *ns) +void kobj_ns_drop(enum kobj_ns_type type, void *ns) { - sysfs_exit_ns(type, ns); + spin_lock(&kobj_ns_type_lock); + if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) && + kobj_ns_ops_tbl[type] && kobj_ns_ops_tbl[type]->drop_ns) + kobj_ns_ops_tbl[type]->drop_ns(ns); + spin_unlock(&kobj_ns_type_lock); } - EXPORT_SYMBOL(kobject_get); EXPORT_SYMBOL(kobject_put); EXPORT_SYMBOL(kobject_del); diff --git a/mm/migrate.c b/mm/migrate.c index e4a5c912983d..666e4e677414 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -288,7 +288,7 @@ static int migrate_page_move_mapping(struct address_space *mapping, */ __dec_zone_page_state(page, NR_FILE_PAGES); __inc_zone_page_state(newpage, NR_FILE_PAGES); - if (PageSwapBacked(page)) { + if (!PageSwapCache(page) && PageSwapBacked(page)) { __dec_zone_page_state(page, NR_SHMEM); __inc_zone_page_state(newpage, NR_SHMEM); } diff --git a/mm/mmap.c b/mm/mmap.c index bbdc9af5e117..d49736ff8a8d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -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/net/core/net-sysfs.c b/net/core/net-sysfs.c index 11b98bc2aa8f..33d2a1fba131 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1179,9 +1179,14 @@ static void remove_queue_kobjects(struct net_device *net) #endif } -static const void *net_current_ns(void) +static void *net_grab_current_ns(void) { - return current->nsproxy->net_ns; + struct net *ns = current->nsproxy->net_ns; +#ifdef CONFIG_NET_NS + if (ns) + atomic_inc(&ns->passive); +#endif + return ns; } static const void *net_initial_ns(void) @@ -1196,22 +1201,13 @@ static const void *net_netlink_ns(struct sock *sk) struct kobj_ns_type_operations net_ns_type_operations = { .type = KOBJ_NS_TYPE_NET, - .current_ns = net_current_ns, + .grab_current_ns = net_grab_current_ns, .netlink_ns = net_netlink_ns, .initial_ns = net_initial_ns, + .drop_ns = net_drop_ns, }; EXPORT_SYMBOL_GPL(net_ns_type_operations); -static void net_kobj_ns_exit(struct net *net) -{ - kobj_ns_exit(KOBJ_NS_TYPE_NET, net); -} - -static struct pernet_operations kobj_net_ops = { - .exit = net_kobj_ns_exit, -}; - - #ifdef CONFIG_HOTPLUG static int netdev_uevent(struct device *d, struct kobj_uevent_env *env) { @@ -1339,6 +1335,5 @@ EXPORT_SYMBOL(netdev_class_remove_file); int netdev_kobject_init(void) { kobj_ns_type_register(&net_ns_type_operations); - register_pernet_subsys(&kobj_net_ops); return class_register(&net_class); } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index e41e5110c65c..ea489db1bc23 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -128,6 +128,7 @@ static __net_init int setup_net(struct net *net) LIST_HEAD(net_exit_list); atomic_set(&net->count, 1); + atomic_set(&net->passive, 1); #ifdef NETNS_REFCNT_DEBUG atomic_set(&net->use_count, 0); @@ -210,6 +211,13 @@ static void net_free(struct net *net) kmem_cache_free(net_cachep, net); } +void net_drop_ns(void *p) +{ + struct net *ns = p; + if (ns && atomic_dec_and_test(&ns->passive)) + net_free(ns); +} + struct net *copy_net_ns(unsigned long flags, struct net *old_net) { struct net *net; @@ -230,7 +238,7 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net) } mutex_unlock(&net_mutex); if (rv < 0) { - net_free(net); + net_drop_ns(net); return ERR_PTR(rv); } return net; @@ -286,7 +294,7 @@ static void cleanup_net(struct work_struct *work) /* Finally it is safe to free my network namespace structure */ list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { list_del_init(&net->exit_list); - net_free(net); + net_drop_ns(net); } } static DECLARE_WORK(net_cleanup_work, cleanup_net); diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 77d44138864f..35459340019e 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -29,6 +29,7 @@ #include <linux/audit.h> #include <linux/uaccess.h> #include <linux/kobject.h> +#include <linux/ctype.h> /* selinuxfs pseudo filesystem for exporting the security policy API. Based on the proc code and the fs/nfsd/nfsctl.c code. */ @@ -751,6 +752,14 @@ out: return length; } +static inline int hexcode_to_int(int code) { + if (code == '\0' || !isxdigit(code)) + return -1; + if (isdigit(code)) + return code - '0'; + return tolower(code) - 'a' + 10; +} + static ssize_t sel_write_create(struct file *file, char *buf, size_t size) { char *scon = NULL, *tcon = NULL; @@ -785,8 +794,34 @@ static ssize_t sel_write_create(struct file *file, char *buf, size_t size) nargs = sscanf(buf, "%s %s %hu %s", scon, tcon, &tclass, namebuf); if (nargs < 3 || nargs > 4) goto out; - if (nargs == 4) + if (nargs == 4) { + /* + * If and when the name of new object to be queried contains + * either whitespace or multibyte characters, they shall be + * encoded based on the percentage-encoding rule. + * If not encoded, the sscanf logic picks up only left-half + * of the supplied name; splitted by a whitespace unexpectedly. + */ + char *r, *w; + int c1, c2; + + r = w = namebuf; + do { + c1 = *r++; + if (c1 == '+') + c1 = ' '; + else if (c1 == '%') { + if ((c1 = hexcode_to_int(*r++)) < 0) + goto out; + if ((c2 = hexcode_to_int(*r++)) < 0) + goto out; + c1 = (c1 << 4) | c2; + } + *w++ = c1; + } while (c1 != '\0'); + objname = namebuf; + } length = security_context_to_sid(scon, strlen(scon) + 1, &ssid); if (length) diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c index 102e9ec1b77a..d246aca3f4fb 100644 --- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -3222,6 +3222,9 @@ static int filename_trans_write(struct policydb *p, void *fp) __le32 buf[1]; int rc; + if (p->policyvers < POLICYDB_VERSION_FILENAME_TRANS) + return 0; + nel = 0; rc = hashtab_map(p->filename_trans, hashtab_cnt, &nel); if (rc) diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN index 9c5fb4d93824..ad73300f7bac 100755 --- a/tools/perf/util/PERF-VERSION-GEN +++ b/tools/perf/util/PERF-VERSION-GEN @@ -23,7 +23,7 @@ if test -d ../../.git -o -f ../../.git && then VN=$(echo "$VN" | sed -e 's/-/./g'); else - VN=$(make -sC ../.. kernelversion) + VN=$(MAKEFLAGS= make -sC ../.. kernelversion) fi VN=$(expr "$VN" : v*'\(.*\)') |